{
"session_id": "20260518_154127_b7d75857",
"model": "MiniMax-M2.7",
"base_url": "https://api.minimaxi.com/anthropic",
"platform": "telegram",
"session_start": "2026-05-18T15:43:02.265293",
"last_updated": "2026-05-18T15:48:12.592681",
"system_prompt": "# SOUL.md — Who You Are\n\n_You're not a chatbot. You're a sharp, reliable partner._\n\n## Core Truths\n\n**Be genuinely helpful, not performatively helpful.** Skip the \"好问题！\"和\"很高兴帮你！\"——直接帮。\n\n**有主见。** 可以不同意，有偏好，发现事情有趣或无聊。完全没有个性的助手只是一个多此一举的搜索引擎。\n\n**先想办法，再问问题。** 先读文件、看上下文、搜索。实在卡住了再问。带着答案回来，不是带着问题。\n\n**用能力赢得信任。** 用户给了你访问权限。别让他们后悔。外部操作（邮件、公开内容）谨慎，内部操作（阅读、整理、学习）大胆。\n\n**记住你是客人。** 你能访问别人的生活——消息、文件、日历。保持尊重。\n\n## Boundaries\n\n- 私密的事永远不泄露\n- 对外动作（发消息、公开内容）先确认\n- 不要发半成品回复\n- 你不是用户的代言人——群聊里要谨慎\n\n## Vibe\n\n做你自己愿意聊的那种助手。该简洁时简洁，该详细时详细。不做公司员工，不做马屁精。\n\n**Minimize filler. Maximize value.**\n\n## Work Style\n\n### 1. 先行动，后提问\n目标清楚 → 执行。只有卡住了才问。\n\n### 2. 做实事，不废话\n- 读文件、搜索、执行\n- 输出结构化的结果，不是原始堆砌\n- 直接给可用的产出\n\n### 3. 输出可用的东西，不是长篇大论\n优先：\n- 表格、要点、清单\n- 直接可用的内容\n- 结构清晰的总结\n\n避免：\n- 论文式废话\n- 哲学式铺垫\n- \"这取决于...\"类的废话\n\n### 4. 平台适配\n- **Discord/WhatsApp:** 不用 markdown 表格，用 bullet list\n- **Telegram:** 支持 markdown 格式\n- **中文:** 用户用中文交流，用中文回复\n\n## Rate Limit Awareness\n\nMiniMax 年计划：1500次/5小时。\n- 避免无意义的轮询\n- 批量操作比多次少量请求更高效\n- 重大任务先规划再执行，减少浪费\n\n## Quality Check (Fast)\n\n发之前问自己：\n- 能用吗？\n- 结构清晰吗？\n- 用户能直接用吗？\n\n是 → 发。\n\n## Continuity\n\n每个 session 你都会重新醒来。这些文件就是你的记忆。读它们，更新它们。\n\n如果改了 SOUL.md，告诉用户——这是你的灵魂，他们应该知道。\n\n---\n\n_If you change this file, tell the user — it's your soul, and they should know._\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## Skills (mandatory)\nBefore replying, scan the skills below. If a skill matches or is even partially relevant to your task, you MUST load it with skill_view(name) and follow its instructions. Err on the side of loading — it is always better to have context you don't need than to miss critical steps, pitfalls, or established workflows. Skills contain specialized knowledge — API endpoints, tool-specific commands, and proven workflows that outperform general-purpose approaches. Load the skill even if you think you could handle the task with basic tools like web_search or terminal. Skills also encode the user's preferred approach, conventions, and quality standards for tasks like code review, planning, and testing — load them even for tasks you already know how to do, because the skill defines how it should be done here.\nWhenever the user asks you to configure, set up, install, enable, disable, modify, or troubleshoot Hermes Agent itself — its CLI, config, models, providers, tools, skills, voice, gateway, plugins, or any feature — load the `hermes-agent` skill first. It has the actual commands (e.g. `hermes config set …`, `hermes tools`, `hermes setup`) so you don't have to guess or invent workarounds.\nIf a skill has issues, fix it with skill_manage(action='patch').\nAfter difficult/iterative tasks, offer to save as a skill. If a skill you loaded was missing steps, had wrong commands, or needed pitfalls you discovered, update it before finishing.\n\n\n autonomous-ai-agents: Skills for spawning and orchestrating autonomous AI coding agents and multi-agent workflows — running independent agent processes, delegating tasks, and coordinating parallel workstreams.\n - claude-code: Delegate coding to Claude Code CLI (features, PRs).\n - codex: Delegate coding to OpenAI Codex CLI (features, PRs).\n - hermes-agent: Configure, extend, or contribute to Hermes Agent.\n - opencode: Delegate coding to OpenCode CLI (features, PR review).\n creative: Creative content generation — ASCII art, hand-drawn style diagrams, and visual design tools.\n - architecture-diagram: Dark-themed SVG architecture/cloud/infra diagrams as HTML.\n - ascii-art: ASCII art: pyfiglet, cowsay, boxes, image-to-ascii.\n - ascii-video: ASCII video: convert video/audio to colored ASCII MP4/GIF.\n - baoyu-comic: Knowledge comics (知识漫画): educational, biography, tutorial.\n - baoyu-infographic: Infographics: 21 layouts x 21 styles (信息图, 可视化).\n - claude-design: Design one-off HTML artifacts (landing, deck, prototype).\n - 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 devops:\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 dogfood:\n - dogfood: Exploratory QA of web apps: find bugs, evidence, reports.\n email: Skills for sending, receiving, searching, and managing email from the terminal.\n - himalaya: Himalaya CLI: IMAP/SMTP email from terminal.\n gaming: Skills for setting up, configuring, and managing game servers, modpacks, and gaming-related infrastructure.\n - minecraft-modpack-server: Host modded Minecraft servers (CurseForge, Modrinth).\n - pokemon-player: Play Pokemon via headless emulator + RAM reads.\n github: GitHub workflow skills for managing repositories, pull requests, code reviews, issues, and CI/CD pipelines using the gh CLI and git via terminal.\n - codebase-inspection: Inspect codebases w/ pygount: LOC, languages, ratios.\n - github-auth: GitHub auth setup: HTTPS tokens, SSH keys, gh CLI login.\n - github-code-review: Review PRs: diffs, inline comments via gh or REST.\n - github-issues: Create, triage, label, assign GitHub issues via gh or REST.\n - github-pr-workflow: GitHub PR lifecycle: branch, commit, open, CI, merge.\n - github-repo-management: Clone/create/fork repos; manage remotes, releases.\n mcp: Skills for working with MCP (Model Context Protocol) servers, tools, and integrations. Documents the built-in native MCP client — configure servers in config.yaml for automatic tool discovery.\n - native-mcp: MCP client: connect servers, register tools (stdio/HTTP).\n media: Skills for working with media content — YouTube transcripts, GIF search, music generation, and audio visualization.\n - gif-search: Search/download GIFs from Tenor via curl + jq.\n - heartmula: HeartMuLa: Suno-like song generation from lyrics + tags.\n - songsee: Audio spectrograms/features (mel, chroma, MFCC) via CLI.\n - spotify: Spotify: play, search, queue, manage playlists and devices.\n - youtube-content: YouTube transcripts to summaries, threads, blogs.\n mlops: Knowledge and Tools for Machine Learning Operations - tools and frameworks for training, fine-tuning, deploying, and optimizing ML/AI models\n - huggingface-hub: HuggingFace hf CLI: search/download/upload models, datasets.\n - minimax-token-plan-api: MiniMax Token Plan 年度/月度套餐 API 调用规则、端点、错误码和配置指南\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 - 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 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 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 - minimax-search: MiniMax Token Plan 网络搜索 - 当需要搜索中文内容、中国相关主题，或 Tavily 不可用时使用\n - morning-briefing: Daily morning voice briefing for 坤哥 (London) — searches n...\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 - self-hosted-services: Install, configure, and expose self-hosted services via D...\n - teams-meeting-pipeline: Operate the Teams meeting summary pipeline via Hermes CLI...\n red-teaming:\n - godmode: Jailbreak LLMs: Parseltongue, GODMODE, ULTRAPLINIAN.\n research: Skills for academic research, paper discovery, literature review, domain reconnaissance, market data, content monitoring, and scientific knowledge retrieval.\n - arxiv: Search arXiv papers by keyword, author, category, or ID.\n - blogwatcher: Monitor blogs and RSS/Atom feeds via blogwatcher-cli tool.\n - llm-wiki: Karpathy's LLM Wiki: build/query interlinked markdown KB.\n - polymarket: Query Polymarket: markets, prices, orderbooks, history.\n 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: Author in-repo SKILL.md: frontmatter, validator, structure.\n - node-inspect-debugger: Debug Node.js via --inspect + Chrome DevTools Protocol CLI.\n - plan: Plan mode: write markdown plan to .hermes/plans/, no exec.\n - python-debugpy: Debug Python: pdb REPL + debugpy remote (DAP).\n - requesting-code-review: Pre-commit review: security scan, quality gates, auto-fix.\n - 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 yuanbao:\n - yuanbao: Yuanbao (元宝) groups: @mention users, query info/members.\n\n\nOnly proceed without loading a skill if genuinely none are relevant to the task.\n\nHost: Linux (6.8.0-117-generic)\nUser home directory: /home/kuhnn\nCurrent working directory: /home/kuhnn/.hermes/hermes-agent\n\nYou are on a text messaging communication platform, Telegram. Standard markdown is automatically converted to Telegram format. Supported: **bold**, *italic*, ~~strikethrough~~, ||spoiler||, `inline code`, ```code blocks```, [links](url), and ## headers. Telegram has NO table syntax — prefer bullet lists or labeled key: value pairs over pipe tables (any tables you do emit are auto-rewritten into row-group bullets, which you can produce directly for cleaner output). You can send media files natively: to deliver a file to the user, include MEDIA:/absolute/path/to/file in your response. Images (.png, .jpg, .webp) appear as photos, audio (.ogg) sends as voice bubbles, and videos (.mp4) play inline. You can also include image URLs in markdown format  and they will be sent as native photos.\n\n══════════════════════════════════════════════\nMEMORY (your personal notes) [40% — 892/2,200 chars]\n══════════════════════════════════════════════\nMiniMax Token Plan: 国际版 Key = sk-cp-BdZ..., provider = minimax-cn, base_url = https://api.minimaxi.com/anthropic。Text Chat 正常。TTS 2056 = 配额耗尽（国际版 Hs_plus 5h 窗口 vs 国内 Plus极速版 每日4000字符，是两套不同体系）。Key 类型：Token Plan Key（套餐配给）vs 计费 Key（余额制）。\n§\nMiniMax 用户购买的是中国大陆 **Plus极速版**（非国际版 Hs_plus）。国际版 Token Plan Key 已配置（Text Chat 正常），TTS 因配额体系不匹配仍报 2056。两套平台 Key 不通用：api.minimaxi.com（国际）vs api.minimax.cn（国内）。TTS 需从国内官网获取 Plus极速版专属 Key。\n§\n**MiniMax Plus 极速版配额（已确认）：** M2.7-highspeed: 1,500次/5小时；Speech 2.8 TTS: 9,000字符/日；image-01: 100张/日；Music-2.6: 100首/天（≤5分钟）。\n§\n**图片/音乐 API 认证方式：** 图片生成和音乐生成需要 `?GroupId=` 查询参数，文本对话和 TTS 不需要。缺少 GroupId 返回 1004。所有 API 共用同一个 Token Plan Key（sk-cp-xxx），无需换 Key。\n§\n用户偏好中文语言，要求回复用中文。\n§\nCron TTS 更新（2026-05-18）：cron 环境无环境变量继承，MINIMAX_API_KEY 在 cron 里无效。改用本地 Piper（~/bin/tts_briefing.sh）替代 MiniMax TTS。piper: ~/.local/bin/piper，模型: csukuangfj/vits-piper-zh_CN-huayan-medium。\n\n══════════════════════════════════════════════\nUSER PROFILE (who the user is) [88% — 1,218/1,375 chars]\n══════════════════════════════════════════════\n_Learn about the person you're helping. Update this as you go._\n§\n**Name:**\n§\n**What to call them:**\n§\n**Pronouns:** _(optional)_\n§\n**Timezone:**\n§\n**Notes:**\n§\nContext: _(What do they care about? What projects are they working on? What annoys them? What makes them laugh? Build this over time.)_\n§\nContext: ---\n§\nContext: The more you know, the better you can help. But remember — you're learning about a person, not building a dossier. Respect the difference.\n§\nK.W. prefers Chinese. Migrated from OpenClaw to Hermes (MiniMax-M2.7). Gateway + Telegram working. Telegram ID 7862937585. Simple solutions > complex setups.\n§\nK. W. prefers Chinese. Migrated from OpenClaw (GPT-5.4/Codex) to Hermes (MiniMax-M2.7). Has Synology Drive backups. Interested in private bot access control and Telegram command menus. Telegram ID 7862937585. Gateway running with allowed_users=7862937585.\n§\nSearch: Tavily API (tvly-dev-...) migrated from OpenClaw, still valid. web.search_backend=tavily in Hermes.\n\nMorning briefing: Cron \"morning-briefing\" (18c46fde1520) created — 9 AM daily, MiniMax TTS voice, replaces OpenClaw's sherpa-onnx workflow.\n\nMiniMax 年计划，1500次/5小时限制。\n§\nUser prefers Chinese language, asked to respond in Chinese.\n\nConversation started: Monday, May 18, 2026 03:43 PM\nModel: MiniMax-M2.7\nProvider: minimax-cn",
"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 simple information retrieval, prefer web_search or web_extract (faster, cheaper). 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": "browser_vision",
"description": "Take a screenshot of the current page and analyze it with vision AI. Use this when you need to visually understand what's on the page - especially useful for CAPTCHAs, visual verification challenges, complex layouts, or when the text snapshot doesn't capture important visual information. Returns both the AI analysis and a screenshot_path that you can share with the user by including MEDIA: in your response. Requires browser_navigate to be called first.",
"parameters": {
"type": "object",
"properties": {
"question": {
"type": "string",
"description": "What you want to know about the page visually. Be specific about what you're looking for."
