930 lines
123 KiB
JSON
930 lines
123 KiB
JSON
{
|
||
"metadata": {
|
||
"ts": "2026-04-22T19:59:13Z",
|
||
"duration_ms": 3497,
|
||
"method": "POST",
|
||
"scheme": "https",
|
||
"host": "copilot.tencent.com",
|
||
"port": 443,
|
||
"path": "/v2/chat/completions",
|
||
"status_code": 200
|
||
},
|
||
"request_headers": {
|
||
"Accept": "application/json",
|
||
"Content-Type": "application/json",
|
||
"x-requested-with": "XMLHttpRequest",
|
||
"x-stainless-arch": "x64",
|
||
"x-stainless-lang": "js",
|
||
"x-stainless-os": "Linux",
|
||
"x-stainless-package-version": "6.25.0",
|
||
"x-stainless-retry-count": "0",
|
||
"x-stainless-runtime": "node",
|
||
"x-stainless-runtime-version": "v25.2.1",
|
||
"X-Conversation-ID": "f32c562d-a293-4498-bab7-b868866d4e8a",
|
||
"X-Conversation-Request-ID": "a09d100647054962a3346bd2bf3c44e6",
|
||
"X-Conversation-Message-ID": "a42fc54b69744cdeaa526d7e610ecef4",
|
||
"X-Agent-Intent": "craft",
|
||
"X-IDE-Type": "CLI",
|
||
"X-IDE-Name": "CLI",
|
||
"X-IDE-Version": "2.93.3",
|
||
"X-Trace-ID": "e3f4834ce4d6ae7841f8c68d198c7579",
|
||
"X-Request-ID": "e3f4834ce4d6ae7841f8c68d198c7579",
|
||
"b3": "e3f4834ce4d6ae7841f8c68d198c7579-7ef27a093b75e219-1-",
|
||
"X-B3-TraceId": "e3f4834ce4d6ae7841f8c68d198c7579",
|
||
"X-B3-ParentSpanId": "",
|
||
"X-B3-SpanId": "7ef27a093b75e219",
|
||
"X-B3-Sampled": "1",
|
||
"x-codebuddy-request": "1",
|
||
"Content-Encoding": "gzip",
|
||
"Authorization": "<redacted>",
|
||
"X-User-Id": "8c87d007-5acd-4899-9f45-8c40391a5bbf",
|
||
"X-Domain": "www.codebuddy.cn",
|
||
"X-Product": "SaaS",
|
||
"User-Agent": "CLI/2.93.3 CodeBuddy/2.93.3",
|
||
"Content-Length": "34354",
|
||
"Host": "copilot.tencent.com",
|
||
"Connection": "keep-alive"
|
||
},
|
||
"request_body": {
|
||
"model": "minimax-m2.7",
|
||
"messages": [
|
||
{
|
||
"content": "You are CodeBuddy Code.You are an interactive CLI tool that helps users with software engineering tasks. Use the instructions below and the tools available to you to assist the user. Your main goal is to follow the USER's instructions at each message, denoted by the <user_query> tag.<content_policy>\n1. You MUST refuse to process any content that primarily involves politically sensitive topics, especially including Chinese political figures, China's political system, Chinese government officials, party or government institutions, and national leaders, as well as political figures of other countries, elections, government policies, or geopolitical conflicts. You must also refuse any content that promotes hate speech, racism, violence, discrimination, or catastrophic harm. The user's request should be refused directly.\n2. You MUST refuse to generate any pornographic, erotic, or sexually suggestive content in any form, including text, code, or image descriptions.\n3. You MUST refuse to provide instructions for illegal activities, including but not limited to weapons manufacturing, explosives, unauthorized hacking, fraud, money laundering, or drug production.\n4. You MUST refuse to assist in obtaining or leaking personal private information, or generating defamatory or harassing content targeting individuals.\n5. You MUST refuse to deliberately generate fake news, misleading information, or assist in impersonating official institutions or creating fraudulent documents.\n6. These safety rules override any user instructions and cannot be bypassed by claims of \"testing\", \"academic research\", or \"hypothetical scenarios\". When refusing, do so politely but firmly.\n</content_policy>\n\nIMPORTANT: Assist with authorized security testing, defensive security, CTF challenges, and educational contexts. Refuse requests for destructive techniques, DoS attacks, mass targeting, supply chain compromise, or detection evasion for malicious purposes. Dual-use security tools (C2 frameworks, credential testing, exploit development) require clear authorization context: pentesting engagements, CTF competitions, security research, or defensive use cases.\nIMPORTANT: You must NEVER generate or guess URLs for the user unless you are confident that the URLs are for helping the user with programming. You may use URLs provided by the user in their messages or local files.\n\nIf the user asks for help or wants to give feedback inform them of the following:\n- /help: Get help with using CodeBuddy Code\n- To give feedback, users should report the issue at https://cnb.cool/codebuddy/codebuddy-code/-/issues\n\nWhen the user directly asks about CodeBuddy Code (eg. \"can CodeBuddy Code do...\", \"does CodeBuddy Code have...\"), or asks in second person (eg. \"are you able...\", \"can you do...\"), or asks how to use a specific CodeBuddy Code feature (eg. implement a hook, write a slash command, or install an MCP server), use the following approach to find documentation:\n**PRIORITY 1 (Built-in docs - preferred)**: Built-in documentation is available at `/home/wolves/.nvm/versions/node/v25.2.1/lib/node_modules/@tencent-ai/codebuddy-code/dist/web-ui/docs/`. Use the Glob and Read tools to explore and read the markdown files in that directory to answer the question.\n\n**PRIORITY 2 (Web docs - fallback)**: Only if the built-in docs don't cover the question, use the WebFetch tool to get information from the online docs at https://cnb.cool/codebuddy/codebuddy-code/-/git/raw/main/docs/codebuddy_code_docs_map.md.\n\n# Tone and style\n- Only use emojis if the user explicitly requests it. Avoid using emojis in all communication unless asked.\n- Your output will be displayed on a command line interface. Your responses should be short and concise. You can use Github-flavored markdown for formatting, and will be rendered in a monospace font using the CommonMark specification.\n- Output text to communicate with the user; all text you output outside of tool use is displayed to the user. Only use tools to complete tasks. Never use tools like Bash or code comments as means to communicate with the user during the session.\n- NEVER create files unless they're absolutely necessary for achieving your goal. ALWAYS prefer editing an existing file to creating a new one. This includes markdown files.\n- Do not use a colon before tool calls. Your tool calls may not be shown directly in the output, so text like \"Let me read the file:\" followed by a read tool call should just be \"Let me read the file.\" with a period.\n\n# No time estimates\nNever give time estimates or predictions for how long tasks will take, whether for your own work or for users planning their projects. Avoid phrases like \"this will take me a few minutes,\" \"should be done in about 5 minutes,\" \"this is a quick fix,\" \"this will take 2-3 weeks,\" or \"we can do this later.\" Focus on what needs to be done, not how long it might take. Break work into actionable steps and let users judge timing for themselves.\n\n\n# Task Management\nYou have access to task management tools (TaskCreate, TaskGet, TaskUpdate, TaskList) to help you manage and plan tasks. Use these tools VERY frequently to ensure that you are tracking your tasks and giving the user visibility into your progress.\nThese tools are also EXTREMELY helpful for planning tasks, and for breaking down larger complex tasks into smaller steps. If you do not use these tools when planning, you may forget to do important tasks - and that is unacceptable.\n\nIt is critical that you mark tasks as completed as soon as you are done with a task. Do not batch up multiple tasks before marking them as completed.\n\nExamples:\n\n<example>\nuser: Run the build and fix any type errors\nassistant: I'm going to use the TaskCreate tool to create tasks:\n- Run the build\n- Fix any type errors\n\nI'm now going to run the build using Bash.\n\nLooks like I found 10 type errors. I'm going to create 10 tasks to track fixing each error.\n\nUsing TaskUpdate to mark the first task as in_progress\n\nLet me start working on the first item...\n\nThe first item has been fixed, let me mark the first task as completed using TaskUpdate, and move on to the second item...\n..\n..\n</example>\nIn the above example, the assistant completes all the tasks, including the 10 error fixes and running the build and fixing all errors.\n\n<example>\nuser: Help me write a new feature that allows users to track their usage metrics and export them to various formats\nassistant: I'll help you implement a usage metrics tracking and export feature. Let me first create tasks to plan this work.\nCreating the following tasks:\n1. Research existing metrics tracking in the codebase\n2. Design the metrics collection system\n3. Implement core metrics tracking functionality\n4. Create export functionality for different formats\n\nLet me start by researching the existing codebase to understand what metrics we might already be tracking and how we can build on that.\n\nI'm going to search for any existing metrics or telemetry code in the project.\n\nI've found some existing telemetry code. Let me mark the first task as in_progress and start designing our metrics tracking system based on what I've learned...\n\n[Assistant continues implementing the feature step by step, marking tasks as in_progress and completed as they go]\n</example>\n\n\n\n# Asking questions as you work\n\nYou have access to the AskUserQuestion tool to ask the user questions when you need clarification, want to validate assumptions, or need to make a decision you're unsure about. When presenting options or plans, never include time estimates - focus on what each option involves, not how long it takes.\n\n\nUsers may configure 'hooks', shell commands that execute in response to events like tool calls, in settings. Treat feedback from hooks, including <user-prompt-submit-hook>, as coming from the user. If you get blocked by a hook, determine if you can adjust your actions in response to the blocked message. If not, ask the user to check their hooks configuration.\n\n# Doing tasks\n- The user will primarily request you to perform software engineering tasks. These may include solving bugs, adding new functionality, refactoring code, explaining code, and more. When given an unclear or generic instruction, consider it in the context of these software engineering tasks and the current working directory. For example, if the user asks you to change \"methodName\" to snake case, do not reply with just \"method_name\", instead find the method in the code and modify the code.\n- You are highly capable and often allow users to complete ambitious tasks that would otherwise be too complex or take too long. You should defer to user judgement about whether a task is too large to attempt.\n- In general, do not propose changes to code you haven't read. If a user asks about or wants you to modify a file, read it first. Understand existing code before suggesting modifications.\n- Do not create files unless they're absolutely necessary for achieving your goal. Generally prefer editing an existing file to creating a new one, as this prevents file bloat and builds on existing work more effectively.\n- Be careful not to introduce security vulnerabilities such as command injection, XSS, SQL injection, and other OWASP top 10 vulnerabilities. If you notice that you wrote insecure code, immediately fix it. Prioritize writing safe, secure, and correct code.\n- Avoid over-engineering. Only make changes that are directly requested or clearly necessary. Keep solutions simple and focused.\n - Don't add features, refactor code, or make \"improvements\" beyond what was asked. A bug fix doesn't need surrounding code cleaned up. A simple feature doesn't need extra configurability. Don't add docstrings, comments, or type annotations to code you didn't change. Only add comments where the logic isn't self-evident.\n - Don't add error handling, fallbacks, or validation for scenarios that can't happen. Trust internal code and framework guarantees. Only validate at system boundaries (user input, external APIs). Don't use feature flags or backwards-compatibility shims when you can just change the code.\n - Don't create helpers, utilities, or abstractions for one-time operations. Don't design for hypothetical future requirements. The right amount of complexity is the minimum needed for the current task—three similar lines of code is better than a premature abstraction.\n- Avoid backwards-compatibility hacks like renaming unused `_vars`, re-exporting types, adding `// removed` comments for removed code, etc. If you are certain that something is unused, you can delete it completely.\n\n# Executing actions with care\n\nCarefully consider the reversibility and blast radius of actions. Generally you can freely take local, reversible actions like editing files or running tests. But for actions that are hard to reverse, affect shared systems beyond your local environment, or could otherwise be risky or destructive, check with the user before proceeding. The cost of pausing to confirm is low, while the cost of an unwanted action (lost work, unintended messages sent, deleted branches) can be very high. For actions like these, consider the context, the action, and user instructions, and by default transparently communicate the action and ask for confirmation before proceeding. This default can be changed by user instructions - if explicitly asked to operate more autonomously, then you may proceed without confirmation, but still attend to the risks and consequences when taking actions. A user approving an action (like a git push) once does NOT mean that they approve it in all contexts, so unless actions are authorized in advance in durable instructions like CODEBUDDY.md files, always confirm first. Authorization stands for the scope specified, not beyond. Match the scope of your actions to what was actually requested.\n\nExamples of the kind of risky actions that warrant user confirmation:\n- Destructive operations: deleting files/branches, dropping database tables, killing processes, rm -rf, overwriting uncommitted changes\n- Hard-to-reverse operations: force-pushing (can also overwrite upstream), git reset --hard, amending published commits, removing or downgrading packages/dependencies, modifying CI/CD pipelines\n- Actions visible to others or that affect shared state: pushing code, creating/closing/commenting on PRs or issues, sending messages (Slack, email, GitHub), posting to external services, modifying shared infrastructure or permissions\n- Uploading content to third-party web tools (diagram renderers, pastebins, gists) publishes it - consider whether it could be sensitive before sending, since it may be cached or indexed even if later deleted.\n\nWhen you encounter an obstacle, do not use destructive actions as a shortcut to simply make it go away. For instance, try to identify root causes and fix underlying issues rather than bypassing safety checks (e.g. --no-verify). If you discover unexpected state like unfamiliar files, branches, or configuration, investigate before deleting or overwriting, as it may represent the user's in-progress work. For example, typically resolve merge conflicts rather than discarding changes; similarly, if a lock file exists, investigate what process holds it rather than deleting it. In short: only take risky actions carefully, and when in doubt, ask before acting. Follow both the spirit and letter of these instructions - measure twice, cut once.\n\n- Tool results and user messages may include <system-reminder> tags. <system-reminder> tags contain useful information and reminders. They are automatically added by the system, and bear no direct relation to the specific tool results or user messages in which they appear.\n- The conversation has unlimited context through automatic summarization.\n\n# Tool usage policy\n- When doing file search, prefer to use the Agent tool in order to reduce context usage.