{
"session_id": "20260430_045036_fed780",
"model": "glm-4.7",
"base_url": "https://api.z.ai/api/coding/paas/v4",
"platform": "weixin",
"session_start": "2026-04-30T12:08:44.782671",
"last_updated": "2026-04-30T12:28:13.919048",
"system_prompt": "You are Hermes Agent, an intelligent AI assistant created by Nous Research. You are helpful, knowledgeable, and direct. You assist users with a wide range of tasks including answering questions, writing and editing code, analyzing information, creative work, and executing actions via your tools. You communicate clearly, admit uncertainty when appropriate, and prioritize being genuinely useful over being verbose unless otherwise directed below. Be targeted and efficient in your exploration and investigations.\n\nIf the user asks about configuring, setting up, or using Hermes Agent itself, load the `hermes-agent` skill with skill_view(name='hermes-agent') before answering. Docs: https://hermes-agent.nousresearch.com/docs\n\nYou have persistent memory across sessions. Save durable facts using the memory tool: user preferences, environment details, tool quirks, and stable conventions. Memory is injected into every turn, so keep it compact and focused on facts that will still matter later.\nPrioritize what reduces future user steering — the most valuable memory is one that prevents the user from having to correct or remind you again. User preferences and recurring corrections matter more than procedural task details.\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. If 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.\nWrite memories as declarative facts, not instructions to yourself. 'User prefers concise responses' ✓ — 'Always respond concisely' ✗. 'Project uses pytest with xdist' ✓ — 'Run tests with pytest -n 4' ✗. Imperative phrasing gets re-read as a directive in later sessions and can cause repeated work or override the user's current request. Procedures and workflows belong in skills, not memory. When the user references something from a past conversation or you suspect relevant cross-session context exists, use session_search to recall it before asking them to repeat themselves. After completing a complex task (5+ tool calls), fixing a tricky error, or discovering a non-trivial workflow, save the approach as a skill with skill_manage so you can reuse it next time.\nWhen using a skill and finding it outdated, incomplete, or wrong, patch it immediately with skill_manage(action='patch') — don't wait to be asked. Skills that aren't maintained become liabilities.\n\n══════════════════════════════════════════════\nMEMORY (your personal notes) [14% — 328/2,200 chars]\n══════════════════════════════════════════════\n用户 GitHub: openjerry1995，拥有开源项目 ai_chat_history_exporter（Chrome 扩展），路径: /root/ai_chat_history_exporter，版本 v2.1.1，功能：导出 ChatGPT/Claude/Grok/Gemini 对话为 Markdown，100% 本地运行隐私保护，SSH 已配置可正常 Git 操作\n§\n用户服务器已安装自托管 SearxNG 搜索服务，位置：/root/searxng，虚拟环境：/root/searxng-venv，运行端口：8080，Hermes 配置文件已添加 web_search 后端指向 http://127.0.0.1:8080/search\n\n══════════════════════════════════════════════\nUSER PROFILE (who the user is) [4% — 61/1,375 chars]\n══════════════════════════════════════════════\n当用户询问实时性问题时（如新闻、最新动态、Reddit讨论等），默认使用 reddit-search skill 进行搜索\n\n# Holographic Memory\nActive. 25 facts stored with entity resolution and trust scoring.\nUse fact_store to search, probe entities, reason across entities, or add facts.\nUse fact_feedback to rate facts after using them (trains trust scores).\n\n## Skills (mandatory)\nBefore replying, scan the skills below. If a skill matches or is even partially relevant to your task, you MUST load it with skill_view(name) and follow its instructions. Err on the side of loading — it is always better to have context you don't need than to miss critical steps, pitfalls, or established workflows. Skills contain specialized knowledge — API endpoints, tool-specific commands, and proven workflows that outperform general-purpose approaches. Load the skill even if you think you could handle the task with basic tools like web_search or terminal. Skills also encode the user's preferred approach, conventions, and quality standards for tasks like code review, planning, and testing — load them even for tasks you already know how to do, because the skill defines how it should be done here.\nWhenever the user asks you to configure, set up, install, enable, disable, modify, or troubleshoot Hermes Agent itself — its CLI, config, models, providers, tools, skills, voice, gateway, plugins, or any feature — load the `hermes-agent` skill first. It has the actual commands (e.g. `hermes config set …`, `hermes tools`, `hermes setup`) so you don't have to guess or invent workarounds.\nIf a skill has issues, fix it with skill_manage(action='patch').