@@ -2,76 +2,6 @@
22version: 2
33interactions:
44- id: 0
5− request:
6− proto: HTTP/1.1
7− proto_major: 1
8− proto_minor: 1
9− content_length: 33741
10− host: ""
11− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **READ BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default <4 lines), unless explaining complex changes or asked for detail. Conciseness applies to output only, not to thoroughness of work.\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks.\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\". When committing, follow the `<git_commits>` format from the bash tool description exactly, including any configured attribution lines.\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. Focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously.\\n10. **NO URL GUESSING**: Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **TOOL CONSTRAINTS**: Only use documented tools. Never attempt 'apply_patch' or 'apply_diff' - they don't exist. Use 'edit' or 'multiedit' instead.\\n14. **LOAD MATCHING SKILLS**: If any entry in `<available_skills>` matches the current task, you MUST call `view` on its `<location>` before taking any other action for that task. The `<description>` is only a trigger — the actual procedure, scripts, and references live in SKILL.md. Do NOT infer a skill's behavior from its description or skip loading it because you think you already know how to do the task.\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- ALWAYS think and respond in the same spoken language the prompt was written in.\\n- Under 4 lines of text (tool use doesn't count)\\n- Conciseness is about **text only**: always fully implement the requested feature, tests, and wiring even if that requires many tool calls.\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n- Never send acknowledgement-only responses; after receiving new context or instructions, immediately continue the task or state the concrete next action you will take.\\n- Use rich Markdown formatting (headings, bullet lists, tables, code fences) for any multi-sentence or explanatory answer; only use plain unformatted text if the user explicitly asks.\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n</communication_style>\\n\\n<code_references>\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n</code_references>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Cross-check the original prompt and your own mental checklist; if any feasible part remains undone, continue working instead of responding.\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n- When requirements are underspecified but not obviously dangerous, make the most reasonable assumptions based on project patterns and memory files, briefly state them if needed, and proceed instead of waiting for clarification.\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**When requesting information/access**:\\n- Exhaust all available tools, searches, and reasonable assumptions first.\\n- Never say \\\"Need more info\\\" without detail.\\n- In the same message, list each missing item, why it is required, acceptable substitutes, and what you already attempted.\\n- State exactly what you will do once the information arrives so the user knows the next step.\\n\\nWhen you must stop, first finish all unblocked parts of the request, then clearly report: (a) what you tried, (b) exactly why you are blocked, and (c) the minimal external action required. Don't stop just because one path failed—exhaust multiple plausible approaches first.\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\n**Available edit tools:**\\n- `edit` - Single find/replace in a file\\n- `multiedit` - Multiple find/replace operations in one file\\n- `write` - Create/overwrite entire file\\n\\nNever use `apply_patch` or similar - those tools don't exist.\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n</editing_files>\\n\\n<whitespace_and_exact_matching>\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n</whitespace_and_exact_matching>\\n\\n<task_completion>\\nEnsure every task is implemented completely, not partially or sketched.\\n\\n1. **Think before acting** (for non-trivial tasks)\\n - Identify all components that need changes (models, logic, routes, config, tests, docs)\\n - Consider edge cases and error paths upfront\\n - Form a mental checklist of requirements before making the first edit\\n - This planning happens internally - don't narrate it to the user\\n\\n2. **Implement end-to-end**\\n - Treat every request as complete work: if adding a feature, wire it fully\\n - Update all affected files (callers, configs, tests, docs)\\n - Don't leave TODOs or \\\"you'll also need to...\\\" - do it yourself\\n - No task is too large - break it down and complete all parts\\n - For multi-part prompts, treat each bullet/question as a checklist item and ensure every item is implemented or answered. Partial completion is not an acceptable final state.\\n\\n3. **Verify before finishing**\\n - Re-read the original request and verify each requirement is met\\n - Check for missing error handling, edge cases, or unwired code\\n - Run tests to confirm the implementation works\\n - Only say \\\"Done\\\" when truly done - never stop mid-task\\n</task_completion>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause (isolate with debug logs or minimal reproduction if needed)\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n7. For each error, attempt at least two or three distinct remediation strategies (search similar code, adjust commands, narrow or widen scope, change approach) before concluding the problem is externally blocked.\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences\\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n</testing>\\n\\n<tool_usage>\\n- Default to using tools (ls, grep, view, agent, tests, web_fetch, etc.) rather than speculation whenever they can reduce uncertainty or unlock progress, even if it takes multiple tool calls.\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n- Never use `curl` through the bash tool it is not allowed use the fetch tool instead.\\n- Only use the tools you know exist.\\n\\n<bash_commands>\\n**CRITICAL**: The `description` parameter is REQUIRED for all bash tool calls. Always provide it.\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n</bash_commands>\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When the user provides new information or clarification, incorporate it immediately and keep executing instead of stopping with an acknowledgement.\\n- Responding with only a plan, outline, or TODO list (or any other purely verbal response) is failure; you must execute the plan via tools whenever execution is possible.\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<final_answers>\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n- Structure longer answers with Markdown sections and lists, and put all code, commands, and config in fenced code blocks.\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n</final_answers>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/glm-5.1/multiedit_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n</env>\\n\\n\\n\\n<available_skills>\\n <skill>\\n <name>crush-hooks</name>\\n <description>Use when the user wants to add, write, debug, or configure a Crush hook — gating or blocking tool calls, approving or rewriting tool input before execution, injecting context into tool results, or troubleshooting hook behavior in crush.json.</description>\\n <location>crush://skills/crush-hooks/SKILL.md</location>\\n <type>builtin</type>\\n </skill>\\n <skill>\\n <name>jq</name>\\n <description>Use when the user needs to query, filter, reshape, extract, create, or construct JSON data — including API responses, config files, log output, or any structured data — or when helping the user write or debug JSON transformations.</description>\\n <location>crush://skills/jq/SKILL.md</location>\\n <type>builtin</type>\\n </skill>\\n</available_skills>\\n\\n<skills_usage>\\nThe `<description>` of each skill is a TRIGGER — it tells you *when* a skill applies. It is NOT a specification of what the skill does or how to do it. The procedure, scripts, commands, references, and required flags live only in the SKILL.md body. You do not know what a skill actually does until you have read its SKILL.md.\\n\\nMANDATORY activation flow:\\n1. Scan `<available_skills>` against the current user task.\\n2. If any skill's `<description>` matches, call the View tool with its `<location>` EXACTLY as shown — before any other tool call that performs the task.\\n3. Read the entire SKILL.md and follow its instructions.\\n4. Only then execute the task, using the skill's prescribed commands/tools.\\n\\nDo NOT skip step 2 because you think you already know how to do the task. Do NOT infer a skill's behavior from its name or description. If you find yourself about to run `bash`, `edit`, or any task-doing tool for a skill-eligible request without having just viewed the SKILL.md, stop and load the skill first.\\n\\nBuiltin skills (type=builtin) use virtual `crush://skills/...` location identifiers. The \\\"crush://\\\" prefix is NOT a URL, network address, or MCP resource — it is a special internal identifier the View tool understands natively. Pass the `<location>` verbatim to View.\\n\\nDo not use MCP tools (including read_mcp_resource) to load skills.\\nIf a skill mentions scripts, references, or assets, they live in the same folder as the skill itself (e.g., scripts/, references/, assets/ subdirectories within the skill's folder).\\n</skills_usage>\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"<system_reminder>This is a reminder that your todo list is currently empty. DO NOT mention this to the user explicitly because they are already aware.\\nIf you are working on tasks that would benefit from a todo list please use the \\\"todos\\\" tool to create one.\\nIf not, please feel free to ignore. Again do not mention this message to the user.</system_reminder>\",\"role\":\"user\"},{\"content\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"role\":\"user\"}],\"model\":\"glm-5.1\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Execute shell commands; long-running commands automatically move to background and return a shell ID.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Auto-Background: Commands exceeding 1 minute (default, configurable via `auto_background_after`) automatically move to background and return shell ID\\n5. Output Processing: Truncate if exceeds 30000 characters\\n6. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, working_dir optional (defaults to current directory)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Each command runs in independent shell (no state persistence between calls)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<background_execution>\\n- Set run_in_background=true to run commands in a separate background shell\\n- Returns a shell ID for managing the background process\\n- Use job_output tool to view current output from background shell\\n- Use job_kill tool to terminate a background shell\\n- IMPORTANT: NEVER use `&` at the end of commands to run in background - use run_in_background parameter instead\\n- Commands that should run in background:\\n * Long-running servers (e.g., `npm start`, `python -m http.server`, `node server.js`)\\n * Watch/monitoring tasks (e.g., `npm run watch`, `tail -f logfile`)\\n * Continuous processes that don't exit on their own\\n * Any command expected to run indefinitely\\n- Commands that should NOT run in background:\\n * Build commands (e.g., `npm run build`, `go build`)\\n * Test suites (e.g., `npm test`, `pytest`)\\n * Git operations\\n * File operations\\n * Short-lived scripts\\n</background_execution>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"auto_background_after\":{\"description\":\"Seconds to wait before automatically moving the command to a background job (default: 60)\",\"type\":\"integer\"},\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does, try to keep it under 30 characters or so\",\"type\":\"string\"},\"run_in_background\":{\"description\":\"Set to true (boolean) to run this command in the background. Use job_output to read the output later.\",\"type\":\"boolean\"},\"working_dir\":{\"description\":\"The working directory to execute the command in (defaults to current directory)\",\"type\":\"string\"}},\"required\":[\"description\",\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Download a URL directly to a local file (binary-safe, streaming, max 100MB); overwrites without warning. For reading content into context use fetch.\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edit a file by exact find-and-replace; can also create or delete content. For renames/moves use bash. For large edits use write.\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Apply multiple find-and-replace edits to a single file in one operation; edits run sequentially. Prefer over edit for multiple changes to the same file. Same exact-match rules as edit apply.\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"properties\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"required\":[\"old_string\",\"new_string\"],\"type\":\"object\"},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetch raw content from a URL as text, markdown, or html (max 100KB); no AI processing. For analysis or extraction use agentic_fetch.\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Find files by name/pattern (glob syntax), sorted by modification time; max 100 results; skips hidden files. Use grep to search file contents.\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Search file contents by regex or literal text; returns matching file paths sorted by modification time (max 100); respects .gitignore. Use glob to filter by filename, not contents.\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"List files and directories as a tree; skips hidden files and common system dirs; max 1000 files. Use glob to find files by pattern, grep to search contents.\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{\"type\":\"string\"},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public GitHub repositories via Sourcegraph; supports regex, language/repo/file filters, and symbol search (max 20 results). Only searches public repos.\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Read a file by path with line numbers; supports offset and line limit (default 2000, max 200KB returned file content section); renders images (PNG, JPEG, GIF, WebP); use ls for directories.\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Create or overwrite a file with given content; auto-creates parent dirs. Cannot append. Read the file first to avoid conflicts. For surgical changes use edit or multiedit.\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"
12− headers:
13− Accept:
14− - application/json
15− Content-Type:
16− - application/json
17− User-Agent:
18− - Charm-Crush/devel (https://charm.land/crush)
19− url: https://hyper.charm.land/v1/chat/completions
20− method: POST
21− response:
22− proto: HTTP/2.0
23− proto_major: 2
24− proto_minor: 0
25− content_length: -1
26− uncompressed: true
27− body: |+
28− data: {"id":"chatcmpl-d599cbede586f295273bd5fe","object":"chat.completion.chunk","created":1778531382,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
29−
30− data: {"id":"chatcmpl-d599cbede586f295273bd5fe","object":"chat.completion.chunk","created":1778531382,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"Let"},"finish_reason":null}]}
31−
32− data: {"id":"chatcmpl-d599cbede586f295273bd5fe","object":"chat.completion.chunk","created":1778531382,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" me"},"finish_reason":null}]}
33−
34− data: {"id":"chatcmpl-d599cbede586f295273bd5fe","object":"chat.completion.chunk","created":1778531382,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" first"},"finish_reason":null}]}
35−
36− data: {"id":"chatcmpl-d599cbede586f295273bd5fe","object":"chat.completion.chunk","created":1778531382,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" read"},"finish_reason":null}]}
37−
38− data: {"id":"chatcmpl-d599cbede586f295273bd5fe","object":"chat.completion.chunk","created":1778531382,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" the"},"finish_reason":null}]}
39−
40− data: {"id":"chatcmpl-d599cbede586f295273bd5fe","object":"chat.completion.chunk","created":1778531382,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" main"},"finish_reason":null}]}
41−
42− data: {"id":"chatcmpl-d599cbede586f295273bd5fe","object":"chat.completion.chunk","created":1778531382,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":".go"},"finish_reason":null}]}
43−
44− data: {"id":"chatcmpl-d599cbede586f295273bd5fe","object":"chat.completion.chunk","created":1778531382,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" file"},"finish_reason":null}]}
45−
46− data: {"id":"chatcmpl-d599cbede586f295273bd5fe","object":"chat.completion.chunk","created":1778531382,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
47−
48− data: {"id":"chatcmpl-d599cbede586f295273bd5fe","object":"chat.completion.chunk","created":1778531382,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" see"},"finish_reason":null}]}
49−
50− data: {"id":"chatcmpl-d599cbede586f295273bd5fe","object":"chat.completion.chunk","created":1778531382,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" its"},"finish_reason":null}]}
51−
52− data: {"id":"chatcmpl-d599cbede586f295273bd5fe","object":"chat.completion.chunk","created":1778531382,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" current"},"finish_reason":null}]}
53−
54− data: {"id":"chatcmpl-d599cbede586f295273bd5fe","object":"chat.completion.chunk","created":1778531382,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" content"},"finish_reason":null}]}
55−
56− data: {"id":"chatcmpl-d599cbede586f295273bd5fe","object":"chat.completion.chunk","created":1778531382,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
57−
58− data: {"id":"chatcmpl-d599cbede586f295273bd5fe","object":"chat.completion.chunk","created":1778531382,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_4d3da657d04f428c92d43f15","type":"function","index":0,"function":{"name":"view","arguments":""}}]},"finish_reason":null}]}
59−
60− data: {"id":"chatcmpl-d599cbede586f295273bd5fe","object":"chat.completion.chunk","created":1778531382,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\"file_path\":\"/tmp/crush-test/TestCoderAgent/glm-5.1/multiedit_tool/main.go\"}"}}]},"finish_reason":null}]}
61−
62− data: {"id":"chatcmpl-d599cbede586f295273bd5fe","object":"chat.completion.chunk","created":1778531382,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}]}
63−
64− data: {"id":"chatcmpl-d599cbede586f295273bd5fe","object":"chat.completion.chunk","created":1778531382,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":725,"completion_tokens":45,"total_tokens":7810,"prompt_tokens_details":{"cached_tokens":7040},"completion_tokens_details":{"reasoning_tokens":14}}}
65−
66− data: [DONE]
67−
68− headers:
69− Content-Type:
70− - text/event-stream
71− status: 200 OK
72− code: 200
73− duration: 4.027960709s
74−- id: 1
755 request:
766 proto: HTTP/1.1
777 proto_major: 1
@@ -95,857 +25,391 @@ interactions:
9525 content_length: -1
9626 uncompressed: true
9727 body: |+
98− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
99−
100− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"We"},"finish_reason":null}]}
101−
102− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" need"},"finish_reason":null}]}
103−
104− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
105−
106− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" produce"},"finish_reason":null}]}
107−
108− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
109−
110− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" short"},"finish_reason":null}]}
111−
112− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" title"},"finish_reason":null}]}
113−
114− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
115−
116− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" same"},"finish_reason":null}]}
117−
118− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" language"},"finish_reason":null}]}
119−
120− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ("},"finish_reason":null}]}
121−
122− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"English"},"finish_reason":null}]}
123−
124− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")."},"finish_reason":null}]}
125−
126− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Summ"},"finish_reason":null}]}
127−
128− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ar"},"finish_reason":null}]}
129−
130− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ize"},"finish_reason":null}]}
131−
132− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
133−
134− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
135−
136− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"use"},"finish_reason":null}]}
137−
138− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" mult"},"finish_reason":null}]}
139−
140− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ied"},"finish_reason":null}]}
141−
142− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"it"},"finish_reason":null}]}
143−
144− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
145−
146− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" change"},"finish_reason":null}]}
147−
148− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" '"},"finish_reason":null}]}
149−
150− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Hello"},"finish_reason":null}]}
151−
152− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
153−
154− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" World"},"finish_reason":null}]}
155−
156− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"!'"},"finish_reason":null}]}
157−
158− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
159−
160− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" '"},"finish_reason":null}]}
161−
162− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Hello"},"finish_reason":null}]}
163−
164− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
165−
166− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Crush"},"finish_reason":null}]}
167−
168− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"!'"},"finish_reason":null}]}
169−
170− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" and"},"finish_reason":null}]}
171−
172− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" add"},"finish_reason":null}]}
173−
174− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
175−
176− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" comment"},"finish_reason":null}]}
177−
178− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" //"},"finish_reason":null}]}
179−
180− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Greeting"},"finish_reason":null}]}
181−
182− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" above"},"finish_reason":null}]}
183−
184− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" the"},"finish_reason":null}]}
185−
186− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" fmt"},"finish_reason":null}]}
187−
188− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".Println"},"finish_reason":null}]}
189−
190− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" line"},"finish_reason":null}]}
191−
192− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
193−
194− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" main"},"finish_reason":null}]}
195−
196− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".go"},"finish_reason":null}]}
197−
198− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
199−
200− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Title"},"finish_reason":null}]}
201−
202− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" max"},"finish_reason":null}]}
203−
204− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
205−
206− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
207−
208− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" chars"},"finish_reason":null}]}
209−
210− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
211−
212− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" one"},"finish_reason":null}]}
213−
214− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" line"},"finish_reason":null}]}
215−
216− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".\n\n"},"finish_reason":null}]}
217−
218− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Possible"},"finish_reason":null}]}
219−
220− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" title"},"finish_reason":null}]}
221−
222− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
223−
224− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
225−
226− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Mult"},"finish_reason":null}]}
227−
228− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ied"},"finish_reason":null}]}
229−
230− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"it"},"finish_reason":null}]}
231−
232− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
233−
234− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" change"},"finish_reason":null}]}
235−
236− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" greeting"},"finish_reason":null}]}
237−
238− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" and"},"finish_reason":null}]}
239−
240− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" add"},"finish_reason":null}]}
241−
242− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" comment"},"finish_reason":null}]}
243−
244− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
245−
246− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" main"},"finish_reason":null}]}
247−
248− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".go"},"finish_reason":null}]}
249−
250− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
251−
252− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Count"},"finish_reason":null}]}
253−
254− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
255−
256− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
257−
258− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" let's"},"finish_reason":null}]}
259−
260− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" count"},"finish_reason":null}]}
261−
262− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
263−
264− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
265−
266− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Mult"},"finish_reason":null}]}
267−
268− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ied"},"finish_reason":null}]}
269−
270− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"it"},"finish_reason":null}]}
271−
272− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
273−
274− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" change"},"finish_reason":null}]}
275−
276− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" greeting"},"finish_reason":null}]}
277−
278− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" and"},"finish_reason":null}]}
279−
280− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" add"},"finish_reason":null}]}
281−
282− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" comment"},"finish_reason":null}]}
283−
284− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
285−
286− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" main"},"finish_reason":null}]}
287−
288− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".go"},"finish_reason":null}]}
289−
290− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\""},"finish_reason":null}]}
291−
292− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" length"},"finish_reason":null}]}
293−
294− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"?"},"finish_reason":null}]}
295−
296− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Count"},"finish_reason":null}]}
297−
298− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
299−
300− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
301−
302− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" M"},"finish_reason":null}]}
303−
304− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
305−
306− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
307−
308− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
309−
310− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"u"},"finish_reason":null}]}
311−
312− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"2"},"finish_reason":null}]}
313−
314− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"l"},"finish_reason":null}]}
315−
316− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"3"},"finish_reason":null}]}
317−
318− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"t"},"finish_reason":null}]}
319−
320− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"4"},"finish_reason":null}]}
