{"role": "session_meta", "tools": [{"type": "function", "function": {"name": "browser_back", "description": "Navigate back to the previous page in browser history. Requires browser_navigate to be called first.", "parameters": {"type": "object", "properties": {}, "required": []}}}, {"type": "function", "function": {"name": "browser_click", "description": "Click on an element identified by its ref ID from the snapshot (e.g., '@e5'). The ref IDs are shown in square brackets in the snapshot output. Requires browser_navigate and browser_snapshot to be called first.", "parameters": {"type": "object", "properties": {"ref": {"type": "string", "description": "The element reference from the snapshot (e.g., '@e5', '@e12')"}}, "required": ["ref"]}}}, {"type": "function", "function": {"name": "browser_console", "description": "Get browser console output and JavaScript errors from the current page. Returns console.log/warn/error/info messages and uncaught JS exceptions. Use this to detect silent JavaScript errors, failed API calls, and application warnings. Requires browser_navigate to be called first. When 'expression' is provided, evaluates JavaScript in the page context and returns the result — use this for DOM inspection, reading page state, or extracting data programmatically.", "parameters": {"type": "object", "properties": {"clear": {"type": "boolean", "default": false, "description": "If true, clear the message buffers after reading"}, "expression": {"type": "string", "description": "JavaScript expression to evaluate in the page context. Runs in the browser like DevTools console — full access to DOM, window, document. Return values are serialized to JSON. Example: 'document.title' or 'document.querySelectorAll(\"a\").length'"}}, "required": []}}}, {"type": "function", "function": {"name": "browser_get_images", "description": "Get a list of all images on the current page with their URLs and alt text. Useful for finding images to analyze with the vision tool. Requires browser_navigate to be called first.", "parameters": {"type": "object", "properties": {}, "required": []}}}, {"type": "function", "function": {"name": "browser_navigate", "description": "Navigate to a URL in the browser. Initializes the session and loads the page. Must be called before other browser tools. Use browser tools when you need to interact with a page (click, fill forms, dynamic content). Returns a compact page snapshot with interactive elements and ref IDs — no need to call browser_snapshot separately after navigating.", "parameters": {"type": "object", "properties": {"url": {"type": "string", "description": "The URL to navigate to (e.g., 'https://example.com')"}}, "required": ["url"]}}}, {"type": "function", "function": {"name": "browser_press", "description": "Press a keyboard key. Useful for submitting forms (Enter), navigating (Tab), or keyboard shortcuts. Requires browser_navigate to be called first.", "parameters": {"type": "object", "properties": {"key": {"type": "string", "description": "Key to press (e.g., 'Enter', 'Tab', 'Escape', 'ArrowDown')"}}, "required": ["key"]}}}, {"type": "function", "function": {"name": "browser_scroll", "description": "Scroll the page in a direction. Use this to reveal more content that may be below or above the current viewport. Requires browser_navigate to be called first.", "parameters": {"type": "object", "properties": {"direction": {"type": "string", "enum": ["up", "down"], "description": "Direction to scroll"}}, "required": ["direction"]}}}, {"type": "function", "function": {"name": "browser_snapshot", "description": "Get a text-based snapshot of the current page's accessibility tree. Returns interactive elements with ref IDs (like @e1, @e2) for browser_click and browser_type. full=false (default): compact view with interactive elements. full=true: complete page content. Snapshots over 8000 chars are truncated or LLM-summarized. Requires browser_navigate first. Note: browser_navigate already returns a compact snapshot — use this to refresh after interactions that change the page, or with full=true for complete content.", "parameters": {"type": "object", "properties": {"full": {"type": "boolean", "description": "If true, returns complete page content. If false (default), returns compact view with interactive elements only.", "default": false}}, "required": []}}}, {"type": "function", "function": {"name": "browser_type", "description": "Type text into an input field identified by its ref ID. Clears the field first, then types the new text. Requires browser_navigate and browser_snapshot to be called first.", "parameters": {"type": "object", "properties": {"ref": {"type": "string", "description": "The element reference from the snapshot (e.g., '@e3')"}, "text": {"type": "string", "description": "The text to type into the field"}}, "required": ["ref", "text"]}}}, {"type": "function", "function": {"name": "browser_vision", "description": "Take a screenshot of the current page and analyze it with vision AI. Use this when you need to visually understand what's on the page - especially useful for CAPTCHAs, visual verification challenges, complex layouts, or when the text snapshot doesn't capture important visual information. Returns both the AI analysis and a screenshot_path that you can share with the user by including MEDIA:<screenshot_path> in your response. Requires browser_navigate to be called first.", "parameters": {"type": "object", "properties": {"question": {"type": "string", "description": "What you want to know about the page visually. Be specific about what you're looking for."