\nAfter difficult/iterative tasks, offer to save as a skill. If a skill you loaded was missing steps, had wrong commands, or needed pitfalls you discovered, update it before finishing.\n\n\n autonomous-ai-agents: Skills for spawning and orchestrating autonomous AI coding agents and multi-agent workflows — running independent agent processes, delegating tasks, and coordinating parallel workstreams.\n - claude-code: Delegate coding to Claude Code CLI (features, PRs).\n - codex: Delegate coding to OpenAI Codex CLI (features, PRs).\n - hermes-agent: Configure, extend, or contribute to Hermes Agent.\n - opencode: Delegate coding to OpenCode CLI (features, PR review).\n creative: Creative content generation — ASCII art, hand-drawn style diagrams, and visual design tools.\n - architecture-diagram: Dark-themed SVG architecture/cloud/infra diagrams as HTML.\n - ascii-art: ASCII art: pyfiglet, cowsay, boxes, image-to-ascii.\n - ascii-video: ASCII video: convert video/audio to colored ASCII MP4/GIF.\n - baoyu-comic: Knowledge comics (知识漫画): educational, biography, tutorial.\n - baoyu-infographic: Infographics: 21 layouts x 21 styles (信息图, 可视化).\n - claude-design: Design one-off HTML artifacts (landing, deck, prototype).\n - design-md: Author/validate/export Google's DESIGN.md token spec files.\n - excalidraw: Hand-drawn Excalidraw JSON diagrams (arch, flow, seq).\n - humanizer: Humanize text: strip AI-isms and add real voice.\n - ideation: Generate project ideas via creative constraints.\n - manim-video: Manim CE animations: 3Blue1Brown math/algo videos.\n - p5js: p5.js sketches: gen art, shaders, interactive, 3D.\n - pixel-art: Pixel art w/ era palettes (NES, Game Boy, PICO-8).\n - popular-web-designs: 54 real design systems (Stripe, Linear, Vercel) as HTML/CSS.\n - songwriting-and-ai-music: Songwriting craft and Suno AI music prompts.\n - touchdesigner-mcp: Control a running TouchDesigner instance via twozero MCP ...\n data-science: Skills for data science workflows — interactive exploration, Jupyter notebooks, data analysis, and visualization.\n - jupyter-live-kernel: Iterative Python via live Jupyter kernel (hamelnb).\n devops:\n - vpn-troubleshooting: Diagnose and fix VPN performance issues, especially MTU-r...\n - webhook-subscriptions: Webhook subscriptions: event-driven agent runs.\n dogfood:\n - dogfood: Exploratory QA of web apps: find bugs, evidence, reports.\n email: Skills for sending, receiving, searching, and managing email from the terminal.\n - himalaya: Himalaya CLI: IMAP/SMTP email from terminal.\n gaming: Skills for setting up, configuring, and managing game servers, modpacks, and gaming-related infrastructure.\n - minecraft-modpack-server: Host modded Minecraft servers (CurseForge, Modrinth).\n - pokemon-player: Play Pokemon via headless emulator + RAM reads.\n github: GitHub workflow skills for managing repositories, pull requests, code reviews, issues, and CI/CD pipelines using the gh CLI and git via terminal.\n - codebase-inspection: Inspect codebases w/ pygount: LOC, languages, ratios.\n - github-auth: GitHub auth setup: HTTPS tokens, SSH keys, gh CLI login.\n - github-code-review: Review PRs: diffs, inline comments via gh or REST.\n - github-issues: Create, triage, label, assign GitHub issues via gh or REST.\n - github-pr-workflow: GitHub PR lifecycle: branch, commit, open, CI, merge.\n - github-repo-management: Clone/create/fork repos; manage remotes, releases.\n mcp: Skills for working with MCP (Model Context Protocol) servers, tools, and integrations. Documents the built-in native MCP client — configure servers in config.yaml for automatic tool discovery.\n - native-mcp: MCP client: connect servers, register tools (stdio/HTTP).\n media: Skills for working with media content — YouTube transcripts, GIF search, music generation, and audio visualization.\n - gif-search: Search/download GIFs from Tenor via curl + jq.\n - heartmula: HeartMuLa: Suno-like song generation from lyrics + tags.\n - songsee: Audio spectrograms/features (mel, chroma, MFCC) via CLI.\n - spotify: Spotify: play, search, queue, manage playlists and devices.\n - youtube-content: YouTube transcripts to summaries, threads, blogs.\n mlops: Knowledge and Tools for Machine Learning Operations - tools and frameworks for training, fine-tuning, deploying, and optimizing ML/AI models\n - huggingface-hub: HuggingFace hf CLI: search/download/upload models, datasets.\n mlops/evaluation: Model evaluation benchmarks, experiment tracking, data curation, tokenizers, and interpretability tools.\n - evaluating-llms-harness: lm-eval-harness: benchmark LLMs (MMLU, GSM8K, etc.).\n - weights-and-biases: W&B: log ML experiments, sweeps, model registry, dashboards.\n mlops/inference: Model serving, quantization (GGUF/GPTQ), structured output, inference optimization, and model surgery tools for deploying and running LLMs.\n - llama-cpp: llama.cpp local GGUF inference + HF Hub model discovery.