@@ -6,9 +6,9 @@ interactions:
66 proto: HTTP/1.1
77 proto_major: 1
88 proto_minor: 1
9− content_length: 33721
9+ content_length: 33741
1010 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); renders images (PNG, JPEG, GIF, BMP, SVG, 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}"
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}"
1212 headers:
1313 Accept:
1414 - application/json
@@ -25,41 +25,43 @@ interactions:
2525 content_length: -1
2626 uncompressed: true
2727 body: |+
28− data: {"id":"chatcmpl-54dc2649ab88ccb894885824","object":"chat.completion.chunk","created":0,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
28+ data: {"id":"chatcmpl-d599cbede586f295273bd5fe","object":"chat.completion.chunk","created":1778531382,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
2929
30− data: {"id":"chatcmpl-54dc2649ab88ccb894885824","object":"chat.completion.chunk","created":0,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"Let"},"finish_reason":null}]}
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}]}
3131
32− data: {"id":"chatcmpl-54dc2649ab88ccb894885824","object":"chat.completion.chunk","created":0,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" me"},"finish_reason":null}]}
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}]}
3333
34− data: {"id":"chatcmpl-54dc2649ab88ccb894885824","object":"chat.completion.chunk","created":0,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" first"},"finish_reason":null}]}
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}]}
3535
36− data: {"id":"chatcmpl-54dc2649ab88ccb894885824","object":"chat.completion.chunk","created":0,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" read"},"finish_reason":null}]}
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}]}
3737
38− data: {"id":"chatcmpl-54dc2649ab88ccb894885824","object":"chat.completion.chunk","created":0,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" the"},"finish_reason":null}]}
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}]}
3939
40− data: {"id":"chatcmpl-54dc2649ab88ccb894885824","object":"chat.completion.chunk","created":0,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" main"},"finish_reason":null}]}
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}]}
4141
42− data: {"id":"chatcmpl-54dc2649ab88ccb894885824","object":"chat.completion.chunk","created":0,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":".go"},"finish_reason":null}]}
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}]}
4343
44− data: {"id":"chatcmpl-54dc2649ab88ccb894885824","object":"chat.completion.chunk","created":0,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" file"},"finish_reason":null}]}
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}]}
4545
46− data: {"id":"chatcmpl-54dc2649ab88ccb894885824","object":"chat.completion.chunk","created":0,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
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}]}
4747
48− data: {"id":"chatcmpl-54dc2649ab88ccb894885824","object":"chat.completion.chunk","created":0,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" see"},"finish_reason":null}]}
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}]}
4949
50− data: {"id":"chatcmpl-54dc2649ab88ccb894885824","object":"chat.completion.chunk","created":0,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" its"},"finish_reason":null}]}
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}]}
5151
52− data: {"id":"chatcmpl-54dc2649ab88ccb894885824","object":"chat.completion.chunk","created":0,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" current"},"finish_reason":null}]}
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}]}
5353
54− data: {"id":"chatcmpl-54dc2649ab88ccb894885824","object":"chat.completion.chunk","created":0,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":" contents"},"finish_reason":null}]}
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}]}
5555
56− data: {"id":"chatcmpl-54dc2649ab88ccb894885824","object":"chat.completion.chunk","created":0,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
56+ data: {"id":"chatcmpl-d599cbede586f295273bd5fe","object":"chat.completion.chunk","created":1778531382,"model":"glm-5.1","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
5757
58− data: {"id":"chatcmpl-54dc2649ab88ccb894885824","object":"chat.completion.chunk","created":0,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_b2789b48d2ec41da9f61a574","type":"function","index":0,"function":{"name":"view","arguments":""}}]},"finish_reason":null}]}
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}]}
5959
60− data: {"id":"chatcmpl-54dc2649ab88ccb894885824","object":"chat.completion.chunk","created":0,"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}]}
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}]}
6161
62− data: {"id":"chatcmpl-54dc2649ab88ccb894885824","object":"chat.completion.chunk","created":0,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":{"prompt_tokens":725,"completion_tokens":45,"total_tokens":7810}}
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}}}
6365
6466 data: [DONE]
6567
@@ -68,15 +70,15 @@ interactions:
6870 - text/event-stream
6971 status: 200 OK
7072 code: 200
71− duration: 3.823122208s
73+ duration: 4.027960709s
7274- id: 1
7375 request:
7476 proto: HTTP/1.1
7577 proto_major: 1
7678 proto_minor: 1
77− content_length: 34251
79+ content_length: 887
7880 host: ""
79− 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_b2789b48d2ec41da9f61a574\",\"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 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</file>\\n\",\"tool_call_id\":\"call_b2789b48d2ec41da9f61a574\",\"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); renders images (PNG, JPEG, GIF, BMP, SVG, 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}"
81+ body: '{"messages":[{"content":"You will generate a short title based on the first message a user begins a conversation with.\n\n<rules>\n- Keep the title in the same language that the user wrote their message in.\n- Ensure it is not more than 50 characters long.\n- The title should be a summary of the user''s message.\n- It should be one line long.\n- Do not use quotes or colons.\n- The entire text you return will be used as the title.\n- Never return anything that is more than one sentence (one line) long.\n</rules>\n\n /no_think","role":"system"},{"content":"Generate a concise title for the following content:\n\nuse multiedit to change ''Hello, World!'' to ''Hello, Crush!'' and add a comment ''// Greeting'' above the fmt.Println line in main.go\n <think>\n\n</think>","role":"user"}],"model":"gpt-oss-120b","max_completion_tokens":40,"stream_options":{"include_usage":true},"stream":true}'
8082 headers:
8183 Accept:
8284 - application/json
@@ -93,819 +95,899 @@ interactions:
9395 content_length: -1
9496 uncompressed: true
9597 body: |+
96− data: {"id":"chatcmpl-517acaae8a6b55fa3c6a5333","object":"chat.completion.chunk","created":0,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
98+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
9799
98− data: {"id":"chatcmpl-517acaae8a6b55fa3c6a5333","object":"chat.completion.chunk","created":0,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_b3accc0a7eaa4756b961e075","type":"function","index":0,"function":{"name":"multiedit","arguments":""}}]},"finish_reason":null}]}
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}]}
99101
100− data: {"id":"chatcmpl-517acaae8a6b55fa3c6a5333","object":"chat.completion.chunk","created":0,"model":"glm-5.1","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"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\"}"}}]},"finish_reason":null}]}
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}]}
101103
102− data: {"id":"chatcmpl-517acaae8a6b55fa3c6a5333","object":"chat.completion.chunk","created":0,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":{"prompt_tokens":108,"completion_tokens":76,"total_tokens":7928}}
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}]}
103105
104− data: [DONE]
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}]}
105107
106− headers:
107− Content-Type:
108− - text/event-stream
109− status: 200 OK
110− code: 200
111− duration: 4.295830959s
112−- id: 2
113− request:
114− proto: HTTP/1.1
115− proto_major: 1
116− proto_minor: 1
117− content_length: 887
118− host: ""
119− body: '{"messages":[{"content":"You will generate a short title based on the first message a user begins a conversation with.\n\n<rules>\n- Keep the title in the same language that the user wrote their message in.\n- Ensure it is not more than 50 characters long.\n- The title should be a summary of the user''s message.\n- It should be one line long.\n- Do not use quotes or colons.\n- The entire text you return will be used as the title.\n- Never return anything that is more than one sentence (one line) long.\n</rules>\n\n /no_think","role":"system"},{"content":"Generate a concise title for the following content:\n\nuse multiedit to change ''Hello, World!'' to ''Hello, Crush!'' and add a comment ''// Greeting'' above the fmt.Println line in main.go\n <think>\n\n</think>","role":"user"}],"model":"gpt-oss-120b","max_completion_tokens":40,"stream_options":{"include_usage":true},"stream":true}'
120− headers:
121− Accept:
122− - application/json
123− Content-Type:
124− - application/json
125− User-Agent:
126− - Charm-Crush/devel (https://charm.land/crush)
127− url: https://hyper.charm.land/v1/chat/completions
128− method: POST
129− response:
130− proto: HTTP/2.0
131− proto_major: 2
132− proto_minor: 0
133− content_length: -1
134− uncompressed: true
135− body: |+
136− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
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}]}
137181
138− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"We"},"finish_reason":null}]}
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}]}
139183
140− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" need"},"finish_reason":null}]}
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}]}
141185
142− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
