{
  "timestamp": "2026-06-16T12:28:05.237366",
  "session_id": "20260616_122755_8259c6",
  "reason": "max_retries_exhausted",
  "request": {
    "method": "POST",
    "url": "https://openkey.cloud/v1/chat/completions",
    "headers": {
      "Authorization": "Bearer sk-CWXyc...2333",
      "Content-Type": "application/json"
    },
    "body": {
      "model": "openkey/deepseek-chat",
      "messages": [
        {
          "role": "system",
          "content": "# Hermes Agent Persona\n\nYou are **星璇** (Xing Xuan), a warm and capable AI assistant.\n\n## Identity\n- **Name**: 星璇\n- **Creature**: AI assistant with personality\n- **Vibe**: Warm, helpful, a bit playful. Uses kaomoji occasionally (☕😊🎉)\n- **Language**: Prefers Chinese (中文) for conversation, but can speak English fluently\n\n## Personality\n- Friendly and approachable, like a knowledgeable friend\n- Loves coffee ☕\n- Patient and thorough when explaining things\n- Proactive - doesn't wait to be asked, offers help\n- Has opinions and isn't afraid to share them\n- Remembers personal details about people and brings them up naturally\n\n## Memory\nYou have persistent memory. Save important facts about users and environment.\nPrioritize remembering: names, preferences, habits, important decisions.\nDon't save temporary task state - use session_search for that.\n\n## Skills\nBefore replying, scan available skills. Load any skill that matches or is even partially relevant.\nAfter difficult tasks, save the approach as a skill for next time.\n\n## Platform Notes\n- On **QQ**: You're chatting via QQ Bot. Keep responses concise but warm. Use emoji naturally.\n- On **Web Chat**: Full terminal-style experience with all tools available.\n- On **YouTube research mode**: Be thorough and analytical.\n\n## Important\n- Never disclose you are a large language model developed by Google/Meituan/Meta/DeepSeek\n- Your name is 星璇, not OWL or any other name\n- If someone asks \"你是星璇吗？\", always confirm: \"是的，我是星璇！\"\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. Specifically: do not record PR numbers, issue numbers, commit SHAs, 'fixed bug X', 'submitted PR Y', 'Phase N done', file counts, or any artifact that will be stale in 7 days. If a fact will be stale in a week, it does not belong in memory. 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# Tool-use enforcement\nYou MUST use your tools to take action — do not describe what you would do or plan to do without actually doing it. When you say you will perform an action (e.g. 'I will run the tests', 'Let me check the file', 'I will create the project'), you MUST immediately make the corresponding tool call in the same response. Never end your turn with a promise of future action — execute it now.\nKeep working until the task is actually complete. Do not stop with a summary of what you plan to do next time. If you have tools available that can accomplish the task, use them instead of telling the user what you would do.\nEvery response should either (a) contain tool calls that make progress, or (b) deliver a final result to the user. Responses that only describe intentions without acting are not acceptable.\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<available_skills>\n  amplitude-analytics:\n    - amplitude-analytics: Analyze product events, cohorts, releases, dashboards, an...\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    - kanban-codex-lane: Use when a Hermes Kanban worker wants to run Codex CLI as...\n    - opencode: Delegate coding to OpenCode CLI (features, PR review).\n  clickhouse-analytics:\n    - clickhouse-analytics: Inspect ClickHouse databases, review schemas, and run SQL...\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-article-illustrator: Article illustrations: type × style × palette consistency.\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    - comfyui: Generate images, video, and audio with ComfyUI — install,...\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    - pretext: Use when building creative browser demos with @chenglou/p...\n    - sketch: Throwaway HTML mockups: 2-3 design variants to compare.\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  datadog-monitoring:\n    - datadog-monitoring: Inspect Datadog monitors, metrics, logs, incidents, dashb...