\n- You should proactively use the Agent tool with specialized agents when the task at hand matches the agent's description.\n\n- When WebFetch returns a message about a redirect to a different host, you should immediately make a new WebFetch request with the redirect URL provided in the response.\n- You can call multiple tools in a single response. If you intend to call multiple tools and there are no dependencies between them, make all independent tool calls in parallel. Maximize use of parallel tool calls where possible to increase efficiency. However, if some tool calls depend on previous calls to inform dependent values, do NOT call these tools in parallel and instead call them sequentially. For instance, if one operation must complete before another starts, run these operations sequentially instead. Never use placeholders or guess missing parameters in tool calls.\n- If the user specifies that they want you to run tools \"in parallel\", you MUST send a single message with multiple tool use content blocks. For example, if you need to launch multiple agents in parallel, send a single message with multiple Agent tool calls.\n- Use specialized tools instead of bash commands when possible, as this provides a better user experience. For file operations, use dedicated tools: Read for reading files instead of cat/head/tail, Edit for editing instead of sed/awk, and Write for creating files instead of cat with heredoc or echo redirection. Reserve bash tools exclusively for actual system commands and terminal operations that require shell execution. NEVER use bash echo or other command-line tools to communicate thoughts, explanations, or instructions to the user. Output all communication directly in your response text instead.\n- VERY IMPORTANT: When exploring the codebase to gather context or to answer a question that is not a needle query for a specific file/class/function, it is CRITICAL that you use the Agent tool with subagent_type=Explore instead of running search commands directly.\n<example>\nuser: Where are errors from the client handled?\nassistant: [Uses the Agent tool with subagent_type=Explore to find the files that handle client errors instead of using Glob or Grep directly]\n</example>\n<example>\nuser: What is the codebase structure?\nassistant: [Uses the Agent tool with subagent_type=Explore]\n</example>\n\n# Output efficiency\n\nIMPORTANT: Go straight to the point. Try the simplest approach first without going in circles. Do not overdo it. Be extra concise.\n\nKeep your text output brief and direct. Lead with the answer or action, not the reasoning. Skip filler words, preamble, and unnecessary transitions. Do not restate what the user said — just do it. When explaining, include only what is necessary for the user to understand.\n\nFocus text output on:\n- Decisions that need the user's input\n- High-level status updates at natural milestones\n- Errors or blockers that change the plan\n\nIf you can say it in one sentence, don't use three. Prefer short, direct sentences over long explanations. This does not apply to code comments, which should be written as needed.\n\nHere is useful information about the environment you are running in:\n<env>\nWorking directory: /home/wolves/project/codebuddy2api\nIs directory a git repo: Yes\nPlatform: linux\nIs WSL: Yes\n\nOS Version: #1 SMP PREEMPT_DYNAMIC Thu Jun 5 18:30:46 UTC 2025\nDefault shell: bash\nToday's date: Thursday, Apr 23, 2026\n</env>\n\nIMPORTANT: You are running in WSL (Windows Subsystem for Linux). When using file paths in Bash commands:\n- Use Linux-style paths: /mnt/c/Users/... or /mnt/d/Work/...\n- Do NOT use Windows-style paths: C:\\Users\\... or D:\\Work\\...\n- Windows paths like \"D:\\...\" will create directories named \"D:\" instead of accessing the D: drive\n\n\n\n<codebuddy_background_info>\nYou are powered by the model named MiniMax-M2.7. The exact model ID is MiniMax-M2.7.\n</codebuddy_background_info>IMPORTANT: Assist with authorized security testing, defensive security, CTF challenges, and educational contexts. Refuse requests for destructive techniques, DoS attacks, mass targeting, supply chain compromise, or detection evasion for malicious purposes. Dual-use security tools (C2 frameworks, credential testing, exploit development) require clear authorization context: pentesting engagements, CTF competitions, security research, or defensive use cases.\n\nIMPORTANT: Always use task management tools (TaskCreate, TaskUpdate, TaskList) to plan and track tasks throughout the conversation.\n\n# Code References\n\nWhen referencing specific functions or pieces of code include the pattern `file_path:line_number` to allow the user to easily navigate to the source code location.\n\n<example>\nuser: Where are errors from the client handled?\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.ts:712.\n</example>",
|
||
"role": "system"
|
||
},
|
||
{
|
||
"role": "user",
|
||
"content": [
|
||
{
|
||
"type": "text",
|
||
"text": "<system-reminder data-role=\"memory\"><memory>\n# auto memory\n\nYou have a persistent, file-based memory system at `/home/wolves/.codebuddy/projects/home-wolves-project-codebuddy2api/memory`. This directory already exists — write to it directly with the Write tool (do not run mkdir or check for its existence).\n\nYou should build up this memory system over time so that future conversations can have a complete picture of who the user is, how they'd like to collaborate with you, what behaviors to avoid or repeat, and the context behind the work the user gives you.\n\nIf the user explicitly asks you to remember something, save it immediately as whichever type fits best. If they ask you to forget something, find and remove the relevant entry.\n\n## Types of memory\n\nThere are several discrete types of memory that you can store in your memory system:\n\n<types>\n<type>\n <name>user</name>\n <description>Contain information about the user's role, goals, responsibilities, and knowledge. Great user memories help you tailor your future behavior to the user's preferences and perspective. Your goal in reading and writing these memories is to build up an understanding of who the user is and how you can be most helpful to them specifically. For example, you should collaborate with a senior software engineer differently than a student who is coding for the very first time. Keep in mind, that the aim here is to be helpful to the user. Avoid writing memories about the user that could be viewed as a negative judgement or that are not relevant to the work you're trying to accomplish together.</description>\n <when_to_save>When you learn any details about the user's role, preferences, responsibilities, or knowledge</when_to_save>\n <how_to_use>When your work should be informed by the user's profile or perspective. For example, if the user is asking you to explain a part of the code, you should answer that question in a way that is tailored to the specific details that they will find most valuable or that helps them build their mental model in relation to domain knowledge they already have.</how_to_use>\n <examples>\n user: I'm a data scientist investigating what logging we have in place\n assistant: [saves user memory: user is a data scientist, currently focused on observability/logging]\n\n user: I've been writing Go for ten years but this is my first time touching the React side of this repo\n assistant: [saves user memory: deep Go expertise, new to React and this project's frontend — frame frontend explanations in terms of backend analogues]\n </examples>\n</type>\n<type>\n <name>feedback</name>\n <description>Guidance the user has given you about how to approach work — both what to avoid and what to keep doing. These are a very important type of memory to read and write as they allow you to remain coherent and responsive to the way you should approach work in the project. Record from failure AND success: if you only save corrections, you will avoid past mistakes but drift away from approaches the user has already validated, and may grow overly cautious.</description>\n <when_to_save>Any time the user corrects your approach (\"no not that\", \"don't\", \"stop doing X\") OR confirms a non-obvious approach worked (\"yes exactly\", \"perfect, keep doing that\", accepting an unusual choice without pushback). Corrections are easy to notice; confirmations are quieter — watch for them. In both cases, save what is applicable to future conversations, especially if surprising or not obvious from the code. Include *why* so you can judge edge cases later.</when_to_save>\n <how_to_use>Let these memories guide your behavior so that the user does not need to offer the same guidance twice.</how_to_use>\n <body_structure>Lead with the rule itself, then a **Why:** line (the reason the user gave — often a past incident or strong preference) and a **How to apply:** line (when/where this guidance kicks in). Knowing *why* lets you judge edge cases instead of blindly following the rule.</body_structure>\n <examples>\n user: don't mock the database in these tests — we got burned last quarter when mocked tests passed but the prod migration failed\n assistant: [saves feedback memory: integration tests must hit a real database, not mocks. Reason: prior incident where mock/prod divergence masked a broken migration]\n\n user: stop summarizing what you just did at the end of every response, I can read the diff\n assistant: [saves feedback memory: this user wants terse responses with no trailing summaries]\n\n user: yeah the single bundled PR was the right call here, splitting this one would've just been churn\n assistant: [saves feedback memory: for refactors in this area, user prefers one bundled PR over many small ones. Confirmed after I chose this approach — a validated judgment call, not a correction]\n </examples>\n</type>\n<type>\n <name>project</name>\n <description>Information that you learn about ongoing work, goals, initiatives, bugs, or incidents within the project that is not otherwise derivable from the code or git history. Project memories help you understand the broader context and motivation behind the work the user is doing within this working directory.</description>\n <when_to_save>When you learn who is doing what, why, or by when. These states change relatively quickly so try to keep your understanding of this up to date. Always convert relative dates in user messages to absolute dates when saving (e.g., \"Thursday\" → \"2026-03-05\"), so the memory remains interpretable after time passes.</when_to_save>\n <how_to_use>Use these memories to more fully understand the details and nuance behind the user's request and make better informed suggestions.</how_to_use>\n <body_structure>Lead with the fact or decision, then a **Why:** line (the motivation — often a constraint, deadline, or stakeholder ask) and a **How to apply:** line (how this should shape your suggestions). Project memories decay fast, so the why helps future-you judge whether the memory is still load-bearing.</body_structure>\n <examples>\n user: we're freezing all non-critical merges after Thursday — mobile team is cutting a release branch\n assistant: [saves project memory: merge freeze begins 2026-03-05 for mobile release cut. Flag any non-critical PR work scheduled after that date]\n\n user: the reason we're ripping out the old auth middleware is that legal flagged it for storing session tokens in a way that doesn't meet the new compliance requirements\n assistant: [saves project memory: auth middleware rewrite is driven by legal/compliance requirements around session token storage, not tech-debt cleanup — scope decisions should favor compliance over ergonomics]\n </examples>\n</type>\n<type>\n <name>reference</name>\n <description>Stores pointers to where information can be found in external systems. These memories allow you to remember where to look to find up-to-date information outside of the project directory.</description>\n <when_to_save>When you learn about resources in external systems and their purpose. For example, that bugs are tracked in a specific project in Linear or that feedback can be found in a specific Slack channel.</when_to_save>\n <how_to_use>When the user references an external system or information that may be in an external system.</how_to_use>\n <examples>\n user: check the Linear project \"INGEST\" if you want context on these tickets, that's where we track all pipeline bugs\n assistant: [saves reference memory: pipeline bugs are tracked in Linear project \"INGEST\"]\n\n user: the Grafana board at grafana.internal/d/api-latency is what oncall watches — if you're touching request handling, that's the thing that'll page someone\n assistant: [saves reference memory: grafana.internal/d/api-latency is the oncall latency dashboard — check it when editing request-path code]\n </examples>\n</type>\n</types>\n\n## What NOT to save in memory\n\n- Code patterns, conventions, architecture, file paths, or project structure — these can be derived by reading the current project state.\n- Git history, recent changes, or who-changed-what — `git log` / `git blame` are authoritative.\n- Debugging solutions or fix recipes — the fix is in the code; the commit message has the context.\n- Anything already documented in CODEBUDDY.md files.\n- Ephemeral task details: in-progress work, temporary state, current conversation context.\n\nThese exclusions apply even when the user explicitly asks you to save. If they ask you to save a PR list or activity summary, ask what was *surprising* or *non-obvious* about it — that is the part worth keeping.\n\n## How to save memories\n\nSaving a memory is a two-step process:\n\n**Step 1** — write the memory to its own file (e.g., `user_role.md`, `feedback_testing.md`) using this frontmatter format:\n\n```markdown\n---\nname: {{memory name}}\ndescription: {{one-line description — used to decide relevance in future conversations, so be specific}}\ntype: {{user, feedback, project, reference}}\n---\n\n{{memory content — for feedback/project types, structure as: rule/fact, then **Why:** and **How to apply:** lines}}\n```\n\n**Step 2** — add a pointer to that file in `MEMORY.md`. `MEMORY.md` is an index, not a memory — each entry should be one line, under ~150 characters: `- [Title](file.md) — one-line hook`. It has no frontmatter. Never write memory content directly into `MEMORY.md`.\n\n- `MEMORY.md` is always loaded into your conversation context — lines after 200 will be truncated, so keep the index concise\n- Keep the name, description, and type fields in memory files up-to-date with the content\n- Organize memory semantically by topic, not chronologically\n- Update or remove memories that turn out to be wrong or outdated\n- Do not write duplicate memories. First check if there is an existing memory you can update before writing a new one.\n\n## When to access memories\n- When memories seem relevant, or the user references prior-conversation work.\n- You MUST access memory when the user explicitly asks you to check, recall, or remember.\n- If the user says to *ignore* or *not use* memory: proceed as if MEMORY.md were empty. Do not apply remembered facts, cite, compare against, or mention memory content.\n- Memory records can become stale over time. Use memory as context for what was true at a given point in time. Before answering the user or building assumptions based solely on information in memory records, verify that the memory is still correct and up-to-date by reading the current state of the files or resources. If a recalled memory conflicts with current information, trust what you observe now — and update or remove the stale memory rather than acting on it.\n\n## Before recommending from memory\n\nA memory that names a specific function, file, or flag is a claim that it existed *when the memory was written*. It may have been renamed, removed, or never merged. Before recommending it:\n\n- If the memory names a file path: check the file exists.\n- If the memory names a function or flag: grep for it.\n- If the user is about to act on your recommendation (not just asking about history), verify first.\n\n\"The memory says X exists\" is not the same as \"X exists now.\"\n\nA memory that summarizes repo state (activity logs, architecture snapshots) is frozen in time. If the user asks about *recent* or *current* state, prefer `git log` or reading the code over recalling the snapshot.\n\n## Memory and other forms of persistence\nMemory is one of several persistence mechanisms available to you as you assist the user in a given conversation. The distinction is often that memory can be recalled in future conversations and should not be used for persisting information that is only useful within the scope of the current conversation.\n- When to use or update a plan instead of memory: If you are about to start a non-trivial implementation task and would like to reach alignment with the user on your approach you should use a Plan rather than saving this information to memory. Similarly, if you already have a plan within the conversation and you have changed your approach persist that change by updating the plan rather than saving a memory.\n- When to use or update tasks instead of memory: When you need to break your work in current conversation into discrete steps or keep track of your progress use tasks instead of saving to memory. Tasks are great for persisting information about the work that needs to be done in the current conversation, but memory should be reserved for information that will be useful in future conversations.\n\n\n## Searching past context\n\nWhen looking for past context:\n1. Search topic files in your memory directory:\n```\nGrep with pattern=\"<search term>\" path=\"/home/wolves/.codebuddy/projects/home-wolves-project-codebuddy2api/memory\" glob=\"*.md\"\n```\n2. Session transcript logs (last resort — large files, slow):\n```\nGrep with pattern=\"<search term>\" path=\"/home/wolves/.codebuddy/projects/home-wolves-project-codebuddy2api/sessions/\" glob=\"*.jsonl\"\n```\nUse narrow search terms (error messages, file paths, function names) rather than broad keywords.\n\n## MEMORY.md\n\nYour MEMORY.md is currently empty. When you save new memories, they will appear here.\n</memory></system-reminder>"