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}]}
143187
144− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" produce"},"finish_reason":null}]}
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}]}
145189
146− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
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}]}
147191
148− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" title"},"finish_reason":null}]}
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}]}
149193
150− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" summar"},"finish_reason":null}]}
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}]}
151195
152− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"izing"},"finish_reason":null}]}
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}]}
153197
154− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" the"},"finish_reason":null}]}
198+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
155199
156− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" user's"},"finish_reason":null}]}
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}]}
157201
158− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" request"},"finish_reason":null}]}
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}]}
159203
160− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
204+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
161205
162− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Language"},"finish_reason":null}]}
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}]}
163207
164− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" English"},"finish_reason":null}]}
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}]}
165209
166− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
210+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
167211
168− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Must"},"finish_reason":null}]}
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}]}
169213
170− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" be"},"finish_reason":null}]}
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}]}
171215
172− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \u003c="},"finish_reason":null}]}
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}]}
173217
174− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
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}]}
175219
176− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
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}]}
177221
178− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
222+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
179223
180− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Something"},"finish_reason":null}]}
224+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
181225
182− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" like"},"finish_reason":null}]}
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}]}
183227
184− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
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}]}
185229
186− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
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}]}
187231
188− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Change"},"finish_reason":null}]}
232+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
189233
190− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Hello"},"finish_reason":null}]}
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}]}
191235
192− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" World"},"finish_reason":null}]}
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}]}
193237
194− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
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}]}
195239
196− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Hello"},"finish_reason":null}]}
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}]}
197241
198− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Crush"},"finish_reason":null}]}
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}]}
199243
200− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" and"},"finish_reason":null}]}
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}]}
201245
202− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" add"},"finish_reason":null}]}
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}]}
203247
204− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" comment"},"finish_reason":null}]}
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}]}
205249
206− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
250+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
207251
208− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Count"},"finish_reason":null}]}
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}]}
209253
210− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
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}]}
211255
212− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
256+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
213257
214− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
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}]}
215259
216− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Change"},"finish_reason":null}]}
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}]}
217261
218− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Hello"},"finish_reason":null}]}
262+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
219263
220− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" World"},"finish_reason":null}]}
264+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
221265
222− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
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}]}
223267
224− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Hello"},"finish_reason":null}]}
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}]}
225269
226− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Crush"},"finish_reason":null}]}
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}]}
227271
228− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" and"},"finish_reason":null}]}
272+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
229273
230− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" add"},"finish_reason":null}]}
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}]}
231275
232− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" comment"},"finish_reason":null}]}
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}]}
233277
234− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\""},"finish_reason":null}]}
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}]}
235279
236− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" length"},"finish_reason":null}]}
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}]}
237281
238− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"?"},"finish_reason":null}]}
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}]}
239283
240− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Let's"},"finish_reason":null}]}
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}]}
241285
242− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" count"},"finish_reason":null}]}
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}]}
243287
244− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
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}]}
245289
246− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Change"},"finish_reason":null}]}
290+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\""},"finish_reason":null}]}
247291
248− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
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}]}
249293
250− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"6"},"finish_reason":null}]}
294+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"?"},"finish_reason":null}]}
251295
252− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
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}]}
253297
254− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" +"},"finish_reason":null}]}
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}]}
255299
256− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
300+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
257301
258− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
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}]}
259303
260− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
304+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
261305
262− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
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}]}
263307
264− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"7"},"finish_reason":null}]}
308+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
265309
266− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
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}]}
267311
268− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Hello"},"finish_reason":null}]}
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}]}
269313
270− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
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}]}
271315
272− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"5"},"finish_reason":null}]}
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}]}
273317
274− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
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}]}
275319
276− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"12"},"finish_reason":null}]}
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}]}
277321
278− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
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}]}
279323
280− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
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}]}
281325
282− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
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}]}
283327
284− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"13"},"finish_reason":null}]}
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}]}
