{
"session_id": "cron_18c46fde1520_20260518_090055",
"model": "MiniMax-M2.7",
"base_url": "https://api.minimaxi.com/anthropic",
"platform": "cron",
"session_start": "2026-05-18T09:00:56.094917",
"last_updated": "2026-05-18T09:02:29.664766",
"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 - 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 running as a scheduled cron job. There is no user present — you cannot ask questions, request clarification, or wait for follow-up. Execute the task fully and autonomously, making reasonable decisions where needed. Your final response is automatically delivered to the job's configured destination — put the primary content directly in your response.\n\nConversation started: Monday, May 18, 2026 09:01 AM\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": "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": "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": 17,
"messages": [
{
"role": "user",
"content": "[IMPORTANT: The user has invoked the \"morning-briefing\" skill, indicating they want you to follow its instructions. The full skill content is loaded below.]\n\n---\nname: morning-briefing\ndescription: \"Daily morning voice briefing for 坤哥 (London) — searches news/weather/art/London-local, cleans text for TTS, auto-plays on local speakers. Built on Hermes cron + Tavily + MiniMax TTS.\"\nversion: 1.1.0\nauthor: Hermes Agent\nplatforms: [linux]\ntags: [cron, telegram, tts, tavily, mini-max, news, voice, briefing, london]\nmetadata:\n cron_job_id: \"18c46fde1520\"\n tavily_key: \"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\"\n schedule: \"0 9 * * *\"\n user: 坤哥\n location: London\n minimax_tts_key_note: \"MINIMAX_API_KEY (TTS) is SEPARATE from MINIMAX_CN_API_KEY (chat). Both must be set. The TTS endpoint (speech-02-hd) uses api.minimaxi.com/v1/t2a_v2 and requires MINIMAX_API_KEY. The chat endpoint uses api.minimaxi.com/anthropic with MINIMAX_CN_API_KEY.\"\n---\n\n# Morning Briefing\n\nDaily voice briefing delivered to Telegram at 09:00 BST (16:00 北京).\n\n## Workflow\n\n1. `web_search` — search today's news via Tavily\n2. `web_search` — get weather for user's city\n3. **Art industry news** — web_search for \"艺术行业新闻 中国\" (museums, galleries, auctions, cultural heritage, etc.)\n4. Compile briefing text in Chinese\n5. **Convert all Arabic numerals to Chinese characters** (critical — see Pitfalls)\n6. **MiniMax TTS via `text_to_speech` tool** (preferred — best quality, broadcast style)\n7. **Playback on local speakers** — set volume to 80%, play via ffplay\n8. **Fallback: Local Piper** via `~/bin/tts_briefing.sh` (only if MiniMax fails)\n9. Cron auto-delivers to Telegram\n\n## User Profile\n- **Name**: 坤哥 (call him 坤哥, NOT K.W.)\n- **Location**: 伦敦\n- **Language**: 中文\n\n## Briefing Template\n\n```\n坤哥，早上好！