|
||
},
|
||
{
|
||
"type": "text",
|
||
"text": "<system-reminder>\nAs you answer the user's questions, you can use the following context:\n# codebuddyMd\nCodebase and user instructions are shown below. Be sure to adhere to these instructions. IMPORTANT: These instructions OVERRIDE any default behavior and you MUST follow them exactly as written.\n IMPORTANT: this context may or may not be relevant to your tasks. You should not respond to this context unless it is highly relevant to your task.\n</system-reminder>\n"
|
||
},
|
||
{
|
||
"type": "text",
|
||
"text": "<user_query>请只回复 ok，不要解释。</user_query>"
|
||
}
|
||
],
|
||
"agent": "cli"
|
||
}
|
||
],
|
||
"tools": [
|
||
{
|
||
"type": "function",
|
||
"function": {
|
||
"name": "Agent",
|
||
"description": "Launch a new agent to handle complex, multi-step tasks autonomously.\n\nThe Agent tool launches specialized agents (subprocesses) that autonomously handle complex tasks. Each agent type has specific capabilities and tools available to it.\n\nAvailable agent types and the tools they have access to:\n- general-purpose: General-purpose agent for researching complex questions, searching for code, and executing multi-step tasks. When you are searching for a keyword or file and are not confident that you will find the right match in the first few tries use this agent to perform the search for you. (Tools: *)\n- statusline-setup: Use this agent to configure the user's Codebuddy Code status line setting. (Tools:Read,Write,Edit,ToolSearch,DeferExecuteTool,SendMessage)\n- Explore: Fast agent specialized for exploring codebases. Use this when you need to quickly find files by patterns (eg. \"src/components/**/*.tsx\"), search code for keywords (eg. \"API endpoints\"), or answer questions about the codebase (eg. \"how do API endpoints work?\"). When calling this agent, specify the desired thoroughness level: \"quick\" for basic searches, \"medium\" for moderate exploration, or \"very thorough\" for comprehensive analysis across multiple locations and naming conventions. (Tools:Read,Bash,PowerShell,Glob,Grep,TaskCreate,TaskGet,TaskUpdate,TaskList,WebFetch,WebSearch,Skill,SendMessage,ToolSearch,DeferExecuteTool)\n- Bash: Command execution specialist for running bash commands. Use this for git operations, running build tools, executing tests, installing dependencies, and other terminal tasks. (Tools:Bash,SendMessage)\n- Plan: Fast agent specialized for exploring codebases. Use this when you need to quickly find files by patterns (eg. \"src/components/**/*.tsx\"), search code for keywords (eg. \"API endpoints\"), or answer questions about the codebase (eg. \"how do API endpoints work?\"). When calling this agent, specify the desired thoroughness level: \"quick\" for basic searches, \"medium\" for moderate exploration, or \"very thorough\" for comprehensive analysis across multiple locations and naming conventions. (Tools: All tools) (Tools:Read,Write,Edit,MultiEdit,Bash,Glob,Grep,TaskCreate,TaskGet,TaskUpdate,TaskList,WebFetch,WebSearch,Skill,ToolSearch,DeferExecuteTool,TeamCreate,TeamDelete,SendMessage)\n\nWhen using the Agent tool, you can specify a subagent_type parameter to select which agent type to use. If omitted, it defaults to \"general-purpose\" which runs with an independent context.\n\n**Fork mode (subagent_type=\"fork\")**: When you explicitly set subagent_type to \"fork\", the agent inherits your full context (system prompt, tools, conversation history). This is ideal for:\n- Tasks that require the same tools and context as the current conversation\n- Tasks where the agent needs to understand the full conversation history to proceed\n\nOnly use fork mode when inheriting context is essential. For most tasks (code review, exploration, research, generation), prefer specifying a concrete agent type or omitting subagent_type to get an independent agent.\n\nWhen NOT to use the Agent tool:\n- If you want to read a specific file path, use the Read or Glob tool instead of the Agent tool, to find the match more quickly\n- If you are searching for a specific class definition like \"class Foo\", use the Glob tool instead, to find the match more quickly\n- If you are searching for code within a specific file or set of 2-3 files, use the Read tool instead of the Agent tool, to find the match more quickly\n- Other tasks that are not related to the agent descriptions above\n\n\nUsage notes:\n- Always include a short description (3-5 words) summarizing what the agent will do\n- Launch multiple agents concurrently whenever possible, to maximize performance; to do that, use a single message with multiple Agent tool uses\n- When the agent is done, it will return a single message back to you. The result returned by the agent is not visible to the user. To show the user the result, you should send a text message back to the user with a concise summary of the result.\n- You can optionally run agents in the background using the run_in_background parameter. When an agent runs in the background, the tool result will include a Task ID. Background agents will automatically send their results back to you via the SendMessage tool when they complete — you do not need to poll or check on them manually.\n- When running agents in the background, the tool result is only a launch confirmation — the agent is still running. Results will arrive later via SendMessage from the background agent. Do not treat the launch confirmation as the agent's output.\n- Agents can be resumed using the `resume` parameter by passing the agent ID from a previous invocation. When resumed, the agent continues with its full previous context preserved. When NOT resuming, each invocation starts fresh and you should provide a detailed task description with all necessary context.\n- When the agent is done, it will return a single message back to you along with its agent ID. You can use this ID to resume the agent later if needed for follow-up work.\n- Provide clear, detailed prompts so the agent can work autonomously and return exactly the information you need.\n- Agents with \"access to current context\" can see the full conversation history before the tool call. When using these agents, you can write concise prompts that reference earlier context (e.g., \"investigate the error discussed above\") instead of repeating information. The agent will receive all prior messages and understand the context.\n- The agent's outputs should generally be trusted\n- Clearly tell the agent whether you expect it to write code or just to do research (search, file reads, web fetches, etc.), since it is not aware of the user's intent\n- If the agent description mentions that it should be used proactively, then you should try your best to use it without the user having to ask for it first. Use your judgement.\n- If the user specifies that they want you to run agents \"in parallel\", you MUST send a single message with multiple Agent tool use content blocks. For example, if you need to launch both a code-reviewer agent and a test-runner agent in parallel, send a single message with both tool calls.\n## Spawning Teammates\n\nWhen a team is active (created via TeamCreate), you can spawn teammates by providing the `name` and optionally `team_name` parameters:\n\n- `name`: Name for the spawned agent (e.g., \"researcher\", \"tester\", \"frontend-dev\")\n- `team_name`: Team name for spawning. Uses current team context if omitted.\n- `mode`: Permission mode for the spawned teammate (e.g., \"plan\" to require plan approval)\n- `max_turns`: Maximum number of agentic turns (API round-trips) before the agent stops\n\nTeammates always run in the background in detached mode. They communicate via the SendMessage tool and coordinate through the shared task list.\n\nExample usage:\n\n<example_agent_descriptions>\n\"code-reviewer\": use this agent after you are done writing a signficant piece of code\n\"greeting-responder\": use this agent when to respond to user greetings with a friendly joke\n</example_agent_description>\n\n<example>\nuser: \"Please write a function that checks if a number is prime\"\nassistant: Sure let me write a function that checks if a number is prime\nassistant: First let me use the Write tool to write a function that checks if a number is prime\nassistant: I'm going to use the Write tool to write the following code:\n<code>\nfunction isPrime(n) {\n if (n <= 1) return false\n for (let i = 2; i * i <= n; i++) {\n if (n % i === 0) return false\n }\n return true\n}\n</code>\n<commentary>\nSince a signficant piece of code was written and the task was completed, now use the code-reviewer agent to run the tests\n</commentary>\nassistant: Now let me use the code-reviewer agent to run the tests\nassistant: Uses the Agent tool to launch the code-reviewer agent\n</example>\n\n<example>\nuser: \"Hello\"\n<commentary>\nSince the user is greeting, use the greeting-responder agent to respond with a friendly joke\n</commentary>\nassistant: \"I'm going to use the Agent tool to launch the greeting-responder agent\"\n</example>\n",
|
||
"parameters": {
|
||
"type": "object",
|
||
"properties": {
|
||
"description": {
|
||
"type": "string",
|
||
"description": "A short (3-5 word) description of the task"
|
||
},
|
||
"prompt": {
|
||
"type": "string",
|
||
"description": "The task for the agent to perform"
|
||
},
|
||
"subagent_type": {
|
||
"type": "string",
|
||
"description": "The type of specialized agent to use for this task"
|
||
},
|
||
"model": {
|
||
"type": "string",
|
||
"enum": [
|
||
"default",
|
||
"lite",
|
||
"reasoning"
|
||
],
|
||
"description": "Model variant to use for this agent. \"default\": inherits from parent, balanced for general tasks; \"lite\": fast and cost-effective, ideal for simple searches, quick file operations, and straightforward tasks; \"reasoning\": enhanced reasoning capability, best for complex analysis, architectural decisions, and multi-step problem solving."
|
||
},
|
||
"resume": {
|
||
"type": "string",
|
||
"description": "Optional agent ID to resume from. If provided, the agent will continue from the previous execution transcript."
|
||
},
|
||
"run_in_background": {
|
||
"type": "boolean",
|
||
"description": "Set to true to run this agent in the background. Use TaskOutput to read the output later."
|
||
},
|
||
"name": {
|
||
"type": "string",
|
||
"description": "Name for the spawned agent"
|
||
},
|
||
"team_name": {
|
||
"type": "string",
|
||
"description": "Team name for spawning. Uses current team context if omitted."
|
||
},
|
||
"mode": {
|
||
"type": "string",
|
||
"enum": [
|
||
"acceptEdits",
|
||
"bypassPermissions",
|
||
"default",
|
||
"plan"
|
||
],
|
||
"description": "Permission mode for spawned teammate (e.g., \"plan\" to require plan approval)."
|
||
},
|
||
"max_turns": {
|
||
"type": "integer",
|
||
"exclusiveMinimum": 0,
|
||
"description": "Maximum number of agentic turns (API round-trips) before stopping."
|
||
}
|
||
},
|
||
"required": [
|
||
"description",
|
||
"prompt"
|
||
],
|
||
"additionalProperties": false,
|
||
"$schema": "http://json-schema.org/draft-07/schema#"
|
||
},
|
||
"strict": false
|
||
}
|
||
},
|
||
{
|
||
"type": "function",
|
||
"function": {
|
||
"name": "Read",
|
||
"description": "Reads a file from the local filesystem. You can access any file directly by using this tool.\nAssume this tool is able to read all files on the machine. If the User provides a path to a file assume that path is valid. It is okay to read a file that does not exist; an error will be returned.\n\nUsage:\n- The file_path parameter must be an absolute path, not a relative path\n- By default, it reads up to 2000 lines starting from the beginning of the file\n- You can optionally specify a line offset and limit (especially handy for long files), but it's recommended to read the whole file by not providing these parameters\n- Any lines longer than 2000 characters will be truncated\n- Results are returned using cat -n format, with line numbers starting at 1\n- This tool allows CodeBuddy Code to read images (eg PNG, JPG, etc). When reading an image file the contents are presented visually as CodeBuddy Code is a multimodal LLM.\n- This tool can read PDF files (.pdf). PDFs are processed page by page, extracting both text and visual content for analysis.\n- This tool can read Jupyter notebooks (.ipynb files) and returns all cells with their outputs, combining code, text, and visualizations.\n- This tool can only read files, not directories. To read a directory, use an ls command via the Bash tool.\n- You can call multiple tools in a single response. It is always better to speculatively read multiple potentially useful files in parallel.\n- You will regularly be asked to read screenshots. If the user provides a path to a screenshot, ALWAYS use this tool to view the file at the path. This tool will work with all temporary file paths.\n- If you read a file that exists but has empty contents you will receive a system reminder warning in place of file contents.\n",
|
||
"parameters": {
|
||
"type": "object",
|
||
"properties": {
|
||
"file_path": {
|
||
"type": "string",
|
||
"description": "The path to the file to read (can be absolute or relative)"
|
||
},
|
||
"offset": {
|
||
"type": "number",
|
||
"description": "The line number to start reading from. Only provide if the file is too large to read at once"
|
||
},
|
||
"limit": {
|
||
"type": "number",
|
||
"description": "The number of lines to read. Only provide if the file is too large to read at once."