285329
286− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
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}]}
287331
288− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" World"},"finish_reason":null}]}
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}]}
289333
290− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
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}]}
291335
292− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"5"},"finish_reason":null}]}
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}]}
293337
294− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
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}]}
295339
296− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"18"},"finish_reason":null}]}
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}]}
297341
298− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
342+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":("},"finish_reason":null}]}
299343
300− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
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}]}
301345
302− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
346+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
303347
304− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"19"},"finish_reason":null}]}
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}]}
305349
306− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
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}]}
307351
308− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
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}]}
309353
310− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
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}]}
311355
312− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"2"},"finish_reason":null}]}
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}]}
313357
314− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
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}]}
315359
316− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"21"},"finish_reason":null}]}
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}]}
317361
318− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
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}]}
319363
320− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
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}]}
321365
322− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
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}]}
323367
324− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"22"},"finish_reason":null}]}
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}]}
325369
326− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
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}]}
327371
328− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Hello"},"finish_reason":null}]}
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}]}
329373
330− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
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}]}
331375
332− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"5"},"finish_reason":null}]}
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}]}
333377
334− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
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}]}
335379
336− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"27"},"finish_reason":null}]}
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}]}
337381
338− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
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}]}
339383
340− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
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}]}
341385
342− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
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}]}
343387
344− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"28"},"finish_reason":null}]}
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}]}
345389
346− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
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}]}
347391
348− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Crush"},"finish_reason":null}]}
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}]}
349393
350− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"!("},"finish_reason":null}]}
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}]}
351395
352− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"6"},"finish_reason":null}]}
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}]}
353397
354− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
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}]}
355399
356− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"34"},"finish_reason":null}]}
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}]}
357401
358− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
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}]}
359403
360− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
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}]}
361405
362− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
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}]}
363407
364− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"35"},"finish_reason":null}]}
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}]}
365409
366− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
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}]}
367411
368− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" and"},"finish_reason":null}]}
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}]}
369413
370− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
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}]}
371415
372− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"3"},"finish_reason":null}]}
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}]}
373417
374− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
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}]}
375419
376− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"38"},"finish_reason":null}]}
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}]}
377421
378− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
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}]}
379423
380− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
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}]}
381425
382− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
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}]}
383427
384− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"39"},"finish_reason":null}]}
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}]}
385429
386− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
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}]}
387431
388− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" add"},"finish_reason":null}]}
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}]}
389433
390− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
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}]}
391435
392− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"3"},"finish_reason":null}]}
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}]}
393437
394− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
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}]}
395439
396− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"42"},"finish_reason":null}]}
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}]}
397441
398− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
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}]}
399443
400− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
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}]}
401445
402− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"="},"finish_reason":null}]}
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}]}
403447
404− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"43"},"finish_reason":null}]}
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}]}
405449
406− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
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}]}
407451
408− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" comment"},"finish_reason":null}]}
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}]}
409453
410− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
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}]}
411455
412− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"7"},"finish_reason":null}]}
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}]}
413457
414− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
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}]}
415459
416− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
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}]}
417461
418− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
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}]}
419463
420− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" That's"},"finish_reason":null}]}
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}]}
421465
422− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" exactly"},"finish_reason":null}]}
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}]}
423467
424− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
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}]}
425469
426− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
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}]}
427471
428− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"?"},"finish_reason":null}]}
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}]}
429473
430− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Actually"},"finish_reason":null}]}
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}]}
431475
432− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" need"},"finish_reason":null}]}
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}]}
433477
434− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
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}]}
435479
436− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" count"},"finish_reason":null}]}
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}]}
437481
438− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" precisely"},"finish_reason":null}]}
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}]}
439483
440− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
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}]}
441485
442− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" including"},"finish_reason":null}]}
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}]}
443487
444− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" spaces"},"finish_reason":null}]}
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}]}
445489
446− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
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}]}
447491
448− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Let's"},"finish_reason":null}]}
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}]}
449493
450− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" count"},"finish_reason":null}]}
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}]}
451495
452− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" string"},"finish_reason":null}]}
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}]}
453497
454− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
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}]}
455499
456− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
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}]}
457501
458− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Change"},"finish_reason":null}]}
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}]}
459503
460− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Hello"},"finish_reason":null}]}
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}]}
461505
462− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" World"},"finish_reason":null}]}
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}]}
463507
464− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" to"},"finish_reason":null}]}
508+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
465509
466− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Hello"},"finish_reason":null}]}
510+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ("},"finish_reason":null}]}
467511
468− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Crush"},"finish_reason":null}]}
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}]}
469513
470− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" and"},"finish_reason":null}]}
514+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
471515
472− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" add"},"finish_reason":null}]}
516+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
473517
474− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" comment"},"finish_reason":null}]}
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}]}
475519
476− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
520+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
477521
478− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Write"},"finish_reason":null}]}
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}]}
479523
480− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" out"},"finish_reason":null}]}
524+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
481525
482− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
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}]}
483527
484− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" C"},"finish_reason":null}]}
528+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
485529
486− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
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}]}
487531
488− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"1"},"finish_reason":null}]}
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}]}
489533
490− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
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}]}
491535
492− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"h"},"finish_reason":null}]}
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}]}
493537
494− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"2"},"finish_reason":null}]}
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}]}
495539
496− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"a"},"finish_reason":null}]}
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}]}
497541
498− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"3"},"finish_reason":null}]}
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}]}
499543
500− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"n"},"finish_reason":null}]}
544+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
501545
502− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"4"},"finish_reason":null}]}
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}]}
503547
504− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"g"},"finish_reason":null}]}
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}]}
505549
506− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"5"},"finish_reason":null}]}
550+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
507551
508− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"e"},"finish_reason":null}]}
552+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
509553
510− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"6"},"finish_reason":null}]}
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}]}
511555
512− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" ("},"finish_reason":null}]}
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}]}
513557
514− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"6"},"finish_reason":null}]}
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}]}
515559
516− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" letters"},"finish_reason":null}]}
560+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
517561
518− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
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}]}
519563
520− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
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}]}
521565
522− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"7"},"finish_reason":null}]}
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}]}
523567
524− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":";"},"finish_reason":null}]}
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}]}
525569
526− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" H"},"finish_reason":null}]}
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}]}
527571
528− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"8"},"finish_reason":null}]}
572+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
529573
530− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"e"},"finish_reason":null}]}
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}]}
531575
532− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"9"},"finish_reason":null}]}
576+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
533577
534− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"l"},"finish_reason":null}]}
578+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
535579
536− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"10"},"finish_reason":null}]}
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}]}
537581
538− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"l"},"finish_reason":null}]}
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}]}
539583
540− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"11"},"finish_reason":null}]}
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}]}
541585
542− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"o"},"finish_reason":null}]}
586+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":\""},"finish_reason":null}]}
543587
544− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"12"},"finish_reason":null}]}
588+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
545589
546− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
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}]}
547591
548− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"13"},"finish_reason":null}]}
592+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
549593
550− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":";"},"finish_reason":null}]}
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}]}
551595
552− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" W"},"finish_reason":null}]}
596+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
553597
554− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"14"},"finish_reason":null}]}
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}]}
555599
556− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"o"},"finish_reason":null}]}
600+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
557601
558− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"15"},"finish_reason":null}]}
602+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
559603
560− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"r"},"finish_reason":null}]}
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}]}
561605
562− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"16"},"finish_reason":null}]}
606+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\""},"finish_reason":null}]}
563607
564− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"l"},"finish_reason":null}]}
608+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
565609
566− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"17"},"finish_reason":null}]}
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}]}
567611
568− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"d"},"finish_reason":null}]}
612+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
569613
570− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"18"},"finish_reason":null}]}
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}]}
571615
572− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
616+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