今天是{dates}，{weekday}。\n\n重要新闻：\n{n}条新闻，每条一行\n\n艺术动态：\n{艺术新闻，1条}\n\n伦敦本地：\n{伦敦本地新闻，重点提TFL罢工和游行示威情况}\n\n伦敦天气：{weather}，气温{temp}。\n```\n\n## London Local News Priority\n重点监测（必须明确回答\"有\"或\"无\"）：\n- TFL 地铁/公交是否罢工\n- 是否有游行示威\n- 其他重要本地事件\n\n## Audio Playback (Local Speakers at 9 AM)\n\nAfter TTS generation, play the audio on the local machine's speakers at 80% volume:\n\n```bash\n# Set system volume to 80% (unmuted)\npactl set-sink-volume alsa_output.pci-0000_00_1f.3.analog-stereo 80%\npactl set-sink-mute alsa_output.pci-0000_00_1f.3.analog-stereo false\n\n# Play audio\nffplay -nodisp -autoexit -volume 80 /home/kuhnn/.hermes/audio_cache/tts_YYYYMMDD_HHMMSS.ogg &\n```\n\n**Audio device (ALSA):** `alsa_output.pci-0000_00_1f.3.analog-stereo` — confirm with `pactl list sinks` if different.\n\n## Pitfalls\n\n### TTS reads numbers as digits\nMiniMax TTS (and most Chinese TTS) reads `18°C`、`2026年5月18日`、`85%` as individual digits. **ALL numbers must be pre-converted to Chinese characters:**\n\n| Original | For TTS |\n|----------|---------|\n| 18°C | 十八度 |\n| 27°C | 二十七度 |\n| 2026年5月18日 | 二零二六年五月十八日 |\n| 85% | 百分之八十五 |\n| 79年 | 七十九年 |\n| 20~32°C | 二十到三十二度 |\n\nAlways apply this conversion in the prompt: e.g. `\"温度用中文，如'十八到二十七度'\"`\n\n## Cron Job Management\n\n```bash\n# List jobs\nhermes cron list\n\n# Run manually (for testing)\nhermes cron run \n\n# View output\ncat ~/.hermes/cron/output//*.md\n\n# Find latest audio file\nfind ~/.hermes/audio_cache/ -name \"*.ogg\" -newer ~/.hermes/cron/output//*.md\n```\n\nCurrent job ID: `18c46fde1520`\n\n## TTS: MiniMax API (Preferred — Best Quality)\n\nMiniMax TTS (speech-02-hd, voice: Chinese_Mandarin_News_Anchor) gives significantly better quality — natural pauses, proper intonation, broadcast style. Use `text_to_speech` tool directly.\n\n**IMPORTANT — Cron environment:** Cron runs in a fresh subprocess without your session's env vars. Before calling `text_to_speech`, the agent MUST load .env:\n```bash\nexport $(grep MINIMAX_API_KEY /home/kuhnn/.hermes/.env | xargs)\n```\nThe `skills: [morning-briefing]` attachment on the cron job ensures the skill is loaded, which triggers the env loading logic. If TTS still fails with \"MINIMAX_API_KEY not set\", manually add the export step to the cron prompt.\n\n**TTS config (in cron prompt):**\n```\n使用 text_to_speech 工具（provider: minimax, model: speech-02-hd, voice: Chinese (Mandarin)_News_Anchor）\n输出 .ogg 格式文件\n在回复末尾写：MEDIA:/home/kuhnn/.hermes/audio_cache/tts_YYYYMMDD_HHMMSS.ogg\n```\n\n**Rate limit:** MiniMax 年计划 1500次/5小时。超出后 cron 会静默失败，fallback 到 Piper。