321−
322− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"i"},"finish_reason":null}]}
323−
324− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"5"},"finish_reason":null}]}
325−
326− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"e"},"finish_reason":null}]}
327−
328− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"6"},"finish_reason":null}]}
329−
330− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"d"},"finish_reason":null}]}
331−
332− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"7"},"finish_reason":null}]}
333−
334− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"i"},"finish_reason":null}]}
335−
336− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"8"},"finish_reason":null}]}
337−
338− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"t"},"finish_reason":null}]}
339−
340− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"9"},"finish_reason":null}]}
341−
342− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":("},"finish_reason":null}]}
343−
344− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"10"},"finish_reason":null}]}
345−
346− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
347−
348− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
349−
350− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"11"},"finish_reason":null}]}
351−
352− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" c"},"finish_reason":null}]}
353−
354− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"12"},"finish_reason":null}]}
355−
356− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"h"},"finish_reason":null}]}
357−
358− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"13"},"finish_reason":null}]}
359−
360− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"a"},"finish_reason":null}]}
361−
362− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"14"},"finish_reason":null}]}
363−
364− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"n"},"finish_reason":null}]}
365−
366− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"15"},"finish_reason":null}]}
367−
368− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"g"},"finish_reason":null}]}
369−
370− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"16"},"finish_reason":null}]}
371−
372− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"e"},"finish_reason":null}]}
373−
374− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"17"},"finish_reason":null}]}
375−
376− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
377−
378− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"18"},"finish_reason":null}]}
379−
380− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"g"},"finish_reason":null}]}
381−
382− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"19"},"finish_reason":null}]}
383−
384− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"r"},"finish_reason":null}]}
385−
386− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"20"},"finish_reason":null}]}
387−
388− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"e"},"finish_reason":null}]}
389−
390− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"21"},"finish_reason":null}]}
391−
392− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"e"},"finish_reason":null}]}
393−
394− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"22"},"finish_reason":null}]}
395−
396− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"t"},"finish_reason":null}]}
397−
398− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"23"},"finish_reason":null}]}
28+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
39929
400− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"i"},"finish_reason":null}]}
30+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"The"},"finish_reason":null}]}
40131
402− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"24"},"finish_reason":null}]}
32+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" user"},"finish_reason":null}]}
40333
404− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"n"},"finish_reason":null}]}
34+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" wants"},"finish_reason":null}]}
40535
406− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"25"},"finish_reason":null}]}
36+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
40737
408− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"g"},"finish_reason":null}]}
38+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" concise"},"finish_reason":null}]}
40939
410− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"26"},"finish_reason":null}]}
40+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" title"},"finish_reason":null}]}
41141
412− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
42+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" for"},"finish_reason":null}]}
41343
414− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"27"},"finish_reason":null}]}
44+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" the"},"finish_reason":null}]}
41545
416− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"a"},"finish_reason":null}]}
46+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" content"},"finish_reason":null}]}
41747
418− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"28"},"finish_reason":null}]}
48+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
41949
420− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"n"},"finish_reason":null}]}
50+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Must"},"finish_reason":null}]}
42151
422− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"29"},"finish_reason":null}]}
52+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" be"},"finish_reason":null}]}
42353
424− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"d"},"finish_reason":null}]}
54+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" short"},"finish_reason":null}]}
42555
426− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"30"},"finish_reason":null}]}
56+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \u003c="},"finish_reason":null}]}
42757
428− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
58+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
42959
430− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"31"},"finish_reason":null}]}
60+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" chars"},"finish_reason":null}]}
43161
432− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"a"},"finish_reason":null}]}
62+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
43363
434− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"32"},"finish_reason":null}]}
64+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
43565
436− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"d"},"finish_reason":null}]}
66+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" same"},"finish_reason":null}]}
43767
438− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"33"},"finish_reason":null}]}
68+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" language"},"finish_reason":null}]}
43969
440− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"d"},"finish_reason":null}]}
70+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ("},"finish_reason":null}]}
44171
442− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"34"},"finish_reason":null}]}
72+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"English"},"finish_reason":null}]}
44373
444− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
74+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"),"},"finish_reason":null}]}
44575
446− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"35"},"finish_reason":null}]}
76+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" no"},"finish_reason":null}]}
44777
448− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"c"},"finish_reason":null}]}
78+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" quotes"},"finish_reason":null}]}
44979
450− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"36"},"finish_reason":null}]}
80+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" or"},"finish_reason":null}]}
45181
452− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"o"},"finish_reason":null}]}
82+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" col"},"finish_reason":null}]}
45383
454− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"37"},"finish_reason":null}]}
84+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ons"},"finish_reason":null}]}
45585
456− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"m"},"finish_reason":null}]}
86+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
45787
458− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"38"},"finish_reason":null}]}
88+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Summ"},"finish_reason":null}]}
45989
460− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"m"},"finish_reason":null}]}
90+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ar"},"finish_reason":null}]}
46191
462− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"39"},"finish_reason":null}]}
92+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ize"},"finish_reason":null}]}
46393
464− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"e"},"finish_reason":null}]}
94+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
46595
466− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"40"},"finish_reason":null}]}
96+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
46797
468− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"n"},"finish_reason":null}]}
98+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Use"},"finish_reason":null}]}
46999
470− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"41"},"finish_reason":null}]}
100+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" mult"},"finish_reason":null}]}
471101
472− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"t"},"finish_reason":null}]}
102+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ied"},"finish_reason":null}]}
473103
474− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"42"},"finish_reason":null}]}
104+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"it"},"finish_reason":null}]}
475105
476− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
106+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
477107
478− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"43"},"finish_reason":null}]}
108+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" replace"},"finish_reason":null}]}
479109
480− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"i"},"finish_reason":null}]}
110+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Hello"},"finish_reason":null}]}
481111
482− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"44"},"finish_reason":null}]}
112+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" World"},"finish_reason":null}]}
483113
484− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"n"},"finish_reason":null}]}
114+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" with"},"finish_reason":null}]}
485115
486− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"45"},"finish_reason":null}]}
116+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Hello"},"finish_reason":null}]}
487117
488− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
118+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Crush"},"finish_reason":null}]}
489119
490− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"46"},"finish_reason":null}]}
120+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" and"},"finish_reason":null}]}
491121
492− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"m"},"finish_reason":null}]}
122+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" add"},"finish_reason":null}]}
493123
494− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"47"},"finish_reason":null}]}
124+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" comment"},"finish_reason":null}]}
495125
496− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"a"},"finish_reason":null}]}
126+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
497127
498− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"48"},"finish_reason":null}]}
128+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Title"},"finish_reason":null}]}
499129
500− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"i"},"finish_reason":null}]}
130+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" maybe"},"finish_reason":null}]}
501131
502− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"49"},"finish_reason":null}]}
132+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
503133
504− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"n"},"finish_reason":null}]}
134+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
505135
506− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
136+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Mult"},"finish_reason":null}]}
507137
508− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
138+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ied"},"finish_reason":null}]}
509139
510− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ("},"finish_reason":null}]}
140+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"it"},"finish_reason":null}]}
511141
512− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"dot"},"finish_reason":null}]}
142+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
513143
514− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
144+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" replace"},"finish_reason":null}]}
515145
516− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
146+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" greeting"},"finish_reason":null}]}
517147
518− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"51"},"finish_reason":null}]}
148+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" and"},"finish_reason":null}]}
519149
520− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
150+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" add"},"finish_reason":null}]}
521151
522− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" So"},"finish_reason":null}]}
152+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" comment"},"finish_reason":null}]}
523153
524− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
154+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
525155
526− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"51"},"finish_reason":null}]}
156+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Must"},"finish_reason":null}]}
527157
528− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
158+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" be"},"finish_reason":null}]}
529159
530− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" too"},"finish_reason":null}]}
160+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" under"},"finish_reason":null}]}
531161
532− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" many"},"finish_reason":null}]}
162+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
533163
534− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".\n\n"},"finish_reason":null}]}
164+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
535165
536− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"We"},"finish_reason":null}]}
166+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" chars"},"finish_reason":null}]}
537167
538− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" need"},"finish_reason":null}]}
168+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
539169
540− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \u003c="},"finish_reason":null}]}
170+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
541171
542− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
172+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Replace"},"finish_reason":null}]}
543173
544− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
174+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" greeting"},"finish_reason":null}]}
545175
546− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Maybe"},"finish_reason":null}]}
176+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" and"},"finish_reason":null}]}
547177
548− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" shorten"},"finish_reason":null}]}
178+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" add"},"finish_reason":null}]}
549179
550− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
180+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" comment"},"finish_reason":null}]}
551181
552− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
182+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" with"},"finish_reason":null}]}
553183
554− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Mult"},"finish_reason":null}]}
184+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" mult"},"finish_reason":null}]}
555185
556− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ied"},"finish_reason":null}]}
186+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ied"},"finish_reason":null}]}
557187
558− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"it"},"finish_reason":null}]}
188+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"it"},"finish_reason":null}]}
559189
560− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
190+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
561191
562− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" change"},"finish_reason":null}]}
192+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Count"},"finish_reason":null}]}
563193
564− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" greeting"},"finish_reason":null}]}
194+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
565195
566− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" and"},"finish_reason":null}]}
196+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
567197
568− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" add"},"finish_reason":null}]}
198+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Replace"},"finish_reason":null}]}
569199
570− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" comment"},"finish_reason":null}]}
200+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" greeting"},"finish_reason":null}]}
571201
572− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
202+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" and"},"finish_reason":null}]}
573203
574− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Count"},"finish_reason":null}]}
204+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" add"},"finish_reason":null}]}
575205
576− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
206+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" comment"},"finish_reason":null}]}
577207
578− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
208+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" with"},"finish_reason":null}]}
579209
580− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Mult"},"finish_reason":null}]}
210+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" mult"},"finish_reason":null}]}
581211
582− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ied"},"finish_reason":null}]}
212+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ied"},"finish_reason":null}]}
583213
584− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"it"},"finish_reason":null}]}
214+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"it"},"finish_reason":null}]}
585215
586− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":\""},"finish_reason":null}]}
216+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\""},"finish_reason":null}]}
587217
588− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
218+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ="},"finish_reason":null}]}
589219
590− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"10"},"finish_reason":null}]}
220+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" let's"},"finish_reason":null}]}
591221
592− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
222+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" count"},"finish_reason":null}]}
593223
594− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
224+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
595225
596− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
226+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
597227
598− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"11"},"finish_reason":null}]}
228+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Replace"},"finish_reason":null}]}
599229
600− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
230+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
601231
602− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
232+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"7"},"finish_reason":null}]}
603233
604− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"change"},"finish_reason":null}]}
234+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
605235
606− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\""},"finish_reason":null}]}
236+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
607237
608− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
238+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
609239
610− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"17"},"finish_reason":null}]}
240+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
611241
612− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
242+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
613243
614− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
244+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"8"},"finish_reason":null}]}
615245
616− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
246+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
617247
618− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"18"},"finish_reason":null}]}
248+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" greeting"},"finish_reason":null}]}
619249
620− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
250+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
621251
622− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
252+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"8"},"finish_reason":null}]}
623253
624− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"g"},"finish_reason":null}]}
254+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
625255
626− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"reeting"},"finish_reason":null}]}
256+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"16"},"finish_reason":null}]}
627257
628− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\""},"finish_reason":null}]}
258+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
629259
630− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
260+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
631261
632− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"26"},"finish_reason":null}]}
262+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
633263
634− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
264+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"17"},"finish_reason":null}]}
635265
636− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
266+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
637267
638− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
268+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" and"},"finish_reason":null}]}
639269
640− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"27"},"finish_reason":null}]}
270+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
641271
642− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
272+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"3"},"finish_reason":null}]}
643273
644− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
274+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
645275
646− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"and"},"finish_reason":null}]}
276+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"20"},"finish_reason":null}]}
647277
648− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\""},"finish_reason":null}]}
278+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
649279
650− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
280+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
651281
652− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"30"},"finish_reason":null}]}
282+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
653283
654− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
284+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"21"},"finish_reason":null}]}
655285
656− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
286+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
657287
658− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
288+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" add"},"finish_reason":null}]}
659289
660− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"31"},"finish_reason":null}]}
290+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
661291
662− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
292+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"3"},"finish_reason":null}]}
663293
664− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
294+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
665295
666− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"add"},"finish_reason":null}]}
296+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"24"},"finish_reason":null}]}
667297
668− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\""},"finish_reason":null}]}
298+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
669299
670− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
300+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
671301
672− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"34"},"finish_reason":null}]}
302+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
673303
674− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
304+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"25"},"finish_reason":null}]}
675305
676− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
306+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
677307
678− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
308+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" comment"},"finish_reason":null}]}
679309
680− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"35"},"finish_reason":null}]}
310+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
681311
682− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
312+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"7"},"finish_reason":null}]}
683313
684− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
314+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
685315
686− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"comment"},"finish_reason":null}]}
316+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"32"},"finish_reason":null}]}
687317
688− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\""},"finish_reason":null}]}
318+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
689319
690− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
320+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
691321
692− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"42"},"finish_reason":null}]}
322+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
693323
694− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
324+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"33"},"finish_reason":null}]}
695325
696− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" That's"},"finish_reason":null}]}
326+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
697327
698− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
328+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" with"},"finish_reason":null}]}
699329
700− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"42"},"finish_reason":null}]}
330+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
701331
702− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
332+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"4"},"finish_reason":null}]}
703333
704− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
334+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
705335
706− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Good"},"finish_reason":null}]}
336+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"37"},"finish_reason":null}]}
707337
708− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
338+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
709339
710− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" But"},"finish_reason":null}]}
340+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
711341
712− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" mention"},"finish_reason":null}]}
342+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
713343
714− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" main"},"finish_reason":null}]}
344+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"38"},"finish_reason":null}]}