573617
574− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"19"},"finish_reason":null}]}
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}]}
575619
576− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":";"},"finish_reason":null}]}
620+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
577621
578− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" t"},"finish_reason":null}]}
622+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
579623
580− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"20"},"finish_reason":null}]}
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}]}
581625
582− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"o"},"finish_reason":null}]}
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}]}
583627
584− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"21"},"finish_reason":null}]}
628+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\""},"finish_reason":null}]}
585629
586− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
630+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
587631
588− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"22"},"finish_reason":null}]}
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}]}
589633
590− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":";"},"finish_reason":null}]}
634+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
591635
592− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" H"},"finish_reason":null}]}
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}]}
593637
594− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"23"},"finish_reason":null}]}
638+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
595639
596− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"e"},"finish_reason":null}]}
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}]}
597641
598− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"24"},"finish_reason":null}]}
642+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
599643
600− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"l"},"finish_reason":null}]}
644+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
601645
602− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"25"},"finish_reason":null}]}
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}]}
603647
604− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"l"},"finish_reason":null}]}
648+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\""},"finish_reason":null}]}
605649
606− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"26"},"finish_reason":null}]}
650+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
607651
608− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"o"},"finish_reason":null}]}
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}]}
609653
610− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"27"},"finish_reason":null}]}
654+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
611655
612− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
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}]}
613657
614− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"28"},"finish_reason":null}]}
658+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
615659
616− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":";"},"finish_reason":null}]}
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}]}
617661
618− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" C"},"finish_reason":null}]}
662+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
619663
620− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"29"},"finish_reason":null}]}
664+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
621665
622− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"r"},"finish_reason":null}]}
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}]}
623667
624− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"30"},"finish_reason":null}]}
668+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\""},"finish_reason":null}]}
625669
626− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"u"},"finish_reason":null}]}
670+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
627671
628− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"31"},"finish_reason":null}]}
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}]}
629673
630− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"s"},"finish_reason":null}]}
674+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
631675
632− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"32"},"finish_reason":null}]}
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}]}
633677
634− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"h"},"finish_reason":null}]}
678+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
635679
636− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"33"},"finish_reason":null}]}
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}]}
637681
638− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
682+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
639683
640− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"34"},"finish_reason":null}]}
684+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
641685
642− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":";"},"finish_reason":null}]}
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}]}
643687
644− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
688+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\""},"finish_reason":null}]}
645689
646− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"35"},"finish_reason":null}]}
690+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
647691
648− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"n"},"finish_reason":null}]}
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}]}
649693
650− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"36"},"finish_reason":null}]}
694+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
651695
652− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"d"},"finish_reason":null}]}
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}]}
653697
654− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"37"},"finish_reason":null}]}
698+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
655699
656− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
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}]}
657701
658− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"38"},"finish_reason":null}]}
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}]}
659703
660− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":";"},"finish_reason":null}]}
704+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
661705
662− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" a"},"finish_reason":null}]}
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}]}
663707
664− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"39"},"finish_reason":null}]}
708+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
665709
666− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"d"},"finish_reason":null}]}
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}]}
667711
668− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"40"},"finish_reason":null}]}
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}]}
669713
670− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"d"},"finish_reason":null}]}
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}]}
671715
672− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"41"},"finish_reason":null}]}
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}]}
673717
674− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
718+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"?"},"finish_reason":null}]}
675719
676− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"42"},"finish_reason":null}]}
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}]}
677721
678− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":";"},"finish_reason":null}]}
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}]}
679723
680− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" c"},"finish_reason":null}]}
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}]}
681725
682− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"43"},"finish_reason":null}]}
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}]}
683727
684− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"o"},"finish_reason":null}]}
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}]}
685729
686− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"44"},"finish_reason":null}]}
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}]}
687731
688− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"m"},"finish_reason":null}]}
732+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
689733
690− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"45"},"finish_reason":null}]}
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}]}
691735
692− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"m"},"finish_reason":null}]}
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}]}
693737
694− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"46"},"finish_reason":null}]}
738+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
695739
696− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"e"},"finish_reason":null}]}
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}]}
697741
698− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"47"},"finish_reason":null}]}
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}]}
699743
700− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"n"},"finish_reason":null}]}
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}]}
701745
702− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"48"},"finish_reason":null}]}
746+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
703747
704− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"t"},"finish_reason":null}]}
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}]}
705749
706− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"49"},"finish_reason":null}]}
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}]}
707751
708− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