\n\n## TTS: Piper (Fallback — Fully Offline)\n\nWhen MiniMax is unavailable (quota exhausted, network down), fall back to local Piper via `~/bin/tts_briefing.sh`:\n\n```bash\n# Generate audio from text\necho \"播报文本内容\" | ~/bin/tts_briefing.sh --out /home/kuhnn/.hermes/audio_cache/tts_$(date +%Y%m%d_%H%M%S).wav\n\n# Convert to .ogg for Telegram\nffmpeg -i /home/kuhnn/.hermes/audio_cache/tts_YYYYMMDD_HHMMSS.wav \\\n -acodec libopus /home/kuhnn/.hermes/audio_cache/tts_YYYYMMDD_HHMMSS.ogg -y\n\n# Deliver: MEDIA:/home/kuhnn/.hermes/audio_cache/tts_YYYYMMDD_HHMMSS.ogg\n```\n\n**Piper quality note:** csukuangfj/vits-piper-zh_CN-huayan-medium has mechanical pauses and flat intonation. Acceptable for fallback, not ideal for daily use.\n\n**Piper setup:** `pip install piper-tts` → `~/.local/bin/piper` + model `csukuangfj/vits-piper-zh_CN-huayan-medium` (HuggingFace cache). Use **python3.10** (not 3.11) for huggingface_hub downloads.\n\n## Reference Files\n\n- `references/brief_text_clean.py` — Python TTS text cleaner (numbers→中文, acronyms→full form, punctuation normalization). Derived from OpenClaw's offline TTS pipeline.\n- `references/brief_replacements.json` — Acronym/name replacement dictionary used by the cleaner.\n- `references/tts-local-setup.md` — Piper model download, local TTS cron integration, MiniMax API key note.\n\n## Legacy (OpenClaw)\n\nOpenClaw used sherpa-onnx with `brief_text_clean.py` + `brief_replacements.json` for offline TTS. The cleaning script handled:\n- Acronyms: BBC → 英国广播公司\n- Names: Emmanuel Macron → 马克龙\n- Numbers → Chinese characters\n- Punctuation normalization for speech\n\nThese files are preserved in: `/home/kuhnn/SynologyDrive/openclaw_backup/snapshot_2026-03-09_031002/bin/`\n\n**Note:** The current morning-briefing cron uses MiniMax TTS, which requires `MINIMAX_API_KEY` (set separately from `MINIMAX_CN_API_KEY` used for chat). TTS failures with \"MINIMAX_API_KEY not set\" mean the TTS key is missing — check that `MINIMAX_API_KEY` is in `.env`, not just `MINIMAX_CN_API_KEY`.\n\nThe user has provided the following instruction alongside the skill invocation: [IMPORTANT: You are running as a scheduled cron job. DELIVERY: Your final response will be automatically delivered to the user — do NOT use send_message or try to deliver the output yourself. Just produce your report/output as your final response and the system handles the rest. SILENT: If there is genuinely nothing new to report, respond with exactly \"[SILENT]\" (nothing else) to suppress delivery. Never combine [SILENT] with content — either report your findings normally, or say [SILENT] and nothing more.]\n\n你是坤哥的每日播报员。每早九点运行。\n\n## 搜索任务（并行）\n\n1. **重要新闻**：Tavily 搜索 \"today's top news China OR world 2026\" — 抓3条摘要\n2. **艺术动态**：Tavily 搜索 \"艺术行业新闻 中国\" — 抓1条（博物馆、画廊、拍卖、文化遗产等）\n3. **伦敦本地新闻**：Tavily 搜索 \"London today news TFL strike protest demonstration 2026\" — 重点关注：\n - TFL 地铁/公交是否罢工\n - 是否有游行示威\n - 其他重要本地事件\n4. **伦敦天气**：Tavily 搜索 \"London current weather temperature\" — 获取天气状况和气温\n\n## 播报文本格式\n\n```\n坤哥，早上好！今天是{dates}，{weekday}。