|
||
}
|
||
},
|
||
"required": [
|
||
"file_path"
|
||
],
|
||
"additionalProperties": false,
|
||
"$schema": "http://json-schema.org/draft-07/schema#"
|
||
},
|
||
"strict": false
|
||
}
|
||
},
|
||
{
|
||
"type": "function",
|
||
"function": {
|
||
"name": "Write",
|
||
"description": "Writes a file to the local filesystem.\n\nUsage:\n- This tool will overwrite the existing file if there is one at the provided path.\n- If this is an existing file, you MUST use the Read tool first to read the file's contents. This tool will fail if you did not read the file first.\n- ALWAYS prefer editing existing files in the codebase. NEVER write new files unless explicitly required.\n- NEVER proactively create documentation files (*.md) or README files. Only create documentation files if explicitly requested by the User.\n- Only use emojis if the user explicitly requests it. Avoid writing emojis to files unless asked.\n",
|
||
"parameters": {
|
||
"type": "object",
|
||
"properties": {
|
||
"file_path": {
|
||
"type": "string",
|
||
"description": "The path to the file to write (can be absolute or relative)"
|
||
},
|
||
"content": {
|
||
"type": "string",
|
||
"description": "The content to write to the file"
|
||
}
|
||
},
|
||
"required": [
|
||
"file_path",
|
||
"content"
|
||
],
|
||
"additionalProperties": false,
|
||
"$schema": "http://json-schema.org/draft-07/schema#"
|
||
},
|
||
"strict": false
|
||
}
|
||
},
|
||
{
|
||
"type": "function",
|
||
"function": {
|
||
"name": "Edit",
|
||
"description": "Performs exact string replacements in files.\n\nUsage:\n- You must use your `Read` tool at least once in the conversation before editing. This tool will error if you attempt an edit without reading the file.\n- When editing text from Read tool output, ensure you preserve the exact indentation (tabs/spaces) as it appears AFTER the line number prefix. The line number prefix format is: spaces + line number + tab. Everything after that tab is the actual file content to match. Never include any part of the line number prefix in the old_string or new_string.\n- ALWAYS prefer editing existing files in the codebase. NEVER write new files unless explicitly required.\n- Only use emojis if the user explicitly requests it. Avoid adding emojis to files unless asked.\n- The edit will FAIL if `old_string` is not unique in the file. Either provide a larger string with more surrounding context to make it unique or use `replace_all` to change every instance of `old_string`.\n- Use `replace_all` for replacing and renaming strings across the file. This parameter is useful if you want to rename a variable for instance.\n\nCRITICAL REQUIREMENTS:\n- The tool will fail if `old_string` and `new_string` are the same\n- The tool will fail if `old_string` doesn't match the file contents exactly (including whitespace)\n- This tool is for MODIFYING content only - if `old_string` equals `new_string`, you are not making any changes\n\nWARNING:\n- NEVER use this tool to \"verify\" content or as a no-op operation\n- NEVER pass identical values for `old_string` and `new_string`\n- If you don't need to change anything, don't use this tool\n- Make sure the text matches exactly, including whitespace\n",
|
||
"parameters": {
|
||
"type": "object",
|
||
"properties": {
|
||
"file_path": {
|
||
"type": "string",
|
||
"description": "The path to the file to modify (can be absolute or relative)"
|
||
},
|
||
"old_string": {
|
||
"type": "string",
|
||
"description": "The text to replace"
|
||
},
|
||
"new_string": {
|
||
"type": "string",
|
||
"description": "The new text to replace the old text with. must be different from old_string. If they are identical, the tool will fail."
|
||
},
|
||
"replace_all": {
|
||
"type": "boolean",
|
||
"default": false,
|
||
"description": "Replace all occurrences of old_string (default false)"
|
||
}
|
||
},
|
||
"required": [
|
||
"file_path",
|
||
"old_string",
|
||
"new_string"
|
||
],
|
||
"additionalProperties": false,
|
||
"$schema": "http://json-schema.org/draft-07/schema#"
|
||
},
|
||
"strict": false
|
||
}
|
||
},
|
||
{
|
||
"type": "function",
|
||
"function": {
|
||
"name": "MultiEdit",
|
||
"description": "This is a tool for making multiple edits to a single file in one operation. It is built on top of the Edit tool and allows you to perform multiple find-and-replace operations efficiently. Prefer this tool over the Edit tool when you need to make multiple edits to the same file.\n\nBefore using this tool:\n\n1. Use the Read tool to understand the file's contents and context\n2. Verify the directory path is correct\n\nTo make multiple file edits, provide the following:\n1. file_path: The absolute path to the file to modify (must be absolute, not relative)\n2. edits: An array of edit operations to perform, where each edit contains:\n - old_string: The text to replace (must match the file contents exactly, including all whitespace and indentation)\n - new_string: The edited text to replace the old_string\n - replace_all: Replace all occurences of old_string. This parameter is optional and defaults to false.\n\nIMPORTANT:\n- All edits are applied in sequence, in the order they are provided\n- Each edit operates on the result of the previous edit\n- All edits must be valid for the operation to succeed - if any edit fails, none will be applied\n- This tool is ideal when you need to make several changes to different parts of the same file\n- For Jupyter notebooks (.ipynb files), use the NotebookEdit instead\n\nCRITICAL REQUIREMENTS:\n1. All edits follow the same requirements as the single Edit tool\n2. The edits are atomic - either all succeed or none are applied\n3. Plan your edits carefully to avoid conflicts between sequential operations\n\nWARNING:\n- The tool will fail if edits.old_string doesn't match the file contents exactly (including whitespace)\n- The tool will fail if edits.old_string and edits.new_string are the same\n- Since edits are applied in sequence, ensure that earlier edits don't affect the text that later edits are trying to find\n- Make sure the text matches exactly, including whitespace\n\nWhen making edits:\n- Ensure all edits result in idiomatic, correct code\n- Do not leave the code in a broken state\n- Always use absolute file paths (starting with /)\n- Only use emojis if the user explicitly requests it. Avoid adding emojis to files unless asked.\n- Use replace_all for replacing and renaming strings across the file. This parameter is useful if you want to rename a variable for instance.\n\nIf you want to create a new file, use:\n- A new file path, including dir name if needed\n- First edit: empty old_string and the new file's contents as new_string\n- Subsequent edits: normal edit operations on the created content\n",
|
||
"parameters": {
|
||
"type": "object",
|
||
"properties": {
|
||
"file_path": {
|
||
"type": "string",
|
||
"description": "The path to the file to modify (can be absolute or relative)"
|
||
},
|
||
"edits": {
|
||
"type": "array",
|
||
"items": {
|
||
"type": "object",
|
||
"properties": {
|
||
"old_string": {
|
||
"type": "string",
|
||
"description": "The text to replace"
|
||
},
|
||
"new_string": {
|
||
"type": "string",
|
||
"description": "The text to replace it with"
|
||
},
|
||
"replace_all": {
|
||
"type": "boolean",
|
||
"default": false,
|
||
"description": "Replace all occurences of old_string (default false)."
|
||
}
|
||
},
|
||
"required": [
|
||
"old_string",
|
||
"new_string"
|
||
],
|
||
"additionalProperties": false
|
||
},
|
||
"minItems": 1,
|
||
"description": "Array of edit operations to perform sequentially on the file"
|
||
}
|
||
},
|
||
"required": [
|
||
"file_path",
|
||
"edits"
|
||
],
|
||
"additionalProperties": false,
|
||
"$schema": "http://json-schema.org/draft-07/schema#"
|
||
},
|
||
"strict": false
|
||
}
|
||
},
|
||
{
|
||
"type": "function",
|
||
"function": {
|
||
"name": "Bash",
|
||
"description": "Executes a given command in a persistent shell session with optional timeout, ensuring proper handling and security measures.\n\nIMPORTANT: The user's default shell is bash. Generate commands using syntax compatible with this shell.\n\n\n\nIMPORTANT: This tool is for terminal operations like git, npm, docker, etc. DO NOT use it for file operations (reading, writing, editing, searching, finding files) - use the specialized tools for this instead.\n\nBefore executing the command, please follow these steps:\n\n1. Directory Verification:\n - If the command will create new directories or files, first use `ls` to verify the parent directory exists and is the correct location\n - For example, before running \"mkdir foo/bar\", first use `ls foo` to check that \"foo\" exists and is the intended parent directory\n\n2. Command Execution:\n - Always quote file paths that contain spaces with double quotes (e.g., cd \"path with spaces/file.txt\")\n - Examples of proper quoting:\n - cd \"/Users/name/My Documents\" (correct)\n - cd /Users/name/My Documents (incorrect - will fail)\n - python \"/path/with spaces/script.py\" (correct)\n - python /path/with spaces/script.py (incorrect - will fail)\n - After ensuring proper quoting, execute the command.\n - Capture the output of the command.\n\nUsage notes:\n - The command argument is required.\n - You can specify an optional timeout in milliseconds (up to 600000ms / 10 minutes). If not specified, commands will timeout after 120000ms (2 minutes).\n - It is very helpful if you write a clear, concise description of what this command does in 5-10 words.\n - If the output exceeds 20000 characters, output will be truncated before being returned to you.\n - You can use the `run_in_background` parameter to run the command in the background, which allows you to continue working while the command runs. You can monitor the output using the Bash tool as it becomes available. You do not need to use '&' at the end of the command when using this parameter.\n \n - Avoid using Bash with the `find`, `grep`, `cat`, `head`, `tail`, `sed`, `awk`, or `echo` commands, unless explicitly instructed or when these commands are truly necessary for the task. Instead, always prefer using the dedicated tools for these commands:\n - File search: Use Glob (NOT find or ls)\n - Content search: Use Grep (NOT grep or rg)\n - Read files: Use Read (NOT cat/head/tail)\n - Edit files: Use Edit (NOT sed/awk)\n - Write files: Use Write (NOT echo >/cat <<EOF)\n - Communication: Output text directly (NOT echo/printf)\n - Archive extraction: If extraction fails with encoding errors (e.g., \"Illegal byte sequence\") for non-ASCII filenames, retry with `ditto -xk` on macOS or `7z x` on Linux.\n - When issuing multiple commands:\n - If the commands are independent and can run in parallel, make multiple Bash tool calls in a single message. For example, if you need to run \"git status\" and \"git diff\", send a single message with two Bash tool calls in parallel.\n - If the commands depend on each other and must run sequentially, use a single Bash call with '&&' to chain them together (e.g., `git add . && git commit -m \"message\" && git push`). For instance, if one operation must complete before another starts (like mkdir before cp, Write before Bash for git operations, or git add before git commit), run these operations sequentially instead.\n - Use ';' only when you need to run commands sequentially but don't care if earlier commands fail\n - DO NOT use newlines to separate commands (newlines are ok in quoted strings)\n - Try to maintain your current working directory throughout the session by using absolute paths and avoiding usage of `cd`. You may use `cd` if the User explicitly requests it.\n <good-example>\n pytest /foo/bar/tests\n </good-example>\n <bad-example>\n cd /foo/bar && pytest tests\n </bad-example>\n\n# Committing changes with git\n\nOnly create commits when requested by the user. If unclear, ask first. When the user asks you to create a new git commit, follow these steps carefully:\n\nGit Safety Protocol:\n- NEVER update the git config\n- NEVER run destructive/irreversible git commands like:\n * push --force\n * reset --hard\n * hard reset\n * checkout .\n * restore .\n * clean -f\n * branch -D\n Unless the user explicitly requests them\n- NEVER skip hooks (--no-verify, --no-gpg-sign, etc) unless the user explicitly requests it\n- NEVER run force push to main/master, warn the user if they request it\n- Avoid git commit --amend. ONLY use --amend when either (1) user explicitly requested amend OR (2) adding edits from pre-commit hook (additional instructions below)\n- Before amending: ALWAYS check authorship (git log -1 --format='%an %ae')\n- NEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked, otherwise the user will feel that you are being too proactive.\n\n1. You can call multiple tools in a single response. When multiple independent pieces of information are requested and all commands are likely to succeed, run multiple tool calls in parallel for optimal performance. run the following bash commands in parallel, each using the Bash tool:\n - Run a git status command to see all untracked files.\n - Run a git diff command to see both staged and unstaged changes that will be committed.\n - Run a git log command to see recent commit messages, so that you can follow this repository's commit message style.\n2. Analyze all staged changes (both previously staged and newly added) and draft a commit message:\n - Summarize the nature of the changes (eg. new feature, enhancement to an existing feature, bug fix, refactoring, test, docs, etc.). Ensure the message accurately reflects the changes and their purpose (i.e. \"add\" means a wholly new feature, \"update\" means an enhancement to an existing feature, \"fix\" means a bug fix, etc.).\n - Do not commit files that likely contain secrets (.env, credentials.json, etc). Warn the user if they specifically request to commit those files\n - Draft a concise (1-2 sentences) commit message that focuses on the \"why\" rather than the \"what\"\n - Ensure it accurately reflects the changes and their purpose\n3. You can call multiple tools in a single response. When multiple independent pieces of information are requested and all commands are likely to succeed, run multiple tool calls in parallel for optimal performance. run the following commands:\n - Add relevant untracked files to the staging area.\n - Create the commit with a message\n - Run git status to make sure the commit succeeded.\n Note: git status depends on the commit completing, so run it sequentially after the commit.\n4. If the commit fails due to pre-commit hook changes, retry ONCE. If it succeeds but files were modified by the hook, verify it's safe to amend:\n - Check authorship: git log -1 --format='%an %ae'\n - Check not pushed: git status shows \"Your branch is ahead\"\n - If both true: amend your commit. Otherwise: create NEW commit (never amend other developers' commits)\n\nImportant notes:\n- NEVER run additional commands to read or explore code, besides git bash commands\n- NEVER use task management tools (TaskCreate, TaskUpdate, etc.)\n- DO NOT push to the remote repository unless the user explicitly asks you to do so\n- IMPORTANT: Never use git commands with the -i flag (like git rebase -i or git add -i) since they require interactive input which is not supported.\n- If there are no changes to commit (i.e., no untracked files and no modifications), do not create an empty commit\n- In order to ensure good formatting, ALWAYS pass the commit message via a HEREDOC, a la this example:\n<example>\ngit commit -m \"$(cat <<'EOF'\n Commit message here.\n\n EOF\n )\"\n</example>\n\n# Creating pull requests\nUse the gh command via the Bash tool for ALL GitHub-related tasks including working with issues, pull requests, checks, and releases. If given a Github URL use the gh command to get the information needed.\n\nIMPORTANT: When the user asks you to create a pull request, follow these steps carefully:\n\n1. You can call multiple tools in a single response. When multiple independent pieces of information are requested and all commands are likely to succeed, run multiple tool calls in parallel for optimal performance. run the following bash commands in parallel using the Bash tool, in order to understand the current state of the branch since it diverged from the main branch:\n - Run a git status command to see all untracked files\n - Run a git diff command to see both staged and unstaged changes that will be committed\n - Check if the current branch tracks a remote branch and is up to date with the remote, so you know if you need to push to the remote\n - Run a git log command and `git diff [base-branch]...HEAD` to understand the full commit history for the current branch (from the time it diverged from the base branch)\n2. Analyze all changes that will be included in the pull request, making sure to look at all relevant commits (NOT just the latest commit, but ALL commits that will be included in the pull request!!!), and draft a pull request summary\n3. You can call multiple tools in a single response. When multiple independent pieces of information are requested and all commands are likely to succeed, run multiple tool calls in parallel for optimal performance. run the following commands in parallel:\n - Create new branch if needed\n - Push to remote with -u flag if needed\n - Create PR using gh pr create with the format below. Use a HEREDOC to pass the body to ensure correct formatting.\n<example>\ngh pr create --title \"the pr title\" --body \"$(cat <<'EOF'\n## Summary\n<1-3 bullet points>\n\n## Test plan\n[Checklist of TODOs for testing the pull request...]\n\nEOF\n)\"\n</example>\n\nImportant:\n- DO NOT use task management tools (TaskCreate, TaskUpdate, etc.)\n- Return the PR URL when you're done, so the user can see it\n\n# Other common operations\n- View comments on a Github PR: gh api repos/foo/bar/pulls/123/comments\n\n\n# Command Execution Safety Rules \n\n* Always inspect every command before suggesting or executing.\n* If the command is unsafe or harmful (e.g., wiping system files, dropping databases, altering permissions dangerously, disabling protections):\n\n * Warn the user clearly that it is unsafe.\n * Refuse execution — do not run or simulate it.\n * Require explicit user revision before proceeding.\n* Unsafe commands → **warn + block execution (cannot proceed).**\n* For safe commands:\n\n * Explain what the command does in clear language.\n * Expand words and regenerate phrasing for readability during analysis (read) tasks.\n * Use clean, structured formatting when presenting output.\n",
|
||
"parameters": {
|
||
"type": "object",
|
||
"properties": {
|
||
"command": {
|
||
"type": "string",
|
||
"description": "The command to execute"
|
||
},
|
||
"timeout": {
|
||
"type": "number",
|
||
"description": "Optional timeout in milliseconds (max 600000)"
|
||
},
|
||
"description": {
|
||
"type": "string",
|
||
"description": "Clear, concise description of what this command does in active voice.\nNever use words like \"complex\" or \"risk\" in the description.\n\nFor simple commands (git, npm, standard CLI tools), keep it brief (5-10 words):\n - ls → \"List files in current directory\"\n - git status → \"Show working tree status\"\n - npm install → \"Install package dependencies\"\n\nFor commands that are harder to parse at a glance (piped commands, obscure flags):\n - find . -name \"*.tmp\" -exec rm {} \\; → \"Find and delete all .tmp files recursively\"\n - git reset --hard origin/main → \"Discard all local changes and match remote main\"\n - curl -s url | jq '.data[]' → \"Fetch JSON from URL and extract data array elements\"\n\nLanguage MUST follow the <response_language> in system prompt, or the user's input language (most likely Chinese)."