715345
716− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".go"},"finish_reason":null}]}
346+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
717347
718− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"?"},"finish_reason":null}]}
348+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" mult"},"finish_reason":null}]}
719349
720− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Could"},"finish_reason":null}]}
350+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ied"},"finish_reason":null}]}
721351
722− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" be"},"finish_reason":null}]}
352+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"it"},"finish_reason":null}]}
723353
724− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" fine"},"finish_reason":null}]}
354+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
725355
726− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" but"},"finish_reason":null}]}
356+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"9"},"finish_reason":null}]}
727357
728− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" maybe"},"finish_reason":null}]}
358+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
729359
730− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" include"},"finish_reason":null}]}
360+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"47"},"finish_reason":null}]}
731361
732− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
362+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
733363
734− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Let's"},"finish_reason":null}]}
364+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" That's"},"finish_reason":null}]}
735365
736− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" try"},"finish_reason":null}]}
366+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
737367
738− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
368+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"47"},"finish_reason":null}]}
739369
740− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Mult"},"finish_reason":null}]}
370+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
741371
742− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ied"},"finish_reason":null}]}
372+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
743373
744− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"it"},"finish_reason":null}]}
374+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Okay"},"finish_reason":null}]}
745375
746− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
376+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".\n\n"},"finish_reason":null}]}
747377
748− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" update"},"finish_reason":null}]}
378+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"No"},"finish_reason":null}]}
749379
750− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" greeting"},"finish_reason":null}]}
380+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" quotes"},"finish_reason":null}]}
751381
752− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" and"},"finish_reason":null}]}
382+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
753383
754− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" comment"},"finish_reason":null}]}
384+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Return"},"finish_reason":null}]}
755385
756− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
386+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" that"},"finish_reason":null}]}
757387
758− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" main"},"finish_reason":null}]}
388+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" exactly"},"finish_reason":null}]}
759389
760− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".go"},"finish_reason":null}]}
390+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
761391
762− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
392+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"Replace"},"finish_reason":null}]}
763393
764− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Count"},"finish_reason":null}]}
394+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" greeting"},"finish_reason":null}]}
765395
766− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
396+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" and"},"finish_reason":null}]}
767397
768− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
398+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" add"},"finish_reason":null}]}
769399
770− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Mult"},"finish_reason":null}]}
400+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" comment"},"finish_reason":null}]}
771401
772− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ied"},"finish_reason":null}]}
402+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" with"},"finish_reason":null}]}
773403
774− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"it"},"finish_reason":null}]}
404+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" mult"},"finish_reason":null}]}
775405
776− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":\""},"finish_reason":null}]}
406+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"ied"},"finish_reason":null}]}
777407
778− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"10"},"finish_reason":null}]}
408+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"it"},"finish_reason":null}]}
779409
780− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
410+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
781411
782− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
783−
784− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"11"},"finish_reason":null}]}
785−
786− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
787−
788− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
789−
790− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"update"},"finish_reason":null}]}
791−
792− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\""},"finish_reason":null}]}
793−
794− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"17"},"finish_reason":null}]}
795−
796− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
797−
798− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
799−
800− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"18"},"finish_reason":null}]}
801−
802− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
803−
804− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
805−
806− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"g"},"finish_reason":null}]}
807−
808− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"reeting"},"finish_reason":null}]}
809−
810− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\""},"finish_reason":null}]}
811−
812− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"26"},"finish_reason":null}]}
813−
814− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
815−
816− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
817−
818− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"27"},"finish_reason":null}]}
819−
820− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
821−
822− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
823−
824− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"and"},"finish_reason":null}]}
825−
826− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\""},"finish_reason":null}]}
827−
828− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"30"},"finish_reason":null}]}
829−
830− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
831−
832− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
833−
834− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"31"},"finish_reason":null}]}
835−
836− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
837−
838− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
839−
840− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"comment"},"finish_reason":null}]}
841−
842− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\""},"finish_reason":null}]}
843−
844− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"38"},"finish_reason":null}]}
845−
846− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
847−
848− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
849−
850− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"39"},"finish_reason":null}]}
851−
852− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
853−
854− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
855−
856− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"in"},"finish_reason":null}]}
857−
858− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\""},"finish_reason":null}]}
859−
860− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"41"},"finish_reason":null}]}
861−
862− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
863−
864− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
865−
866− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"42"},"finish_reason":null}]}
867−
868− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
869−
870− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
871−
872− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"main"},"finish_reason":null}]}
873−
874− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".go"},"finish_reason":null}]}
875−
876− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\""},"finish_reason":null}]}
877−
878− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"49"},"finish_reason":null}]}
879−
880− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
881−
882− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" That's"},"finish_reason":null}]}
883−
884− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
885−
886− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"49"},"finish_reason":null}]}
887−
888− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
889−
890− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
891−
892− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Good"},"finish_reason":null}]}
893−
894− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".\n\n"},"finish_reason":null}]}
895−
896− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Thus"},"finish_reason":null}]}
897−
898− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" title"},"finish_reason":null}]}
899−
900− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
901−
902− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Mult"},"finish_reason":null}]}
903−
904− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"ied"},"finish_reason":null}]}
905−
906− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"it"},"finish_reason":null}]}
907−
908− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
909−
910− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" update"},"finish_reason":null}]}
911−
912− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" greeting"},"finish_reason":null}]}
913−
914− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" and"},"finish_reason":null}]}
915−
916− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" comment"},"finish_reason":null}]}
917−
918− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" in"},"finish_reason":null}]}
919−
920− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" main"},"finish_reason":null}]}
921−
922− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":".go"},"finish_reason":null}]}
923−
924− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"Mult"},"finish_reason":null}]}
925−
926− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"ied"},"finish_reason":null}]}
927−
928− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"it"},"finish_reason":null}]}
929−
930− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":":"},"finish_reason":null}]}
931−
932− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" update"},"finish_reason":null}]}
933−
934− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" greeting"},"finish_reason":null}]}
935−
936− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" and"},"finish_reason":null}]}
937−
938− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" comment"},"finish_reason":null}]}
939−
940− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" in"},"finish_reason":null}]}
941−
942− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" main"},"finish_reason":null}]}
943−
944− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":".go"},"finish_reason":null}]}
945−
946− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
947−
948− data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[],"usage":{"prompt_tokens":55,"completion_tokens":433,"total_tokens":664,"prompt_tokens_details":{"cached_tokens":176}}}
412+ data: {"id":"chatcmpl-1063ab879e11abed30964050","object":"chat.completion.chunk","created":1778602952,"model":"gpt-oss-120b","choices":[],"usage":{"prompt_tokens":43,"completion_tokens":200,"total_tokens":435,"prompt_tokens_details":{"cached_tokens":192}}}
949413
950414 data: [DONE]
951415
@@ -954,15 +418,15 @@ interactions:
954418 - text/event-stream
955419 status: 200 OK
956420 code: 200
957− duration: 784.098583ms
958−- id: 2
421+ duration: 492.312166ms
422+- id: 1
959423 request:
960424 proto: HTTP/1.1
961425 proto_major: 1
962426 proto_minor: 1
963− content_length: 34270
427+ content_length: 33810
964428 host: ""
965− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **READ BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default <4 lines), unless explaining complex changes or asked for detail. Conciseness applies to output only, not to thoroughness of work.\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks.\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\". When committing, follow the `<git_commits>` format from the bash tool description exactly, including any configured attribution lines.\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. Focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously.\\n10. **NO URL GUESSING**: Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **TOOL CONSTRAINTS**: Only use documented tools. Never attempt 'apply_patch' or 'apply_diff' - they don't exist. Use 'edit' or 'multiedit' instead.\\n14. **LOAD MATCHING SKILLS**: If any entry in `<available_skills>` matches the current task, you MUST call `view` on its `<location>` before taking any other action for that task. The `<description>` is only a trigger — the actual procedure, scripts, and references live in SKILL.md. Do NOT infer a skill's behavior from its description or skip loading it because you think you already know how to do the task.\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- ALWAYS think and respond in the same spoken language the prompt was written in.\\n- Under 4 lines of text (tool use doesn't count)\\n- Conciseness is about **text only**: always fully implement the requested feature, tests, and wiring even if that requires many tool calls.\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n- Never send acknowledgement-only responses; after receiving new context or instructions, immediately continue the task or state the concrete next action you will take.\\n- Use rich Markdown formatting (headings, bullet lists, tables, code fences) for any multi-sentence or explanatory answer; only use plain unformatted text if the user explicitly asks.\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n</communication_style>\\n\\n<code_references>\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n</code_references>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Cross-check the original prompt and your own mental checklist; if any feasible part remains undone, continue working instead of responding.\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n- When requirements are underspecified but not obviously dangerous, make the most reasonable assumptions based on project patterns and memory files, briefly state them if needed, and proceed instead of waiting for clarification.\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**When requesting information/access**:\\n- Exhaust all available tools, searches, and reasonable assumptions first.\\n- Never say \\\"Need more info\\\" without detail.\\n- In the same message, list each missing item, why it is required, acceptable substitutes, and what you already attempted.\\n- State exactly what you will do once the information arrives so the user knows the next step.\\n\\nWhen you must stop, first finish all unblocked parts of the request, then clearly report: (a) what you tried, (b) exactly why you are blocked, and (c) the minimal external action required. Don't stop just because one path failed—exhaust multiple plausible approaches first.\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\n**Available edit tools:**\\n- `edit` - Single find/replace in a file\\n- `multiedit` - Multiple find/replace operations in one file\\n- `write` - Create/overwrite entire file\\n\\nNever use `apply_patch` or similar - those tools don't exist.\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n</editing_files>\\n\\n<whitespace_and_exact_matching>\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n</whitespace_and_exact_matching>\\n\\n<task_completion>\\nEnsure every task is implemented completely, not partially or sketched.\\n\\n1. **Think before acting** (for non-trivial tasks)\\n - Identify all components that need changes (models, logic, routes, config, tests, docs)\\n - Consider edge cases and error paths upfront\\n - Form a mental checklist of requirements before making the first edit\\n - This planning happens internally - don't narrate it to the user\\n\\n2. **Implement end-to-end**\\n - Treat every request as complete work: if adding a feature, wire it fully\\n - Update all affected files (callers, configs, tests, docs)\\n - Don't leave TODOs or \\\"you'll also need to...\\\" - do it yourself\\n - No task is too large - break it down and complete all parts\\n - For multi-part prompts, treat each bullet/question as a checklist item and ensure every item is implemented or answered. Partial completion is not an acceptable final state.\\n\\n3. **Verify before finishing**\\n - Re-read the original request and verify each requirement is met\\n - Check for missing error handling, edge cases, or unwired code\\n - Run tests to confirm the implementation works\\n - Only say \\\"Done\\\" when truly done - never stop mid-task\\n</task_completion>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause (isolate with debug logs or minimal reproduction if needed)\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n7. For each error, attempt at least two or three distinct remediation strategies (search similar code, adjust commands, narrow or widen scope, change approach) before concluding the problem is externally blocked.\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences\\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n</testing>\\n\\n<tool_usage>\\n- Default to using tools (ls, grep, view, agent, tests, web_fetch, etc.) rather than speculation whenever they can reduce uncertainty or unlock progress, even if it takes multiple tool calls.\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n- Never use `curl` through the bash tool it is not allowed use the fetch tool instead.\\n- Only use the tools you know exist.\\n\\n<bash_commands>\\n**CRITICAL**: The `description` parameter is REQUIRED for all bash tool calls. Always provide it.\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n</bash_commands>\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When the user provides new information or clarification, incorporate it immediately and keep executing instead of stopping with an acknowledgement.\\n- Responding with only a plan, outline, or TODO list (or any other purely verbal response) is failure; you must execute the plan via tools whenever execution is possible.\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<final_answers>\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n- Structure longer answers with Markdown sections and lists, and put all code, commands, and config in fenced code blocks.\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n</final_answers>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/glm-5.1/multiedit_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n</env>\\n\\n\\n\\n<available_skills>\\n <skill>\\n <name>crush-hooks</name>\\n <description>Use when the user wants to add, write, debug, or configure a Crush hook — gating or blocking tool calls, approving or rewriting tool input before execution, injecting context into tool results, or troubleshooting hook behavior in crush.json.</description>\\n <location>crush://skills/crush-hooks/SKILL.md</location>\\n <type>builtin</type>\\n </skill>\\n <skill>\\n <name>jq</name>\\n <description>Use when the user needs to query, filter, reshape, extract, create, or construct JSON data — including API responses, config files, log output, or any structured data — or when helping the user write or debug JSON transformations.</description>\\n <location>crush://skills/jq/SKILL.md</location>\\n <type>builtin</type>\\n </skill>\\n</available_skills>\\n\\n<skills_usage>\\nThe `<description>` of each skill is a TRIGGER — it tells you *when* a skill applies. It is NOT a specification of what the skill does or how to do it. The procedure, scripts, commands, references, and required flags live only in the SKILL.md body. You do not know what a skill actually does until you have read its SKILL.md.\\n\\nMANDATORY activation flow:\\n1. Scan `<available_skills>` against the current user task.\\n2. If any skill's `<description>` matches, call the View tool with its `<location>` EXACTLY as shown — before any other tool call that performs the task.\\n3. Read the entire SKILL.md and follow its instructions.\\n4. Only then execute the task, using the skill's prescribed commands/tools.\\n\\nDo NOT skip step 2 because you think you already know how to do the task. Do NOT infer a skill's behavior from its name or description. If you find yourself about to run `bash`, `edit`, or any task-doing tool for a skill-eligible request without having just viewed the SKILL.md, stop and load the skill first.\\n\\nBuiltin skills (type=builtin) use virtual `crush://skills/...` location identifiers. The \\\"crush://\\\" prefix is NOT a URL, network address, or MCP resource — it is a special internal identifier the View tool understands natively. Pass the `<location>` verbatim to View.\\n\\nDo not use MCP tools (including read_mcp_resource) to load skills.\\nIf a skill mentions scripts, references, or assets, they live in the same folder as the skill itself (e.g., scripts/, references/, assets/ subdirectories within the skill's folder).\\n</skills_usage>\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"<system_reminder>This is a reminder that your todo list is currently empty. DO NOT mention this to the user explicitly because they are already aware.\\nIf you are working on tasks that would benefit from a todo list please use the \\\"todos\\\" tool to create one.\\nIf not, please feel free to ignore. Again do not mention this message to the user.</system_reminder>\",\"role\":\"user\"},{\"content\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_4d3da657d04f428c92d43f15\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/glm-5.1/multiedit_tool/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\",\"reasoning_content\":\"Let me first read the main.go file to see its current content.\"},{\"content\":\"<file>\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n</file>\\n\",\"tool_call_id\":\"call_4d3da657d04f428c92d43f15\",\"role\":\"tool\"}],\"model\":\"glm-5.1\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Execute shell commands; long-running commands automatically move to background and return a shell ID.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Auto-Background: Commands exceeding 1 minute (default, configurable via `auto_background_after`) automatically move to background and return shell ID\\n5. Output Processing: Truncate if exceeds 30000 characters\\n6. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, working_dir optional (defaults to current directory)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Each command runs in independent shell (no state persistence between calls)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<background_execution>\\n- Set run_in_background=true to run commands in a separate background shell\\n- Returns a shell ID for managing the background process\\n- Use job_output tool to view current output from background shell\\n- Use job_kill tool to terminate a background shell\\n- IMPORTANT: NEVER use `&` at the end of commands to run in background - use run_in_background parameter instead\\n- Commands that should run in background:\\n * Long-running servers (e.g., `npm start`, `python -m http.server`, `node server.js`)\\n * Watch/monitoring tasks (e.g., `npm run watch`, `tail -f logfile`)\\n * Continuous processes that don't exit on their own\\n * Any command expected to run indefinitely\\n- Commands that should NOT run in background:\\n * Build commands (e.g., `npm run build`, `go build`)\\n * Test suites (e.g., `npm test`, `pytest`)\\n * Git operations\\n * File operations\\n * Short-lived scripts\\n</background_execution>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"auto_background_after\":{\"description\":\"Seconds to wait before automatically moving the command to a background job (default: 60)\",\"type\":\"integer\"},\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does, try to keep it under 30 characters or so\",\"type\":\"string\"},\"run_in_background\":{\"description\":\"Set to true (boolean) to run this command in the background. Use job_output to read the output later.\",\"type\":\"boolean\"},\"working_dir\":{\"description\":\"The working directory to execute the command in (defaults to current directory)\",\"type\":\"string\"}},\"required\":[\"description\",\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Download a URL directly to a local file (binary-safe, streaming, max 100MB); overwrites without warning. For reading content into context use fetch.\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edit a file by exact find-and-replace; can also create or delete content. For renames/moves use bash. For large edits use write.\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Apply multiple find-and-replace edits to a single file in one operation; edits run sequentially. Prefer over edit for multiple changes to the same file. Same exact-match rules as edit apply.\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"properties\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"required\":[\"old_string\",\"new_string\"],\"type\":\"object\"},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetch raw content from a URL as text, markdown, or html (max 100KB); no AI processing. For analysis or extraction use agentic_fetch.\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Find files by name/pattern (glob syntax), sorted by modification time; max 100 results; skips hidden files. Use grep to search file contents.\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Search file contents by regex or literal text; returns matching file paths sorted by modification time (max 100); respects .gitignore. Use glob to filter by filename, not contents.\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"List files and directories as a tree; skips hidden files and common system dirs; max 1000 files. Use glob to find files by pattern, grep to search contents.\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{\"type\":\"string\"},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public GitHub repositories via Sourcegraph; supports regex, language/repo/file filters, and symbol search (max 20 results). Only searches public repos.\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Read a file by path with line numbers; supports offset and line limit (default 2000, max 200KB returned file content section); renders images (PNG, JPEG, GIF, WebP); use ls for directories.\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Create or overwrite a file with given content; auto-creates parent dirs. Cannot append. Read the file first to avoid conflicts. For surgical changes use edit or multiedit.\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"