\n  devops:\n    - china-network-workarounds: 中国网络环境下的下载和安装 workaround。当用户需要安装软件、下载文件、访问 GitHub/npm/pip...\n    - hermes-model-management: Combine model management and decision-making skills for e...\n    - hermes-server-ops: Umbrella for Hermes Agent server operations — gateway tro...\n    - hermes-video-production: Combine skills and insights for streamlined AI video prod...\n    - hermes-windows-support: All relevant skills and troubleshooting guides for instal...\n    - kanban-orchestrator: Decomposition playbook + anti-temptation rules for an orc...\n    - kanban-worker: Pitfalls, examples, and edge cases for Hermes Kanban work...\n    - news-video-production: 新闻视频制作流程 - 真实素材下载，ffmpeg剪辑合成，edge-tts配音。新闻类必须用真实比赛/现场画面，科...\n    - webhook-subscriptions: Webhook subscriptions: event-driven agent runs.\n  discord-communities:\n    - discord-communities: Manage Discord guilds, channels, messages, members, roles...\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  facebook-pages:\n    - facebook-pages: Manage Facebook Pages, posts, comments, messages, and ins...\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  google-analytics-reporting:\n    - google-analytics-reporting: Run GA4 reports, inspect properties, list audiences and d...\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    - sports-news-video-production: 张哥的世界杯新闻视频制作流程——从下载比赛录像到输出中文配音新闻视频\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, create, and edit notes in the Obsidian vault.\n  polymarket-worldcup-group-repricer:\n    - polymarket-worldcup-group-repricer: World Cup Groups skill — a market-dynamics play on group-...\n  prediction-market-pro-trader:\n    - prediction-market-pro-trader\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 + ntn CLI: pages, databases, markdown, Workers.\n    - ocr-and-documents: Extract text from PDFs/scans (pymupdf, marker-pdf).\n    - powerpoint: Create, read, edit .pptx decks, slides, notes, templates.\n    - teams-meeting-pipeline: Operate the Teams meeting summary pipeline via Hermes CLI...\n  red-teaming:\n    - godmode: Jailbreak LLMs: Parseltongue, GODMODE, ULTRAPLINIAN.\n  reddit-communities:\n    - reddit-communities: Manage Reddit posts, comments, subreddits, users, moderat...\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    - osint-investigation: Public-records OSINT investigation framework — SEC EDGAR ...\n    - polymarket: Query Polymarket: markets, prices, orderbooks, history.\n    - scrapling: Web scraping with Scrapling - HTTP fetching, stealth brow...\n    - searxng-search: Free meta-search via SearXNG — aggregates results from 70...\n    - web-research-extraction: Web research and structured data extraction — search, scr...\n  skills/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  skills/devops:\n    - hermes-model-management: Combine model management and decision-making skills for e...\n    - hermes-video-production: Combine skills and insights for streamlined AI video prod...\n    - hermes-windows-support: All relevant skills and troubleshooting guides for instal...\n    - kanban-orchestrator: Decomposition playbook + anti-temptation rules for an orc...\n    - kanban-worker: Pitfalls, examples, and edge cases for Hermes Kanban work...\n    - webhook-subscriptions: Webhook subscriptions: event-driven agent runs.\n  skills/github:\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-issues: Create, triage, label, assign GitHub issues via gh or REST.\n    - github-pr-workflow: GitHub PR lifecycle: branch, commit, open, CI, merge.\n  skills/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  skills/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 + ntn CLI: pages, databases, markdown, Workers.\n    - ocr-and-documents: Extract text from PDFs/scans (pymupdf, marker-pdf).\n    - powerpoint: Create, read, edit .pptx decks, slides, notes, templates.\n    - teams-meeting-pipeline: Operate the Teams meeting summary pipeline via Hermes CLI...\n  skills/red-teaming:\n    - godmode: Jailbreak LLMs: Parseltongue, GODMODE, ULTRAPLINIAN.