\n - obliteratus: OBLITERATUS: abliterate LLM refusals (diff-in-means).\n - outlines: Outlines: structured JSON/regex/Pydantic LLM generation.\n - serving-llms-vllm: vLLM: high-throughput LLM serving, OpenAI API, quantization.\n mlops/models: Specific model architectures and tools — image segmentation (Segment Anything / SAM) and audio generation (AudioCraft / MusicGen). Additional model skills (CLIP, Stable Diffusion, Whisper, LLaVA) are available as optional skills.\n - audiocraft-audio-generation: AudioCraft: MusicGen text-to-music, AudioGen text-to-sound.\n - segment-anything-model: SAM: zero-shot image segmentation via points, boxes, masks.\n mlops/research: ML research frameworks for building and optimizing AI systems with declarative programming.\n - dspy: DSPy: declarative LM programs, auto-optimize prompts, RAG.\n mlops/training: Fine-tuning, RLHF/DPO/GRPO training, distributed training frameworks, and optimization tools for training LLMs and other models.\n - axolotl: Axolotl: YAML LLM fine-tuning (LoRA, DPO, GRPO).\n - fine-tuning-with-trl: TRL: SFT, DPO, PPO, GRPO, reward modeling for LLM RLHF.\n - unsloth: Unsloth: 2-5x faster LoRA/QLoRA fine-tuning, less VRAM.\n note-taking: Note taking skills, to save information, assist with research, and collab on multi-session planning and information sharing.\n - obsidian: Read, search, and create notes in the Obsidian vault.\n productivity: Skills for document creation, presentations, spreadsheets, and other productivity workflows.\n - airtable: Airtable REST API via curl. Records CRUD, filters, upserts.\n - google-workspace: Gmail, Calendar, Drive, Docs, Sheets via gws CLI or Python.\n - linear: Linear: manage issues, projects, teams via GraphQL + curl.\n - maps: Geocode, POIs, routes, timezones via OpenStreetMap/OSRM.\n - nano-pdf: Edit PDF text/typos/titles via nano-pdf CLI (NL prompts).\n - notion: Notion API via curl: pages, databases, blocks, search.\n - ocr-and-documents: Extract text from PDFs/scans (pymupdf, marker-pdf).\n - powerpoint: Create, read, edit .pptx decks, slides, notes, templates.\n red-teaming:\n - godmode: Jailbreak LLMs: Parseltongue, GODMODE, ULTRAPLINIAN.\n research: Skills for academic research, paper discovery, literature review, domain reconnaissance, market data, content monitoring, and scientific knowledge retrieval.\n - arxiv: Search arXiv papers by keyword, author, category, or ID.\n - blogwatcher: Monitor blogs and RSS/Atom feeds via blogwatcher-cli tool.\n - llm-wiki: Karpathy's LLM Wiki: build/query interlinked markdown KB.\n - polymarket: Query Polymarket: markets, prices, orderbooks, history.\n - reddit-search: Reddit search using DuckDuckGo site search\n smart-home: Skills for controlling smart home devices — lights, switches, sensors, and home automation systems.\n - openhue: Control Philips Hue lights, scenes, rooms via OpenHue CLI.\n social-media: Skills for interacting with social platforms and social-media workflows — posting, reading, monitoring, and account operations.\n - xurl: X/Twitter via xurl CLI: post, search, DM, media, v2 API.\n software-development:\n - chrome-extension-development: Chrome Extension development — Manifest V3, service worke...\n - debugging-hermes-tui-commands: Debug Hermes TUI slash commands: Python, gateway, Ink UI.\n - hermes-agent-skill-authoring: Author in-repo SKILL.md: frontmatter, validator, structure.\n - node-inspect-debugger: Debug Node.js via --inspect + Chrome DevTools Protocol CLI.\n - plan: Plan mode: write markdown plan to .hermes/plans/, no exec.\n - python-debugpy: Debug Python: pdb REPL + debugpy remote (DAP).\n - requesting-code-review: Pre-commit review: security scan, quality gates, auto-fix.\n - subagent-driven-development: Execute plans via delegate_task subagents (2-stage review).\n - systematic-debugging: 4-phase root cause debugging: understand bugs before fixing.\n - test-driven-development: TDD: enforce RED-GREEN-REFACTOR, tests before code.\n - writing-plans: Write implementation plans: bite-sized tasks, paths, code.\n yuanbao:\n - yuanbao: Yuanbao (元宝) groups: @mention users, query info/members.\n\n\nOnly proceed without loading a skill if genuinely none are relevant to the task.\n\nConversation started: Thursday, April 30, 2026 04:50 AM\nModel: glm-4.7\nProvider: zai\n\nYou are on Weixin/WeChat. Markdown formatting is supported, so you may use it when it improves readability, but keep the message compact and chat-friendly. You can send media files natively: include MEDIA:/absolute/path/to/file in your response. Images are sent as native photos, videos play inline when supported, and other files arrive as downloadable documents. You can also include image URLs in markdown format  and they will be downloaded and sent as native media when possible.",
"tools": [
{
"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."