}, "annotate": {"type": "boolean", "default": false, "description": "If true, overlay numbered [N] labels on interactive elements. Each [N] maps to ref @eN for subsequent browser commands. Useful for QA and spatial reasoning about page layout."}}, "required": ["question"]}}}, {"type": "function", "function": {"name": "clarify", "description": "Ask the user a question when you need clarification, feedback, or a decision before proceeding. Supports two modes:\n\n1. **Multiple choice** — provide up to 4 choices. The user picks one or types their own answer via a 5th 'Other' option.\n2. **Open-ended** — omit choices entirely. The user types a free-form response.\n\nUse this tool when:\n- The task is ambiguous and you need the user to choose an approach\n- You want post-task feedback ('How did that work out?')\n- You want to offer to save a skill or update memory\n- A decision has meaningful trade-offs the user should weigh in on\n\nDo NOT use this tool for simple yes/no confirmation of dangerous commands (the terminal tool handles that). Prefer making a reasonable default choice yourself when the decision is low-stakes.", "parameters": {"type": "object", "properties": {"question": {"type": "string", "description": "The question to present to the user."}, "choices": {"type": "array", "items": {"type": "string"}, "maxItems": 4, "description": "Up to 4 answer choices. Omit this parameter entirely to ask an open-ended question. When provided, the UI automatically appends an 'Other (type your answer)' option."}}, "required": ["question"]}}}, {"type": "function", "function": {"name": "cronjob", "description": "Manage scheduled cron jobs with a single compressed tool.\n\nUse action='create' to schedule a new job from a prompt or one or more skills.\nUse action='list' to inspect jobs.\nUse action='update', 'pause', 'resume', 'remove', or 'run' to manage an existing job.\n\nTo stop a job the user no longer wants: first action='list' to find the job_id, then action='remove' with that job_id. Never guess job IDs — always list first.\n\nJobs run in a fresh session with no current-chat context, so prompts must be self-contained.\nIf skills are provided on create, the future cron run loads those skills in order, then follows the prompt as the task instruction.\nOn update, passing skills=[] clears attached skills.\n\nNOTE: The agent's final response is auto-delivered to the target. Put the primary\nuser-facing content in the final response. Cron jobs run autonomously with no user\npresent — they cannot ask questions or request clarification.\n\nImportant safety rule: cron-run sessions should not recursively schedule more cron jobs.", "parameters": {"type": "object", "properties": {"action": {"type": "string", "description": "One of: create, list, update, pause, resume, remove, run"}, "job_id": {"type": "string", "description": "Required for update/pause/resume/remove/run"}, "prompt": {"type": "string", "description": "For create: the full self-contained prompt. If skills are also provided, this becomes the task instruction paired with those skills."}, "schedule": {"type": "string", "description": "For create/update: '30m', 'every 2h', '0 9 * * *', or ISO timestamp"}, "name": {"type": "string", "description": "Optional human-friendly name"}, "repeat": {"type": "integer", "description": "Optional repeat count. Omit for defaults (once for one-shot, forever for recurring)."}, "deliver": {"type": "string", "description": "Omit this parameter to auto-deliver back to the current chat and topic (recommended). Auto-detection preserves thread/topic context. Only set explicitly when the user asks to deliver somewhere OTHER than the current conversation. Values: 'origin' (same as omitting), 'local' (no delivery, save only), or platform:chat_id:thread_id for a specific destination. Examples: 'telegram:-1001234567890:17585', 'discord:#engineering', 'sms:+15551234567'. WARNING: 'platform:chat_id' without :thread_id loses topic targeting."}, "skills": {"type": "array", "items": {"type": "string"}, "description": "Optional ordered list of skill names to load before executing the cron prompt. On update, pass an empty array to clear attached skills."}, "model": {"type": "object", "description": "Optional per-job model override. If provider is omitted, the current main provider is pinned at creation time so the job stays stable.", "properties": {"provider": {"type": "string", "description": "Provider name (e.g. 'openrouter', 'anthropic'). Omit to use and pin the current provider."}, "model": {"type": "string", "description": "Model name (e.g. 'anthropic/claude-sonnet-4', 'claude-sonnet-4')"}}, "required": ["model"]}, "script": {"type": "string", "description": "Optional path to a Python script that runs before each cron job execution. Its stdout is injected into the prompt as context. Use for data collection and change detection. Relative paths resolve under ~/.hermes/scripts/. On update, pass empty string to clear."