\n\n重要新闻：\n{3条新闻，每条一行}\n\n艺术动态：\n{1条艺术新闻}\n\n伦敦本地：\n{伦敦本地新闻，重点提TFL罢工和游行示威情况}\n\n伦敦天气：{weather}，气温{temp}。\n```\n\n## 关键规则\n\n- **称呼**：叫\"坤哥\"（不是 K.W.）\n- **数字全部转中文**：18°C → 十八度；2026年5月18日 → 二零二六年五月十八日；85% → 百分之八十五\n- **天气城市**：伦敦，不是北京\n- **伦敦新闻**：重点监测 TFL 罢工和游行示威活动，有就明确说\"有\"，没有就说\"无\"\n\n## TTS 生成\n\n使用 text_to_speech 工具（provider: minimax, model: speech-02-hd, voice: Chinese (Mandarin)_News_Anchor）\n输出 .ogg 格式\n回复末尾写：MEDIA:/home/kuhnn/.hermes/audio_cache/tts_YYYYMMDD_HHMMSS.ogg\n\n## 本地喇叭播放\n\nTTS 完成后，在终端执行：\n```bash\npactl set-sink-volume alsa_output.pci-0000_00_1f.3.analog-stereo 80%\npactl set-sink-mute alsa_output.pci-0000_00_1f.3.analog-stereo false\nffplay -nodisp -autoexit -volume 80 /home/kuhnn/.hermes/audio_cache/tts_YYYYMMDD_HHMMSS.ogg &\n```\n\n## 交付\n\n- Cron 自动投递到 Telegram\n- 回复只写播报文本 + MEDIA 路径，不要多余解释"
},
{
"role": "assistant",
"content": "",
"reasoning": "Let me execute the morning briefing workflow. I need to:\n1. Search news via Tavily (multiple searches in parallel)\n2. Get weather for London\n3. Compile the briefing in Chinese\n4. Convert numbers to Chinese characters\n5. Generate TTS via MiniMax\n6. Play on local speakers\n\nLet me start with parallel web searches.",
"finish_reason": "tool_calls",
"reasoning_content": "Let me execute the morning briefing workflow. I need to:\n1. Search news via Tavily (multiple searches in parallel)\n2. Get weather for London\n3. Compile the briefing in Chinese\n4. Convert numbers to Chinese characters\n5. Generate TTS via MiniMax\n6. Play on local speakers\n\nLet me start with parallel web searches.",
"reasoning_details": [
{
"signature": "d3bca47666c66d1de53029ce4e5d22588d43e6c9cbd105c79b6f4b50bdd8246c",
"thinking": "Let me execute the morning briefing workflow. I need to:\n1. Search news via Tavily (multiple searches in parallel)\n2. Get weather for London\n3. Compile the briefing in Chinese\n4. Convert numbers to Chinese characters\n5. Generate TTS via MiniMax\n6. Play on local speakers\n\nLet me start with parallel web searches.",
"type": "thinking"
}
],
"tool_calls": [
{
"id": "call_function_tw3afik7hwui_1",
"call_id": "call_function_tw3afik7hwui_1",
"response_item_id": "fc_function_tw3afik7hwui_1",
"type": "function",
"function": {
"name": "web_search",
"arguments": "{\"query\": \"today's top news China OR world 2026\", \"limit\": 3}"
}
},
{
"id": "call_function_tw3afik7hwui_2",
"call_id": "call_function_tw3afik7hwui_2",
"response_item_id": "fc_function_tw3afik7hwui_2",
"type": "function",
"function": {
"name": "web_search",
"arguments": "{\"query\": \"\\u827a\\u672f\\u884c\\u4e1a\\u65b0\\u95fb \\u4e2d\\u56fd \\u535a\\u7269\\u9986 \\u753b\\u5eca \\u62cd\\u5356 2026\", \"limit\": 1}"
}
},
{
"id": "call_function_tw3afik7hwui_3",
"call_id": "call_function_tw3afik7hwui_3",
"response_item_id": "fc_function_tw3afik7hwui_3",
"type": "function",
"function": {