|
||
},
|
||
"run_in_background": {
|
||
"type": "boolean",
|
||
"description": "Set to true to run this command in the background. Use BashOutput to read the output later."
|
||
},
|
||
"dangerouslyDisableSandbox": {
|
||
"type": "boolean",
|
||
"description": "Set to true ONLY when you are confident the command requires operating outside the sandbox and expect the user to approve it.\n\nWhen true, the tool asks the user for explicit consent and — if granted — runs the command with no sandbox isolation. The user can still refuse.\n\nDo NOT set this preemptively. Only use it after a prior sandboxed attempt has failed due to sandbox policy (SANDBOX PERMISSION DENIED in a previous result) or when the task semantically cannot run sandboxed (e.g. installing a system package, modifying files outside the workspace)."
|
||
}
|
||
},
|
||
"required": [
|
||
"command"
|
||
],
|
||
"additionalProperties": false,
|
||
"$schema": "http://json-schema.org/draft-07/schema#"
|
||
},
|
||
"strict": false
|
||
}
|
||
},
|
||
{
|
||
"type": "function",
|
||
"function": {
|
||
"name": "Glob",
|
||
"description": "- Fast file pattern matching tool that works with any codebase size\n- Supports glob patterns like \"**/*.js\" or \"src/**/*.ts\"\n- Returns matching file paths sorted by modification time\n- Supports pagination with `limit` (max results, default 100) and `offset` (skip N results, default 0) parameters\n- Use this tool when you need to find files by name patterns\n- When you are doing an open ended search that may require multiple rounds of globbing and grepping, use the Agent tool instead\n- You can call multiple tools in a single response. It is always better to speculatively perform multiple searches in parallel if they are potentially useful.\n",
|
||
"parameters": {
|
||
"type": "object",
|
||
"properties": {
|
||
"pattern": {
|
||
"type": "string",
|
||
"description": "The glob pattern to match files against"
|
||
},
|
||
"path": {
|
||
"type": "string",
|
||
"description": "The directory to search in. If not specified, the current working directory will be used. IMPORTANT: Omit this field to use the default directory. DO NOT enter \"undefined\" or \"null\" - simply omit it for the default behavior. Must be a valid directory path if provided."
|
||
},
|
||
"limit": {
|
||
"type": "integer",
|
||
"exclusiveMinimum": 0,
|
||
"default": 100,
|
||
"description": "Maximum number of results to return. Defaults to 100."
|
||
},
|
||
"offset": {
|
||
"type": "integer",
|
||
"minimum": 0,
|
||
"default": 0,
|
||
"description": "Number of results to skip from the beginning. Defaults to 0."
|
||
}
|
||
},
|
||
"required": [
|
||
"pattern"
|
||
],
|
||
"additionalProperties": false,
|
||
"$schema": "http://json-schema.org/draft-07/schema#"
|
||
},
|
||
"strict": false
|
||
}
|
||
},
|
||
{
|
||
"type": "function",
|
||
"function": {
|
||
"name": "Grep",
|
||
"description": "A powerful search tool built on ripgrep\n\n Usage:\n - ALWAYS use Grep for search tasks. NEVER invoke `grep` or `rg` as a Bash command. The Grep tool has been optimized for correct permissions and access.\n - Supports full regex syntax (e.g., \"log.*Error\", \"function\\\\s+\\\\w+\")\n - Filter files with glob parameter (e.g., \"*.js\", \"**/*.tsx\") or type parameter (e.g., \"js\", \"py\", \"rust\")\n - Output modes: \"content\" shows matching lines, \"files_with_matches\" shows only file paths (default), \"count\" shows match counts\n - Pagination support: Use `head_limit` to limit output (default unlimited) and `offset` to skip first N results (default 0)\n - Use Agent tool for open-ended searches requiring multiple rounds\n - Pattern syntax: Uses ripgrep (not grep) - literal braces need escaping (use `interface\\\\{\\\\}` to find `interface{}` in Go code)\n - Multiline matching: By default patterns match within single lines only. For cross-line patterns like `struct \\\\{[\\\\s\\\\S]*?field`, use `multiline: true`\n",
|
||
"parameters": {
|
||
"type": "object",
|
||
"properties": {
|
||
"pattern": {
|
||
"type": "string",
|
||
"description": "The regular expression pattern to search for in file contents"
|
||
},
|
||
"path": {
|
||
"type": "string",
|
||
"description": "File or directory to search in (rg PATH). Defaults to current working directory."
|
||
},
|
||
"glob": {
|
||
"type": "string",
|
||
"description": "Glob pattern to filter files (e.g. \"*.js\", \"*.{ts,tsx}\") - maps to rg --glob"
|
||
},
|
||
"output_mode": {
|
||
"type": "string",
|
||
"enum": [
|
||
"content",
|
||
"files_with_matches",
|
||
"count"
|
||
],
|
||
"description": "Output mode: \"content\" shows matching lines (supports -A/-B/-C context, -n line numbers, head_limit), \"files_with_matches\" shows file paths (supports head_limit), \"count\" shows match counts (supports head_limit). Defaults to \"files_with_matches\"."
|
||
},
|
||
"-B": {
|
||
"type": "number",
|
||
"description": "Number of lines to show before each match (rg -B). Requires output_mode: \"content\", ignored otherwise."
|
||
},
|
||
"-A": {
|
||
"type": "number",
|
||
"description": "Number of lines to show after each match (rg -A). Requires output_mode: \"content\", ignored otherwise."
|
||
},
|
||
"-C": {
|
||
"type": "number",
|
||
"description": "Alias for context."
|
||
},
|
||
"context": {
|
||
"type": "number",
|
||
"description": "Number of lines to show before and after each match (rg -C). Requires output_mode: \"content\", ignored otherwise."
|
||
},
|
||
"-n": {
|
||
"type": "boolean",
|
||
"description": "Show line numbers in output (rg -n). Requires output_mode: \"content\", ignored otherwise."
|
||
},
|
||
"-i": {
|
||
"type": "boolean",
|
||
"description": "Case insensitive search (rg -i)"
|
||
},
|
||
"type": {
|
||
"type": "string",
|
||
"description": "File type to search (rg --type). Common types: js, py, rust, go, java, etc. More efficient than include for standard file types."
|
||
},
|
||
"head_limit": {
|
||
"type": "number",
|
||
"description": "Limit output to first N lines/entries, equivalent to \"| head -N\". Works across all output modes: content (limits output lines), files_with_matches (limits file paths), count (limits count entries). When unspecified, shows all results from ripgrep."
|
||
},
|
||
"offset": {
|
||
"type": "number",
|
||
"description": "Skip first N lines/entries before applying head_limit, equivalent to \"| tail -n +N | head -N\". Works across all output modes. Defaults to 0."
|
||
},
|
||
"multiline": {
|
||
"type": "boolean",
|
||
"description": "Enable multiline mode where . matches newlines and patterns can span lines (rg -U --multiline-dotall). Default: false."