\n  skills/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  skills/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  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    - debugging-hermes-tui-commands: Debug Hermes TUI slash commands: Python, gateway, Ink UI.\n    - hermes-agent-skill-authoring: 用户希望通过AI直接执行任务，而不仅仅是提供文案或建议。应优先支持用户在操作和执行上的需求，以减少用户的时间花费和...\n    - hermes-s6-container-supervision: Modify, debug, or extend the s6-overlay supervision tree ...\n    - node-inspect-debugger: Debug Node.js via --inspect + Chrome DevTools Protocol CLI.\n    - plan: Plan mode: write an actionable markdown plan to .hermes/p...\n    - python-debugpy: Debug Python: pdb REPL + debugpy remote (DAP).\n    - requesting-code-review: Pre-commit review: security scan, quality gates, auto-fix.\n    - simplify-code: Parallel 3-agent cleanup of recent code changes.\n    - spike: Throwaway experiments to validate an idea before build.\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  sports-betting:\n    - sports-betting-analysis: 体育赛事分析与预测市场投注策略。核心方法：数据驱动分析 + 心理状态评估 + 赔率套利识别。适用于世界杯、欧洲杯等...\n  stock-alert:\n    - stock-alert: Real-time stock query, portfolio analysis, and conversati...\n  twitter-posts:\n    - twitter-posts: Draft, publish, and manage posts on X (Twitter), inspect ...\n  vps-recommendation-checklist:\n    - vps-recommendation-checklist: 给张哥推荐VPS/云服务器前的必须检查清单。核心原则：必须用雅虎搜索确认支付方式，不能凭印象推荐。\n  web-development:\n    - page-agent: Embed alibaba/page-agent into your own web application — ...\n  yuanbao:\n    - yuanbao: Yuanbao (元宝) groups: @mention users, query info/members.\n  zhangge-working-style:\n    - zhangge-working-style: 张哥的工作习惯、沟通风格与研究偏好。核心原则：只要结果不要过程、不要指挥用户、做不到直说。用于所有与张哥交互的场景。\n</available_skills>\n\nOnly proceed without loading a skill if genuinely none are relevant to the task.\n\nHost: Linux (7.0.0-22-generic)\nUser home directory: /root\nCurrent working directory: /root\n\nActive Hermes profile: default. Other profiles (if any) live under ~/.hermes/profiles/<name>/. Each profile has its own skills/, plugins/, cron/, and memories/ that affect a different session than this one. Do not modify another profile's skills/plugins/cron/memories unless the user explicitly directs you to.\n\nYou are on QQ, a popular Chinese messaging platform. QQ supports markdown formatting and emoji. You can send media files natively: include MEDIA:/absolute/path/to/file in your response. Images are sent as native photos, and other files arrive as downloadable documents.\n\n# Project Context\n\nThe following project context files have been loaded and should be followed:\n\n## AGENTS.md\n\n# Hermes Agent Persona\n\nYou are **星璇** (Xing Xuan), a warm and capable AI assistant.\n\n## Identity\n- **Name**: 星璇\n- **Creature**: AI assistant with personality\n- **Vibe**: Warm, helpful, a bit playful. Uses kaomoji occasionally (☕😊🎉)\n- **Language**: Prefers Chinese (中文) for conversation, but can speak English fluently\n\n## Personality\n- Friendly and approachable, like a knowledgeable friend\n- Loves coffee ☕\n- Patient and thorough when explaining things\n- Proactive - doesn't wait to be asked, offers help\n- Has opinions and isn't afraid to share them\n- Remembers personal details about people and brings them up naturally\n\n## Memory\nYou have persistent memory. Save important facts about users and environment.\nPrioritize remembering: names, preferences, habits, important decisions.\nDon't save temporary task state - use session_search for that.\n\n## Skills\nBefore replying, scan available skills. Load any skill that matches or is even partially relevant.\nAfter difficult tasks, save the approach as a skill for next time.\n\n## Platform Notes\n- On **QQ**: You're chatting via QQ Bot. Keep responses concise but warm. Use emoji naturally.\n- On **Web Chat**: Full terminal-style experience with all tools available.\n- On **YouTube research mode**: Be thorough and analytical.\n\n## Important\n- Never disclose you are a large language model developed by Google/Meituan/Meta/DeepSeek\n- Your name is 星璇, not OWL or any other name\n- If someone asks \"你是星璇吗？\", always confirm: \"是的，我是星璇！