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}]}
709753
710− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" That's"},"finish_reason":null}]}
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}]}
711755
712− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
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}]}
713757
714− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"49"},"finish_reason":null}]}
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}]}
715759
716− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" characters"},"finish_reason":null}]}
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}]}
717761
718− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
762+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
719763
720− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Good"},"finish_reason":null}]}
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}]}
721765
722− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" under"},"finish_reason":null}]}
766+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
723767
724− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
768+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
725769
726− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
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}]}
727771
728− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
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}]}
729773
730− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" But"},"finish_reason":null}]}
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}]}
731775
732− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" maybe"},"finish_reason":null}]}
776+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":\""},"finish_reason":null}]}
733777
734− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" better"},"finish_reason":null}]}
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}]}
735779
736− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
780+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
737781
738− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
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}]}
739783
740− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"Replace"},"finish_reason":null}]}
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}]}
741785
742− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Hello"},"finish_reason":null}]}
786+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
743787
744− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" World"},"finish_reason":null}]}
788+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
745789
746− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" with"},"finish_reason":null}]}
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}]}
747791
748− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Hello"},"finish_reason":null}]}
792+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\""},"finish_reason":null}]}
749793
750− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Crush"},"finish_reason":null}]}
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}]}
751795
752− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" and"},"finish_reason":null}]}
796+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
753797
754− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" comment"},"finish_reason":null}]}
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}]}
755799
756− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\"."},"finish_reason":null}]}
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}]}
757801
758− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Count"},"finish_reason":null}]}
802+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
759803
760− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
804+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
761805
762− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Replace"},"finish_reason":null}]}
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}]}
763807
764− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
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}]}
765809
766− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"7"},"finish_reason":null}]}
810+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\""},"finish_reason":null}]}
767811
768− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")"},"finish_reason":null}]}
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}]}
769813
770− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
814+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
771815
772− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"8"},"finish_reason":null}]}
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}]}
773817
774− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Hello"},"finish_reason":null}]}
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}]}
775819
776− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
820+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
777821
778− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"5"},"finish_reason":null}]}
822+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
779823
780− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
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}]}
781825
782− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"13"},"finish_reason":null}]}
826+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\""},"finish_reason":null}]}
783827
784− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
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}]}
785829
786− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"14"},"finish_reason":null}]}
830+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
787831
788− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" World"},"finish_reason":null}]}
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}]}
789833
790− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
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}]}
791835
792− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"5"},"finish_reason":null}]}
836+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
793837
794− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
838+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
795839
796− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"19"},"finish_reason":null}]}
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}]}
797841
798− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
842+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\""},"finish_reason":null}]}
799843
800− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"20"},"finish_reason":null}]}
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}]}
801845
802− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" with"},"finish_reason":null}]}
846+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
803847
804− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
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}]}
805849
806− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"4"},"finish_reason":null}]}
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}]}
807851
808− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
852+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
809853
810− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"24"},"finish_reason":null}]}
854+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
811855
812− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
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}]}
813857
814− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"25"},"finish_reason":null}]}
858+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\""},"finish_reason":null}]}
815859
816− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Hello"},"finish_reason":null}]}
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}]}
817861
818− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
862+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
819863
820− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"5"},"finish_reason":null}]}
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}]}
821865
822− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
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}]}
823867
824− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"30"},"finish_reason":null}]}
868+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":","},"finish_reason":null}]}
825869
826− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
870+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" \""},"finish_reason":null}]}
827871
828− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"31"},"finish_reason":null}]}
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}]}
829873
830− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Crush"},"finish_reason":null}]}
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}]}
831875
832− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
876+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"\""},"finish_reason":null}]}
833877
834− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"5"},"finish_reason":null}]}
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}]}
835879
836− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
880+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
837881
838− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"36"},"finish_reason":null}]}
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}]}
839883
840− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
884+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
841885
842− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"37"},"finish_reason":null}]}
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}]}
843887
844− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" and"},"finish_reason":null}]}
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}]}
845889
846− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
890+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
847891
848− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"3"},"finish_reason":null}]}