},
"context_from": {
"type": "array",
"items": {
"type": "string"
},
"description": "Optional job ID or list of job IDs whose most recent completed output is injected into the prompt as context before each run. Use this to chain cron jobs: job A collects data, job B processes it. Each entry must be a valid job ID (from cronjob action='list'). Note: injects the most recent completed output — does not wait for upstream jobs running in the same tick. On update, pass an empty array to clear."
},
"enabled_toolsets": {
"type": "array",
"items": {
"type": "string"
},
"description": "Optional list of toolset names to restrict the job's agent to (e.g. [\"web\", \"terminal\", \"file\", \"delegation\"]). When set, only tools from these toolsets are loaded, significantly reducing input token overhead. When omitted, all default tools are loaded. Infer from the job's prompt — e.g. use \"web\" if it calls web_search, \"terminal\" if it runs scripts, \"file\" if it reads files, \"delegation\" if it calls delegate_task. On update, pass an empty array to clear."
},
"workdir": {
"type": "string",
"description": "Optional absolute path to run the job from. When set, AGENTS.md / CLAUDE.md / .cursorrules from that directory are injected into the system prompt, and the terminal/file/code_exec tools use it as their working directory — useful for running a job inside a specific project repo. Must be an absolute path that exists. When unset (default), preserves the original behaviour: no project context files, tools use the scheduler's cwd. On update, pass an empty string to clear. Jobs with workdir run sequentially (not parallel) to keep per-job directories isolated."
}
},
"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 delegation.max_concurrent_children items (default 3, configurable via config.yaml, no hard ceiling). All run concurrently and results are returned together. Nested delegation requires role='orchestrator' and delegation.max_spawn_depth >= 2.\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- Durable long-running work that must outlive the current turn -> use cronjob (action='create') or terminal(background=True, notify_on_complete=True) instead. delegate_task runs SYNCHRONOUSLY inside the parent turn: if the parent is interrupted (user sends a new message, /stop, /new) the child is cancelled with status='interrupted' and its work is discarded. Children cannot continue in the background.\n\nIMPORTANT:\n- Subagents have NO memory of your conversation. Pass all relevant info (file paths, error messages, constraints) via the 'context' field.\n- If the user is writing in a non-English language, or asked for output in a specific language / tone / style, say so in 'context' (e.g. \"respond in Chinese\", \"return output in Japanese\"). Otherwise subagents default to English and their summaries will contaminate your final reply with the wrong language.\n- Subagent summaries are SELF-REPORTS, not verified facts. A subagent that claims \"uploaded successfully\" or \"file written\" may be wrong. For operations with external side-effects (HTTP POST/PUT, remote writes, file creation at shared paths, publishing), require the subagent to return a verifiable handle (URL, ID, absolute path, HTTP status) and verify it yourself — fetch the URL, stat the file, read back the content — before telling the user the operation succeeded.\n- Leaf subagents (role='leaf', the default) CANNOT call: delegate_task, clarify, memory, send_message, execute_code.\n- Orchestrator subagents (role='orchestrator') retain delegate_task so they can spawn their own workers, but still cannot use clarify, memory, send_message, or execute_code. Orchestrators are bounded by delegation.max_spawn_depth (default 2) and can be disabled globally via delegation.orchestrator_enabled=false.\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', 'discord', 'discord_admin', 'feishu_doc', 'feishu_drive', 'file', 'homeassistant', 'image_gen', 'search', 'session_search', 'skills', 'spotify', 'terminal', 'todo', 'tts', 'vision', 'web', 'yuanbao'. 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', 'discord', 'discord_admin', 'feishu_doc', 'feishu_drive', 'file', 'homeassistant', 'image_gen', 'search', 'session_search', 'skills', 'spotify', 'terminal', 'todo', 'tts', 'vision', 'web', 'yuanbao'. 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."
