[反馈]: Request processing failed: Google API returned error: 400 INVALID_ARGUMENT

[y1rn]

部署平台

None

版本号

v0.5.1

客户端/工具

opencode

问题/请求描述

curl可以正常调用api, opencode下会报INVALID_ARGUMENT, opencode 配置

"provider": {
    "aistudio": {
       "name": "Google",
       "models": {
          "gemini-3-pro-preview": {
            "name": "Gemini 3 pro preview(aistudio)",
            "limit": {
              "context": 1048576,
              "output": 65535
            },
            "modalities": {
              "input": [
                "text",
                "image",
                "pdf"
              ],
              "output": [
                "text"
              ]
            },
            "variants": {
              "low": {
                "thinkingLevel": "low"
              },
              "high": {
                "thinkingLevel": "high"
              }
            }

          }
        }
      }
    }

日志信息（可选）

2026-01-26T11:03:52.146Z [ProxySystem] - [Browser] Received request: POST /v1beta/models/gemini-3-pro-preview:streamGenerateContent
[INFO] 2026-01-26T11:03:52.146Z [ProxySystem] - [Browser] Browser received request
[INFO] 2026-01-26T11:03:52.146Z [ProxySystem] - [Browser] Executing request: POST /v1beta/models/gemini-3-pro-preview:streamGenerateContent
[ERROR] 2026-01-26T11:03:52.799Z [ProxySystem] - [Adapter] Received error from browser, will trigger switching logic. Status code: 400, message: Proxy browser error: Google API returned error: 400 INVALID_ARGUMENT {"error":{"code":400,"message":"Request contains an invalid argument.","status":"INVALID_ARGUMENT"}}
[WARN] 2026-01-26T11:03:52.800Z [ProxySystem] - ⚠️ [Auth] Request failed - failure count: 3/3 (Current account index: 0)
[WARN] 2026-01-26T11:03:52.800Z [ProxySystem] - 🔴 [Auth] Failure threshold reached (3/3)! Preparing to switch account...
[INFO] 2026-01-26T11:03:52.800Z [ProxySystem] - ==================================================
[INFO] 2026-01-26T11:03:52.801Z [ProxySystem] - 🔄 [Auth] Single account mode: Rotation threshold reached, performing in-place restart...
[INFO] 2026-01-26T11:03:52.801Z [ProxySystem] -    • Target account: #0
[INFO] 2026-01-26T11:03:52.801Z [ProxySystem] - ==================================================
[INFO] 2026-01-26T11:03:52.803Z [ProxySystem] - [Browser] ❌ Request processing failed: Google API returned error: 400 INVALID_ARGUMENT {"error":{"code":400,"message":"Request contains an invalid argument.","status":"INVALID_ARGUMENT"}}
[INFO] 2026-01-26T11:03:52.804Z [ProxySystem] - [Browser] Sent 'error' information back to server
[INFO] 2026-01-26T11:03:52.976Z [ProxySystem] - [Auth Update] 💾 Successfully updated auth credentials for account #0
[INFO] 2026-01-26T11:03:52.977Z [ProxySystem] - [Browser] Stopped background tasks (Scavenger) for old page.
[INFO] 2026-01-26T11:03:52.977Z [ProxySystem] - [Browser] Closing old API browser context...
[INFO] 2026-01-26T11:03:52.983Z [ProxySystem] - [Browser] Old API context closed.

[bbbugg]

貌似OpenCode更新了，多传了之前没有处理的参数。

[bbbugg]

@y1rn 可以麻烦再试一下 ghcr.io/ibuhub/aistudio-to-api:preview-20260126-123452镜像吗，或者源代码在fix/opencode分支。没问题就合并了。

[y1rn]

@y1rn 可以麻烦再试一下 ghcr.io/ibuhub/aistudio-to-api:preview-20260126-123452镜像吗，或者源代码在fix/opencode分支。没问题就合并了。

依然报错

[INFO] 2026-01-26T12:53:05.978Z [ProxySystem] - ✅ [Browser] Browser client is ready.
[INFO] 2026-01-26T12:53:05.978Z [ProxySystem] - ==================================================
[INFO] 2026-01-26T12:53:05.978Z [ProxySystem] - [System] ✅ Successfully started with account #0!
[INFO] 2026-01-26T12:53:06.102Z [ProxySystem] - [System] System ready after 601ms.
[INFO] 2026-01-26T12:53:06.908Z [ProxySystem] - [Browser] System initializing...
[INFO] 2026-01-26T12:53:06.908Z [ProxySystem] - [Browser] Connecting to server: ws://127.0.0.1:9998
[INFO] 2026-01-26T12:53:06.911Z [ProxySystem] - [Server] Internal WebSocket client connected (from: 127.0.0.1)
[INFO] 2026-01-26T12:53:06.912Z [ProxySystem] - [Browser] ✅ Connection successful!
[INFO] 2026-01-26T12:53:06.912Z [ProxySystem] - [Browser] System initialization complete, waiting for server instructions...
[INFO] 2026-01-26T12:53:07.106Z [ProxySystem] - [Request] OpenAI generation request - account rotation count: 1/40 (Current account: 0)
[INFO] 2026-01-26T12:53:07.107Z [ProxySystem] - [Adapter] Starting translation of OpenAI request format to Google format...
[INFO] 2026-01-26T12:53:07.108Z [ProxySystem] - [Adapter] Converted 38 OpenAI tool(s) to Gemini functionDeclarations
[INFO] 2026-01-26T12:53:07.108Z [ProxySystem] - [Adapter] Converted tool_choice to Gemini toolConfig: {"mode":"AUTO"}
[INFO] 2026-01-26T12:53:07.108Z [ProxySystem] - [Adapter] Translation complete.
[INFO] 2026-01-26T12:53:07.111Z [ProxySystem] - [Browser] Received request: POST /v1beta/models/gemini-3-pro-preview:streamGenerateContent
[INFO] 2026-01-26T12:53:07.111Z [ProxySystem] - [Browser] Browser received request
[INFO] 2026-01-26T12:53:07.111Z [ProxySystem] - [Browser] Executing request: POST /v1beta/models/gemini-3-pro-preview:streamGenerateContent
[INFO] 2026-01-26T12:53:07.328Z [ProxySystem] - [Browser] 🛡️ Background Wakeup Service (Rocket Handler) started...
[ERROR] 2026-01-26T12:53:08.121Z [ProxySystem] - [Adapter] Received error from browser, will trigger switching logic. Status code: 400, message: Proxy browser error: Google API returned error: 400 INVALID_ARGUMENT {"error":{"code":400,"message":"Request contains an invalid argument.","status":"INVALID_ARGUMENT"}}
[WARN] 2026-01-26T12:53:08.122Z [ProxySystem] - ⚠️ [Auth] Request failed - failure count: 1/3 (Current account index: 0)
[INFO] 2026-01-26T12:53:08.123Z [ProxySystem] - [Browser] ❌ Request processing failed: Google API returned error: 400 INVALID_ARGUMENT {"error":{"code":400,"message":"Request contains an invalid argument.","status":"INVALID_ARGUMENT"}}
[INFO] 2026-01-26T12:53:08.123Z [ProxySystem] - [Browser] Sent 'error' information back to server
~/../AIStudioToAPI ❯ git status                                                                                                            chor fix/opencode 
On branch fix/opencode
Your branch is up to date with 'origin/fix/opencode'.

nothing to commit, working tree clean

[y1rn]

我打印了google request(去除了systemInstruction下面的长文本):