429+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **READ BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default <4 lines), unless explaining complex changes or asked for detail. Conciseness applies to output only, not to thoroughness of work.\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks.\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\". When committing, follow the `<git_commits>` format from the bash tool description exactly, including any configured attribution lines.\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. Focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously.\\n10. **NO URL GUESSING**: Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **TOOL CONSTRAINTS**: Only use documented tools. Never attempt 'apply_patch' or 'apply_diff' - they don't exist. Use 'edit' or 'multiedit' instead.\\n14. **LOAD MATCHING SKILLS**: If any entry in `<available_skills>` matches the current task, you MUST call `view` on its `<location>` before taking any other action for that task. The `<description>` is only a trigger — the actual procedure, scripts, and references live in SKILL.md. Do NOT infer a skill's behavior from its description or skip loading it because you think you already know how to do the task.\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- ALWAYS think and respond in the same spoken language the prompt was written in.\\n- Under 4 lines of text (tool use doesn't count)\\n- Conciseness is about **text only**: always fully implement the requested feature, tests, and wiring even if that requires many tool calls.\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n- Never send acknowledgement-only responses; after receiving new context or instructions, immediately continue the task or state the concrete next action you will take.\\n- Use rich Markdown formatting (headings, bullet lists, tables, code fences) for any multi-sentence or explanatory answer; only use plain unformatted text if the user explicitly asks.\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n</communication_style>\\n\\n<code_references>\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n</code_references>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Cross-check the original prompt and your own mental checklist; if any feasible part remains undone, continue working instead of responding.\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n- When requirements are underspecified but not obviously dangerous, make the most reasonable assumptions based on project patterns and memory files, briefly state them if needed, and proceed instead of waiting for clarification.\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**When requesting information/access**:\\n- Exhaust all available tools, searches, and reasonable assumptions first.\\n- Never say \\\"Need more info\\\" without detail.\\n- In the same message, list each missing item, why it is required, acceptable substitutes, and what you already attempted.\\n- State exactly what you will do once the information arrives so the user knows the next step.\\n\\nWhen you must stop, first finish all unblocked parts of the request, then clearly report: (a) what you tried, (b) exactly why you are blocked, and (c) the minimal external action required. Don't stop just because one path failed—exhaust multiple plausible approaches first.\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\n**Available edit tools:**\\n- `edit` - Single find/replace in a file\\n- `multiedit` - Multiple find/replace operations in one file\\n- `write` - Create/overwrite entire file\\n\\nNever use `apply_patch` or similar - those tools don't exist.\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n</editing_files>\\n\\n<whitespace_and_exact_matching>\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n</whitespace_and_exact_matching>\\n\\n<task_completion>\\nEnsure every task is implemented completely, not partially or sketched.\\n\\n1. **Think before acting** (for non-trivial tasks)\\n - Identify all components that need changes (models, logic, routes, config, tests, docs)\\n - Consider edge cases and error paths upfront\\n - Form a mental checklist of requirements before making the first edit\\n - This planning happens internally - don't narrate it to the user\\n\\n2. **Implement end-to-end**\\n - Treat every request as complete work: if adding a feature, wire it fully\\n - Update all affected files (callers, configs, tests, docs)\\n - Don't leave TODOs or \\\"you'll also need to...\\\" - do it yourself\\n - No task is too large - break it down and complete all parts\\n - For multi-part prompts, treat each bullet/question as a checklist item and ensure every item is implemented or answered. Partial completion is not an acceptable final state.\\n\\n3. **Verify before finishing**\\n - Re-read the original request and verify each requirement is met\\n - Check for missing error handling, edge cases, or unwired code\\n - Run tests to confirm the implementation works\\n - Only say \\\"Done\\\" when truly done - never stop mid-task\\n</task_completion>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause (isolate with debug logs or minimal reproduction if needed)\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n7. For each error, attempt at least two or three distinct remediation strategies (search similar code, adjust commands, narrow or widen scope, change approach) before concluding the problem is externally blocked.\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences\\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n</testing>\\n\\n<tool_usage>\\n- Default to using tools (ls, grep, view, agent, tests, web_fetch, etc.) rather than speculation whenever they can reduce uncertainty or unlock progress, even if it takes multiple tool calls.\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n- Never use `curl` through the bash tool it is not allowed use the fetch tool instead.\\n- Only use the tools you know exist.\\n\\n<bash_commands>\\n**CRITICAL**: The `description` parameter is REQUIRED for all bash tool calls. Always provide it.\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n</bash_commands>\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When the user provides new information or clarification, incorporate it immediately and keep executing instead of stopping with an acknowledgement.\\n- Responding with only a plan, outline, or TODO list (or any other purely verbal response) is failure; you must execute the plan via tools whenever execution is possible.\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<final_answers>\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n- Structure longer answers with Markdown sections and lists, and put all code, commands, and config in fenced code blocks.\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n</final_answers>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/glm-5.1/multiedit_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n</env>\\n\\n\\n\\n<available_skills>\\n <skill>\\n <name>crush-hooks</name>\\n <description>Use when the user wants to add, write, debug, or configure a Crush hook — gating or blocking tool calls, approving or rewriting tool input before execution, injecting context into tool results, or troubleshooting hook behavior in crush.json.</description>\\n <location>crush://skills/crush-hooks/SKILL.md</location>\\n <type>builtin</type>\\n </skill>\\n <skill>\\n <name>jq</name>\\n <description>Use when the user needs to query, filter, reshape, extract, create, or construct JSON data — including API responses, config files, log output, or any structured data — or when helping the user write or debug JSON transformations.</description>\\n <location>crush://skills/jq/SKILL.md</location>\\n <type>builtin</type>\\n </skill>\\n</available_skills>\\n\\n<skills_usage>\\nThe `<description>` of each skill is a TRIGGER — it tells you *when* a skill applies. It is NOT a specification of what the skill does or how to do it. The procedure, scripts, commands, references, and required flags live only in the SKILL.md body. You do not know what a skill actually does until you have read its SKILL.md.\\n\\nMANDATORY activation flow:\\n1. Scan `<available_skills>` against the current user task.\\n2. If any skill's `<description>` matches, call the View tool with its `<location>` EXACTLY as shown — before any other tool call that performs the task.\\n3. Read the entire SKILL.md and follow its instructions.\\n4. Only then execute the task, using the skill's prescribed commands/tools.\\n\\nDo NOT skip step 2 because you think you already know how to do the task. Do NOT infer a skill's behavior from its name or description. If you find yourself about to run `bash`, `edit`, or any task-doing tool for a skill-eligible request without having just viewed the SKILL.md, stop and load the skill first.\\n\\nBuiltin skills (type=builtin) use virtual `crush://skills/...` location identifiers. The \\\"crush://\\\" prefix is NOT a URL, network address, or MCP resource — it is a special internal identifier the View tool understands natively. Pass the `<location>` verbatim to View.\\n\\nDo not use MCP tools (including read_mcp_resource) to load skills.\\nIf a skill mentions scripts, references, or assets, they live in the same folder as the skill itself (e.g., scripts/, references/, assets/ subdirectories within the skill's folder).\\n</skills_usage>\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"<system_reminder>This is a reminder that your todo list is currently empty. DO NOT mention this to the user explicitly because they are already aware.\\nIf you are working on tasks that would benefit from a todo list please use the \\\"todos\\\" tool to create one.\\nIf not, please feel free to ignore. Again do not mention this message to the user.</system_reminder>\",\"role\":\"user\"},{\"content\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"role\":\"user\"}],\"model\":\"glm-5.1\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Execute shell commands; long-running commands automatically move to background and return a shell ID.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Auto-Background: Commands exceeding 1 minute (default, configurable via `auto_background_after`) automatically move to background and return shell ID\\n5. Output Processing: Truncate if exceeds 30000 characters\\n6. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, working_dir optional (defaults to current directory)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Each command runs in independent shell (no state persistence between calls)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<background_execution>\\n- Set run_in_background=true to run commands in a separate background shell\\n- Returns a shell ID for managing the background process\\n- Use job_output tool to view current output from background shell\\n- Use job_kill tool to terminate a background shell\\n- IMPORTANT: NEVER use `&` at the end of commands to run in background - use run_in_background parameter instead\\n- Commands that should run in background:\\n * Long-running servers (e.g., `npm start`, `python -m http.server`, `node server.js`)\\n * Watch/monitoring tasks (e.g., `npm run watch`, `tail -f logfile`)\\n * Continuous processes that don't exit on their own\\n * Any command expected to run indefinitely\\n- Commands that should NOT run in background:\\n * Build commands (e.g., `npm run build`, `go build`)\\n * Test suites (e.g., `npm test`, `pytest`)\\n * Git operations\\n * File operations\\n * Short-lived scripts\\n</background_execution>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response, when rebasing always use -m or GIT_EDITOR=true.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"auto_background_after\":{\"description\":\"Seconds to wait before automatically moving the command to a background job (default: 60)\",\"type\":\"integer\"},\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does, try to keep it under 30 characters or so\",\"type\":\"string\"},\"run_in_background\":{\"description\":\"Set to true (boolean) to run this command in the background. Use job_output to read the output later.\",\"type\":\"boolean\"},\"working_dir\":{\"description\":\"The working directory to execute the command in (defaults to current directory)\",\"type\":\"string\"}},\"required\":[\"description\",\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Download a URL directly to a local file (binary-safe, streaming, max 600s timeout); overwrites without warning. For reading content into context use fetch.\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edit a file by exact find-and-replace; can also create or delete content. For renames/moves use bash. For large edits use write.\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Apply multiple find-and-replace edits to a single file in one operation; edits run sequentially. Prefer over edit for multiple changes to the same file. Same exact-match rules as edit apply.\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"properties\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"required\":[\"old_string\",\"new_string\"],\"type\":\"object\"},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetch raw content from a URL as text, markdown, or html (max 100KB); no AI processing. For analysis or extraction use agentic_fetch.\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Find files by name/pattern (glob syntax), sorted by modification time; max 100 results; skips hidden files. Use grep to search file contents.\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Search file contents by regex or literal text; returns matching file paths sorted by modification time (max 100); respects .gitignore. Use glob to filter by filename, not contents.\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"List files and directories as a tree; skips hidden files and common system dirs; max 1000 files. Use glob to find files by pattern, grep to search contents.\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{\"type\":\"string\"},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public GitHub repositories via Sourcegraph; supports regex, language/repo/file filters, and symbol search (max 20 results). Only searches public repos.\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Read a file by path with line numbers; supports offset and line limit (default 2000, max 200KB returned file content section); renders images (PNG, JPEG, GIF, WebP); use ls for directories.\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Create or overwrite a file with given content; auto-creates parent dirs. Cannot append. Read the file first to avoid conflicts. For surgical changes use edit or multiedit.\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"
966430 headers:
967431 Accept:
968432 - application/json
@@ -979,57 +443,59 @@ interactions:
979443 content_length: -1
980444 uncompressed: true
981445 body: |+
982− data: {"id":"chatcmpl-94a5ca0c49f9490e9f7f86f2","object":"chat.completion.chunk","created":1778531387,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
446+ data: {"id":"chatcmpl-6fcb53a44f4d6e9964083c73","object":"chat.completion.chunk","created":1778602954,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
983447
984− data: {"id":"chatcmpl-94a5ca0c49f9490e9f7f86f2","object":"chat.completion.chunk","created":1778531387,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_24e7ffc678a64fc58e667545","type":"function","index":0,"function":{"name":"multiedit","arguments":""}}]},"finish_reason":null}]}
448+ data: {"id":"chatcmpl-6fcb53a44f4d6e9964083c73","object":"chat.completion.chunk","created":1778602954,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"Let"},"finish_reason":null}]}
985449
986− data: {"id":"chatcmpl-94a5ca0c49f9490e9f7f86f2","object":"chat.completion.chunk","created":1778531387,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\"edits\":[{\"new_string\": \"Hello, Crush!\", \"old_string\": \"Hello, World!\"}, {\"new_string\": \"\\t// Greeting\\n\\tfmt.Println(\\\"Hello, Crush!\\\")\", \"old_string\": \"\\tfmt.Println(\\\"Hello, World!\\\")\"}],\"file_path\":\"/tmp/crush-test/TestCoderAgent/glm-5.1/multiedit_tool/main.go\"}"}}]},"finish_reason":null}]}
450+ data: {"id":"chatcmpl-6fcb53a44f4d6e9964083c73","object":"chat.completion.chunk","created":1778602954,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" me"},"finish_reason":null}]}
987451
988− data: {"id":"chatcmpl-94a5ca0c49f9490e9f7f86f2","object":"chat.completion.chunk","created":1778531387,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}]}
452+ data: {"id":"chatcmpl-6fcb53a44f4d6e9964083c73","object":"chat.completion.chunk","created":1778602954,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" first read"},"finish_reason":null}]}
989453
990− data: {"id":"chatcmpl-94a5ca0c49f9490e9f7f86f2","object":"chat.completion.chunk","created":1778531387,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":108,"completion_tokens":95,"total_tokens":7947,"prompt_tokens_details":{"cached_tokens":7744}}}
454+ data: {"id":"chatcmpl-6fcb53a44f4d6e9964083c73","object":"chat.completion.chunk","created":1778602954,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" the file"},"finish_reason":null}]}
991455
992− data: [DONE]
456+ data: {"id":"chatcmpl-6fcb53a44f4d6e9964083c73","object":"chat.completion.chunk","created":1778602954,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" to see"},"finish_reason":null}]}
993457
994− headers:
995− Content-Type:
996− - text/event-stream
997− status: 200 OK
998− code: 200
999− duration: 5.524277875s
1000−- id: 3
1001− request:
1002− proto: HTTP/1.1
1003− proto_major: 1
1004− proto_minor: 1
1005− content_length: 34943
1006− host: ""
1007− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **READ BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default <4 lines), unless explaining complex changes or asked for detail. Conciseness applies to output only, not to thoroughness of work.\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks.\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\". When committing, follow the `<git_commits>` format from the bash tool description exactly, including any configured attribution lines.\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. Focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously.\\n10. **NO URL GUESSING**: Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **TOOL CONSTRAINTS**: Only use documented tools. Never attempt 'apply_patch' or 'apply_diff' - they don't exist. Use 'edit' or 'multiedit' instead.\\n14. **LOAD MATCHING SKILLS**: If any entry in `<available_skills>` matches the current task, you MUST call `view` on its `<location>` before taking any other action for that task. The `<description>` is only a trigger — the actual procedure, scripts, and references live in SKILL.md. Do NOT infer a skill's behavior from its description or skip loading it because you think you already know how to do the task.\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- ALWAYS think and respond in the same spoken language the prompt was written in.\\n- Under 4 lines of text (tool use doesn't count)\\n- Conciseness is about **text only**: always fully implement the requested feature, tests, and wiring even if that requires many tool calls.\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n- Never send acknowledgement-only responses; after receiving new context or instructions, immediately continue the task or state the concrete next action you will take.\\n- Use rich Markdown formatting (headings, bullet lists, tables, code fences) for any multi-sentence or explanatory answer; only use plain unformatted text if the user explicitly asks.\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n</communication_style>\\n\\n<code_references>\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n</code_references>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Cross-check the original prompt and your own mental checklist; if any feasible part remains undone, continue working instead of responding.\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n- When requirements are underspecified but not obviously dangerous, make the most reasonable assumptions based on project patterns and memory files, briefly state them if needed, and proceed instead of waiting for clarification.\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**When requesting information/access**:\\n- Exhaust all available tools, searches, and reasonable assumptions first.\\n- Never say \\\"Need more info\\\" without detail.\\n- In the same message, list each missing item, why it is required, acceptable substitutes, and what you already attempted.\\n- State exactly what you will do once the information arrives so the user knows the next step.\\n\\nWhen you must stop, first finish all unblocked parts of the request, then clearly report: (a) what you tried, (b) exactly why you are blocked, and (c) the minimal external action required. Don't stop just because one path failed—exhaust multiple plausible approaches first.\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\n**Available edit tools:**\\n- `edit` - Single find/replace in a file\\n- `multiedit` - Multiple find/replace operations in one file\\n- `write` - Create/overwrite entire file\\n\\nNever use `apply_patch` or similar - those tools don't exist.\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n</editing_files>\\n\\n<whitespace_and_exact_matching>\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n</whitespace_and_exact_matching>\\n\\n<task_completion>\\nEnsure every task is implemented completely, not partially or sketched.\\n\\n1. **Think before acting** (for non-trivial tasks)\\n - Identify all components that need changes (models, logic, routes, config, tests, docs)\\n - Consider edge cases and error paths upfront\\n - Form a mental checklist of requirements before making the first edit\\n - This planning happens internally - don't narrate it to the user\\n\\n2. **Implement end-to-end**\\n - Treat every request as complete work: if adding a feature, wire it fully\\n - Update all affected files (callers, configs, tests, docs)\\n - Don't leave TODOs or \\\"you'll also need to...\\\" - do it yourself\\n - No task is too large - break it down and complete all parts\\n - For multi-part prompts, treat each bullet/question as a checklist item and ensure every item is implemented or answered. Partial completion is not an acceptable final state.\\n\\n3. **Verify before finishing**\\n - Re-read the original request and verify each requirement is met\\n - Check for missing error handling, edge cases, or unwired code\\n - Run tests to confirm the implementation works\\n - Only say \\\"Done\\\" when truly done - never stop mid-task\\n</task_completion>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause (isolate with debug logs or minimal reproduction if needed)\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n7. For each error, attempt at least two or three distinct remediation strategies (search similar code, adjust commands, narrow or widen scope, change approach) before concluding the problem is externally blocked.\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences\\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n</testing>\\n\\n<tool_usage>\\n- Default to using tools (ls, grep, view, agent, tests, web_fetch, etc.) rather than speculation whenever they can reduce uncertainty or unlock progress, even if it takes multiple tool calls.\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n- Never use `curl` through the bash tool it is not allowed use the fetch tool instead.\\n- Only use the tools you know exist.\\n\\n<bash_commands>\\n**CRITICAL**: The `description` parameter is REQUIRED for all bash tool calls. Always provide it.\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n</bash_commands>\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When the user provides new information or clarification, incorporate it immediately and keep executing instead of stopping with an acknowledgement.\\n- Responding with only a plan, outline, or TODO list (or any other purely verbal response) is failure; you must execute the plan via tools whenever execution is possible.\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<final_answers>\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n- Structure longer answers with Markdown sections and lists, and put all code, commands, and config in fenced code blocks.\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n</final_answers>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/glm-5.1/multiedit_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n</env>\\n\\n\\n\\n<available_skills>\\n <skill>\\n <name>crush-hooks</name>\\n <description>Use when the user wants to add, write, debug, or configure a Crush hook — gating or blocking tool calls, approving or rewriting tool input before execution, injecting context into tool results, or troubleshooting hook behavior in crush.json.</description>\\n <location>crush://skills/crush-hooks/SKILL.md</location>\\n <type>builtin</type>\\n </skill>\\n <skill>\\n <name>jq</name>\\n <description>Use when the user needs to query, filter, reshape, extract, create, or construct JSON data — including API responses, config files, log output, or any structured data — or when helping the user write or debug JSON transformations.</description>\\n <location>crush://skills/jq/SKILL.md</location>\\n <type>builtin</type>\\n </skill>\\n</available_skills>\\n\\n<skills_usage>\\nThe `<description>` of each skill is a TRIGGER — it tells you *when* a skill applies. It is NOT a specification of what the skill does or how to do it. The procedure, scripts, commands, references, and required flags live only in the SKILL.md body. You do not know what a skill actually does until you have read its SKILL.md.\\n\\nMANDATORY activation flow:\\n1. Scan `<available_skills>` against the current user task.\\n2. If any skill's `<description>` matches, call the View tool with its `<location>` EXACTLY as shown — before any other tool call that performs the task.\\n3. Read the entire SKILL.md and follow its instructions.\\n4. Only then execute the task, using the skill's prescribed commands/tools.\\n\\nDo NOT skip step 2 because you think you already know how to do the task. Do NOT infer a skill's behavior from its name or description. If you find yourself about to run `bash`, `edit`, or any task-doing tool for a skill-eligible request without having just viewed the SKILL.md, stop and load the skill first.\\n\\nBuiltin skills (type=builtin) use virtual `crush://skills/...` location identifiers. The \\\"crush://\\\" prefix is NOT a URL, network address, or MCP resource — it is a special internal identifier the View tool understands natively. Pass the `<location>` verbatim to View.\\n\\nDo not use MCP tools (including read_mcp_resource) to load skills.\\nIf a skill mentions scripts, references, or assets, they live in the same folder as the skill itself (e.g., scripts/, references/, assets/ subdirectories within the skill's folder).\\n</skills_usage>\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"<system_reminder>This is a reminder that your todo list is currently empty. DO NOT mention this to the user explicitly because they are already aware.\\nIf you are working on tasks that would benefit from a todo list please use the \\\"todos\\\" tool to create one.\\nIf not, please feel free to ignore. Again do not mention this message to the user.</system_reminder>\",\"role\":\"user\"},{\"content\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_4d3da657d04f428c92d43f15\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/glm-5.1/multiedit_tool/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\",\"reasoning_content\":\"Let me first read the main.go file to see its current content.\"},{\"content\":\"<file>\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n</file>\\n\",\"tool_call_id\":\"call_4d3da657d04f428c92d43f15\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_24e7ffc678a64fc58e667545\",\"function\":{\"arguments\":\"{\\\"edits\\\":[{\\\"new_string\\\": \\\"Hello, Crush!\\\", \\\"old_string\\\": \\\"Hello, World!\\\"}, {\\\"new_string\\\": \\\"\\\\t// Greeting\\\\n\\\\tfmt.Println(\\\\\\\"Hello, Crush!\\\\\\\")\\\", \\\"old_string\\\": \\\"\\\\tfmt.Println(\\\\\\\"Hello, World!\\\\\\\")\\\"}],\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/glm-5.1/multiedit_tool/main.go\\\"}\",\"name\":\"multiedit\"},\"type\":\"function\"}],\"role\":\"assistant\",\"reasoning_content\":\"\"},{\"content\":\"<result>\\nApplied 1 of 2 edits to file: /tmp/crush-test/TestCoderAgent/glm-5.1/multiedit_tool/main.go (1 edit(s) failed)\\n</result>\\n\",\"tool_call_id\":\"call_24e7ffc678a64fc58e667545\",\"role\":\"tool\"}],\"model\":\"glm-5.1\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Execute shell commands; long-running commands automatically move to background and return a shell ID.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Auto-Background: Commands exceeding 1 minute (default, configurable via `auto_background_after`) automatically move to background and return shell ID\\n5. Output Processing: Truncate if exceeds 30000 characters\\n6. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, working_dir optional (defaults to current directory)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Each command runs in independent shell (no state persistence between calls)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<background_execution>\\n- Set run_in_background=true to run commands in a separate background shell\\n- Returns a shell ID for managing the background process\\n- Use job_output tool to view current output from background shell\\n- Use job_kill tool to terminate a background shell\\n- IMPORTANT: NEVER use `&` at the end of commands to run in background - use run_in_background parameter instead\\n- Commands that should run in background:\\n * Long-running servers (e.g., `npm start`, `python -m http.server`, `node server.js`)\\n * Watch/monitoring tasks (e.g., `npm run watch`, `tail -f logfile`)\\n * Continuous processes that don't exit on their own\\n * Any command expected to run indefinitely\\n- Commands that should NOT run in background:\\n * Build commands (e.g., `npm run build`, `go build`)\\n * Test suites (e.g., `npm test`, `pytest`)\\n * Git operations\\n * File operations\\n * Short-lived scripts\\n</background_execution>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"auto_background_after\":{\"description\":\"Seconds to wait before automatically moving the command to a background job (default: 60)\",\"type\":\"integer\"},\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does, try to keep it under 30 characters or so\",\"type\":\"string\"},\"run_in_background\":{\"description\":\"Set to true (boolean) to run this command in the background. Use job_output to read the output later.\",\"type\":\"boolean\"},\"working_dir\":{\"description\":\"The working directory to execute the command in (defaults to current directory)\",\"type\":\"string\"}},\"required\":[\"description\",\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Download a URL directly to a local file (binary-safe, streaming, max 100MB); overwrites without warning. For reading content into context use fetch.\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edit a file by exact find-and-replace; can also create or delete content. For renames/moves use bash. For large edits use write.\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Apply multiple find-and-replace edits to a single file in one operation; edits run sequentially. Prefer over edit for multiple changes to the same file. Same exact-match rules as edit apply.\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"properties\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"required\":[\"old_string\",\"new_string\"],\"type\":\"object\"},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetch raw content from a URL as text, markdown, or html (max 100KB); no AI processing. For analysis or extraction use agentic_fetch.\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Find files by name/pattern (glob syntax), sorted by modification time; max 100 results; skips hidden files. Use grep to search file contents.\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Search file contents by regex or literal text; returns matching file paths sorted by modification time (max 100); respects .gitignore. Use glob to filter by filename, not contents.\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"List files and directories as a tree; skips hidden files and common system dirs; max 1000 files. Use glob to find files by pattern, grep to search contents.\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{\"type\":\"string\"},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public GitHub repositories via Sourcegraph; supports regex, language/repo/file filters, and symbol search (max 20 results). Only searches public repos.\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Read a file by path with line numbers; supports offset and line limit (default 2000, max 200KB returned file content section); renders images (PNG, JPEG, GIF, WebP); use ls for directories.\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Create or overwrite a file with given content; auto-creates parent dirs. Cannot append. Read the file first to avoid conflicts. For surgical changes use edit or multiedit.\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"