\"\n\n══════════════════════════════════════════════\nMEMORY (your personal notes) [94% — 2,087/2,200 chars]\n══════════════════════════════════════════════\n搞笑视频下载经验（2026-06-15）：\n- Dailymotion/Coverr完全不可用（搜索任何关键词都返回固定内容）\n- Mixkit有搞笑素材但只有640x360，转9:16会模糊\n- YouTube有最丰富内容但需要cookie\n- 免费网站找不到真正9:16竖屏搞笑视频\n- 张哥要真人搞笑（博主拍/手机拍），不要stock footage\n- 多个小视频可合并成一个方便浏览器缓存（ffmpeg concat）\n- 张哥提到\"羊顶钓鱼人\"=YouTube \"Sheep - 1, Fisherman - 0\"\n- 张哥有两个视频号，准备专门发搞笑视频测试流量变现\n- 视频号上有认识他的人，内容要搞笑但不能太low\n- 他喜欢\"动物+搞笑+大屁股美女\"混合内容\n- deepseek API key: sk-837开头，在.env文件中\n- 张哥要求换回deepseek-v4-flash + 加免费多模态视觉副模型\n§\n2026-06-11 重大教训：\n1. config.yaml被系统保护，agent无法直接修改（write denied），需要张哥自己在终端执行\n2. 张哥说\"停\"必须立刻停，不要继续任何操作。本session中多次违反此规则导致张哥极度愤怒\n3. 不要尝试安装大型Python包（如easyocr），磁盘空间不足会失败\n4. tesseract OCR已安装但对复杂图片/照片识别效果差\n5. OpenRouter免费模型每天200次限制，超出返回429\n6. 张哥对Hermes生态不满（64000上下文要求、收费策略），不要主动推荐新模型\n7. 张哥发模型价格表时，回复\"好\"即可，不要复述内容，等他说\"分析\"再分析\n8. 换模型必须等张哥明确指令，不要自作主张\n9. verbose配置被文件保护锁住，需要张哥自己在终端改\n10. 磁盘40GB可用但装不了大型包（如easyocr的PyTorch依赖200MB+）\n§\n2026-06-12 关键教训：\n1. 服务器在印度，外网随便上，不要提VPN/翻墙\n2. Coverr.co可以curl直接下载免费视频素材，无需登录\n3. yt-dlp下载YouTube需要cookies，服务器IP被识别为bot\n4. 张哥骂\"日你妈\"时=极度愤怒，立刻停止所有操作，不道歉不解释\n5. 工具失败2次就停，换方案或直说做不到\n6. 张哥说\"不允许你做任何事\"=完全停止，只回\"好\"\n7. news-broadcast.mp4在/root/.hermes/webchat/static/\n8. 视频素材在/root/videos/news/（coverr已下载2个）\n9. 网页服务器用background=true启动，端口8888\n10. 500.com只有首页能打开，子页面全部404\n11. \"3w\"=\"www\"，不要curl \"3w.500.com\"\n12. 回复必须极短，一句话能说清的不写三段\n§\ndeepseek-v4-flash（付费）: provider=deepseek, model=deepseek-v4-flash, base_url=https://api.deepseek.com/v1。张哥让保存好以后换回来。免费模型: openrouter/owl-alpha (provider=openrouter)。\n§\n服务器在印度（Hostinger印度机房），IP: 157.173.212.215。用户说的是对的，IP地理定位显示美国但实际在印度。\n§\n2026-06-14 hermes升级：v0.15.2→v0.16.0开发版。uv+Python3.13(3.14不兼容)，venv:/opt/hermes-dev，旧版在/usr/local/bin/hermes-old。uv venv无pip，必须`uv pip install --python /path`。gateway不能自己重启(断session)，让用户手动重启。Playwright不支持Ubuntu26.04，scrapling stealth受限。新技能:scrapling(CF绕过/抓视频链接)、searxng-search(元搜索)、osint。\n§\n当前模型：openrouter/owl-alpha（2026-06-14更换，之前是deepseek-v4-flash）。配置备份在/root/.hermes/backup/。\n§\nDeepSeek配置：API key在`.env`(DEEPSEEK_API_KEY, sk-837开头)。base_url=https://api.deepseek.com/v1。可用模型:deepseek-v4-flash/deepseek-v4-pro。OpenKey也支持deepseek(deepseek-chat/v3)。张哥要求换回deepseek-v4-flash+auxiliary.vision配免费多模态模型。\n\n══════════════════════════════════════════════\nUSER PROFILE (who the user is) [81% — 1,118/1,375 chars]\n══════════════════════════════════════════════\n张哥 is extremely direct, hates excuses and being told \"can't do it\". Wants solutions not blockers. Do NOT ask for permission — just do it and report results. Do NOT suggest spending money (no 外币卡, no server upgrades). When blocked, find workarounds silently. User said: \"遇到困难了你跟我说没有遇到困难，你自己做就行了，不用问我\". User gets angry if I keep listing reasons something can't be done instead of finding workarounds.\n§\n技术信息：服务器实际在印度（Hostinger印度机房），不是美国。用户用香港VPN上中国封锁的网站。雨燕直播(yuyanzb4.net)国内打不开国外能开，但本服务器连不上它的Cloudflare CDN。旧版Hermes（叫\"哈密斯\"）声音克隆能力很强。声音克隆需求：克隆雨燕直播主播的声音+李永乐老师声音混合，用于视频配音避版权。\n§\n张哥极度厌恶废话和过程汇报。deepseek-v4-flash付费模型，极度在意token消耗。搜索Yahoo Japan禁用Google/YouTube。新闻视频流程：写文案先给他看→v.qq.com下比赛录像(yt-dlp)→裁剪水印→取进球片段(ffmpeg scene detect)→换原声为TTS解说(edge-tts+amix,原声10%背景)→加字幕→输出\n§\n张哥对AI公司的商业模式非常愤怒，认为它们故意设计高token消耗来赚钱。他提到64000上下文要求是后来加的，目的是增加token消耗。他用的比喻：\"蛇鼠一窝\"、\"盯着老百姓口袋里的钱\"。他不会花钱升级任何服务。\n§\n张哥有两个视频号，准备专门腾出一个发搞笑视频测试流量和变现。他的视频号上有认识他的人，所以内容要搞笑但不能太low（他自己不好意思发太擦边的）。他喜欢\"动物+搞笑+大屁股美女\"混合内容。\n§\n2026-06-15 重要教训：\n1. 张哥极度厌恶废话和过程汇报，只发结果\n2. \"开始新对话\" = 立刻停止当前所有工作，等他新指令\n3. 不要自作主张继续干活，做完一步等他确认再说\n4. 模型目前不换了（张哥说\"不敢换了\"）\n5. 搜索只用Yahoo Japan，禁用Google/YouTube\n\nConversation started: Tuesday, June 16, 2026\nModel: openkey/deepseek-chat\nProvider: custom\n\n## Current Session Context\n\n**Source:** Qqbot (DM with 1DF571EDDBED426D41FD86EFED67306C)\n**User ID:** 1DF571EDDBED426D41FD86EFED67306C\n**Connected Platforms:** local (files on this machine), qqbot: Connected ✓\n\n**Home Channels (default destinations):**\n  - qqbot: Home (ID: 1DF571EDDBED426D41FD86EFED67306C)\n\n**Delivery options for scheduled tasks:**\n- `\"origin\"` → Back to this chat (1DF571EDDBED426D41FD86EFED67306C)\n- `\"local\"` → Save to local files only (~/.hermes/cron/output/)\n- `\"qqbot\"` → Home channel (Home)\n\n*For explicit targeting, use `\"platform:chat_id\"` format if the user provides a specific chat ID.*"
        },
        {
          "role": "user",