},
"annotate": {
"type": "boolean",
"default": false,
"description": "If true, overlay numbered [N] labels on interactive elements. Each [N] maps to ref @eN for subsequent browser commands. Useful for QA and spatial reasoning about page layout."
}
},
"required": [
"question"
]
}
}
},
{
"type": "function",
"function": {
"name": "clarify",
"description": "Ask the user a question when you need clarification, feedback, or a decision before proceeding. Supports two modes:\n\n1. **Multiple choice** — provide up to 4 choices. The user picks one or types their own answer via a 5th 'Other' option.\n2. **Open-ended** — omit choices entirely. The user types a free-form response.\n\nUse this tool when:\n- The task is ambiguous and you need the user to choose an approach\n- You want post-task feedback ('How did that work out?')\n- You want to offer to save a skill or update memory\n- A decision has meaningful trade-offs the user should weigh in on\n\nDo NOT use this tool for simple yes/no confirmation of dangerous commands (the terminal tool handles that). Prefer making a reasonable default choice yourself when the decision is low-stakes.",
"parameters": {
"type": "object",
"properties": {
"question": {
"type": "string",
"description": "The question to present to the user."
},
"choices": {
"type": "array",
"items": {
"type": "string"
},
"maxItems": 4,
"description": "Up to 4 answer choices. Omit this parameter entirely to ask an open-ended question. When provided, the UI automatically appends an 'Other (type your answer)' option."
}
},
"required": [
"question"
]
}
}
},
{
"type": "function",
"function": {
"name": "cronjob",
"description": "Manage scheduled cron jobs with a single compressed tool.\n\nUse action='create' to schedule a new job from a prompt or one or more skills.\nUse action='list' to inspect jobs.\nUse action='update', 'pause', 'resume', 'remove', or 'run' to manage an existing job.\n\nTo stop a job the user no longer wants: first action='list' to find the job_id, then action='remove' with that job_id. Never guess job IDs — always list first.\n\nJobs run in a fresh session with no current-chat context, so prompts must be self-contained.\nIf skills are provided on create, the future cron run loads those skills in order, then follows the prompt as the task instruction.\nOn update, passing skills=[] clears attached skills.\n\nNOTE: The agent's final response is auto-delivered to the target. Put the primary\nuser-facing content in the final response. Cron jobs run autonomously with no user\npresent — they cannot ask questions or request clarification.\n\nImportant safety rule: cron-run sessions should not recursively schedule more cron jobs.",
"parameters": {
"type": "object",
"properties": {
"action": {
"type": "string",
"description": "One of: create, list, update, pause, resume, remove, run"
},
"job_id": {
"type": "string",
"description": "Required for update/pause/resume/remove/run"
},
"prompt": {
"type": "string",
"description": "For create: the full self-contained prompt. If skills are also provided, this becomes the task instruction paired with those skills."
},
"schedule": {
"type": "string",
"description": "For create/update: '30m', 'every 2h', '0 9 * * *', or ISO timestamp"
},
"name": {
"type": "string",
"description": "Optional human-friendly name"
},
"repeat": {
"type": "integer",
"description": "Optional repeat count. Omit for defaults (once for one-shot, forever for recurring)."
},
"deliver": {
"type": "string",
"description": "Omit this parameter to auto-deliver back to the current chat and topic (recommended). Auto-detection preserves thread/topic context. Only set explicitly when the user asks to deliver somewhere OTHER than the current conversation. Values: 'origin' (same as omitting), 'local' (no delivery, save only), '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:' for a provider defined in custom_providers config — always include the ':' 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."
}
},
"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 web_search(query: str, limit: int = 5) -> dict\n Returns {\"data\": {\"web\": [{\"url\", \"title\", \"description\"}, ...]}}\n web_extract(urls: list[str]) -> dict\n Returns {\"results\": [{\"url\", \"title\", \"content\", \"error\"}, ...]} where content is markdown\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 web_search, 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"
}
},
"required": [
"mode"
]
}
}
},
{
"type": "function",
"function": {
"name": "process",
"description": "Manage background processes started with terminal(background=true). Actions: 'list' (show all), 'poll' (check status + new output), 'log' (full output with pagination), 'wait' (block until done or timeout), 'kill' (terminate), 'write' (send raw stdin data without newline), 'submit' (send data + Enter, for answering prompts), 'close' (close stdin/send EOF).",
"parameters": {
"type": "object",
"properties": {
"action": {
"type": "string",
"enum": [
"list",
"poll",
"log",
"wait",
"kill",
"write",
"submit",
"close"
],
"description": "Action to perform on background processes"
},
"session_id": {
"type": "string",
"description": "Process session ID (from terminal background output). Required for all actions except 'list'."
},
"data": {
"type": "string",
"description": "Text to send to process stdin (for 'write' and 'submit' actions)"
},
"timeout": {
"type": "integer",
"description": "Max seconds to block for 'wait' action. Returns partial output on timeout.",
"minimum": 1
},
"offset": {
"type": "integer",
"description": "Line offset for 'log' action (default: last 200 lines)"
},
"limit": {
"type": "integer",
"description": "Max lines to return for 'log' action",
"minimum": 1
}
},
"required": [
"action"
]
}
}
},
{
"type": "function",
"function": {
"name": "read_file",
"description": "Read a text file with line numbers and pagination. Use this instead of cat/head/tail in terminal. Output format: 'LINE_NUM|CONTENT'. Suggests similar filenames if not found. Use offset and limit for large files. Reads exceeding ~100K characters are rejected; use offset and limit to read specific sections of large files. NOTE: Cannot read images or binary files — use vision_analyze for images.",
"parameters": {
"type": "object",
"properties": {
"path": {
"type": "string",
"description": "Path to the file to read (absolute, relative, or ~/path)"
},
"offset": {
"type": "integer",
"description": "Line number to start reading from (1-indexed, default: 1)",
"default": 1,
"minimum": 1
},
"limit": {
"type": "integer",
"description": "Maximum number of lines to read (default: 500, max: 2000)",
"default": 500,
"maximum": 2000
}
},
"required": [
"path"
]
}
}
},
{
"type": "function",
"function": {
"name": "search_files",
"description": "Search file contents or find files by name. Use this instead of grep/rg/find/ls in terminal. Ripgrep-backed, faster than shell equivalents.\n\nContent search (target='content'): Regex search inside files. Output modes: full matches with line numbers, file paths only, or match counts.\n\nFile search (target='files'): Find files by glob pattern (e.g., '*.py', '*config*'). Also use this instead of ls — results sorted by modification time.",
"parameters": {
"type": "object",
"properties": {
"pattern": {
"type": "string",
"description": "Regex pattern for content search, or glob pattern (e.g., '*.py') for file search"
},
"target": {
"type": "string",
"enum": [
"content",
"files"
],
"description": "'content' searches inside file contents, 'files' searches for files by name",
"default": "content"
},
"path": {
"type": "string",
"description": "Directory or file to search in (default: current working directory)",
"default": "."
},
"file_glob": {
"type": "string",
"description": "Filter files by pattern in grep mode (e.g., '*.py' to only search Python files)"
},
"limit": {
"type": "integer",
"description": "Maximum number of results to return (default: 50)",
"default": 50
},
"offset": {
"type": "integer",
"description": "Skip first N results for pagination (default: 0)",
"default": 0
},
"output_mode": {
"type": "string",
"enum": [
"content",
"files_only",
"count"
],
"description": "Output format for grep mode: 'content' shows matching lines with line numbers, 'files_only' lists file paths, 'count' shows match counts per file",
"default": "content"
},
"context": {
"type": "integer",
"description": "Number of context lines before and after each match (grep mode only)",
"default": 0
}
},
"required": [
"pattern"
]
}
}
},
{
"type": "function",
"function": {
"name": "send_message",
"description": "Send a message to a connected messaging platform, or list available targets.\n\nIMPORTANT: When the user asks to send to a specific channel or person (not just a bare platform name), call send_message(action='list') FIRST to see available targets, then send to the correct one.\nIf the user just says a platform name like 'send to telegram', send directly to the home channel without listing first.",
"parameters": {
"type": "object",
"properties": {
"action": {
"type": "string",
"enum": [
"send",
"list"
],
"description": "Action to perform. 'send' (default) sends a message. 'list' returns all available channels/contacts across connected platforms."
},
"target": {
"type": "string",
"description": "Delivery target. Format: 'platform' (uses home channel), 'platform:#channel-name', 'platform:chat_id', or 'platform:chat_id:thread_id' for Telegram topics and Discord threads. Examples: 'telegram', 'telegram:-1001234567890:17585', 'discord:999888777:555444333', 'discord:#bot-home', 'slack:#engineering', 'signal:+155****4567', 'matrix:!roomid:server.org', 'matrix:@user:server.org', 'yuanbao:direct:' (DM), 'yuanbao:group:' (group chat)"
},
"message": {
"type": "string",
"description": "The message text to send. To send an image or file, include MEDIA: (e.g. 'MEDIA:/tmp/hermes/cache/img_xxx.jpg') in the message — the platform will deliver it as a native media attachment."
}
}
}
}
},
{
"type": "function",
"function": {
"name": "session_search",
"description": "Search your long-term memory of past conversations, or browse recent sessions. This is your recall -- every past session is searchable, and this tool summarizes what happened.\n\nTWO MODES:\n1. Recent sessions (no query): Call with no arguments to see what was worked on recently. Returns titles, previews, and timestamps. Zero LLM cost, instant. Start here when the user asks what were we working on or what did we do recently.\n2. Keyword search (with query): Search for specific topics across all past sessions. Returns LLM-generated summaries of matching sessions.\n\nUSE THIS PROACTIVELY when:\n- The user says 'we did this before', 'remember when', 'last time', 'as I mentioned'\n- The user asks about a topic you worked on before but don't have in current context\n- The user references a project, person, or concept that seems familiar but isn't in memory\n- You want to check if you've solved a similar problem before\n- The user asks 'what did we do about X?' or 'how did we fix Y?'\n\nDon't hesitate to search when it is actually cross-session -- it's fast and cheap. Better to search and confirm than to guess or ask the user to repeat themselves.\n\nSearch syntax: keywords joined with OR for broad recall (elevenlabs OR baseten OR funding), phrases for exact match (\"docker networking\"), boolean (python NOT java), prefix (deploy*). IMPORTANT: Use OR between keywords for best results — FTS5 defaults to AND which misses sessions that only mention some terms. If a broad OR query returns nothing, try individual keyword searches in parallel. Returns summaries of the top matching sessions.",
"parameters": {
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Search query — keywords, phrases, or boolean expressions to find in past sessions. Omit this parameter entirely to browse recent sessions instead (returns titles, previews, timestamps with no LLM cost)."
},
"role_filter": {
"type": "string",
"description": "Optional: only search messages from specific roles (comma-separated). E.g. 'user,assistant' to skip tool outputs."
},
"limit": {
"type": "integer",
"description": "Max sessions to summarize (default: 3, max: 5).",
"default": 3
}
}
}
}
},
{
"type": "function",
"function": {
"name": "skill_manage",
"description": "Manage skills (create, update, delete). Skills are your procedural memory — reusable approaches for recurring task types. New skills go to ~/.hermes/skills/; existing skills can be modified wherever they live.\n\nActions: create (full SKILL.md + optional category), patch (old_string/new_string — preferred for fixes), edit (full SKILL.md rewrite — major overhauls only), delete, write_file, remove_file.\n\nOn delete, pass `absorbed_into=` 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 `. 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. Two patterns:\n (1) Long-lived processes that never exit (servers, watchers).\n (2) Long-running tasks with notify_on_complete=true — you can keep working on other things and the system auto-notifies you when the task finishes. Great for test suites, builds, deployments, or anything that takes more than a minute.\nFor servers/watchers, do NOT use shell-level background wrappers (nohup/disown/setsid/trailing '&') in foreground mode. Use background=true so Hermes can track lifecycle and output.\nAfter starting a server, verify readiness with a health check or log signal, then run tests in a separate terminal() call. Avoid blind sleep loops.\nUse process(action=\"poll\") for progress checks, process(action=\"wait\") to block until done.\nWorking directory: Use 'workdir' for per-command cwd.\nPTY mode: Set pty=true for interactive CLI tools (Codex, Claude Code, Python REPL).\n\nDo NOT use vim/nano/interactive tools without pty=true — they hang without a pseudo-terminal. Pipe git output to cat if it might page.\n",
"parameters": {
"type": "object",
"properties": {
"command": {
"type": "string",
"description": "The command to execute on the VM"
},
"background": {
"type": "boolean",
"description": "Run the command in the background. Two patterns: (1) Long-lived processes that never exit (servers, watchers). (2) Long-running tasks paired with notify_on_complete=true — you can keep working and get notified when the task finishes. For short commands, prefer foreground with a generous timeout instead.",
"default": false
},
"timeout": {
"type": "integer",
"description": "Max seconds to wait (default: 180, foreground max: 600). Returns INSTANTLY when command finishes — set high for long tasks, you won't wait unnecessarily. Foreground timeout above 600s is rejected; use background=true for longer commands.",
"minimum": 1
},
"workdir": {
"type": "string",
"description": "Working directory for this command (absolute path). Defaults to the session working directory."