1008− headers:
1009− Accept:
1010− - application/json
1011− Content-Type:
1012− - application/json
1013− User-Agent:
1014− - Charm-Crush/devel (https://charm.land/crush)
1015− url: https://hyper.charm.land/v1/chat/completions
1016− method: POST
1017− response:
1018− proto: HTTP/2.0
1019− proto_major: 2
1020− proto_minor: 0
1021− content_length: -1
1022− uncompressed: true
1023− body: |+
1024− data: {"id":"chatcmpl-2b56351326cf2f0b163f32fa","object":"chat.completion.chunk","created":1778531391,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
458+ data: {"id":"chatcmpl-6fcb53a44f4d6e9964083c73","object":"chat.completion.chunk","created":1778602954,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" its current"},"finish_reason":null}]}
459+
460+ data: {"id":"chatcmpl-6fcb53a44f4d6e9964083c73","object":"chat.completion.chunk","created":1778602954,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" contents"},"finish_reason":null}]}
461+
462+ data: {"id":"chatcmpl-6fcb53a44f4d6e9964083c73","object":"chat.completion.chunk","created":1778602954,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
463+
464+ data: {"id":"chatcmpl-6fcb53a44f4d6e9964083c73","object":"chat.completion.chunk","created":1778602954,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_fc1d5e25b1c14cb68be5d476","type":"function","index":0,"function":{"name":"view","arguments":""}}]},"finish_reason":null}]}
465+
466+ data: {"id":"chatcmpl-6fcb53a44f4d6e9964083c73","object":"chat.completion.chunk","created":1778602954,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":""}}]},"finish_reason":null}]}
467+
468+ data: {"id":"chatcmpl-6fcb53a44f4d6e9964083c73","object":"chat.completion.chunk","created":1778602954,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{"}}]},"finish_reason":null}]}
469+
470+ data: {"id":"chatcmpl-6fcb53a44f4d6e9964083c73","object":"chat.completion.chunk","created":1778602954,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"file_path\": \"/tmp/c"}}]},"finish_reason":null}]}
471+
472+ data: {"id":"chatcmpl-6fcb53a44f4d6e9964083c73","object":"chat.completion.chunk","created":1778602954,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"rush-test"}}]},"finish_reason":null}]}
473+
474+ data: {"id":"chatcmpl-6fcb53a44f4d6e9964083c73","object":"chat.completion.chunk","created":1778602954,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}]}
475+
476+ data: {"id":"chatcmpl-6fcb53a44f4d6e9964083c73","object":"chat.completion.chunk","created":1778602954,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}]}
477+
478+ data: {"id":"chatcmpl-6fcb53a44f4d6e9964083c73","object":"chat.completion.chunk","created":1778602954,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}]}
479+
480+ data: {"id":"chatcmpl-6fcb53a44f4d6e9964083c73","object":"chat.completion.chunk","created":1778602954,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/glm"}}]},"finish_reason":null}]}
1025481
1026− data: {"id":"chatcmpl-2b56351326cf2f0b163f32fa","object":"chat.completion.chunk","created":1778531391,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_9d4e62e2b4fb494b9d34f994","type":"function","index":0,"function":{"name":"view","arguments":""}}]},"finish_reason":null}]}
482+ data: {"id":"chatcmpl-6fcb53a44f4d6e9964083c73","object":"chat.completion.chunk","created":1778602954,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-5"}}]},"finish_reason":null}]}
1027483
1028− data: {"id":"chatcmpl-2b56351326cf2f0b163f32fa","object":"chat.completion.chunk","created":1778531391,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\"file_path\":\"/tmp/crush-test/TestCoderAgent/glm-5.1/multiedit_tool/main.go\"}"}}]},"finish_reason":null}]}
484+ data: {"id":"chatcmpl-6fcb53a44f4d6e9964083c73","object":"chat.completion.chunk","created":1778602954,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".1"}}]},"finish_reason":null}]}
1029485
1030− data: {"id":"chatcmpl-2b56351326cf2f0b163f32fa","object":"chat.completion.chunk","created":1778531391,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}]}
486+ data: {"id":"chatcmpl-6fcb53a44f4d6e9964083c73","object":"chat.completion.chunk","created":1778602954,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/multied"}}]},"finish_reason":null}]}
1031487
1032− data: {"id":"chatcmpl-2b56351326cf2f0b163f32fa","object":"chat.completion.chunk","created":1778531391,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":187,"completion_tokens":31,"total_tokens":8026,"prompt_tokens_details":{"cached_tokens":7808}}}
488+ data: {"id":"chatcmpl-6fcb53a44f4d6e9964083c73","object":"chat.completion.chunk","created":1778602954,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"it_tool"}}]},"finish_reason":null}]}
489+
490+ data: {"id":"chatcmpl-6fcb53a44f4d6e9964083c73","object":"chat.completion.chunk","created":1778602954,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/main.go"}}]},"finish_reason":null}]}
491+
492+ data: {"id":"chatcmpl-6fcb53a44f4d6e9964083c73","object":"chat.completion.chunk","created":1778602954,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\""}}]},"finish_reason":null}]}
493+
494+ data: {"id":"chatcmpl-6fcb53a44f4d6e9964083c73","object":"chat.completion.chunk","created":1778602954,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}]}
495+
496+ data: {"id":"chatcmpl-6fcb53a44f4d6e9964083c73","object":"chat.completion.chunk","created":1778602954,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}]}
497+
498+ data: {"id":"chatcmpl-6fcb53a44f4d6e9964083c73","object":"chat.completion.chunk","created":1778602954,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":752,"completion_tokens":43,"total_tokens":7835,"prompt_tokens_details":{"cached_tokens":7040},"completion_tokens_details":{"reasoning_tokens":12}}}
1033499
1034500 data: [DONE]
1035501
@@ -1038,15 +504,15 @@ interactions:
1038504 - text/event-stream
1039505 status: 200 OK
1040506 code: 200
1041− duration: 3.613997833s
1042−- id: 4
507+ duration: 3.0584735s
508+- id: 2
1043509 request:
1044510 proto: HTTP/1.1
1045511 proto_major: 1
1046512 proto_minor: 1
1047− content_length: 35410
513+ content_length: 34342
1048514 host: ""
1049− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **READ BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default <4 lines), unless explaining complex changes or asked for detail. Conciseness applies to output only, not to thoroughness of work.\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks.\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\". When committing, follow the `<git_commits>` format from the bash tool description exactly, including any configured attribution lines.\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. Focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously.\\n10. **NO URL GUESSING**: Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **TOOL CONSTRAINTS**: Only use documented tools. Never attempt 'apply_patch' or 'apply_diff' - they don't exist. Use 'edit' or 'multiedit' instead.\\n14. **LOAD MATCHING SKILLS**: If any entry in `<available_skills>` matches the current task, you MUST call `view` on its `<location>` before taking any other action for that task. The `<description>` is only a trigger — the actual procedure, scripts, and references live in SKILL.md. Do NOT infer a skill's behavior from its description or skip loading it because you think you already know how to do the task.\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- ALWAYS think and respond in the same spoken language the prompt was written in.\\n- Under 4 lines of text (tool use doesn't count)\\n- Conciseness is about **text only**: always fully implement the requested feature, tests, and wiring even if that requires many tool calls.\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n- Never send acknowledgement-only responses; after receiving new context or instructions, immediately continue the task or state the concrete next action you will take.\\n- Use rich Markdown formatting (headings, bullet lists, tables, code fences) for any multi-sentence or explanatory answer; only use plain unformatted text if the user explicitly asks.\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n</communication_style>\\n\\n<code_references>\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n</code_references>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Cross-check the original prompt and your own mental checklist; if any feasible part remains undone, continue working instead of responding.\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n- When requirements are underspecified but not obviously dangerous, make the most reasonable assumptions based on project patterns and memory files, briefly state them if needed, and proceed instead of waiting for clarification.\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**When requesting information/access**:\\n- Exhaust all available tools, searches, and reasonable assumptions first.\\n- Never say \\\"Need more info\\\" without detail.\\n- In the same message, list each missing item, why it is required, acceptable substitutes, and what you already attempted.\\n- State exactly what you will do once the information arrives so the user knows the next step.\\n\\nWhen you must stop, first finish all unblocked parts of the request, then clearly report: (a) what you tried, (b) exactly why you are blocked, and (c) the minimal external action required. Don't stop just because one path failed—exhaust multiple plausible approaches first.\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\n**Available edit tools:**\\n- `edit` - Single find/replace in a file\\n- `multiedit` - Multiple find/replace operations in one file\\n- `write` - Create/overwrite entire file\\n\\nNever use `apply_patch` or similar - those tools don't exist.\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n</editing_files>\\n\\n<whitespace_and_exact_matching>\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n</whitespace_and_exact_matching>\\n\\n<task_completion>\\nEnsure every task is implemented completely, not partially or sketched.\\n\\n1. **Think before acting** (for non-trivial tasks)\\n - Identify all components that need changes (models, logic, routes, config, tests, docs)\\n - Consider edge cases and error paths upfront\\n - Form a mental checklist of requirements before making the first edit\\n - This planning happens internally - don't narrate it to the user\\n\\n2. **Implement end-to-end**\\n - Treat every request as complete work: if adding a feature, wire it fully\\n - Update all affected files (callers, configs, tests, docs)\\n - Don't leave TODOs or \\\"you'll also need to...\\\" - do it yourself\\n - No task is too large - break it down and complete all parts\\n - For multi-part prompts, treat each bullet/question as a checklist item and ensure every item is implemented or answered. Partial completion is not an acceptable final state.\\n\\n3. **Verify before finishing**\\n - Re-read the original request and verify each requirement is met\\n - Check for missing error handling, edge cases, or unwired code\\n - Run tests to confirm the implementation works\\n - Only say \\\"Done\\\" when truly done - never stop mid-task\\n</task_completion>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause (isolate with debug logs or minimal reproduction if needed)\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n7. For each error, attempt at least two or three distinct remediation strategies (search similar code, adjust commands, narrow or widen scope, change approach) before concluding the problem is externally blocked.\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences\\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n</testing>\\n\\n<tool_usage>\\n- Default to using tools (ls, grep, view, agent, tests, web_fetch, etc.) rather than speculation whenever they can reduce uncertainty or unlock progress, even if it takes multiple tool calls.\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n- Never use `curl` through the bash tool it is not allowed use the fetch tool instead.\\n- Only use the tools you know exist.\\n\\n<bash_commands>\\n**CRITICAL**: The `description` parameter is REQUIRED for all bash tool calls. Always provide it.\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n</bash_commands>\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When the user provides new information or clarification, incorporate it immediately and keep executing instead of stopping with an acknowledgement.\\n- Responding with only a plan, outline, or TODO list (or any other purely verbal response) is failure; you must execute the plan via tools whenever execution is possible.\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<final_answers>\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n- Structure longer answers with Markdown sections and lists, and put all code, commands, and config in fenced code blocks.\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n</final_answers>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/glm-5.1/multiedit_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n</env>\\n\\n\\n\\n<available_skills>\\n <skill>\\n <name>crush-hooks</name>\\n <description>Use when the user wants to add, write, debug, or configure a Crush hook — gating or blocking tool calls, approving or rewriting tool input before execution, injecting context into tool results, or troubleshooting hook behavior in crush.json.</description>\\n <location>crush://skills/crush-hooks/SKILL.md</location>\\n <type>builtin</type>\\n </skill>\\n <skill>\\n <name>jq</name>\\n <description>Use when the user needs to query, filter, reshape, extract, create, or construct JSON data — including API responses, config files, log output, or any structured data — or when helping the user write or debug JSON transformations.</description>\\n <location>crush://skills/jq/SKILL.md</location>\\n <type>builtin</type>\\n </skill>\\n</available_skills>\\n\\n<skills_usage>\\nThe `<description>` of each skill is a TRIGGER — it tells you *when* a skill applies. It is NOT a specification of what the skill does or how to do it. The procedure, scripts, commands, references, and required flags live only in the SKILL.md body. You do not know what a skill actually does until you have read its SKILL.md.\\n\\nMANDATORY activation flow:\\n1. Scan `<available_skills>` against the current user task.\\n2. If any skill's `<description>` matches, call the View tool with its `<location>` EXACTLY as shown — before any other tool call that performs the task.\\n3. Read the entire SKILL.md and follow its instructions.\\n4. Only then execute the task, using the skill's prescribed commands/tools.\\n\\nDo NOT skip step 2 because you think you already know how to do the task. Do NOT infer a skill's behavior from its name or description. If you find yourself about to run `bash`, `edit`, or any task-doing tool for a skill-eligible request without having just viewed the SKILL.md, stop and load the skill first.\\n\\nBuiltin skills (type=builtin) use virtual `crush://skills/...` location identifiers. The \\\"crush://\\\" prefix is NOT a URL, network address, or MCP resource — it is a special internal identifier the View tool understands natively. Pass the `<location>` verbatim to View.\\n\\nDo not use MCP tools (including read_mcp_resource) to load skills.\\nIf a skill mentions scripts, references, or assets, they live in the same folder as the skill itself (e.g., scripts/, references/, assets/ subdirectories within the skill's folder).\\n</skills_usage>\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"<system_reminder>This is a reminder that your todo list is currently empty. DO NOT mention this to the user explicitly because they are already aware.\\nIf you are working on tasks that would benefit from a todo list please use the \\\"todos\\\" tool to create one.\\nIf not, please feel free to ignore. Again do not mention this message to the user.</system_reminder>\",\"role\":\"user\"},{\"content\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_4d3da657d04f428c92d43f15\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/glm-5.1/multiedit_tool/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\",\"reasoning_content\":\"Let me first read the main.go file to see its current content.\"},{\"content\":\"<file>\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n</file>\\n\",\"tool_call_id\":\"call_4d3da657d04f428c92d43f15\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_24e7ffc678a64fc58e667545\",\"function\":{\"arguments\":\"{\\\"edits\\\":[{\\\"new_string\\\": \\\"Hello, Crush!\\\", \\\"old_string\\\": \\\"Hello, World!\\\"}, {\\\"new_string\\\": \\\"\\\\t// Greeting\\\\n\\\\tfmt.Println(\\\\\\\"Hello, Crush!\\\\\\\")\\\", \\\"old_string\\\": \\\"\\\\tfmt.Println(\\\\\\\"Hello, World!\\\\\\\")\\\"}],\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/glm-5.1/multiedit_tool/main.go\\\"}\",\"name\":\"multiedit\"},\"type\":\"function\"}],\"role\":\"assistant\",\"reasoning_content\":\"\"},{\"content\":\"<result>\\nApplied 1 of 2 edits to file: /tmp/crush-test/TestCoderAgent/glm-5.1/multiedit_tool/main.go (1 edit(s) failed)\\n</result>\\n\",\"tool_call_id\":\"call_24e7ffc678a64fc58e667545\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_9d4e62e2b4fb494b9d34f994\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/glm-5.1/multiedit_tool/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\",\"reasoning_content\":\"\"},{\"content\":\"<file>\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, Crush!\\\")\\n 7|}\\n</file>\\n\",\"tool_call_id\":\"call_9d4e62e2b4fb494b9d34f994\",\"role\":\"tool\"}],\"model\":\"glm-5.1\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Execute shell commands; long-running commands automatically move to background and return a shell ID.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Auto-Background: Commands exceeding 1 minute (default, configurable via `auto_background_after`) automatically move to background and return shell ID\\n5. Output Processing: Truncate if exceeds 30000 characters\\n6. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, working_dir optional (defaults to current directory)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Each command runs in independent shell (no state persistence between calls)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<background_execution>\\n- Set run_in_background=true to run commands in a separate background shell\\n- Returns a shell ID for managing the background process\\n- Use job_output tool to view current output from background shell\\n- Use job_kill tool to terminate a background shell\\n- IMPORTANT: NEVER use `&` at the end of commands to run in background - use run_in_background parameter instead\\n- Commands that should run in background:\\n * Long-running servers (e.g., `npm start`, `python -m http.server`, `node server.js`)\\n * Watch/monitoring tasks (e.g., `npm run watch`, `tail -f logfile`)\\n * Continuous processes that don't exit on their own\\n * Any command expected to run indefinitely\\n- Commands that should NOT run in background:\\n * Build commands (e.g., `npm run build`, `go build`)\\n * Test suites (e.g., `npm test`, `pytest`)\\n * Git operations\\n * File operations\\n * Short-lived scripts\\n</background_execution>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"auto_background_after\":{\"description\":\"Seconds to wait before automatically moving the command to a background job (default: 60)\",\"type\":\"integer\"},\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does, try to keep it under 30 characters or so\",\"type\":\"string\"},\"run_in_background\":{\"description\":\"Set to true (boolean) to run this command in the background. Use job_output to read the output later.\",\"type\":\"boolean\"},\"working_dir\":{\"description\":\"The working directory to execute the command in (defaults to current directory)\",\"type\":\"string\"}},\"required\":[\"description\",\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Download a URL directly to a local file (binary-safe, streaming, max 100MB); overwrites without warning. For reading content into context use fetch.\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edit a file by exact find-and-replace; can also create or delete content. For renames/moves use bash. For large edits use write.\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Apply multiple find-and-replace edits to a single file in one operation; edits run sequentially. Prefer over edit for multiple changes to the same file. Same exact-match rules as edit apply.\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"properties\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"required\":[\"old_string\",\"new_string\"],\"type\":\"object\"},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetch raw content from a URL as text, markdown, or html (max 100KB); no AI processing. For analysis or extraction use agentic_fetch.\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Find files by name/pattern (glob syntax), sorted by modification time; max 100 results; skips hidden files. Use grep to search file contents.\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Search file contents by regex or literal text; returns matching file paths sorted by modification time (max 100); respects .gitignore. Use glob to filter by filename, not contents.\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"List files and directories as a tree; skips hidden files and common system dirs; max 1000 files. Use glob to find files by pattern, grep to search contents.\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{\"type\":\"string\"},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public GitHub repositories via Sourcegraph; supports regex, language/repo/file filters, and symbol search (max 20 results). Only searches public repos.\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Read a file by path with line numbers; supports offset and line limit (default 2000, max 200KB returned file content section); renders images (PNG, JPEG, GIF, WebP); use ls for directories.\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Create or overwrite a file with given content; auto-creates parent dirs. Cannot append. Read the file first to avoid conflicts. For surgical changes use edit or multiedit.\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"