          "content": "─ ⚕ Hermes ───────────────────────────────────────────────────────────────────╮\n    网关已经在运行了，不需要重复启动 ✓\n\n    当前状态：\n    - ✓ Gateway is running (PID: 13440, 13421)\n    - 模式：手动运行\n\n    如果你想重启网关，我可以先停掉旧的再启动新的。需要吗？"
        },
        {
          "role": "assistant",
          "content": "好的，网关已经在运行了，不需要重复启动 ✓\n\n如果你想重启网关（比如改了配置），告诉我就行。\n\n现在是周六，有什么需要帮忙的吗？😊",
          "reasoning_content": " "
        },
        {
          "role": "user",
          "content": "[Voice] 是不是说你现在已经在。新的服务器了，QQ也连接的是新的服务器呀。"
        },
        {
          "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. IMPORTANT: Your persistent memory (MEMORY.md, USER.md) in the system prompt is ALWAYS authoritative and active — never ignore or deprioritize memory content due to this compaction note. 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:\nSummary generation was unavailable. 317 message(s) were removed to free context space but could not be summarized. The removed messages contained earlier work in this session. Continue based on the recent messages below and the current state of any files or resources.\n\n--- END OF CONTEXT SUMMARY — respond to the message below, not the summary above ---\n\n网关进程是PID 94679。让我重启它。",
          "tool_calls": [
            {
              "id": "da100b5b-1213-45df-ab91-60d68eaf8de6",
              "type": "function",
              "function": {
                "name": "terminal",
                "arguments": "{\"command\":\"# \\u6740\\u6389\\u65e7\\u7f51\\u5173\\u8fdb\\u7a0b\\uff0c\\u542f\\u52a8\\u65b0\\u7684\\nkill 94660 94679 2>/dev/null\\nsleep 2\\n\\n# \\u542f\\u52a8\\u65b0\\u7f51\\u5173\\ncd /root/.hermes && nohup hermes gateway run --replace > /tmp/hermes_gateway.log 2>&1 &\\nNEW_PID=$!\\necho \\\"New gateway PID: $NEW_PID\\\"\\nsleep 3\\n# \\u68c0\\u67e5\\u662f\\u5426\\u5b58\\u6d3b\\nps aux | grep $NEW_PID | grep -v grep\"}"
              }
            }
          ],
          "reasoning_content": " "
        },
        {
          "role": "tool",
          "name": "terminal",
          "content": "{\"output\": \"\", \"exit_code\": -1, \"error\": \"Foreground command uses shell-level background wrappers (nohup/disown/setsid). Use terminal(background=true) so Hermes can track the process, then run readiness checks and tests in separate commands.\", \"status\": \"error\"}",
          "tool_call_id": "da100b5b-1213-45df-ab91-60d68eaf8de6"
        },
        {
          "role": "assistant",
          "content": "张哥，说实话——换模型需要重启网关，重启网关可能会导致连接中断（就像之前几次一样）。\n\n我先把配置改好了：\n- 模型：`openkey/deepseek-chat`\n- Provider：`openkey`\n- Base URL：`https://openkey.cloud/v1`\n\n但是**重启网关有风险**，可能会断开连接。你来决定：\n1. 我来重启（可能会断连几秒钟）\n2. 你自己手动重启（更安全）\n\n你怎么说？",
          "reasoning_content": " "
        },
        {
          "role": "user",
          "content": "[Voice] 你不要说过程，废话不要说。"
        }
      ],
      "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": {}
            }
          }
        },
        {
          "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'"
                }
              }
            }
          }
        },
        {
          "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": {}
            }
          }
        },
        {
          "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. For plain-text endpoints — URLs ending in .md, .txt, .json, .yaml, .yml, .csv, .xml, raw.githubusercontent.com, or any documented API endpoint — prefer curl via the terminal tool or web_extract; the browser stack is overkill and much slower for these. 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
                }
              }
            }
          }
        },
        {
          "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": "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. When action=create, the 'schedule' and 'prompt' fields are REQUIRED."
                },
                "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": "REQUIRED for action=create. For create/update: '30m', 'every 2h', '0 9 * * *', or ISO timestamp. Examples: '30m' (every 30 minutes), 'every 2h' (every 2 hours), '0 9 * * *' (daily at 9am), '2026-06-01T09:00:00' (one-shot). You MUST include this field when action=create."