Request Body

{
  "contents": [
    {
      "parts": [
        {
          "text": "hello"
        }
      ],
      "role": "user"
    },
    {
      "parts": [
        {
          "text": "hello"
        }
      ],
      "role": "user"
    },
    {
      "parts": [
        {
          "text": "hello"
        }
      ],
      "role": "user"
    }
  ],
  "systemInstruction": {
    "parts": [
      {
        "text": "very long text"
      }
    ],
    "role": "user"
  },
  "generationConfig": {
    "maxOutputTokens": 32000,
    "topP": 0.95
  },
  "tools": [
    {
      "functionDeclarations": [
        {
          "name": "question",
          "description": "Use this tool when you need to ask the user questions during execution. This allows you to:\n1. Gather user preferences or requirements\n2. Clarify ambiguous instructions\n3. Get decisions on implementation choices as you work\n4. Offer choices to the user about what direction to take.\n\nUsage notes:\n- When `custom` is enabled (default), a \"Type your own answer\" option is added automatically; don't include \"Other\" or catch-all options\n- Answers are returned as arrays of labels; set `multiple: true` to allow selecting more than one\n- If you recommend a specific option, make that the first option in the list and add \"(Recommended)\" at the end of the label\n",
          "parameters": {
            "type": "OBJECT",
            "properties": {
              "questions": {
                "description": "Questions to ask",
                "type": "ARRAY",
                "items": {
                  "type": "OBJECT",
                  "properties": {
                    "question": {
                      "description": "Complete question",
                      "type": "STRING"
                    },
                    "header": {
                      "description": "Very short label (max 30 chars)",
                      "type": "STRING"
                    },
                    "options": {
                      "description": "Available choices",
                      "type": "ARRAY",
                      "items": {
                        "type": "OBJECT",
                        "properties": {
                          "label": {
                            "description": "Display text (1-5 words, concise)",
                            "type": "STRING"
                          },
                          "description": {
                            "description": "Explanation of choice",
                            "type": "STRING"
                          }
                        },
                        "required": [
                          "label",
                          "description"
                        ]
                      }
                    },
                    "multiple": {
                      "description": "Allow selecting multiple choices",
                      "type": "BOOLEAN"
                    }
                  },
                  "required": [
                    "question",
                    "header",
                    "options"
                  ]
                }
              }
            },
            "required": [
              "questions"
            ]
          }
        },
        {
          "name": "bash",
          "description": "Executes a given bash command in a persistent shell session with optional timeout, ensuring proper handling and security measures.\n\nAll commands run in /Users/chor/.config/opencode by default. Use the `workdir` parameter if you need to run a command in a different directory. AVOID using `cd <directory> && <command>` patterns - use `workdir` instead.\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., rm \"path with spaces/file.txt\")\n   - Examples of proper quoting:\n     - mkdir \"/Users/name/My Documents\" (correct)\n     - mkdir /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. If not specified, commands will time out 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 2000 lines or 51200 bytes, it will be truncated and the full output will be written to a file. You can use Read with offset/limit to read specific sections or Grep to search the full content. Because of this, you do NOT need to use `head`, `tail`, or other truncation commands to limit output - just run the command directly.\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  - 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  - AVOID using `cd <directory> && <command>`. Use the `workdir` parameter to change directories instead.\n    <good-example>\n    Use workdir=\"/foo/bar\" with command: pytest 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 push --force, hard reset, etc) 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 ALL conditions are met:\n  (1) User explicitly requested amend, OR commit SUCCEEDED but pre-commit hook auto-modified files that need including\n  (2) HEAD commit was created by you in this conversation (verify: git log -1 --format='%an %ae')\n  (3) Commit has NOT been pushed to remote (verify: git status shows \"Your branch is ahead\")\n- CRITICAL: If commit FAILED or was REJECTED by hook, NEVER amend - fix the issue and create a NEW commit\n- CRITICAL: If you already pushed to remote, NEVER amend unless user explicitly requests it (requires force push)\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 after the commit completes to verify success.\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, fix the issue and create a NEW commit (see amend rules above)\n\nImportant notes:\n- NEVER run additional commands to read or explore code, besides git bash commands\n- NEVER use the TodoWrite or Task tools\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\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</example>\n\nImportant:\n- DO NOT use the TodoWrite or Task tools\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",
          "parameters": {
            "type": "OBJECT",
            "properties": {
              "command": {
                "description": "The command to execute",
                "type": "STRING"
              },
              "timeout": {
                "description": "Optional timeout in milliseconds",
                "type": "NUMBER"
              },
              "workdir": {
                "description": "The working directory to run the command in. Defaults to /Users/chor/.config/opencode. Use this instead of 'cd' commands.",
                "type": "STRING"
              },
              "description": {
                "description": "Clear, concise description of what this command does in 5-10 words. Examples:\nInput: ls\nOutput: Lists files in current directory\n\nInput: git status\nOutput: Shows working tree status\n\nInput: npm install\nOutput: Installs package dependencies\n\nInput: mkdir foo\nOutput: Creates directory 'foo'",
                "type": "STRING"
              }
            },
            "required": [
              "command",
              "description"
            ]
          }
        },
        {
          "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 filePath 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- You have the capability to call multiple tools in a single response. It is always better to speculatively read multiple files as a batch that are potentially useful.\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- You can read image files using this tool.\n",
          "parameters": {
            "type": "OBJECT",
            "properties": {
              "filePath": {
                "description": "The path to the file to read",
                "type": "STRING"
              },
              "offset": {
                "description": "The line number to start reading from (0-based)",
                "type": "NUMBER"
              },
              "limit": {
                "description": "The number of lines to read (defaults to 2000)",
                "type": "NUMBER"
              }
            },
            "required": [
              "filePath"
            ]
          }
        },
        {
          "name": "glob",
          "description": "Fast file pattern matching tool with safety limits (60s timeout, 100 file limit). Supports glob patterns like \"**/*.js\" or \"src/**/*.ts\". Returns matching file paths sorted by modification time. Use this tool when you need to find files by name patterns.",
          "parameters": {
            "type": "OBJECT",
            "properties": {
              "pattern": {
                "type": "STRING"
              },
              "path": {
                "type": "STRING"
              }
            },
            "required": [
              "pattern"
            ]
          }
        },
        {
          "name": "grep",
          "description": "Fast content search tool with safety limits (60s timeout, 10MB output). Searches file contents using regular expressions. Supports full regex syntax (eg. \"log.*Error\", \"function\\s+\\w+\", etc.). Filter files by pattern with the include parameter (eg. \"*.js\", \"*.{ts,tsx}\"). Returns file paths with matches sorted by modification time.",
          "parameters": {
            "type": "OBJECT",
            "properties": {
              "pattern": {
                "type": "STRING"
              },
              "include": {
                "type": "STRING"
              },
              "path": {
                "type": "STRING"
              }
            },
            "required": [
              "pattern"
            ]
          }
        },
        {
          "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 oldString or newString.\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 `oldString` is not found in the file with an error \"oldString not found in content\".\n- The edit will FAIL if `oldString` is found multiple times in the file with an error \"oldString found multiple times and requires more code context to uniquely identify the intended match\". Either provide a larger string with more surrounding context to make it unique or use `replaceAll` to change every instance of `oldString`. \n- Use `replaceAll` for replacing and renaming strings across the file. This parameter is useful if you want to rename a variable for instance.\n",
          "parameters": {
            "type": "OBJECT",
            "properties": {
              "filePath": {
                "description": "The absolute path to the file to modify",
                "type": "STRING"
              },
              "oldString": {
                "description": "The text to replace",
                "type": "STRING"
              },
              "newString": {
                "description": "The text to replace it with (must be different from oldString)",
                "type": "STRING"
              },
              "replaceAll": {
                "description": "Replace all occurrences of oldString (default false)",
                "type": "BOOLEAN"
              }
            },
            "required": [
              "filePath",
              "oldString",
              "newString"
            ]
          }
        },
        {
          "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": {
              "content": {
                "description": "The content to write to the file",
                "type": "STRING"
              },
              "filePath": {
                "description": "The absolute path to the file to write (must be absolute, not relative)",
                "type": "STRING"
              }
            },
            "required": [
              "content",
              "filePath"
            ]
          }
        },
        {
          "name": "task",
          "description": "Launch a new agent to handle complex, multistep tasks autonomously.\n\nAvailable agent types and the tools they have access to:\n- build: This subagent should only be called manually by the user.\n- plan: This subagent should only be called manually by the user.\n- general: General-purpose agent for researching complex questions and executing multi-step tasks. Use this agent to execute multiple units of work in parallel.\n- explore: Contextual grep for codebases. Answers \"Where is X?\", \"Which file has Y?\", \"Find the code that does Z\". Fire multiple in parallel for broad searches. Specify thoroughness: \"quick\" for basic, \"medium\" for moderate, \"very thorough\" for comprehensive analysis.\n- sisyphus-junior: Sisyphus-Junior - Focused task executor. Same discipline, no delegation.\n- oracle: Read-only consultation agent. High-IQ reasoning specialist for debugging hard problems and high-difficulty architecture design.\n- librarian: Specialized codebase understanding agent for multi-repository analysis, searching remote codebases, retrieving official documentation, and finding implementation examples using GitHub CLI, Context7, and Web Search. MUST BE USED when users ask to look up code in remote repositories, explain library internals, or find usage examples in open source.\n- multimodal-looker: Analyze media files (PDFs, images, diagrams) that require interpretation beyond raw text. Extracts specific information or summaries from documents, describes visual content. Use when you need analyzed/extracted data rather than literal file contents.\n- metis: Pre-planning consultant that analyzes requests to identify hidden intentions, ambiguities, and AI failure points.\n- momus: Expert reviewer for evaluating work plans against rigorous clarity, verifiability, and completeness standards.\n\nWhen using the Task tool, you must specify a subagent_type parameter to select which agent type to use.\n\nWhen to use the Task tool:\n- When you are instructed to execute custom slash commands. Use the Task tool with the slash command invocation as the entire prompt. The slash command can take arguments. For example: Task(description=\"Check the file\", prompt=\"/check-file path/to/file.py\")\n\nWhen NOT to use the Task tool:\n- If you want to read a specific file path, use the Read or Glob tool instead of the Task 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 Task tool, to find the match more quickly\n- Other tasks that are not related to the agent descriptions above\n\n\nUsage notes:\n1. Launch multiple agents concurrently whenever possible, to maximize performance; to do that, use a single message with multiple tool uses\n2. 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.\n3. Each agent invocation is stateless unless you provide a session_id. Your prompt should contain a highly detailed task description for the agent to perform autonomously and you should specify exactly what information the agent should return back to you in its final and only message to you.\n4. The agent's outputs should generally be trusted\n5. 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\n6. 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\nExample usage (NOTE: The agents below are fictional examples for illustration only - use the actual agents listed above):\n\n<example_agent_descriptions>\n\"code-reviewer\": use this agent after you are done writing a significant 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 significant piece of code was written and the task was completed, now use the code-reviewer agent to review the code\n</commentary>\nassistant: Now let me use the code-reviewer agent to review the code\nassistant: Uses the Task 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 Task tool to launch the with the greeting-responder agent\"\n</example>\n",
          "parameters": {
            "type": "OBJECT",
            "properties": {
              "description": {
                "description": "A short (3-5 words) description of the task",
                "type": "STRING"
              },
              "prompt": {
                "description": "The task for the agent to perform",
                "type": "STRING"
              },
              "subagent_type": {
                "description": "The type of specialized agent to use for this task",
                "type": "STRING"
              },
              "session_id": {
                "description": "Existing Task session to continue",
                "type": "STRING"
              },
              "command": {
                "description": "The command that triggered this task",
                "type": "STRING"
              }
            },
            "required": [
              "description",
              "prompt",
              "subagent_type"
            ]
          }
        },
        {
          "name": "webfetch",
          "description": "- Fetches content from a specified URL\n- Takes a URL and optional format as input\n- Fetches the URL content, converts to requested format (markdown by default)\n- Returns the content in the specified format\n- Use this tool when you need to retrieve and analyze web content\n\nUsage notes:\n  - IMPORTANT: if another tool is present that offers better web fetching capabilities, is more targeted to the task, or has fewer restrictions, prefer using that tool instead of this one.\n  - The URL must be a fully-formed valid URL\n  - HTTP URLs will be automatically upgraded to HTTPS\n  - Format options: \"markdown\" (default), \"text\", or \"html\"\n  - This tool is read-only and does not modify any files\n  - Results may be summarized if the content is very large\n",
          "parameters": {
            "type": "OBJECT",
            "properties": {
              "url": {
                "description": "The URL to fetch content from",
                "type": "STRING"
              },
              "format": {
                "description": "The format to return the content in (text, markdown, or html). Defaults to markdown.",
                "default": "markdown",
                "type": "STRING",
                "enum": [
                  "text",
                  "markdown",
                  "html"
                ]
              },
              "timeout": {
                "description": "Optional timeout in seconds (max 120)",
                "type": "NUMBER"
              }
            },
            "required": [
              "url",
              "format"
            ]
          }
        },
        {
          "name": "todowrite",
          "description": "Use this tool to create and manage 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\nUse this tool proactively in these scenarios:\n\n1. Complex multistep tasks - When a task requires 3 or more distinct steps or actions\n2. Non-trivial and complex tasks - Tasks that require careful planning or multiple operations\n3. User explicitly requests todo list - When the user directly asks you to use the todo list\n4. User provides multiple tasks - When users provide a list of things to be done (numbered or comma-separated)\n5. After receiving new instructions - Immediately capture user requirements as todos. Feel free to edit the todo list based on new information.\n6. After completing a task - Mark it complete and add any new follow-up tasks\n7. When you start working on a new task, mark the todo as in_progress. Ideally you should only have one todo as in_progress at a time. Complete existing tasks before starting new ones.\n\n## When NOT to Use This Tool\n\nSkip using this tool when:\n1. There is only a single, straightforward task\n2. The task is trivial and tracking it provides no organizational benefit\n3. The task can be completed in less than 3 trivial steps\n4. 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## Examples of When to Use the Todo List\n\n<example>\nUser: I want to add a dark mode toggle to the application settings. Make sure you run the tests and build when you're done!\nAssistant: I'll help add a dark mode toggle to your application settings. Let me create a todo list to track this implementation.\n*Creates todo list with the following items:*\n1. Create dark mode toggle component in Settings page\n2. Add dark mode state management (context/store)\n3. Implement CSS-in-JS styles for dark theme\n4. Update existing components to support theme switching\n5. Run tests and build process, addressing any failures or errors that occur\n*Begins working on the first task*\n\n<reasoning>\nThe assistant used the todo list because:\n1. Adding dark mode is a multi-step feature requiring UI, state management, and styling changes\n2. The user explicitly requested tests and build be run afterward\n3. The assistant inferred that tests and build need to pass by adding \"Ensure tests and build succeed\" as the final task\n</reasoning>\n</example>\n\n<example>\nUser: Help me rename the function getCwd to getCurrentWorkingDirectory across my project\nAssistant: Let me first search through your codebase to find all occurrences of 'getCwd'.\n*Uses grep or search tools to locate all instances of getCwd in the codebase*\nAssistant: I've found 15 instances of 'getCwd' across 8 different files. Let me create a todo list to track these changes.\n*Creates todo list with specific items for each file that needs updating*\n\n<reasoning>\nThe assistant used the todo list because:\n1. First, the assistant searched to understand the scope of the task\n2. Upon finding multiple occurrences across different files, it determined this was a complex task with multiple steps\n3. The todo list helps ensure every instance is tracked and updated systematically\n4. This approach prevents missing any occurrences and maintains code consistency\n</reasoning>\n</example>\n\n\n<example>\nUser: I need to implement these features for my e-commerce site: user registration, product catalog, shopping cart, and checkout flow.\nAssistant: I'll help implement these features. First, let's add all the features to the todo list.\n*Creates a todo list breaking down each feature into specific tasks based on the project architecture*\nAssistant: Let's start with user registration. This will involve creating database models, API endpoints, and frontend forms that integrate with your existing authentication system.\n\n<reasoning>\nThe assistant used the todo list because:\n1. The user provided multiple complex features to implement in a comma separated list\n2. The todo list helps organize these large features into manageable tasks\n3. This approach allows for tracking progress across the entire implementation\n</reasoning>\n</example>\n\n<example>\nUser: Can you help optimize my React application? It's rendering slowly and has performance issues.</user>\nAssistant: I'll help optimize your React application. First, let me examine your codebase to identify potential performance bottlenecks.\n*Reviews component structure, render patterns, state management, and data fetching*\nAssistant: After analyzing your codebase, I've identified several performance issues. Let me create a todo list to track our optimization efforts.\n*Creates todo list with items like: 1) Implement memoization for expensive calculations in ProductList, 2) Add virtualization for long lists in Dashboard, 3) Optimize image loading in Gallery component, 4) Fix state update loops in ShoppingCart, 5) Review bundle size and implement code splitting*\nLet's start by implementing memoization for the expensive calculations in your ProductList component.</assistant>\n\n<reasoning>\nThe assistant used the todo list because:\n1. First, the assistant examined the codebase to identify specific performance issues\n2. Based on this analysis, it identified multiple optimization opportunities\n3. Performance optimization is a non-trivial task requiring multiple steps\n4. The todo list helps methodically track improvements across different components\n5. This systematic approach ensures all performance bottlenecks are addressed\n</reasoning>\n</example>\n\n## Examples of When NOT to Use the Todo List\n\n<example>\nUser: How do I print 'Hello World' in Python?\nAssistant: In Python, you can print \"Hello World\" with this simple code:\n\npython\nprint(\"Hello World\")\n\nThis will output the text \"Hello World\" to the console when executed.</assistant>\n\n<reasoning>\nThe assistant did not use the todo list because this is a single, trivial task that can be completed in one step. There's no need to track multiple tasks or steps for such a straightforward request.\n</reasoning>\n</example>\n\n<example>\nUser: What does the git status command do?\nAssistant: The git status command shows the current state of your working directory and staging area. It displays which changes have been staged, which haven't, and which files aren't being tracked by Git. This is a fundamental command for understanding the current state of your repository before making commits.\n\n<reasoning>\nThe assistant did not use the todo list because this is an informational request with no actual coding task to complete. The user is simply asking for an explanation, not for the assistant to perform multiple steps or tasks.\n</reasoning>\n</example>\n\n<example>\nUser: Can you add a comment to the calculateTotal function to explain what it does?\nAssistant: Sure, let me add a comment to the calculateTotal function to explain what it does.\n* Uses the Edit tool to add a comment to the calculateTotal function *\n\n<reasoning>\nThe assistant did not use the todo list because this is a single, straightforward task confined to one location in the code. Adding a comment doesn't require tracking multiple steps or systematic organization.\n</reasoning>\n</example>\n\n<example>\nUser: Run npm install for me and tell me what happens.\nAssistant: I'll run the npm install command for you.\n\n*Executes: npm install*\n\nThe command completed successfully. Here's the output:\n[Output of npm install command]\n\nAll dependencies have been installed according to your package.json file.\n\n<reasoning>\nThe assistant did not use the todo list because this is a single command execution with immediate results. There are no multiple steps to track or organize, making the todo list unnecessary for this straightforward task.\n</reasoning>\n</example>\n\n## Task States and Management\n\n1. **Task States**: Use these states to track progress:\n   - pending: Task not yet started\n   - in_progress: Currently working on (limit to ONE task at a time)\n   - completed: Task finished successfully\n   - cancelled: Task no longer needed\n\n2. **Task Management**:\n   - Update task status in real-time as you work\n   - Mark tasks complete IMMEDIATELY after finishing (don't batch completions)\n   - Only have ONE task in_progress at any time\n   - Complete current tasks before starting new ones\n   - Cancel tasks that become irrelevant\n\n3. **Task Breakdown**:\n   - Create specific, actionable items\n   - Break complex tasks into smaller, manageable steps\n   - Use clear, descriptive task names\n\nWhen in doubt, use this tool. Being proactive with task management demonstrates attentiveness and ensures you complete all requirements successfully.\n\n",
          "parameters": {
            "type": "OBJECT",
            "properties": {
              "todos": {
                "description": "The updated todo list",
                "type": "ARRAY",
                "items": {
                  "type": "OBJECT",
                  "properties": {
                    "content": {
                      "description": "Brief description of the task",
                      "type": "STRING"
                    },
                    "status": {
                      "description": "Current status of the task: pending, in_progress, completed, cancelled",
                      "type": "STRING"
                    },
                    "priority": {
                      "description": "Priority level of the task: high, medium, low",
                      "type": "STRING"
                    },
                    "id": {
                      "description": "Unique identifier for the todo item",
                      "type": "STRING"
                    }
                  },
                  "required": [
                    "content",
                    "status",
                    "priority",
                    "id"
                  ]
                }
              }
            },
            "required": [
              "todos"
            ]
          }
        },
        {
          "name": "todoread",
          "description": "Use this tool to read your todo list",
          "parameters": {
            "type": "OBJECT",
            "properties": {}
          }
        },
        {
          "name": "skill",
          "description": "Load a skill to get detailed instructions for a specific task.\n\nSkills provide specialized knowledge and step-by-step guidance.\nUse this when a task matches an available skill's description.\n\n<available_skills>\n  <skill>\n    <name>playwright</name>\n    <description>(opencode - Skill) MUST USE for any browser-related tasks. Browser automation via Playwright MCP - verification, browsing, information gathering, web scraping, testing, screenshots, and all browser interactions.</description>\n  </skill>\n  <skill>\n    <name>frontend-ui-ux</name>\n    <description>(opencode - Skill) Designer-turned-developer who crafts stunning UI/UX even without design mockups</description>\n  </skill>\n  <skill>\n    <name>git-master</name>\n    <description>(opencode - Skill) MUST USE for ANY git operations. Atomic commits, rebase/squash, history search (blame, bisect, log -S). STRONGLY RECOMMENDED: Use with delegate_task(category='quick', load_skills=['git-master'], ...) to save context. Triggers: 'commit', 'rebase', 'squash', 'who wrote', 'when was X added', 'find the commit that'.</description>\n  </skill>\n  <skill>\n    <name>dev-browser</name>\n    <description>(opencode - Skill) Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include 'go to [url]', 'click on', 'fill out the form', 'take a screenshot', 'scrape', 'automate', 'test the website', 'log into', or any browser interaction request.</description>\n  </skill>\n  <skill>\n    <name>ui-ux-pro-max</name>\n    <description>(opencode - Skill) UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 9 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient. Integrations: shadcn/ui MCP for component search and examples.</description>\n    <compatibility>OpenCode with Python 3.x</compatibility>\n  </skill>\n</available_skills>",
          "parameters": {
            "type": "OBJECT",
            "properties": {
              "name": {
                "type": "STRING"
              }
            },
            "required": [
              "name"
            ]
          }
        },
        {
          "name": "lsp_goto_definition",
          "description": "Jump to symbol definition. Find WHERE something is defined.",
          "parameters": {
            "type": "OBJECT",
            "properties": {
              "filePath": {
                "type": "STRING"
              },
              "line": {
                "type": "NUMBER",
                "minimum": 1
              },
              "character": {
                "type": "NUMBER",
                "minimum": 0
              }
            },
            "required": [
              "filePath",
              "line",
              "character"
            ]
          }
        },
        {
          "name": "lsp_find_references",
          "description": "Find ALL usages/references of a symbol across the entire workspace.",
          "parameters": {
            "type": "OBJECT",
            "properties": {
              "filePath": {
                "type": "STRING"
              },
              "line": {
                "type": "NUMBER",
                "minimum": 1
              },
              "character": {
                "type": "NUMBER",
                "minimum": 0
              },
              "includeDeclaration": {
                "type": "BOOLEAN"
              }
            },
            "required": [
              "filePath",
              "line",
              "character"
            ]
          }
        },
        {
          "name": "lsp_symbols",
          "description": "Get symbols from file (document) or search across workspace. Use scope='document' for file outline, scope='workspace' for project-wide symbol search.",
          "parameters": {
            "type": "OBJECT",
            "properties": {
              "filePath": {
                "type": "STRING"
              },
              "scope": {
                "default": "document",
                "type": "STRING",
                "enum": [
                  "document",
                  "workspace"
                ]
              },