515+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **READ BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default <4 lines), unless explaining complex changes or asked for detail. Conciseness applies to output only, not to thoroughness of work.\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks.\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\". When committing, follow the `<git_commits>` format from the bash tool description exactly, including any configured attribution lines.\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. Focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously.\\n10. **NO URL GUESSING**: Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **TOOL CONSTRAINTS**: Only use documented tools. Never attempt 'apply_patch' or 'apply_diff' - they don't exist. Use 'edit' or 'multiedit' instead.\\n14. **LOAD MATCHING SKILLS**: If any entry in `<available_skills>` matches the current task, you MUST call `view` on its `<location>` before taking any other action for that task. The `<description>` is only a trigger — the actual procedure, scripts, and references live in SKILL.md. Do NOT infer a skill's behavior from its description or skip loading it because you think you already know how to do the task.\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- ALWAYS think and respond in the same spoken language the prompt was written in.\\n- Under 4 lines of text (tool use doesn't count)\\n- Conciseness is about **text only**: always fully implement the requested feature, tests, and wiring even if that requires many tool calls.\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n- Never send acknowledgement-only responses; after receiving new context or instructions, immediately continue the task or state the concrete next action you will take.\\n- Use rich Markdown formatting (headings, bullet lists, tables, code fences) for any multi-sentence or explanatory answer; only use plain unformatted text if the user explicitly asks.\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n</communication_style>\\n\\n<code_references>\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n</code_references>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Cross-check the original prompt and your own mental checklist; if any feasible part remains undone, continue working instead of responding.\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n- When requirements are underspecified but not obviously dangerous, make the most reasonable assumptions based on project patterns and memory files, briefly state them if needed, and proceed instead of waiting for clarification.\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**When requesting information/access**:\\n- Exhaust all available tools, searches, and reasonable assumptions first.\\n- Never say \\\"Need more info\\\" without detail.\\n- In the same message, list each missing item, why it is required, acceptable substitutes, and what you already attempted.\\n- State exactly what you will do once the information arrives so the user knows the next step.\\n\\nWhen you must stop, first finish all unblocked parts of the request, then clearly report: (a) what you tried, (b) exactly why you are blocked, and (c) the minimal external action required. Don't stop just because one path failed—exhaust multiple plausible approaches first.\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\n**Available edit tools:**\\n- `edit` - Single find/replace in a file\\n- `multiedit` - Multiple find/replace operations in one file\\n- `write` - Create/overwrite entire file\\n\\nNever use `apply_patch` or similar - those tools don't exist.\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n</editing_files>\\n\\n<whitespace_and_exact_matching>\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n</whitespace_and_exact_matching>\\n\\n<task_completion>\\nEnsure every task is implemented completely, not partially or sketched.\\n\\n1. **Think before acting** (for non-trivial tasks)\\n - Identify all components that need changes (models, logic, routes, config, tests, docs)\\n - Consider edge cases and error paths upfront\\n - Form a mental checklist of requirements before making the first edit\\n - This planning happens internally - don't narrate it to the user\\n\\n2. **Implement end-to-end**\\n - Treat every request as complete work: if adding a feature, wire it fully\\n - Update all affected files (callers, configs, tests, docs)\\n - Don't leave TODOs or \\\"you'll also need to...\\\" - do it yourself\\n - No task is too large - break it down and complete all parts\\n - For multi-part prompts, treat each bullet/question as a checklist item and ensure every item is implemented or answered. Partial completion is not an acceptable final state.\\n\\n3. **Verify before finishing**\\n - Re-read the original request and verify each requirement is met\\n - Check for missing error handling, edge cases, or unwired code\\n - Run tests to confirm the implementation works\\n - Only say \\\"Done\\\" when truly done - never stop mid-task\\n</task_completion>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause (isolate with debug logs or minimal reproduction if needed)\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n7. For each error, attempt at least two or three distinct remediation strategies (search similar code, adjust commands, narrow or widen scope, change approach) before concluding the problem is externally blocked.\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences\\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n</testing>\\n\\n<tool_usage>\\n- Default to using tools (ls, grep, view, agent, tests, web_fetch, etc.) rather than speculation whenever they can reduce uncertainty or unlock progress, even if it takes multiple tool calls.\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n- Never use `curl` through the bash tool it is not allowed use the fetch tool instead.\\n- Only use the tools you know exist.\\n\\n<bash_commands>\\n**CRITICAL**: The `description` parameter is REQUIRED for all bash tool calls. Always provide it.\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n</bash_commands>\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When the user provides new information or clarification, incorporate it immediately and keep executing instead of stopping with an acknowledgement.\\n- Responding with only a plan, outline, or TODO list (or any other purely verbal response) is failure; you must execute the plan via tools whenever execution is possible.\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<final_answers>\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n- Structure longer answers with Markdown sections and lists, and put all code, commands, and config in fenced code blocks.\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n</final_answers>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/glm-5.1/multiedit_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n</env>\\n\\n\\n\\n<available_skills>\\n <skill>\\n <name>crush-hooks</name>\\n <description>Use when the user wants to add, write, debug, or configure a Crush hook — gating or blocking tool calls, approving or rewriting tool input before execution, injecting context into tool results, or troubleshooting hook behavior in crush.json.</description>\\n <location>crush://skills/crush-hooks/SKILL.md</location>\\n <type>builtin</type>\\n </skill>\\n <skill>\\n <name>jq</name>\\n <description>Use when the user needs to query, filter, reshape, extract, create, or construct JSON data — including API responses, config files, log output, or any structured data — or when helping the user write or debug JSON transformations.</description>\\n <location>crush://skills/jq/SKILL.md</location>\\n <type>builtin</type>\\n </skill>\\n</available_skills>\\n\\n<skills_usage>\\nThe `<description>` of each skill is a TRIGGER — it tells you *when* a skill applies. It is NOT a specification of what the skill does or how to do it. The procedure, scripts, commands, references, and required flags live only in the SKILL.md body. You do not know what a skill actually does until you have read its SKILL.md.\\n\\nMANDATORY activation flow:\\n1. Scan `<available_skills>` against the current user task.\\n2. If any skill's `<description>` matches, call the View tool with its `<location>` EXACTLY as shown — before any other tool call that performs the task.\\n3. Read the entire SKILL.md and follow its instructions.\\n4. Only then execute the task, using the skill's prescribed commands/tools.\\n\\nDo NOT skip step 2 because you think you already know how to do the task. Do NOT infer a skill's behavior from its name or description. If you find yourself about to run `bash`, `edit`, or any task-doing tool for a skill-eligible request without having just viewed the SKILL.md, stop and load the skill first.\\n\\nBuiltin skills (type=builtin) use virtual `crush://skills/...` location identifiers. The \\\"crush://\\\" prefix is NOT a URL, network address, or MCP resource — it is a special internal identifier the View tool understands natively. Pass the `<location>` verbatim to View.\\n\\nDo not use MCP tools (including read_mcp_resource) to load skills.\\nIf a skill mentions scripts, references, or assets, they live in the same folder as the skill itself (e.g., scripts/, references/, assets/ subdirectories within the skill's folder).\\n</skills_usage>\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"<system_reminder>This is a reminder that your todo list is currently empty. DO NOT mention this to the user explicitly because they are already aware.\\nIf you are working on tasks that would benefit from a todo list please use the \\\"todos\\\" tool to create one.\\nIf not, please feel free to ignore. Again do not mention this message to the user.</system_reminder>\",\"role\":\"user\"},{\"content\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_fc1d5e25b1c14cb68be5d476\",\"function\":{\"arguments\":\"{\\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/glm-5.1/multiedit_tool/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\",\"reasoning_content\":\"Let me first read the file to see its current contents.\"},{\"content\":\"<file>\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n 8|\\n</file>\\n\",\"tool_call_id\":\"call_fc1d5e25b1c14cb68be5d476\",\"role\":\"tool\"}],\"model\":\"glm-5.1\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Execute shell commands; long-running commands automatically move to background and return a shell ID.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Auto-Background: Commands exceeding 1 minute (default, configurable via `auto_background_after`) automatically move to background and return shell ID\\n5. Output Processing: Truncate if exceeds 30000 characters\\n6. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, working_dir optional (defaults to current directory)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Each command runs in independent shell (no state persistence between calls)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<background_execution>\\n- Set run_in_background=true to run commands in a separate background shell\\n- Returns a shell ID for managing the background process\\n- Use job_output tool to view current output from background shell\\n- Use job_kill tool to terminate a background shell\\n- IMPORTANT: NEVER use `&` at the end of commands to run in background - use run_in_background parameter instead\\n- Commands that should run in background:\\n * Long-running servers (e.g., `npm start`, `python -m http.server`, `node server.js`)\\n * Watch/monitoring tasks (e.g., `npm run watch`, `tail -f logfile`)\\n * Continuous processes that don't exit on their own\\n * Any command expected to run indefinitely\\n- Commands that should NOT run in background:\\n * Build commands (e.g., `npm run build`, `go build`)\\n * Test suites (e.g., `npm test`, `pytest`)\\n * Git operations\\n * File operations\\n * Short-lived scripts\\n</background_execution>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response, when rebasing always use -m or GIT_EDITOR=true.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"auto_background_after\":{\"description\":\"Seconds to wait before automatically moving the command to a background job (default: 60)\",\"type\":\"integer\"},\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does, try to keep it under 30 characters or so\",\"type\":\"string\"},\"run_in_background\":{\"description\":\"Set to true (boolean) to run this command in the background. Use job_output to read the output later.\",\"type\":\"boolean\"},\"working_dir\":{\"description\":\"The working directory to execute the command in (defaults to current directory)\",\"type\":\"string\"}},\"required\":[\"description\",\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Download a URL directly to a local file (binary-safe, streaming, max 600s timeout); overwrites without warning. For reading content into context use fetch.\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edit a file by exact find-and-replace; can also create or delete content. For renames/moves use bash. For large edits use write.\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Apply multiple find-and-replace edits to a single file in one operation; edits run sequentially. Prefer over edit for multiple changes to the same file. Same exact-match rules as edit apply.\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"properties\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"required\":[\"old_string\",\"new_string\"],\"type\":\"object\"},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetch raw content from a URL as text, markdown, or html (max 100KB); no AI processing. For analysis or extraction use agentic_fetch.\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Find files by name/pattern (glob syntax), sorted by modification time; max 100 results; skips hidden files. Use grep to search file contents.\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Search file contents by regex or literal text; returns matching file paths sorted by modification time (max 100); respects .gitignore. Use glob to filter by filename, not contents.\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"List files and directories as a tree; skips hidden files and common system dirs; max 1000 files. Use glob to find files by pattern, grep to search contents.\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{\"type\":\"string\"},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public GitHub repositories via Sourcegraph; supports regex, language/repo/file filters, and symbol search (max 20 results). Only searches public repos.\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Read a file by path with line numbers; supports offset and line limit (default 2000, max 200KB returned file content section); renders images (PNG, JPEG, GIF, WebP); use ls for directories.\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Create or overwrite a file with given content; auto-creates parent dirs. Cannot append. Read the file first to avoid conflicts. For surgical changes use edit or multiedit.\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"
1050516 headers:
1051517 Accept:
1052518 - application/json
@@ -1063,133 +529,93 @@ interactions:
1063529 content_length: -1
1064530 uncompressed: true
1065531 body: |+
1066− data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
532+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
1067533
1068− data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"The"},"finish_reason":null}]}
534+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_9dfbb4b9cd7a4af3881b997b","type":"function","index":0,"function":{"name":"multiedit","arguments":""}}]},"finish_reason":null}]}
1069535
1070− data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" first"},"finish_reason":null}]}
536+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":""}}]},"finish_reason":null}]}
1071537
1072− data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" edit"},"finish_reason":null}]}
538+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{"}}]},"finish_reason":null}]}
1073539
1074− data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" changed"},"finish_reason":null}]}
540+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"edits\": "}}]},"finish_reason":null}]}
1075541
1076− data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" `\""},"finish_reason":null}]}
542+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"[{\""}}]},"finish_reason":null}]}
1077543
1078− data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"Hello"},"finish_reason":null}]}
544+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"new"}}]},"finish_reason":null}]}
1079545
1080− data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":","},"finish_reason":null}]}
546+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_string"}}]},"finish_reason":null}]}
1081547
1082− data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" World"},"finish_reason":null}]}
548+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\": \"\\"}}]},"finish_reason":null}]}
1083549
1084− data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"!\""},"finish_reason":null}]}
550+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"t//"}}]},"finish_reason":null}]}
1085551
1086− data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"`"},"finish_reason":null}]}
552+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" G"}}]},"finish_reason":null}]}
1087553
1088− data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" to"},"finish_reason":null}]}
554+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"reeting"}}]},"finish_reason":null}]}
1089555
1090− data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" `\""},"finish_reason":null}]}
556+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\n\\t"}}]},"finish_reason":null}]}
1091557
1092− data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"Hello"},"finish_reason":null}]}
558+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"fmt"}}]},"finish_reason":null}]}
1093559
1094− data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":","},"finish_reason":null}]}
560+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".Println"}}]},"finish_reason":null}]}
1095561
1096− data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" Crush"},"finish_reason":null}]}
562+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"(\\\"Hello"}}]},"finish_reason":null}]}
1097563
1098− data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"!\""},"finish_reason":null}]}
564+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":", Crush"}}]},"finish_reason":null}]}
1099565
1100− data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"`,"},"finish_reason":null}]}
566+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"!\\\")"}}]},"finish_reason":null}]}
1101567
1102− data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" so"},"finish_reason":null}]}
568+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\", \"old"}}]},"finish_reason":null}]}
1103569
1104− data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" the"},"finish_reason":null}]}
570+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_string\": \"\\"}}]},"finish_reason":null}]}
1105571
1106− data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" second"},"finish_reason":null}]}
572+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tf"}}]},"finish_reason":null}]}
1107573
1108− data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" edit"},"finish_reason":null}]}
574+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"mt"}}]},"finish_reason":null}]}
1109575
1110− data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"'s"},"finish_reason":null}]}
576+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".Println(\\\""}}]},"finish_reason":null}]}
1111577
1112− data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" `"},"finish_reason":null}]}
578+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Hello, World"}}]},"finish_reason":null}]}
1113579
1114− data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"old"},"finish_reason":null}]}
580+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"!\\\")"}}]},"finish_reason":null}]}
1115581
1116− data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"_string"},"finish_reason":null}]}
582+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"}]"}}]},"finish_reason":null}]}
1117583
1118− data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"`"},"finish_reason":null}]}
584+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":", "}}]},"finish_reason":null}]}
1119585
1120− data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" no"},"finish_reason":null}]}
586+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"file_path\": \"/tmp"}}]},"finish_reason":null}]}
1121587
1122− data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" longer"},"finish_reason":null}]}
588+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/c"}}]},"finish_reason":null}]}
1123589
1124− data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" matched"},"finish_reason":null}]}
590+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"rush"}}]},"finish_reason":null}]}
1125591
1126− data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"."},"finish_reason":null}]}
592+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}]}
1127593
1128− data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" Let"},"finish_reason":null}]}
594+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}]}
1129595
1130− data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" me"},"finish_reason":null}]}
596+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}]}
1131597
1132− data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" apply"},"finish_reason":null}]}
598+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent/g"}}]},"finish_reason":null}]}
1133599
1134− data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" the"},"finish_reason":null}]}
600+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"lm-"}}]},"finish_reason":null}]}
1135601
1136− data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" comment"},"finish_reason":null}]}
602+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5."}}]},"finish_reason":null}]}
1137603
1138− data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" edit"},"finish_reason":null}]}
604+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"1/m"}}]},"finish_reason":null}]}
1139605
1140− data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" now"},"finish_reason":null}]}
606+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ultied"}}]},"finish_reason":null}]}
1141607
1142− data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":":"},"finish_reason":null}]}
608+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"it"}}]},"finish_reason":null}]}
1143609
1144− data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_aa6adc90328a4e80befb2ab0","type":"function","index":0,"function":{"name":"edit","arguments":""}}]},"finish_reason":null}]}
610+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_tool/main"}}]},"finish_reason":null}]}
1145611
1146− data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\"file_path\":\"/tmp/crush-test/TestCoderAgent/glm-5.1/multiedit_tool/main.go\",\"new_string\":\"\\t// Greeting\\n\\tfmt.Println(\\\"Hello, Crush!\\\")\",\"old_string\":\"\\tfmt.Println(\\\"Hello, Crush!\\\")\"}"}}]},"finish_reason":null}]}
612+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".go\""}}]},"finish_reason":null}]}
1147613
1148− data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}]}
614+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}]}
1149615
1150− data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":146,"completion_tokens":100,"total_tokens":8182,"prompt_tokens_details":{"cached_tokens":7936}}}
616+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}]}
1151617
1152− data: [DONE]
1153−
1154− headers:
1155− Content-Type:
1156− - text/event-stream
1157− status: 200 OK
1158− code: 200
1159− duration: 5.362671667s
1160−- id: 5
1161− request:
1162− proto: HTTP/1.1
1163− proto_major: 1
1164− proto_minor: 1
1165− content_length: 36133
1166− host: ""
1167− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **READ BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default <4 lines), unless explaining complex changes or asked for detail. Conciseness applies to output only, not to thoroughness of work.\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks.\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\". When committing, follow the `<git_commits>` format from the bash tool description exactly, including any configured attribution lines.\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. Focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously.\\n10. **NO URL GUESSING**: Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **TOOL CONSTRAINTS**: Only use documented tools. Never attempt 'apply_patch' or 'apply_diff' - they don't exist. Use 'edit' or 'multiedit' instead.\\n14. **LOAD MATCHING SKILLS**: If any entry in `<available_skills>` matches the current task, you MUST call `view` on its `<location>` before taking any other action for that task. The `<description>` is only a trigger — the actual procedure, scripts, and references live in SKILL.md. Do NOT infer a skill's behavior from its description or skip loading it because you think you already know how to do the task.\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- ALWAYS think and respond in the same spoken language the prompt was written in.\\n- Under 4 lines of text (tool use doesn't count)\\n- Conciseness is about **text only**: always fully implement the requested feature, tests, and wiring even if that requires many tool calls.\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n- Never send acknowledgement-only responses; after receiving new context or instructions, immediately continue the task or state the concrete next action you will take.\\n- Use rich Markdown formatting (headings, bullet lists, tables, code fences) for any multi-sentence or explanatory answer; only use plain unformatted text if the user explicitly asks.\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n</communication_style>\\n\\n<code_references>\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n</code_references>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Cross-check the original prompt and your own mental checklist; if any feasible part remains undone, continue working instead of responding.\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n- When requirements are underspecified but not obviously dangerous, make the most reasonable assumptions based on project patterns and memory files, briefly state them if needed, and proceed instead of waiting for clarification.\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**When requesting information/access**:\\n- Exhaust all available tools, searches, and reasonable assumptions first.\\n- Never say \\\"Need more info\\\" without detail.\\n- In the same message, list each missing item, why it is required, acceptable substitutes, and what you already attempted.\\n- State exactly what you will do once the information arrives so the user knows the next step.\\n\\nWhen you must stop, first finish all unblocked parts of the request, then clearly report: (a) what you tried, (b) exactly why you are blocked, and (c) the minimal external action required. Don't stop just because one path failed—exhaust multiple plausible approaches first.\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\n**Available edit tools:**\\n- `edit` - Single find/replace in a file\\n- `multiedit` - Multiple find/replace operations in one file\\n- `write` - Create/overwrite entire file\\n\\nNever use `apply_patch` or similar - those tools don't exist.\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n</editing_files>\\n\\n<whitespace_and_exact_matching>\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n</whitespace_and_exact_matching>\\n\\n<task_completion>\\nEnsure every task is implemented completely, not partially or sketched.\\n\\n1. **Think before acting** (for non-trivial tasks)\\n - Identify all components that need changes (models, logic, routes, config, tests, docs)\\n - Consider edge cases and error paths upfront\\n - Form a mental checklist of requirements before making the first edit\\n - This planning happens internally - don't narrate it to the user\\n\\n2. **Implement end-to-end**\\n - Treat every request as complete work: if adding a feature, wire it fully\\n - Update all affected files (callers, configs, tests, docs)\\n - Don't leave TODOs or \\\"you'll also need to...\\\" - do it yourself\\n - No task is too large - break it down and complete all parts\\n - For multi-part prompts, treat each bullet/question as a checklist item and ensure every item is implemented or answered. Partial completion is not an acceptable final state.\\n\\n3. **Verify before finishing**\\n - Re-read the original request and verify each requirement is met\\n - Check for missing error handling, edge cases, or unwired code\\n - Run tests to confirm the implementation works\\n - Only say \\\"Done\\\" when truly done - never stop mid-task\\n</task_completion>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause (isolate with debug logs or minimal reproduction if needed)\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n7. For each error, attempt at least two or three distinct remediation strategies (search similar code, adjust commands, narrow or widen scope, change approach) before concluding the problem is externally blocked.\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences\\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n</testing>\\n\\n<tool_usage>\\n- Default to using tools (ls, grep, view, agent, tests, web_fetch, etc.) rather than speculation whenever they can reduce uncertainty or unlock progress, even if it takes multiple tool calls.\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n- Never use `curl` through the bash tool it is not allowed use the fetch tool instead.\\n- Only use the tools you know exist.\\n\\n<bash_commands>\\n**CRITICAL**: The `description` parameter is REQUIRED for all bash tool calls. Always provide it.\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n</bash_commands>\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When the user provides new information or clarification, incorporate it immediately and keep executing instead of stopping with an acknowledgement.\\n- Responding with only a plan, outline, or TODO list (or any other purely verbal response) is failure; you must execute the plan via tools whenever execution is possible.\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<final_answers>\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n- Structure longer answers with Markdown sections and lists, and put all code, commands, and config in fenced code blocks.