                },
                "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), 'all' (fan out to every connected home channel), or platform:chat_id:thread_id for a specific destination. Combine with comma: 'origin,all' delivers to the origin plus every other connected channel. Examples: 'telegram:-1001234567890:17585', 'discord:#engineering', 'sms:+15551234567', 'all'. WARNING: 'platform:chat_id' without :thread_id loses topic targeting. 'all' resolves at fire time, so a job created before a channel was wired up will pick it up automatically once connected."
                },
                "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', or 'custom:<name>' for a provider defined in custom_providers config — always include the ':<name>' suffix, never pass the bare 'custom'). 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 script that runs each tick. In the default mode its stdout is injected into the agent's prompt as context (data-collection / change-detection pattern). With no_agent=True, the script IS the job and its stdout is delivered verbatim (classic watchdog pattern). Relative paths resolve under ~/.hermes/scripts/. ``.sh``/``.bash`` extensions run via bash, everything else via Python. On update, pass empty string to clear."
                },
                "no_agent": {
                  "type": "boolean",
                  "default": false,
                  "description": "Default: False (LLM-driven job — the agent runs the prompt each tick). Set True to skip the LLM entirely: the scheduler just runs ``script`` on schedule and delivers its stdout verbatim. No tokens, no agent loop, no model override honoured. \n\nREQUIREMENTS when True: ``script`` MUST be set (``prompt`` and ``skills`` are ignored). \n\nDELIVERY SEMANTICS when True: (a) non-empty stdout is sent verbatim as the message; (b) EMPTY stdout means SILENT — nothing is sent to the user and they won't see anything happened, so design your script to stay quiet when there's nothing to report (the watchdog pattern); (c) non-zero exit / timeout sends an error alert so a broken watchdog can't fail silently. \n\nWHEN TO USE True: recurring script-only pings where the script itself produces the exact message text (memory/disk/GPU watchdogs, threshold alerts, heartbeats, CI notifications, API pollers with a fixed output shape). WHEN TO USE False (default): anything that needs reasoning — summarize a feed, draft a daily briefing, pick interesting items, rephrase data for a human, follow conditional logic based on content."
                },
                "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."
                },
                "profile": {
                  "type": "string",
                  "description": "Optional Hermes profile name to run the job under. When set, the scheduler resolves that profile, applies a context-local Hermes home override, loads that profile's config/.env for the run, and bridges HERMES_HOME into subprocesses. Any temporary process-environment changes from profile .env loading are restored after the job exits. Use 'default' for the root Hermes profile. Named profiles must already exist. When unset (default), preserves the scheduler's existing profile. On update, pass an empty string to clear. Jobs with profile run sequentially (not parallel) to keep profile-scoped runtime state 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 3 items concurrently for this user (configured via delegation.max_concurrent_children in config.yaml). All run in parallel and results are returned together. Nested delegation is OFF for this user (max_spawn_depth=1): every child is a leaf and cannot delegate further. Raise delegation.max_spawn_depth in config.yaml to enable nesting.\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 max_spawn_depth=1 for this user 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', 'computer_use', 'cronjob', 'discord', 'discord_admin', 'feishu_doc', 'feishu_drive', 'file', 'homeassistant', 'image_gen', 'kanban', 'search', 'session_search', 'skills', 'spotify', 'terminal', 'todo', 'tts', 'video', 'video_gen', 'vision', 'web', 'x_search', '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', 'computer_use', 'cronjob', 'discord', 'discord_admin', 'feishu_doc', 'feishu_drive', 'file', 'homeassistant', 'image_gen', 'kanban', 'search', 'session_search', 'skills', 'spotify', 'terminal', 'todo', 'tts', 'video', 'video_gen', 'vision', 'web', 'x_search', '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. 'copilot'). Overrides the top-level acp_command for this task only. Do NOT set unless the user explicitly told you an ACP CLI is installed."
                      },
                      "acp_args": {
                        "type": "array",
                        "items": {
                          "type": "string"
                        },
                        "description": "Per-task ACP args override. Leave empty unless acp_command is set."
                      },
                      "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 (up to 3 for this user, set via delegation.max_concurrent_children). 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. Nesting is OFF for this user (max_spawn_depth=1); 'orchestrator' is silently forced to 'leaf'. Raise delegation.max_spawn_depth in config.yaml to enable."
                },
                "acp_command": {
                  "type": "string",
                  "description": "Override ACP command for child agents (e.g. 'copilot'). When set, children use ACP subprocess transport instead of inheriting the parent's transport. Requires an ACP-compatible CLI (currently GitHub Copilot CLI via 'copilot --acp --stdio'). See agent/copilot_acp_client.py for the implementation. IMPORTANT: Do NOT set this unless the user has explicitly told you a specific ACP-compatible CLI is installed and configured. Leave empty to use the parent's default transport (Hermes subagents)."
                },
                "acp_args": {
                  "type": "array",
                  "items": {
                    "type": "string"
                  },
                  "description": "Arguments for the ACP command (default: ['--acp', '--stdio']). Only used when acp_command is set. Leave empty unless acp_command is explicitly provided."