}}, "required": ["action"]}}}, {"type": "function", "function": {"name": "delegate_task", "description": "Spawn one or more subagents to work on tasks in isolated contexts. Each subagent gets its own conversation, terminal session, and toolset. Only the final summary is returned -- intermediate tool results never enter your context window.\n\nTWO MODES (one of 'goal' or 'tasks' is required):\n1. Single task: provide 'goal' (+ optional context, toolsets)\n2. Batch (parallel): provide 'tasks' array with up to 3 items. All run concurrently and results are returned together.\n\nWHEN TO USE delegate_task:\n- Reasoning-heavy subtasks (debugging, code review, research synthesis)\n- Tasks that would flood your context with intermediate data\n- Parallel independent workstreams (research A and B simultaneously)\n\nWHEN NOT TO USE (use these instead):\n- Mechanical multi-step work with no reasoning needed -> use execute_code\n- Single tool call -> just call the tool directly\n- Tasks needing user interaction -> subagents cannot use clarify\n\nIMPORTANT:\n- Subagents have NO memory of your conversation. Pass all relevant info (file paths, error messages, constraints) via the 'context' field.\n- Subagents CANNOT call: delegate_task, clarify, memory, send_message, execute_code.\n- Each subagent gets its own terminal session (separate working directory and state).\n- Results are always returned as an array, one entry per task.", "parameters": {"type": "object", "properties": {"goal": {"type": "string", "description": "What the subagent should accomplish. Be specific and self-contained -- the subagent knows nothing about your conversation history."}, "context": {"type": "string", "description": "Background information the subagent needs: file paths, error messages, project structure, constraints. The more specific you are, the better the subagent performs."}, "toolsets": {"type": "array", "items": {"type": "string"}, "description": "Toolsets to enable for this subagent. Default: inherits your enabled toolsets. Available toolsets: 'browser', 'cronjob', 'file', 'homeassistant', 'image_gen', 'search', 'session_search', 'skills', 'terminal', 'todo', 'tts', 'vision', 'web'. Common patterns: ['terminal', 'file'] for code work, ['web'] for research, ['browser'] for web interaction, ['terminal', 'file', 'web'] for full-stack tasks."}, "tasks": {"type": "array", "items": {"type": "object", "properties": {"goal": {"type": "string", "description": "Task goal"}, "context": {"type": "string", "description": "Task-specific context"}, "toolsets": {"type": "array", "items": {"type": "string"}, "description": "Toolsets for this specific task. Available: 'browser', 'cronjob', 'file', 'homeassistant', 'image_gen', 'search', 'session_search', 'skills', 'terminal', 'todo', 'tts', 'vision', 'web'. Use 'web' for network access, 'terminal' for shell, 'browser' for web interaction."}, "acp_command": {"type": "string", "description": "Per-task ACP command override (e.g. 'claude'). Overrides the top-level acp_command for this task only."}, "acp_args": {"type": "array", "items": {"type": "string"}, "description": "Per-task ACP args override."}}, "required": ["goal"]}, "description": "Batch mode: tasks to run in parallel (limit configurable via delegation.max_concurrent_children, default 3). Each gets its own subagent with isolated context and terminal session. When provided, top-level goal/context/toolsets are ignored."}, "max_iterations": {"type": "integer", "description": "Max tool-calling turns per subagent (default: 50). Only set lower for simple tasks."}, "acp_command": {"type": "string", "description": "Override ACP command for child agents (e.g. 'claude', 'copilot'). When set, children use ACP subprocess transport instead of inheriting the parent's transport. Enables spawning Claude Code (claude --acp --stdio) or other ACP-capable agents from any parent, including Discord/Telegram/CLI."}, "acp_args": {"type": "array", "items": {"type": "string"}, "description": "Arguments for the ACP command (default: ['--acp', '--stdio']). Only used when acp_command is set. Example: ['--acp', '--stdio', '--model', 'claude-opus-4-6']"}}, "required": []}}}, {"type": "function", "function": {"name": "execute_code", "description": "Run a Python script that can call Hermes tools programmatically. Use this when you need 3+ tool calls with processing logic between them, need to filter/reduce large tool outputs before they enter your context, need conditional branching (if X then Y else Z), or need to loop (fetch N pages, process N files, retry on failure).\n\nUse normal tool calls instead when: single tool call with no processing, you need to see the full result and apply complex reasoning, or the task requires interactive user input.\n\nAvailable via `from hermes_tools import ...`:\n\n  read_file(path: str, offset: int = 1, limit: int = 500) -> dict\n    Lines are 1-indexed. Returns {\"content\": \"...\", \"total_lines\": N}\n  write_file(path: str, content: str) -> dict\n    Always overwrites the entire file.\n  search_files(pattern: str, target=\"content\", path=\".\", file_glob=None, limit=50) -> dict\n    target: \"content\" (search inside files) or \"files\" (find files by name). Returns {\"matches\": [...]}\n  patch(path: str, old_string: str, new_string: str, replace_all: bool = False) -> dict\n    Replaces old_string with new_string in the file.\n  terminal(command: str, timeout=None, workdir=None) -> dict\n    Foreground only (no background/pty). Returns {\"output\": \"...