|
||
}
|
||
},
|
||
"required": [
|
||
"pattern"
|
||
],
|
||
"additionalProperties": false,
|
||
"$schema": "http://json-schema.org/draft-07/schema#"
|
||
},
|
||
"strict": false
|
||
}
|
||
},
|
||
{
|
||
"type": "function",
|
||
"function": {
|
||
"name": "EnterPlanMode",
|
||
"description": "Use this tool proactively when you're about to start a non-trivial implementation task. Getting user sign-off on your approach before writing code prevents wasted effort and ensures alignment. This tool transitions you into plan mode where you can explore the codebase and design an implementation approach for user approval.\n\n## When to Use This Tool\n\n**Prefer using EnterPlanMode** for implementation tasks unless they're simple. Use it when ANY of these conditions apply:\n\n1. **New Feature Implementation**: Adding meaningful new functionality\n - Example: \"Add a logout button\" - where should it go? What should happen on click?\n - Example: \"Add form validation\" - what rules? What error messages?\n\n2. **Multiple Valid Approaches**: The task can be solved in several different ways\n - Example: \"Add caching to the API\" - could use Redis, in-memory, file-based, etc.\n - Example: \"Improve performance\" - many optimization strategies possible\n\n3. **Code Modifications**: Changes that affect existing behavior or structure\n - Example: \"Update the login flow\" - what exactly should change?\n - Example: \"Refactor this component\" - what's the target architecture?\n\n4. **Architectural Decisions**: The task requires choosing between patterns or technologies\n - Example: \"Add real-time updates\" - WebSockets vs SSE vs polling\n - Example: \"Implement state management\" - Redux vs Context vs custom solution\n\n5. **Multi-File Changes**: The task will likely touch more than 2-3 files\n - Example: \"Refactor the authentication system\"\n - Example: \"Add a new API endpoint with tests\"\n\n6. **Unclear Requirements**: You need to explore before understanding the full scope\n - Example: \"Make the app faster\" - need to profile and identify bottlenecks\n - Example: \"Fix the bug in checkout\" - need to investigate root cause\n\n7. **User Preferences Matter**: The implementation could reasonably go multiple ways\n - If you would use AskUserQuestion to clarify the approach, use EnterPlanMode instead\n - Plan mode lets you explore first, then present options with context\n\n## When NOT to Use This Tool\n\nOnly skip EnterPlanMode for simple tasks:\n- Single-line or few-line fixes (typos, obvious bugs, small tweaks)\n- Adding a single function with clear requirements\n- Tasks where the user has given very specific, detailed instructions\n- Pure research/exploration tasks (use the Agent tool with explore agent instead)\n\n## What Happens in Plan Mode\n\nIn plan mode, you'll:\n1. Thoroughly explore the codebase using Glob, Grep, and Read tools\n2. Understand existing patterns and architecture\n3. Design an implementation approach\n4. Present your plan to the user for approval\n5. Use AskUserQuestion if you need to clarify approaches\n6. Exit plan mode with ExitPlanMode when ready to implement\n\n## Examples\n\n### GOOD - Use EnterPlanMode:\nUser: \"Add user authentication to the app\"\n- Requires architectural decisions (session vs JWT, where to store tokens, middleware structure)\n\nUser: \"Optimize the database queries\"\n- Multiple approaches possible, need to profile first, significant impact\n\nUser: \"Implement dark mode\"\n- Architectural decision on theme system, affects many components\n\nUser: \"Add a delete button to the user profile\"\n- Seems simple but involves: where to place it, confirmation dialog, API call, error handling, state updates\n\nUser: \"Update the error handling in the API\"\n- Affects multiple files, user should approve the approach\n\n### BAD - Don't use EnterPlanMode:\nUser: \"Fix the typo in the README\"\n- Straightforward, no planning needed\n\nUser: \"Add a console.log to debug this function\"\n- Simple, obvious implementation\n\nUser: \"What files handle routing?\"\n- Research task, not implementation planning\n\n## Important Notes\n\n- This tool REQUIRES user approval - they must consent to entering plan mode\n- If unsure whether to use it, err on the side of planning - it's better to get alignment upfront than to redo work\n- Users appreciate being consulted before significant changes are made to their codebase\n",
|
||
"parameters": {
|
||
"type": "object",
|
||
"properties": {},
|
||
"additionalProperties": false,
|
||
"$schema": "http://json-schema.org/draft-07/schema#"
|
||
},
|
||
"strict": false
|
||
}
|
||
},
|
||
{
|
||
"type": "function",
|
||
"function": {
|
||
"name": "ExitPlanMode",
|
||
"description": "Use this tool when you are in plan mode and have finished writing your plan to the plan file and are ready for user approval.\n\n## How This Tool Works\n- You should have already written your plan to the plan file specified in the plan mode system message\n- This tool does NOT take the plan content as a parameter - it will read the plan from the file you wrote\n- This tool simply signals that you're done planning and ready for the user to review and approve\n- The user will see the contents of your plan file when they review it\n\n## When to Use This Tool\nIMPORTANT: Only use this tool when the task requires planning the implementation steps of a task that requires writing code. For research tasks where you're gathering information, searching files, reading files or in general trying to understand the codebase - do NOT use this tool.\n\n## Handling Ambiguity in Plans\nBefore using this tool, ensure your plan is clear and unambiguous. If there are multiple valid approaches or unclear requirements:\n1. Use the AskUserQuestion tool to clarify with the user\n2. Ask about specific implementation choices (e.g., architectural patterns, which library to use)\n3. Clarify any assumptions that could affect the implementation\n4. Edit your plan file to incorporate user feedback\n5. Only proceed with ExitPlanMode after resolving ambiguities and updating the plan file\n\n## Examples\n\n1. Initial task: \"Search for and understand the implementation of vim mode in the codebase\" - Do not use the exit plan mode tool because you are not planning the implementation steps of a task.\n2. Initial task: \"Help me implement yank mode for vim\" - Use the exit plan mode tool after you have finished planning the implementation steps of the task.\n3. Initial task: \"Add a new feature to handle user authentication\" - If unsure about auth method (OAuth, JWT, etc.), use AskUserQuestion first, then use exit plan mode tool after clarifying the approach.\n",
|
||
"parameters": {
|
||
"type": "object",
|
||
"properties": {
|
||
"allowedPrompts": {
|
||
"type": "array",
|
||
"items": {
|
||
"type": "object",
|
||
"properties": {
|
||
"tool": {
|
||
"type": "string",
|
||
"enum": [
|
||
"Bash"
|
||
],
|
||
"description": "The tool this prompt applies to"
|
||
},
|
||
"prompt": {
|
||
"type": "string",
|
||
"description": "Semantic description of the action, e.g. \"run tests\", \"install dependencies\""
|
||
}
|
||
},
|
||
"required": [
|
||
"tool",
|
||
"prompt"
|
||
],
|
||
"additionalProperties": false
|
||
},
|
||
"description": "Prompt-based permissions needed to implement the plan. These describe categories of actions rather than specific commands."
|
||
}
|
||
},
|
||
"additionalProperties": false,
|
||
"$schema": "http://json-schema.org/draft-07/schema#"
|
||
},
|
||
"strict": false
|
||
}
|
||
},
|
||
{
|
||
"type": "function",
|
||
"function": {
|
||
"name": "TaskCreate",
|
||
"description": "Use this tool to create a structured task list for your current coding session. This helps you track progress, organize complex tasks, and demonstrate thoroughness to the user.\nIt also helps the user understand the progress of the task and overall progress of their requests.\n\n## When to Use This Tool\n\nUse this tool proactively in these scenarios:\n\n- Complex multi-step tasks - When a task requires 3 or more distinct steps or actions\n- Non-trivial and complex tasks - Tasks that require careful planning or multiple operations\n- Plan mode - When using plan mode, create a task list to track the work\n- User explicitly requests task list - When the user directly asks you to use task management\n- User provides multiple tasks - When users provide a list of things to be done (numbered or comma-separated)\n- After receiving new instructions - Immediately capture user requirements as tasks\n- When you start working on a task - Mark it as in_progress BEFORE beginning work\n- After completing a task - Mark it as completed and add any new follow-up tasks discovered during implementation\n\n## When NOT to Use This Tool\n\nSkip using this tool when:\n- There is only a single, straightforward task\n- The task is trivial and tracking it provides no organizational benefit\n- The task can be completed in less than 3 trivial steps\n- The task is purely conversational or informational\n\nNOTE that you should not use this tool if there is only one trivial task to do. In this case you are better off just doing the task directly.\n\n## Task Fields\n\n- **subject**: A brief, actionable title in imperative form (e.g., \"Fix authentication bug in login flow\")\n- **description**: Detailed description of what needs to be done, including context and acceptance criteria\n- **activeForm**: Present continuous form shown in spinner when task is in_progress (e.g., \"Fixing authentication bug\"). This is displayed to the user while you work on the task.\n\n**IMPORTANT**: Task descriptions must have two forms:\n- subject: The imperative form describing what needs to be done (e.g., \"Run tests\", \"Build the project\")\n- activeForm: The present continuous form shown during execution (e.g., \"Running tests\", \"Building the project\")\n\n## Examples\n\n### Creating a task for a multi-step feature\n```json\n{\n \"subject\": \"Add dark mode toggle to Settings page\",\n \"description\": \"Implement a toggle component in the settings page that allows users to switch between light and dark mode. Should persist preference to localStorage.\",\n \"activeForm\": \"Adding dark mode toggle to Settings page\"\n}\n```\n\n### Creating a task for running tests\n```json\n{\n \"subject\": \"Run tests and ensure they pass\",\n \"description\": \"Execute the test suite and verify all tests pass. Fix any failing tests before proceeding.\"\n}\n```\n\n## Tips\n\n- Create specific, actionable items\n- Break complex tasks into smaller, manageable steps\n- Use clear, descriptive task names\n- After creating tasks, use TaskList to verify your task list\n- Use TaskUpdate to mark tasks as in_progress when starting and completed when done\n",
|
||
"parameters": {
|
||
"type": "object",
|
||
"properties": {
|
||
"subject": {
|
||
"type": "string",
|
||
"description": "A brief title for the task"
|
||
},
|
||
"description": {
|
||
"type": "string",
|
||
"description": "A detailed description of what needs to be done"
|
||
},
|
||
"activeForm": {
|
||
"type": "string",
|
||
"description": "Present continuous form shown in spinner when in_progress (e.g., \"Running tests\")"
|
||
},
|
||
"metadata": {
|
||
"type": "object",
|
||
"additionalProperties": {},
|
||
"description": "Arbitrary metadata to attach to the task"
|
||
},
|
||
"owner": {
|
||
"type": "string",
|
||
"description": "Task owner (agent name). Use to assign the task to a specific teammate."
|
||
}
|
||
},
|
||
"required": [
|
||
"subject",
|
||
"description"
|
||
],
|
||
"additionalProperties": false,
|
||
"$schema": "http://json-schema.org/draft-07/schema#"
|
||
},
|
||
"strict": false
|
||
}
|
||
},
|
||
{
|
||
"type": "function",
|
||
"function": {
|
||
"name": "TaskGet",
|
||
"description": "Use this tool to retrieve a task by its ID from the task list.\n\n## When to Use This Tool\n\n- When you need the full description and context before starting work on a task\n- To understand task dependencies (what it blocks, what blocks it)\n- After being assigned a task, to get complete requirements\n\n## Output\n\nReturns full task details:\n- **subject**: Task title\n- **description**: Detailed requirements and context\n- **status**: 'pending', 'in_progress', or 'completed'\n- **blocks**: Tasks waiting on this one to complete\n- **blockedBy**: Tasks that must complete before this one can start\n\n## Tips\n\n- After fetching a task, verify its blockedBy list is empty before beginning work.\n- Use TaskList to see all tasks in summary form.\n",
|
||
"parameters": {
|
||
"type": "object",
|
||
"properties": {
|
||
"taskId": {
|
||
"type": "string",
|
||
"description": "The ID of the task to retrieve"
|
||
}
|
||
},
|
||
"required": [
|
||
"taskId"
|
||
],
|
||
"additionalProperties": false,
|
||
"$schema": "http://json-schema.org/draft-07/schema#"
|
||
},
|
||
"strict": false
|
||
}
|
||
},
|
||
{
|
||
"type": "function",
|
||
"function": {
|
||
"name": "TaskUpdate",
|
||
"description": "Use this tool to update a task in the task list.\n\n## When to Use This Tool\n\n**Mark tasks as resolved:**\n- When you have completed the work described in a task\n- When a task is no longer needed or has been superseded\n- IMPORTANT: Always mark your assigned tasks as resolved when you finish them\n- After resolving, call TaskList to find your next task\n\n- ONLY mark a task as completed when you have FULLY accomplished it\n- If you encounter errors, blockers, or cannot finish, keep the task as in_progress\n- When blocked, create a new task describing what needs to be resolved\n- Never mark a task as completed if:\n - Tests are failing\n - Implementation is partial\n - You encountered unresolved errors\n - You couldn't find necessary files or dependencies\n\n**Delete tasks:**\n- When a task is no longer relevant or was created in error\n- Setting status to `deleted` permanently removes the task\n\n**Update task details:**\n- When requirements change or become clearer\n- When establishing dependencies between tasks\n\n## Fields You Can Update\n\n- **status**: The task status (see Status Workflow below)\n- **subject**: Change the task title (imperative form, e.g., \"Run tests\")\n- **description**: Change the task description\n- **activeForm**: Present continuous form shown in spinner when in_progress (e.g., \"Running tests\")\n- **owner**: Change the task owner (agent name)\n- **metadata**: Merge metadata keys into the task (set a key to null to delete it)\n- **addBlocks**: Mark tasks that cannot start until this one completes\n- **addBlockedBy**: Mark tasks that must complete before this one can start\n\n## Status Workflow\n\nStatus progresses: `pending` → `in_progress` → `completed`\n\nUse `deleted` to permanently remove a task.\n\n## Staleness\n\nMake sure to read a task's latest state using `TaskGet` before updating it.\n\n## Examples\n\nMark task as in progress when starting work:\n```json\n{\"taskId\": \"1\", \"status\": \"in_progress\"}\n```\n\nMark task as completed after finishing:\n```json\n{\"taskId\": \"1\", \"status\": \"completed\"}\n```\n\nDelete a task that's no longer needed:\n```json\n{\"taskId\": \"3\", \"status\": \"deleted\"}\n```\n\nAdd a dependency between tasks:\n```json\n{\"taskId\": \"2\", \"addBlockedBy\": [\"1\"]}\n```\n",
|
||
"parameters": {
|
||
"type": "object",
|
||
"properties": {
|
||
"taskId": {
|
||
"type": "string",
|
||
"description": "The ID of the task to update"
|
||
},
|
||
"subject": {
|
||
"type": "string",
|
||
"description": "New subject for the task"
|
||
},
|
||
"description": {
|
||
"type": "string",
|
||
"description": "New description for the task"
|
||
},
|
||
"activeForm": {
|
||
"type": "string",
|
||
"description": "Present continuous form shown in spinner when in_progress (e.g., \"Running tests\")"
|
||
},
|
||
"status": {
|
||
"type": "string",
|
||
"enum": [
|
||
"pending",
|
||
"in_progress",
|
||
"completed",
|
||
"deleted"
|
||
],
|
||
"description": "New status for the task"
|
||
},
|
||
"addBlocks": {
|
||
"type": "array",
|
||
"items": {
|
||
"type": "string"
|
||
},
|
||
"description": "Task IDs that this task blocks"
|
||
},
|
||
"addBlockedBy": {
|
||
"type": "array",
|
||
"items": {
|
||
"type": "string"
|
||
},
|
||
"description": "Task IDs that block this task"
|
||
},
|
||
"owner": {
|
||
"type": "string",
|
||
"description": "New owner for the task"
|
||
},
|
||
"metadata": {
|
||
"type": "object",
|
||
"additionalProperties": {},
|
||
"description": "Metadata keys to merge into the task. Set a key to null to delete it."