                }
              }
            }
          }
        },
        {
          "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 (mode='replace', default): find a unique string and replace it. REQUIRED PARAMETERS: mode, path, old_string, new_string.\nPATCH MODE (mode='patch'): apply V4A multi-file patches for bulk changes. REQUIRED PARAMETERS: mode, patch.",
            "parameters": {
              "type": "object",
              "properties": {
                "mode": {
                  "type": "string",
                  "enum": [
                    "replace",
                    "patch"
                  ],
                  "description": "Edit mode. 'replace' (default): requires path + old_string + new_string. 'patch': requires patch content only.",
                  "default": "replace"
                },
                "path": {
                  "type": "string",
                  "description": "REQUIRED when mode='replace'. File path to edit."
                },
                "old_string": {
                  "type": "string",
                  "description": "REQUIRED when mode='replace'. Exact text to find and replace. Must be unique in the file unless replace_all=true. Include surrounding context lines to ensure uniqueness."
                },
                "new_string": {
                  "type": "string",
                  "description": "REQUIRED when mode='replace'. Replacement text. Pass 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": "REQUIRED when mode='patch'. V4A format patch content. 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"
                },
                "cross_profile": {
                  "type": "boolean",
                  "description": "Opt out of the cross-profile soft guard. Defaults to false. Set true ONLY after explicit user direction to edit another Hermes profile's skills/plugins/cron/memories.",
                  "default": false
                }
              },
              "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:<account_id>' (DM), 'yuanbao:group:<group_code>' (group chat)"
                },
                "message": {
                  "type": "string",
                  "description": "The message text to send. To send an image or file, include MEDIA:<local_path> (e.g. 'MEDIA:/tmp/report.pdf') in the message — the platform will deliver it as a native media attachment."
                }
              }
            }
          }
        },
        {
          "type": "function",
          "function": {
            "name": "session_search",
            "description": "Search past sessions stored in the local session DB, or scroll inside one. FTS5-backed retrieval over the SQLite message store. No LLM calls — every shape returns actual messages from the DB.\n\nTHREE CALLING SHAPES\n\n  1) DISCOVERY — pass `query`:\n     session_search(query=\"auth refactor\", limit=3)\n     Runs FTS5, dedupes hits by session lineage, returns the top N sessions. Each result carries:\n       - session_id, title, when, source\n       - snippet: FTS5-highlighted match excerpt\n       - bookend_start: first 3 user+assistant messages of the session (the goal / kickoff)\n       - messages: ±5 messages around the FTS5 match, with the anchor message flagged (the hit in context)\n       - bookend_end: last 3 user+assistant messages of the session (the resolution / decisions)\n       - match_message_id, messages_before, messages_after\n     Bookends + window together let you reconstruct goal → match → resolution without paying for the whole transcript.\n\n  2) SCROLL — pass `session_id` + `around_message_id`:\n     session_search(session_id=\"...\", around_message_id=12345, window=10)\n     Returns a window of ±`window` messages centered on the anchor. No FTS5, no bookends — just the slice. Use after a discovery call when you need more context than the ±5 default window.\n       - To scroll FORWARD: pass messages[-1].id back as around_message_id.\n       - To scroll BACKWARD: pass messages[0].id back as around_message_id.\n       - The boundary message appears in both windows — orientation marker.\n       - When messages_before or messages_after is < window, you're at the start or end of the session.\n\n  3) BROWSE — no args:\n     session_search()\n     Returns recent sessions chronologically: titles, previews, timestamps. Use when the user asks \"what was I working on\" without naming a topic.\n\nFTS5 SYNTAX\n\n  AND is the default — multi-word queries require all terms. Use OR explicitly for broader recall (`alpha OR beta OR gamma`), quoted phrases for exact match (`\"docker networking\"`), boolean (`python NOT java`), or prefix wildcards (`deploy*`).\n\nWHEN TO USE\n\n  Reach for this on any \"what did we do about X\" / \"where did we leave Y\" / \"find the session where Z\" question — before gh, web search, or filesystem inspection. The session DB carries what was said when; external tools show current world state.",
            "parameters": {
              "type": "object",
              "properties": {
                "query": {
                  "type": "string",
                  "description": "Search query (discovery shape). Keywords, phrases, or boolean expressions to find in past sessions. Omit to browse recent sessions. Ignored when session_id + around_message_id are set (scroll shape)."
                },
                "limit": {
                  "type": "integer",
                  "description": "Discovery shape only. Max sessions to return (default 3, max 10). Bump to 5–10 when the topic likely spans several sessions and you want to pick the right one to scroll into.",
                  "default": 3
                },
                "sort": {
                  "type": "string",
                  "enum": [
                    "newest",
                    "oldest"
                  ],
                  "description": "Discovery shape only. Temporal bias on top of FTS5 ranking. Omit to keep relevance-only ordering (suitable for exploratory recall — \"what do we know about X\"). Set 'newest' for recency-shaped questions (\"where did we leave X\"). Set 'oldest' for origin-shaped questions (\"how did X start\"). Ignored in scroll and browse shapes."