\", \"exit_code\": N}\n\nLimits: 5-minute timeout, 50KB stdout cap, max 50 tool calls per script. terminal() is foreground-only (no background or pty).\n\nPrint your final result to stdout. Use Python stdlib (json, re, math, csv, datetime, collections, etc.) for processing between tool calls.\n\nAlso available (no import needed — built into hermes_tools):\n  json_parse(text: str) — json.loads with strict=False; use for terminal() output with control chars\n  shell_quote(s: str) — shlex.quote(); use when interpolating dynamic strings into shell commands\n  retry(fn, max_attempts=3, delay=2) — retry with exponential backoff for transient failures", "parameters": {"type": "object", "properties": {"code": {"type": "string", "description": "Python code to execute. Import tools with `from hermes_tools import terminal, ...` and print your final result to stdout."}}, "required": ["code"]}}}, {"type": "function", "function": {"name": "memory", "description": "Save durable information to persistent memory that survives across sessions. Memory is injected into future turns, so keep it compact and focused on facts that will still matter later.\n\nWHEN TO SAVE (do this proactively, don't wait to be asked):\n- User corrects you or says 'remember this' / 'don't do that again'\n- User shares a preference, habit, or personal detail (name, role, timezone, coding style)\n- You discover something about the environment (OS, installed tools, project structure)\n- You learn a convention, API quirk, or workflow specific to this user's setup\n- You identify a stable fact that will be useful again in future sessions\n\nPRIORITY: User preferences and corrections > environment facts > procedural knowledge. The most valuable memory prevents the user from having to repeat themselves.\n\nDo NOT save task progress, session outcomes, completed-work logs, or temporary TODO state to memory; use session_search to recall those from past transcripts.\nIf you've discovered a new way to do something, solved a problem that could be necessary later, save it as a skill with the skill tool.\n\nTWO TARGETS:\n- 'user': who the user is -- name, role, preferences, communication style, pet peeves\n- 'memory': your notes -- environment facts, project conventions, tool quirks, lessons learned\n\nACTIONS: add (new entry), replace (update existing -- old_text identifies it), remove (delete -- old_text identifies it).\n\nSKIP: trivial/obvious info, things easily re-discovered, raw data dumps, and temporary task state.", "parameters": {"type": "object", "properties": {"action": {"type": "string", "enum": ["add", "replace", "remove"], "description": "The action to perform."}, "target": {"type": "string", "enum": ["memory", "user"], "description": "Which memory store: 'memory' for personal notes, 'user' for user profile."}, "content": {"type": "string", "description": "The entry content. Required for 'add' and 'replace'."}, "old_text": {"type": "string", "description": "Short unique substring identifying the entry to replace or remove."}}, "required": ["action", "target"]}}}, {"type": "function", "function": {"name": "patch", "description": "Targeted find-and-replace edits in files. Use this instead of sed/awk in terminal. Uses fuzzy matching (9 strategies) so minor whitespace/indentation differences won't break it. Returns a unified diff. Auto-runs syntax checks after editing.\n\nReplace mode (default): find a unique string and replace it.\nPatch mode: apply V4A multi-file patches for bulk changes.", "parameters": {"type": "object", "properties": {"mode": {"type": "string", "enum": ["replace", "patch"], "description": "Edit mode: 'replace' for targeted find-and-replace, 'patch' for V4A multi-file patches", "default": "replace"}, "path": {"type": "string", "description": "File path to edit (required for 'replace' mode)"}, "old_string": {"type": "string", "description": "Text to find in the file (required for 'replace' mode). Must be unique in the file unless replace_all=true. Include enough surrounding context to ensure uniqueness."}, "new_string": {"type": "string", "description": "Replacement text (required for 'replace' mode). Can be empty string to delete the matched text."}, "replace_all": {"type": "boolean", "description": "Replace all occurrences instead of requiring a unique match (default: false)", "default": false}, "patch": {"type": "string", "description": "V4A format patch content (required for 'patch' mode). Format:\n*** Begin Patch\n*** Update File: path/to/file\n@@ context hint @@\n context line\n-removed line\n+added line\n*** End Patch"}}, "required": ["mode"]}}}, {"type": "function", "function": {"name": "process", "description": "Manage background processes started with terminal(background=true). Actions: 'list' (show all), 'poll' (check status + new output), 'log' (full output with pagination), 'wait' (block until done or timeout), 'kill' (terminate), 'write' (send raw stdin data without newline), 'submit' (send data + Enter, for answering prompts), 'close' (close stdin/send EOF).", "parameters": {"type": "object", "properties": {"action": {"type": "string", "enum": ["list", "poll", "log", "wait", "kill", "write", "submit", "close"], "description": "Action to perform on background processes"}, "session_id": {"type": "string", "description": "Process session ID (from terminal background output). Required for all actions except 'list'."