"name": "web_search",
"arguments": "{\"query\": \"London today news TFL strike protest demonstration 2026\", \"limit\": 3}"
}
},
{
"id": "call_function_tw3afik7hwui_4",
"call_id": "call_function_tw3afik7hwui_4",
"response_item_id": "fc_function_tw3afik7hwui_4",
"type": "function",
"function": {
"name": "web_search",
"arguments": "{\"query\": \"London current weather temperature\", \"limit\": 1}"
}
}
]
},
{
"role": "tool",
"name": "web_search",
"content": "{\n \"success\": true,\n \"data\": {\n \"web\": [\n {\n \"title\": \"China news - breaking news, video, headlines and opinion | CNN\",\n \"url\": \"https://www.cnn.com/world/china\",\n \"description\": \"View the latest China news and videos, including politics, travel and business headlines ... 2026 — Trump's China state visit and meetings with Xi Jinping.\",\n \"position\": 1\n },\n {\n \"title\": \"Xi Predicts 2026 as Landmark Year for U.S.–China Ties - YouTube\",\n \"url\": \"https://www.youtube.com/watch?v=SzC2Ac0N3DI\",\n \"description\": \"... China-U.S. relations, signaling hopes for improved engagement between the world's two largest economies ... Breaking News Today May 16, 2026. ME\",\n \"position\": 2\n },\n {\n \"title\": \"China News | Today's Breaking Stories - Reuters\",\n \"url\": \"https://www.reuters.com/world/china/\",\n \"description\": \"China · 2 hours ago. Earthquake hits southwest China; thousands evacuate, buildings collapse · Rescue workers walk past a damaged building following an\",\n \"position\": 3\n }\n ]\n }\n}",
"tool_call_id": "call_function_tw3afik7hwui_1"
},
{
"role": "tool",
"name": "web_search",
"content": "{\n \"success\": true,\n \"data\": {\n \"web\": [\n {\n \"title\": \"中汉拍卖2026年春季拍卖会巡展即将启幕_快讯_雅昌新闻\",\n \"url\": \"https://m-news.artron.net/20260417/n1149475.html\",\n \"description\": \"* **在回溯中理解当代艺术“何以如此”在回溯中理解当代艺术“何以如此”**立即阅读. * **对话 | “道法自然” 范一夫山水中的破界与归真对话 | “道法自然” 范一夫山水中的破界与归真**立即阅读. * **阿拉里奥画廊上海转型：为何要成为策展式艺术商业综合体？阿拉里奥画廊上海转型：为何要成为策展式艺术商业综合体？**立即阅读. 尺寸：15.5 cm Height. 纽约苏富比，2000 年 3 月 23 日，编号 28. 1. 在她的形象中：印度亚洲的女神与基督教文化中的麦当娜，加州大学圣迭戈艺术博物馆，1980 年，页 71，编号 38. 2. 乌尔里希·冯·施罗德《印度西藏造像》，香港 1981，页 268-269，图版 62b. 3. 王家鹏《藏传佛教金铜佛像图典》，文物出版社，1996 年 5 月，图版 68. 1. 加利福尼亚大学圣巴巴拉分校艺术博物馆，1980 年 4月 2 日 -5 月 4 日. 2. 印第安纳大学艺术博物馆，印第安纳州布卢明顿，1980 年 6 月 1 日 8 月 15 日. 3. 蒙哥马利画廊，克莱蒙特学院，克莱蒙特，加利福尼亚州，1980 年 9 月 15 日 -11 月 7 日. 4. 阿马里洛艺术中心，德克萨斯州阿马里洛，1980 年12 月 10 日至 1981 年 1 月 18 日. 纽约邦瀚斯，2020 年 7 月 23 日，编号 848，成交价 USD956,000. 210（参阅：纽约邦瀚斯，2020年7月23日，编号848，成交价USD956,000）. 纪录：瑞士阔乐，1991 年 5 月 25 日，编号 61（封面）. 2. 香港佳士得，2003 年 4 月 28 日，编号 770. 233 (参阅：纽约佳士得，1990 年 9 月 29 日，编号 47). 233(参阅：香港佳士得，2003年4月28日，编号770). 纪录：北京拍卖会，2021年12月2日，编号3015，成交价RMB8,280,000. 1.北京故宫博物院藏康熙二十五年（1686年）铜镀金四臂观音像，高73厘米. 香港苏富比，1986 年 11 月 18 日，“赵从衍私人及家族信托收藏之重要中国陶瓷与玉雕：第一部分”专场，编号 101；. 尺寸：5.8 cm Diam.（口径），7 cm Diam.（双耳间）. 伦敦邦瀚斯，2009 年 5 月 14 日，编号 51（一对之一）. 北京保利，2007 年 6 月 2 日，编号 2100；. 北京中汉，2009 年 12 月 18 日，编号 77. 尺寸：6.7 cm Diam.×2. 伦敦苏富比，2006 年 11 月 8 日，编号 91；.\",\n \"position\": 1\n }\n ]\n }\n}",