\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n</final_answers>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/glm-5.1/multiedit_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n</env>\\n\\n\\n\\n<available_skills>\\n <skill>\\n <name>crush-hooks</name>\\n <description>Use when the user wants to add, write, debug, or configure a Crush hook — gating or blocking tool calls, approving or rewriting tool input before execution, injecting context into tool results, or troubleshooting hook behavior in crush.json.</description>\\n <location>crush://skills/crush-hooks/SKILL.md</location>\\n <type>builtin</type>\\n </skill>\\n <skill>\\n <name>jq</name>\\n <description>Use when the user needs to query, filter, reshape, extract, create, or construct JSON data — including API responses, config files, log output, or any structured data — or when helping the user write or debug JSON transformations.</description>\\n <location>crush://skills/jq/SKILL.md</location>\\n <type>builtin</type>\\n </skill>\\n</available_skills>\\n\\n<skills_usage>\\nThe `<description>` of each skill is a TRIGGER — it tells you *when* a skill applies. It is NOT a specification of what the skill does or how to do it. The procedure, scripts, commands, references, and required flags live only in the SKILL.md body. You do not know what a skill actually does until you have read its SKILL.md.\\n\\nMANDATORY activation flow:\\n1. Scan `<available_skills>` against the current user task.\\n2. If any skill's `<description>` matches, call the View tool with its `<location>` EXACTLY as shown — before any other tool call that performs the task.\\n3. Read the entire SKILL.md and follow its instructions.\\n4. Only then execute the task, using the skill's prescribed commands/tools.\\n\\nDo NOT skip step 2 because you think you already know how to do the task. Do NOT infer a skill's behavior from its name or description. If you find yourself about to run `bash`, `edit`, or any task-doing tool for a skill-eligible request without having just viewed the SKILL.md, stop and load the skill first.\\n\\nBuiltin skills (type=builtin) use virtual `crush://skills/...` location identifiers. The \\\"crush://\\\" prefix is NOT a URL, network address, or MCP resource — it is a special internal identifier the View tool understands natively. Pass the `<location>` verbatim to View.\\n\\nDo not use MCP tools (including read_mcp_resource) to load skills.\\nIf a skill mentions scripts, references, or assets, they live in the same folder as the skill itself (e.g., scripts/, references/, assets/ subdirectories within the skill's folder).\\n</skills_usage>\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"<system_reminder>This is a reminder that your todo list is currently empty. DO NOT mention this to the user explicitly because they are already aware.\\nIf you are working on tasks that would benefit from a todo list please use the \\\"todos\\\" tool to create one.\\nIf not, please feel free to ignore. Again do not mention this message to the user.</system_reminder>\",\"role\":\"user\"},{\"content\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_4d3da657d04f428c92d43f15\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/glm-5.1/multiedit_tool/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\",\"reasoning_content\":\"Let me first read the main.go file to see its current content.\"},{\"content\":\"<file>\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n</file>\\n\",\"tool_call_id\":\"call_4d3da657d04f428c92d43f15\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_24e7ffc678a64fc58e667545\",\"function\":{\"arguments\":\"{\\\"edits\\\":[{\\\"new_string\\\": \\\"Hello, Crush!\\\", \\\"old_string\\\": \\\"Hello, World!\\\"}, {\\\"new_string\\\": \\\"\\\\t// Greeting\\\\n\\\\tfmt.Println(\\\\\\\"Hello, Crush!\\\\\\\")\\\", \\\"old_string\\\": \\\"\\\\tfmt.Println(\\\\\\\"Hello, World!\\\\\\\")\\\"}],\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/glm-5.1/multiedit_tool/main.go\\\"}\",\"name\":\"multiedit\"},\"type\":\"function\"}],\"role\":\"assistant\",\"reasoning_content\":\"\"},{\"content\":\"<result>\\nApplied 1 of 2 edits to file: /tmp/crush-test/TestCoderAgent/glm-5.1/multiedit_tool/main.go (1 edit(s) failed)\\n</result>\\n\",\"tool_call_id\":\"call_24e7ffc678a64fc58e667545\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_9d4e62e2b4fb494b9d34f994\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/glm-5.1/multiedit_tool/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\",\"reasoning_content\":\"\"},{\"content\":\"<file>\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, Crush!\\\")\\n 7|}\\n</file>\\n\",\"tool_call_id\":\"call_9d4e62e2b4fb494b9d34f994\",\"role\":\"tool\"},{\"content\":\"The first edit changed `\\\"Hello, World!\\\"` to `\\\"Hello, Crush!\\\"`, so the second edit's `old_string` no longer matched. Let me apply the comment edit now:\",\"tool_calls\":[{\"id\":\"call_aa6adc90328a4e80befb2ab0\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/glm-5.1/multiedit_tool/main.go\\\",\\\"new_string\\\":\\\"\\\\t// Greeting\\\\n\\\\tfmt.Println(\\\\\\\"Hello, Crush!\\\\\\\")\\\",\\\"old_string\\\":\\\"\\\\tfmt.Println(\\\\\\\"Hello, Crush!\\\\\\\")\\\"}\",\"name\":\"edit\"},\"type\":\"function\"}],\"role\":\"assistant\",\"reasoning_content\":\"\"},{\"content\":\"<result>\\nContent replaced in file: /tmp/crush-test/TestCoderAgent/glm-5.1/multiedit_tool/main.go\\n</result>\\n\",\"tool_call_id\":\"call_aa6adc90328a4e80befb2ab0\",\"role\":\"tool\"}],\"model\":\"glm-5.1\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Execute shell commands; long-running commands automatically move to background and return a shell ID.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Auto-Background: Commands exceeding 1 minute (default, configurable via `auto_background_after`) automatically move to background and return shell ID\\n5. Output Processing: Truncate if exceeds 30000 characters\\n6. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, working_dir optional (defaults to current directory)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Each command runs in independent shell (no state persistence between calls)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<background_execution>\\n- Set run_in_background=true to run commands in a separate background shell\\n- Returns a shell ID for managing the background process\\n- Use job_output tool to view current output from background shell\\n- Use job_kill tool to terminate a background shell\\n- IMPORTANT: NEVER use `&` at the end of commands to run in background - use run_in_background parameter instead\\n- Commands that should run in background:\\n * Long-running servers (e.g., `npm start`, `python -m http.server`, `node server.js`)\\n * Watch/monitoring tasks (e.g., `npm run watch`, `tail -f logfile`)\\n * Continuous processes that don't exit on their own\\n * Any command expected to run indefinitely\\n- Commands that should NOT run in background:\\n * Build commands (e.g., `npm run build`, `go build`)\\n * Test suites (e.g., `npm test`, `pytest`)\\n * Git operations\\n * File operations\\n * Short-lived scripts\\n</background_execution>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"auto_background_after\":{\"description\":\"Seconds to wait before automatically moving the command to a background job (default: 60)\",\"type\":\"integer\"},\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does, try to keep it under 30 characters or so\",\"type\":\"string\"},\"run_in_background\":{\"description\":\"Set to true (boolean) to run this command in the background. Use job_output to read the output later.\",\"type\":\"boolean\"},\"working_dir\":{\"description\":\"The working directory to execute the command in (defaults to current directory)\",\"type\":\"string\"}},\"required\":[\"description\",\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Download a URL directly to a local file (binary-safe, streaming, max 100MB); overwrites without warning. For reading content into context use fetch.\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edit a file by exact find-and-replace; can also create or delete content. For renames/moves use bash. For large edits use write.\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Apply multiple find-and-replace edits to a single file in one operation; edits run sequentially. Prefer over edit for multiple changes to the same file. Same exact-match rules as edit apply.\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"properties\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"required\":[\"old_string\",\"new_string\"],\"type\":\"object\"},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetch raw content from a URL as text, markdown, or html (max 100KB); no AI processing. For analysis or extraction use agentic_fetch.\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Find files by name/pattern (glob syntax), sorted by modification time; max 100 results; skips hidden files. Use grep to search file contents.\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Search file contents by regex or literal text; returns matching file paths sorted by modification time (max 100); respects .gitignore. Use glob to filter by filename, not contents.\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"List files and directories as a tree; skips hidden files and common system dirs; max 1000 files. Use glob to find files by pattern, grep to search contents.\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{\"type\":\"string\"},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public GitHub repositories via Sourcegraph; supports regex, language/repo/file filters, and symbol search (max 20 results). Only searches public repos.\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Read a file by path with line numbers; supports offset and line limit (default 2000, max 200KB returned file content section); renders images (PNG, JPEG, GIF, WebP); use ls for directories.\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Create or overwrite a file with given content; auto-creates parent dirs. Cannot append. Read the file first to avoid conflicts. For surgical changes use edit or multiedit.\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"
1168− headers:
1169− Accept:
1170− - application/json
1171− Content-Type:
1172− - application/json
1173− User-Agent:
1174− - Charm-Crush/devel (https://charm.land/crush)
1175− url: https://hyper.charm.land/v1/chat/completions
1176− method: POST
1177− response:
1178− proto: HTTP/2.0
1179− proto_major: 2
1180− proto_minor: 0
1181− content_length: -1
1182− uncompressed: true
1183− body: |+
1184− data: {"id":"chatcmpl-865f0331bfb0dc0125e79faa","object":"chat.completion.chunk","created":1778531400,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
1185−
1186− data: {"id":"chatcmpl-865f0331bfb0dc0125e79faa","object":"chat.completion.chunk","created":1778531400,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_ca8435944b9f42279725cba9","type":"function","index":0,"function":{"name":"view","arguments":""}}]},"finish_reason":null}]}
1187−
1188− data: {"id":"chatcmpl-865f0331bfb0dc0125e79faa","object":"chat.completion.chunk","created":1778531400,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\"file_path\":\"/tmp/crush-test/TestCoderAgent/glm-5.1/multiedit_tool/main.go\"}"}}]},"finish_reason":null}]}
1189−
1190− data: {"id":"chatcmpl-865f0331bfb0dc0125e79faa","object":"chat.completion.chunk","created":1778531400,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}]}
1191−
1192− data: {"id":"chatcmpl-865f0331bfb0dc0125e79faa","object":"chat.completion.chunk","created":1778531400,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":155,"completion_tokens":31,"total_tokens":8250,"prompt_tokens_details":{"cached_tokens":8064}}}
618+ data: {"id":"chatcmpl-7b646eb6b9a029f931c804fd","object":"chat.completion.chunk","created":1778602959,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":843,"completion_tokens":76,"total_tokens":7959,"prompt_tokens_details":{"cached_tokens":7040},"completion_tokens_details":{"reasoning_tokens":75}}}
1193619
1194620 data: [DONE]
1195621
@@ -1198,15 +624,15 @@ interactions:
1198624 - text/event-stream
1199625 status: 200 OK
1200626 code: 200
1201− duration: 3.595254708s
1202−- id: 6
627+ duration: 3.67935125s
628+- id: 3
1203629 request:
1204630 proto: HTTP/1.1
1205631 proto_major: 1
1206632 proto_minor: 1
1207− content_length: 36622
633+ content_length: 34922
1208634 host: ""
1209− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **READ BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default <4 lines), unless explaining complex changes or asked for detail. Conciseness applies to output only, not to thoroughness of work.\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks.\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\". When committing, follow the `<git_commits>` format from the bash tool description exactly, including any configured attribution lines.\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. Focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously.\\n10. **NO URL GUESSING**: Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **TOOL CONSTRAINTS**: Only use documented tools. Never attempt 'apply_patch' or 'apply_diff' - they don't exist. Use 'edit' or 'multiedit' instead.\\n14. **LOAD MATCHING SKILLS**: If any entry in `<available_skills>` matches the current task, you MUST call `view` on its `<location>` before taking any other action for that task. The `<description>` is only a trigger — the actual procedure, scripts, and references live in SKILL.md. Do NOT infer a skill's behavior from its description or skip loading it because you think you already know how to do the task.\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- ALWAYS think and respond in the same spoken language the prompt was written in.\\n- Under 4 lines of text (tool use doesn't count)\\n- Conciseness is about **text only**: always fully implement the requested feature, tests, and wiring even if that requires many tool calls.\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n- Never send acknowledgement-only responses; after receiving new context or instructions, immediately continue the task or state the concrete next action you will take.\\n- Use rich Markdown formatting (headings, bullet lists, tables, code fences) for any multi-sentence or explanatory answer; only use plain unformatted text if the user explicitly asks.\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n</communication_style>\\n\\n<code_references>\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n</code_references>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Cross-check the original prompt and your own mental checklist; if any feasible part remains undone, continue working instead of responding.\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n- When requirements are underspecified but not obviously dangerous, make the most reasonable assumptions based on project patterns and memory files, briefly state them if needed, and proceed instead of waiting for clarification.\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**When requesting information/access**:\\n- Exhaust all available tools, searches, and reasonable assumptions first.\\n- Never say \\\"Need more info\\\" without detail.\\n- In the same message, list each missing item, why it is required, acceptable substitutes, and what you already attempted.\\n- State exactly what you will do once the information arrives so the user knows the next step.\\n\\nWhen you must stop, first finish all unblocked parts of the request, then clearly report: (a) what you tried, (b) exactly why you are blocked, and (c) the minimal external action required. Don't stop just because one path failed—exhaust multiple plausible approaches first.\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\n**Available edit tools:**\\n- `edit` - Single find/replace in a file\\n- `multiedit` - Multiple find/replace operations in one file\\n- `write` - Create/overwrite entire file\\n\\nNever use `apply_patch` or similar - those tools don't exist.\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n</editing_files>\\n\\n<whitespace_and_exact_matching>\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n</whitespace_and_exact_matching>\\n\\n<task_completion>\\nEnsure every task is implemented completely, not partially or sketched.\\n\\n1. **Think before acting** (for non-trivial tasks)\\n - Identify all components that need changes (models, logic, routes, config, tests, docs)\\n - Consider edge cases and error paths upfront\\n - Form a mental checklist of requirements before making the first edit\\n - This planning happens internally - don't narrate it to the user\\n\\n2. **Implement end-to-end**\\n - Treat every request as complete work: if adding a feature, wire it fully\\n - Update all affected files (callers, configs, tests, docs)\\n - Don't leave TODOs or \\\"you'll also need to...\\\" - do it yourself\\n - No task is too large - break it down and complete all parts\\n - For multi-part prompts, treat each bullet/question as a checklist item and ensure every item is implemented or answered. Partial completion is not an acceptable final state.\\n\\n3. **Verify before finishing**\\n - Re-read the original request and verify each requirement is met\\n - Check for missing error handling, edge cases, or unwired code\\n - Run tests to confirm the implementation works\\n - Only say \\\"Done\\\" when truly done - never stop mid-task\\n</task_completion>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause (isolate with debug logs or minimal reproduction if needed)\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n7. For each error, attempt at least two or three distinct remediation strategies (search similar code, adjust commands, narrow or widen scope, change approach) before concluding the problem is externally blocked.\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences\\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n</testing>\\n\\n<tool_usage>\\n- Default to using tools (ls, grep, view, agent, tests, web_fetch, etc.) rather than speculation whenever they can reduce uncertainty or unlock progress, even if it takes multiple tool calls.\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n- Never use `curl` through the bash tool it is not allowed use the fetch tool instead.\\n- Only use the tools you know exist.\\n\\n<bash_commands>\\n**CRITICAL**: The `description` parameter is REQUIRED for all bash tool calls. Always provide it.\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n</bash_commands>\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When the user provides new information or clarification, incorporate it immediately and keep executing instead of stopping with an acknowledgement.\\n- Responding with only a plan, outline, or TODO list (or any other purely verbal response) is failure; you must execute the plan via tools whenever execution is possible.\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<final_answers>\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n- Structure longer answers with Markdown sections and lists, and put all code, commands, and config in fenced code blocks.\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n</final_answers>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/glm-5.1/multiedit_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n</env>\\n\\n\\n\\n<available_skills>\\n <skill>\\n <name>crush-hooks</name>\\n <description>Use when the user wants to add, write, debug, or configure a Crush hook — gating or blocking tool calls, approving or rewriting tool input before execution, injecting context into tool results, or troubleshooting hook behavior in crush.json.</description>\\n <location>crush://skills/crush-hooks/SKILL.md</location>\\n <type>builtin</type>\\n </skill>\\n <skill>\\n <name>jq</name>\\n <description>Use when the user needs to query, filter, reshape, extract, create, or construct JSON data — including API responses, config files, log output, or any structured data — or when helping the user write or debug JSON transformations.</description>\\n <location>crush://skills/jq/SKILL.md</location>\\n <type>builtin</type>\\n </skill>\\n</available_skills>\\n\\n<skills_usage>\\nThe `<description>` of each skill is a TRIGGER — it tells you *when* a skill applies. It is NOT a specification of what the skill does or how to do it. The procedure, scripts, commands, references, and required flags live only in the SKILL.md body. You do not know what a skill actually does until you have read its SKILL.md.\\n\\nMANDATORY activation flow:\\n1. Scan `<available_skills>` against the current user task.\\n2. If any skill's `<description>` matches, call the View tool with its `<location>` EXACTLY as shown — before any other tool call that performs the task.\\n3. Read the entire SKILL.md and follow its instructions.\\n4. Only then execute the task, using the skill's prescribed commands/tools.\\n\\nDo NOT skip step 2 because you think you already know how to do the task. Do NOT infer a skill's behavior from its name or description. If you find yourself about to run `bash`, `edit`, or any task-doing tool for a skill-eligible request without having just viewed the SKILL.md, stop and load the skill first.\\n\\nBuiltin skills (type=builtin) use virtual `crush://skills/...` location identifiers. The \\\"crush://\\\" prefix is NOT a URL, network address, or MCP resource — it is a special internal identifier the View tool understands natively. Pass the `<location>` verbatim to View.\\n\\nDo not use MCP tools (including read_mcp_resource) to load skills.\\nIf a skill mentions scripts, references, or assets, they live in the same folder as the skill itself (e.g., scripts/, references/, assets/ subdirectories within the skill's folder).\\n</skills_usage>\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"<system_reminder>This is a reminder that your todo list is currently empty. DO NOT mention this to the user explicitly because they are already aware.\\nIf you are working on tasks that would benefit from a todo list please use the \\\"todos\\\" tool to create one.\\nIf not, please feel free to ignore. Again do not mention this message to the user.</system_reminder>\",\"role\":\"user\"},{\"content\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_4d3da657d04f428c92d43f15\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/glm-5.1/multiedit_tool/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\",\"reasoning_content\":\"Let me first read the main.go file to see its current content.\"},{\"content\":\"<file>\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n</file>\\n\",\"tool_call_id\":\"call_4d3da657d04f428c92d43f15\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_24e7ffc678a64fc58e667545\",\"function\":{\"arguments\":\"{\\\"edits\\\":[{\\\"new_string\\\": \\\"Hello, Crush!\\\", \\\"old_string\\\": \\\"Hello, World!\\\"}, {\\\"new_string\\\": \\\"\\\\t// Greeting\\\\n\\\\tfmt.Println(\\\\\\\"Hello, Crush!\\\\\\\")\\\", \\\"old_string\\\": \\\"\\\\tfmt.Println(\\\\\\\"Hello, World!\\\\\\\")\\\"}],\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/glm-5.1/multiedit_tool/main.go\\\"}\",\"name\":\"multiedit\"},\"type\":\"function\"}],\"role\":\"assistant\",\"reasoning_content\":\"\"},{\"content\":\"<result>\\nApplied 1 of 2 edits to file: /tmp/crush-test/TestCoderAgent/glm-5.1/multiedit_tool/main.go (1 edit(s) failed)\\n</result>\\n\",\"tool_call_id\":\"call_24e7ffc678a64fc58e667545\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_9d4e62e2b4fb494b9d34f994\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/glm-5.1/multiedit_tool/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\",\"reasoning_content\":\"\"},{\"content\":\"<file>\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, Crush!\\\")\\n 7|}\\n</file>\\n\",\"tool_call_id\":\"call_9d4e62e2b4fb494b9d34f994\",\"role\":\"tool\"},{\"content\":\"The first edit changed `\\\"Hello, World!\\\"` to `\\\"Hello, Crush!\\\"`, so the second edit's `old_string` no longer matched. Let me apply the comment edit now:\",\"tool_calls\":[{\"id\":\"call_aa6adc90328a4e80befb2ab0\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/glm-5.1/multiedit_tool/main.go\\\",\\\"new_string\\\":\\\"\\\\t// Greeting\\\\n\\\\tfmt.Println(\\\\\\\"Hello, Crush!\\\\\\\")\\\",\\\"old_string\\\":\\\"\\\\tfmt.Println(\\\\\\\"Hello, Crush!\\\\\\\")\\\"}\",\"name\":\"edit\"},\"type\":\"function\"}],\"role\":\"assistant\",\"reasoning_content\":\"\"},{\"content\":\"<result>\\nContent replaced in file: /tmp/crush-test/TestCoderAgent/glm-5.1/multiedit_tool/main.go\\n</result>\\n\",\"tool_call_id\":\"call_aa6adc90328a4e80befb2ab0\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_ca8435944b9f42279725cba9\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/glm-5.1/multiedit_tool/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\",\"reasoning_content\":\"\"},{\"content\":\"<file>\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\t// Greeting\\n 7|\\tfmt.Println(\\\"Hello, Crush!\\\")\\n 8|}\\n</file>\\n\",\"tool_call_id\":\"call_ca8435944b9f42279725cba9\",\"role\":\"tool\"}],\"model\":\"glm-5.1\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Execute shell commands; long-running commands automatically move to background and return a shell ID.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Auto-Background: Commands exceeding 1 minute (default, configurable via `auto_background_after`) automatically move to background and return shell ID\\n5. Output Processing: Truncate if exceeds 30000 characters\\n6. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, working_dir optional (defaults to current directory)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Each command runs in independent shell (no state persistence between calls)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<background_execution>\\n- Set run_in_background=true to run commands in a separate background shell\\n- Returns a shell ID for managing the background process\\n- Use job_output tool to view current output from background shell\\n- Use job_kill tool to terminate a background shell\\n- IMPORTANT: NEVER use `&` at the end of commands to run in background - use run_in_background parameter instead\\n- Commands that should run in background:\\n * Long-running servers (e.g., `npm start`, `python -m http.server`, `node server.js`)\\n * Watch/monitoring tasks (e.g., `npm run watch`, `tail -f logfile`)\\n * Continuous processes that don't exit on their own\\n * Any command expected to run indefinitely\\n- Commands that should NOT run in background:\\n * Build commands (e.g., `npm run build`, `go build`)\\n * Test suites (e.g., `npm test`, `pytest`)\\n * Git operations\\n * File operations\\n * Short-lived scripts\\n</background_execution>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"auto_background_after\":{\"description\":\"Seconds to wait before automatically moving the command to a background job (default: 60)\",\"type\":\"integer\"},\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does, try to keep it under 30 characters or so\",\"type\":\"string\"},\"run_in_background\":{\"description\":\"Set to true (boolean) to run this command in the background. Use job_output to read the output later.\",\"type\":\"boolean\"},\"working_dir\":{\"description\":\"The working directory to execute the command in (defaults to current directory)\",\"type\":\"string\"}},\"required\":[\"description\",\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Download a URL directly to a local file (binary-safe, streaming, max 100MB); overwrites without warning. For reading content into context use fetch.\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edit a file by exact find-and-replace; can also create or delete content. For renames/moves use bash. For large edits use write.\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Apply multiple find-and-replace edits to a single file in one operation; edits run sequentially. Prefer over edit for multiple changes to the same file. Same exact-match rules as edit apply.\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"properties\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"required\":[\"old_string\",\"new_string\"],\"type\":\"object\"},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetch raw content from a URL as text, markdown, or html (max 100KB); no AI processing. For analysis or extraction use agentic_fetch.\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Find files by name/pattern (glob syntax), sorted by modification time; max 100 results; skips hidden files. Use grep to search file contents.\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Search file contents by regex or literal text; returns matching file paths sorted by modification time (max 100); respects .gitignore. Use glob to filter by filename, not contents.\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"List files and directories as a tree; skips hidden files and common system dirs; max 1000 files. Use glob to find files by pattern, grep to search contents.\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{\"type\":\"string\"},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public GitHub repositories via Sourcegraph; supports regex, language/repo/file filters, and symbol search (max 20 results). Only searches public repos.\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Read a file by path with line numbers; supports offset and line limit (default 2000, max 200KB returned file content section); renders images (PNG, JPEG, GIF, WebP); use ls for directories.\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Create or overwrite a file with given content; auto-creates parent dirs. Cannot append. Read the file first to avoid conflicts. For surgical changes use edit or multiedit.\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"