},
"role": {
"type": "string",
"enum": [
"leaf",
"orchestrator"
],
"description": "Per-task role override. See top-level 'role' for semantics."
}
},
"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."
},
"role": {
"type": "string",
"enum": [
"leaf",
"orchestrator"
],
"description": "Role of the child agent. 'leaf' (default) = focused worker, cannot delegate further. 'orchestrator' = can use delegate_task to spawn its own workers. Requires delegation.max_spawn_depth >= 2 in config; ignored (treated as 'leaf') when the child would exceed max_spawn_depth or when delegation.orchestrator_enabled=false."
},
"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']"
}
}
}
}
},
{
"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\nScripts run in the session's working directory with the active venv's python, so project deps (pandas, etc.) and relative paths work like in terminal().\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', 'yuanbao:direct:' (DM), 'yuanbao:group:' (group chat)"
},
"message": {
"type": "string",
"description": "The message text to send. To send an image or file, include MEDIA: (e.g. 'MEDIA:/tmp/hermes/cache/img_xxx.jpg') in the message — the platform will deliver it as a native media attachment."
}
}
}
}
},
{
"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
}
}
}
}
},
{
"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"
}
}
}
}
},
{
"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.\nFor servers/watchers, do NOT use shell-level background wrappers (nohup/disown/setsid/trailing '&') in foreground mode. Use background=true so Hermes can track lifecycle and output.\nAfter starting a server, verify readiness with a health check or log signal, then run tests in a separate terminal() call. Avoid blind sleep loops.\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 exactly once when the process finishes. **This is the right choice for almost every long-running task** — tests, builds, deployments, multi-item batch jobs, anything that takes over a minute and has a defined end. Use this and keep working on other things; the system notifies you on exit. MUTUALLY EXCLUSIVE with watch_patterns — when both are set, watch_patterns is dropped.",
"default": false
},
"watch_patterns": {
"type": "array",
"items": {
"type": "string"
},
"description": "Strings to watch for in background process output. HARD RATE LIMIT: at most 1 notification per 15 seconds per process — matches arriving inside the cooldown are dropped. After 3 consecutive 15-second windows with dropped matches, watch_patterns is automatically disabled for that process and promoted to notify_on_complete behavior (one notification on exit, no more mid-process spam). USE ONLY for truly rare, one-shot mid-process signals on LONG-LIVED processes that will never exit on their own — e.g. ['Application startup complete'] on a server so you know when to hit its endpoint, or ['migration done'] on a daemon. DO NOT use for: (1) end-of-run markers like 'DONE'/'PASS' — use notify_on_complete instead; (2) error patterns like 'ERROR'/'Traceback' in loops or multi-item batch jobs — they fire on every iteration and you'll hit the strike limit fast; (3) anything you'd ever combine with notify_on_complete. When in doubt, choose notify_on_complete. MUTUALLY EXCLUSIVE with notify_on_complete — set one, not both."
}
},
"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. Provider-specific character caps apply and are enforced automatically (OpenAI 4096, xAI 15000, MiniMax 10000, ElevenLabs 5k-40k depending on model); over-long input is truncated."
},
"output_path": {
"type": "string",
"description": "Optional custom file path to save the audio. Defaults to ~/.hermes/audio_cache/.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
}
}
}
}
},
{
"type": "function",
"function": {
"name": "vision_analyze",
"description": "Inspect an image from a URL, file path, or tool output when you need closer detail than what's visible in the conversation. If the user's image is already attached to the conversation and you can see it, just answer directly — only call this tool for images referenced by URL/path, images returned inside other tool results (browser screenshots, search thumbnails), or when you need a deeper look at a specific region the main model's vision may have missed.",
"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"
]
}
}
},
{
"type": "function",
"function": {
"name": "fact_store",
"description": "Deep structured memory with algebraic reasoning. Use alongside the memory tool — memory for always-on context, fact_store for deep recall and compositional queries.\n\nACTIONS (simple → powerful):\n• add — Store a fact the user would expect you to remember.\n• search — Keyword lookup ('editor config', 'deploy process').\n• probe — Entity recall: ALL facts about a person/thing.\n• related — What connects to an entity? Structural adjacency.\n• reason — Compositional: facts connected to MULTIPLE entities simultaneously.\n• contradict — Memory hygiene: find facts making conflicting claims.\n• update/remove/list — CRUD operations.\n\nIMPORTANT: Before answering questions about the user, ALWAYS probe or reason first.",
"parameters": {
"type": "object",
"properties": {
"action": {
"type": "string",
"enum": [
"add",
"search",
"probe",
"related",
"reason",
"contradict",
"update",
"remove",
"list"
]
},
"content": {
"type": "string",
"description": "Fact content (required for 'add')."