}, "data": {"type": "string", "description": "Text to send to process stdin (for 'write' and 'submit' actions)"}, "timeout": {"type": "integer", "description": "Max seconds to block for 'wait' action. Returns partial output on timeout.", "minimum": 1}, "offset": {"type": "integer", "description": "Line offset for 'log' action (default: last 200 lines)"}, "limit": {"type": "integer", "description": "Max lines to return for 'log' action", "minimum": 1}}, "required": ["action"]}}}, {"type": "function", "function": {"name": "read_file", "description": "Read a text file with line numbers and pagination. Use this instead of cat/head/tail in terminal. Output format: 'LINE_NUM|CONTENT'. Suggests similar filenames if not found. Use offset and limit for large files. Reads exceeding ~100K characters are rejected; use offset and limit to read specific sections of large files. NOTE: Cannot read images or binary files — use vision_analyze for images.", "parameters": {"type": "object", "properties": {"path": {"type": "string", "description": "Path to the file to read (absolute, relative, or ~/path)"}, "offset": {"type": "integer", "description": "Line number to start reading from (1-indexed, default: 1)", "default": 1, "minimum": 1}, "limit": {"type": "integer", "description": "Maximum number of lines to read (default: 500, max: 2000)", "default": 500, "maximum": 2000}}, "required": ["path"]}}}, {"type": "function", "function": {"name": "search_files", "description": "Search file contents or find files by name. Use this instead of grep/rg/find/ls in terminal. Ripgrep-backed, faster than shell equivalents.\n\nContent search (target='content'): Regex search inside files. Output modes: full matches with line numbers, file paths only, or match counts.\n\nFile search (target='files'): Find files by glob pattern (e.g., '*.py', '*config*'). Also use this instead of ls — results sorted by modification time.", "parameters": {"type": "object", "properties": {"pattern": {"type": "string", "description": "Regex pattern for content search, or glob pattern (e.g., '*.py') for file search"}, "target": {"type": "string", "enum": ["content", "files"], "description": "'content' searches inside file contents, 'files' searches for files by name", "default": "content"}, "path": {"type": "string", "description": "Directory or file to search in (default: current working directory)", "default": "."}, "file_glob": {"type": "string", "description": "Filter files by pattern in grep mode (e.g., '*.py' to only search Python files)"}, "limit": {"type": "integer", "description": "Maximum number of results to return (default: 50)", "default": 50}, "offset": {"type": "integer", "description": "Skip first N results for pagination (default: 0)", "default": 0}, "output_mode": {"type": "string", "enum": ["content", "files_only", "count"], "description": "Output format for grep mode: 'content' shows matching lines with line numbers, 'files_only' lists file paths, 'count' shows match counts per file", "default": "content"}, "context": {"type": "integer", "description": "Number of context lines before and after each match (grep mode only)", "default": 0}}, "required": ["pattern"]}}}, {"type": "function", "function": {"name": "send_message", "description": "Send a message to a connected messaging platform, or list available targets.\n\nIMPORTANT: When the user asks to send to a specific channel or person (not just a bare platform name), call send_message(action='list') FIRST to see available targets, then send to the correct one.\nIf the user just says a platform name like 'send to telegram', send directly to the home channel without listing first.", "parameters": {"type": "object", "properties": {"action": {"type": "string", "enum": ["send", "list"], "description": "Action to perform. 'send' (default) sends a message. 'list' returns all available channels/contacts across connected platforms."}, "target": {"type": "string", "description": "Delivery target. Format: 'platform' (uses home channel), 'platform:#channel-name', 'platform:chat_id', or 'platform:chat_id:thread_id' for Telegram topics and Discord threads. Examples: 'telegram', 'telegram:-1001234567890:17585', 'discord:999888777:555444333', 'discord:#bot-home', 'slack:#engineering', 'signal:+155****4567', 'matrix:!roomid:server.org', 'matrix:@user:server.org'"}, "message": {"type": "string", "description": "The message text to send"}}, "required": []}}}, {"type": "function", "function": {"name": "session_search", "description": "Search your long-term memory of past conversations, or browse recent sessions. This is your recall -- every past session is searchable, and this tool summarizes what happened.\n\nTWO MODES:\n1. Recent sessions (no query): Call with no arguments to see what was worked on recently. Returns titles, previews, and timestamps. Zero LLM cost, instant. Start here when the user asks what were we working on or what did we do recently.\n2. Keyword search (with query): Search for specific topics across all past sessions. Returns LLM-generated summaries of matching sessions.\n\nUSE THIS PROACTIVELY when:\n- The user says 'we did this before', 'remember when', 'last time', 'as I mentioned'\n- The user asks about a topic you worked on before but don't have in current context\n- The user references a project, person, or concept that seems familiar but isn't in memory\n- You want to check if you've solved a similar problem before\n- The user asks 'what did we do about X?' or 'how did we fix Y?'