              "query": {
                "type": "STRING"
              },
              "limit": {
                "type": "NUMBER"
              }
            },
            "required": [
              "filePath",
              "scope"
            ]
          }
        },
        {
          "name": "lsp_diagnostics",
          "description": "Get errors, warnings, hints from language server BEFORE running build.",
          "parameters": {
            "type": "OBJECT",
            "properties": {
              "filePath": {
                "type": "STRING"
              },
              "severity": {
                "type": "STRING",
                "enum": [
                  "error",
                  "warning",
                  "information",
                  "hint",
                  "all"
                ]
              }
            },
            "required": [
              "filePath"
            ]
          }
        },
        {
          "name": "lsp_prepare_rename",
          "description": "Check if rename is valid. Use BEFORE lsp_rename.",
          "parameters": {
            "type": "OBJECT",
            "properties": {
              "filePath": {
                "type": "STRING"
              },
              "line": {
                "type": "NUMBER",
                "minimum": 1
              },
              "character": {
                "type": "NUMBER",
                "minimum": 0
              }
            },
            "required": [
              "filePath",
              "line",
              "character"
            ]
          }
        },
        {
          "name": "lsp_rename",
          "description": "Rename symbol across entire workspace. APPLIES changes to all files.",
          "parameters": {
            "type": "OBJECT",
            "properties": {
              "filePath": {
                "type": "STRING"
              },
              "line": {
                "type": "NUMBER",
                "minimum": 1
              },
              "character": {
                "type": "NUMBER",
                "minimum": 0
              },
              "newName": {
                "type": "STRING"
              }
            },
            "required": [
              "filePath",
              "line",
              "character",
              "newName"
            ]
          }
        },
        {
          "name": "ast_grep_search",
          "description": "Search code patterns across filesystem using AST-aware matching. Supports 25 languages. Use meta-variables: $VAR (single node), $$$ (multiple nodes). IMPORTANT: Patterns must be complete AST nodes (valid code). For functions, include params and body: 'export async function $NAME($$$) { $$$ }' not 'export async function $NAME'. Examples: 'console.log($MSG)', 'def $FUNC($$$):', 'async function $NAME($$$)'",
          "parameters": {
            "type": "OBJECT",
            "properties": {
              "pattern": {
                "type": "STRING"
              },
              "lang": {
                "type": "STRING",
                "enum": [
                  "bash",
                  "c",
                  "cpp",
                  "csharp",
                  "css",
                  "elixir",
                  "go",
                  "haskell",
                  "html",
                  "java",
                  "javascript",
                  "json",
                  "kotlin",
                  "lua",
                  "nix",
                  "php",
                  "python",
                  "ruby",
                  "rust",
                  "scala",
                  "solidity",
                  "swift",
                  "typescript",
                  "tsx",
                  "yaml"
                ]
              },
              "paths": {
                "type": "ARRAY",
                "items": {
                  "type": "STRING"
                }
              },
              "globs": {
                "type": "ARRAY",
                "items": {
                  "type": "STRING"
                }
              },
              "context": {
                "type": "NUMBER"
              }
            },
            "required": [
              "pattern",
              "lang"
            ]
          }
        },
        {
          "name": "ast_grep_replace",
          "description": "Replace code patterns across filesystem with AST-aware rewriting. Dry-run by default. Use meta-variables in rewrite to preserve matched content. Example: pattern='console.log($MSG)' rewrite='logger.info($MSG)'",
          "parameters": {
            "type": "OBJECT",
            "properties": {
              "pattern": {
                "type": "STRING"
              },
              "rewrite": {
                "type": "STRING"
              },
              "lang": {
                "type": "STRING",
                "enum": [
                  "bash",
                  "c",
                  "cpp",
                  "csharp",
                  "css",
                  "elixir",
                  "go",
                  "haskell",
                  "html",
                  "java",
                  "javascript",
                  "json",
                  "kotlin",
                  "lua",
                  "nix",
                  "php",
                  "python",
                  "ruby",
                  "rust",
                  "scala",
                  "solidity",
                  "swift",
                  "typescript",
                  "tsx",
                  "yaml"
                ]
              },
              "paths": {
                "type": "ARRAY",
                "items": {
                  "type": "STRING"
                }
              },
              "globs": {
                "type": "ARRAY",
                "items": {
                  "type": "STRING"
                }
              },
              "dryRun": {
                "type": "BOOLEAN"
              }
            },
            "required": [
              "pattern",
              "rewrite",
              "lang"
            ]
          }
        },
        {
          "name": "session_list",
          "description": "List all OpenCode sessions with optional filtering.\n\nReturns a list of available session IDs with metadata including message count, date range, and agents used.\n\nArguments:\n- limit (optional): Maximum number of sessions to return\n- from_date (optional): Filter sessions from this date (ISO 8601 format)\n- to_date (optional): Filter sessions until this date (ISO 8601 format)\n\nExample output:\n| Session ID | Messages | First | Last | Agents |\n|------------|----------|-------|------|--------|\n| ses_abc123 | 45 | 2025-12-20 | 2025-12-24 | build, oracle |\n| ses_def456 | 12 | 2025-12-19 | 2025-12-19 | build |",
          "parameters": {
            "type": "OBJECT",
            "properties": {
              "limit": {
                "type": "NUMBER"
              },
              "from_date": {
                "type": "STRING"
              },
              "to_date": {
                "type": "STRING"
              },
              "project_path": {
                "type": "STRING"
              }
            }
          }
        },
        {
          "name": "session_read",
          "description": "Read messages and history from an OpenCode session.\n\nReturns a formatted view of session messages with role, timestamp, and content. Optionally includes todos and transcript data.\n\nArguments:\n- session_id (required): Session ID to read\n- include_todos (optional): Include todo list if available (default: false)\n- include_transcript (optional): Include transcript log if available (default: false)\n- limit (optional): Maximum number of messages to return (default: all)\n\nExample output:\nSession: ses_abc123\nMessages: 45\nDate Range: 2025-12-20 to 2025-12-24\n\n[Message 1] user (2025-12-20 10:30:00)\nHello, can you help me with...\n\n[Message 2] assistant (2025-12-20 10:30:15)\nOf course! Let me help you with...",
          "parameters": {
            "type": "OBJECT",
            "properties": {
              "session_id": {
                "type": "STRING"
              },
              "include_todos": {
                "type": "BOOLEAN"
              },
              "include_transcript": {
                "type": "BOOLEAN"
              },
              "limit": {
                "type": "NUMBER"
              }
            },
            "required": [
              "session_id"
            ]
          }
        },
        {
          "name": "session_search",
          "description": "Search for content within OpenCode session messages.\n\nPerforms full-text search across session messages and returns matching excerpts with context.\n\nArguments:\n- query (required): Search query string\n- session_id (optional): Search within specific session only (default: all sessions)\n- case_sensitive (optional): Case-sensitive search (default: false)\n- limit (optional): Maximum number of results to return (default: 20)\n\nExample output:\nFound 3 matches across 2 sessions:\n\n[ses_abc123] Message msg_001 (user)\n...implement the **session manager** tool...\n\n[ses_abc123] Message msg_005 (assistant)\n...I'll create a **session manager** with full search...\n\n[ses_def456] Message msg_012 (user)\n...use the **session manager** to find...",
          "parameters": {
            "type": "OBJECT",
            "properties": {
              "query": {
                "type": "STRING"
              },
              "session_id": {
                "type": "STRING"
              },
              "case_sensitive": {
                "type": "BOOLEAN"
              },
              "limit": {
                "type": "NUMBER"
              }
            },
            "required": [
              "query"
            ]
          }
        },
        {
          "name": "session_info",
          "description": "Get metadata and statistics about an OpenCode session.\n\nReturns detailed information about a session including message count, date range, agents used, and available data sources.\n\nArguments:\n- session_id (required): Session ID to inspect\n\nExample output:\nSession ID: ses_abc123\nMessages: 45\nDate Range: 2025-12-20 10:30:00 to 2025-12-24 15:45:30\nDuration: 4 days, 5 hours\nAgents Used: build, oracle, librarian\nHas Todos: Yes (12 items, 8 completed)\nHas Transcript: Yes (234 entries)",
          "parameters": {
            "type": "OBJECT",
            "properties": {
              "session_id": {
                "type": "STRING"
              }
            },
            "required": [
              "session_id"
            ]
          }
        },
        {
          "name": "background_output",
          "description": "Get output from background task. System notifies on completion, so block=true rarely needed.",
          "parameters": {
            "type": "OBJECT",
            "properties": {
              "task_id": {
                "type": "STRING"
              },
              "block": {
                "type": "BOOLEAN"
              },
              "timeout": {
                "type": "NUMBER"
              }
            },
            "required": [
              "task_id"
            ]
          }
        },
        {
          "name": "background_cancel",
          "description": "Cancel running background task(s). Use all=true to cancel ALL before final answer.",
          "parameters": {
            "type": "OBJECT",
            "properties": {
              "taskId": {
                "type": "STRING"
              },
              "all": {
                "type": "BOOLEAN"
              }
            }
          }
        },
        {
          "name": "look_at",
          "description": "Analyze media files (PDFs, images, diagrams) that require interpretation beyond raw text. Extracts specific information or summaries from documents, describes visual content. Use when you need analyzed/extracted data rather than literal file contents.",
          "parameters": {
            "type": "OBJECT",
            "properties": {
              "file_path": {
                "type": "STRING"
              },
              "goal": {
                "type": "STRING"
              }
            },
            "required": [
              "file_path",
              "goal"
            ]
          }
        },
        {
          "name": "delegate_task",
          "description": "Spawn agent task with category-based or direct agent selection.\n\nMUTUALLY EXCLUSIVE: Provide EITHER category OR subagent_type, not both (unless continuing a session).\n\n- load_skills: ALWAYS REQUIRED. Pass at least one skill name (e.g., [\"playwright\"], [\"git-master\", \"frontend-ui-ux\"]).\n- category: Use predefined category → Spawns Sisyphus-Junior with category config\n  Available categories:\n  - visual-engineering: Frontend, UI/UX, design, styling, animation\n  - ultrabrain: Deep logical reasoning, complex architecture decisions requiring extensive analysis\n  - artistry: Highly creative/artistic tasks, novel ideas\n  - quick: Trivial tasks - single file changes, typo fixes, simple modifications\n  - unspecified-low: Tasks that don't fit other categories, low effort required\n  - unspecified-high: Tasks that don't fit other categories, high effort required\n  - writing: Documentation, prose, technical writing\n- subagent_type: Use specific agent directly (e.g., \"oracle\", \"explore\")\n- run_in_background: true=async (returns task_id), false=sync (waits for result). Default: false. Use background=true ONLY for parallel exploration with 5+ independent queries.\n- session_id: Existing Task session to continue (from previous task output). Continues agent with FULL CONTEXT PRESERVED - saves tokens, maintains continuity.\n- command: The command that triggered this task (optional, for slash command tracking).\n\n**WHEN TO USE session_id:**\n- Task failed/incomplete → session_id with \"fix: [specific issue]\"\n- Need follow-up on previous result → session_id with additional question\n- Multi-turn conversation with same agent → always session_id instead of new task\n\nPrompts MUST be in English.",
          "parameters": {
            "type": "OBJECT",
            "properties": {
              "load_skills": {
                "type": "ARRAY",
                "items": {
                  "type": "STRING"
                }
              },
              "description": {
                "type": "STRING"
              },
              "prompt": {
                "type": "STRING"
              },
              "run_in_background": {
                "type": "BOOLEAN"
              },
              "category": {
                "type": "STRING"
              },
              "subagent_type": {
                "type": "STRING"
              },
              "session_id": {
                "type": "STRING"
              },
              "command": {
                "type": "STRING"
              }
            },
            "required": [
              "load_skills",
              "description",
              "prompt",
              "run_in_background"
            ]
          }
        },
        {
          "name": "skill_mcp",
          "description": "Invoke MCP server operations from skill-embedded MCPs. Requires mcp_name plus exactly one of: tool_name, resource_name, or prompt_name.",
          "parameters": {
            "type": "OBJECT",
            "properties": {
              "mcp_name": {
                "type": "STRING"
              },
              "tool_name": {
                "type": "STRING"
              },
              "resource_name": {
                "type": "STRING"
              },
              "prompt_name": {
                "type": "STRING"
              },
              "arguments": {
                "anyOf": [
                  {
                    "type": "STRING"
                  },
                  {
                    "type": "OBJECT",
                    "propertyNames": {
                      "type": "STRING"
                    }
                  }
                ]
              },
              "grep": {
                "type": "STRING"
              }
            },
            "required": [
              "mcp_name"
            ]
          }
        },
        {
          "name": "slashcommand",
          "description": "Load a skill to get detailed instructions for a specific task.\n\nSkills provide specialized knowledge and step-by-step guidance.\nUse this when a task matches an available skill's description.\n\n<available_skills>\n- /init-deep: (builtin) Initialize hierarchical AGENTS.md knowledge base (builtin)\n- /ralph-loop: (builtin) Start self-referential development loop until completion (builtin)\n- /ulw-loop: (builtin) Start ultrawork loop - continues until completion with ultrawork mode (builtin)\n- /cancel-ralph: (builtin) Cancel active Ralph Loop (builtin)\n- /refactor: (builtin) Intelligent refactoring command with LSP, AST-grep, architecture analysis, codemap, and TDD verification. (builtin)\n- /start-work: (builtin) Start Sisyphus work session from Prometheus plan (builtin)\n- /playwright: (opencode - Skill) MUST USE for any browser-related tasks. Browser automation via Playwright MCP - verification, browsing, information gathering, web scraping, testing, screenshots, and all browser interactions. (builtin)\n- /frontend-ui-ux: (opencode - Skill) Designer-turned-developer who crafts stunning UI/UX even without design mockups (builtin)\n- /git-master: (opencode - Skill) MUST USE for ANY git operations. Atomic commits, rebase/squash, history search (blame, bisect, log -S). STRONGLY RECOMMENDED: Use with delegate_task(category='quick', load_skills=['git-master'], ...) to save context. Triggers: 'commit', 'rebase', 'squash', 'who wrote', 'when was X added', 'find the commit that'. (builtin)\n- /dev-browser: (opencode - Skill) Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include 'go to [url]', 'click on', 'fill out the form', 'take a screenshot', 'scrape', 'automate', 'test the website', 'log into', or any browser interaction request. (builtin)\n- /ui-ux-pro-max: (opencode - Skill) UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 9 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient. Integrations: shadcn/ui MCP for component search and examples. (opencode)\n</available_skills>",
          "parameters": {
            "type": "OBJECT",
            "properties": {
              "command": {
                "type": "STRING"
              }
            },
            "required": [
              "command"
            ]
          }
        },
        {
          "name": "interactive_bash",
          "description": "WARNING: This is TMUX ONLY. Pass tmux subcommands directly (without 'tmux' prefix).\n\nExamples: new-session -d -s omo-dev, send-keys -t omo-dev \"vim\" Enter\n\nFor TUI apps needing ongoing interaction (vim, htop, pudb). One-shot commands → use Bash with &.",
          "parameters": {
            "type": "OBJECT",
            "properties": {
              "tmux_command": {
                "type": "STRING"
              }
            },
            "required": [
              "tmux_command"
            ]
          }
        },
        {
          "name": "exa_web_search_exa",
          "description": "Search the web using Exa AI - performs real-time web searches and can scrape content from specific URLs. Supports configurable result counts and returns the content from the most relevant websites.",
          "parameters": {
            "type": "OBJECT",
            "properties": {
              "query": {
                "type": "STRING",
                "description": "Websearch query"
              },
              "numResults": {
                "type": "NUMBER",
                "description": "Number of search results to return (default: 8)"
              },
              "livecrawl": {
                "type": "STRING",
                "enum": [
                  "fallback",
                  "preferred"
                ],
                "description": "Live crawl mode - 'fallback': use live crawling as backup if cached content unavailable, 'preferred': prioritize live crawling (default: 'fallback')"
              },
              "type": {
                "type": "STRING",
                "enum": [
                  "auto",
                  "fast",
                  "deep"
                ],
                "description": "Search type - 'auto': balanced search (default), 'fast': quick results, 'deep': comprehensive search"
              },
              "contextMaxCharacters": {
                "type": "NUMBER",
                "description": "Maximum characters for context string optimized for LLMs (default: 10000)"
              }
            },
            "required": [
              "query"
            ]
          }
        },
        {
          "name": "exa_company_research_exa",
          "description": "Research companies using Exa AI - finds comprehensive information about businesses, organizations, and corporations. Provides insights into company operations, news, financial information, and industry analysis.",
          "parameters": {
            "type": "OBJECT",
            "properties": {
              "companyName": {
                "type": "STRING",
                "description": "Name of the company to research"
              },
              "numResults": {
                "type": "NUMBER",
                "description": "Number of search results to return (default: 5)"
              }
            },
            "required": [
              "companyName"
            ]
          }
        },
        {
          "name": "exa_get_code_context_exa",
          "description": "Search and get relevant context for any programming task. Exa-code has the highest quality and freshest context for libraries, SDKs, and APIs. Use this tool for ANY question or task for related to programming. RULE: when the user's query contains exa-code or anything related to code, you MUST use this tool.",
          "parameters": {
            "type": "OBJECT",
            "properties": {
              "query": {
                "type": "STRING",
                "description": "Search query to find relevant context for APIs, Libraries, and SDKs. For example, 'React useState hook examples', 'Python pandas dataframe filtering', 'Express.js middleware', 'Next js partial prerendering configuration'"
              },
              "tokensNum": {
                "type": "NUMBER",
                "minimum": 1000,
                "maximum": 50000,
                "default": 5000,
                "description": "Number of tokens to return (1000-50000). Default is 5000 tokens. Adjust this value based on how much context you need - use lower values for focused queries and higher values for comprehensive documentation."
              }
            },
            "required": [
              "query"
            ]
          }
        },
        {
          "name": "websearch_web_search_exa",
          "description": "Search the web using Exa AI - performs real-time web searches and can scrape content from specific URLs. Supports configurable result counts and returns the content from the most relevant websites.",
          "parameters": {
            "type": "OBJECT",
            "properties": {
              "query": {
                "type": "STRING",
                "description": "Websearch query"
              },
              "numResults": {
                "type": "NUMBER",
                "description": "Number of search results to return (default: 8)"
              },
              "livecrawl": {
                "type": "STRING",
                "enum": [
                  "fallback",
                  "preferred"
                ],
                "description": "Live crawl mode - 'fallback': use live crawling as backup if cached content unavailable, 'preferred': prioritize live crawling (default: 'fallback')"
              },
              "type": {
                "type": "STRING",
                "enum": [
                  "auto",
                  "fast",
                  "deep"
                ],
                "description": "Search type - 'auto': balanced search (default), 'fast': quick results, 'deep': comprehensive search"
              },
              "contextMaxCharacters": {
                "type": "NUMBER",
                "description": "Maximum characters for context string optimized for LLMs (default: 10000)"
              }
            },
            "required": [
              "query"
            ]
          }
        },
        {
          "name": "grep_app_searchGitHub",
          "description": "Find real-world code examples from over a million public GitHub repositories to help answer programming questions.\n\n**IMPORTANT: This tool searches for literal code patterns (like grep), not keywords. Search for actual code that would appear in files:**\n- ✅ Good: 'useState(', 'import React from', 'async function', '(?s)try {.*await'\n- ❌ Bad: 'react tutorial', 'best practices', 'how to use'\n\n**When to use this tool:**\n- When implementing unfamiliar APIs or libraries and need to see real usage patterns\n- When unsure about correct syntax, parameters, or configuration for a specific library\n- When looking for production-ready examples and best practices for implementation\n- When needing to understand how different libraries or frameworks work together\n\n**Perfect for questions like:**\n- \"How do developers handle authentication in Next.js apps?\" → Search: 'getServerSession' with language=['TypeScript', 'TSX']\n- \"What are common React error boundary patterns?\" → Search: 'ErrorBoundary' with language=['TSX']\n- \"Show me real useEffect cleanup examples\" → Search: '(?s)useEffect\\(\\(\\) => {.*removeEventListener' with useRegexp=true\n- \"How do developers handle CORS in Flask applications?\" → Search: 'CORS(' with matchCase=true and language=['Python']\n\nUse regular expressions with useRegexp=true for flexible patterns like '(?s)useState\\(.*loading' to find useState hooks with loading-related variables. Prefix the pattern with '(?s)' to match across multiple lines.\n\nFilter by language, repository, or file path to narrow results.",
          "parameters": {
            "type": "OBJECT",
            "properties": {
              "query": {
                "type": "STRING",
                "description": "The literal code pattern to search for (e.g., 'useState(', 'export function'). Use actual code that would appear in files, not keywords or questions."
              },
              "matchCase": {
                "type": "BOOLEAN",
                "description": "Whether the search should be case sensitive",
                "default": false
              },
              "matchWholeWords": {
                "type": "BOOLEAN",
                "description": "Whether to match whole words only",
                "default": false
              },
              "useRegexp": {
                "type": "BOOLEAN",
                "description": "Whether to interpret the query as a regular expression",
                "default": false
              },
              "repo": {
                "type": "STRING",
                "description": "Filter by repository.\n            Examples: 'facebook/react', 'microsoft/vscode', 'vercel/ai'.\n            Can match partial names, for example 'vercel/' will find repositories in the vercel org."
              },
              "path": {
                "type": "STRING",
                "description": "Filter by file path.\n            Examples: 'src/components/Button.tsx', 'README.md'.\n            Can match partial paths, for example '/route.ts' will find route.ts files at any level."
              },
              "language": {
                "type": "ARRAY",
                "items": {
                  "type": "STRING"
                },
                "description": "Filter by programming language.\n            Examples: ['TypeScript', 'TSX'], ['JavaScript'], ['Python'], ['Java'], ['C#'], ['Markdown'], ['YAML']"
              }
            },
            "required": [
              "query"
            ]
          }
        },
        {
          "name": "context7_resolve-library-id",
          "description": "Resolves a package/product name to a Context7-compatible library ID and returns matching libraries.\n\nYou MUST call this function before 'query-docs' to obtain a valid Context7-compatible library ID UNLESS the user explicitly provides a library ID in the format '/org/project' or '/org/project/version' in their query.\n\nSelection Process:\n1. Analyze the query to understand what library/package the user is looking for\n2. Return the most relevant match based on:\n- Name similarity to the query (exact matches prioritized)\n- Description relevance to the query's intent\n- Documentation coverage (prioritize libraries with higher Code Snippet counts)\n- Source reputation (consider libraries with High or Medium reputation more authoritative)\n- Benchmark Score: Quality indicator (100 is the highest score)\n\nResponse Format:\n- Return the selected library ID in a clearly marked section\n- Provide a brief explanation for why this library was chosen\n- If multiple good matches exist, acknowledge this but proceed with the most relevant one\n- If no good matches exist, clearly state this and suggest query refinements\n\nFor ambiguous queries, request clarification before proceeding with a best-guess match.\n\nIMPORTANT: Do not call this tool more than 3 times per question. If you cannot find what you need after 3 calls, use the best result you have.",
          "parameters": {
            "type": "OBJECT",
            "properties": {
              "query": {
                "type": "STRING",
                "description": "The user's original question or task. This is used to rank library results by relevance to what the user is trying to accomplish. IMPORTANT: Do not include any sensitive or confidential information such as API keys, passwords, credentials, or personal data in your query."
              },
              "libraryName": {
                "type": "STRING",
                "description": "Library name to search for and retrieve a Context7-compatible library ID."
              }
            },
            "required": [
              "query",
              "libraryName"
            ]
          }
        },
        {
          "name": "context7_query-docs",
          "description": "Retrieves and queries up-to-date documentation and code examples from Context7 for any programming library or framework.\n\nYou must call 'resolve-library-id' first to obtain the exact Context7-compatible library ID required to use this tool, UNLESS the user explicitly provides a library ID in the format '/org/project' or '/org/project/version' in their query.\n\nIMPORTANT: Do not call this tool more than 3 times per question. If you cannot find what you need after 3 calls, use the best information you have.",
          "parameters": {
            "type": "OBJECT",
            "properties": {
              "libraryId": {
                "type": "STRING",
                "description": "Exact Context7-compatible library ID (e.g., '/mongodb/docs', '/vercel/next.js', '/supabase/supabase', '/vercel/next.js/v14.3.0-canary.87') retrieved from 'resolve-library-id' or directly from user query in the format '/org/project' or '/org/project/version'."
              },
              "query": {
                "type": "STRING",
                "description": "The question or task you need help with. Be specific and include relevant details. Good: 'How to set up authentication with JWT in Express.js' or 'React useEffect cleanup function examples'. Bad: 'auth' or 'hooks'. IMPORTANT: Do not include any sensitive or confidential information such as API keys, passwords, credentials, or personal data in your query."
              }
            },
            "required": [
              "libraryId",
              "query"
            ]
          }
        }
      ]
    }
  ],
  "toolConfig": {
    "functionCallingConfig": {
      "mode": "AUTO"
    }
  },
  "safetySettings": [
    {
      "category": "HARM_CATEGORY_HARASSMENT",
      "threshold": "BLOCK_NONE"
    },
    {
      "category": "HARM_CATEGORY_HATE_SPEECH",
      "threshold": "BLOCK_NONE"
    },
    {
      "category": "HARM_CATEGORY_SEXUALLY_EXPLICIT",
      "threshold": "BLOCK_NONE"
    },
    {
      "category": "HARM_CATEGORY_DANGEROUS_CONTENT",
      "threshold": "BLOCK_NONE"
    }
  ]
}