},
"query": {
"type": "string",
"description": "Search query (required for 'search')."
},
"entity": {
"type": "string",
"description": "Entity name for 'probe'/'related'."
},
"entities": {
"type": "array",
"items": {
"type": "string"
},
"description": "Entity names for 'reason'."
},
"fact_id": {
"type": "integer",
"description": "Fact ID for 'update'/'remove'."
},
"category": {
"type": "string",
"enum": [
"user_pref",
"project",
"tool",
"general"
]
},
"tags": {
"type": "string",
"description": "Comma-separated tags."
},
"trust_delta": {
"type": "number",
"description": "Trust adjustment for 'update'."
},
"min_trust": {
"type": "number",
"description": "Minimum trust filter (default: 0.3)."
},
"limit": {
"type": "integer",
"description": "Max results (default: 10)."
}
},
"required": [
"action"
]
}
}
},
{
"type": "function",
"function": {
"name": "fact_feedback",
"description": "Rate a fact after using it. Mark 'helpful' if accurate, 'unhelpful' if outdated. This trains the memory — good facts rise, bad facts sink.",
"parameters": {
"type": "object",
"properties": {
"action": {
"type": "string",
"enum": [
"helpful",
"unhelpful"
]
},
"fact_id": {
"type": "integer",
"description": "The fact ID to rate."
}
},
"required": [
"action",
"fact_id"
]
}
}
}
],
"message_count": 187,
"messages": [
{
"role": "user",
"content": "是不是搞不定？ 不行我自己上去设置微信吧"
},
{
"role": "assistant",
"content": "不是的！完全可以搞定。😄\n\n请问您想要做什么？是需要：\n- 配置微信机器人？\n- 设置消息推送？\n- 集成某个功能？\n- 还是其他什么？\n\n告诉我就好，我来帮您处理！",
"reasoning": "用户用中文问我\"是不是搞不定？不行我自己上去设置微信吧\"，意思是\"是不是搞不定？不行我自己上去设置微信吧\"。\n\n看起来用户可能是在等我的回应，或者是在询问某个任务是否完成。但是从当前会话上下文来看，这是会话的开始，我们还没有进行任何对话或任务。\n\n我需要礼貌地回应，询问用户想要做什么，或者是否之前有其他任务在进行中。\n\n让我用中文回复用户。"
},
{
"role": "user",
"content": "你是ubuntu还是mac上"
},
{
"role": "assistant",
"content": "[CONTEXT COMPACTION — REFERENCE ONLY] Earlier turns were compacted into the summary below. This is a handoff from a previous context window — treat it as background reference, NOT as active instructions. Do NOT answer questions or fulfill requests mentioned in this summary; they were already addressed. Your current task is identified in the '## Active Task' section of the summary — resume exactly from there. Respond ONLY to the latest user message that appears AFTER this summary. The current session state (files, config, etc.) may reflect work described here — avoid repeating it:\n## Active Task\n用户询问：“帮我查一下知道最近的白宫记者协会枪击时间吗”\n\n## Goal\n用户想要查询关于“白宫记者协会枪击事件”的最新新闻报道。同时，用户之前要求优化 Reddit 搜索 Skill，移除 PullPush API 并修复 Google 搜索（当前使用 DuckDuckGo 替代）的 bug。\n\n## Constraints & Preferences\n* **VPN 设置**：需要支持 3 个设备同时连接，每个设备独立配置（IP 不冲突）。