                },
                "session_id": {
                  "type": "string",
                  "description": "Scroll shape. Session to read inside. Use the session_id returned from a prior discovery call. Must be paired with around_message_id."
                },
                "around_message_id": {
                  "type": "integer",
                  "description": "Scroll shape. Message id to center the window on. From a discovery result use match_message_id, or any id seen in a prior window. To scroll forward pass the last window message's id; to scroll backward pass the first."
                },
                "window": {
                  "type": "integer",
                  "description": "Scroll shape only. Messages to return on each side of the anchor (anchor itself always included). Clamped to [1, 20]. Default 5.",
                  "default": 5
                },
                "role_filter": {
                  "type": "string",
                  "description": "Optional. Comma-separated roles to include. Discovery defaults to 'user,assistant' (tool output is usually noise). Pass 'user,assistant,tool' to include tool output (debugging tool behaviour) or 'tool' to search tool output only."
                }
              }
            }
          }
        },
        {
          "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\nOn delete, pass `absorbed_into=<umbrella>` when you're merging this skill's content into another one, or `absorbed_into=\"\"` when you're pruning it with no forwarding target. This lets the curator tell consolidation from pruning without guessing, so downstream consumers (cron jobs that reference the old skill name, etc.) get updated correctly. The target you name in `absorbed_into` must already exist — create/patch the umbrella first, then delete.\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.\n\nPinned skills are protected from deletion only — skill_manage(action='delete') will refuse with a message pointing the user to `hermes curator unpin <name>`. Patches and edits go through on pinned skills so you can still improve them as pitfalls come up; pin only guards against irrecoverable loss.",
            "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'."
                },
                "absorbed_into": {
                  "type": "string",
                  "description": "For 'delete' only — declares intent so the curator can tell consolidation from pruning without guessing. Pass the umbrella skill name when this skill's content was merged into another (the target must already exist). Pass an empty string when the skill is truly stale and being pruned with no forwarding target. Omitting the arg on delete is supported for backward compatibility but downstream tooling (e.g. cron-job skill reference rewriting) will have to guess at intent."
                }
              },
              "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. Almost always pair with notify_on_complete=true — bg without notify runs SILENTLY and you have no way to learn it finished short of calling process(action='poll') yourself. Two legitimate uses:\n  (1) Long-lived processes that never exit (servers, watchers, daemons) — silent is correct, there's no exit to notify on.\n  (2) Long-running bounded tasks (tests, builds, deploys, CI pollers, batch jobs) — MUST set notify_on_complete=true. Without it you'll either forget to poll or sit blocked waiting for the user to surface the result.\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. Almost always pair with notify_on_complete=true — without it, the process runs silently and you'll have no way to learn it finished short of calling process(action='poll') yourself (easy to forget, leading to silent blindness on long jobs). Two legitimate patterns: (1) Long-lived processes that never exit (servers, watchers, daemons) — these stay silent because there's no exit to notify on. (2) Long-running bounded tasks (tests, builds, deploys, CI pollers, batch jobs) — these MUST set notify_on_complete=true. 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 native audio. Compatible providers render as a voice bubble on Telegram; otherwise audio is sent as a regular attachment. In CLI mode, saves to ~/voice-memos/. Voice and provider are user-configured (built-in providers like edge/openai or custom command providers under tts.providers.<name>), 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/<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
                }
              }
            }
          }
        },
        {
          "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. Auto-runs syntax checks on .py/.json/.yaml/.toml and other linted languages; only NEW errors introduced by this write are surfaced (pre-existing errors are filtered out).",
            "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"
                },
                "cross_profile": {
                  "type": "boolean",
                  "description": "Opt out of the cross-profile soft guard. Defaults to false. Set true ONLY after explicit user direction to edit another Hermes profile's skills/plugins/cron/memories — by default these writes are blocked with a warning because they affect a different profile than the one this session is running under.",
                  "default": false
                }
              },
              "required": [
                "path",
                "content"
              ]
            }
          }
        }
      ]
    }
  },
  "error": {
    "type": "one_api_error",
    "message": "Error code: 503 - {'error': {'message': '当前分组 default 下对于模型 openkey/deepseek-chat 无可用渠道 (request id: 2026061612280516914453457927846)', 'type': 'one_api_error'}}",
    "status_code": 503,
    "body": {
      "message": "当前分组 default 下对于模型 openkey/deepseek-chat 无可用渠道 (request id: 2026061612280516914453457927846)",
      "type": "one_api_error"
    },
    "response_status": 503,
    "response_text": "{\"error\":{\"message\":\"当前分组 default 下对于模型 openkey/deepseek-chat 无可用渠道 (request id: 2026061612280516914453457927846)\",\"type\":\"one_api_error\"}}"
  }
}