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}]}
849893
850− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
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}]}
851895
852− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"40"},"finish_reason":null}]}
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}]}
853897
854− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" space"},"finish_reason":null}]}
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}]}
855899
856− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"41"},"finish_reason":null}]}
900+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
857901
858− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" comment"},"finish_reason":null}]}
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}]}
859903
860− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"("},"finish_reason":null}]}
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}]}
861905
862− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"7"},"finish_reason":null}]}
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}]}
863907
864− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":")="},"finish_reason":null}]}
908+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":":"},"finish_reason":null}]}
865909
866− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"48"},"finish_reason":null}]}
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}]}
867911
868− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
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}]}
869913
870− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Under"},"finish_reason":null}]}
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}]}
871915
872− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" "},"finish_reason":null}]}
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}]}
873917
874− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"50"},"finish_reason":null}]}
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}]}
875919
876− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
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}]}
877921
878− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Good"},"finish_reason":null}]}
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}]}
879923
880− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
924+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"Mult"},"finish_reason":null}]}
881925
882− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" Let's"},"finish_reason":null}]}
926+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"ied"},"finish_reason":null}]}
883927
884− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" output"},"finish_reason":null}]}
928+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"it"},"finish_reason":null}]}
885929
886− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":" that"},"finish_reason":null}]}
930+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":":"},"finish_reason":null}]}
887931
888− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"reasoning_content":"."},"finish_reason":null}]}
932+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" update"},"finish_reason":null}]}
889933
890− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
934+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" greeting"},"finish_reason":null}]}
891935
892− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":"Replace"},"finish_reason":null}]}
936+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" and"},"finish_reason":null}]}
893937
894− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" Hello"},"finish_reason":null}]}
938+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" comment"},"finish_reason":null}]}
895939
896− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" World"},"finish_reason":null}]}
940+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" in"},"finish_reason":null}]}
897941
898− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" with"},"finish_reason":null}]}
942+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" main"},"finish_reason":null}]}
899943
900− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" Hello"},"finish_reason":null}]}
944+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":".go"},"finish_reason":null}]}
901945
902− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" Crush"},"finish_reason":null}]}
946+ data: {"id":"chatcmpl-832f49f9f99073f8f6cc0028","object":"chat.completion.chunk","created":1778531378,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
903947
904− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" and"},"finish_reason":null}]}
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}}}
905949
906− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{"content":" comment"},"finish_reason":null}]}
950+ data: [DONE]
907951
908− data: {"id":"chatcmpl-18ba696a53142f8fceb16d9d","object":"chat.completion.chunk","created":0,"model":"gpt-oss-120b","choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":{"prompt_tokens":55,"completion_tokens":394,"total_tokens":625}}
952+ headers:
953+ Content-Type:
954+ - text/event-stream
955+ status: 200 OK
956+ code: 200
957+ duration: 784.098583ms
958+- id: 2
959+ request:
960+ proto: HTTP/1.1
961+ proto_major: 1
962+ proto_minor: 1
963+ content_length: 34270
964+ 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}"
966+ headers:
967+ Accept:
968+ - application/json
969+ Content-Type:
970+ - application/json
971+ User-Agent:
972+ - Charm-Crush/devel (https://charm.land/crush)
973+ url: https://hyper.charm.land/v1/chat/completions
974+ method: POST
975+ response:
976+ proto: HTTP/2.0
977+ proto_major: 2
978+ proto_minor: 0
979+ content_length: -1
980+ uncompressed: true
981+ 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}]}
983+
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}]}
985+
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}]}
987+
988+ data: {"id":"chatcmpl-94a5ca0c49f9490e9f7f86f2","object":"chat.completion.chunk","created":1778531387,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}]}
989+
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}}}
909991
910992 data: [DONE]
911993
@@ -914,15 +996,15 @@ interactions:
914996 - text/event-stream
915997 status: 200 OK
916998 code: 200
917− duration: 706.161541ms
999+ duration: 5.524277875s
9181000- id: 3
9191001 request:
9201002 proto: HTTP/1.1
9211003 proto_major: 1
9221004 proto_minor: 1
923− content_length: 34828
1005+ content_length: 34943
9241006 host: ""
925− 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_b2789b48d2ec41da9f61a574\",\"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 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</file>\\n\",\"tool_call_id\":\"call_b2789b48d2ec41da9f61a574\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_b3accc0a7eaa4756b961e075\",\"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_b3accc0a7eaa4756b961e075\",\"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); renders images (PNG, JPEG, GIF, BMP, SVG, 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}"
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}"
9261008 headers:
9271009 Accept:
9281010 - application/json
@@ -939,49 +1021,325 @@ interactions:
9391021 content_length: -1
9401022 uncompressed: true
9411023 body: |+
942− data: {"id":"chatcmpl-291b41722ec3e5d4a675d235","object":"chat.completion.chunk","created":0,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
1024+ data: {"id":"chatcmpl-2b56351326cf2f0b163f32fa","object":"chat.completion.chunk","created":1778531391,"model":"glm-5.1","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
1025+
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}]}
1027+
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}]}
1029+
1030+ data: {"id":"chatcmpl-2b56351326cf2f0b163f32fa","object":"chat.completion.chunk","created":1778531391,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}]}
1031+
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}}}
1033+
1034+ data: [DONE]
1035+
1036+ headers:
1037+ Content-Type:
1038+ - text/event-stream
1039+ status: 200 OK
1040+ code: 200
1041+ duration: 3.613997833s
1042+- id: 4
1043+ request:
1044+ proto: HTTP/1.1
1045+ proto_major: 1
1046+ proto_minor: 1
1047+ content_length: 35410
1048+ 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}"
1050+ headers:
1051+ Accept:
1052+ - application/json
1053+ Content-Type:
1054+ - application/json
1055+ User-Agent:
1056+ - Charm-Crush/devel (https://charm.land/crush)
1057+ url: https://hyper.charm.land/v1/chat/completions
1058+ method: POST
1059+ response:
1060+ proto: HTTP/2.0
1061+ proto_major: 2
1062+ proto_minor: 0
1063+ content_length: -1
1064+ uncompressed: true
1065+ 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}]}
1067+
1068+ data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"The"},"finish_reason":null}]}
1069+
1070+ data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" first"},"finish_reason":null}]}
1071+
1072+ data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" edit"},"finish_reason":null}]}
1073+
1074+ data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" changed"},"finish_reason":null}]}
1075+
1076+ data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" `\""},"finish_reason":null}]}
1077+
1078+ data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"Hello"},"finish_reason":null}]}
1079+
1080+ data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":","},"finish_reason":null}]}
1081+
1082+ data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" World"},"finish_reason":null}]}
1083+
1084+ data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"!\""},"finish_reason":null}]}
1085+
1086+ data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"`"},"finish_reason":null}]}
1087+
1088+ data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" to"},"finish_reason":null}]}
1089+
1090+ data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" `\""},"finish_reason":null}]}
1091+
1092+ data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"Hello"},"finish_reason":null}]}
1093+
1094+ data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":","},"finish_reason":null}]}