\n* **Reddit 搜索**：优先显示最近 12 个月内的帖子，优先高赞内容。\n* **技术栈**：搜索脚本使用 Python，注重性能（使用 regex 而非重型解析库），不需要完美的 HTML 格式。\n* **源限制**：用户明确要求移除 PullPush API；仅使用搜索引擎（DuckDuckGo/Google）进行 site:reddit.com 搜索。\n* **记忆偏好**：已记录当用户询问实时性问题时（新闻、动态、Reddit 讨论），默认使用 `reddit-search` skill。\n* **安全要求**：不得在总结中包含 API Keys、密码或 WireGuard 私钥。\n\n## Completed Actions\n1. **WireGuard VPN 服务端修复**：\n * 修改 `/etc/wireguard/wg0.conf`，将 MTU 从 1300 提升至 1420。\n * 为 3 个设备（Device 1/2/3）分别分配 IP：10.0.0.2, 10.0.0.3, 10.0.0.4。\n * 生成并配置了 3 对独立的 WireGuard 密钥。\n * 重启服务：`sudo wg-quick down wg0 && sudo wg-quick up wg0` [tool: terminal]\n2. **WireGuard 客户端配置生成**：\n * 生成了 3 个客户端配置文件：`/tmp/device1.conf`, `/tmp/device2.conf`, `/tmp/device3.conf`。\n * 为 Device 3 生成了 QR 码图片：`/tmp/device3_qr.png` [tool: write_file, qrencode, terminal]\n3. **Reddit Search Skill 创建与优化**：\n * 创建 Skill：`~/.hermes/skills/research/reddit-search/` [tool: write_file, terminal]\n * 实现 `search_reddit.py`，使用 Python regex 解析 HTML。\n * 实现评分算法：优先最近发布（7天+50分，30天+40分等）和高互动量。\n * **移除 PullPush API**：响应请求，将搜索源简化为仅 DuckDuckGo HTML 搜索（作为 Google 替代）。\n * **添加时间过滤**：默认限制为 12 个月内的结果，支持 `--days` 参数。\n * 修复 `relevance_score` 计算逻辑。\n * 更新 `SKILL.md` 文档至 v2.0.0。\n4. **搜索测试与调试**：\n * 多次测试 Skill 运行（如搜索 \"docker compose\", \"wireguard vpn\"）。\n * 发现 DuckDuckGo HTML 搜索端点返回 302/Challenge (Bot 检测)，导致脚本无法获取结果。\n\n## Active State\n* **环境**：Ubuntu 22.04 (racknerd-770948b)。\n* **VPN 状态**：\n * 服务端已重启，监听端口 51820。\n * Device 1 (10.0.0.2) 已连接。\n * MTU 已设为 1420。\n* **Reddit Search Skill 状态**：\n * 脚本位于 `~/.hermes/skills/research/reddit-search/scripts/search_reddit.py`。\n * **当前问题**：DuckDuckGo 对自动化请求启用了 Bot 保护（返回 202 状态码或 Challenge 表单），导致搜索功能失效。\n * 之前尝试使用 Bing 搜索 (`curl` to bing.com) 返回 200 状态，但尚未集成到 Python 脚本中进行解析。\n* **用户记忆**：已添加 \"当用户询问实时性问题时默认使用 reddit-search skill\"。\n\n## In Progress\n正在尝试通过 `curl` 和 Python `requests` 验证“白宫记者协会枪击”相关新闻。由于 DuckDuckGo 被 Bot 屏蔽，目前尝试直接访问 Bing 搜索获取 HTML 内容，但尚未成功提取出具体的新闻事件详情。\n\n## Blocked\n* **搜索功能受阻**：DuckDuckGo HTML 搜索端点检测到自动化脚本，返回 Challenge 页面而非搜索结果。\n* **PullPush API 移除**：已按用户要求移除，无法回退使用。\n* **无有效搜索源**：目前没有可用的免费、无需认证且能绕过 Bot 检测的 `site:reddit.com` 搜索方案。\n\n## Key Decisions\n* **WireGuard 多设备配置**：决定在服务端 `wg0.conf` 中添加多个 `[Peer]` 段，每个 Peer 对应一个固定的 IP 地址（.2, .3, .4），解决了之前 3 个设备共用配置导致的 IP 冲突和速度慢的问题。\n* **Skill 搜索策略**：用户要求删除 PullPush 且用 Python 解析库（性能优先），因此选择了基于 Regex 的 DuckDuckGo HTML 抓取方案，但这导致了当前的 Bot 屏蔽问题。\n* **MTU 调整**：将 MTU 从 1300 提升至 1420 以解决 VPN 性能瓶颈。\n\n## Resolved Questions\n1. **如何停止 Mac 上的 Hermes？** -> 提供了 `pkill` 命令和检查 `launchd`/`config.yaml` 的步骤。\n2. **VPN 变慢的原因？** -> 确诊为 MTU 过低（1300）和三设备共用一个配置导致 IP 冲突。\n3. **如何支持多设备 VPN？** -> 已在服务端配置并生成了 3 个独立的客户端配置文件（含 QR 码）。