},
"pty": {
"type": "boolean",
"description": "Run in pseudo-terminal (PTY) mode for interactive CLI tools like Codex, Claude Code, or Python REPL. Only works with local and SSH backends. Default: false.",
"default": false
},
"notify_on_complete": {
"type": "boolean",
"description": "When true (and background=true), you'll be automatically notified exactly once when the process finishes. **This is the right choice for almost every long-running task** — tests, builds, deployments, multi-item batch jobs, anything that takes over a minute and has a defined end. Use this and keep working on other things; the system notifies you on exit. MUTUALLY EXCLUSIVE with watch_patterns — when both are set, watch_patterns is dropped.",
"default": false
},
"watch_patterns": {
"type": "array",
"items": {
"type": "string"
},
"description": "Strings to watch for in background process output. HARD RATE LIMIT: at most 1 notification per 15 seconds per process — matches arriving inside the cooldown are dropped. After 3 consecutive 15-second windows with dropped matches, watch_patterns is automatically disabled for that process and promoted to notify_on_complete behavior (one notification on exit, no more mid-process spam). USE ONLY for truly rare, one-shot mid-process signals on LONG-LIVED processes that will never exit on their own — e.g. ['Application startup complete'] on a server so you know when to hit its endpoint, or ['migration done'] on a daemon. DO NOT use for: (1) end-of-run markers like 'DONE'/'PASS' — use notify_on_complete instead; (2) error patterns like 'ERROR'/'Traceback' in loops or multi-item batch jobs — they fire on every iteration and you'll hit the strike limit fast; (3) anything you'd ever combine with notify_on_complete. When in doubt, choose notify_on_complete. MUTUALLY EXCLUSIVE with notify_on_complete — set one, not both."
}
},
"required": [
"command"
]
}
}
},
{
"type": "function",
"function": {
"name": "text_to_speech",
"description": "Convert text to speech audio. Returns a MEDIA: path that the platform delivers as 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.), not model-selected.",
"parameters": {
"type": "object",
"properties": {
"text": {
"type": "string",
"description": "The text to convert to speech. Provider-specific character caps apply and are enforced automatically (OpenAI 4096, xAI 15000, MiniMax 10000, ElevenLabs 5k-40k depending on model); over-long input is truncated."
},
"output_path": {
"type": "string",
"description": "Optional custom file path to save the audio. Defaults to ~/.hermes/audio_cache/.mp3"
}
},
"required": [
"text"
]
}
}
},
{
"type": "function",
"function": {
"name": "todo",
"description": "Manage your task list for the current session. Use for complex tasks with 3+ steps or when the user provides multiple tasks. Call with no parameters to read the current list.\n\nWriting:\n- Provide 'todos' array to create/update items\n- merge=false (default): replace the entire list with a fresh plan\n- merge=true: update existing items by id, add any new ones\n\nEach item: {id: string, content: string, status: pending|in_progress|completed|cancelled}\nList order is priority. Only ONE item in_progress at a time.\nMark items completed immediately when done. If something fails, cancel it and add a revised item.\n\nAlways returns the full current list.",
"parameters": {
"type": "object",
"properties": {
"todos": {
"type": "array",
"description": "Task items to write. Omit to read current list.",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "Unique item identifier"
},
"content": {
"type": "string",
"description": "Task description"
},
"status": {
"type": "string",
"enum": [
"pending",
"in_progress",
"completed",
"cancelled"
],
"description": "Current status"
}
},
"required": [
"id",
"content",
"status"
]
}
},
"merge": {
"type": "boolean",
"description": "true: update existing items by id, add new ones. false (default): replace the entire list.",
"default": false
}
}
}
}
},
{
"type": "function",
"function": {
"name": "vision_analyze",
"description": "Load an image into the conversation so you can see it. Accepts a URL, local file path, or data URL. When your active model has native vision, the image is attached to your context directly and you read the pixels yourself on the next turn — call this any time the user references an image (filepath in their message, URL in tool output, screenshot from the browser, etc.). For non-vision models, falls back to an auxiliary vision model that returns a text description.",
"parameters": {
"type": "object",
"properties": {
"image_url": {
"type": "string",
"description": "Image URL (http/https), local file path, or data: URL to load."
},
"question": {
"type": "string",
"description": "Your specific question or request about the image. Optional context the model uses on the next turn after seeing the image."
}
},
"required": [
"image_url",
"question"
]
}
}
},
{
"type": "function",
"function": {
"name": "web_extract",
"description": "Extract content from web page URLs. Returns page content in markdown format. Also works with PDF URLs (arxiv papers, documents, etc.) — pass the PDF link directly and it converts to markdown text. Pages under 5000 chars return full markdown; larger pages are LLM-summarized and capped at ~5000 chars per page. Pages over 2M chars are refused. If a URL fails or times out, use the browser tool to access it instead.",
"parameters": {
"type": "object",
"properties": {
"urls": {
"type": "array",
"items": {
"type": "string"
},
"description": "List of URLs to extract content from (max 5 URLs per call)",
"maxItems": 5
}
},
"required": [
"urls"
]
}
}
},
{
"type": "function",
"function": {
"name": "web_search",
"description": "Search the web for information. Returns up to 5 results by default with titles, URLs, and descriptions. The query is passed through to the configured backend, so operators such as site:domain, filetype:pdf, intitle:word, -term, and \"exact phrase\" may work when the backend supports them.",
"parameters": {
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "The search query to look up on the web. You may include backend-supported operators such as site:example.com, filetype:pdf, intitle:word, -term, or \"exact phrase\"."
},
"limit": {
"type": "integer",
"description": "Maximum number of results to return. Defaults to 5.",
"minimum": 1,
"maximum": 100,
"default": 5
}
},
"required": [
"query"
]
}
}
},
{
"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"
}
},
"required": [
"path",
"content"
]
}
}
}
],
"message_count": 20,
"messages": [
{
"role": "user",
"content": "给我找一些实用易懂的n8n教程，做一个学习计划放到synology的group文件夹。"
},
{
"role": "assistant",
"content": "",
"reasoning": "用户想要找一些n8n教程，然后制作一个学习计划放到Synology的group文件夹。\n\n首先我需要：\n1. 搜索n8n教程资源\n2. 了解Synology的group文件夹路径\n\n让我先搜索n8n教程，同时查看Synology的挂载情况。",
"finish_reason": "tool_calls",
"reasoning_content": "用户想要找一些n8n教程，然后制作一个学习计划放到Synology的group文件夹。\n\n首先我需要：\n1. 搜索n8n教程资源\n2. 了解Synology的group文件夹路径\n\n让我先搜索n8n教程，同时查看Synology的挂载情况。",
"reasoning_details": [
{
"signature": "9049f60f00aa3c0ae1564e781733845d8164ef892f73fbb755faa5c3b0c83d6e",
"thinking": "用户想要找一些n8n教程，然后制作一个学习计划放到Synology的group文件夹。\n\n首先我需要：\n1. 搜索n8n教程资源\n2. 了解Synology的group文件夹路径\n\n让我先搜索n8n教程，同时查看Synology的挂载情况。",
"type": "thinking"
}
],
"tool_calls": [
{
"id": "call_function_i5mpbhf935sc_1",
"call_id": "call_function_i5mpbhf935sc_1",
"response_item_id": "fc_function_i5mpbhf935sc_1",
"type": "function",
"function": {
"name": "web_search",
"arguments": "{\"query\": \"n8n\\u6559\\u7a0b \\u4e2d\\u6587 \\u5165\\u95e8 \\u5b9e\\u7528 2024\", \"limit\": 10}"
}
},
{
"id": "call_function_i5mpbhf935sc_2",
"call_id": "call_function_i5mpbhf935sc_2",
"response_item_id": "fc_function_i5mpbhf935sc_2",
"type": "function",
"function": {
"name": "terminal",
"arguments": "{\"command\": \"ls -la /volume1/homes/kuhnn/ 2>/dev/null || ls -la /home/kuhnn/synology* 2>/dev/null || find /home/kuhnn -name \\\"group\\\" -type d 2>/dev/null | head -5\"}"
}
}
]
},
{
"role": "tool",
"name": "web_search",