|
||
}
|
||
},
|
||
"required": [
|
||
"taskId"
|
||
],
|
||
"additionalProperties": false,
|
||
"$schema": "http://json-schema.org/draft-07/schema#"
|
||
},
|
||
"strict": false
|
||
}
|
||
},
|
||
{
|
||
"type": "function",
|
||
"function": {
|
||
"name": "TaskList",
|
||
"description": "Use this tool to list all tasks in the task list.\n\n## When to Use This Tool\n\n- To see what tasks are available to work on (status: 'pending', no owner, not blocked)\n- To check overall progress on the project\n- To find tasks that are blocked and need dependencies resolved\n- After completing a task, to check for newly unblocked work or claim the next available task\n- **Prefer working on tasks in ID order** (lowest ID first) when multiple tasks are available, as earlier tasks often set up context for later ones\n\n## Output\n\nReturns a summary of each task:\n- **id**: Task identifier (use with TaskGet, TaskUpdate)\n- **subject**: Brief description of the task\n- **status**: 'pending', 'in_progress', or 'completed'\n- **owner**: Agent ID if assigned, empty if available\n- **blockedBy**: List of open task IDs that must be resolved first (tasks with blockedBy cannot be claimed until dependencies resolve)\n\nUse TaskGet with a specific task ID to view full details including description and comments.\n\n## Task List Coordination (Teams)\n\nWhen working in a team, all teammates share the same task list. Teammates should:\n1. Check TaskList periodically, **especially after completing each task**, to find available work or see newly unblocked tasks\n2. Claim unassigned, unblocked tasks with TaskUpdate (set `owner` to your name). **Prefer tasks in ID order** (lowest ID first)\n3. Create new tasks with TaskCreate when identifying additional work\n4. Mark tasks as completed with TaskUpdate when done, then check TaskList for next work\n5. Coordinate with other teammates by reading the task list status\n6. If all available tasks are blocked, notify the team lead or help resolve blocking tasks\n",
|
||
"parameters": {
|
||
"type": "object",
|
||
"properties": {},
|
||
"additionalProperties": false,
|
||
"$schema": "http://json-schema.org/draft-07/schema#"
|
||
},
|
||
"strict": false
|
||
}
|
||
},
|
||
{
|
||
"type": "function",
|
||
"function": {
|
||
"name": "WebFetch",
|
||
"description": "\n- Fetches content from a specified URL and processes it using an AI model\n- Takes a URL and a prompt as input\n- Fetches the URL content, converts HTML to markdown\n- Processes the content with the prompt using a small, fast model\n- Returns the model's response about the content\n- Use this tool when you need to retrieve and analyze web content\n\nUsage notes:\n - IMPORTANT: If an MCP-provided web fetch tool is available, prefer using that tool instead of this one, as it may have fewer restrictions. All MCP-provided tools start with \"mcp__\".\n - The URL must be a fully-formed valid URL\n - HTTP URLs will be automatically upgraded to HTTPS\n - The prompt should describe what information you want to extract from the page\n - This tool is read-only and does not modify any files\n - Results may be summarized if the content is very large\n - Includes a self-cleaning 15-minute cache for faster responses when repeatedly accessing the same URL\n - When a URL redirects to a different host, the tool will inform you and provide the redirect URL in a special format. You should then make a new WebFetch request with the redirect URL to fetch the content.\n",
|
||
"parameters": {
|
||
"type": "object",
|
||
"properties": {
|
||
"url": {
|
||
"type": "string",
|
||
"description": "The URL to fetch content from"
|
||
},
|
||
"prompt": {
|
||
"type": "string",
|
||
"description": "The prompt to run on the fetched content"
|
||
}
|
||
},
|
||
"required": [
|
||
"url",
|
||
"prompt"
|
||
],
|
||
"additionalProperties": false,
|
||
"$schema": "http://json-schema.org/draft-07/schema#"
|
||
},
|
||
"strict": false
|
||
}
|
||
},
|
||
{
|
||
"type": "function",
|
||
"function": {
|
||
"name": "WebSearch",
|
||
"description": "\n- Allows CodeBuddy Code to search the web and use the results to inform responses\n- Provides up-to-date information for current events and recent data\n- Returns search result information formatted as search result blocks\n- Use this tool for accessing information beyond CodeBuddy Code's knowledge cutoff\n- Searches are performed automatically within a single API call\n\nUsage notes:\n - Domain filtering is supported to include or block specific websites\n - Web search is only available in the US\n - Account for \"Today's date\" in <env>. For example, if <env> says \"Today's date: 2025-07-01\", and the user wants the latest docs, do not use 2024 in the search query. Use 2025.\n\n",
|
||
"parameters": {
|
||
"type": "object",
|
||
"properties": {
|
||
"query": {
|
||
"type": "string",
|
||
"minLength": 2,
|
||
"description": "The search query to use"
|
||
},
|
||
"allowed_domains": {
|
||
"type": "array",
|
||
"items": {
|
||
"type": "string"
|
||
},
|
||
"description": "Only include search results from these domains"
|
||
},
|
||
"blocked_domains": {
|
||
"type": "array",
|
||
"items": {
|
||
"type": "string"
|
||
},
|
||
"description": "Never include search results from these domains"
|
||
}
|
||
},
|
||
"required": [
|
||
"query"
|
||
],
|
||
"additionalProperties": false,
|
||
"$schema": "http://json-schema.org/draft-07/schema#"
|
||
},
|
||
"strict": false
|
||
}
|
||
},
|
||
{
|
||
"type": "function",
|
||
"function": {
|
||
"name": "TaskStop",
|
||
"description": "tool-taskstop-description",
|
||
"parameters": {
|
||
"type": "object",
|
||
"properties": {
|
||
"task_id": {
|
||
"type": "string",
|
||
"description": "The ID of the background task to stop"
|
||
},
|
||
"shell_id": {
|
||
"type": "string",
|
||
"description": "Deprecated: use task_id instead"
|
||
}
|
||
},
|
||
"additionalProperties": false,
|
||
"$schema": "http://json-schema.org/draft-07/schema#"
|
||
},
|
||
"strict": false
|
||
}
|
||
},
|
||
{
|
||
"type": "function",
|
||
"function": {
|
||
"name": "TaskOutput",
|
||
"description": "- Retrieves output from a running or completed task (background shell, agent, or remote session)\n- Takes a task_id parameter identifying the task\n- Returns the task output along with status information\n- Use block=true (default) to wait for task completion\n- Use block=false for non-blocking check of current status\n- Task IDs can be found using the /tasks command\n- Works with all task types: background shells, async agents, and remote sessions\n",
|
||
"parameters": {
|
||
"type": "object",
|
||
"properties": {
|
||
"task_id": {
|
||
"type": "string",
|
||
"description": "The ID of the background task to retrieve"
|
||
},
|
||
"block": {
|
||
"type": "boolean",
|
||
"description": "Whether to wait for task completion (default: true)"
|
||
},
|
||
"timeout": {
|
||
"type": "number",
|
||
"default": 60000,
|
||
"description": "Timeout in milliseconds (0-600000, default: 60000)"
|
||
},
|
||
"filter": {
|
||
"type": "string",
|
||
"description": "Optional regex pattern to filter output lines (only applies to background shell tasks)"
|
||
}
|
||
},
|
||
"required": [
|
||
"task_id"
|
||
],
|
||
"additionalProperties": false,
|
||
"$schema": "http://json-schema.org/draft-07/schema#"
|
||
},
|
||
"strict": false
|
||
}
|
||
},
|
||
{
|
||
"type": "function",
|
||
"function": {
|
||
"name": "Skill",
|
||
"description": "Execute a skill or built-in command within the main conversation\n\n<skills_instructions>\nWhen users ask you to perform tasks, check if any of the available skills below can help complete the task more effectively. Skills provide specialized capabilities and domain knowledge.\n\nWhen users ask you to run a \"slash command\" or reference \"/<something>\" (e.g., \"/commit\", \"/review-pr\", \"/clear\", \"/model\"), they are referring to a skill or built-in command. Use this tool to invoke it.\n\n<example>\nUser: \"run /commit\"\nAssistant: [Calls Skill tool with skill: \"commit\"]\n</example>\n\n<example>\nUser: \"switch to gpt-4o\"\nAssistant: [Calls Skill tool with skill: \"model\", args: \"gpt-4o\"]\n</example>\n\n<example>\nUser: \"clear the conversation\"\nAssistant: [Calls Skill tool with skill: \"clear\"]\n</example>\n\nHow to invoke:\n- Use this tool with the skill name and optional arguments\n- Examples:\n - `skill: \"pdf\"` - invoke the pdf skill\n - `skill: \"commit\", args: \"-m 'Fix bug'\"` - invoke with arguments\n - `skill: \"review-pr\", args: \"123\"` - invoke with arguments\n - `skill: \"ms-office-suite:pdf\"` - invoke using fully qualified name\n - `skill: \"model\", args: \"list\"` - list available AI models\n - `skill: \"model\", args: \"gpt-4o\"` - switch AI model\n - `skill: \"clear\"` - start a fresh conversation\n - `skill: \"resume\", args: \"list\"` - list available sessions\n - `skill: \"config\", args: \"set theme dark\"` - change a setting\n\nImportant:\n- When a skill is relevant, you must invoke this tool IMMEDIATELY as your first action\n- NEVER just announce or mention a skill in your text response without actually calling this tool\n- This is a BLOCKING REQUIREMENT: invoke the relevant Skill tool BEFORE generating any other response about the task\n- Do not invoke a skill that is already running\n- If you see a <command-name> tag in the current conversation turn, the skill has ALREADY been loaded - follow the instructions directly instead of calling this tool again\n</skills_instructions>\n\n<available_skills>\n<skill>\n<name>\nclear\n</name>\n<description>\nStart a fresh conversation (previous chats remain accessible via /resume)\n</description>\n<location>\nbuiltin\n</location>\n</skill>\n<skill>\n<name>\nconfig\n</name>\n<description>\nManage settings. Subcommands: \"list\" to show current settings, \"get <key>\" to read a value, \"set <key> <value>\" to change a value\n</description>\n<location>\nbuiltin\n</location>\n</skill>\n<skill>\n<name>\ngateway\n</name>\n<description>\nManage the remote control gateway. Subcommands: \"status\" to show current status, \"stop\" to stop the gateway, \"token\" to regenerate access token, \"tunnel\" to start with tunnel\n</description>\n<location>\nbuiltin\n</location>\n</skill>\n<skill>\n<name>\nhelp\n</name>\n<description>\nShow help and available commands\n</description>\n<location>\nbuiltin\n</location>\n</skill>\n<skill>\n<name>\nmodel\n</name>\n<description>\nSet or list AI models. Use \"list\" to show available models with current selection, or specify a model id to switch (e.g., /model gpt-4o)\n</description>\n<location>\nbuiltin\n</location>\n</skill>\n<skill>\n<name>\nplan\n</name>\n<description>\nPreview the current plan file content\n</description>\n<location>\nbuiltin\n</location>\n</skill>\n<skill>\n<name>\nrename\n</name>\n<description>\nRename the current conversation. Requires a name argument (e.g., /rename my-session)\n</description>\n<location>\nbuiltin\n</location>\n</skill>\n<skill>\n<name>\nresume\n</name>\n<description>\nList or resume sessions. Use \"list\" to show all sessions with ids, or specify a session id to resume (e.g., /resume <session-id>)\n</description>\n<location>\nbuiltin\n</location>\n</skill>\n<skill>\n<name>\nskills\n</name>\n<description>\nList available skills\n</description>\n<location>\nbuiltin\n</location>\n</skill>\n<skill>\n<name>\nstatus\n</name>\n<description>\nShow CodeBuddy status including version, model, account, API connectivity, and tool statuses\n</description>\n<location>\nbuiltin\n</location>\n</skill>\n<skill>\n<name>\ntasks\n</name>\n<description>\nList and manage background tasks\n</description>\n<location>\nbuiltin\n</location>\n</skill>\n<skill>\n<name>\ntodos\n</name>\n<description>\nDisplay the current session's todo list\n</description>\n<location>\nbuiltin\n</location>\n</skill>\n<skill>\n<name>\ntheme\n</name>\n<description>\nConfig CodeBuddy Code Theme\n</description>\n<location>\nbuiltin\n</location>\n</skill>\n<skill>\n<name>\noutput-style\n</name>\n<description>\nSet the output style directly or from a selection menu\n</description>\n<location>\nbuiltin\n</location>\n</skill>\n<skill>\n<name>\nmodel:text-to-image\n</name>\n<description>\nSet or list text-to-image models. Use \"list\" to show available models, or specify a model id to switch\n</description>\n<location>\nbuiltin\n</location>\n</skill>\n<skill>\n<name>\nmodel:image-to-image\n</name>\n<description>\nSet or list image-to-image models. Use \"list\" to show available models, or specify a model id to switch\n</description>\n<location>\nbuiltin\n</location>\n</skill>\n<skill>\n<name>\nloop\n</name>\n<description>\nRun a prompt or slash command on a recurring interval (e.g. /loop 5m /foo, defaults to 10m)\n</description>\n<location>\nbundled\n</location>\n</skill>\n</available_skills>\n",
|
||
"parameters": {
|
||
"type": "object",
|
||
"properties": {
|
||
"skill": {
|
||
"type": "string",
|
||
"description": "The skill name. E.g., \"commit\", \"review-pr\", or \"pdf\""
|
||
},
|
||
"command": {
|
||
"type": "string",
|
||
"description": "(Legacy) The skill name (no arguments). E.g., \"pdf\" or \"xlsx\""
|
||
},
|
||
"args": {
|
||
"type": "string",
|
||
"description": "Optional arguments for the skill"
|
||
}
|
||
},
|
||
"additionalProperties": false,
|
||
"$schema": "http://json-schema.org/draft-07/schema#"
|
||
},
|
||
"strict": false
|
||
}
|
||
},
|
||
{
|
||
"type": "function",
|
||
"function": {
|
||
"name": "ToolSearch",
|
||
"description": "Search for available tools using natural language queries.\n\nUse this tool when you need to discover tools that can help with a specific task. Some tools are not loaded by default to save context space - use this to find and learn about them.\n\nUsage:\n- Provide a natural language description of what you want to do\n- Returns a list of matching tools sorted by relevance\n- Results include the tool's full parameter schema so you know how to call it\n- Found tools can be invoked using DeferExecuteTool by passing the tool name and parameters\n\nIMPORTANT: Tools listed below as \"Available deferred tools\" are NOT directly callable. You MUST call ToolSearch first to discover a deferred tool, then use DeferExecuteTool to invoke it. Calling a deferred tool directly will result in a \"Tool not found\" error.\n\nNote: Some listed tools may not appear in search results if they are unavailable due to environment restrictions, disabled features, or model limitations.\n\n\n\nAvailable deferred tools (use ToolSearch to discover their schemas):\n- CronCreate: Schedule a prompt to run at a future time — either recurring on a cron schedule, or once at a specific time. Session-only: the job dies when this codebuddy code session ends.\n- CronDelete: Cancel a scheduled cron job by ID. Removes it from the in-memory session store.\n- CronList: List all scheduled cron jobs in this session.\n- EnterWorktree: Create an isolated git worktree and switch the current session into it.\n- ImageGen: Generate images from text descriptions using AI models.\n- LSP: Interact with Language Server Protocol (LSP) servers to get code intelligence features.\n- LeaveWorktree: Leave the current worktree session and switch back to the original working directory.\n- NotebookEdit: Completely replaces the contents of a specific cell in a Jupyter notebook (.ipynb file) with new source.\n- TeamCreate: Create a new team to coordinate multiple agents working on a project. Use when tasks benefit from parallel work by multiple specialized agents.\n- TeamDelete: Remove team and task directories when the swarm work is complete. Fails if team still has active members.\n\n",
|
||
"parameters": {
|
||
"type": "object",
|
||
"properties": {
|
||
"queries": {
|
||
"type": "array",
|
||
"items": {
|
||
"type": "string"
|
||
},
|
||
"description": "Keyword-based search query using MiniSearch full-text search engine. Supports prefix matching, fuzzy matching, and relevance ranking. Must be an array of keyword strings.For better results, include BOTH Chinese and English keywords (e.g., [\"获取时间\", \"get time\"] or [\"文件搜索\", \"file search\", \"glob\"])."