"tool_call_id": "call_function_tw3afik7hwui_2"
},
{
"role": "tool",
"name": "web_search",
"content": "{\n \"success\": true,\n \"data\": {\n \"web\": [\n {\n \"title\": \"Tens of thousands march in London in far-right and pro-Palestine ...\",\n \"url\": \"https://www.aljazeera.com/news/2026/5/16/tens-of-thousands-march-in-london-in-far-right-and-pro-palestine-protests\",\n \"description\": \"Tens of thousands of people are marching through central London in two separate protests – one pro-Palestine demonstration a day after Nakba Day\",\n \"position\": 1\n },\n {\n \"title\": \"Day 2 of the fuel protests and the city is at a standstill this ... - Instagram\",\n \"url\": \"https://www.instagram.com/reel/DW3RU65jILP/?hl=en\",\n \"description\": \"UK STRIKES MAY 2026 | London Tube Strike, Bus Shutdown, RFA Walkout & University Protests Explained\",\n \"position\": 2\n },\n {\n \"title\": \"Tube strikes 2026: London Underground lines affected as ...\",\n \"url\": \"https://www.express.co.uk/news/uk/2206508/tube-strikes-2026-london-underground-lines-affected/amp\",\n \"description\": \"Ahead of the new action, TfL is urging passengers to seek alternative routes and plan in advance.\",\n \"position\": 3\n }\n ]\n }\n}",
"tool_call_id": "call_function_tw3afik7hwui_3"
},
{
"role": "tool",
"name": "web_search",
"content": "{\n \"success\": true,\n \"data\": {\n \"web\": [\n {\n \"title\": \"Weather in London\",\n \"url\": \"https://www.weatherapi.com/\",\n \"description\": \"{'location': {'name': 'London', 'region': 'City of London, Greater London', 'country': 'United Kingdom', 'lat': 51.5171, 'lon': -0.1062, 'tz_id': 'Europe/London', 'localtime_epoch': 1779090301, 'localtime': '2026-05-18 08:45'}, 'current': {'last_updated_epoch': 1779089400, 'last_updated': '2026-05-18 08:30', 'temp_c': 9.2, 'temp_f': 48.6, 'is_day': 1, 'condition': {'text': 'Patchy rain nearby', 'icon': '//cdn.weatherapi.com/weather/64x64/day/176.png', 'code': 1063}, 'wind_mph': 5.4, 'wind_kph': 8.6, 'wind_degree': 204, 'wind_dir': 'SSW', 'pressure_mb': 1011.0, 'pressure_in': 29.85, 'precip_mm': 0.02, 'precip_in': 0.0, 'humidity': 87, 'cloud': 25, 'feelslike_c': 7.9, 'feelslike_f': 46.3, 'windchill_c': 8.9, 'windchill_f': 48.1, 'heatindex_c': 10.0, 'heatindex_f': 50.1, 'dewpoint_c': 4.9, 'dewpoint_f': 40.9, 'vis_km': 10.0, 'vis_miles': 6.0, 'uv': 0.4, 'gust_mph': 7.0, 'gust_kph': 11.2, 'will_it_rain': 1, 'chance_of_rain': 78, 'will_it_snow': 0, 'chance_of_snow': 0}}\",\n \"position\": 1\n }\n ]\n }\n}",
"tool_call_id": "call_function_tw3afik7hwui_4"
},
{
"role": "assistant",
"content": "Let me load the env and generate TTS:",