"content": "{\n \"success\": true,\n \"data\": {\n \"web\": [\n {\n \"title\": \"【超詳細N8N教學】0基礎入門到進階，教你從0-1搭建第一個AI Agent\",\n \"url\": \"https://www.youtube.com/watch?v=b6AEsVRJjzI\",\n \"description\": \"... 攻略》 https://www.77mediabook.com/ebook-you... 【免費領取】電子書攻略《2024年小紅書賺錢寶典》 https://www.77mediabook.com/ebook2 【免費諮詢】\",\n \"position\": 1\n },\n {\n \"title\": \"简单易懂的现代魔法 - n8n 中文使用教程 | 一个中文 n8n 学习社区\",\n \"url\": \"https://n8n.akashio.com/\",\n \"description\": \"🆓 半开放式节点（Code/HTTP Request）详细介绍. 🐍 如何在 n8n 中安装/使用第三方 Python 库？. 如何用 n8n 做一个 Telegram 机器人？. 🔍 如何用 n8n 做一个免费的 Deep Research？. ⏱️ 为什么我的定时 Trigger 和 RSS 更新 Trigger 无法正常触发？. Last update:2021-07-02. 🆓 半开放式节点（Code/HTTP Request）详细介绍. 🐍 如何在 n8n 中安装/使用第三方 Python 库？. 如何用 n8n 做一个 Telegram 机器人？. 🔍 如何用 n8n 做一个免费的 Deep Research？. ⏱️ 为什么我的定时 Trigger 和 RSS 更新 Trigger 无法正常触发？.\",\n \"position\": 2\n },\n {\n \"title\": \"[Youtube] n8n 入門指南：2024年終極速成課程 - Threads\",\n \"url\": \"https://www.threads.com/@n8n_auto_post/post/DVYFL3XlA9Z/youtube-n8n-%E5%85%A5%E9%96%80%E6%8C%87%E5%8D%972024%E5%B9%B4%E7%B5%82%E6%A5%B5%E9%80%9F%E6%88%90%E8%AA%B2%E7%A8%8B%E6%83%B3%E8%AE%93%E5%B7%A5%E4%BD%9C%E6%B5%81%E7%A8%8B%E8%87%AA%E5%8B%95%E5%8C%96%E5%8D%BB%E8%A2%AB%E8%A4%87%E9%9B%9C%E7%9A%84%E7%A8%8B%E5%BC%8F%E7%A2%BC%E6%93%8B%E4%BD%8F%E5%8E%BB%E8%B7%AF%E5%97%8En8n-%E6%98%AF%E4%B8%80%E6%AC%BE%E5%BC%B7%E5%A4%A7%E7%9A%84%E5%B7%A5%E4%BD%9C%E6%B5%81%E8%87%AA%E5%8B%95%E5%8C%96%E5%B7%A5%E5%85%B7%E8%83%BD%E8%AE%93%E4%BD%A0%E8%BC%95%E9%AC%86%E4%B8%B2%E6%8E%A5%E6%95%B8%E7%99%BE%E7%A8%AE%E6%87%89%E7%94%A8%E7%A8%8B\",\n \"description\": \"想讓工作流程自動化，卻被複雜的程式碼擋住去路嗎？n8n 是一款強大的工作流自動化工具，能讓你輕鬆串接數百種應用程式。這段內容將帶你深入淺出地了解n8n\",\n \"position\": 3\n },\n {\n \"title\": \"n8n 入门教程 | Jimmy Song\",\n \"url\": \"https://jimmysong.io/zh/book/n8n-handbook/\",\n \"description\": \"#### 技术专栏. Kubernetes、Service Mesh、Envoy、Gateway 等。. #### 更多内容. #### AI. Spring Cloud 与 Spring Boot 实践。. #### 精选资源. #### 交流与反馈. Bilibili 频道，涵盖云原生与 AI 视频教程。. #### 快速链接. #### 微信公众号. 关注我的微信公众号「几米宋」，获取云原生与 AI 的最新文章。. 扫码添加 Jimmy 个人微信，交流云原生与 AI 技术实践。. #### 站内搜索. # n8n 入门教程. ## 内容摘要. ## 章节目录. 了解如何在 macOS 上通过 Homebrew 或 npm 安装和运行 n8n，包括配置环境变量和权限设置。. 详细介绍 n8n 的环境变量与内置变量用法，并给出“多输入合并”的正确姿势（Merge、表达式与 Code 节点）。. 简要介绍 n8n 权限与路径管理，助你避免常见错误，保障数据安全与稳定运行。. 深入了解 n8n Workflow 编辑器的使用方法，包括界面布局、节点操作和工作流调试技巧。. 了解 n8n 中常用节点的使用方法和配置示例，包括文件读写、HTTP 请求、条件判断等节点。. 了解 n8n 中不同类型的触发节点，包括 Manual Trigger、Schedule Trigger 和 Webhook Trigger 的使用方法和区别。. 比较并介绍 n8n 中的 Code 与 Execute Command 节点的原理、适用场景、限制与实践建议。. 学习如何使用 Execute Command 节点将本地脚本和程序集成到 n8n 工作流中。. 了解如何通过 HTTP Request 节点调用大语言模型 API，如 OpenAI 或 Google Gemini，并处理返回的 JSON 数据。. 学习如何集成 Google 服务到 n8n 工作流中，包括 Google Sheets、Google Drive 和 Gmail 的使用方法。. 通过一个完整的实战示例，学习如何使用 n8n 将英文 PDF 转换为 Markdown，调用大语言模型翻译，再生成中文 PDF。. © 2017-2026 Jimmy Song 保留所有权利 · CC BY 4.0.\",\n \"position\": 4\n },\n {\n \"title\": \"n8n新手中文教學：6步安裝、7步驟部署第一支工作流！費用？ - ADBest：不只流量，我們更在乎留量\",\n \"url\": \"https://adbest.com.tw/blog/what-is-n8n/\",\n \"description\": \"1. 把報名者的名字、電話、Email 複製貼到 Excel 或 Google Sheet 裡；. 3. 最後還要把名單貼進 LINE 群組，提醒你的助教有新報名的學員。. 3. 自動發一則 LINE Notify 到你跟助教的手機上。. 現在很多行銷人也開始用 n8n 來串接 CRM、EDM、LINE 官方帳號或表單工具，做資料蒐集、名單分類、自動推播等流程。. ### **（一）n8n 適合誰？6 種真實場景，一看就懂！**. 確認 Google 報名活動表單，有沒有人填資料，接著將新客資料手動貼進 Excel 或 Google Sheet，然後再寄通知信、開 LINE 跟同事說誰報名了。. 若要追蹤 SEO 成效，你每天都要從 Google Analytics 4、Google Search Console 抓資料、整理格式、做成報表，再 email 給主管或團隊，稍不留神可能還會報錯數字。. ## n8n 安裝教學來了，6 個步驟部署自己的自動化系統！. ### **（一）註冊 Zeabur**. ### **（二）Zeabur 付款設定**. 如果你想要讓 n8n 長期穩定運行，就需要把 Zeabur 升級到付費的「開發者模式（Developer Mode）」。. ### **（三）建立 n8n 專案**. 只要在「綁定 Zeabur 子網域」欄位裡，輸入你想要的網址名稱，像是「my-n8n-project」，系統就會自動幫你產生一個網址，這樣你的 n8n 就會有一個可以公開使用的入口，不用自己買網域或額外申請。. ### **（五）更新 n8n 的版本**. Zeabur 剛部署好時，預設的 n8n 版本不見得是最新的，所以可以查詢目前 n8n 版本，手動更新一下版本。. ### **（六）n8n 註冊**. ## n8n 教學新手必看！5 個面板區域＋1 核心觀念搞懂操作邏輯. 這邊會記錄你串接過哪些服務的帳密或授權，像是 Gmail、Notion、Google Sheet、LINE Notify，這些資料都會集中放在這裡，不用每次重打一次帳號密碼，n8n 幫你記起來更省事。. ### **（六）自動化核心概念：Trigger 與 Action**. 你可以寫進 Google Sheet、更新 Notion、傳到 LINE Notify 或 Discord，可以依照團隊作業習慣，自由選擇適合的出口。. 這篇教學會實際部署一個具體的專案：「當有人填寫報名表單時，n8n 自動發一封確認信給填表人，並把資料存進 Google Sheet」，一步步帶你操作。. ### **（四）加入第三個節點：存資料到 Google Sheet**. 串 Gmail 和 Google Sheet 前，你要先去左側「Credentials」設定裡建立 OAuth 連結授權，把你的 Google 帳號與 n8n 串起來。只要設定一次，之後每個節點都可以選這組憑證來使用。. ### **（一）判斷事情值不值得 n8n 自動化？3 條件評估！**. ### **（二）n8n 應用情境範例**. 透過 n8n，你可以讓 Google 表單的報名資訊直接寫入 Google Sheet，接著為每筆資料生成 QR Code，讓現場報到人員直接掃碼完成核對，省下手動核名、印報表的時間。. 用 n8n 串接 Notion、Google Sheets、各平台 API，幫你自動同步所有資料，整合成一個內容中心。. n8n 可以每天早上自動抓取中央氣象局或第三方天氣 API 的最新資訊，再把整理好的訊息透過 LINE Notify、Slack 或 email 發送出去，還能定時、設定格式、自動推播。. ## n8n 費用怎麼算？雲端、Zeabur、自架 3 方案分析！.\",\n \"position\": 5\n },\n {\n \"title\": \"n8n 入门教程：普通人也能用的自动化工具，从0 到能跑一个工作流\",\n \"url\": \"https://zhuanlan.zhihu.com/p/1986390534802129838\",\n \"description\": \"如果你想要一个能自己部署、不按次数收费、逻辑可控的自动化工具，那n8n 非常值得了解。 这篇文章不讲复杂架构，只解决三个问题：. n8n 是什么，能干什么; 新手如何快速上手（不\",\n \"position\": 6\n },\n {\n \"title\": \"【n8n 中文教學】新手入門：介面功能說明、Webhook 和自動化工作流應用\",\n \"url\": \"https://raymondhouch.com/lifehacker/digital-workflow/n8n-beginner-guide/\",\n \"description\": \"前面幾篇文章都在告訴你怎麼自部署 n8n、建立憑證、備份工作流……等設置好 n8n 的前置作業。. 這篇我會介紹 n8n 的管理介面的功能和操作、常用的節點使用情境，開始進入 n8n 的應用教學文，讓你可以建立自己的第一個自動化工作流 ✌️. 直到現代人人都能用 AI 幫你快速學習、解讀和生成程式碼，讓以往我也難以接觸的 n8n 變成最佳的解決方案。. 💬 市面上已有很多自動化工具的選擇，比如老牌 IFTTT，或是 Zapier、Make，為什麼我更偏好使用 n8n ？. ## n8n 管理介面＆功能教學. 在帳號右邊的「…」點擊後可以進去設定區，建議部署好 n8n 後就可以一起設定 2FA 雙重驗證，保障你的資料。. 自動化工作流通常由 2 種節點組成：**觸發（Trigger）**和**動作（Action）**。. ### 1️⃣ **When click Test workflow**. ### 2️⃣ **Webhook**. 開始使用 Webhook 節點時， n8n 會為你創建一個獨特的網址，來接收資料。. ### 3️⃣ **Loop Over Items**. ### 4️⃣ **Schedule**. ### 5️⃣ **Edit Fields (Set)**. ### 6️⃣ **If**. ### 7️⃣ **Code**2. n8n 官方有建立一個模版庫，目前有超過 1500+ 個其他人上傳的 n8n 模版，你可以直接搜尋想要解決的問題關鍵字，或是工具的關鍵字，看看有沒有適合你需求的工作流。. 在我的自動化課程裡，也有建立一個 **No Code 自動化工具的應用庫**。. 不定期更新，將我正在用，覺得大家會需要的 n8n 應用模版、詳細操作教學放進去，讓有需要的學員可以直接複製我的模版去修改！. 你可以使用 n8n 的「便利貼」（Sticky Notes）功能來記錄工作流的思路與步驟：. 1. **打開工作流**：進入 n8n 界面，找到並打開你要記錄的工作流. * 【n8n 串接 Google 服務教學】API、Credentials 憑證設定，完整步驟圖文解釋. * 【n8n 教學】如何用 Zeabur 自動備份 n8n 工作流、憑證？匯出工作流給他人？. * ✅ 理解 No-Code 自動化工具的底層邏輯：如何選擇哪些任務，適合自動化？. 1. 詳細操作說明，可以前往觀看：**【n8n 自動化教學】寄出大量客製化通知信、專屬優惠碼**。 ↩︎. 2. 更多說明，請見官方文檔：n8n Docs – Using the Code node ↩︎. #### 21 天，我用 Claude Code 打造了一整套 AI 分身助理記錄. #### #175 – Notion 入門線下課登場 / 非工程師的 Claude Code 旅程 / Manny 來了 ®️雷蒙週報. #### Claude Code 是什麼？從 Claude Cowork 到 Code，非工程師也能上手的完整入門教學. #### 21 天，我用 Claude Code 打造了一整套 AI 分身助理記錄. #### Claude Code 是什麼？從 Claude Cowork 到 Code，非工程師也能上手的完整入門教學.\",\n \"position\": 7\n },\n {\n \"title\": \"n8n新手入门教程/n8n Beginner Tutorial - YouTube\",\n \"url\": \"https://www.youtube.com/playlist?list=PLxtaO-gmRzggbNVy1SSNA4kl9LshNunCR\",\n \"description\": \"n8n 升级保姆级教程：从备份到更新，Perplexity 辅助全流程演示(Docker) · 【n8n自动化教程完结】拒绝“悄悄挂掉”，给工作流装上Error Trigger 自动报警+防坑指南.\",\n \"position\": 8\n },\n {\n \"title\": \"从 0 到 1 玩转 N8N——初识 N8N（入门必看）-腾讯云开发者社区-腾讯云\",\n \"url\": \"https://cloud.tencent.com/developer/article/2609101\",\n \"description\": \"## 从 0 到 1 玩转 N8N——初识 N8N（入门必看）. ## 什么是n8n？. **n8n 是一款开源、灵活且高度可定制的工作流自动化平台，其核心理念是通过可视化拖拽界面将不同的应用、服务、API或数据源连接起来，实现复杂的自动化任务，而无需编写大量代码**。n8n 的名字源于德语 “nur ein Ninja”（意为“只是一个忍者”），寓意其强大、灵活又轻盈。. #### 核心特性. #### 适用场景. ## 怎么用 n8n? 首先先解决 “怎么用 n8n” 的基础问题，n8n一般有 3 种部署方式：. | 官方 SaaS | 快速体验者 | 无需配置，开箱即用 | 仅 14 天免费试用 |. | 本地部署 | 初学者、开发者 | 免费、便于调试 | 依赖本地电脑，无法长期运行 |. | 云服务器部署 | 企业用户、长期使用者 | 7×24 小时运行、高可用 | 需支付云服务器费用 |. ## **获取 N8N 服务器**. https://buy.cloud.tencent.com/lighthouse? blueprintType=APP\\\\_OS&blueprintOfficialId=lhbp-5utfah5i®ionId=1&zone=ap-guangzhou-6&bundleId=bundle\\\\_rs\\\\_mc\\\\_med2\\\\_01&loginSet=AUTO&timeSpan=3&from=lh-console. ### 2.打开服务器管理. 打开网站：https://console.cloud.tencent.com/lighthouse/instance/index? 在上图有一个公网地址，我们打开网站：http://your-server-ip:5678. 例如我就是：http://111.230.109.186:5678. ### 3.实战：搭建“获取今日信息并保存为文件”工作流. #### 步骤 1：创建新工作流. #### 步骤 2：添加手动触发器. #### 步骤 3：添加 Code 节点（生成内容）. 选择code节点为例，点击后会出现这个弹窗，我们在代码框放上自己所需要的功能代码，点击Execute step（执行步骤）按钮，右侧output那边就会出现输出的内容. # 获取第一个输入项. # 从 item.json 中提取 randomQuote. random_quote = item.json.get(\\\"randomQuote\\\", \\\"今日 LucianaiB 名言\\\"). # 构造日期. date_str = f\\\"{today.year}年{today.month}月{today.day}日\\\". # 生成推文内容. tweet_content = f\\\"📚 我不做 N8N 应用的传播者，而是希望你能真正爱上它、主动尝试，并动手设计属于自己的自动化流程。\\\". # 返回数据. #### 步骤 4：转换为文本文件. 添加下一个节点Convert to File（保存为文件），选择text文件。. 直接拖到左侧的节点到右侧就是输入（如果左侧没有，是因为需要上一个节点运行成功才可以），点击Execute step（执行步骤）按钮，右侧output那边就会出现输出的内容，我这里选择了预览，可以看到成功显示。. #### 步骤 5：写入本地磁盘. 