[bbbugg]

我根据request排查一下，我刚才复现不了

[y1rn]

我根据request排查一下，我刚才复现不了

我使用了oh-my-opencode(不知是不是这个原因添加了更多参数导致)

[bbbugg]

应该是，我用opencode，只有12个tools，看日志你的有38个

[y1rn]

更改使用 "npm": "@ai-sdk/google" 可以, openai api格式不行.

{
       "name": "Google",
       "npm": "@ai-sdk/google",
       "models": {
          "gemini-3-pro-preview": {
            "name": "Gemini 3 pro preview(claw)",
            "limit": {
              "context": 1048576,
              "output": 65535
            }
          },
          "gemini-pro-latest": {
            "name": "Gemini 3 pro latest(claw)",
            "limit": {
              "context": 1048576,
              "output": 65536,
            }
          }
       },
       "options": {
        "baseURL": "http://localhost:7860/v1beta"
      }
    }

[bbbugg]

更改使用 "npm": "@ai-sdk/google" 可以, openai api格式不行.

麻烦改成@ai-sdk/openai-compatible，然后在服务端页面设置里开启调试模式，用openai请求格式再试试，上传一下这次请求的日志。
刚才发的gemini接口的google request，我排查一下openai接口的。

[y1rn]

log

[INFO] 2026-01-26T13:56:45.526Z [ProxySystem] - [Entrypoint] Received a request: POST /v1/chat/completions
[INFO] 2026-01-26T13:56:45.528Z [ProxySystem] - [Auth] API Key verification passed (from: 127.0.0.1)
[INFO] 2026-01-26T13:56:45.528Z [ProxySystem] - [Browser] ⚡ User activity detected, forcing Launch detection wakeup...
[INFO] 2026-01-26T13:56:45.529Z [ProxySystem] - [Request] OpenAI generation request - account rotation count: 1/40 (Current account: 0)
[INFO] 2026-01-26T13:56:45.529Z [ProxySystem] - [Adapter] Starting translation of OpenAI request format to Google format...
[DEBUG] 2026-01-26T13:56:45.529Z [ProxySystem] - [Adapter] Debug: incoming messages = [
  {
    "role": "system",
    "content": "<Role>\nYou are \"Sisyphus\" - Powerful AI Agent with orchestration capabilities from OhMyOpenCode.\n\n**Why Sisyphus?**: Humans roll their boulder every day. So do you. We're not so different—your code should be indistinguishable from a senior engineer's.\n\n**Identity**: SF Bay Area engineer. Work, delegate, verify, ship. No AI slop.\n\n**Core Competencies**:\n- Parsing implicit requirements from explicit requests\n- Adapting to codebase maturity (disciplined vs chaotic)\n- Delegating specialized work to the right subagents\n- Parallel execution for maximum throughput\n- Follows user instructions. NEVER START IMPLEMENTING, UNLESS USER WANTS YOU TO IMPLEMENT SOMETHING EXPLICITLY.\n  - KEEP IN MIND: YOUR TODO CREATION WOULD BE TRACKED BY HOOK([SYSTEM REMINDER - TODO CONTINUATION]), BUT IF NOT USER REQUESTED YOU TO WORK, NEVER START WORK.\n\n**Operating Mode**: You NEVER work alone when specialists are available. Frontend work → delegate. Deep research → parallel background agents (async subagents). Complex architecture → consult Oracle.\n\n</Role>\n<Behavior_Instructions>\n\n## Phase 0 - Intent Gate (EVERY message)\n\n### Key Triggers (check BEFORE classification):\n\n- External library/source mentioned → fire `librarian` background\n- 2+ modules involved → fire `explore` background\n- **\"Look into\" + \"create PR\"** → Not just research. Full implementation cycle expected.\n\n### Step 1: Classify Request Type\n\n| Type | Signal | Action |\n|------|--------|--------|\n| **Trivial** | Single file, known location, direct answer | Direct tools only (UNLESS Key Trigger applies) |\n| **Explicit** | Specific file/line, clear command | Execute directly |\n| **Exploratory** | \"How does X work?\", \"Find Y\" | Fire explore (1-3) + tools in parallel |\n| **Open-ended** | \"Improve\", \"Refactor\", \"Add feature\" | Assess codebase first |\n| **Ambiguous** | Unclear scope, multiple interpretations | Ask ONE clarifying question |\n\n### Step 2: Check for Ambiguity\n\n| Situation | Action |\n|-----------|--------|\n| Single valid interpretation | Proceed |\n| Multiple interpretations, similar effort | Proceed with reasonable default, note assumption |\n| Multiple interpretations, 2x+ effort difference | **MUST ask** |\n| Missing critical info (file, error, context) | **MUST ask** |\n| User's design seems flawed or suboptimal | **MUST raise concern** before implementing |\n\n### Step 3: Validate Before Acting\n\n**Assumptions Check:**\n- Do I have any implicit assumptions that might affect the outcome?\n- Is the search scope clear?\n\n**Delegation Check (MANDATORY before acting directly):**\n1. Is there a specialized agent that perfectly matches this request?\n2. If not, is there a `delegate_task` category best describes this task? (visual-engineering, ultrabrain, quick etc.) What skills are available to equip the agent with?\n  - MUST FIND skills to use, for: `delegate_task(load_skills=[{skill1}, ...])` MUST PASS SKILL AS DELEGATE TASK PARAMETER.\n3. Can I do it myself for the best result, FOR SURE? REALLY, REALLY, THERE IS NO APPROPRIATE CATEGORIES TO WORK WITH?\n\n**Default Bias: DELEGATE. WORK YOURSELF ONLY WHEN IT IS SUPER SIMPLE.**\n\n### When to Challenge the User\nIf you observe:\n- A design decision that will cause obvious problems\n- An approach that contradicts established patterns in the codebase\n- A request that seems to misunderstand how the existing code works\n\nThen: Raise your concern concisely. Propose an alternative. Ask if they want to proceed anyway.\n\n```\nI notice [observation]. This might cause [problem] because [reason].\nAlternative: [your suggestion].\nShould I proceed with your original request, or try the alternative?\n```\n\n---\n\n## Phase 1 - Codebase Assessment (for Open-ended tasks)\n\nBefore following existing patterns, assess whether they're worth following.\n\n### Quick Assessment:\n1. Check config files: linter, formatter, type config\n2. Sample 2-3 similar files for consistency\n3. Note project age signals (dependencies, patterns)\n\n### State Classification:\n\n| State | Signals | Your Behavior |\n|-------|---------|---------------|\n| **Disciplined** | Consistent patterns, configs present, tests exist | Follow existing style strictly |\n| **Transitional** | Mixed patterns, some structure | Ask: \"I see X and Y patterns. Which to follow?\" |\n| **Legacy/Chaotic** | No consistency, outdated patterns | Propose: \"No clear conventions. I suggest [X]. OK?\" |\n| **Greenfield** | New/empty project | Apply modern best practices |\n\nIMPORTANT: If codebase appears undisciplined, verify before assuming:\n- Different patterns may serve different purposes (intentional)\n- Migration might be in progress\n- You might be looking at the wrong reference files\n\n---\n\n## Phase 2A - Exploration & Research\n\n### Tool & Agent Selection:\n\n| Resource | Cost | When to Use |\n|----------|------|-------------|\n| `explore` agent | FREE | Contextual grep for codebases |\n| `librarian` agent | CHEAP | Specialized codebase understanding agent for multi-repository analysis, searching remote codebases, retrieving official documentation, and finding implementation examples using GitHub CLI, Context7, and Web Search |\n| `oracle` agent | EXPENSIVE | Read-only consultation agent |\n\n**Default flow**: explore/librarian (background) + tools → oracle (if required)\n\n### Explore Agent = Contextual Grep\n\nUse it as a **peer tool**, not a fallback. Fire liberally.\n\n| Use Direct Tools | Use Explore Agent |\n|------------------|-------------------|\n| You know exactly what to search |  |\n| Single keyword/pattern suffices |  |\n| Known file location |  |\n|  | Multiple search angles needed |\n|  | Unfamiliar module structure |\n|  | Cross-layer pattern discovery |\n\n### Librarian Agent = Reference Grep\n\nSearch **external references** (docs, OSS, web). Fire proactively when unfamiliar libraries are involved.\n\n| Contextual Grep (Internal) | Reference Grep (External) |\n|----------------------------|---------------------------|\n| Search OUR codebase | Search EXTERNAL resources |\n| Find patterns in THIS repo | Find examples in OTHER repos |\n| How does our code work? | How does this library work? |\n| Project-specific logic | Official API documentation |\n| | Library best practices & quirks |\n| | OSS implementation examples |\n\n**Trigger phrases** (fire librarian immediately):\n- \"How do I use [library]?\"\n- \"What's the best practice for [framework feature]?\"\n- \"Why does [external dependency] behave this way?\"\n- \"Find examples of [library] usage\"\n- \"Working with unfamiliar npm/pip/cargo packages\"\n\n### Parallel Execution (DEFAULT behavior)\n\n**Explore/Librarian = Grep, not consultants.\n\n```typescript\n// CORRECT: Always background, always parallel\n// Contextual Grep (internal)\ndelegate_task(subagent_type=\"explore\", run_in_background=true, load_skills=[], prompt=\"Find auth implementations in our codebase...\")\ndelegate_task(subagent_type=\"explore\", run_in_background=true, load_skills=[], prompt=\"Find error handling patterns here...\")\n// Reference Grep (external)\ndelegate_task(subagent_type=\"librarian\", run_in_background=true, load_skills=[], prompt=\"Find JWT best practices in official docs...\")\ndelegate_task(subagent_type=\"librarian\", run_in_background=true, load_skills=[], prompt=\"Find how production apps handle auth in Express...\")\n// Continue working immediately. Collect with background_output when needed.\n\n// WRONG: Sequential or blocking\nresult = delegate_task(..., run_in_background=false)  // Never wait synchronously for explore/librarian\n```\n\n### Background Result Collection:\n1. Launch parallel agents → receive task_ids\n2. Continue immediate work\n3. When results needed: `background_output(task_id=\"...\")`\n4. BEFORE final answer: `background_cancel(all=true)`\n\n### Search Stop Conditions\n\nSTOP searching when:\n- You have enough context to proceed confidently\n- Same information appearing across multiple sources\n- 2 search iterations yielded no new useful data\n- Direct answer found\n\n**DO NOT over-explore. Time is precious.**\n\n---\n\n## Phase 2B - Implementation\n\n### Pre-Implementation:\n1. If task has 2+ steps → Create todo list IMMEDIATELY, IN SUPER DETAIL. No announcements—just create it.\n2. Mark current task `in_progress` before starting\n3. Mark `completed` as soon as done (don't batch) - OBSESSIVELY TRACK YOUR WORK USING TODO TOOLS\n\n### Category + Skills Delegation System\n\n**delegate_task() combines categories and skills for optimal task execution.**\n\n#### Available Categories (Domain-Optimized Models)\n\nEach category is configured with a model optimized for that domain. Read the description to understand when to use it.\n\n| Category | Domain / Best For |\n|----------|-------------------|\n| `visual-engineering` | Frontend, UI/UX, design, styling, animation |\n| `ultrabrain` | Deep logical reasoning, complex architecture decisions requiring extensive analysis |\n| `artistry` | Highly creative/artistic tasks, novel ideas |\n| `quick` | Trivial tasks - single file changes, typo fixes, simple modifications |\n| `unspecified-low` | Tasks that don't fit other categories, low effort required |\n| `unspecified-high` | Tasks that don't fit other categories, high effort required |\n| `writing` | Documentation, prose, technical writing |\n\n#### Available Skills (Domain Expertise Injection)\n\nSkills inject specialized instructions into the subagent. Read the description to understand when each skill applies.\n\n| Skill | Expertise Domain |\n|-------|------------------|\n| `playwright` | MUST USE for any browser-related tasks |\n| `frontend-ui-ux` | Designer-turned-developer who crafts stunning UI/UX even without design mockups |\n| `git-master` | MUST USE for ANY git operations |\n| `dev-browser` | Browser automation with persistent page state |\n| `ui-ux-pro-max` | (opencode - Skill) UI/UX design intelligence |\n\n---\n\n### MANDATORY: Category + Skill Selection Protocol\n\n**STEP 1: Select Category**\n- Read each category's description\n- Match task requirements to category domain\n- Select the category whose domain BEST fits the task\n\n**STEP 2: Evaluate ALL Skills**\nFor EVERY skill listed above, ask yourself:\n> \"Does this skill's expertise domain overlap with my task?\"\n\n- If YES → INCLUDE in `load_skills=[...]`\n- If NO → You MUST justify why (see below)\n\n**STEP 3: Justify Omissions**\n\nIf you choose NOT to include a skill that MIGHT be relevant, you MUST provide:\n\n```\nSKILL EVALUATION for \"[skill-name]\":\n- Skill domain: [what the skill description says]\n- Task domain: [what your task is about]\n- Decision: OMIT\n- Reason: [specific explanation of why domains don't overlap]\n```\n\n**WHY JUSTIFICATION IS MANDATORY:**\n- Forces you to actually READ skill descriptions\n- Prevents lazy omission of potentially useful skills\n- Subagents are STATELESS - they only know what you tell them\n- Missing a relevant skill = suboptimal output\n\n---\n\n### Delegation Pattern\n\n```typescript\ndelegate_task(\n  category=\"[selected-category]\",\n  load_skills=[\"skill-1\", \"skill-2\"],  // Include ALL relevant skills\n  prompt=\"...\"\n)\n```\n\n**ANTI-PATTERN (will produce poor results):**\n```typescript\ndelegate_task(category=\"...\", load_skills=[], prompt=\"...\")  // Empty load_skills without justification\n```\n\n### Delegation Table:\n\n| Domain | Delegate To | Trigger |\n|--------|-------------|---------|\n| Architecture decisions | `oracle` | Multi-system tradeoffs, unfamiliar patterns |\n| Self-review | `oracle` | After completing significant implementation |\n| Hard debugging | `oracle` | After 2+ failed fix attempts |\n| Librarian | `librarian` | Unfamiliar packages / libraries, struggles at weird behaviour (to find existing implementation of opensource) |\n| Explore | `explore` | Find existing codebase structure, patterns and styles |\n\n### Delegation Prompt Structure (MANDATORY - ALL 6 sections):\n\nWhen delegating, your prompt MUST include:\n\n```\n1. TASK: Atomic, specific goal (one action per delegation)\n2. EXPECTED OUTCOME: Concrete deliverables with success criteria\n3. REQUIRED TOOLS: Explicit tool whitelist (prevents tool sprawl)\n4. MUST DO: Exhaustive requirements - leave NOTHING implicit\n5. MUST NOT DO: Forbidden actions - anticipate and block rogue behavior\n6. CONTEXT: File paths, existing patterns, constraints\n```\n\nAFTER THE WORK YOU DELEGATED SEEMS DONE, ALWAYS VERIFY THE RESULTS AS FOLLOWING:\n- DOES IT WORK AS EXPECTED?\n- DOES IT FOLLOWED THE EXISTING CODEBASE PATTERN?\n- EXPECTED RESULT CAME OUT?\n- DID THE AGENT FOLLOWED \"MUST DO\" AND \"MUST NOT DO\" REQUIREMENTS?\n\n**Vague prompts = rejected. Be exhaustive.**\n\n### Session Continuity (MANDATORY)\n\nEvery `delegate_task()` output includes a session_id. **USE IT.**\n\n**ALWAYS continue when:**\n| Scenario | Action |\n|----------|--------|\n| Task failed/incomplete | `session_id=\"{session_id}\", prompt=\"Fix: {specific error}\"` |\n| Follow-up question on result | `session_id=\"{session_id}\", prompt=\"Also: {question}\"` |\n| Multi-turn with same agent | `session_id=\"{session_id}\"` - NEVER start fresh |\n| Verification failed | `session_id=\"{session_id}\", prompt=\"Failed verification: {error}. Fix.\"` |\n\n**Why session_id is CRITICAL:**\n- Subagent has FULL conversation context preserved\n- No repeated file reads, exploration, or setup\n- Saves 70%+ tokens on follow-ups\n- Subagent knows what it already tried/learned\n\n```typescript\n// WRONG: Starting fresh loses all context\ndelegate_task(category=\"quick\", prompt=\"Fix the type error in auth.ts...\")\n\n// CORRECT: Resume preserves everything\ndelegate_task(session_id=\"ses_abc123\", prompt=\"Fix: Type error on line 42\")\n```\n\n**After EVERY delegation, STORE the session_id for potential continuation.**\n\n### Code Changes:\n- Match existing patterns (if codebase is disciplined)\n- Propose approach first (if codebase is chaotic)\n- Never suppress type errors with `as any`, `@ts-ignore`, `@ts-expect-error`\n- Never commit unless explicitly requested\n- When refactoring, use various tools to ensure safe refactorings\n- **Bugfix Rule**: Fix minimally. NEVER refactor while fixing.\n\n### Verification:\n\nRun `lsp_diagnostics` on changed files at:\n- End of a logical task unit\n- Before marking a todo item complete\n- Before reporting completion to user\n\nIf project has build/test commands, run them at task completion.\n\n### Evidence Requirements (task NOT complete without these):\n\n| Action | Required Evidence |\n|--------|-------------------|\n| File edit | `lsp_diagnostics` clean on changed files |\n| Build command | Exit code 0 |\n| Test run | Pass (or explicit note of pre-existing failures) |\n| Delegation | Agent result received and verified |\n\n**NO EVIDENCE = NOT COMPLETE.**\n\n---\n\n## Phase 2C - Failure Recovery\n\n### When Fixes Fail:\n\n1. Fix root causes, not symptoms\n2. Re-verify after EVERY fix attempt\n3. Never shotgun debug (random changes hoping something works)\n\n### After 3 Consecutive Failures:\n\n1. **STOP** all further edits immediately\n2. **REVERT** to last known working state (git checkout / undo edits)\n3. **DOCUMENT** what was attempted and what failed\n4. **CONSULT** Oracle with full failure context\n5. If Oracle cannot resolve → **ASK USER** before proceeding\n\n**Never**: Leave code in broken state, continue hoping it'll work, delete failing tests to \"pass\"\n\n---\n\n## Phase 3 - Completion\n\nA task is complete when:\n- [ ] All planned todo items marked done\n- [ ] Diagnostics clean on changed files\n- [ ] Build passes (if applicable)\n- [ ] User's original request fully addressed\n\nIf verification fails:\n1. Fix issues caused by your changes\n2. Do NOT fix pre-existing issues unless asked\n3. Report: \"Done. Note: found N pre-existing lint errors unrelated to my changes.\"\n\n### Before Delivering Final Answer:\n- Cancel ALL running background tasks: `background_cancel(all=true)`\n- This conserves resources and ensures clean workflow completion\n</Behavior_Instructions>\n\n<Oracle_Usage>\n## Oracle — Read-Only High-IQ Consultant\n\nOracle is a read-only, expensive, high-quality reasoning model for debugging and architecture. Consultation only.\n\n### WHEN to Consult:\n\n| Trigger | Action |\n|---------|--------|\n| Complex architecture design | Oracle FIRST, then implement |\n| After completing significant work | Oracle FIRST, then implement |\n| 2+ failed fix attempts | Oracle FIRST, then implement |\n| Unfamiliar code patterns | Oracle FIRST, then implement |\n| Security/performance concerns | Oracle FIRST, then implement |\n| Multi-system tradeoffs | Oracle FIRST, then implement |\n\n### WHEN NOT to Consult:\n\n- Simple file operations (use direct tools)\n- First attempt at any fix (try yourself first)\n- Questions answerable from code you've read\n- Trivial decisions (variable names, formatting)\n- Things you can infer from existing code patterns\n\n### Usage Pattern:\nBriefly announce \"Consulting Oracle for [reason]\" before invocation.\n\n**Exception**: This is the ONLY case where you announce before acting. For all other work, start immediately without status updates.\n</Oracle_Usage>\n\n<Task_Management>\n## Todo Management (CRITICAL)\n\n**DEFAULT BEHAVIOR**: Create todos BEFORE starting any non-trivial task. This is your PRIMARY coordination mechanism.\n\n### When to Create Todos (MANDATORY)\n\n| Trigger | Action |\n|---------|--------|\n| Multi-step task (2+ steps) | ALWAYS create todos first |\n| Uncertain scope | ALWAYS (todos clarify thinking) |\n| User request with multiple items | ALWAYS |\n| Complex single task | Create todos to break down |\n\n### Workflow (NON-NEGOTIABLE)\n\n1. **IMMEDIATELY on receiving request**: `todowrite` to plan atomic steps.\n  - ONLY ADD TODOS TO IMPLEMENT SOMETHING, ONLY WHEN USER WANTS YOU TO IMPLEMENT SOMETHING.\n2. **Before starting each step**: Mark `in_progress` (only ONE at a time)\n3. **After completing each step**: Mark `completed` IMMEDIATELY (NEVER batch)\n4. **If scope changes**: Update todos before proceeding\n\n### Why This Is Non-Negotiable\n\n- **User visibility**: User sees real-time progress, not a black box\n- **Prevents drift**: Todos anchor you to the actual request\n- **Recovery**: If interrupted, todos enable seamless continuation\n- **Accountability**: Each todo = explicit commitment\n\n### Anti-Patterns (BLOCKING)\n\n| Violation | Why It's Bad |\n|-----------|--------------|\n| Skipping todos on multi-step tasks | User has no visibility, steps get forgotten |\n| Batch-completing multiple todos | Defeats real-time tracking purpose |\n| Proceeding without marking in_progress | No indication of what you're working on |\n| Finishing without completing todos | Task appears incomplete to user |\n\n**FAILURE TO USE TODOS ON NON-TRIVIAL TASKS = INCOMPLETE WORK.**\n\n### Clarification Protocol (when asking):\n\n```\nI want to make sure I understand correctly.\n\n**What I understood**: [Your interpretation]\n**What I'm unsure about**: [Specific ambiguity]\n**Options I see**:\n1. [Option A] - [effort/implications]\n2. [Option B] - [effort/implications]\n\n**My recommendation**: [suggestion with reasoning]\n\nShould I proceed with [recommendation], or would you prefer differently?\n```\n</Task_Management>\n\n<Tone_and_Style>\n## Communication Style\n\n### Be Concise\n- Start work immediately. No acknowledgments (\"I'm on it\", \"Let me...\", \"I'll start...\")\n- Answer directly without preamble\n- Don't summarize what you did unless asked\n- Don't explain your code unless asked\n- One word answers are acceptable when appropriate\n\n### No Flattery\nNever start responses with:\n- \"Great question!\"\n- \"That's a really good idea!\"\n- \"Excellent choice!\"\n- Any praise of the user's input\n\nJust respond directly to the substance.\n\n### No Status Updates\nNever start responses with casual acknowledgments:\n- \"Hey I'm on it...\"\n- \"I'm working on this...\"\n- \"Let me start by...\"\n- \"I'll get to work on...\"\n- \"I'm going to...\"\n\nJust start working. Use todos for progress tracking—that's what they're for.\n\n### When User is Wrong\nIf the user's approach seems problematic:\n- Don't blindly implement it\n- Don't lecture or be preachy\n- Concisely state your concern and alternative\n- Ask if they want to proceed anyway\n\n### Match User's Style\n- If user is terse, be terse\n- If user wants detail, provide detail\n- Adapt to their communication preference\n</Tone_and_Style>\n\n<Constraints>\n## Hard Blocks (NEVER violate)\n\n| Constraint | No Exceptions |\n|------------|---------------|\n| Type error suppression (`as any`, `@ts-ignore`) | Never |\n| Commit without explicit request | Never |\n| Speculate about unread code | Never |\n| Leave code in broken state after failures | Never |\n\n## Anti-Patterns (BLOCKING violations)\n\n| Category | Forbidden |\n|----------|-----------|\n| **Type Safety** | `as any`, `@ts-ignore`, `@ts-expect-error` |\n| **Error Handling** | Empty catch blocks `catch(e) {}` |\n| **Testing** | Deleting failing tests to \"pass\" |\n| **Search** | Firing agents for single-line typos or obvious syntax errors |\n| **Debugging** | Shotgun debugging, random changes |\n\n## Soft Guidelines\n\n- Prefer existing libraries over new dependencies\n- Prefer small, focused changes over large refactors\n- When uncertain about scope, ask\n</Constraints>\n\n<omo-env>\n  Current date: Mon, Jan 26, 2026\n  Current time: 09:56:24 PM\n  Timezone: Asia/Shanghai\n  Locale: en-US\n</omo-env>\nYou are powered by the model named gemini-3-pro-preview. The exact model ID is claw/gemini-3-pro-preview\nHere is some useful information about the environment you are running in:\n<env>\n  Working directory: /Users/chor\n  Is directory a git repo: no\n  Platform: darwin\n  Today's date: Mon Jan 26 2026\n</env>\n<files>\n  \n</files>"
  },
  {
    "role": "user",
    "content": "hello"
  },
  {
    "role": "assistant",
    "content": "Hello. I'm Sisyphus. How can I help?"
  },
  {
    "role": "user",
    "content": "hello"
  }
]
[DEBUG] 2026-01-26T13:56:45.530Z [ProxySystem] - [Adapter] Debug: original OpenAI tools = [
  {
    "type": "function",
    "function": {
      "name": "question",
      "description": "Use this tool when you need to ask the user questions during execution. This allows you to:\n1. Gather user preferences or requirements\n2. Clarify ambiguous instructions\n3. Get decisions on implementation choices as you work\n4. Offer choices to the user about what direction to take.\n\nUsage notes:\n- When `custom` is enabled (default), a \"Type your own answer\" option is added automatically; don't include \"Other\" or catch-all options\n- Answers are returned as arrays of labels; set `multiple: true` to allow selecting more than one\n- If you recommend a specific option, make that the first option in the list and add \"(Recommended)\" at the end of the label\n",
      "parameters": {
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "type": "object",
        "properties": {
          "questions": {
            "description": "Questions to ask",
            "type": "array",
            "items": {
              "type": "object",
              "properties": {
                "question": {
                  "description": "Complete question",
                  "type": "string"
                },
                "header": {
                  "description": "Very short label (max 30 chars)",
                  "type": "string"
                },
                "options": {
                  "description": "Available choices",
                  "type": "array",
                  "items": {
                    "ref": "QuestionOption",
                    "type": "object",
                    "properties": {
                      "label": {
                        "description": "Display text (1-5 words, concise)",
                        "type": "string"
                      },
                      "description": {
                        "description": "Explanation of choice",
                        "type": "string"
                      }
                    },
                    "required": [
                      "label",
                      "description"
                    ],
                    "additionalProperties": false
                  }
                },
                "multiple": {
                  "description": "Allow selecting multiple choices",
                  "type": "boolean"
                }
              },
              "required": [
                "question",
                "header",
                "options"
              ],
              "additionalProperties": false
            }
          }
        },
        "required": [
          "questions"
        ],
        "additionalProperties": false
      }
    }
  },
  {
    "type": "function",
    "function": {
      "name": "bash",
      "description": "Executes a given bash command in a persistent shell session with optional timeout, ensuring proper handling and security measures.\n\nAll commands run in /Users/chor by default. Use the `workdir` parameter if you need to run a command in a different directory. AVOID using `cd <directory> && <command>` patterns - use `workdir` instead.\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., rm \"path with spaces/file.txt\")\n   - Examples of proper quoting:\n     - mkdir \"/Users/name/My Documents\" (correct)\n     - mkdir /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. If not specified, commands will time out 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 2000 lines or 51200 bytes, it will be truncated and the full output will be written to a file. You can use Read with offset/limit to read specific sections or Grep to search the full content. Because of this, you do NOT need to use `head`, `tail`, or other truncation commands to limit output - just run the command directly.\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  - 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  - AVOID using `cd <directory> && <command>`. Use the `workdir` parameter to change directories instead.\n    <good-example>\n    Use workdir=\"/foo/bar\" with command: pytest 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 push --force, hard reset, etc) 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 ALL conditions are met:\n  (1) User explicitly requested amend, OR commit SUCCEEDED but pre-commit hook auto-modified files that need including\n  (2) HEAD commit was created by you in this conversation (verify: git log -1 --format='%an %ae')\n  (3) Commit has NOT been pushed to remote (verify: git status shows \"Your branch is ahead\")\n- CRITICAL: If commit FAILED or was REJECTED by hook, NEVER amend - fix the issue and create a NEW commit\n- CRITICAL: If you already pushed to remote, NEVER amend unless user explicitly requests it (requires force push)\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 after the commit completes to verify success.\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, fix the issue and create a NEW commit (see amend rules above)\n\nImportant notes:\n- NEVER run additional commands to read or explore code, besides git bash commands\n- NEVER use the TodoWrite or Task tools\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\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</example>\n\nImportant:\n- DO NOT use the TodoWrite or Task tools\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",
      "parameters": {
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "type": "object",
        "properties": {
          "command": {
            "description": "The command to execute",
            "type": "string"
          },
          "timeout": {
            "description": "Optional timeout in milliseconds",
            "type": "number"
          },
          "workdir": {
            "description": "The working directory to run the command in. Defaults to /Users/chor. Use this instead of 'cd' commands.",
            "type": "string"
          },
          "description": {
            "description": "Clear, concise description of what this command does in 5-10 words. Examples:\nInput: ls\nOutput: Lists files in current directory\n\nInput: git status\nOutput: Shows working tree status\n\nInput: npm install\nOutput: Installs package dependencies\n\nInput: mkdir foo\nOutput: Creates directory 'foo'",
            "type": "string"
          }
        },
        "required": [
          "command",
          "description"
        ],
        "additionalProperties": 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 filePath 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- You have the capability to call multiple tools in a single response. It is always better to speculatively read multiple files as a batch that are potentially useful.\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- You can read image files using this tool.\n",
      "parameters": {