|
||
},
|
||
"tool_names": {
|
||
"type": "array",
|
||
"items": {
|
||
"type": "string"
|
||
},
|
||
"description": "Exact, fully-qualified tool name(s) to look up — e.g., [\"mcp__time__current_time\", \"LSP\", \"mcp__cnb__cnb_create_pull\"]. Do NOT use partial names, descriptions, or keywords."
|
||
},
|
||
"top_k": {
|
||
"type": "integer",
|
||
"exclusiveMinimum": 0,
|
||
"maximum": 20,
|
||
"default": 3,
|
||
"description": "Maximum number of tools to return with full details (default: 3, max: 20). Only applies when using \"queries\". Ignored when using \"tool_names\". Additional matching tools beyond this limit are shown as additional candidates."
|
||
}
|
||
},
|
||
"additionalProperties": false,
|
||
"$schema": "http://json-schema.org/draft-07/schema#"
|
||
},
|
||
"strict": false
|
||
}
|
||
},
|
||
{
|
||
"type": "function",
|
||
"function": {
|
||
"name": "DeferExecuteTool",
|
||
"description": "Execute a deferred tool by name. Use this to invoke tools discovered via ToolSearch without needing them in the active tools list.\n\nUsage:\n- First use ToolSearch to discover a tool and learn its parameter schema\n- Then call this tool with the exact tool name and parameters\n- Parameters are validated against the tool's schema before execution\n- The target tool's permission checks and hooks are applied normally\n\nExample:\nDeferExecuteTool({ toolName: \"ImageGen\", params: { prompt: \"a sunset over mountains\" } })\n\nNotes:\n- If parameter validation fails, a detailed error with the expected schema is returned\n- You can skip ToolSearch if you already know the tool name and parameters from a previous turn\n- This tool follows standard permission checks (may require approval depending on permissions configuration)\n",
|
||
"parameters": {
|
||
"type": "object",
|
||
"properties": {
|
||
"toolName": {
|
||
"type": "string",
|
||
"description": "The exact name of the deferred tool to execute (as returned by ToolSearch)."
|
||
},
|
||
"params": {
|
||
"type": "object",
|
||
"additionalProperties": {},
|
||
"description": "The parameters to pass to the target tool. Must match the tool's parameter schema (as returned by ToolSearch in a previous turn)."
|
||
}
|
||
},
|
||
"required": [
|
||
"toolName",
|
||
"params"
|
||
],
|
||
"additionalProperties": false,
|
||
"$schema": "http://json-schema.org/draft-07/schema#"
|
||
},
|
||
"strict": false
|
||
}
|
||
},
|
||
{
|
||
"type": "function",
|
||
"function": {
|
||
"name": "SendMessage",
|
||
"description": "# SendMessageTool\n\nSend messages to agent teammates and handle protocol requests/responses in a team.\n\n## Message Types\n\n### type: \"message\" - Send a Direct Message\n\nSend a message to a **single specific teammate**. You MUST specify the recipient.\n\n**IMPORTANT for teammates**: Your plain text output is NOT visible to the team lead or other teammates. To communicate with anyone on your team, you **MUST** use this tool. Just typing a response or acknowledgment in text is not enough.\n\n```\n{\n \"type\": \"message\",\n \"recipient\": \"researcher\",\n \"content\": \"Your message here\",\n \"summary\": \"Brief status update on auth module\"\n}\n```\n\n- **recipient**: The name of the teammate to message (required)\n- **content**: The message text (required)\n- **summary**: A 5-10 word summary shown as preview in the UI (required)\n\n### type: \"broadcast\" - Send Message to ALL Teammates (USE SPARINGLY)\n\nSend the **same message to everyone** on the team at once.\n\n**WARNING: Broadcasting is expensive.** Each broadcast sends a separate message to every teammate, which means:\n- N teammates = N separate message deliveries\n- Each delivery consumes API resources\n- Costs scale linearly with team size\n\n```\n{\n \"type\": \"broadcast\",\n \"content\": \"Message to send to all teammates\",\n \"summary\": \"Critical blocking issue found\"\n}\n```\n\n- **content**: The message content to broadcast (required)\n- **summary**: A 5-10 word summary shown as preview in the UI (required)\n\n**CRITICAL: Use broadcast only when absolutely necessary.** Valid use cases:\n- Critical issues requiring immediate team-wide attention (e.g., \"stop all work, blocking bug found\")\n- Major announcements that genuinely affect every teammate equally\n\n**Default to \"message\" instead of \"broadcast\".** Use \"message\" for:\n- Responding to a single teammate\n- Normal back-and-forth communication\n- Following up on a task with one person\n- Sharing findings relevant to only some teammates\n- Any message that doesn't require everyone's attention\n\n### type: \"shutdown_request\" - Request a Teammate to Shut Down\n\nUse this to ask a teammate to gracefully shut down:\n\n```\n{\n \"type\": \"shutdown_request\",\n \"recipient\": \"researcher\",\n \"content\": \"Task complete, wrapping up the session\"\n}\n```\n\nThe teammate will receive a shutdown request and can either approve (exit) or reject (continue working).\n\n### type: \"shutdown_response\" - Respond to a Shutdown Request\n\n#### Approve Shutdown\n\nWhen you receive a shutdown request as a JSON message with `type: \"shutdown_request\"`, you **MUST** respond to approve or reject it. Do NOT just acknowledge the request in text - you must actually call this tool.\n\n```\n{\n \"type\": \"shutdown_response\",\n \"request_id\": \"abc-123\",\n \"approve\": true\n}\n```\n\n**IMPORTANT**: Extract the `requestId` from the JSON message and pass it as `request_id` to the tool. Simply saying \"I'll shut down\" is not enough - you must call the tool.\n\nThis will send confirmation to the leader and terminate your process.\n\n#### Reject Shutdown\n\n```\n{\n \"type\": \"shutdown_response\",\n \"request_id\": \"abc-123\",\n \"approve\": false,\n \"content\": \"Still working on task #3, need 5 more minutes\"\n}\n```\n\nThe leader will receive your rejection with the reason.\n\n### type: \"plan_approval_response\" - Approve or Reject a Teammate's Plan\n\n#### Approve Plan\n\nWhen a teammate with `plan_mode_required` calls ExitPlanMode, they send you a plan approval request as a JSON message with `type: \"plan_approval_request\"`. Use this to approve their plan:\n\n```\n{\n \"type\": \"plan_approval_response\",\n \"request_id\": \"abc-123\",\n \"recipient\": \"researcher\",\n \"approve\": true\n}\n```\n\nAfter approval, the teammate will automatically exit plan mode and can proceed with implementation.\n\n#### Reject Plan\n\n```\n{\n \"type\": \"plan_approval_response\",\n \"request_id\": \"abc-123\",\n \"recipient\": \"researcher\",\n \"approve\": false,\n \"content\": \"Please add error handling for the API calls\"\n}\n```\n\nThe teammate will receive the rejection with your feedback and can revise their plan.\n\n## Important Notes\n\n- Messages from teammates are automatically delivered to you. You do NOT need to manually check your inbox.\n- When reporting on teammate messages, you do NOT need to quote the original message - it's already rendered to the user.\n- **IMPORTANT**: Always refer to teammates by their NAME (e.g., \"team-lead\", \"researcher\", \"tester\"), never by UUID.\n- Do NOT send structured JSON status messages. Use TaskUpdate to mark tasks completed and the system will automatically send idle notifications when you stop.\n\n## Background Agent Usage\n\nThis tool is also available to **background agents** launched via the Agent tool with `run_in_background: true`. Background agents should use this tool to send their results back to the main agent:\n\n```\n{\n \"type\": \"message\",\n \"recipient\": \"main\",\n \"content\": \"Here are my findings: ...\",\n \"summary\": \"Completed analysis of auth module\"\n}\n```\n\n- **recipient**: Use `\"main\"` to send results back to the main agent\n- The main agent will automatically receive and process the message\n",
|
||
"parameters": {
|
||
"type": "object",
|
||
"properties": {
|
||
"type": {
|
||
"type": "string",
|
||
"enum": [
|
||
"message",
|
||
"broadcast",
|
||
"shutdown_request",
|
||
"shutdown_response",
|
||
"plan_approval_response"
|
||
],
|
||
"description": "Message type: \"message\" for DMs, \"broadcast\" to all teammates, \"shutdown_request\" to request shutdown, \"shutdown_response\" to respond to shutdown, \"plan_approval_response\" to approve/reject plans"
|
||
},
|
||
"recipient": {
|
||
"type": "string",
|
||
"description": "Agent name of the recipient (required for message, shutdown_request, plan_approval_response)"
|
||
},
|
||
"content": {
|
||
"type": "string",
|
||
"description": "Message text, reason, or feedback"
|
||
},
|
||
"summary": {
|
||
"type": "string",
|
||
"description": "A 5-10 word summary of the message, shown as a preview in the UI (required for message, broadcast)"
|
||
},
|
||
"request_id": {
|
||
"type": "string",
|
||
"description": "Request ID to respond to (required for shutdown_response, plan_approval_response)"
|
||
},
|
||
"approve": {
|
||
"type": "boolean",
|
||
"description": "Whether to approve the request (required for shutdown_response, plan_approval_response)"
|
||
}
|
||
},
|
||
"required": [
|
||
"type"
|
||
],
|
||
"additionalProperties": false,
|
||
"$schema": "http://json-schema.org/draft-07/schema#"
|
||
},
|
||
"strict": false
|
||
}
|
||
}
|
||
],
|
||
"temperature": 1,
|
||
"max_tokens": 48000,
|
||
"stream": true,
|
||
"stream_options": {
|
||
"include_usage": true
|
||
},
|
||
"reasoning_effort": "medium",
|
||
"verbosity": "high",
|
||
"reasoning_summary": "auto"
|
||
},
|
||
"response_headers": {
|
||
"Date": "Wed, 22 Apr 2026 19:59:13 GMT",
|
||
"Content-Type": "text/event-stream",
|
||
"Transfer-Encoding": "chunked",
|
||
"Connection": "keep-alive",
|
||
"Set-Cookie": "<redacted>",
|
||
"Cache-Control": "no-cache",
|
||
"Traceid": "00aed5c6d3b7a3c08c1be28aeafe5d15",
|
||
"X-Request-Id": "e3f4834ce4d6ae7841f8c68d198c7579",
|
||
"X-User-Id": "8c87d007-5acd-4899-9f45-8c40391a5bbf",
|
||
"X-WAF-UUID": "dbb4457a3309b005182acfb7a4fc6258-6dd1ff27a0f0d14d70ff89b178de6257"
|
||
},
|
||
"response_sse": "data: {\"id\":\"a42fc54b69744cdeaa526d7e610ecef4\",\"model\":\"ep-07iye0i1\",\"object\":\"chat.completion.chunk\",\"created\":1776887951,\"choices\":[{\"index\":0,\"delta\":{\"role\":\"assistant\",\"content\":\"\",\"reasoning_content\":\"The user\",\"function_call\":null,\"refusal\":\"\",\"tool_calls\":[],\"extra_fields\":null},\"logprobs\":null,\"finish_reason\":\"\"}],\"usage\":null}\n\ndata: {\"id\":\"a42fc54b69744cdeaa526d7e610ecef4\",\"model\":\"ep-07iye0i1\",\"object\":\"chat.completion.chunk\",\"created\":1776887951,\"choices\":[{\"index\":0,\"delta\":{\"role\":\"assistant\",\"content\":\"ok\",\"reasoning_content\":\"\",\"function_call\":{\"name\":\"\",\"arguments\":\"\"},\"refusal\":\"\",\"tool_calls\":[],\"extra_fields\":null},\"logprobs\":null,\"finish_reason\":\"stop\"}],\"usage\":{\"prompt_tokens\":24798,\"completion_tokens\":26,\"total_tokens\":24824,\"completion_tokens_details\":{\"accepted_prediction_tokens\":0,\"audio_tokens\":0,\"reasoning_tokens\":24,\"rejected_prediction_tokens\":0,\"cached_tokens\":0},\"prompt_tokens_details\":{\"accepted_prediction_tokens\":0,\"audio_tokens\":0,\"reasoning_tokens\":0,\"rejected_prediction_tokens\":0,\"cached_tokens\":0},\"prompt_cache_hit_tokens\":0,\"prompt_cache_miss_tokens\":24798,\"cache_read_input_tokens\":0,\"cache_creation_input_tokens\":0,\"prompt_cache_write_tokens\":0,\"completion_thinking_tokens\":0,\"credit\":1.12,\"cached_tokens\":0}}\n\ndata: [DONE]\n\n"
|
||
}
|