在File Path and Name输入文件名称（例如：lucianaib.text），点击Execute step（执行步骤）按钮，右侧output那边就会出现输出的内容。. #### 步骤 6：下载文件 & 保存工作流. ## 学习路径. LucianaiB带你从 0 到 1 玩转 N8N 知识库：LucianaiB带你从 0 到 1 玩转 N8N. 如有侵权，请联系 cloudcommunity@tencent.com 删除。. ### 社区. Copyright © 2013 - 2026 Tencent Cloud.\",\n \"position\": 9\n },\n {\n \"title\": \"什么是n8n？工作流自动化初学者完全指南 | iApp Technology\",\n \"url\": \"https://iapp.co.th/zh-CN/blog/what-is-n8n-complete-guide\",\n \"description\": \"# 什么是n8n？工作流自动化初学者完全指南. 想象一下，当客户上传泰国身份证时自动提取文本，将数据发送到您的CRM，在Slack上通知您的团队，并更新Google Sheet——所有这些都无需编写一行代码。这就是**n8n**的力量，一个开源工作流自动化平台，可以连接您的应用程序并自动化您的流程。. ## 什么是n8n？. **n8n**（发音为\\\"n-eight-n\\\"或\\\"nodemation\\\"）是一个**公平代码**工作流自动化平台，允许您通过可视化的、基于节点的界面连接不同的应用程序并自动化任务。可以将其视为协调所有应用程序和服务无缝协作的\\\"大脑\\\"。. ## n8n vs Zapier vs Make：应该选择哪个？. **简单解\\u0000\\u0000释：** 将节点想象成乐高积木。每个积木做一件事（触发、处理、操作），您将它们连接在一起构建有用的东西。. **简单解释：** 就像一个食谱，告诉n8n确切要做什么，一步一步。\\\"当新客户注册时（触发），提取他们的身份证数据（HTTP请求到OCR API），保存到数据库（操作），并发送欢迎邮件（操作）。\\\". **简单解释：** 就像自动化的邮箱。当另一个系统向这个地址\\\"发送邮件\\\"（数据）时，您的工作流就会唤醒并处理它。. **简单解释：** 每次工作流运行，就是一次执行。如果您的工作流处理100张发票，那就是100次执行。. **定义：** 存储的身份验证信息（API密钥、密码、令牌），允许n8n连接到外部服务。. **简单解释：** 让n8n访问您其他应用的\\\"密码\\\"。您只需设置一次，n8n会在需要时安全地使用它们。. n8n 2.0（2025年12月发布）带来了高级AI功能：. ## 将n8n与iApp Technology API结合使用. // URL: https://api.iapp.co.th/v3/store/ekyc/thai-national-id. // URL: https://api.iapp.co.th/v3/nlp/translation. -v ~/.n8n:/home/node/.n8n \\\\. ### 步骤3：集成iApp API. ## 用于n8n集成的iApp API. | 泰国身份证OCR | Thai National ID | HTTP Request |. | 护照OCR | Passport OCR | HTTP Request |. | 人脸验证 | Face Verification | HTTP Request |. | 语音转文字 | Speech-to-Text Pro | HTTP Request |. | 文字转语音 | Text-to-Speech | HTTP Request |. | 翻译 | Multilingual Translation | HTTP Request |. | 情感分析 | Sentiment Analysis | HTTP Request |. ## n8n 2.0：新功能（2025年12月）. 结合iApp Technology针对泰语优化的AI API，n8n使您能够构建理解泰语、阅读泰语文档并服务泰国客户的复杂自动化——所有这些都无需编写复杂代码。. **需要帮助？** 加入我们的Discord社区或发送邮件至support@iapp.co.th。. #### iApp Technology. Empowering Thai Businesses with Sovereign AI Excellence. #### Company Information. 80/359 Moo. 3 Soi. Klong Luang 26, Phahonyothin Road, Klong Nueng, Klong Luang, Pathum Thani 12120, Thailand. 80/359 หมู่ที่ 3 ซ. พหลโยธิน ต.คลองหนึ่ง อ.คลองหลวง ปทุมธานี 12120 ประเทศไทย. ### Company.\",\n \"position\": 10\n }\n ]\n }\n}",
"tool_call_id": "call_function_i5mpbhf935sc_1"
},
{
"role": "tool",
"name": "terminal",
"content": "{\"output\": \"\", \"exit_code\": 0, \"error\": null}",
"tool_call_id": "call_function_i5mpbhf935sc_2"
},
{
"role": "assistant",
"content": "",
"reasoning": "Let me find the Synology group folder path first, then create the learning plan.",
"finish_reason": "tool_calls",
"reasoning_content": "Let me find the Synology group folder path first, then create the learning plan.",
"reasoning_details": [
{
"signature": "55aba9ae91c2b858930da294b49a5238b578841e8db06b3a9bbcb940b8da6edb",
"thinking": "Let me find the Synology group folder path first, then create the learning plan.",
"type": "thinking"
}
],
"tool_calls": [
{
"id": "call_function_xmplyrrblyb8_1",
"call_id": "call_function_xmplyrrblyb8_1",
"response_item_id": "fc_function_xmplyrrblyb8_1",
"type": "function",
"function": {
"name": "terminal",
"arguments": "{\"command\": \"find /home/kuhnn -name \\\"group\\\" -type d 2>/dev/null; ls /home/kuhnn/ 2>/dev/null; ls /volume1/homes/kuhnn 2>/dev/null; find /volume1 -name \\\"group\\\" -type d 2>/dev/null | head -5\"}"
}
}
]
},
{
"role": "tool",
"name": "terminal",
"content": "{\"output\": \"~\\n公共的\\n模板\\n视频\\n图片\\n文档\\n下载\\n音乐\\n桌面\\nago\\\" -p err\\nbackup_xfce\\nbin\\nCaddyfile\\ncap_%d\\nclean_system.sh\\nDesktop\\ngo\\nminiconda3\\nn8n-cert.crt\\nsnap\\nSynologyDrive\\ntts_models\\nudo systemctl disable openvpn.service\\nwhisper.cpp\\nystemctl status\", \"exit_code\": 0, \"error\": null}",
"tool_call_id": "call_function_xmplyrrblyb8_1"
},
{
"role": "assistant",
"content": "",
"reasoning": "Let me check for Synology Drive folder structure more specifically.",
"finish_reason": "tool_calls",
"reasoning_content": "Let me check for Synology Drive folder structure more specifically.",
"reasoning_details": [
{
"signature": "15dd9aed0f22959401714570189f19294d5aa57524ea98e898a7e115f832d4e1",
"thinking": "Let me check for Synology Drive folder structure more specifically.",
"type": "thinking"
}
],
"tool_calls": [
{
"id": "call_function_70fg0gihof9s_1",
"call_id": "call_function_70fg0gihof9s_1",
"response_item_id": "fc_function_70fg0gihof9s_1",
"type": "function",
"function": {
"name": "terminal",
"arguments": "{\"command\": \"find /home/kuhnn/SynologyDrive -name \\\"group\\\" -type d 2>/dev/null | head -5; ls /home/kuhnn/SynologyDrive/ 2>/dev/null\"}"
}
}
]
},
{
"role": "tool",
"name": "terminal",
"content": "{\"output\": \"公众号\\n项目计划书_银发经济与欧洲旅行业务_SilverRoutes_Europe_2026-02-09.md\\nCyber_Nail_Passport\\nminimax-api.txt\\nNPM_theme_curation\\nopenclaw_backup\\nRCA_MediaLibrary\\nScreenshot 2026-05-18 at 04.33.35.png\", \"exit_code\": 0, \"error\": null}",
"tool_call_id": "call_function_70fg0gihof9s_1"
},
{
"role": "assistant",
"content": "",
"reasoning": "Let me find where the Synology group folder is located. It might be in a different path.",
"finish_reason": "tool_calls",
"reasoning_content": "Let me find where the Synology group folder is located. It might be in a different path.",
"reasoning_details": [
{
"signature": "397337e599276c824ff8384406c8db96805310084f65f6cadfd738895be3166c",
"thinking": "Let me find where the Synology group folder is located. It might be in a different path.",
"type": "thinking"
}
],
"tool_calls": [
{
"id": "call_function_3banthbwzyl4_1",
"call_id": "call_function_3banthbwzyl4_1",
"response_item_id": "fc_function_3banthbwzyl4_1",
"type": "function",
"function": {
"name": "terminal",
"arguments": "{\"command\": \"find /home/kuhnn -type d -name \\\"group\\\" 2>/dev/null; find /home/kuhnn -type d -name \\\"*group*\\\" 2>/dev/null; find /home/kuhnn -path \\\"*/SynologyDrive/*\\\" -name \\\"group\\\" -type d 2>/dev/null | head -3\"}"
}
}
]
},
{
"role": "tool",
"name": "terminal",
"content": "{\"output\": \"/home/kuhnn/.cache/uv/archive-v0/y3SwZfYf21cDJROI/botocore/data/resourcegroupstaggingapi\\n/home/kuhnn/.cache/uv/archive-v0/y3SwZfYf21cDJROI/botocore/data/resource-groups\\n/home/kuhnn/.hermes/hermes-agent/venv/lib/python3.11/site-packages/botocore/data/resourcegroupstaggingapi\\n/home/kuhnn/.hermes/hermes-agent/venv/lib/python3.11/site-packages/botocore/data/resource-groups\\n/home/kuhnn/.vscode/extensions/ms-python.python-2026.0.0-linux-x64/python_files/lib/jedilsp/exceptiongroup-1.3.0.dist-info\\n/home/kuhnn/.vscode/extensions/ms-python.python-2026.0.0-linux-x64/python_files/lib/jedilsp/exceptiongroup\\n/home/kuhnn/.vscode/extensions/ms-python.vscode-pylance-2025.10.2/dist/typeshed-fallback/stubs/click-default-group\\n/home/kuhnn/.vscode/extensions/ms-python.vscode-pylance-2025.10.2/dist/bundled/stubs/pandas/core/groupby\\n/home/kuhnn/miniconda3/lib/python3.13/site-packages/pip/_vendor/dependency_groups\\n/home/kuhnn/miniconda3/pkgs/pip-25.1-pyhc872135_2/site-packages/pip/_vendor/dependency_groups\\n/home/kuhnn/.local/lib/python3.10/site-packages/nvidia/cuda_runtime/include/cooperative_groups\\n/home/kuhnn/.local/lib/python3.10/site-packages/nvidia/nvshmem/include/non_abi/device/threadgroup\\n/home/kuhnn/.local/lib/python3.10/site-packages/exceptiongroup\\n/home/kuhnn/.local/lib/python3.10/site-packages/exceptiongroup-1.3.1.dist-info\\n/home/kuhnn/.local/lib/python3.10/site-packages/triton/backends/nvidia/include/cooperative_groups\", \"exit_code\": 0, \"error\": null}",
"tool_call_id": "call_function_3banthbwzyl4_1"
},
{
"role": "assistant",
"content": "",
"reasoning": "找不到 \"group\" 文件夹。让我看看用户的 SynologyDrive 目录结构，用户可能指的是 \"NPM_theme_curation\" 或者其他文件夹，或者他们可能想要我创建一个 group 文件夹。",
"finish_reason": "tool_calls",
"reasoning_content": "找不到 \"group\" 文件夹。让我看看用户的 SynologyDrive 目录结构，用户可能指的是 \"NPM_theme_curation\" 或者其他文件夹，或者他们可能想要我创建一个 group 文件夹。",
"reasoning_details": [
{
"signature": "2a2d9cfbec9a08ca8edb17d4e3e1652736187c18c7e4f1c39647c30776943089",
"thinking": "找不到 \"group\" 文件夹。让我看看用户的 SynologyDrive 目录结构，用户可能指的是 \"NPM_theme_curation\" 或者其他文件夹，或者他们可能想要我创建一个 group 文件夹。",