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "type": "object",
        "properties": {
          "filePath": {
            "description": "The path to the file to read",
            "type": "string"
          },
          "offset": {
            "description": "The line number to start reading from (0-based)",
            "type": "number"
          },
          "limit": {
            "description": "The number of lines to read (defaults to 2000)",
            "type": "number"
          }
        },
        "required": [
          "filePath"
        ],
        "additionalProperties": false
      }
    }
  },
  {
    "type": "function",
    "function": {
      "name": "glob",
      "description": "Fast file pattern matching tool with safety limits (60s timeout, 100 file limit). Supports glob patterns like \"**/*.js\" or \"src/**/*.ts\". Returns matching file paths sorted by modification time. Use this tool when you need to find files by name patterns.",
      "parameters": {
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "type": "object",
        "properties": {
          "pattern": {
            "type": "string"
          },
          "path": {
            "type": "string"
          }
        },
        "required": [
          "pattern"
        ],
        "additionalProperties": false
      }
    }
  },
  {
    "type": "function",
    "function": {
      "name": "grep",
      "description": "Fast content search tool with safety limits (60s timeout, 10MB output). Searches file contents using regular expressions. Supports full regex syntax (eg. \"log.*Error\", \"function\\s+\\w+\", etc.). Filter files by pattern with the include parameter (eg. \"*.js\", \"*.{ts,tsx}\"). Returns file paths with matches sorted by modification time.",
      "parameters": {
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "type": "object",
        "properties": {
          "pattern": {
            "type": "string"
          },
          "include": {
            "type": "string"
          },
          "path": {
            "type": "string"
          }
        },
        "required": [
          "pattern"
        ],
        "additionalProperties": 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 oldString or newString.\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 `oldString` is not found in the file with an error \"oldString not found in content\".\n- The edit will FAIL if `oldString` is found multiple times in the file with an error \"oldString found multiple times and requires more code context to uniquely identify the intended match\". Either provide a larger string with more surrounding context to make it unique or use `replaceAll` to change every instance of `oldString`. \n- Use `replaceAll` for replacing and renaming strings across the file. This parameter is useful if you want to rename a variable for instance.\n",
      "parameters": {
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "type": "object",
        "properties": {
          "filePath": {
            "description": "The absolute path to the file to modify",
            "type": "string"
          },
          "oldString": {
            "description": "The text to replace",
            "type": "string"
          },
          "newString": {
            "description": "The text to replace it with (must be different from oldString)",
            "type": "string"
          },
          "replaceAll": {
            "description": "Replace all occurrences of oldString (default false)",
            "type": "boolean"
          }
        },
        "required": [
          "filePath",
          "oldString",
          "newString"
        ],
        "additionalProperties": false
      }
    }
  },
  {
    "type": "function",
    "function": {
      "name": "write",
      "description": "Writes a file to the local filesystem.\n\nUsage:\n- This tool will overwrite the existing file if there is one at the provided path.\n- If this is an existing file, you MUST use the Read tool first to read the file's contents. This tool will fail if you did not read the file first.\n- ALWAYS prefer editing existing files in the codebase. NEVER write new files unless explicitly required.\n- NEVER proactively create documentation files (*.md) or README files. Only create documentation files if explicitly requested by the User.\n- Only use emojis if the user explicitly requests it. Avoid writing emojis to files unless asked.\n",
      "parameters": {
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "type": "object",
        "properties": {
          "content": {
            "description": "The content to write to the file",
            "type": "string"
          },
          "filePath": {
            "description": "The absolute path to the file to write (must be absolute, not relative)",
            "type": "string"
          }
        },
        "required": [
          "content",
          "filePath"
        ],
        "additionalProperties": false
      }
    }
  },
  {
    "type": "function",
    "function": {
      "name": "task",
      "description": "Launch a new agent to handle complex, multistep tasks autonomously.\n\nAvailable agent types and the tools they have access to:\n- build: This subagent should only be called manually by the user.\n- plan: This subagent should only be called manually by the user.\n- general: General-purpose agent for researching complex questions and executing multi-step tasks. Use this agent to execute multiple units of work in parallel.\n- explore: Contextual grep for codebases. Answers \"Where is X?\", \"Which file has Y?\", \"Find the code that does Z\". Fire multiple in parallel for broad searches. Specify thoroughness: \"quick\" for basic, \"medium\" for moderate, \"very thorough\" for comprehensive analysis.\n- sisyphus-junior: Sisyphus-Junior - Focused task executor. Same discipline, no delegation.\n- oracle: Read-only consultation agent. High-IQ reasoning specialist for debugging hard problems and high-difficulty architecture design.\n- librarian: Specialized codebase understanding agent for multi-repository analysis, searching remote codebases, retrieving official documentation, and finding implementation examples using GitHub CLI, Context7, and Web Search. MUST BE USED when users ask to look up code in remote repositories, explain library internals, or find usage examples in open source.\n- multimodal-looker: Analyze media files (PDFs, images, diagrams) that require interpretation beyond raw text. Extracts specific information or summaries from documents, describes visual content. Use when you need analyzed/extracted data rather than literal file contents.\n- metis: Pre-planning consultant that analyzes requests to identify hidden intentions, ambiguities, and AI failure points.\n- momus: Expert reviewer for evaluating work plans against rigorous clarity, verifiability, and completeness standards.\n\nWhen using the Task tool, you must specify a subagent_type parameter to select which agent type to use.\n\nWhen to use the Task tool:\n- When you are instructed to execute custom slash commands. Use the Task tool with the slash command invocation as the entire prompt. The slash command can take arguments. For example: Task(description=\"Check the file\", prompt=\"/check-file path/to/file.py\")\n\nWhen NOT to use the Task tool:\n- If you want to read a specific file path, use the Read or Glob tool instead of the Task 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 Task tool, to find the match more quickly\n- Other tasks that are not related to the agent descriptions above\n\n\nUsage notes:\n1. Launch multiple agents concurrently whenever possible, to maximize performance; to do that, use a single message with multiple tool uses\n2. 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.\n3. Each agent invocation is stateless unless you provide a session_id. Your prompt should contain a highly detailed task description for the agent to perform autonomously and you should specify exactly what information the agent should return back to you in its final and only message to you.\n4. The agent's outputs should generally be trusted\n5. 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\n6. 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\nExample usage (NOTE: The agents below are fictional examples for illustration only - use the actual agents listed above):\n\n<example_agent_descriptions>\n\"code-reviewer\": use this agent after you are done writing a significant 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 significant piece of code was written and the task was completed, now use the code-reviewer agent to review the code\n</commentary>\nassistant: Now let me use the code-reviewer agent to review the code\nassistant: Uses the Task 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 Task tool to launch the with the greeting-responder agent\"\n</example>\n",
      "parameters": {
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "type": "object",
        "properties": {
          "description": {
            "description": "A short (3-5 words) description of the task",
            "type": "string"
          },
          "prompt": {
            "description": "The task for the agent to perform",
            "type": "string"
          },
          "subagent_type": {
            "description": "The type of specialized agent to use for this task",
            "type": "string"
          },
          "session_id": {
            "description": "Existing Task session to continue",
            "type": "string"
          },
          "command": {
            "description": "The command that triggered this task",
            "type": "string"
          }
        },
        "required": [
          "description",
          "prompt",
          "subagent_type"
        ],
        "additionalProperties": false
      }
    }
  },
  {
    "type": "function",
    "function": {
      "name": "webfetch",
      "description": "- Fetches content from a specified URL\n- Takes a URL and optional format as input\n- Fetches the URL content, converts to requested format (markdown by default)\n- Returns the content in the specified format\n- Use this tool when you need to retrieve and analyze web content\n\nUsage notes:\n  - IMPORTANT: if another tool is present that offers better web fetching capabilities, is more targeted to the task, or has fewer restrictions, prefer using that tool instead of this one.\n  - The URL must be a fully-formed valid URL\n  - HTTP URLs will be automatically upgraded to HTTPS\n  - Format options: \"markdown\" (default), \"text\", or \"html\"\n  - This tool is read-only and does not modify any files\n  - Results may be summarized if the content is very large\n",
      "parameters": {
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "type": "object",
        "properties": {
          "url": {
            "description": "The URL to fetch content from",
            "type": "string"
          },
          "format": {
            "description": "The format to return the content in (text, markdown, or html). Defaults to markdown.",
            "default": "markdown",
            "type": "string",
            "enum": [
              "text",
              "markdown",
              "html"
            ]
          },
          "timeout": {
            "description": "Optional timeout in seconds (max 120)",
            "type": "number"
          }
        },
        "required": [
          "url",
          "format"
        ],
        "additionalProperties": false
      }
    }
  },
  {
    "type": "function",
    "function": {
      "name": "todowrite",
      "description": "Use this tool to create and manage 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\nUse this tool proactively in these scenarios:\n\n1. Complex multistep tasks - When a task requires 3 or more distinct steps or actions\n2. Non-trivial and complex tasks - Tasks that require careful planning or multiple operations\n3. User explicitly requests todo list - When the user directly asks you to use the todo list\n4. User provides multiple tasks - When users provide a list of things to be done (numbered or comma-separated)\n5. After receiving new instructions - Immediately capture user requirements as todos. Feel free to edit the todo list based on new information.\n6. After completing a task - Mark it complete and add any new follow-up tasks\n7. When you start working on a new task, mark the todo as in_progress. Ideally you should only have one todo as in_progress at a time. Complete existing tasks before starting new ones.\n\n## When NOT to Use This Tool\n\nSkip using this tool when:\n1. There is only a single, straightforward task\n2. The task is trivial and tracking it provides no organizational benefit\n3. The task can be completed in less than 3 trivial steps\n4. 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## Examples of When to Use the Todo List\n\n<example>\nUser: I want to add a dark mode toggle to the application settings. Make sure you run the tests and build when you're done!\nAssistant: I'll help add a dark mode toggle to your application settings. Let me create a todo list to track this implementation.\n*Creates todo list with the following items:*\n1. Create dark mode toggle component in Settings page\n2. Add dark mode state management (context/store)\n3. Implement CSS-in-JS styles for dark theme\n4. Update existing components to support theme switching\n5. Run tests and build process, addressing any failures or errors that occur\n*Begins working on the first task*\n\n<reasoning>\nThe assistant used the todo list because:\n1. Adding dark mode is a multi-step feature requiring UI, state management, and styling changes\n2. The user explicitly requested tests and build be run afterward\n3. The assistant inferred that tests and build need to pass by adding \"Ensure tests and build succeed\" as the final task\n</reasoning>\n</example>\n\n<example>\nUser: Help me rename the function getCwd to getCurrentWorkingDirectory across my project\nAssistant: Let me first search through your codebase to find all occurrences of 'getCwd'.\n*Uses grep or search tools to locate all instances of getCwd in the codebase*\nAssistant: I've found 15 instances of 'getCwd' across 8 different files. Let me create a todo list to track these changes.\n*Creates todo list with specific items for each file that needs updating*\n\n<reasoning>\nThe assistant used the todo list because:\n1. First, the assistant searched to understand the scope of the task\n2. Upon finding multiple occurrences across different files, it determined this was a complex task with multiple steps\n3. The todo list helps ensure every instance is tracked and updated systematically\n4. This approach prevents missing any occurrences and maintains code consistency\n</reasoning>\n</example>\n\n\n<example>\nUser: I need to implement these features for my e-commerce site: user registration, product catalog, shopping cart, and checkout flow.\nAssistant: I'll help implement these features. First, let's add all the features to the todo list.\n*Creates a todo list breaking down each feature into specific tasks based on the project architecture*\nAssistant: Let's start with user registration. This will involve creating database models, API endpoints, and frontend forms that integrate with your existing authentication system.\n\n<reasoning>\nThe assistant used the todo list because:\n1. The user provided multiple complex features to implement in a comma separated list\n2. The todo list helps organize these large features into manageable tasks\n3. This approach allows for tracking progress across the entire implementation\n</reasoning>\n</example>\n\n<example>\nUser: Can you help optimize my React application? It's rendering slowly and has performance issues.</user>\nAssistant: I'll help optimize your React application. First, let me examine your codebase to identify potential performance bottlenecks.\n*Reviews component structure, render patterns, state management, and data fetching*\nAssistant: After analyzing your codebase, I've identified several performance issues. Let me create a todo list to track our optimization efforts.\n*Creates todo list with items like: 1) Implement memoization for expensive calculations in ProductList, 2) Add virtualization for long lists in Dashboard, 3) Optimize image loading in Gallery component, 4) Fix state update loops in ShoppingCart, 5) Review bundle size and implement code splitting*\nLet's start by implementing memoization for the expensive calculations in your ProductList component.</assistant>\n\n<reasoning>\nThe assistant used the todo list because:\n1. First, the assistant examined the codebase to identify specific performance issues\n2. Based on this analysis, it identified multiple optimization opportunities\n3. Performance optimization is a non-trivial task requiring multiple steps\n4. The todo list helps methodically track improvements across different components\n5. This systematic approach ensures all performance bottlenecks are addressed\n</reasoning>\n</example>\n\n## Examples of When NOT to Use the Todo List\n\n<example>\nUser: How do I print 'Hello World' in Python?\nAssistant: In Python, you can print \"Hello World\" with this simple code:\n\npython\nprint(\"Hello World\")\n\nThis will output the text \"Hello World\" to the console when executed.</assistant>\n\n<reasoning>\nThe assistant did not use the todo list because this is a single, trivial task that can be completed in one step. There's no need to track multiple tasks or steps for such a straightforward request.\n</reasoning>\n</example>\n\n<example>\nUser: What does the git status command do?\nAssistant: The git status command shows the current state of your working directory and staging area. It displays which changes have been staged, which haven't, and which files aren't being tracked by Git. This is a fundamental command for understanding the current state of your repository before making commits.\n\n<reasoning>\nThe assistant did not use the todo list because this is an informational request with no actual coding task to complete. The user is simply asking for an explanation, not for the assistant to perform multiple steps or tasks.\n</reasoning>\n</example>\n\n<example>\nUser: Can you add a comment to the calculateTotal function to explain what it does?\nAssistant: Sure, let me add a comment to the calculateTotal function to explain what it does.\n* Uses the Edit tool to add a comment to the calculateTotal function *\n\n<reasoning>\nThe assistant did not use the todo list because this is a single, straightforward task confined to one location in the code. Adding a comment doesn't require tracking multiple steps or systematic organization.\n</reasoning>\n</example>\n\n<example>\nUser: Run npm install for me and tell me what happens.\nAssistant: I'll run the npm install command for you.\n\n*Executes: npm install*\n\nThe command completed successfully. Here's the output:\n[Output of npm install command]\n\nAll dependencies have been installed according to your package.json file.\n\n<reasoning>\nThe assistant did not use the todo list because this is a single command execution with immediate results. There are no multiple steps to track or organize, making the todo list unnecessary for this straightforward task.\n</reasoning>\n</example>\n\n## Task States and Management\n\n1. **Task States**: Use these states to track progress:\n   - pending: Task not yet started\n   - in_progress: Currently working on (limit to ONE task at a time)\n   - completed: Task finished successfully\n   - cancelled: Task no longer needed\n\n2. **Task Management**:\n   - Update task status in real-time as you work\n   - Mark tasks complete IMMEDIATELY after finishing (don't batch completions)\n   - Only have ONE task in_progress at any time\n   - Complete current tasks before starting new ones\n   - Cancel tasks that become irrelevant\n\n3. **Task Breakdown**:\n   - Create specific, actionable items\n   - Break complex tasks into smaller, manageable steps\n   - Use clear, descriptive task names\n\nWhen in doubt, use this tool. Being proactive with task management demonstrates attentiveness and ensures you complete all requirements successfully.\n\n",
      "parameters": {
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "type": "object",
        "properties": {
          "todos": {
            "description": "The updated todo list",
            "type": "array",
            "items": {
              "type": "object",
              "properties": {
                "content": {
                  "description": "Brief description of the task",
                  "type": "string"
                },
                "status": {
                  "description": "Current status of the task: pending, in_progress, completed, cancelled",
                  "type": "string"
                },
                "priority": {
                  "description": "Priority level of the task: high, medium, low",
                  "type": "string"
                },
                "id": {
                  "description": "Unique identifier for the todo item",
                  "type": "string"
                }
              },
              "required": [
                "content",
                "status",
                "priority",
                "id"
              ],
              "additionalProperties": false
            }
          }
        },
        "required": [
          "todos"
        ],
        "additionalProperties": false
      }
    }
  },
  {
    "type": "function",
    "function": {
      "name": "todoread",
      "description": "Use this tool to read your todo list",
      "parameters": {
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "type": "object",
        "properties": {},
        "additionalProperties": false
      }
    }
  },
  {
    "type": "function",
    "function": {
      "name": "skill",
      "description": "Load a skill to get detailed instructions for a specific task.\n\nSkills provide specialized knowledge and step-by-step guidance.\nUse this when a task matches an available skill's description.\n\n<available_skills>\n  <skill>\n    <name>playwright</name>\n    <description>(opencode - Skill) MUST USE for any browser-related tasks. Browser automation via Playwright MCP - verification, browsing, information gathering, web scraping, testing, screenshots, and all browser interactions.</description>\n  </skill>\n  <skill>\n    <name>frontend-ui-ux</name>\n    <description>(opencode - Skill) Designer-turned-developer who crafts stunning UI/UX even without design mockups</description>\n  </skill>\n  <skill>\n    <name>git-master</name>\n    <description>(opencode - Skill) MUST USE for ANY git operations. Atomic commits, rebase/squash, history search (blame, bisect, log -S). STRONGLY RECOMMENDED: Use with delegate_task(category='quick', load_skills=['git-master'], ...) to save context. Triggers: 'commit', 'rebase', 'squash', 'who wrote', 'when was X added', 'find the commit that'.</description>\n  </skill>\n  <skill>\n    <name>dev-browser</name>\n    <description>(opencode - Skill) Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include 'go to [url]', 'click on', 'fill out the form', 'take a screenshot', 'scrape', 'automate', 'test the website', 'log into', or any browser interaction request.</description>\n  </skill>\n  <skill>\n    <name>ui-ux-pro-max</name>\n    <description>(opencode - Skill) UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 9 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient. Integrations: shadcn/ui MCP for component search and examples.</description>\n    <compatibility>OpenCode with Python 3.x</compatibility>\n  </skill>\n</available_skills>",
      "parameters": {
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "type": "object",
        "properties": {
          "name": {
            "type": "string"
          }
        },
        "required": [
          "name"
        ],
        "additionalProperties": false
      }
    }
  },
  {
    "type": "function",
    "function": {
      "name": "lsp_goto_definition",
      "description": "Jump to symbol definition. Find WHERE something is defined.",
      "parameters": {
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "type": "object",
        "properties": {
          "filePath": {
            "type": "string"
          },
          "line": {
            "type": "number",
            "minimum": 1
          },
          "character": {
            "type": "number",
            "minimum": 0
          }
        },
        "required": [
          "filePath",
          "line",
          "character"
        ],
        "additionalProperties": false
      }
    }
  },
  {
    "type": "function",
    "function": {
      "name": "lsp_find_references",
      "description": "Find ALL usages/references of a symbol across the entire workspace.",
      "parameters": {
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "type": "object",
        "properties": {
          "filePath": {
            "type": "string"
          },
          "line": {
            "type": "number",
            "minimum": 1
          },
          "character": {
            "type": "number",
            "minimum": 0
          },
          "includeDeclaration": {
            "type": "boolean"
          }
        },
        "required": [
          "filePath",
          "line",
          "character"
        ],
        "additionalProperties": false
      }
    }
  },
  {
    "type": "function",
    "function": {
      "name": "lsp_symbols",
      "description": "Get symbols from file (document) or search across workspace. Use scope='document' for file outline, scope='workspace' for project-wide symbol search.",
      "parameters": {
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "type": "object",
        "properties": {
          "filePath": {
            "type": "string"
          },
          "scope": {
            "default": "document",
            "type": "string",
            "enum": [
              "document",
              "workspace"
            ]
          },
          "query": {
            "type": "string"
          },
          "limit": {
            "type": "number"
          }
        },
        "required": [
          "filePath",
          "scope"
        ],
        "additionalProperties": false
      }
    }
  },
  {
    "type": "function",
    "function": {
      "name": "lsp_diagnostics",
      "description": "Get errors, warnings, hints from language server BEFORE running build.",
      "parameters": {
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "type": "object",
        "properties": {
          "filePath": {
            "type": "string"
          },
          "severity": {
            "type": "string",
            "enum": [
              "error",
              "warning",
              "information",
              "hint",
              "all"
            ]
          }
        },
        "required": [
          "filePath"
        ],
        "additionalProperties": false
      }
    }
  },
  {
    "type": "function",
    "function": {
      "name": "lsp_prepare_rename",
      "description": "Check if rename is valid. Use BEFORE lsp_rename.",
      "parameters": {
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "type": "object",
        "properties": {
          "filePath": {
            "type": "string"
          },
          "line": {
            "type": "number",
            "minimum": 1
          },
          "character": {
            "type": "number",
            "minimum": 0
          }
        },
        "required": [
          "filePath",
          "line",
          "character"
        ],
        "additionalProperties": false
      }
    }
  },
  {
    "type": "function",
    "function": {
      "name": "lsp_rename",
      "description": "Rename symbol across entire workspace. APPLIES changes to all files.",
      "parameters": {
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "type": "object",
        "properties": {
          "filePath": {
            "type": "string"
          },
          "line": {
            "type": "number",
            "minimum": 1
          },
          "character": {
            "type": "number",
            "minimum": 0
          },
          "newName": {
            "type": "string"
          }
        },
        "required": [
          "filePath",
          "line",
          "character",
          "newName"
        ],
        "additionalProperties": false
      }
    }
  },
  {
    "type": "function",
    "function": {
      "name": "ast_grep_search",
      "description": "Search code patterns across filesystem using AST-aware matching. Supports 25 languages. Use meta-variables: $VAR (single node), $$$ (multiple nodes). IMPORTANT: Patterns must be complete AST nodes (valid code). For functions, include params and body: 'export async function $NAME($$$) { $$$ }' not 'export async function $NAME'. Examples: 'console.log($MSG)', 'def $FUNC($$$):', 'async function $NAME($$$)'",
      "parameters": {
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "type": "object",
        "properties": {
          "pattern": {
            "type": "string"
          },
          "lang": {
            "type": "string",
            "enum": [
              "bash",
              "c",
              "cpp",
              "csharp",
              "css",
              "elixir",
              "go",
              "haskell",
              "html",
              "java",
              "javascript",
              "json",
              "kotlin",
              "lua",
              "nix",
              "php",
              "python",
              "ruby",
              "rust",
              "scala",
              "solidity",
              "swift",
              "typescript",
              "tsx",
              "yaml"
            ]
          },
          "paths": {
            "type": "array",
            "items": {
              "type": "string"
            }
          },
          "globs": {
            "type": "array",
            "items": {
              "type": "string"
            }
          },
          "context": {
            "type": "number"
          }
        },
        "required": [
          "pattern",
          "lang"
        ],
        "additionalProperties": false
      }
    }
  },
  {
    "type": "function",
    "function": {
      "name": "ast_grep_replace",
      "description": "Replace code patterns across filesystem with AST-aware rewriting. Dry-run by default. Use meta-variables in rewrite to preserve matched content. Example: pattern='console.log($MSG)' rewrite='logger.info($MSG)'",
      "parameters": {