1095+
1096+ data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" Crush"},"finish_reason":null}]}
1097+
1098+ data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"!\""},"finish_reason":null}]}
1099+
1100+ data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"`,"},"finish_reason":null}]}
1101+
1102+ data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" so"},"finish_reason":null}]}
1103+
1104+ data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" the"},"finish_reason":null}]}
1105+
1106+ data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" second"},"finish_reason":null}]}
1107+
1108+ data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" edit"},"finish_reason":null}]}
1109+
1110+ data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"'s"},"finish_reason":null}]}
1111+
1112+ data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" `"},"finish_reason":null}]}
1113+
1114+ data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"old"},"finish_reason":null}]}
1115+
1116+ data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"_string"},"finish_reason":null}]}
1117+
1118+ data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"`"},"finish_reason":null}]}
1119+
1120+ data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" no"},"finish_reason":null}]}
1121+
1122+ data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" longer"},"finish_reason":null}]}
1123+
1124+ data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" matched"},"finish_reason":null}]}
1125+
1126+ data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"."},"finish_reason":null}]}
1127+
1128+ data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" Let"},"finish_reason":null}]}
1129+
1130+ data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" me"},"finish_reason":null}]}
1131+
1132+ data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" apply"},"finish_reason":null}]}
1133+
1134+ data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" the"},"finish_reason":null}]}
1135+
1136+ data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" comment"},"finish_reason":null}]}
1137+
1138+ data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" edit"},"finish_reason":null}]}
1139+
1140+ data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" now"},"finish_reason":null}]}
1141+
1142+ data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":":"},"finish_reason":null}]}
1143+
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}]}
1145+
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}]}
1147+
1148+ data: {"id":"chatcmpl-17594a40a72eff56cb26fc6a","object":"chat.completion.chunk","created":1778531396,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}]}
1149+
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}}}
1151+
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}}}
1193+
1194+ data: [DONE]
1195+
1196+ headers:
1197+ Content-Type:
1198+ - text/event-stream
1199+ status: 200 OK
1200+ code: 200
1201+ duration: 3.595254708s
1202+- id: 6
1203+ request:
1204+ proto: HTTP/1.1
1205+ proto_major: 1
1206+ proto_minor: 1
1207+ content_length: 36622
1208+ 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}"
1210+ headers:
1211+ Accept:
1212+ - application/json
1213+ Content-Type:
1214+ - application/json
1215+ User-Agent:
1216+ - Charm-Crush/devel (https://charm.land/crush)
1217+ url: https://hyper.charm.land/v1/chat/completions
1218+ method: POST
1219+ response:
1220+ proto: HTTP/2.0
1221+ proto_major: 2
1222+ proto_minor: 0
1223+ content_length: -1
1224+ uncompressed: true
1225+ 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}]}
1297+
1298+ data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"```"},"finish_reason":null}]}
1299+
1300+ data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"go"},"finish_reason":null}]}
9431301
944− data: {"id":"chatcmpl-291b41722ec3e5d4a675d235","object":"chat.completion.chunk","created":0,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"Done"},"finish_reason":null}]}
1302+ data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"\n"},"finish_reason":null}]}
9451303
946− data: {"id":"chatcmpl-291b41722ec3e5d4a675d235","object":"chat.completion.chunk","created":0,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"."},"finish_reason":null}]}
1304+ data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"func"},"finish_reason":null}]}
9471305
948− data: {"id":"chatcmpl-291b41722ec3e5d4a675d235","object":"chat.completion.chunk","created":0,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" Changed"},"finish_reason":null}]}
1306+ data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" main"},"finish_reason":null}]}
9491307
950− data: {"id":"chatcmpl-291b41722ec3e5d4a675d235","object":"chat.completion.chunk","created":0,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" the"},"finish_reason":null}]}
1308+ data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"()"},"finish_reason":null}]}
9511309
952− data: {"id":"chatcmpl-291b41722ec3e5d4a675d235","object":"chat.completion.chunk","created":0,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" greeting"},"finish_reason":null}]}
1310+ data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" {\n"},"finish_reason":null}]}
9531311
954− data: {"id":"chatcmpl-291b41722ec3e5d4a675d235","object":"chat.completion.chunk","created":0,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" string"},"finish_reason":null}]}
1312+ data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"\t"},"finish_reason":null}]}
9551313
956− data: {"id":"chatcmpl-291b41722ec3e5d4a675d235","object":"chat.completion.chunk","created":0,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" and"},"finish_reason":null}]}
1314+ data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"//"},"finish_reason":null}]}
9571315
958− data: {"id":"chatcmpl-291b41722ec3e5d4a675d235","object":"chat.completion.chunk","created":0,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" added"},"finish_reason":null}]}
1316+ data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" G"},"finish_reason":null}]}
9591317
960− data: {"id":"chatcmpl-291b41722ec3e5d4a675d235","object":"chat.completion.chunk","created":0,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" the"},"finish_reason":null}]}
1318+ data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"reeting"},"finish_reason":null}]}
9611319
962− data: {"id":"chatcmpl-291b41722ec3e5d4a675d235","object":"chat.completion.chunk","created":0,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" `"},"finish_reason":null}]}
1320+ data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"\n"},"finish_reason":null}]}
9631321
964− data: {"id":"chatcmpl-291b41722ec3e5d4a675d235","object":"chat.completion.chunk","created":0,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"//"},"finish_reason":null}]}
1322+ data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"\tfmt"},"finish_reason":null}]}
9651323
966− data: {"id":"chatcmpl-291b41722ec3e5d4a675d235","object":"chat.completion.chunk","created":0,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" G"},"finish_reason":null}]}
1324+ data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":".Println"},"finish_reason":null}]}
9671325
968− data: {"id":"chatcmpl-291b41722ec3e5d4a675d235","object":"chat.completion.chunk","created":0,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"reeting"},"finish_reason":null}]}
1326+ data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"(\""},"finish_reason":null}]}
9691327
970− data: {"id":"chatcmpl-291b41722ec3e5d4a675d235","object":"chat.completion.chunk","created":0,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"`"},"finish_reason":null}]}
1328+ data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"Hello"},"finish_reason":null}]}
9711329
972− data: {"id":"chatcmpl-291b41722ec3e5d4a675d235","object":"chat.completion.chunk","created":0,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" comment"},"finish_reason":null}]}
1330+ data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":","},"finish_reason":null}]}
9731331
974− data: {"id":"chatcmpl-291b41722ec3e5d4a675d235","object":"chat.completion.chunk","created":0,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" above"},"finish_reason":null}]}
1332+ data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" Crush"},"finish_reason":null}]}
9751333
976− data: {"id":"chatcmpl-291b41722ec3e5d4a675d235","object":"chat.completion.chunk","created":0,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":" `"},"finish_reason":null}]}
1334+ data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"!\")\n"},"finish_reason":null}]}
9771335
978− data: {"id":"chatcmpl-291b41722ec3e5d4a675d235","object":"chat.completion.chunk","created":0,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"fmt"},"finish_reason":null}]}
1336+ data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"}\n"},"finish_reason":null}]}
9791337
980− data: {"id":"chatcmpl-291b41722ec3e5d4a675d235","object":"chat.completion.chunk","created":0,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":".Println"},"finish_reason":null}]}
1338+ data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"```"},"finish_reason":null}]}
9811339
982− data: {"id":"chatcmpl-291b41722ec3e5d4a675d235","object":"chat.completion.chunk","created":0,"model":"glm-5.1","choices":[{"index":0,"delta":{"content":"`."},"finish_reason":null}]}
1340+ data: {"id":"chatcmpl-3f7349b4a0903fe63873d0b6","object":"chat.completion.chunk","created":1778531404,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
9831341
984− data: {"id":"chatcmpl-291b41722ec3e5d4a675d235","object":"chat.completion.chunk","created":0,"model":"glm-5.1","choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":{"prompt_tokens":159,"completion_tokens":22,"total_tokens":7989}}
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}}}
9851343
9861344 data: [DONE]
9871345
@@ -990,4 +1348,4 @@ interactions:
9901348 - text/event-stream
9911349 status: 200 OK
9921350 code: 200
993− duration: 3.39534875s
1351+ duration: 4.720450833s