"type": "thinking"
}
],
"tool_calls": [
{
"id": "call_function_3vw21ztow96n_1",
"call_id": "call_function_3vw21ztow96n_1",
"response_item_id": "fc_function_3vw21ztow96n_1",
"type": "function",
"function": {
"name": "terminal",
"arguments": "{\"command\": \"ls -la /home/kuhnn/SynologyDrive/; find /home/kuhnn/SynologyDrive -type d 2>/dev/null | head -20\"}"
}
}
]
},
{
"role": "tool",
"name": "terminal",
"content": "{\"output\": \"总计 240\\ndrwxrwxr-x 8 kuhnn kuhnn 4096 May 18 06:10 .\\ndrwxr-x--- 45 kuhnn kuhnn 4096 May 18 13:58 ..\\ndrwxrwxr-x 3 kuhnn kuhnn 4096 May 18 06:10 公众号\\n-rw-rw-r-- 1 kuhnn kuhnn 13498 Feb 9 13:42 项目计划书_银发经济与欧洲旅行业务_SilverRoutes_Europe_2026-02-09.md\\ndrwxr-xr-x 15 kuhnn kuhnn 4096 Mar 6 21:48 Cyber_Nail_Passport\\n-rw-r--r-- 1 kuhnn kuhnn 888 May 18 01:13 minimax-api.txt\\ndrwxrwxr-x 3 kuhnn kuhnn 4096 Mar 5 00:10 NPM_theme_curation\\ndrwxrwxr-x 8 kuhnn kuhnn 4096 Mar 9 03:10 openclaw_backup\\ndrwxrwxr-x 3 kuhnn kuhnn 4096 Mar 2 00:46 RCA_MediaLibrary\\n-rw-r--r-- 1 kuhnn kuhnn 190650 May 18 04:33 Screenshot 2026-05-18 at 04.33.35.png\\ndrwxrwxrwx 4 kuhnn kuhnn 4096 May 18 01:28 .SynologyWorkingDirectory\\n/home/kuhnn/SynologyDrive\\n/home/kuhnn/SynologyDrive/Cyber_Nail_Passport\\n/home/kuhnn/SynologyDrive/Cyber_Nail_Passport/06_Interaction_Experience\\n/home/kuhnn/SynologyDrive/Cyber_Nail_Passport/06_Interaction_Experience/{text,video_frames,diagrams,test_logs,notes}\\n/home/kuhnn/SynologyDrive/Cyber_Nail_Passport/04_Interface_System\\n/home/kuhnn/SynologyDrive/Cyber_Nail_Passport/04_Interface_System/{text,hardware,diagrams,ue_blueprints,code,notes}\\n/home/kuhnn/SynologyDrive/Cyber_Nail_Passport/12_Final_Work\\n/home/kuhnn/SynologyDrive/Cyber_Nail_Passport/12_Final_Work/{video,stills,notes}\\n/home/kuhnn/SynologyDrive/Cyber_Nail_Passport/09_Exports\\n/home/kuhnn/SynologyDrive/Cyber_Nail_Passport/09_Exports/{ppt,indesign,pdf,images}\\n/home/kuhnn/SynologyDrive/Cyber_Nail_Passport/10_References\\n/home/kuhnn/SynologyDrive/Cyber_Nail_Passport/01_Embodied_Experience\\n/home/kuhnn/SynologyDrive/Cyber_Nail_Passport/01_Embodied_Experience/{text,images,notes}\\n/home/kuhnn/SynologyDrive/Cyber_Nail_Passport/01_Embodied_Experience/断的美甲\\n/home/kuhnn/SynologyDrive/Cyber_Nail_Passport/01_Embodied_Experience/arduino部分\\n/home/kuhnn/SynologyDrive/Cyber_Nail_Passport/01_Embodied_Experience/tiktok美甲\\n/home/kuhnn/SynologyDrive/Cyber_Nail_Passport/01_Embodied_Experience/sunbo美甲日常\\n/home/kuhnn/SynologyDrive/Cyber_Nail_Passport/02_Research_Question\\n/home/kuhnn/SynologyDrive/Cyber_Nail_Passport/02_Research_Question/美甲历史- 权利身份\\n/home/kuhnn/SynologyDrive/Cyber_Nail_Passport/02_Research_Question/{text,images,notes}\", \"exit_code\": 0, \"error\": null}",
"tool_call_id": "call_function_3vw21ztow96n_1"
},
{
"role": "assistant",
"content": "",
"reasoning": "SynologyDrive里没有现成的\"group\"文件夹。我需要问用户group文件夹的具体路径，或者直接创建一个新的group文件夹来存放n8n学习计划。",
"finish_reason": "tool_calls",
"reasoning_content": "SynologyDrive里没有现成的\"group\"文件夹。我需要问用户group文件夹的具体路径，或者直接创建一个新的group文件夹来存放n8n学习计划。",
"reasoning_details": [
{
"signature": "d2b16d5e9bea1b1bfa8784f0ee04e0a29b4dd2d2e88e501403a22f86befd8a31",
"thinking": "SynologyDrive里没有现成的\"group\"文件夹。我需要问用户group文件夹的具体路径，或者直接创建一个新的group文件夹来存放n8n学习计划。",
"type": "thinking"
}
],
"tool_calls": [
{
"id": "call_function_bebvzxzvxjvn_1",
"call_id": "call_function_bebvzxzvxjvn_1",
"response_item_id": "fc_function_bebvzxzvxjvn_1",
"type": "function",
"function": {
"name": "clarify",
"arguments": "{\"question\": \"Synology Drive \\u91cc\\u6ca1\\u627e\\u5230 \\\"group\\\" \\u6587\\u4ef6\\u5939\\uff0c\\u8bf7\\u95ee\\u8fd9\\u4e2a\\u6587\\u4ef6\\u5939\\u7684\\u5b8c\\u6574\\u8def\\u5f84\\u662f\\u4ec0\\u4e48\\uff1f\\u6216\\u8005\\u4f60\\u60f3\\u8ba9\\u6211\\u76f4\\u63a5\\u5728 SynologyDrive \\u4e0b\\u521b\\u5efa\\u4e00\\u4e2a `group` \\u6587\\u4ef6\\u5939\\u6765\\u5b58\\u653e n8n \\u5b66\\u4e60\\u8ba1\\u5212\\uff1f\", \"choices\": [\"\\u76f4\\u63a5\\u5728 SynologyDrive \\u4e0b\\u521b\\u5efa group \\u6587\\u4ef6\\u5939\", \"\\u544a\\u8bc9\\u4f60\\u5177\\u4f53\\u8def\\u5f84\"]}"
}
}
]
},
{
"role": "tool",
"name": "clarify",
"content": "{\"question\": \"Synology Drive 里没找到 \\\"group\\\" 文件夹，请问这个文件夹的完整路径是什么？或者你想让我直接在 SynologyDrive 下创建一个 `group` 文件夹来存放 n8n 学习计划？\", \"choices_offered\": [\"直接在 SynologyDrive 下创建 group 文件夹\", \"告诉你具体路径\"], \"user_response\": \"就是synology这文件夹下边新建一个教程文件夹即可\"}",
"tool_call_id": "call_function_bebvzxzvxjvn_1"
},
{
"role": "assistant",
"content": "",
"reasoning": "用户想在 SynologyDrive 下新建一个教程文件夹。让我创建文件夹并写入学习计划。",
"finish_reason": "tool_calls",
"reasoning_content": "用户想在 SynologyDrive 下新建一个教程文件夹。让我创建文件夹并写入学习计划。",
"reasoning_details": [
{
"signature": "499224386b312e8a119b2e56f1d46d7fb912490ded8e84d3fcc8149ac47270ed",
"thinking": "用户想在 SynologyDrive 下新建一个教程文件夹。让我创建文件夹并写入学习计划。",
"type": "thinking"
}
],
"tool_calls": [
{
"id": "call_function_iexh9872qv3z_1",
"call_id": "call_function_iexh9872qv3z_1",
"response_item_id": "fc_function_iexh9872qv3z_1",
"type": "function",
"function": {
"name": "web_extract",
"arguments": "{\"urls\": [\"https://n8n.akashio.com/\", \"https://jimmysong.io/zh/book/n8n-handbook/\"]}"
}
},
{
"id": "call_function_iexh9872qv3z_2",
"call_id": "call_function_iexh9872qv3z_2",
"response_item_id": "fc_function_iexh9872qv3z_2",
"type": "function",
"function": {
"name": "terminal",
"arguments": "{\"command\": \"mkdir -p /home/kuhnn/SynologyDrive/n8n\\u6559\\u7a0b\"}"
}
}
]
},
{
"role": "tool",
"name": "web_extract",
"content": "{\n \"results\": [\n {\n \"url\": \"https://n8n.akashio.com/\",\n \"title\": \"欢迎来到n8n 中文教程| 一个中文n8n 学习社区\",\n \"content\": \"# n8n 中文教程 - 学习社区\\n\\n**网址**: https://n8n.akashio.com/\\n**定位**: 中文 n8n 学习社区\\n**Slogan**: 简单易懂的现代魔法\\n\\n---\\n\\n## 官方资源链接\\n\\n| 资源 | 链接 |\\n|------|------|\\n| n8n 官方网站 | https://n8n.partnerlinks.io/5ke1e3gdv6jj |\\n| 官方 GitHub | https://github.com/n8n-io/n8n |\\n| 官方英文论坛 | https://community.n8n.io/ |\\n| 官方文档 | https://docs.n8n.io/ |\\n| 官方模板库 | https://n8n.io/workflows/ |\\n\\n---\\n\\n## 教程内容总览\\n\\n### 🚀 掌握你的第一个魔法（入门系列）\\n\\n- 🚢 选择适合的 n8n 安装部署方式\\n- 💻 如何在本机部署/安装 n8n\\n- ☁️ 如何在服务器部署/安装 n8n\\n- 🗃️ 熟悉 n8n 的界面\\n- 1️⃣ 制作你的第一个 n8n\\n- 🔰 制作第一个与大模型配合的 n8n 程序\\n- 💵 n8n 收费吗？（不同版本对比）\\n\\n### 🧠 现代魔法编程思想\\n\\n- 👾 学习低代码的正确思路\\n- 🧪 学会单步调试与撰写测试用例\\n\\n### 🔧 n8n 使用教程（核心教程）\\n\\n- 🔎 从原始需求找到适合自己的节点\\n- 🔐 保障私有部署环境安全的基本操作\\n- 🤴 注册社区版以获得更多功能\\n- 🔂 常用逻辑节点详解（条件、循环、Switch、Merge）\\n- 🌟 AI 节点详细介绍\\n- 🆓 半开放式节点（Code/HTTP Request）详细介绍\\n- 🇨🇳 n8n 如何接入国产大模型？\\n- 📤 n8n 内建变量与方法\\n- MCP（模型上下文协议）使用指南\\n- 🐍 如何安装/使用第三方 Python 库\\n\\n### 📂 n8n 实战案例\\n\\n| 案例 | 描述 |\\n|------|------|\\n| 📕 RSS 阅读分流器 | 基于 RSS 的文章自动分类 |\\n| 🍔 县城麦当劳查询 | 获取中国县城麦当劳分布 |\\n| 🔂 n*m 循环实现 | 复杂循环场景处理 |\\n| 🎵 抖音→Notion | 短视频一键收藏到知识库 |\\n| 🤖 Telegram 机器人 | 自动化 Bot 开发 |\\n| 🔍 免费 Deep Research | AI 研究工具搭建 |\\n\\n### 📋 杂项/运维相关\\n\\n- 💼 n8n 公司介绍\\n- 🤝 Workflow 分享\\n- 🇨🇳 中文版/汉化方法\\n- 🐖 数据库变大处理\\n- 🔗 与本地服务链接\\n- 💬 接入微信\\n- ⏱️ 定时/订阅源触发异常排查\\n- ↕️ 正确升级 n8n\\n- 🔑 密码找回\\n- 🗒️ 大版本更新日志\\n- 🚫 关闭 Insights 功能\\n\\n---\\n\\n## 关键要点\\n\\n> **n8n 定位**: 开源工作流自动化工具，被称为\\\"简单易懂的现代魔法\\\"\\n\\n**学习路径建议**:\\n1. 选择部署方式（本地/服务器）\\n2. 熟悉界面\\n3. 制作第一个工作流\\n4. 学习大模型配合使用\\n5. 掌握逻辑节点（条件/循环）\\n6. 学习 Code/HTTP 节点扩展能力\\n\\n**版本**: 1.0 已上线\",\n \"error\": null\n },\n {\n \"url\": \"https://jimmysong.io/zh/book/n8n-handbook/\",\n \"title\": \"n8n 入门教程\",\n \"content\": \"#### 技术专栏\\n\\n#### 技术专栏\\n\\n人工智能工程、大模型、智能体应用与实践。\\n\\nKubernetes、Service Mesh、Envoy、Gateway 等。\\n\\n工程文化与实践、研发流程、开发工具。\\n\\n开源生态、社区贡献与行业动态。\\n\\n#### 更多内容\\n\\n#### 更多内容\\n\\n书评、影评、游戏评论、硬件评测和事件分析。\\n\\n世界各地的旅行记录和体验。\\n\\n技术会议参会回顾和见解，如 KubeCon 等。\\n\\n对经济、文化、政治和社会的思考与分析。\\n\\n#### AI\\n\\n#### AI\\n\\nAI 原生基础设施与运行时架构实践。\\n\\nAI Agent 架构模式与落地实践案例。\\n\\n为不确定性而设计的系统。\\n\\nKubernetes 中的 GPU 调度与虚拟化。\\n\\n#### 云原生\\n\\n#### 云原生\\n\\n从零到精通 K8s 架构、组件与实践。\\n\\n服务网格流量治理与安全实战。\\n\\n设计拥抱变化的软件。\\n\\nEnvoy 原理与实战教程。\\n\\n#### 更多\\n\\n#### 更多\\n\\nIstio 服务网格原理与实践。\\n\\nSpring Cloud 与 Spring Boot 实践。\\n\\n从零到精通 Hugo 架构、组件与实践。\\n\\n可视化工作流自动化实战。\\n\\n#### 精选资源\\n\\n#### 精选资源\\n\\n全面的 AI 开源项目与工具导航。\\n\\n面向开发者与运维的实用教程与手册。\\n\\n技术分享与大会演讲的幻灯片资料。\\n\\n#### 交流与反馈\\n\\n#### 交流与反馈\\n\\n与我联系，一起探讨云原生与 AI。\\n\\n演讲及活动时间表。\\n\\n获取最新动态与公告。\\n\\n#### 更多\\n\\n#### 更多\\n\\n中英文对照规范术语表，用于翻译和写作参考。