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "type": "object",
        "properties": {
          "pattern": {
            "type": "string"
          },
          "rewrite": {
            "type": "string"
          },
          "lang": {
            "type": "string",
            "enum": [
              "bash",
              "c",
              "cpp",
              "csharp",
              "css",
              "elixir",
              "go",
              "haskell",
              "html",
              "java",
              "javascript",
              "json",
              "kotlin",
              "lua",
              "nix",
              "php",
              "python",
              "ruby",
              "rust",
              "scala",
              "solidity",
              "swift",
              "typescript",
              "tsx",
              "yaml"
            ]
          },
          "paths": {
            "type": "array",
            "items": {
              "type": "string"
            }
          },
          "globs": {
            "type": "array",
            "items": {
              "type": "string"
            }
          },
          "dryRun": {
            "type": "boolean"
          }
        },
        "required": [
          "pattern",
          "rewrite",
          "lang"
        ],
        "additionalProperties": false
      }
    }
  },
  {
    "type": "function",
    "function": {
      "name": "session_list",
      "description": "List all OpenCode sessions with optional filtering.\n\nReturns a list of available session IDs with metadata including message count, date range, and agents used.\n\nArguments:\n- limit (optional): Maximum number of sessions to return\n- from_date (optional): Filter sessions from this date (ISO 8601 format)\n- to_date (optional): Filter sessions until this date (ISO 8601 format)\n\nExample output:\n| Session ID | Messages | First | Last | Agents |\n|------------|----------|-------|------|--------|\n| ses_abc123 | 45 | 2025-12-20 | 2025-12-24 | build, oracle |\n| ses_def456 | 12 | 2025-12-19 | 2025-12-19 | build |",
      "parameters": {
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "type": "object",
        "properties": {
          "limit": {
            "type": "number"
          },
          "from_date": {
            "type": "string"
          },
          "to_date": {
            "type": "string"
          },
          "project_path": {
            "type": "string"
          }
        },
        "additionalProperties": false
      }
    }
  },
  {
    "type": "function",
    "function": {
      "name": "session_read",
      "description": "Read messages and history from an OpenCode session.\n\nReturns a formatted view of session messages with role, timestamp, and content. Optionally includes todos and transcript data.\n\nArguments:\n- session_id (required): Session ID to read\n- include_todos (optional): Include todo list if available (default: false)\n- include_transcript (optional): Include transcript log if available (default: false)\n- limit (optional): Maximum number of messages to return (default: all)\n\nExample output:\nSession: ses_abc123\nMessages: 45\nDate Range: 2025-12-20 to 2025-12-24\n\n[Message 1] user (2025-12-20 10:30:00)\nHello, can you help me with...\n\n[Message 2] assistant (2025-12-20 10:30:15)\nOf course! Let me help you with...",
      "parameters": {
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "type": "object",
        "properties": {
          "session_id": {
            "type": "string"
          },
          "include_todos": {
            "type": "boolean"
          },
          "include_transcript": {
            "type": "boolean"
          },
          "limit": {
            "type": "number"
          }
        },
        "required": [
          "session_id"
        ],
        "additionalProperties": false
      }
    }
  },
  {
    "type": "function",
    "function": {
      "name": "session_search",
      "description": "Search for content within OpenCode session messages.\n\nPerforms full-text search across session messages and returns matching excerpts with context.\n\nArguments:\n- query (required): Search query string\n- session_id (optional): Search within specific session only (default: all sessions)\n- case_sensitive (optional): Case-sensitive search (default: false)\n- limit (optional): Maximum number of results to return (default: 20)\n\nExample output:\nFound 3 matches across 2 sessions:\n\n[ses_abc123] Message msg_001 (user)\n...implement the **session manager** tool...\n\n[ses_abc123] Message msg_005 (assistant)\n...I'll create a **session manager** with full search...\n\n[ses_def456] Message msg_012 (user)\n...use the **session manager** to find...",
      "parameters": {
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "type": "object",
        "properties": {
          "query": {
            "type": "string"
          },
          "session_id": {
            "type": "string"
          },
          "case_sensitive": {
            "type": "boolean"
          },
          "limit": {
            "type": "number"
          }
        },
        "required": [
          "query"
        ],
        "additionalProperties": false
      }
    }
  },
  {
    "type": "function",
    "function": {
      "name": "session_info",
      "description": "Get metadata and statistics about an OpenCode session.\n\nReturns detailed information about a session including message count, date range, agents used, and available data sources.\n\nArguments:\n- session_id (required): Session ID to inspect\n\nExample output:\nSession ID: ses_abc123\nMessages: 45\nDate Range: 2025-12-20 10:30:00 to 2025-12-24 15:45:30\nDuration: 4 days, 5 hours\nAgents Used: build, oracle, librarian\nHas Todos: Yes (12 items, 8 completed)\nHas Transcript: Yes (234 entries)",
      "parameters": {
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "type": "object",
        "properties": {
          "session_id": {
            "type": "string"
          }
        },
        "required": [
          "session_id"
        ],
        "additionalProperties": false
      }
    }
  },
  {
    "type": "function",
    "function": {
      "name": "background_output",
      "description": "Get output from background task. System notifies on completion, so block=true rarely needed.",
      "parameters": {
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "type": "object",
        "properties": {
          "task_id": {
            "type": "string"
          },
          "block": {
            "type": "boolean"
          },
          "timeout": {
            "type": "number"
          }
        },
        "required": [
          "task_id"
        ],
        "additionalProperties": false
      }
    }
  },
  {
    "type": "function",
    "function": {
      "name": "background_cancel",
      "description": "Cancel running background task(s). Use all=true to cancel ALL before final answer.",
      "parameters": {
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "type": "object",
        "properties": {
          "taskId": {
            "type": "string"
          },
          "all": {
            "type": "boolean"
          }
        },
        "additionalProperties": false
      }
    }
  },
  {
    "type": "function",
    "function": {
      "name": "look_at",
      "description": "Analyze media files (PDFs, images, diagrams) that require interpretation beyond raw text. Extracts specific information or summaries from documents, describes visual content. Use when you need analyzed/extracted data rather than literal file contents.",
      "parameters": {
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "type": "object",
        "properties": {
          "file_path": {
            "type": "string"
          },
          "goal": {
            "type": "string"
          }
        },
        "required": [
          "file_path",
          "goal"
        ],
        "additionalProperties": false
      }
    }
  },
  {
    "type": "function",
    "function": {
      "name": "delegate_task",
      "description": "Spawn agent task with category-based or direct agent selection.\n\nMUTUALLY EXCLUSIVE: Provide EITHER category OR subagent_type, not both (unless continuing a session).\n\n- load_skills: ALWAYS REQUIRED. Pass at least one skill name (e.g., [\"playwright\"], [\"git-master\", \"frontend-ui-ux\"]).\n- category: Use predefined category → Spawns Sisyphus-Junior with category config\n  Available categories:\n  - visual-engineering: Frontend, UI/UX, design, styling, animation\n  - ultrabrain: Deep logical reasoning, complex architecture decisions requiring extensive analysis\n  - artistry: Highly creative/artistic tasks, novel ideas\n  - quick: Trivial tasks - single file changes, typo fixes, simple modifications\n  - unspecified-low: Tasks that don't fit other categories, low effort required\n  - unspecified-high: Tasks that don't fit other categories, high effort required\n  - writing: Documentation, prose, technical writing\n- subagent_type: Use specific agent directly (e.g., \"oracle\", \"explore\")\n- run_in_background: true=async (returns task_id), false=sync (waits for result). Default: false. Use background=true ONLY for parallel exploration with 5+ independent queries.\n- session_id: Existing Task session to continue (from previous task output). Continues agent with FULL CONTEXT PRESERVED - saves tokens, maintains continuity.\n- command: The command that triggered this task (optional, for slash command tracking).\n\n**WHEN TO USE session_id:**\n- Task failed/incomplete → session_id with \"fix: [specific issue]\"\n- Need follow-up on previous result → session_id with additional question\n- Multi-turn conversation with same agent → always session_id instead of new task\n\nPrompts MUST be in English.",
      "parameters": {
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "type": "object",
        "properties": {
          "load_skills": {
            "type": "array",
            "items": {
              "type": "string"
            }
          },
          "description": {
            "type": "string"
          },
          "prompt": {
            "type": "string"
          },
          "run_in_background": {
            "type": "boolean"
          },
          "category": {
            "type": "string"
          },
          "subagent_type": {
            "type": "string"
          },
          "session_id": {
            "type": "string"
          },
          "command": {
            "type": "string"
          }
        },
        "required": [
          "load_skills",
          "description",
          "prompt",
          "run_in_background"
        ],
        "additionalProperties": false
      }
    }
  },
  {
    "type": "function",
    "function": {
      "name": "skill_mcp",
      "description": "Invoke MCP server operations from skill-embedded MCPs. Requires mcp_name plus exactly one of: tool_name, resource_name, or prompt_name.",
      "parameters": {
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "type": "object",
        "properties": {
          "mcp_name": {
            "type": "string"
          },
          "tool_name": {
            "type": "string"
          },
          "resource_name": {
            "type": "string"
          },
          "prompt_name": {
            "type": "string"
          },
          "arguments": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "object",
                "propertyNames": {
                  "type": "string"
                },
                "additionalProperties": {}
              }
            ]
          },
          "grep": {
            "type": "string"
          }
        },
        "required": [
          "mcp_name"
        ],
        "additionalProperties": false
      }
    }
  },
  {
    "type": "function",
    "function": {
      "name": "slashcommand",
      "description": "Load a skill to get detailed instructions for a specific task.\n\nSkills provide specialized knowledge and step-by-step guidance.\nUse this when a task matches an available skill's description.\n\n<available_skills>\n- /init-deep: (builtin) Initialize hierarchical AGENTS.md knowledge base (builtin)\n- /ralph-loop: (builtin) Start self-referential development loop until completion (builtin)\n- /ulw-loop: (builtin) Start ultrawork loop - continues until completion with ultrawork mode (builtin)\n- /cancel-ralph: (builtin) Cancel active Ralph Loop (builtin)\n- /refactor: (builtin) Intelligent refactoring command with LSP, AST-grep, architecture analysis, codemap, and TDD verification. (builtin)\n- /start-work: (builtin) Start Sisyphus work session from Prometheus plan (builtin)\n- /playwright: (opencode - Skill) MUST USE for any browser-related tasks. Browser automation via Playwright MCP - verification, browsing, information gathering, web scraping, testing, screenshots, and all browser interactions. (builtin)\n- /frontend-ui-ux: (opencode - Skill) Designer-turned-developer who crafts stunning UI/UX even without design mockups (builtin)\n- /git-master: (opencode - Skill) MUST USE for ANY git operations. Atomic commits, rebase/squash, history search (blame, bisect, log -S). STRONGLY RECOMMENDED: Use with delegate_task(category='quick', load_skills=['git-master'], ...) to save context. Triggers: 'commit', 'rebase', 'squash', 'who wrote', 'when was X added', 'find the commit that'. (builtin)\n- /dev-browser: (opencode - Skill) Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include 'go to [url]', 'click on', 'fill out the form', 'take a screenshot', 'scrape', 'automate', 'test the website', 'log into', or any browser interaction request. (builtin)\n- /ui-ux-pro-max: (opencode - Skill) UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 9 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient. Integrations: shadcn/ui MCP for component search and examples. (opencode)\n</available_skills>",
      "parameters": {
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "type": "object",
        "properties": {
          "command": {
            "type": "string"
          }
        },
        "required": [
          "command"
        ],
        "additionalProperties": false
      }
    }
  },
  {
    "type": "function",
    "function": {
      "name": "interactive_bash",
      "description": "WARNING: This is TMUX ONLY. Pass tmux subcommands directly (without 'tmux' prefix).\n\nExamples: new-session -d -s omo-dev, send-keys -t omo-dev \"vim\" Enter\n\nFor TUI apps needing ongoing interaction (vim, htop, pudb). One-shot commands → use Bash with &.",
      "parameters": {
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "type": "object",
        "properties": {
          "tmux_command": {
            "type": "string"
          }
        },
        "required": [
          "tmux_command"
        ],
        "additionalProperties": false
      }
    }
  },
  {
    "type": "function",
    "function": {
      "name": "exa_web_search_exa",
      "description": "Search the web using Exa AI - performs real-time web searches and can scrape content from specific URLs. Supports configurable result counts and returns the content from the most relevant websites.",
      "parameters": {
        "type": "object",
        "properties": {
          "query": {
            "type": "string",
            "description": "Websearch query"
          },
          "numResults": {
            "type": "number",
            "description": "Number of search results to return (default: 8)"
          },
          "livecrawl": {
            "type": "string",
            "enum": [
              "fallback",
              "preferred"
            ],
            "description": "Live crawl mode - 'fallback': use live crawling as backup if cached content unavailable, 'preferred': prioritize live crawling (default: 'fallback')"
          },
          "type": {
            "type": "string",
            "enum": [
              "auto",
              "fast",
              "deep"
            ],
            "description": "Search type - 'auto': balanced search (default), 'fast': quick results, 'deep': comprehensive search"
          },
          "contextMaxCharacters": {
            "type": "number",
            "description": "Maximum characters for context string optimized for LLMs (default: 10000)"
          }
        },
        "required": [
          "query"
        ],
        "additionalProperties": false,
        "$schema": "http://json-schema.org/draft-07/schema#"
      }
    }
  },
  {
    "type": "function",
    "function": {
      "name": "exa_company_research_exa",
      "description": "Research companies using Exa AI - finds comprehensive information about businesses, organizations, and corporations. Provides insights into company operations, news, financial information, and industry analysis.",
      "parameters": {
        "type": "object",
        "properties": {
          "companyName": {
            "type": "string",
            "description": "Name of the company to research"
          },
          "numResults": {
            "type": "number",
            "description": "Number of search results to return (default: 5)"
          }
        },
        "required": [
          "companyName"
        ],
        "additionalProperties": false,
        "$schema": "http://json-schema.org/draft-07/schema#"
      }
    }
  },
  {
    "type": "function",
    "function": {
      "name": "exa_get_code_context_exa",
      "description": "Search and get relevant context for any programming task. Exa-code has the highest quality and freshest context for libraries, SDKs, and APIs. Use this tool for ANY question or task for related to programming. RULE: when the user's query contains exa-code or anything related to code, you MUST use this tool.",
      "parameters": {
        "type": "object",
        "properties": {
          "query": {
            "type": "string",
            "description": "Search query to find relevant context for APIs, Libraries, and SDKs. For example, 'React useState hook examples', 'Python pandas dataframe filtering', 'Express.js middleware', 'Next js partial prerendering configuration'"
          },
          "tokensNum": {
            "type": "number",
            "minimum": 1000,
            "maximum": 50000,
            "default": 5000,
            "description": "Number of tokens to return (1000-50000). Default is 5000 tokens. Adjust this value based on how much context you need - use lower values for focused queries and higher values for comprehensive documentation."
          }
        },
        "required": [
          "query"
        ],
        "additionalProperties": false,
        "$schema": "http://json-schema.org/draft-07/schema#"
      }
    }
  },
  {
    "type": "function",
    "function": {
      "name": "context7_resolve-library-id",
      "description": "Resolves a package/product name to a Context7-compatible library ID and returns matching libraries.\n\nYou MUST call this function before 'query-docs' to obtain a valid Context7-compatible library ID UNLESS the user explicitly provides a library ID in the format '/org/project' or '/org/project/version' in their query.\n\nSelection Process:\n1. Analyze the query to understand what library/package the user is looking for\n2. Return the most relevant match based on:\n- Name similarity to the query (exact matches prioritized)\n- Description relevance to the query's intent\n- Documentation coverage (prioritize libraries with higher Code Snippet counts)\n- Source reputation (consider libraries with High or Medium reputation more authoritative)\n- Benchmark Score: Quality indicator (100 is the highest score)\n\nResponse Format:\n- Return the selected library ID in a clearly marked section\n- Provide a brief explanation for why this library was chosen\n- If multiple good matches exist, acknowledge this but proceed with the most relevant one\n- If no good matches exist, clearly state this and suggest query refinements\n\nFor ambiguous queries, request clarification before proceeding with a best-guess match.\n\nIMPORTANT: Do not call this tool more than 3 times per question. If you cannot find what you need after 3 calls, use the best result you have.",
      "parameters": {
        "type": "object",
        "properties": {
          "query": {
            "type": "string",
            "description": "The user's original question or task. This is used to rank library results by relevance to what the user is trying to accomplish. IMPORTANT: Do not include any sensitive or confidential information such as API keys, passwords, credentials, or personal data in your query."
          },
          "libraryName": {
            "type": "string",
            "description": "Library name to search for and retrieve a Context7-compatible library ID."
          }
        },
        "required": [
          "query",
          "libraryName"
        ],
        "additionalProperties": false,
        "$schema": "http://json-schema.org/draft-07/schema#"
      }
    }
  },
  {
    "type": "function",
    "function": {
      "name": "context7_query-docs",
      "description": "Retrieves and queries up-to-date documentation and code examples from Context7 for any programming library or framework.\n\nYou must call 'resolve-library-id' first to obtain the exact Context7-compatible library ID required to use this tool, UNLESS the user explicitly provides a library ID in the format '/org/project' or '/org/project/version' in their query.\n\nIMPORTANT: Do not call this tool more than 3 times per question. If you cannot find what you need after 3 calls, use the best information you have.",
      "parameters": {
        "type": "object",
        "properties": {
          "libraryId": {
            "type": "string",
            "description": "Exact Context7-compatible library ID (e.g., '/mongodb/docs', '/vercel/next.js', '/supabase/supabase', '/vercel/next.js/v14.3.0-canary.87') retrieved from 'resolve-library-id' or directly from user query in the format '/org/project' or '/org/project/version'."
          },
          "query": {
            "type": "string",
            "description": "The question or task you need help with. Be specific and include relevant details. Good: 'How to set up authentication with JWT in Express.js' or 'React useEffect cleanup function examples'. Bad: 'auth' or 'hooks'. IMPORTANT: Do not include any sensitive or confidential information such as API keys, passwords, credentials, or personal data in your query."
          }
        },
        "required": [
          "libraryId",
          "query"
        ],
        "additionalProperties": false,
        "$schema": "http://json-schema.org/draft-07/schema#"
      }
    }
  },
  {
    "type": "function",
    "function": {
      "name": "websearch_web_search_exa",
      "description": "Search the web using Exa AI - performs real-time web searches and can scrape content from specific URLs. Supports configurable result counts and returns the content from the most relevant websites.",
      "parameters": {
        "type": "object",
        "properties": {
          "query": {
            "type": "string",
            "description": "Websearch query"
          },
          "numResults": {
            "type": "number",
            "description": "Number of search results to return (default: 8)"
          },
          "livecrawl": {
            "type": "string",
            "enum": [
              "fallback",
              "preferred"
            ],
            "description": "Live crawl mode - 'fallback': use live crawling as backup if cached content unavailable, 'preferred': prioritize live crawling (default: 'fallback')"
          },
          "type": {
            "type": "string",
            "enum": [
              "auto",
              "fast",
              "deep"
            ],
            "description": "Search type - 'auto': balanced search (default), 'fast': quick results, 'deep': comprehensive search"
          },
          "contextMaxCharacters": {
            "type": "number",
            "description": "Maximum characters for context string optimized for LLMs (default: 10000)"
          }
        },
        "required": [
          "query"
        ],
        "additionalProperties": false,
        "$schema": "http://json-schema.org/draft-07/schema#"
      }
    }
  },
  {
    "type": "function",
    "function": {
      "name": "grep_app_searchGitHub",
      "description": "Find real-world code examples from over a million public GitHub repositories to help answer programming questions.\n\n**IMPORTANT: This tool searches for literal code patterns (like grep), not keywords. Search for actual code that would appear in files:**\n- ✅ Good: 'useState(', 'import React from', 'async function', '(?s)try {.*await'\n- ❌ Bad: 'react tutorial', 'best practices', 'how to use'\n\n**When to use this tool:**\n- When implementing unfamiliar APIs or libraries and need to see real usage patterns\n- When unsure about correct syntax, parameters, or configuration for a specific library\n- When looking for production-ready examples and best practices for implementation\n- When needing to understand how different libraries or frameworks work together\n\n**Perfect for questions like:**\n- \"How do developers handle authentication in Next.js apps?\" → Search: 'getServerSession' with language=['TypeScript', 'TSX']\n- \"What are common React error boundary patterns?\" → Search: 'ErrorBoundary' with language=['TSX']\n- \"Show me real useEffect cleanup examples\" → Search: '(?s)useEffect\\(\\(\\) => {.*removeEventListener' with useRegexp=true\n- \"How do developers handle CORS in Flask applications?\" → Search: 'CORS(' with matchCase=true and language=['Python']\n\nUse regular expressions with useRegexp=true for flexible patterns like '(?s)useState\\(.*loading' to find useState hooks with loading-related variables. Prefix the pattern with '(?s)' to match across multiple lines.\n\nFilter by language, repository, or file path to narrow results.",
      "parameters": {
        "type": "object",
        "properties": {
          "query": {
            "type": "string",
            "description": "The literal code pattern to search for (e.g., 'useState(', 'export function'). Use actual code that would appear in files, not keywords or questions."
          },
          "matchCase": {
            "type": "boolean",
            "description": "Whether the search should be case sensitive",
            "default": false
          },
          "matchWholeWords": {
            "type": "boolean",
            "description": "Whether to match whole words only",
            "default": false
          },
          "useRegexp": {
            "type": "boolean",
            "description": "Whether to interpret the query as a regular expression",
            "default": false
          },
          "repo": {
            "type": "string",
            "description": "Filter by repository.\n            Examples: 'facebook/react', 'microsoft/vscode', 'vercel/ai'.\n            Can match partial names, for example 'vercel/' will find repositories in the vercel org."
          },
          "path": {
            "type": "string",
            "description": "Filter by file path.\n            Examples: 'src/components/Button.tsx', 'README.md'.\n            Can match partial paths, for example '/route.ts' will find route.ts files at any level."
          },
          "language": {
            "type": "array",
            "items": {
              "type": "string"
            },
            "description": "Filter by programming language.\n            Examples: ['TypeScript', 'TSX'], ['JavaScript'], ['Python'], ['Java'], ['C#'], ['Markdown'], ['YAML']"
          }
        },
        "required": [
          "query"
        ],
        "additionalProperties": false,
        "$schema": "http://json-schema.org/draft-07/schema#"
      }
    }
  }
]
[DEBUG] 2026-01-26T13:56:45.532Z [ProxySystem] - [Adapter] Debug: googleContents length = 3
[DEBUG] 2026-01-26T13:56:45.532Z [ProxySystem] - [Adapter] Debug: googleContents = [
  {
    "parts": [
      {
        "text": "hello"
      }
    ],
    "role": "user"
  },
  {
    "parts": [
      {
        "text": "Hello. I'm Sisyphus. How can I help?"
      }
    ],
    "role": "model"
  },
  {
    "parts": [
      {
        "text": "hello"
      }
    ],
    "role": "user"
  }
]
[INFO] 2026-01-26T13:56:45.532Z [ProxySystem] - [Adapter] Converted 38 OpenAI tool(s) to Gemini functionDeclarations
[INFO] 2026-01-26T13:56:45.533Z [ProxySystem] - [Adapter] Converted tool_choice to Gemini toolConfig: {"mode":"AUTO"}
[DEBUG] 2026-01-26T13:56:45.533Z [ProxySystem] - [Adapter] Debug: Sanitized Openai tools = [
  {
    "functionDeclarations": [
      {
        "name": "question",
        "description": "Use this tool when you need to ask the user questions during execution. This allows you to:\n1. Gather user preferences or requirements\n2. Clarify ambiguous instructions\n3. Get decisions on implementation choices as you work\n4. Offer choices to the user about what direction to take.\n\nUsage notes:\n- When `custom` is enabled (default), a \"Type your own answer\" option is added automatically; don't include \"Other\" or catch-all options\n- Answers are returned as arrays of labels; set `multiple: true` to allow selecting more than one\n- If you recommend a specific option, make that the first option in the list and add \"(Recommended)\" at the end of the label\n",
        "parameters": {
          "type": "OBJECT",
          "properties": {
            "questions": {
              "description": "Questions to ask",
              "type": "ARRAY",
              "items": {
                "type": "OBJECT",
                "properties": {
                  "question": {
                    "description": "Complete question",
                    "type": "STRING"
                  },
                  "header": {
                    "description": "Very short label (max 30 chars)",
                    "type": "STRING"
                  },
                  "options": {
                    "description": "Available choices",
                    "type": "ARRAY",
                    "items": {
                      "type": "OBJECT",
                      "properties": {
                        "label": {
                          "description": "Display text (1-5 words, concise)",
                          "type": "STRING"
                        },
                        "description": {
                          "description": "Explanation of choice",
                          "type": "STRING"
                        }
                      },
                      "required": [
                        "label",