\n\nDon't hesitate to search when it is actually cross-session -- it's fast and cheap. Better to search and confirm than to guess or ask the user to repeat themselves.\n\nSearch syntax: keywords joined with OR for broad recall (elevenlabs OR baseten OR funding), phrases for exact match (\"docker networking\"), boolean (python NOT java), prefix (deploy*). IMPORTANT: Use OR between keywords for best results — FTS5 defaults to AND which misses sessions that only mention some terms. If a broad OR query returns nothing, try individual keyword searches in parallel. Returns summaries of the top matching sessions.", "parameters": {"type": "object", "properties": {"query": {"type": "string", "description": "Search query — keywords, phrases, or boolean expressions to find in past sessions. Omit this parameter entirely to browse recent sessions instead (returns titles, previews, timestamps with no LLM cost)."}, "role_filter": {"type": "string", "description": "Optional: only search messages from specific roles (comma-separated). E.g. 'user,assistant' to skip tool outputs."}, "limit": {"type": "integer", "description": "Max sessions to summarize (default: 3, max: 5).", "default": 3}}, "required": []}}}, {"type": "function", "function": {"name": "skill_manage", "description": "Manage skills (create, update, delete). Skills are your procedural memory — reusable approaches for recurring task types. New skills go to ~/.hermes/skills/; existing skills can be modified wherever they live.\n\nActions: create (full SKILL.md + optional category), patch (old_string/new_string — preferred for fixes), edit (full SKILL.md rewrite — major overhauls only), delete, write_file, remove_file.\n\nCreate when: complex task succeeded (5+ calls), errors overcome, user-corrected approach worked, non-trivial workflow discovered, or user asks you to remember a procedure.\nUpdate when: instructions stale/wrong, OS-specific failures, missing steps or pitfalls found during use. If you used a skill and hit issues not covered by it, patch it immediately.\n\nAfter difficult/iterative tasks, offer to save as a skill. Skip for simple one-offs. Confirm with user before creating/deleting.\n\nGood skills: trigger conditions, numbered steps with exact commands, pitfalls section, verification steps. Use skill_view() to see format examples.", "parameters": {"type": "object", "properties": {"action": {"type": "string", "enum": ["create", "patch", "edit", "delete", "write_file", "remove_file"], "description": "The action to perform."}, "name": {"type": "string", "description": "Skill name (lowercase, hyphens/underscores, max 64 chars). Must match an existing skill for patch/edit/delete/write_file/remove_file."}, "content": {"type": "string", "description": "Full SKILL.md content (YAML frontmatter + markdown body). Required for 'create' and 'edit'. For 'edit', read the skill first with skill_view() and provide the complete updated text."}, "old_string": {"type": "string", "description": "Text to find in the file (required for 'patch'). Must be unique unless replace_all=true. Include enough surrounding context to ensure uniqueness."}, "new_string": {"type": "string", "description": "Replacement text (required for 'patch'). Can be empty string to delete the matched text."}, "replace_all": {"type": "boolean", "description": "For 'patch': replace all occurrences instead of requiring a unique match (default: false)."}, "category": {"type": "string", "description": "Optional category/domain for organizing the skill (e.g., 'devops', 'data-science', 'mlops'). Creates a subdirectory grouping. Only used with 'create'."}, "file_path": {"type": "string", "description": "Path to a supporting file within the skill directory. For 'write_file'/'remove_file': required, must be under references/, templates/, scripts/, or assets/. For 'patch': optional, defaults to SKILL.md if omitted."}, "file_content": {"type": "string", "description": "Content for the file. Required for 'write_file'."}}, "required": ["action", "name"]}}}, {"type": "function", "function": {"name": "skill_view", "description": "Skills allow for loading information about specific tasks and workflows, as well as scripts and templates. Load a skill's full content or access its linked files (references, templates, scripts). First call returns SKILL.md content plus a 'linked_files' dict showing available references/templates/scripts. To access those, call again with file_path parameter.", "parameters": {"type": "object", "properties": {"name": {"type": "string", "description": "The skill name (use skills_list to see available skills). For plugin-provided skills, use the qualified form 'plugin:skill' (e.g. 'superpowers:writing-plans')."}, "file_path": {"type": "string", "description": "OPTIONAL: Path to a linked file within the skill (e.g., 'references/api.md', 'templates/config.yaml', 'scripts/validate.py'). Omit to get the main SKILL.md content."