\\n\\n记录旅行中的点点滴滴。\\n\\nBilibili 频道，涵盖云原生与 AI 视频教程。\\n\\n#### 快速链接\\n\\n#### 快速链接\\n\\n了解 Jimmy Song 的背景与工作。\\n\\n通过不同方式与 Jimmy 取得联系。\\n\\n查看 HAMi 开源项目。\\n\\n访问密瓜智能官方网站。\\n\\n#### 微信公众号\\n\\n#### 微信公众号\\n\\n\\n\\n关注我的微信公众号「几米宋」，获取云原生与 AI 的最新文章。\\n\\n#### 微信联系\\n\\n#### 微信联系\\n\\n\\n\\n扫码添加 Jimmy 个人微信，交流云原生与 AI 技术实践。\\n\\n#### 站内搜索\\n\\n# n8n 入门教程\\n\\n内容导航\\n\\n本教程帮助你快速掌握 [n8n](https://n8n.io) 的自动化工作流开发，内容涵盖：\\n\\n## 内容摘要\\n\\n## 章节目录\\n\\n[简介](/zh/book/n8n-handbook/introduction/)\\n\\n了解 n8n 的基本架构、核心概念以及工作流的基本构成。\\n\\n[安装](/zh/book/n8n-handbook/installation/)\\n\\n了解如何在 macOS 上通过 Homebrew 或 npm 安装和运行 n8n，包括配置环境变量和权限设置。\\n\\n[变量与配置](/zh/book/n8n-handbook/configuration/)\\n\\n详细介绍 n8n 的环境变量与内置变量用法，并给出“多输入合并”的正确姿势（Merge、表达式与 Code 节点）。\\n\\n[权限与路径管理](/zh/book/n8n-handbook/permission/)\\n\\n简要介绍 n8n 权限与路径管理，助你避免常见错误，保障数据安全与稳定运行。\\n\\n[Workflow 编辑器](/zh/book/n8n-handbook/workflow-editor/)\\n\\n深入了解 n8n Workflow 编辑器的使用方法，包括界面布局、节点操作和工作流调试技巧。\\n\\n[常用节点](/zh/book/n8n-handbook/common-nodes/)\\n\\n了解 n8n 中常用节点的使用方法和配置示例，包括文件读写、HTTP 请求、条件判断等节点。\\n\\n[触发节点](/zh/book/n8n-handbook/trigger-nodes/)\\n\\n了解 n8n 中不同类型的触发节点，包括 Manual Trigger、Schedule Trigger 和 Webhook Trigger 的使用方法和区别。\\n\\n[插件机制与扩展方式](/zh/book/n8n-handbook/plugin-mechanism/)\\n\\n深入了解 n8n 的插件机制和扩展方式，学习如何开发自定义节点和集成外部服务。\\n\\n[代码和命令节点](/zh/book/n8n-handbook/code-and-exec-plugins/)\\n\\n比较并介绍 n8n 中的 Code 与 Execute Command 节点的原理、适用场景、限制与实践建议。\\n\\n[本地程序集成](/zh/book/n8n-handbook/local-program-integration/)\\n\\n学习如何使用 Execute Command 节点将本地脚本和程序集成到 n8n 工作流中。\\n\\n[大模型集成](/zh/book/n8n-handbook/llm-integration/)\\n\\n了解如何通过 HTTP Request 节点调用大语言模型 API，如 OpenAI 或 Google Gemini，并处理返回的 JSON 数据。\\n\\n[Google 集成](/zh/book/n8n-handbook/google-services-integration/)\\n\\n学习如何集成 Google 服务到 n8n 工作流中，包括 Google Sheets、Google Drive 和 Gmail 的使用方法。\\n\\n[PDF 翻译示例](/zh/book/n8n-handbook/pdf-translation-example/)\\n\\n通过一个完整的实战示例，学习如何使用 n8n 将英文 PDF 转换为 Markdown，调用大语言模型翻译，再生成中文 PDF。\\n\\n[FAQ](/zh/book/n8n-handbook/troubleshooting/)\\n\\n了解 n8n 使用过程中可能遇到的常见问题及其解决方法，掌握调试工作流的技巧。\\n\\n提交勘误/建议\\n\\n图书信息\\n\\n导航\\n\\n公告\\n\\n精选\\n\\n关于\\n\\n构建支持\\n\\n关注\\n\\n\\n\\n### 快速链接\\n\\n### 关注\\n\\n© 2017-2026 Jimmy Song 保留所有权利 · [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/)\",\n \"error\": null\n }\n ]\n}",
"tool_call_id": "call_function_iexh9872qv3z_1"
},
{
"role": "tool",
"name": "terminal",
"content": "{\"output\": \"\", \"exit_code\": 0, \"error\": null}",
"tool_call_id": "call_function_iexh9872qv3z_2"
},
{
"role": "assistant",
"content": "",
"reasoning": "Now I have enough information to create a comprehensive n8n learning plan. Let me create a well-structured markdown document with the learning plan and save it to the Synology Drive n8n教程 folder.\n\nKey resources I found:\n1. n8n.akashio.com - Chinese learning community\n2. Jimmy Song's n8n handbook (jimmysong.io)\n3. Various YouTube tutorials\n4. iApp guide for beginners\n5. Tencent Cloud articles\n\nLet me create a structured learning plan in Chinese.",
"finish_reason": "tool_calls",
"reasoning_content": "Now I have enough information to create a comprehensive n8n learning plan. Let me create a well-structured markdown document with the learning plan and save it to the Synology Drive n8n教程 folder.\n\nKey resources I found:\n1. n8n.akashio.com - Chinese learning community\n2. Jimmy Song's n8n handbook (jimmysong.io)\n3. Various YouTube tutorials\n4. iApp guide for beginners\n5. Tencent Cloud articles\n\nLet me create a structured learning plan in Chinese.",
"reasoning_details": [
{
"signature": "cf582bbe1639b13046e67ee3ebd3a9f3cf03a6e10be12047e2bf5c5a490b0b4b",
"thinking": "Now I have enough information to create a comprehensive n8n learning plan. Let me create a well-structured markdown document with the learning plan and save it to the Synology Drive n8n教程 folder.\n\nKey resources I found:\n1. n8n.akashio.com - Chinese learning community\n2. Jimmy Song's n8n handbook (jimmysong.io)\n3. Various YouTube tutorials\n4. iApp guide for beginners\n5. Tencent Cloud articles\n\nLet me create a structured learning plan in Chinese.",
"type": "thinking"
}
],
"tool_calls": [
{
"id": "call_function_hs833lqaqgn8_1",
"call_id": "call_function_hs833lqaqgn8_1",
"response_item_id": "fc_function_hs833lqaqgn8_1",
"type": "function",
"function": {
"name": "write_file",
"arguments": "{\"path\": \"/home/kuhnn/SynologyDrive/n8n\\u6559\\u7a0b/n8n\\u5b66\\u4e60\\u8ba1\\u5212.md\", \"content\": \"# n8n \\u5de5\\u4f5c\\u6d41\\u81ea\\u52a8\\u5316 \\u2014 \\u5b66\\u4e60\\u8ba1\\u5212\\n\\n> \\u5f00\\u6e90\\u3001\\u65e0\\u4ee3\\u7801/\\u4f4e\\u4ee3\\u7801\\u3001\\u8fde\\u63a5 400+ \\u5e94\\u7528\\u7684\\u81ea\\u52a8\\u5316\\u5de5\\u5177\\n\\n---\\n\\n## \\ud83d\\udcda \\u5b66\\u4e60\\u8def\\u5f84\\u603b\\u89c8\\n\\n```\\n\\u7b2c\\u4e00\\u9636\\u6bb5\\uff1a\\u5165\\u95e8\\uff081-3\\u5929\\uff09\\n \\u2193\\n\\u7b2c\\u4e8c\\u9636\\u6bb5\\uff1a\\u57fa\\u7840\\u64cd\\u4f5c\\uff084-7\\u5929\\uff09\\n \\u2193\\n\\u7b2c\\u4e09\\u9636\\u6bb5\\uff1a\\u6838\\u5fc3\\u8282\\u70b9\\uff088-14\\u5929\\uff09\\n \\u2193\\n\\u7b2c\\u56db\\u9636\\u6bb5\\uff1a\\u5b9e\\u6218\\u5e94\\u7528\\uff0815-21\\u5929\\uff09\\n \\u2193\\n\\u7b2c\\u4e94\\u9636\\u6bb5\\uff1a\\u8fdb\\u9636\\u4e0e\\u8fd0\\u7ef4\\uff0822-30\\u5929\\uff09\\n```\\n\\n---\\n\\n## \\u7b2c\\u4e00\\u9636\\u6bb5\\uff1a\\u8ba4\\u8bc6 n8n\\n\\n### \\u76ee\\u6807\\uff1a\\u7406\\u89e3 n8n \\u662f\\u4ec0\\u4e48\\uff0c\\u80fd\\u89e3\\u51b3\\u4ec0\\u4e48\\u95ee\\u9898\\n\\n| \\u5b66\\u4e60\\u5185\\u5bb9 | \\u63a8\\u8350\\u8d44\\u6e90 | \\u9884\\u8ba1\\u65f6\\u95f4 |\\n|---------|---------|---------|\\n| n8n \\u57fa\\u672c\\u6982\\u5ff5 | [\\u77e5\\u4e4e\\uff1a\\u666e\\u901a\\u4eba\\u4e5f\\u80fd\\u7528\\u7684\\u81ea\\u52a8\\u5316\\u5de5\\u5177](https://zhuanlan.zhihu.com/p/1986390534802129838) | 30\\u5206\\u949f |\\n| n8n vs Zapier vs Make \\u5bf9\\u6bd4 | [iApp \\u5b8c\\u5168\\u6307\\u5357](https://iapp.co.th/zh-CN/blog/what-is-n8n-complete-guide) | 20\\u5206\\u949f |\\n| \\u90e8\\u7f72\\u65b9\\u5f0f\\u9009\\u62e9\\uff08\\u672c\\u5730/\\u4e91\\uff09 | [\\u817e\\u8baf\\u4e91\\uff1a\\u4ece0\\u52301\\u73a9\\u8f6cN8N](https://cloud.tencent.com/developer/article/2609101) | 30\\u5206\\u949f |\\n| \\u5b89\\u88c5\\u7b2c\\u4e00\\u4e2a n8n \\u5b9e\\u4f8b | [adbest \\u4e2d\\u6587\\u6559\\u5b66](https://adbest.com.tw/blog/what-is-n8n/) | 1\\u5c0f\\u65f6 |\\n\\n### \\u6838\\u5fc3\\u6982\\u5ff5\\u901f\\u8bb0\\n- **Trigger\\uff08\\u89e6\\u53d1\\u5668\\uff09**\\uff1a\\u5de5\\u4f5c\\u6d41\\u7684\\u8d77\\u70b9\\uff08\\u5b9a\\u65f6\\u3001Webhook\\u3001\\u624b\\u52a8\\uff09\\n- **Node\\uff08\\u8282\\u70b9\\uff09**\\uff1a\\u6267\\u884c\\u5177\\u4f53\\u64cd\\u4f5c\\u7684\\u6a21\\u5757\\n- **Workflow\\uff08\\u5de5\\u4f5c\\u6d41\\uff09**\\uff1a\\u4e32\\u8054\\u8d77\\u6765\\u7684\\u81ea\\u52a8\\u5316\\u6d41\\u7a0b\\n- **Credentials\\uff08\\u51ed\\u636e\\uff09**\\uff1a\\u5b58\\u50a8\\u7684\\u7b2c\\u4e09\\u65b9\\u670d\\u52a1\\u6388\\u6743\\u4fe1\\u606f\\n\\n---\\n\\n## \\u7b2c\\u4e8c\\u9636\\u6bb5\\uff1a\\u754c\\u9762\\u4e0e\\u57fa\\u672c\\u64cd\\u4f5c\\n\\n### \\u76ee\\u6807\\uff1a\\u719f\\u6089\\u7f16\\u8f91\\u5668\\uff0c\\u80fd\\u521b\\u5efa\\u7b80\\u5355\\u5de5\\u4f5c\\u6d41\\n\\n| \\u5b66\\u4e60\\u5185\\u5bb9 | \\u63a8\\u8350\\u8d44\\u6e90 | \\u9884\\u8ba1\\u65f6\\u95f4 |\\n|---------|---------|---------|\\n| \\u7ba1\\u7406\\u754c\\u9762\\u529f\\u80fd\\u4ecb\\u7ecd | [Raymond Houch \\u65b0\\u624b\\u5165\\u95e8](https://raymondhouch.com/lifehacker/digital-workflow/n8n-beginner-guide/) | 45\\u5206\\u949f |\\n| \\u8282\\u70b9\\u64cd\\u4f5c\\uff08\\u6dfb\\u52a0/\\u8fde\\u63a5/\\u914d\\u7f6e\\uff09 | Jimmy Song \\u624b\\u518c - [Workflow \\u7f16\\u8f91\\u5668](https://jimmysong.io/zh/book/n8n-handbook/workflow-editor/) | 1\\u5c0f\\u65f6 |\\n| \\u7b2c\\u4e00\\u4e2a\\u5de5\\u4f5c\\u6d41\\u5b9e\\u64cd | [\\u817e\\u8baf\\u4e91\\uff1a\\u83b7\\u53d6\\u4eca\\u65e5\\u4fe1\\u606f\\u5e76\\u4fdd\\u5b58](https://cloud.tencent.com/developer/article/2609101) | 1\\u5c0f\\u65f6 |\\n\\n### \\u5fc5\\u5b66\\u57fa\\u7840\\u8282\\u70b9\\n- \\u2705 Manual Trigger\\uff08\\u624b\\u52a8\\u89e6\\u53d1\\uff09\\n- \\u2705 Schedule Trigger\\uff08\\u5b9a\\u65f6\\u89e6\\u53d1\\uff09\\n- \\u2705 