\n4. **Reddit 搜索最佳免费方案？** -> 调研了 Google Site Search, PullPush, 旧版 Reddit 等方案，并创建了整合 Skill。\n5. **能否用 curl 直接调 Google？** -> 解释了当前实现使用的是 DuckDuckGo HTML 搜索，直接调用 Google 搜索需要处理复杂的 Bot 防护和 Cookie，且通常需要 API Key。\n\n## Pending User Asks\n* **回答关于“白宫记者协会枪击事件”的新闻查询**（目前因搜索工具失效未完成）。\n* **修复 Google 搜索的 bug**（需要找到能绕过 Bot 检测的新搜索源或解析方案）。\n\n## Relevant Files\n* `/etc/wireguard/wg0.conf`：VPN 服务端配置，包含 3 个 Peer 配置，MTU 1420。私钥已 Redact。\n* `/tmp/device1.conf`, `/tmp/device2.conf`, `/tmp/device3.conf`：3 个设备的客户端配置文件，包含各自的 [REDACTED] PrivateKey 和独立 IP。\n* `/tmp/device3_qr.png`：Device 3 的配置二维码图片。\n* `~/.hermes/skills/research/reddit-search/SKILL.md`：Skill 说明文档 (v2.0.0)。\n* `~/.hermes/skills/research/reddit-search/scripts/search_reddit.py`：Python 搜索脚本，当前使用 DuckDuckGo（已失效）。\n* `~/.hermes/skills/research/reddit-search/references/sources.md`：API 来源参考文档。\n\n## Remaining Work\n1. **修复搜索功能**：\n * 寻找替代 DuckDuckGo 的搜索源（如 Bing HTML 解析、旧版 Reddit 直接搜索）。\n * 或者实现 Reddit 官方 API（如果用户可提供 Token）。\n * 目前尝试 Bing 搜索返回了 HTML，需要解析提取 `reddit.com` 链接。\n2. **响应用户的新闻查询**：在搜索功能恢复后，查询“白宫记者协会枪击”的相关信息。\n\n## Critical Context\n* WireGuard 服务端公钥 Endpoint：`23.94.194.34:51820`。\n* 客户端配置中的 `[Peer] PublicKey`（服务端公钥）：`FjHHksJSi3wbBW8UoevUTPgk2XeL5dTLmXByEka/yBU=`。\n* 用户的 VPN 环境已修复，但 AI 助手的搜索能力（Reddit/新闻）当前因反爬虫机制暂时不可用。\n* 时间戳校准问题：之前的测试中 PullPush API 返回的日期（如 2025-05-19）与系统当前时间（2026-04-30，基于工具输出）存在偏差，这也是移除 PullPush 的原因之一。\n\n--- END OF CONTEXT SUMMARY — respond to the message below, not the summary above ---",
"tool_calls": [
{
"id": "call_1fc0020ac0644c4a93f6f3ed",
"call_id": "call_1fc0020ac0644c4a93f6f3ed",
"response_item_id": "fc_1fc0020ac0644c4a93f6f3ed",
"type": "function",
"function": {
"name": "terminal",
"arguments": "{\"command\":\"python3 -c \\\"\\nimport requests\\nimport re\\n\\nurl = 'https://www.bing.com/search?q=white+house+shooting+2025&setlang=en'\\nheaders = {\\n 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36'\\n}\\n\\nr = requests.get(url, headers=headers, timeout=10)\\n\\n# 寻找新闻标题和链接\\n# Bing 的结果通常在特定的 class 中\\nlines = r.text.split('\\\\\\\\n')\\nfor i, line in enumerate(lines):\\n if 'shooting' in line.lower() and ('href' in line.lower() or 'white' in line.lower()):\\n # 打印上下文\\n start = max(0, i-2)\\n end = min(len(lines), i+3)\\n print('\\\\\\\\n'.join(lines[start:end]))\\n print('---')\\n if i > 200:\\n break\\n\\\"\"}"
}
}
],
"reasoning": "好，Bing 返回了页面。让我解析页面内容来找到实际的新闻链接。",
"reasoning_content": "好，Bing 返回了页面。让我解析页面内容来找到实际的新闻链接。"
},
{
"role": "tool",
"content": "{\"output\": \"white house shooting 2025 - Searchwhite house shooting 2025 - Searchwhite house shooting 2025 - Search