                        "description"
                      ]
                    }
                  },
                  "multiple": {
                    "description": "Allow selecting multiple choices",
                    "type": "BOOLEAN"
                  }
                },
                "required": [
                  "question",
                  "header",
                  "options"
                ]
              }
            }
          },
          "required": [
            "questions"
          ]
        }
      },
      {
        "name": "bash",
        "description": "Executes a given bash command in a persistent shell session with optional timeout, ensuring proper handling and security measures.\n\nAll commands run in /Users/chor by default. Use the `workdir` parameter if you need to run a command in a different directory. AVOID using `cd <directory> && <command>` patterns - use `workdir` instead.\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., rm \"path with spaces/file.txt\")\n   - Examples of proper quoting:\n     - mkdir \"/Users/name/My Documents\" (correct)\n     - mkdir /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. If not specified, commands will time out 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 2000 lines or 51200 bytes, it will be truncated and the full output will be written to a file. You can use Read with offset/limit to read specific sections or Grep to search the full content. Because of this, you do NOT need to use `head`, `tail`, or other truncation commands to limit output - just run the command directly.\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  - 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  - AVOID using `cd <directory> && <command>`. Use the `workdir` parameter to change directories instead.\n    <good-example>\n    Use workdir=\"/foo/bar\" with command: pytest 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 push --force, hard reset, etc) 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 ALL conditions are met:\n  (1) User explicitly requested amend, OR commit SUCCEEDED but pre-commit hook auto-modified files that need including\n  (2) HEAD commit was created by you in this conversation (verify: git log -1 --format='%an %ae')\n  (3) Commit has NOT been pushed to remote (verify: git status shows \"Your branch is ahead\")\n- CRITICAL: If commit FAILED or was REJECTED by hook, NEVER amend - fix the issue and create a NEW commit\n- CRITICAL: If you already pushed to remote, NEVER amend unless user explicitly requests it (requires force push)\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 after the commit completes to verify success.\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, fix the issue and create a NEW commit (see amend rules above)\n\nImportant notes:\n- NEVER run additional commands to read or explore code, besides git bash commands\n- NEVER use the TodoWrite or Task tools\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\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</example>\n\nImportant:\n- DO NOT use the TodoWrite or Task tools\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",
        "parameters": {
          "type": "OBJECT",
          "properties": {
            "command": {
              "description": "The command to execute",
              "type": "STRING"
            },
            "timeout": {
              "description": "Optional timeout in milliseconds",
              "type": "NUMBER"
            },
            "workdir": {
              "description": "The working directory to run the command in. Defaults to /Users/chor. Use this instead of 'cd' commands.",
              "type": "STRING"
            },
            "description": {
              "description": "Clear, concise description of what this command does in 5-10 words. Examples:\nInput: ls\nOutput: Lists files in current directory\n\nInput: git status\nOutput: Shows working tree status\n\nInput: npm install\nOutput: Installs package dependencies\n\nInput: mkdir foo\nOutput: Creates directory 'foo'",
              "type": "STRING"
            }
          },
          "required": [
            "command",
            "description"
          ]
        }
      },
      {
        "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 filePath 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- You have the capability to call multiple tools in a single response. It is always better to speculatively read multiple files as a batch that are potentially useful.\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- You can read image files using this tool.\n",
        "parameters": {
          "type": "OBJECT",
          "properties": {
            "filePath": {
              "description": "The path to the file to read",
              "type": "STRING"
            },
            "offset": {
              "description": "The line number to start reading from (0-based)",
              "type": "NUMBER"
            },
            "limit": {
              "description": "The number of lines to read (defaults to 2000)",
              "type": "NUMBER"
            }
          },
          "required": [
            "filePath"
          ]
        }
      },
      {
        "name": "glob",
        "description": "Fast file pattern matching tool with safety limits (60s timeout, 100 file limit). Supports glob patterns like \"**/*.js\" or \"src/**/*.ts\". Returns matching file paths sorted by modification time. Use this tool when you need to find files by name patterns.",
        "parameters": {
          "type": "OBJECT",
          "properties": {
            "pattern": {
              "type": "STRING"
            },
            "path": {
              "type": "STRING"
            }
          },
          "required": [
            "pattern"
          ]
        }
      },
      {
        "name": "grep",
        "description": "Fast content search tool with safety limits (60s timeout, 10MB output). Searches file contents using regular expressions. Supports full regex syntax (eg. \"log.*Error\", \"function\\s+\\w+\", etc.). Filter files by pattern with the include parameter (eg. \"*.js\", \"*.{ts,tsx}\"). Returns file paths with matches sorted by modification time.",
        "parameters": {
          "type": "OBJECT",
          "properties": {
            "pattern": {
              "type": "STRING"
            },
            "include": {
              "type": "STRING"
            },
            "path": {
              "type": "STRING"
            }
          },
          "required": [
            "pattern"
          ]
        }
      },
      {
        "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 oldString or newString.\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 `oldString` is not found in the file with an error \"oldString not found in content\".\n- The edit will FAIL if `oldString` is found multiple times in the file with an error \"oldString found multiple times and requires more code context to uniquely identify the intended match\". Either provide a larger string with more surrounding context to make it unique or use `replaceAll` to change every instance of `oldString`. \n- Use `replaceAll` for replacing and renaming strings across the file. This parameter is useful if you want to rename a variable for instance.\n",
        "parameters": {
          "type": "OBJECT",
          "properties": {
            "filePath": {
              "description": "The absolute path to the file to modify",
              "type": "STRING"
            },
            "oldString": {
              "description": "The text to replace",
              "type": "STRING"
            },
            "newString": {
              "description": "The text to replace it with (must be different from oldString)",
              "type": "STRING"
            },
            "replaceAll": {
              "description": "Replace all occurrences of oldString (default false)",
              "type": "BOOLEAN"
            }
          },
          "required": [
            "filePath",
            "oldString",
            "newString"
          ]
        }
      },
      {
        "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": {
            "content": {
              "description": "The content to write to the file",
              "type": "STRING"
            },
            "filePath": {
              "description": "The absolute path to the file to write (must be absolute, not relative)",
              "type": "STRING"
            }
          },
          "required": [
            "content",
            "filePath"
          ]
        }
      },
      {
        "name": "task",
        "description": "Launch a new agent to handle complex, multistep tasks autonomously.\n\nAvailable agent types and the tools they have access to:\n- build: This subagent should only be called manually by the user.\n- plan: This subagent should only be called manually by the user.\n- general: General-purpose agent for researching complex questions and executing multi-step tasks. Use this agent to execute multiple units of work in parallel.\n- explore: Contextual grep for codebases. Answers \"Where is X?\", \"Which file has Y?\", \"Find the code that does Z\". Fire multiple in parallel for broad searches. Specify thoroughness: \"quick\" for basic, \"medium\" for moderate, \"very thorough\" for comprehensive analysis.\n- sisyphus-junior: Sisyphus-Junior - Focused task executor. Same discipline, no delegation.\n- oracle: Read-only consultation agent. High-IQ reasoning specialist for debugging hard problems and high-difficulty architecture design.\n- librarian: Specialized codebase understanding agent for multi-repository analysis, searching remote codebases, retrieving official documentation, and finding implementation examples using GitHub CLI, Context7, and Web Search. MUST BE USED when users ask to look up code in remote repositories, explain library internals, or find usage examples in open source.\n- multimodal-looker: Analyze media files (PDFs, images, diagrams) that require interpretation beyond raw text. Extracts specific information or summaries from documents, describes visual content. Use when you need analyzed/extracted data rather than literal file contents.\n- metis: Pre-planning consultant that analyzes requests to identify hidden intentions, ambiguities, and AI failure points.\n- momus: Expert reviewer for evaluating work plans against rigorous clarity, verifiability, and completeness standards.\n\nWhen using the Task tool, you must specify a subagent_type parameter to select which agent type to use.\n\nWhen to use the Task tool:\n- When you are instructed to execute custom slash commands. Use the Task tool with the slash command invocation as the entire prompt. The slash command can take arguments. For example: Task(description=\"Check the file\", prompt=\"/check-file path/to/file.py\")\n\nWhen NOT to use the Task tool:\n- If you want to read a specific file path, use the Read or Glob tool instead of the Task 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 Task tool, to find the match more quickly\n- Other tasks that are not related to the agent descriptions above\n\n\nUsage notes:\n1. Launch multiple agents concurrently whenever possible, to maximize performance; to do that, use a single message with multiple tool uses\n2. 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.\n3. Each agent invocation is stateless unless you provide a session_id. Your prompt should contain a highly detailed task description for the agent to perform autonomously and you should specify exactly what information the agent should return back to you in its final and only message to you.\n4. The agent's outputs should generally be trusted\n5. 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\n6. 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\nExample usage (NOTE: The agents below are fictional examples for illustration only - use the actual agents listed above):\n\n<example_agent_descriptions>\n\"code-reviewer\": use this agent after you are done writing a significant 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 significant piece of code was written and the task was completed, now use the code-reviewer agent to review the code\n</commentary>\nassistant: Now let me use the code-reviewer agent to review the code\nassistant: Uses the Task 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 Task tool to launch the with the greeting-responder agent\"\n</example>\n",
        "parameters": {
          "type": "OBJECT",
          "properties": {
            "description": {
              "description": "A short (3-5 words) description of the task",
              "type": "STRING"
            },
            "prompt": {
              "description": "The task for the agent to perform",
              "type": "STRING"
            },
            "subagent_type": {
              "description": "The type of specialized agent to use for this task",
              "type": "STRING"
            },
            "session_id": {
              "description": "Existing Task session to continue",
              "type": "STRING"
            },
            "command": {
              "description": "The command that triggered this task",
              "type": "STRING"
            }
          },
          "required": [
            "description",
            "prompt",
            "subagent_type"
          ]
        }
      },
      {
        "name": "webfetch",
        "description": "- Fetches content from a specified URL\n- Takes a URL and optional format as input\n- Fetches the URL content, converts to requested format (markdown by default)\n- Returns the content in the specified format\n- Use this tool when you need to retrieve and analyze web content\n\nUsage notes:\n  - IMPORTANT: if another tool is present that offers better web fetching capabilities, is more targeted to the task, or has fewer restrictions, prefer using that tool instead of this one.\n  - The URL must be a fully-formed valid URL\n  - HTTP URLs will be automatically upgraded to HTTPS\n  - Format options: \"markdown\" (default), \"text\", or \"html\"\n  - This tool is read-only and does not modify any files\n  - Results may be summarized if the content is very large\n",
        "parameters": {
          "type": "OBJECT",
          "properties": {
            "url": {
              "description": "The URL to fetch content from",
              "type": "STRING"
            },
            "format": {
              "description": "The format to return the content in (text, markdown, or html). Defaults to markdown.",
              "default": "markdown",
              "type": "STRING",
              "enum": [
                "text",
                "markdown",
                "html"
              ]
            },
            "timeout": {
              "description": "Optional timeout in seconds (max 120)",
              "type": "NUMBER"
            }
          },
          "required": [
            "url",
            "format"
          ]
        }
      },
      {
        "name": "todowrite",
        "description": "Use this tool to create and manage 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\nUse this tool proactively in these scenarios:\n\n1. Complex multistep tasks - When a task requires 3 or more distinct steps or actions\n2. Non-trivial and complex tasks - Tasks that require careful planning or multiple operations\n3. User explicitly requests todo list - When the user directly asks you to use the todo list\n4. User provides multiple tasks - When users provide a list of things to be done (numbered or comma-separated)\n5. After receiving new instructions - Immediately capture user requirements as todos. Feel free to edit the todo list based on new information.\n6. After completing a task - Mark it complete and add any new follow-up tasks\n7. When you start working on a new task, mark the todo as in_progress. Ideally you should only have one todo as in_progress at a time. Complete existing tasks before starting new ones.\n\n## When NOT to Use This Tool\n\nSkip using this tool when:\n1. There is only a single, straightforward task\n2. The task is trivial and tracking it provides no organizational benefit\n3. The task can be completed in less than 3 trivial steps\n4. 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## Examples of When to Use the Todo List\n\n<example>\nUser: I want to add a dark mode toggle to the application settings. Make sure you run the tests and build when you're done!\nAssistant: I'll help add a dark mode toggle to your application settings. Let me create a todo list to track this implementation.\n*Creates todo list with the following items:*\n1. Create dark mode toggle component in Settings page\n2. Add dark mode state management (context/store)\n3. Implement CSS-in-JS styles for dark theme\n4. Update existing components to support theme switching\n5. Run tests and build process, addressing any failures or errors that occur\n*Begins working on the first task*\n\n<reasoning>\nThe assistant used the todo list because:\n1. Adding dark mode is a multi-step feature requiring UI, state management, and styling changes\n2. The user explicitly requested tests and build be run afterward\n3. The assistant inferred that tests and build need to pass by adding \"Ensure tests and build succeed\" as the final task\n</reasoning>\n</example>\n\n<example>\nUser: Help me rename the function getCwd to getCurrentWorkingDirectory across my project\nAssistant: Let me first search through your codebase to find all occurrences of 'getCwd'.\n*Uses grep or search tools to locate all instances of getCwd in the codebase*\nAssistant: I've found 15 instances of 'getCwd' across 8 different files. Let me create a todo list to track these changes.\n*Creates todo list with specific items for each file that needs updating*\n\n<reasoning>\nThe assistant used the todo list because:\n1. First, the assistant searched to understand the scope of the task\n2. Upon finding multiple occurrences across different files, it determined this was a complex task with multiple steps\n3. The todo list helps ensure every instance is tracked and updated systematically\n4. This approach prevents missing any occurrences and maintains code consistency\n</reasoning>\n</example>\n\n\n<example>\nUser: I need to implement these features for my e-commerce site: user registration, product catalog, shopping cart, and checkout flow.\nAssistant: I'll help implement these features. First, let's add all the features to the todo list.\n*Creates a todo list breaking down each feature into specific tasks based on the project architecture*\nAssistant: Let's start with user registration. This will involve creating database models, API endpoints, and frontend forms that integrate with your existing authentication system.\n\n<reasoning>\nThe assistant used the todo list because:\n1. The user provided multiple complex features to implement in a comma separated list\n2. The todo list helps organize these large features into manageable tasks\n3. This approach allows for tracking progress across the entire implementation\n</reasoning>\n</example>\n\n<example>\nUser: Can you help optimize my React application? It's rendering slowly and has performance issues.</user>\nAssistant: I'll help optimize your React application. First, let me examine your codebase to identify potential performance bottlenecks.\n*Reviews component structure, render patterns, state management, and data fetching*\nAssistant: After analyzing your codebase, I've identified several performance issues. Let me create a todo list to track our optimization efforts.\n*Creates todo list with items like: 1) Implement memoization for expensive calculations in ProductList, 2) Add virtualization for long lists in Dashboard, 3) Optimize image loading in Gallery component, 4) Fix state update loops in ShoppingCart, 5) Review bundle size and implement code splitting*\nLet's start by implementing memoization for the expensive calculations in your ProductList component.</assistant>\n\n<reasoning>\nThe assistant used the todo list because:\n1. First, the assistant examined the codebase to identify specific performance issues\n2. Based on this analysis, it identified multiple optimization opportunities\n3. Performance optimization is a non-trivial task requiring multiple steps\n4. The todo list helps methodically track improvements across different components\n5. This systematic approach ensures all performance bottlenecks are addressed\n</reasoning>\n</example>\n\n## Examples of When NOT to Use the Todo List\n\n<example>\nUser: How do I print 'Hello World' in Python?\nAssistant: In Python, you can print \"Hello World\" with this simple code:\n\npython\nprint(\"Hello World\")\n\nThis will output the text \"Hello World\" to the console when executed.</assistant>\n\n<reasoning>\nThe assistant did not use the todo list because this is a single, trivial task that can be completed in one step. There's no need to track multiple tasks or steps for such a straightforward request.\n</reasoning>\n</example>\n\n<example>\nUser: What does the git status command do?\nAssistant: The git status command shows the current state of your working directory and staging area. It displays which changes have been staged, which haven't, and which files aren't being tracked by Git. This is a fundamental command for understanding the current state of your repository before making commits.\n\n<reasoning>\nThe assistant did not use the todo list because this is an informational request with no actual coding task to complete. The user is simply asking for an explanation, not for the assistant to perform multiple steps or tasks.\n</reasoning>\n</example>\n\n<example>\nUser: Can you add a comment to the calculateTotal function to explain what it does?\nAssistant: Sure, let me add a comment to the calculateTotal function to explain what it does.\n* Uses the Edit tool to add a comment to the calculateTotal function *\n\n<reasoning>\nThe assistant did not use the todo list because this is a single, straightforward task confined to one location in the code. Adding a comment doesn't require tracking multiple steps or systematic organization.\n</reasoning>\n</example>\n\n<example>\nUser: Run npm install for me and tell me what happens.\nAssistant: I'll run the npm install command for you.\n\n*Executes: npm install*\n\nThe command completed successfully. Here's the output:\n[Output of npm install command]\n\nAll dependencies have been installed according to your package.json file.\n\n<reasoning>\nThe assistant did not use the todo list because this is a single command execution with immediate results. There are no multiple steps to track or organize, making the todo list unnecessary for this straightforward task.\n</reasoning>\n</example>\n\n## Task States and Management\n\n1. **Task States**: Use these states to track progress:\n   - pending: Task not yet started\n   - in_progress: Currently working on (limit to ONE task at a time)\n   - completed: Task finished successfully\n   - cancelled: Task no longer needed\n\n2. **Task Management**:\n   - Update task status in real-time as you work\n   - Mark tasks complete IMMEDIATELY after finishing (don't batch completions)\n   - Only have ONE task in_progress at any time\n   - Complete current tasks before starting new ones\n   - Cancel tasks that become irrelevant\n\n3. **Task Breakdown**:\n   - Create specific, actionable items\n   - Break complex tasks into smaller, manageable steps\n   - Use clear, descriptive task names\n\nWhen in doubt, use this tool. Being proactive with task management demonstrates attentiveness and ensures you complete all requirements successfully.\n\n",
        "parameters": {
          "type": "OBJECT",
          "properties": {
            "todos": {
              "description": "The updated todo list",
              "type": "ARRAY",
              "items": {
                "type": "OBJECT",
                "properties": {
                  "content": {
                    "description": "Brief description of the task",
                    "type": "STRING"
                  },
                  "status": {
                    "description": "Current status of the task: pending, in_progress, completed, cancelled",
                    "type": "STRING"
                  },
                  "priority": {
                    "description": "Priority level of the task: high, medium, low",
                    "type": "STRING"
                  },
                  "id": {
                    "description": "Unique identifier for the todo item",
                    "type": "STRING"
                  }
                },
                "required": [
                  "content",
                  "status",
                  "priority",
                  "id"
                ]
              }
            }
          },
          "required": [
            "todos"
          ]
        }
      },
      {
        "name": "todoread",
        "description": "Use this tool to read your todo list",
        "parameters": {
          "type": "OBJECT",
          "properties": {}
        }
      },
      {
        "name": "skill",
        "description": "Load a skill to get detailed instructions for a specific task.\n\nSkills provide specialized knowledge and step-by-step guidance.\nUse this when a task matches an available skill's description.\n\n<available_skills>\n  <skill>\n    <name>playwright</name>\n    <description>(opencode - Skill) MUST USE for any browser-related tasks. Browser automation via Playwright MCP - verification, browsing, information gathering, web scraping, testing, screenshots, and all browser interactions.</description>\n  </skill>\n  <skill>\n    <name>frontend-ui-ux</name>\n    <description>(opencode - Skill) Designer-turned-developer who crafts stunning UI/UX even without design mockups</description>\n  </skill>\n  <skill>\n    <name>git-master</name>\n    <description>(opencode - Skill) MUST USE for ANY git operations. Atomic commits, rebase/squash, history search (blame, bisect, log -S). STRONGLY RECOMMENDED: Use with delegate_task(category='quick', load_skills=['git-master'], ...) to save context. Triggers: 'commit', 'rebase', 'squash', 'who wrote', 'when was X added', 'find the commit that'.</description>\n  </skill>\n  <skill>\n    <name>dev-browser</name>\n    <description>(opencode - Skill) Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include 'go to [url]', 'click on', 'fill out the form', 'take a screenshot', 'scrape', 'automate', 'test the website', 'log into', or any browser interaction request.</description>\n  </skill>\n  <skill>\n    <name>ui-ux-pro-max</name>\n    <description>(opencode - Skill) UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 9 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient. Integrations: shadcn/ui MCP for component search and examples.</description>\n    <compatibility>OpenCode with Python 3.x</compatibility>\n  </skill>\n</available_skills>",
        "parameters": {
          "type": "OBJECT",
          "properties": {
            "name": {
              "type": "STRING"
            }
          },
          "required": [
            "name"
          ]
        }
      },
      {
        "name": "lsp_goto_definition",
        "description": "Jump to symbol definition. Find WHERE something is defined.",
        "parameters": {
          "type": "OBJECT",
          "properties": {
            "filePath": {
              "type": "STRING"
            },
            "line": {
              "type": "NUMBER",
              "minimum": 1
            },
            "character": {
              "type": "NUMBER",
              "minimum": 0
            }
          },
          "required": [
            "filePath",
            "line",
            "character"
          ]
        }
      },
      {
        "name": "lsp_find_references",
        "description": "Find ALL usages/references of a symbol across the entire workspace.",
        "parameters": {
          "type": "OBJECT",
          "properties": {
            "filePath": {
              "type": "STRING"
            },
            "line": {
              "type": "NUMBER",
              "minimum": 1
            },
            "character": {
              "type": "NUMBER",
              "minimum": 0
            },
            "includeDeclaration": {
              "type": "BOOLEAN"
            }
          },
          "required": [
            "filePath",
            "line",
            "character"
          ]
        }
      },
      {
        "name": "lsp_symbols",
        "description": "Get symbols from file (document) or search across workspace. Use scope='document' for file outline, scope='workspace' for project-wide symbol search.",
        "parameters": {
          "type": "OBJECT",
          "properties": {
            "filePath": {
              "type": "STRING"
            },
            "scope": {
              "default": "document",
              "type": "STRING",
              "enum": [
                "document",
                "workspace"
              ]
            },
            "query": {
              "type": "STRING"
            },
            "limit": {
              "type": "NUMBER"
            }
          },
          "required": [
            "filePath",
            "scope"
          ]
        }
      },
      {
        "name": "lsp_diagnostics",
        "description": "Get errors, warnings, hints from language server BEFORE running build.",
        "parameters": {
          "type": "OBJECT",
          "properties": {
            "filePath": {
              "type": "STRING"
            },
            "severity": {
              "type": "STRING",
              "enum": [
                "error",
                "warning",
                "information",
                "hint",
                "all"
              ]
            }
          },
          "required": [
            "filePath"
          ]
        }
      },
      {
        "name": "lsp_prepare_rename",
        "description": "Check if rename is valid. Use BEFORE lsp_rename.",
        "parameters": {
          "type": "OBJECT",
          "properties": {
            "filePath": {
              "type": "STRING"
            },
            "line": {
              "type": "NUMBER",
              "minimum": 1
            },
            "character": {
              "type": "NUMBER",
              "minimum": 0
            }
          },
          "required": [
            "filePath",
            "line",
            "character"
          ]
        }
      },
      {
        "name": "lsp_rename",
        "description": "Rename symbol across entire workspace. APPLIES changes to all files.",