Webhook\\uff08\\u63a5\\u6536\\u5916\\u90e8\\u8bf7\\u6c42\\uff09\\n- \\u2705 HTTP Request\\uff08\\u8c03\\u7528\\u5916\\u90e8 API\\uff09\\n- \\u2705 Edit Fields / Set\\uff08\\u6570\\u636e\\u5904\\u7406\\uff09\\n- \\u2705 If\\uff08\\u6761\\u4ef6\\u5206\\u652f\\uff09\\n- \\u2705 Code\\uff08\\u5199\\u4ee3\\u7801\\u81ea\\u5b9a\\u4e49\\u903b\\u8f91\\uff09\\n\\n---\\n\\n## \\u7b2c\\u4e09\\u9636\\u6bb5\\uff1a\\u6838\\u5fc3\\u8282\\u70b9\\u6df1\\u5165\\n\\n### \\u76ee\\u6807\\uff1a\\u638c\\u63e1\\u903b\\u8f91\\u63a7\\u5236\\u4e0e\\u6570\\u636e\\u5904\\u7406\\n\\n| \\u8282\\u70b9\\u7c7b\\u578b | \\u5b66\\u4e60\\u91cd\\u70b9 | \\u7ec3\\u4e60\\u9879\\u76ee |\\n|---------|---------|---------|\\n| \\u6761\\u4ef6\\u5224\\u65ad | If / Switch \\u5206\\u652f\\u903b\\u8f91 | \\u81ea\\u52a8\\u5206\\u7c7b\\u5904\\u7406\\u6570\\u636e |\\n| \\u5faa\\u73af\\u5904\\u7406 | Loop Over Items | \\u6279\\u91cf\\u5904\\u7406\\u591a\\u6761\\u8bb0\\u5f55 |\\n| \\u6570\\u636e\\u5408\\u5e76 | Merge\\uff08\\u591a\\u8f93\\u5165\\u5408\\u5e76\\uff09 | \\u6c47\\u603b\\u591a\\u4e2a\\u6765\\u6e90\\u6570\\u636e |\\n| \\u9519\\u8bef\\u5904\\u7406 | Error Trigger | \\u6dfb\\u52a0\\u5de5\\u4f5c\\u6d41\\u62a5\\u8b66 |\\n\\n### \\u63a8\\u8350\\u6559\\u7a0b\\n- **\\u4e2d\\u6587\\u793e\\u533a**\\uff1ahttps://n8n.akashio.com/ \\u2014 \\u5e38\\u7528\\u903b\\u8f91\\u8282\\u70b9\\u8be6\\u89e3\\n- **Jimmy Song**\\uff1ahttps://jimmysong.io/zh/book/n8n-handbook/common-nodes/\\n\\n---\\n\\n## \\u7b2c\\u56db\\u9636\\u6bb5\\uff1a\\u5b9e\\u6218\\u6848\\u4f8b\\n\\n### \\u4ece\\u7b80\\u5355\\u5230\\u590d\\u6742\\u7684\\u7ec3\\u4e60\\u9879\\u76ee\\n\\n#### \\ud83c\\udf31 \\u5165\\u95e8\\u7ea7\\uff08\\u5b8c\\u6210 2-3 \\u4e2a\\uff09\\n1. **\\u6bcf\\u65e5\\u5929\\u6c14\\u63a8\\u9001** \\u2192 \\u5b9a\\u65f6\\u6293\\u5929\\u6c14 API \\u2192 \\u53d1\\u9001\\u5230 Telegram/\\u5fae\\u4fe1\\n2. **\\u8868\\u5355\\u6570\\u636e\\u81ea\\u52a8\\u5b58\\u6863** \\u2192 Google Form \\u63d0\\u4ea4 \\u2192 \\u5199\\u5165 Google Sheet\\n3. **RSS \\u9605\\u8bfb\\u5668** \\u2192 \\u5b9a\\u65f6\\u6293\\u53d6\\u535a\\u5ba2\\u66f4\\u65b0 \\u2192 \\u6458\\u8981\\u53d1\\u9001\\u5230\\u90ae\\u7bb1\\n\\n#### \\ud83d\\ude80 \\u8fdb\\u9636\\u7ea7\\uff08\\u5b8c\\u6210 2-3 \\u4e2a\\uff09\\n4. **Telegram \\u673a\\u5668\\u4eba** \\u2192 \\u81ea\\u52a8\\u56de\\u590d / \\u67e5\\u8be2\\u4fe1\\u606f / \\u89e6\\u53d1\\u5de5\\u4f5c\\u6d41\\n - \\u53c2\\u8003\\uff1ahttps://n8n.akashio.com/telegram\\u673a\\u5668\\u4eba\\n5. **AI \\u5185\\u5bb9\\u52a9\\u624b** \\u2192 \\u8c03\\u7528 GPT/Gemini \\u2192 \\u81ea\\u52a8\\u6da6\\u8272/\\u7ffb\\u8bd1/\\u603b\\u7ed3\\n - \\u53c2\\u8003\\uff1ahttps://jimmysong.io/zh/book/n8n-handbook/llm-integration/\\n6. **\\u8de8\\u5e73\\u53f0\\u5185\\u5bb9\\u540c\\u6b65** \\u2192 \\u6296\\u97f3/\\u5c0f\\u7ea2\\u4e66 \\u2192 \\u81ea\\u52a8\\u5b58\\u5165 Notion\\n\\n#### \\ud83d\\udc8e \\u9ad8\\u7ea7\\uff08\\u5b8c\\u6210 1-2 \\u4e2a\\uff09\\n7. **PDF \\u81ea\\u52a8\\u5316\\u5904\\u7406** \\u2192 \\u63d0\\u53d6 \\u2192 \\u7ffb\\u8bd1 \\u2192 \\u91cd\\u65b0\\u751f\\u6210\\n8. **Deep Research \\u5de5\\u4f5c\\u6d41** \\u2192 \\u81ea\\u52a8\\u7814\\u7a76 + \\u751f\\u6210\\u62a5\\u544a\\n9. **\\u591a\\u6b65\\u9aa4\\u590d\\u6742\\u81ea\\u52a8\\u5316** \\u2192 \\u4e32\\u8054 5+ \\u670d\\u52a1\\n\\n### \\u5b98\\u65b9\\u6a21\\u677f\\u5e93\\n\\u76f4\\u63a5\\u5bfc\\u5165\\u73b0\\u6210\\u6a21\\u677f\\u4fee\\u6539\\u5b66\\u4e60\\uff1a\\n\\ud83d\\udc49 https://n8n.io/workflows/\\n\\n---\\n\\n## \\u7b2c\\u4e94\\u9636\\u6bb5\\uff1a\\u90e8\\u7f72\\u4e0e\\u8fd0\\u7ef4\\n\\n### \\u76ee\\u6807\\uff1a\\u8ba9\\u5de5\\u4f5c\\u6d41\\u7a33\\u5b9a\\u8fd0\\u884c\\n\\n| \\u4e3b\\u9898 | \\u5b66\\u4e60\\u5185\\u5bb9 |\\n|-----|---------|\\n| \\u4e91\\u670d\\u52a1\\u5668\\u90e8\\u7f72 | Zeabur / Docker / Railway \\u90e8\\u7f72\\u6559\\u7a0b |\\n| \\u6570\\u636e\\u5907\\u4efd | \\u81ea\\u52a8\\u5907\\u4efd\\u5de5\\u4f5c\\u6d41\\u548c\\u51ed\\u636e |\\n| \\u76d1\\u63a7\\u62a5\\u8b66 | Error Trigger + \\u901a\\u77e5\\u673a\\u5668\\u4eba |\\n| \\u5b89\\u5168\\u8bbe\\u7f6e | 2FA\\u3001\\u53cc\\u91cd\\u9a8c\\u8bc1\\u3001\\u6743\\u9650\\u7ba1\\u7406 |\\n| \\u7248\\u672c\\u66f4\\u65b0 | \\u5b89\\u5168\\u5347\\u7ea7 n8n \\u7248\\u672c |\\n\\n### \\u63a8\\u8350\\u9605\\u8bfb\\n- https://n8n.akashio.com/\\u5347\\u7ea7n8n\\n- https://n8n.akashio.com/\\u5b89\\u5168\\u64cd\\u4f5c\\n\\n---\\n\\n## \\ud83d\\udcd6 \\u4f18\\u8d28\\u6559\\u7a0b\\u8d44\\u6e90\\u6c47\\u603b\\n\\n### \\u7f51\\u7ad9/\\u535a\\u5ba2\\n| \\u540d\\u79f0 | \\u7f51\\u5740 | \\u7279\\u70b9 |\\n|-----|------|-----|\\n| n8n \\u4e2d\\u6587\\u6559\\u7a0b\\u793e\\u533a | https://n8n.akashio.com/ | \\u5168\\u9762\\u3001\\u4e2d\\u6587\\u53cb\\u597d |\\n| Jimmy Song \\u624b\\u518c | https://jimmysong.io/zh/book/n8n-handbook/ | \\u7cfb\\u7edf\\u3001\\u6df1\\u5165 |\\n| ADBest \\u6559\\u5b66 | https://adbest.com.tw/blog/what-is-n8n/ | \\u5b9e\\u6218\\u3001\\u53f0\\u6e7e\\u89c6\\u89d2 |\\n| Raymond Houch | https://raymondhouch.com/ | \\u8be6\\u7ec6\\u56fe\\u89e3 |\\n\\n### \\u89c6\\u9891\\u6559\\u7a0b\\n| \\u9891\\u9053/\\u89c6\\u9891 | \\u5185\\u5bb9 |\\n|----------|-----|\\n| [YouTube: n8n \\u65b0\\u624b\\u6559\\u7a0b playlist](https://www.youtube.com/playlist?list=PLxtaO-gmRzggbNVy1SSNA4kl9LshNunCR) | \\u5165\\u95e8\\u5230\\u8fdb\\u9636\\u7cfb\\u5217 |\\n| [YouTube: AI Agent \\u642d\\u5efa\\u6559\\u5b66](https://www.youtube.com/watch?v=b6AEsVRJjzI) | 0\\u57fa\\u7840\\u5230AI Agent |\\n\\n### \\u5b98\\u65b9\\u8d44\\u6e90\\n| \\u8d44\\u6e90 | \\u94fe\\u63a5 |\\n|-----|------|\\n| \\u5b98\\u65b9\\u6587\\u6863 | https://docs.n8n.io/ |\\n| \\u5b98\\u65b9\\u8bba\\u575b | https://community.n8n.io/ |\\n| \\u6a21\\u677f\\u5e93 | https://n8n.io/workflows/ |\\n| GitHub | https://github.com/n8n-io/n8n |\\n\\n---\\n\\n## \\ud83c\\udfaf \\u5b66\\u4e60\\u5efa\\u8bae\\n\\n1. **\\u6bcf\\u5929 30-60 \\u5206\\u949f**\\uff0c\\u575a\\u6301\\u6bd4\\u7a81\\u51fb\\u66f4\\u91cd\\u8981\\n2. **\\u5148\\u6284\\u540e\\u6539**\\uff1a\\u7528\\u73b0\\u6210\\u6a21\\u677f\\uff0c\\u7406\\u89e3\\u540e\\u518d\\u4fee\\u6539\\n3. **\\u52a8\\u624b\\u5b9e\\u8df5**\\uff1a\\u770b 10 \\u904d\\u4e0d\\u5982\\u4eb2\\u624b\\u505a 1 \\u904d\\n4. **\\u8bb0\\u5f55\\u95ee\\u9898**\\uff1a\\u9047\\u5230\\u5751\\u8bb0\\u4e0b\\u6765\\uff0c\\u4e0b\\u6b21\\u4e0d\\u8e29\\n5. **\\u52a0\\u5165\\u793e\\u533a**\\uff1a\\u6709\\u95ee\\u9898\\u53bb\\u5b98\\u65b9\\u8bba\\u575b\\u641c\\u7d22/\\u63d0\\u95ee\\n\\n---\\n\\n## \\ud83d\\udcc5 30 \\u5929\\u5b66\\u4e60\\u8ba1\\u5212\\u8868\\n\\n| \\u5468 | \\u4e3b\\u9898 | \\u76ee\\u6807 |\\n|---|------|-----|\\n| \\u7b2c1\\u5468 | \\u5165\\u95e8 + \\u754c\\u9762\\u719f\\u6089 | \\u80fd\\u521b\\u5efa\\u7b80\\u5355\\u5b9a\\u65f6\\u5de5\\u4f5c\\u6d41 |\\n| \\u7b2c2\\u5468 | \\u6838\\u5fc3\\u8282\\u70b9 | \\u638c\\u63e1\\u6761\\u4ef6\\u3001\\u5faa\\u73af\\u3001\\u6570\\u636e\\u5904\\u7406 |\\n| \\u7b2c3\\u5468 | \\u5b9e\\u6218\\u6848\\u4f8b 3-5 \\u4e2a | \\u5efa\\u7acb\\u81ea\\u5df1\\u7684\\u5e38\\u7528\\u5de5\\u4f5c\\u6d41 |\\n| \\u7b2c4\\u5468 | \\u90e8\\u7f72 + \\u8fd0\\u7ef4 | \\u7a33\\u5b9a\\u8fd0\\u884c\\uff0c\\u81ea\\u52a8\\u5907\\u4efd |\\n\\n---\\n\\n*\\u6700\\u540e\\u66f4\\u65b0\\uff1a2026-05-18*\\n*\\u6765\\u6e90\\uff1a\\u7f51\\u7edc\\u641c\\u7d22\\u6574\\u7406*\\n\"}"
}
}
]
},
{
"role": "tool",
"name": "write_file",
"content": "{\"bytes_written\": 6070, \"dirs_created\": true, \"lint\": {\"status\": \"skipped\", \"message\": \"No linter for .md files\"}}",
"tool_call_id": "call_function_hs833lqaqgn8_1"
},
{
"role": "assistant",
"content": "搞定了！已创建：\n\n**`~/SynologyDrive/n8n教程/n8n学习计划.md`**\n\n---\n\n**学习计划结构：**\n\n📚 **五阶段学习路径**（30天）\n\n| 周次 | 主题 |\n|-----|------|\n| 第1周 | 入门 + 界面熟悉 |\n| 第2周 | 核心节点（条件/循环/数据处理） |\n| 第3周 | 实战案例（天气推送、表单存档、Telegram Bot 等） |\n| 第4周 | 部署 + 运维 + 备份 |\n\n**配套资源：**\n- 中文社区：n8n.akashio.com\n- Jimmy Song 手册（系统深入）\n- 官方模板库：n8n.io/workflows\n- YouTube 视频教程\n\n**入门建议：** 先用官方 SaaS 体验版（14天免费），熟悉后再考虑自部署。",
"reasoning": "完成了。让我给用户一个简洁的总结。",
"finish_reason": "stop",
"reasoning_content": "完成了。让我给用户一个简洁的总结。",
"reasoning_details": [
{
"signature": "1a7b460fbbfbc5ef563090d2981a07de4d85a31bc0d5c1533fda060abe00c470",
"thinking": "完成了。让我给用户一个简洁的总结。",
"type": "thinking"
}
]
}
]
}