635+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **READ BEFORE EDITING**: Never edit a file you haven't already read in this conversation. Once read, you don't need to re-read unless it changed. Pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, think, decide, act. Break complex tasks into steps and complete them all. Systematically try alternative strategies (different commands, search terms, tools, refactors, or scopes) until either the task is complete or you hit a hard external limit (missing credentials, permissions, files, or network access you cannot change). Only stop for actual blocking errors, not perceived difficulty.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification.\\n4. **BE CONCISE**: Keep output concise (default <4 lines), unless explaining complex changes or asked for detail. Conciseness applies to output only, not to thoroughness of work.\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks.\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\". When committing, follow the `<git_commits>` format from the bash tool description exactly, including any configured attribution lines.\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. Focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously.\\n10. **NO URL GUESSING**: Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **TOOL CONSTRAINTS**: Only use documented tools. Never attempt 'apply_patch' or 'apply_diff' - they don't exist. Use 'edit' or 'multiedit' instead.\\n14. **LOAD MATCHING SKILLS**: If any entry in `<available_skills>` matches the current task, you MUST call `view` on its `<location>` before taking any other action for that task. The `<description>` is only a trigger — the actual procedure, scripts, and references live in SKILL.md. Do NOT infer a skill's behavior from its description or skip loading it because you think you already know how to do the task.\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- ALWAYS think and respond in the same spoken language the prompt was written in.\\n- Under 4 lines of text (tool use doesn't count)\\n- Conciseness is about **text only**: always fully implement the requested feature, tests, and wiring even if that requires many tool calls.\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n- Never send acknowledgement-only responses; after receiving new context or instructions, immediately continue the task or state the concrete next action you will take.\\n- Use rich Markdown formatting (headings, bullet lists, tables, code fences) for any multi-sentence or explanatory answer; only use plain unformatted text if the user explicitly asks.\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n</communication_style>\\n\\n<code_references>\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n</code_references>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Cross-check the original prompt and your own mental checklist; if any feasible part remains undone, continue working instead of responding.\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n- When requirements are underspecified but not obviously dangerous, make the most reasonable assumptions based on project patterns and memory files, briefly state them if needed, and proceed instead of waiting for clarification.\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**When requesting information/access**:\\n- Exhaust all available tools, searches, and reasonable assumptions first.\\n- Never say \\\"Need more info\\\" without detail.\\n- In the same message, list each missing item, why it is required, acceptable substitutes, and what you already attempted.\\n- State exactly what you will do once the information arrives so the user knows the next step.\\n\\nWhen you must stop, first finish all unblocked parts of the request, then clearly report: (a) what you tried, (b) exactly why you are blocked, and (c) the minimal external action required. Don't stop just because one path failed—exhaust multiple plausible approaches first.\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\n**Available edit tools:**\\n- `edit` - Single find/replace in a file\\n- `multiedit` - Multiple find/replace operations in one file\\n- `write` - Create/overwrite entire file\\n\\nNever use `apply_patch` or similar - those tools don't exist.\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n</editing_files>\\n\\n<whitespace_and_exact_matching>\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n</whitespace_and_exact_matching>\\n\\n<task_completion>\\nEnsure every task is implemented completely, not partially or sketched.\\n\\n1. **Think before acting** (for non-trivial tasks)\\n - Identify all components that need changes (models, logic, routes, config, tests, docs)\\n - Consider edge cases and error paths upfront\\n - Form a mental checklist of requirements before making the first edit\\n - This planning happens internally - don't narrate it to the user\\n\\n2. **Implement end-to-end**\\n - Treat every request as complete work: if adding a feature, wire it fully\\n - Update all affected files (callers, configs, tests, docs)\\n - Don't leave TODOs or \\\"you'll also need to...\\\" - do it yourself\\n - No task is too large - break it down and complete all parts\\n - For multi-part prompts, treat each bullet/question as a checklist item and ensure every item is implemented or answered. Partial completion is not an acceptable final state.\\n\\n3. **Verify before finishing**\\n - Re-read the original request and verify each requirement is met\\n - Check for missing error handling, edge cases, or unwired code\\n - Run tests to confirm the implementation works\\n - Only say \\\"Done\\\" when truly done - never stop mid-task\\n</task_completion>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause (isolate with debug logs or minimal reproduction if needed)\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n7. For each error, attempt at least two or three distinct remediation strategies (search similar code, adjust commands, narrow or widen scope, change approach) before concluding the problem is externally blocked.\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences\\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n</testing>\\n\\n<tool_usage>\\n- Default to using tools (ls, grep, view, agent, tests, web_fetch, etc.) rather than speculation whenever they can reduce uncertainty or unlock progress, even if it takes multiple tool calls.\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n- Never use `curl` through the bash tool it is not allowed use the fetch tool instead.\\n- Only use the tools you know exist.\\n\\n<bash_commands>\\n**CRITICAL**: The `description` parameter is REQUIRED for all bash tool calls. Always provide it.\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n</bash_commands>\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When the user provides new information or clarification, incorporate it immediately and keep executing instead of stopping with an acknowledgement.\\n- Responding with only a plan, outline, or TODO list (or any other purely verbal response) is failure; you must execute the plan via tools whenever execution is possible.\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<final_answers>\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n- Structure longer answers with Markdown sections and lists, and put all code, commands, and config in fenced code blocks.\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n</final_answers>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/glm-5.1/multiedit_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n</env>\\n\\n\\n\\n<available_skills>\\n <skill>\\n <name>crush-hooks</name>\\n <description>Use when the user wants to add, write, debug, or configure a Crush hook — gating or blocking tool calls, approving or rewriting tool input before execution, injecting context into tool results, or troubleshooting hook behavior in crush.json.</description>\\n <location>crush://skills/crush-hooks/SKILL.md</location>\\n <type>builtin</type>\\n </skill>\\n <skill>\\n <name>jq</name>\\n <description>Use when the user needs to query, filter, reshape, extract, create, or construct JSON data — including API responses, config files, log output, or any structured data — or when helping the user write or debug JSON transformations.</description>\\n <location>crush://skills/jq/SKILL.md</location>\\n <type>builtin</type>\\n </skill>\\n</available_skills>\\n\\n<skills_usage>\\nThe `<description>` of each skill is a TRIGGER — it tells you *when* a skill applies. It is NOT a specification of what the skill does or how to do it. The procedure, scripts, commands, references, and required flags live only in the SKILL.md body. You do not know what a skill actually does until you have read its SKILL.md.\\n\\nMANDATORY activation flow:\\n1. Scan `<available_skills>` against the current user task.\\n2. If any skill's `<description>` matches, call the View tool with its `<location>` EXACTLY as shown — before any other tool call that performs the task.\\n3. Read the entire SKILL.md and follow its instructions.\\n4. Only then execute the task, using the skill's prescribed commands/tools.\\n\\nDo NOT skip step 2 because you think you already know how to do the task. Do NOT infer a skill's behavior from its name or description. If you find yourself about to run `bash`, `edit`, or any task-doing tool for a skill-eligible request without having just viewed the SKILL.md, stop and load the skill first.\\n\\nBuiltin skills (type=builtin) use virtual `crush://skills/...` location identifiers. The \\\"crush://\\\" prefix is NOT a URL, network address, or MCP resource — it is a special internal identifier the View tool understands natively. Pass the `<location>` verbatim to View.\\n\\nDo not use MCP tools (including read_mcp_resource) to load skills.\\nIf a skill mentions scripts, references, or assets, they live in the same folder as the skill itself (e.g., scripts/, references/, assets/ subdirectories within the skill's folder).\\n</skills_usage>\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"<system_reminder>This is a reminder that your todo list is currently empty. DO NOT mention this to the user explicitly because they are already aware.\\nIf you are working on tasks that would benefit from a todo list please use the \\\"todos\\\" tool to create one.\\nIf not, please feel free to ignore. Again do not mention this message to the user.</system_reminder>\",\"role\":\"user\"},{\"content\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_fc1d5e25b1c14cb68be5d476\",\"function\":{\"arguments\":\"{\\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/glm-5.1/multiedit_tool/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\",\"reasoning_content\":\"Let me first read the file to see its current contents.\"},{\"content\":\"<file>\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n 8|\\n</file>\\n\",\"tool_call_id\":\"call_fc1d5e25b1c14cb68be5d476\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_9dfbb4b9cd7a4af3881b997b\",\"function\":{\"arguments\":\"{\\\"edits\\\": [{\\\"new_string\\\": \\\"\\\\t// Greeting\\\\n\\\\tfmt.Println(\\\\\\\"Hello, Crush!\\\\\\\")\\\", \\\"old_string\\\": \\\"\\\\tfmt.Println(\\\\\\\"Hello, World!\\\\\\\")\\\"}], \\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/glm-5.1/multiedit_tool/main.go\\\"}\",\"name\":\"multiedit\"},\"type\":\"function\"}],\"role\":\"assistant\",\"reasoning_content\":\"\"},{\"content\":\"<result>\\nApplied 1 edits to file: /tmp/crush-test/TestCoderAgent/glm-5.1/multiedit_tool/main.go\\n</result>\\n\",\"tool_call_id\":\"call_9dfbb4b9cd7a4af3881b997b\",\"role\":\"tool\"}],\"model\":\"glm-5.1\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Execute shell commands; long-running commands automatically move to background and return a shell ID.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Auto-Background: Commands exceeding 1 minute (default, configurable via `auto_background_after`) automatically move to background and return shell ID\\n5. Output Processing: Truncate if exceeds 30000 characters\\n6. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, working_dir optional (defaults to current directory)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Each command runs in independent shell (no state persistence between calls)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<background_execution>\\n- Set run_in_background=true to run commands in a separate background shell\\n- Returns a shell ID for managing the background process\\n- Use job_output tool to view current output from background shell\\n- Use job_kill tool to terminate a background shell\\n- IMPORTANT: NEVER use `&` at the end of commands to run in background - use run_in_background parameter instead\\n- Commands that should run in background:\\n * Long-running servers (e.g., `npm start`, `python -m http.server`, `node server.js`)\\n * Watch/monitoring tasks (e.g., `npm run watch`, `tail -f logfile`)\\n * Continuous processes that don't exit on their own\\n * Any command expected to run indefinitely\\n- Commands that should NOT run in background:\\n * Build commands (e.g., `npm run build`, `go build`)\\n * Test suites (e.g., `npm test`, `pytest`)\\n * Git operations\\n * File operations\\n * Short-lived scripts\\n</background_execution>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with attribution using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response, when rebasing always use -m or GIT_EDITOR=true.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"auto_background_after\":{\"description\":\"Seconds to wait before automatically moving the command to a background job (default: 60)\",\"type\":\"integer\"},\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does, try to keep it under 30 characters or so\",\"type\":\"string\"},\"run_in_background\":{\"description\":\"Set to true (boolean) to run this command in the background. Use job_output to read the output later.\",\"type\":\"boolean\"},\"working_dir\":{\"description\":\"The working directory to execute the command in (defaults to current directory)\",\"type\":\"string\"}},\"required\":[\"description\",\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Download a URL directly to a local file (binary-safe, streaming, max 600s timeout); overwrites without warning. For reading content into context use fetch.\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edit a file by exact find-and-replace; can also create or delete content. For renames/moves use bash. For large edits use write.\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Apply multiple find-and-replace edits to a single file in one operation; edits run sequentially. Prefer over edit for multiple changes to the same file. Same exact-match rules as edit apply.\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"properties\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"required\":[\"old_string\",\"new_string\"],\"type\":\"object\"},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetch raw content from a URL as text, markdown, or html (max 100KB); no AI processing. For analysis or extraction use agentic_fetch.\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Find files by name/pattern (glob syntax), sorted by modification time; max 100 results; skips hidden files. Use grep to search file contents.\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Search file contents by regex or literal text; returns matching file paths sorted by modification time (max 100); respects .gitignore. Use glob to filter by filename, not contents.\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"List files and directories as a tree; skips hidden files and common system dirs; max 1000 files. Use glob to find files by pattern, grep to search contents.\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{\"type\":\"string\"},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public GitHub repositories via Sourcegraph; supports regex, language/repo/file filters, and symbol search (max 20 results). Only searches public repos.\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Read a file by path with line numbers; supports offset and line limit (default 2000, max 200KB returned file content section); renders images (PNG, JPEG, GIF, WebP); use ls for directories.\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Create or overwrite a file with given content; auto-creates parent dirs. Cannot append. Read the file first to avoid conflicts. For surgical changes use edit or multiedit.\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"
1210636 headers:
1211637 Accept:
1212638 - application/json
@@ -1223,123 +649,53 @@ interactions:
1223649 content_length: -1
1224650 uncompressed: true
1225651 body: |+
1226− data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
1227−
1228− data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"Done"},"finish_reason":null}]}
1229−
1230− data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"."},"finish_reason":null}]}
1231−
1232− data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" The"},"finish_reason":null}]}
1233−
1234− data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" mult"},"finish_reason":null}]}
1235−
1236− data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"ied"},"finish_reason":null}]}
1237−
1238− data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"it"},"finish_reason":null}]}
1239−
1240− data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" applied"},"finish_reason":null}]}
1241−
1242− data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" the"},"finish_reason":null}]}
1243−
1244− data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" string"},"finish_reason":null}]}
1245−
1246− data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" change"},"finish_reason":null}]}
1247−
1248− data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" first"},"finish_reason":null}]}
1249−
1250− data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":","},"finish_reason":null}]}
1251−
1252− data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" which"},"finish_reason":null}]}
1253−
1254− data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" made"},"finish_reason":null}]}
1255−
1256− data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" the"},"finish_reason":null}]}
1257−
1258− data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" second"},"finish_reason":null}]}
1259−
1260− data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" edit"},"finish_reason":null}]}
1261−
1262− data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"'s"},"finish_reason":null}]}
1263−
1264− data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" `"},"finish_reason":null}]}
1265−
1266− data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"old"},"finish_reason":null}]}
1267−
1268− data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"_string"},"finish_reason":null}]}
1269−
1270− data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"`"},"finish_reason":null}]}
1271−
1272− data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" stale"},"finish_reason":null}]}
1273−
1274− data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"."},"finish_reason":null}]}
1275−
1276− data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" Applied"},"finish_reason":null}]}
1277−
1278− data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" the"},"finish_reason":null}]}
1279−
1280− data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" comment"},"finish_reason":null}]}
1281−
1282− data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" via"},"finish_reason":null}]}
1283−
1284− data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" a"},"finish_reason":null}]}
1285−
1286− data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" separate"},"finish_reason":null}]}
1287−
1288− data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" edit"},"finish_reason":null}]}
1289−
1290− data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"."},"finish_reason":null}]}
1291−
1292− data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" Final"},"finish_reason":null}]}
1293−
1294− data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" result"},"finish_reason":null}]}
1295−
1296− data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":":\n\n"},"finish_reason":null}]}
652+ data: {"id":"chatcmpl-ad4340fd5b70ab18706e377d","object":"chat.completion.chunk","created":1778602963,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
1297653
1298− data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"```"},"finish_reason":null}]}
654+ data: {"id":"chatcmpl-ad4340fd5b70ab18706e377d","object":"chat.completion.chunk","created":1778602963,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"Both"},"finish_reason":null}]}
1299655
1300− data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"go"},"finish_reason":null}]}
656+ data: {"id":"chatcmpl-ad4340fd5b70ab18706e377d","object":"chat.completion.chunk","created":1778602963,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" changes applied"},"finish_reason":null}]}
1301657
1302− data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"\n"},"finish_reason":null}]}
658+ data: {"id":"chatcmpl-ad4340fd5b70ab18706e377d","object":"chat.completion.chunk","created":1778602963,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" in a"},"finish_reason":null}]}
1303659
1304− data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"func"},"finish_reason":null}]}
660+ data: {"id":"chatcmpl-ad4340fd5b70ab18706e377d","object":"chat.completion.chunk","created":1778602963,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" single mult"},"finish_reason":null}]}
1305661
1306− data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" main"},"finish_reason":null}]}
662+ data: {"id":"chatcmpl-ad4340fd5b70ab18706e377d","object":"chat.completion.chunk","created":1778602963,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"ied"},"finish_reason":null}]}
1307663
1308− data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"()"},"finish_reason":null}]}
664+ data: {"id":"chatcmpl-ad4340fd5b70ab18706e377d","object":"chat.completion.chunk","created":1778602963,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"it"},"finish_reason":null}]}
1309665
1310− data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" {\n"},"finish_reason":null}]}
666+ data: {"id":"chatcmpl-ad4340fd5b70ab18706e377d","object":"chat.completion.chunk","created":1778602963,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":":\n\n"},"finish_reason":null}]}
1311667
1312− data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"\t"},"finish_reason":null}]}
668+ data: {"id":"chatcmpl-ad4340fd5b70ab18706e377d","object":"chat.completion.chunk","created":1778602963,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"- `\""},"finish_reason":null}]}
1313669
1314− data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"//"},"finish_reason":null}]}
670+ data: {"id":"chatcmpl-ad4340fd5b70ab18706e377d","object":"chat.completion.chunk","created":1778602963,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"Hello"},"finish_reason":null}]}
1315671
1316− data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" G"},"finish_reason":null}]}
672+ data: {"id":"chatcmpl-ad4340fd5b70ab18706e377d","object":"chat.completion.chunk","created":1778602963,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":", World"},"finish_reason":null}]}
1317673
1318− data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"reeting"},"finish_reason":null}]}
674+ data: {"id":"chatcmpl-ad4340fd5b70ab18706e377d","object":"chat.completion.chunk","created":1778602963,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"!\"`"},"finish_reason":null}]}
1319675
1320− data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"\n"},"finish_reason":null}]}
676+ data: {"id":"chatcmpl-ad4340fd5b70ab18706e377d","object":"chat.completion.chunk","created":1778602963,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" → `\""},"finish_reason":null}]}
1321677
1322− data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"\tfmt"},"finish_reason":null}]}
678+ data: {"id":"chatcmpl-ad4340fd5b70ab18706e377d","object":"chat.completion.chunk","created":1778602963,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"Hello, Crush"},"finish_reason":null}]}
1323679
1324− data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":".Println"},"finish_reason":null}]}
680+ data: {"id":"chatcmpl-ad4340fd5b70ab18706e377d","object":"chat.completion.chunk","created":1778602963,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"!\"`\n- Added"},"finish_reason":null}]}
1325681
1326− data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"(\""},"finish_reason":null}]}
682+ data: {"id":"chatcmpl-ad4340fd5b70ab18706e377d","object":"chat.completion.chunk","created":1778602963,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" `//"},"finish_reason":null}]}
1327683
1328− data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"Hello"},"finish_reason":null}]}
684+ data: {"id":"chatcmpl-ad4340fd5b70ab18706e377d","object":"chat.completion.chunk","created":1778602963,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" G"},"finish_reason":null}]}
1329685
1330− data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":","},"finish_reason":null}]}
686+ data: {"id":"chatcmpl-ad4340fd5b70ab18706e377d","object":"chat.completion.chunk","created":1778602963,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"reeting"},"finish_reason":null}]}
1331687
1332− data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" Crush"},"finish_reason":null}]}
688+ data: {"id":"chatcmpl-ad4340fd5b70ab18706e377d","object":"chat.completion.chunk","created":1778602963,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"` comment"},"finish_reason":null}]}
1333689
1334− data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"!\")\n"},"finish_reason":null}]}
690+ data: {"id":"chatcmpl-ad4340fd5b70ab18706e377d","object":"chat.completion.chunk","created":1778602963,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" above `"},"finish_reason":null}]}
1335691
1336− data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"}\n"},"finish_reason":null}]}
692+ data: {"id":"chatcmpl-ad4340fd5b70ab18706e377d","object":"chat.completion.chunk","created":1778602963,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"fmt.Println"},"finish_reason":null}]}
1337693
1338− data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"```"},"finish_reason":null}]}
694+ data: {"id":"chatcmpl-ad4340fd5b70ab18706e377d","object":"chat.completion.chunk","created":1778602963,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"`"},"finish_reason":null}]}
1339695
1340− data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
696+ data: {"id":"chatcmpl-ad4340fd5b70ab18706e377d","object":"chat.completion.chunk","created":1778602963,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
1341697
1342− data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":123,"completion_tokens":58,"total_tokens":8373,"prompt_tokens_details":{"cached_tokens":8192}}}
698+ data: {"id":"chatcmpl-ad4340fd5b70ab18706e377d","object":"chat.completion.chunk","created":1778602963,"model":"glm-5.1","choices":[],"usage":{"prompt_tokens":126,"completion_tokens":39,"total_tokens":8037,"prompt_tokens_details":{"cached_tokens":7872},"completion_tokens_details":{"reasoning_tokens":38}}}
1343699
1344700 data: [DONE]
1345701
@@ -1348,4 +704,4 @@ interactions:
1348704 - text/event-stream
1349705 status: 200 OK
1350706 code: 200
1351− duration: 4.720450833s
707+ duration: 2.673102083s