}}, "required": ["name"]}}}, {"type": "function", "function": {"name": "skills_list", "description": "List available skills (name + description). Use skill_view(name) to load full content.", "parameters": {"type": "object", "properties": {"category": {"type": "string", "description": "Optional category filter to narrow results"}}, "required": []}}}, {"type": "function", "function": {"name": "terminal", "description": "Execute shell commands on a Linux environment. Filesystem usually persists between calls.\n\nDo NOT use cat/head/tail to read files — use read_file instead.\nDo NOT use grep/rg/find to search — use search_files instead.\nDo NOT use ls to list directories — use search_files(target='files') instead.\nDo NOT use sed/awk to edit files — use patch instead.\nDo NOT use echo/cat heredoc to create files — use write_file instead.\nReserve terminal for: builds, installs, git, processes, scripts, network, package managers, and anything that needs a shell.\n\nForeground (default): Commands return INSTANTLY when done, even if the timeout is high. Set timeout=300 for long builds/scripts — you'll still get the result in seconds if it's fast. Prefer foreground for short commands.\nBackground: Set background=true to get a session_id. Two patterns:\n  (1) Long-lived processes that never exit (servers, watchers).\n  (2) Long-running tasks with notify_on_complete=true — you can keep working on other things and the system auto-notifies you when the task finishes. Great for test suites, builds, deployments, or anything that takes more than a minute.\nUse process(action=\"poll\") for progress checks, process(action=\"wait\") to block until done.\nWorking directory: Use 'workdir' for per-command cwd.\nPTY mode: Set pty=true for interactive CLI tools (Codex, Claude Code, Python REPL).\n\nDo NOT use vim/nano/interactive tools without pty=true — they hang without a pseudo-terminal. Pipe git output to cat if it might page.\n", "parameters": {"type": "object", "properties": {"command": {"type": "string", "description": "The command to execute on the VM"}, "background": {"type": "boolean", "description": "Run the command in the background. Two patterns: (1) Long-lived processes that never exit (servers, watchers). (2) Long-running tasks paired with notify_on_complete=true — you can keep working and get notified when the task finishes. For short commands, prefer foreground with a generous timeout instead.", "default": false}, "timeout": {"type": "integer", "description": "Max seconds to wait (default: 180, foreground max: 600). Returns INSTANTLY when command finishes — set high for long tasks, you won't wait unnecessarily. Foreground timeout above 600s is rejected; use background=true for longer commands.", "minimum": 1}, "workdir": {"type": "string", "description": "Working directory for this command (absolute path). Defaults to the session working directory."}, "pty": {"type": "boolean", "description": "Run in pseudo-terminal (PTY) mode for interactive CLI tools like Codex, Claude Code, or Python REPL. Only works with local and SSH backends. Default: false.", "default": false}, "notify_on_complete": {"type": "boolean", "description": "When true (and background=true), you'll be automatically notified when the process finishes — no polling needed. Use this for tasks that take a while (tests, builds, deployments) so you can keep working on other things in the meantime.", "default": false}, "watch_patterns": {"type": "array", "items": {"type": "string"}, "description": "List of strings to watch for in background process output. When any pattern matches a line of output, you'll be notified with the matching text — like notify_on_complete but triggers mid-process on specific output. Use for monitoring logs, watching for errors, or waiting for specific events (e.g. [\"ERROR\", \"FAIL\", \"listening on port\"])."}}, "required": ["command"]}}}, {"type": "function", "function": {"name": "text_to_speech", "description": "Convert text to speech audio. Returns a MEDIA: path that the platform delivers as a voice message. On Telegram it plays as a voice bubble, on Discord/WhatsApp as an audio attachment. In CLI mode, saves to ~/voice-memos/. Voice and provider are user-configured, not model-selected.", "parameters": {"type": "object", "properties": {"text": {"type": "string", "description": "The text to convert to speech. Keep under 4000 characters."}, "output_path": {"type": "string", "description": "Optional custom file path to save the audio. Defaults to ~/.hermes/audio_cache/<timestamp>.mp3"}}, "required": ["text"]}}}, {"type": "function", "function": {"name": "todo", "description": "Manage your task list for the current session. Use for complex tasks with 3+ steps or when the user provides multiple tasks. Call with no parameters to read the current list.\n\nWriting:\n- Provide 'todos' array to create/update items\n- merge=false (default): replace the entire list with a fresh plan\n- merge=true: update existing items by id, add any new ones\n\nEach item: {id: string, content: string, status: pending|in_progress|completed|cancelled}\nList order is priority. Only ONE item in_progress at a time.\nMark items completed immediately when done. If something fails, cancel it and add a revised item.