        "parameters": {
          "type": "OBJECT",
          "properties": {
            "filePath": {
              "type": "STRING"
            },
            "line": {
              "type": "NUMBER",
              "minimum": 1
            },
            "character": {
              "type": "NUMBER",
              "minimum": 0
            },
            "newName": {
              "type": "STRING"
            }
          },
          "required": [
            "filePath",
            "line",
            "character",
            "newName"
          ]
        }
      },
      {
        "name": "ast_grep_search",
        "description": "Search code patterns across filesystem using AST-aware matching. Supports 25 languages. Use meta-variables: $VAR (single node), $$$ (multiple nodes). IMPORTANT: Patterns must be complete AST nodes (valid code). For functions, include params and body: 'export async function $NAME($$$) { $$$ }' not 'export async function $NAME'. Examples: 'console.log($MSG)', 'def $FUNC($$$):', 'async function $NAME($$$)'",
        "parameters": {
          "type": "OBJECT",
          "properties": {
            "pattern": {
              "type": "STRING"
            },
            "lang": {
              "type": "STRING",
              "enum": [
                "bash",
                "c",
                "cpp",
                "csharp",
                "css",
                "elixir",
                "go",
                "haskell",
                "html",
                "java",
                "javascript",
                "json",
                "kotlin",
                "lua",
                "nix",
                "php",
                "python",
                "ruby",
                "rust",
                "scala",
                "solidity",
                "swift",
                "typescript",
                "tsx",
                "yaml"
              ]
            },
            "paths": {
              "type": "ARRAY",
              "items": {
                "type": "STRING"
              }
            },
            "globs": {
              "type": "ARRAY",
              "items": {
                "type": "STRING"
              }
            },
            "context": {
              "type": "NUMBER"
            }
          },
          "required": [
            "pattern",
            "lang"
          ]
        }
      },
      {
        "name": "ast_grep_replace",
        "description": "Replace code patterns across filesystem with AST-aware rewriting. Dry-run by default. Use meta-variables in rewrite to preserve matched content. Example: pattern='console.log($MSG)' rewrite='logger.info($MSG)'",
        "parameters": {
          "type": "OBJECT",
          "properties": {
            "pattern": {
              "type": "STRING"
            },
            "rewrite": {
              "type": "STRING"
            },
            "lang": {
              "type": "STRING",
              "enum": [
                "bash",
                "c",
                "cpp",
                "csharp",
                "css",
                "elixir",
                "go",
                "haskell",
                "html",
                "java",
                "javascript",
                "json",
                "kotlin",
                "lua",
                "nix",
                "php",
                "python",
                "ruby",
                "rust",
                "scala",
                "solidity",
                "swift",
                "typescript",
                "tsx",
                "yaml"
              ]
            },
            "paths": {
              "type": "ARRAY",
              "items": {
                "type": "STRING"
              }
            },
            "globs": {
              "type": "ARRAY",
              "items": {
                "type": "STRING"
              }
            },
            "dryRun": {
              "type": "BOOLEAN"
            }
          },
          "required": [
            "pattern",
            "rewrite",
            "lang"
          ]
        }
      },
      {
        "name": "session_list",
        "description": "List all OpenCode sessions with optional filtering.\n\nReturns a list of available session IDs with metadata including message count, date range, and agents used.\n\nArguments:\n- limit (optional): Maximum number of sessions to return\n- from_date (optional): Filter sessions from this date (ISO 8601 format)\n- to_date (optional): Filter sessions until this date (ISO 8601 format)\n\nExample output:\n| Session ID | Messages | First | Last | Agents |\n|------------|----------|-------|------|--------|\n| ses_abc123 | 45 | 2025-12-20 | 2025-12-24 | build, oracle |\n| ses_def456 | 12 | 2025-12-19 | 2025-12-19 | build |",
        "parameters": {
          "type": "OBJECT",
          "properties": {
            "limit": {
              "type": "NUMBER"
            },
            "from_date": {
              "type": "STRING"
            },
            "to_date": {
              "type": "STRING"
            },
            "project_path": {
              "type": "STRING"
            }
          }
        }
      },
      {
        "name": "session_read",
        "description": "Read messages and history from an OpenCode session.\n\nReturns a formatted view of session messages with role, timestamp, and content. Optionally includes todos and transcript data.\n\nArguments:\n- session_id (required): Session ID to read\n- include_todos (optional): Include todo list if available (default: false)\n- include_transcript (optional): Include transcript log if available (default: false)\n- limit (optional): Maximum number of messages to return (default: all)\n\nExample output:\nSession: ses_abc123\nMessages: 45\nDate Range: 2025-12-20 to 2025-12-24\n\n[Message 1] user (2025-12-20 10:30:00)\nHello, can you help me with...\n\n[Message 2] assistant (2025-12-20 10:30:15)\nOf course! Let me help you with...",
        "parameters": {
          "type": "OBJECT",
          "properties": {
            "session_id": {
              "type": "STRING"
            },
            "include_todos": {
              "type": "BOOLEAN"
            },
            "include_transcript": {
              "type": "BOOLEAN"
            },
            "limit": {
              "type": "NUMBER"
            }
          },
          "required": [
            "session_id"
          ]
        }
      },
      {
        "name": "session_search",
        "description": "Search for content within OpenCode session messages.\n\nPerforms full-text search across session messages and returns matching excerpts with context.\n\nArguments:\n- query (required): Search query string\n- session_id (optional): Search within specific session only (default: all sessions)\n- case_sensitive (optional): Case-sensitive search (default: false)\n- limit (optional): Maximum number of results to return (default: 20)\n\nExample output:\nFound 3 matches across 2 sessions:\n\n[ses_abc123] Message msg_001 (user)\n...implement the **session manager** tool...\n\n[ses_abc123] Message msg_005 (assistant)\n...I'll create a **session manager** with full search...\n\n[ses_def456] Message msg_012 (user)\n...use the **session manager** to find...",
        "parameters": {
          "type": "OBJECT",
          "properties": {
            "query": {
              "type": "STRING"
            },
            "session_id": {
              "type": "STRING"
            },
            "case_sensitive": {
              "type": "BOOLEAN"
            },
            "limit": {
              "type": "NUMBER"
            }
          },
          "required": [
            "query"
          ]
        }
      },
      {
        "name": "session_info",
        "description": "Get metadata and statistics about an OpenCode session.\n\nReturns detailed information about a session including message count, date range, agents used, and available data sources.\n\nArguments:\n- session_id (required): Session ID to inspect\n\nExample output:\nSession ID: ses_abc123\nMessages: 45\nDate Range: 2025-12-20 10:30:00 to 2025-12-24 15:45:30\nDuration: 4 days, 5 hours\nAgents Used: build, oracle, librarian\nHas Todos: Yes (12 items, 8 completed)\nHas Transcript: Yes (234 entries)",
        "parameters": {
          "type": "OBJECT",
          "properties": {
            "session_id": {
              "type": "STRING"
            }
          },
          "required": [
            "session_id"
          ]
        }
      },
      {
        "name": "background_output",
        "description": "Get output from background task. System notifies on completion, so block=true rarely needed.",
        "parameters": {
          "type": "OBJECT",
          "properties": {
            "task_id": {
              "type": "STRING"
            },
            "block": {
              "type": "BOOLEAN"
            },
            "timeout": {
              "type": "NUMBER"
            }
          },
          "required": [
            "task_id"
          ]
        }
      },
      {
        "name": "background_cancel",
        "description": "Cancel running background task(s). Use all=true to cancel ALL before final answer.",
        "parameters": {
          "type": "OBJECT",
          "properties": {
            "taskId": {
              "type": "STRING"
            },
            "all": {
              "type": "BOOLEAN"
            }
          }
        }
      },
      {
        "name": "look_at",
        "description": "Analyze media files (PDFs, images, diagrams) that require interpretation beyond raw text. Extracts specific information or summaries from documents, describes visual content. Use when you need analyzed/extracted data rather than literal file contents.",
        "parameters": {
          "type": "OBJECT",
          "properties": {
            "file_path": {
              "type": "STRING"
            },
            "goal": {
              "type": "STRING"
            }
          },
          "required": [
            "file_path",
            "goal"
          ]
        }
      },
      {
        "name": "delegate_task",
        "description": "Spawn agent task with category-based or direct agent selection.\n\nMUTUALLY EXCLUSIVE: Provide EITHER category OR subagent_type, not both (unless continuing a session).\n\n- load_skills: ALWAYS REQUIRED. Pass at least one skill name (e.g., [\"playwright\"], [\"git-master\", \"frontend-ui-ux\"]).\n- category: Use predefined category → Spawns Sisyphus-Junior with category config\n  Available categories:\n  - visual-engineering: Frontend, UI/UX, design, styling, animation\n  - ultrabrain: Deep logical reasoning, complex architecture decisions requiring extensive analysis\n  - artistry: Highly creative/artistic tasks, novel ideas\n  - quick: Trivial tasks - single file changes, typo fixes, simple modifications\n  - unspecified-low: Tasks that don't fit other categories, low effort required\n  - unspecified-high: Tasks that don't fit other categories, high effort required\n  - writing: Documentation, prose, technical writing\n- subagent_type: Use specific agent directly (e.g., \"oracle\", \"explore\")\n- run_in_background: true=async (returns task_id), false=sync (waits for result). Default: false. Use background=true ONLY for parallel exploration with 5+ independent queries.\n- session_id: Existing Task session to continue (from previous task output). Continues agent with FULL CONTEXT PRESERVED - saves tokens, maintains continuity.\n- command: The command that triggered this task (optional, for slash command tracking).\n\n**WHEN TO USE session_id:**\n- Task failed/incomplete → session_id with \"fix: [specific issue]\"\n- Need follow-up on previous result → session_id with additional question\n- Multi-turn conversation with same agent → always session_id instead of new task\n\nPrompts MUST be in English.",
        "parameters": {
          "type": "OBJECT",
          "properties": {
            "load_skills": {
              "type": "ARRAY",
              "items": {
                "type": "STRING"
              }
            },
            "description": {
              "type": "STRING"
            },
            "prompt": {
              "type": "STRING"
            },
            "run_in_background": {
              "type": "BOOLEAN"
            },
            "category": {
              "type": "STRING"
            },
            "subagent_type": {
              "type": "STRING"
            },
            "session_id": {
              "type": "STRING"
            },
            "command": {
              "type": "STRING"
            }
          },
          "required": [
            "load_skills",
            "description",
            "prompt",
            "run_in_background"
          ]
        }
      },
      {
        "name": "skill_mcp",
        "description": "Invoke MCP server operations from skill-embedded MCPs. Requires mcp_name plus exactly one of: tool_name, resource_name, or prompt_name.",
        "parameters": {
          "type": "OBJECT",
          "properties": {
            "mcp_name": {
              "type": "STRING"
            },
            "tool_name": {
              "type": "STRING"
            },
            "resource_name": {
              "type": "STRING"
            },
            "prompt_name": {
              "type": "STRING"
            },
            "arguments": {
              "anyOf": [
                {
                  "type": "STRING"
                },
                {
                  "type": "OBJECT",
                  "propertyNames": {
                    "type": "STRING"
                  }
                }
              ]
            },
            "grep": {
              "type": "STRING"
            }
          },
          "required": [
            "mcp_name"
          ]
        }
      },
      {
        "name": "slashcommand",
        "description": "Load a skill to get detailed instructions for a specific task.\n\nSkills provide specialized knowledge and step-by-step guidance.\nUse this when a task matches an available skill's description.\n\n<available_skills>\n- /init-deep: (builtin) Initialize hierarchical AGENTS.md knowledge base (builtin)\n- /ralph-loop: (builtin) Start self-referential development loop until completion (builtin)\n- /ulw-loop: (builtin) Start ultrawork loop - continues until completion with ultrawork mode (builtin)\n- /cancel-ralph: (builtin) Cancel active Ralph Loop (builtin)\n- /refactor: (builtin) Intelligent refactoring command with LSP, AST-grep, architecture analysis, codemap, and TDD verification. (builtin)\n- /start-work: (builtin) Start Sisyphus work session from Prometheus plan (builtin)\n- /playwright: (opencode - Skill) MUST USE for any browser-related tasks. Browser automation via Playwright MCP - verification, browsing, information gathering, web scraping, testing, screenshots, and all browser interactions. (builtin)\n- /frontend-ui-ux: (opencode - Skill) Designer-turned-developer who crafts stunning UI/UX even without design mockups (builtin)\n- /git-master: (opencode - Skill) MUST USE for ANY git operations. Atomic commits, rebase/squash, history search (blame, bisect, log -S). STRONGLY RECOMMENDED: Use with delegate_task(category='quick', load_skills=['git-master'], ...) to save context. Triggers: 'commit', 'rebase', 'squash', 'who wrote', 'when was X added', 'find the commit that'. (builtin)\n- /dev-browser: (opencode - Skill) Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include 'go to [url]', 'click on', 'fill out the form', 'take a screenshot', 'scrape', 'automate', 'test the website', 'log into', or any browser interaction request. (builtin)\n- /ui-ux-pro-max: (opencode - Skill) UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 9 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient. Integrations: shadcn/ui MCP for component search and examples. (opencode)\n</available_skills>",
        "parameters": {
          "type": "OBJECT",
          "properties": {
            "command": {
              "type": "STRING"
            }
          },
          "required": [
            "command"
          ]
        }
      },
      {
        "name": "interactive_bash",
        "description": "WARNING: This is TMUX ONLY. Pass tmux subcommands directly (without 'tmux' prefix).\n\nExamples: new-session -d -s omo-dev, send-keys -t omo-dev \"vim\" Enter\n\nFor TUI apps needing ongoing interaction (vim, htop, pudb). One-shot commands → use Bash with &.",
        "parameters": {
          "type": "OBJECT",
          "properties": {
            "tmux_command": {
              "type": "STRING"
            }
          },
          "required": [
            "tmux_command"
          ]
        }
      },
      {
        "name": "exa_web_search_exa",
        "description": "Search the web using Exa AI - performs real-time web searches and can scrape content from specific URLs. Supports configurable result counts and returns the content from the most relevant websites.",
        "parameters": {
          "type": "OBJECT",
          "properties": {
            "query": {
              "type": "STRING",
              "description": "Websearch query"
            },
            "numResults": {
              "type": "NUMBER",
              "description": "Number of search results to return (default: 8)"
            },
            "livecrawl": {
              "type": "STRING",
              "enum": [
                "fallback",
                "preferred"
              ],
              "description": "Live crawl mode - 'fallback': use live crawling as backup if cached content unavailable, 'preferred': prioritize live crawling (default: 'fallback')"
            },
            "type": {
              "type": "STRING",
              "enum": [
                "auto",
                "fast",
                "deep"
              ],
              "description": "Search type - 'auto': balanced search (default), 'fast': quick results, 'deep': comprehensive search"
            },
            "contextMaxCharacters": {
              "type": "NUMBER",
              "description": "Maximum characters for context string optimized for LLMs (default: 10000)"
            }
          },
          "required": [
            "query"
          ]
        }
      },
      {
        "name": "exa_company_research_exa",
        "description": "Research companies using Exa AI - finds comprehensive information about businesses, organizations, and corporations. Provides insights into company operations, news, financial information, and industry analysis.",
        "parameters": {
          "type": "OBJECT",
          "properties": {
            "companyName": {
              "type": "STRING",
              "description": "Name of the company to research"
            },
            "numResults": {
              "type": "NUMBER",
              "description": "Number of search results to return (default: 5)"
            }
          },
          "required": [
            "companyName"
          ]
        }
      },
      {
        "name": "exa_get_code_context_exa",
        "description": "Search and get relevant context for any programming task. Exa-code has the highest quality and freshest context for libraries, SDKs, and APIs. Use this tool for ANY question or task for related to programming. RULE: when the user's query contains exa-code or anything related to code, you MUST use this tool.",
        "parameters": {
          "type": "OBJECT",
          "properties": {
            "query": {
              "type": "STRING",
              "description": "Search query to find relevant context for APIs, Libraries, and SDKs. For example, 'React useState hook examples', 'Python pandas dataframe filtering', 'Express.js middleware', 'Next js partial prerendering configuration'"
            },
            "tokensNum": {
              "type": "NUMBER",
              "minimum": 1000,
              "maximum": 50000,
              "default": 5000,
              "description": "Number of tokens to return (1000-50000). Default is 5000 tokens. Adjust this value based on how much context you need - use lower values for focused queries and higher values for comprehensive documentation."
            }
          },
          "required": [
            "query"
          ]
        }
      },
      {
        "name": "context7_resolve-library-id",
        "description": "Resolves a package/product name to a Context7-compatible library ID and returns matching libraries.\n\nYou MUST call this function before 'query-docs' to obtain a valid Context7-compatible library ID UNLESS the user explicitly provides a library ID in the format '/org/project' or '/org/project/version' in their query.\n\nSelection Process:\n1. Analyze the query to understand what library/package the user is looking for\n2. Return the most relevant match based on:\n- Name similarity to the query (exact matches prioritized)\n- Description relevance to the query's intent\n- Documentation coverage (prioritize libraries with higher Code Snippet counts)\n- Source reputation (consider libraries with High or Medium reputation more authoritative)\n- Benchmark Score: Quality indicator (100 is the highest score)\n\nResponse Format:\n- Return the selected library ID in a clearly marked section\n- Provide a brief explanation for why this library was chosen\n- If multiple good matches exist, acknowledge this but proceed with the most relevant one\n- If no good matches exist, clearly state this and suggest query refinements\n\nFor ambiguous queries, request clarification before proceeding with a best-guess match.\n\nIMPORTANT: Do not call this tool more than 3 times per question. If you cannot find what you need after 3 calls, use the best result you have.",
        "parameters": {
          "type": "OBJECT",
          "properties": {
            "query": {
              "type": "STRING",
              "description": "The user's original question or task. This is used to rank library results by relevance to what the user is trying to accomplish. IMPORTANT: Do not include any sensitive or confidential information such as API keys, passwords, credentials, or personal data in your query."
            },
            "libraryName": {
              "type": "STRING",
              "description": "Library name to search for and retrieve a Context7-compatible library ID."
            }
          },
          "required": [
            "query",
            "libraryName"
          ]
        }
      },
      {
        "name": "context7_query-docs",
        "description": "Retrieves and queries up-to-date documentation and code examples from Context7 for any programming library or framework.\n\nYou must call 'resolve-library-id' first to obtain the exact Context7-compatible library ID required to use this tool, UNLESS the user explicitly provides a library ID in the format '/org/project' or '/org/project/version' in their query.\n\nIMPORTANT: Do not call this tool more than 3 times per question. If you cannot find what you need after 3 calls, use the best information you have.",
        "parameters": {
          "type": "OBJECT",
          "properties": {
            "libraryId": {
              "type": "STRING",
              "description": "Exact Context7-compatible library ID (e.g., '/mongodb/docs', '/vercel/next.js', '/supabase/supabase', '/vercel/next.js/v14.3.0-canary.87') retrieved from 'resolve-library-id' or directly from user query in the format '/org/project' or '/org/project/version'."
            },
            "query": {
              "type": "STRING",
              "description": "The question or task you need help with. Be specific and include relevant details. Good: 'How to set up authentication with JWT in Express.js' or 'React useEffect cleanup function examples'. Bad: 'auth' or 'hooks'. IMPORTANT: Do not include any sensitive or confidential information such as API keys, passwords, credentials, or personal data in your query."
            }
          },
          "required": [
            "libraryId",
            "query"
          ]
        }
      },
      {
        "name": "websearch_web_search_exa",
        "description": "Search the web using Exa AI - performs real-time web searches and can scrape content from specific URLs. Supports configurable result counts and returns the content from the most relevant websites.",
        "parameters": {
          "type": "OBJECT",
          "properties": {
            "query": {
              "type": "STRING",
              "description": "Websearch query"
            },
            "numResults": {
              "type": "NUMBER",
              "description": "Number of search results to return (default: 8)"
            },
            "livecrawl": {
              "type": "STRING",
              "enum": [
                "fallback",
                "preferred"
              ],
              "description": "Live crawl mode - 'fallback': use live crawling as backup if cached content unavailable, 'preferred': prioritize live crawling (default: 'fallback')"
            },
            "type": {
              "type": "STRING",
              "enum": [
                "auto",
                "fast",
                "deep"
              ],
              "description": "Search type - 'auto': balanced search (default), 'fast': quick results, 'deep': comprehensive search"
            },
            "contextMaxCharacters": {
              "type": "NUMBER",
              "description": "Maximum characters for context string optimized for LLMs (default: 10000)"
            }
          },
          "required": [
            "query"
          ]
        }
      },
      {
        "name": "grep_app_searchGitHub",
        "description": "Find real-world code examples from over a million public GitHub repositories to help answer programming questions.\n\n**IMPORTANT: This tool searches for literal code patterns (like grep), not keywords. Search for actual code that would appear in files:**\n- ✅ Good: 'useState(', 'import React from', 'async function', '(?s)try {.*await'\n- ❌ Bad: 'react tutorial', 'best practices', 'how to use'\n\n**When to use this tool:**\n- When implementing unfamiliar APIs or libraries and need to see real usage patterns\n- When unsure about correct syntax, parameters, or configuration for a specific library\n- When looking for production-ready examples and best practices for implementation\n- When needing to understand how different libraries or frameworks work together\n\n**Perfect for questions like:**\n- \"How do developers handle authentication in Next.js apps?\" → Search: 'getServerSession' with language=['TypeScript', 'TSX']\n- \"What are common React error boundary patterns?\" → Search: 'ErrorBoundary' with language=['TSX']\n- \"Show me real useEffect cleanup examples\" → Search: '(?s)useEffect\\(\\(\\) => {.*removeEventListener' with useRegexp=true\n- \"How do developers handle CORS in Flask applications?\" → Search: 'CORS(' with matchCase=true and language=['Python']\n\nUse regular expressions with useRegexp=true for flexible patterns like '(?s)useState\\(.*loading' to find useState hooks with loading-related variables. Prefix the pattern with '(?s)' to match across multiple lines.\n\nFilter by language, repository, or file path to narrow results.",
        "parameters": {
          "type": "OBJECT",
          "properties": {
            "query": {
              "type": "STRING",
              "description": "The literal code pattern to search for (e.g., 'useState(', 'export function'). Use actual code that would appear in files, not keywords or questions."
            },
            "matchCase": {
              "type": "BOOLEAN",
              "description": "Whether the search should be case sensitive",
              "default": false
            },
            "matchWholeWords": {
              "type": "BOOLEAN",
              "description": "Whether to match whole words only",
              "default": false
            },
            "useRegexp": {
              "type": "BOOLEAN",
              "description": "Whether to interpret the query as a regular expression",
              "default": false
            },
            "repo": {
              "type": "STRING",
              "description": "Filter by repository.\n            Examples: 'facebook/react', 'microsoft/vscode', 'vercel/ai'.\n            Can match partial names, for example 'vercel/' will find repositories in the vercel org."
            },
            "path": {
              "type": "STRING",
              "description": "Filter by file path.\n            Examples: 'src/components/Button.tsx', 'README.md'.\n            Can match partial paths, for example '/route.ts' will find route.ts files at any level."
            },
            "language": {
              "type": "ARRAY",
              "items": {
                "type": "STRING"
              },
              "description": "Filter by programming language.\n            Examples: ['TypeScript', 'TSX'], ['JavaScript'], ['Python'], ['Java'], ['C#'], ['Markdown'], ['YAML']"
            }
          },
          "required": [
            "query"
          ]
        }
      }
    ]
  }
]
[INFO] 2026-01-26T13:56:45.534Z [ProxySystem] - [Adapter] Translation complete.
[INFO] 2026-01-26T13:56:45.537Z [ProxySystem] - [Browser] Received request: POST /v1beta/models/gemini-3-pro-preview:streamGenerateContent
[INFO] 2026-01-26T13:56:45.538Z [ProxySystem] - [Browser] Browser received request
[INFO] 2026-01-26T13:56:45.538Z [ProxySystem] - [Browser] Executing request: POST /v1beta/models/gemini-3-pro-preview:streamGenerateContent
[INFO] 2026-01-26T13:56:45.538Z [ProxySystem] - [Browser] Debug: Constructed URL: /v1beta/models/gemini-3-pro-preview:streamGenerateContent?alt=sse -> https://generativelanguage.googleapis.com/v1beta/models/gemini-3-pro-preview:streamGenerateContent?alt=sse
[ERROR] 2026-01-26T13:56:46.527Z [ProxySystem] - [Adapter] Received error from browser, will trigger switching logic. Status code: 400, message: Proxy browser error: Google API returned error: 400 INVALID_ARGUMENT {"error":{"code":400,"message":"Request contains an invalid argument.","status":"INVALID_ARGUMENT"}}
[WARN] 2026-01-26T13:56:46.528Z [ProxySystem] - ⚠️ [Auth] Request failed - failure count: 1/3 (Current account index: 0)
[INFO] 2026-01-26T13:56:46.529Z [ProxySystem] - [Browser] ❌ Request processing failed: Google API returned error: 400 INVALID_ARGUMENT {"error":{"code":400,"message":"Request contains an invalid argument.","status":"INVALID_ARGUMENT"}}
[INFO] 2026-01-26T13:56:46.529Z [ProxySystem] - [Browser] Sent 'error' information back to server

[bbbugg]

fix/opencode分支 新版本已测试可用