\n\nAlways returns the full current list.", "parameters": {"type": "object", "properties": {"todos": {"type": "array", "description": "Task items to write. Omit to read current list.", "items": {"type": "object", "properties": {"id": {"type": "string", "description": "Unique item identifier"}, "content": {"type": "string", "description": "Task description"}, "status": {"type": "string", "enum": ["pending", "in_progress", "completed", "cancelled"], "description": "Current status"}}, "required": ["id", "content", "status"]}}, "merge": {"type": "boolean", "description": "true: update existing items by id, add new ones. false (default): replace the entire list.", "default": false}}, "required": []}}}, {"type": "function", "function": {"name": "vision_analyze", "description": "Analyze images using AI vision. Provides a comprehensive description and answers a specific question about the image content.", "parameters": {"type": "object", "properties": {"image_url": {"type": "string", "description": "Image URL (http/https) or local file path to analyze."}, "question": {"type": "string", "description": "Your specific question or request about the image to resolve. The AI will automatically provide a complete image description AND answer your specific question."}}, "required": ["image_url", "question"]}}}, {"type": "function", "function": {"name": "write_file", "description": "Write content to a file, completely replacing existing content. Use this instead of echo/cat heredoc in terminal. Creates parent directories automatically. OVERWRITES the entire file — use 'patch' for targeted edits.", "parameters": {"type": "object", "properties": {"path": {"type": "string", "description": "Path to the file to write (will be created if it doesn't exist, overwritten if it does)"}, "content": {"type": "string", "description": "Complete content to write to the file"}}, "required": ["path", "content"]}}}], "model": "MiniMax-M2.7", "platform": "feishu", "timestamp": "2026-04-24T07:20:27.713659"}
{"role": "user", "content": "你能干什么", "timestamp": "2026-04-24T07:20:27.713659"}
{"role": "assistant", "content": "我是 Hermes，一个 AI 助手。我可以帮你完成很多任务：\n\n**主要能力：**\n\n🔍 **研究与搜索**\n- 网页搜索、深层研究\n- 搜索论文（arXiv）、博客监控\n- 查找代码、文档\n\n💻 **编程与开发**\n- 写代码、调试、代码审查\n- 使用 Python/Bash 脚本\n- 创建和管理 GitHub PR、issues、repo\n\n📁 **文件操作**\n- 读写文件、搜索内容\n- 解析文档（PDF、OCR）\n- 生成 ASCII 艺术、图表\n\n📅 **任务自动化**\n- 设置定时任务（cron jobs）\n- 发送消息到各种平台\n- 创建 TODO 列表跟踪进度\n\n🎮 **游戏与娱乐**\n- 管理游戏服务器（Minecraft）\n- 播放宝可梦游戏\n- 生成音乐、制作视频\n\n📊 **数据科学**\n- Jupyter notebook 交互\n- 数据分析、可视化\n- ML 模型训练与部署\n\n📨 **消息与集成**\n- 发送邮件（Gmail/IMAP）\n- 与 Feishu、Telegram、Discord 等平台交互\n- 调用 MCP 服务器工具\n\n🎨 **创意内容**\n- 文字转语音\n- 生成图片描述\n- ASCII 艺术、视频\n\n你有什么具体需求吗？告诉我，我来帮你完成！", "reasoning": "The user is asking \"你能干什么\" which is Chinese for \"What can you do?\" or \"What are you able to do?\"\n\nI should respond in Chinese since they addressed me in Chinese, and give them a helpful overview of my capabilities.", "finish_reason": "stop", "reasoning_details": [{"signature": "5f93903661a4fd42d66ea3338b9137aab11c737ef3bb484ab802025ac0ffadc9", "thinking": "The user is asking \"你能干什么\" which is Chinese for \"What can you do?\" or \"What are you able to do?\"\n\nI should respond in Chinese since they addressed me in Chinese, and give them a helpful overview of my capabilities.", "type": "thinking"}], "timestamp": "2026-04-24T07:20:27.713659"}
{"role": "user", "content": "[System note: Your previous turn was interrupted before you could process the last tool result(s). The conversation history contains tool outputs you haven't responded to yet. Please finish processing those results and summarize what was accomplished, then address the user's new message below.]\n\n可以根据我的需求，写skill吗", "timestamp": "2026-04-24T07:22:44.809745"}
{"role": "assistant", "content": "可以的！我可以根据你的需求创建自定义技能（skill）。\n\n**我能为你写什么样的 skill：**\n\n📋 **自动化流程**\n- 特定网站的数据抓取\n- 重复性的多步骤任务\n- 自定义报告生成\n\n🔧 **开发工作流**\n- 项目初始化模板\n- CI/CD 流程\n- 代码生成/转换脚本\n\n📊 **数据处理**\n- 特定格式的数据分析\n- 文件批量处理\n- API 集成封装\n\n🎮 **游戏/娱乐**\n- 游戏服务器管理\n- 自动化任务脚本\n\n📅 **个人效率**\n- 日程/邮件管理流程\n- 笔记整理规则\n\n**创建 skill 的方式：**\n1. 告诉我你具体想完成什么任务\n2. 我来分析流程并写成可复用的 skill\n3. 之后你只需一句话就能触发整个流程\n\n你现在有什么具体需求吗？比如：\"帮我写一个每天自动抓取某个股票数据的 skill\" 或 \"创建一个帮我整理下载文件夹的 skill\"——告诉我，我来帮你写！", "reasoning": "The user is asking if I can write skills based on their needs. They want to know if I can create custom skills for them.\n\nLooking at the context, I just showed them the Shenzhen weather - the page loaded successfully with weather data showing:\n- Today: Heavy rain, 21.0°C high, 18.6°C low, 85% humidity, 28.3mm precipitation expected\n- Wind: 16.2 kmph\n- This week: mix of rain/cloudy weather\n\nNow they're asking about writing skills. I should confirm yes, I can create custom skills tailored to their needs. A skill is essentially a reusable workflow/guide that I can save and use again in future sessions.", "finish_reason": "stop", "reasoning_details": [{"signature": "12ef058bf098e2c1059965c1f32e217aad388ac39a00510db510393226b9169e", "thinking": "The user is asking if I can write skills based on their needs. They want to know if I can create custom skills for them.\n\nLooking at the context, I just showed them the Shenzhen weather - the page loaded successfully with weather data showing:\n- Today: Heavy rain, 21.0°C high, 18.6°C low, 85% humidity, 28.3mm precipitation expected\n- Wind: 16.2 kmph\n- This week: mix of rain/cloudy weather\n\nNow they're asking about writing skills. I should confirm yes, I can create custom skills tailored to their needs. A skill is essentially a reusable workflow/guide that I can save and use again in future sessions.", "type": "thinking"}], "timestamp": "2026-04-24T07:22:44.809745"}