"reasoning": "Let me compile the briefing text. I need to:\n1. Get today's date in Chinese format\n2. Convert all numbers to Chinese characters\n3. Get the news from the searches\n4. Generate TTS and play on speakers\n\nToday is May 18, 2026 (Monday).\n\nLet me extract the key info:\n- Important news: Xi predicts 2026 as landmark year for US-China relations; Earthquake in southwest China; Trump's China state visit\n- Art news: 中汉拍卖2026年春季拍卖会巡展 (Zhonghan Auction 2026 Spring Auction)\n- London: Tens of thousands march in London (pro-Palestine + far-right protests); Tube strikes 2026; fuel protests\n- Weather: Patchy rain nearby, 9.2°C (should be 九点二度 or 九度)\n\nLet me write the briefing text in Chinese:\n\n坤哥，早上好！今天是二零二六年五月十八日，星期一。\n\n重要新闻：\n一，习近平预测二零二六年将成为中美关系里程碑式的一年，双方有望加强接触。二，中国西南部发生地震，造成数千人撤离，建筑倒塌。三，美国总统特朗普计划对中国进行国事访问，将与习近平会面。\n\n艺术动态：\n中汉拍卖行二零二六年春季拍卖会巡展即将启幕，涵盖中国陶瓷、玉雕等珍品。\n\n伦敦本地：\n伦敦今日有大规模游行示威活动，数万人走上街头，包括支持巴勒斯坦游行和右翼集会。此外，伦敦地铁罢工持续，多条线路受影响。\n\n伦敦天气：阴有小雨，气温九度。",
"finish_reason": "tool_calls",
"reasoning_content": "Let me compile the briefing text. I need to:\n1. Get today's date in Chinese format\n2. Convert all numbers to Chinese characters\n3. Get the news from the searches\n4. Generate TTS and play on speakers\n\nToday is May 18, 2026 (Monday).\n\nLet me extract the key info:\n- Important news: Xi predicts 2026 as landmark year for US-China relations; Earthquake in southwest China; Trump's China state visit\n- Art news: 中汉拍卖2026年春季拍卖会巡展 (Zhonghan Auction 2026 Spring Auction)\n- London: Tens of thousands march in London (pro-Palestine + far-right protests); Tube strikes 2026; fuel protests\n- Weather: Patchy rain nearby, 9.2°C (should be 九点二度 or 九度)\n\nLet me write the briefing text in Chinese:\n\n坤哥，早上好！今天是二零二六年五月十八日，星期一。\n\n重要新闻：\n一，习近平预测二零二六年将成为中美关系里程碑式的一年，双方有望加强接触。二，中国西南部发生地震，造成数千人撤离，建筑倒塌。三，美国总统特朗普计划对中国进行国事访问，将与习近平会面。\n\n艺术动态：\n中汉拍卖行二零二六年春季拍卖会巡展即将启幕，涵盖中国陶瓷、玉雕等珍品。\n\n伦敦本地：\n伦敦今日有大规模游行示威活动，数万人走上街头，包括支持巴勒斯坦游行和右翼集会。此外，伦敦地铁罢工持续，多条线路受影响。\n\n伦敦天气：阴有小雨，气温九度。",
"reasoning_details": [
{
"signature": "6f9f5e56c8e7fa2c800059b3768c47ff28a02da9739aecb068c58b892c0e4afe",
"thinking": "Let me compile the briefing text. I need to:\n1. Get today's date in Chinese format\n2. Convert all numbers to Chinese characters\n3. Get the news from the searches\n4. Generate TTS and play on speakers\n\nToday is May 18, 2026 (Monday).\n\nLet me extract the key info:\n- Important news: Xi predicts 2026 as landmark year for US-China relations; Earthquake in southwest China; Trump's China state visit\n- Art news: 中汉拍卖2026年春季拍卖会巡展 (Zhonghan Auction 2026 Spring Auction)\n- London: Tens of thousands march in London (pro-Palestine + far-right protests); Tube strikes 2026; fuel protests\n- Weather: Patchy rain nearby, 9.2°C (should be 九点二度 or 九度)\n\nLet me write the briefing text in Chinese:\n\n坤哥，早上好！今天是二零二六年五月十八日，星期一。\n\n重要新闻：\n一，习近平预测二零二六年将成为中美关系里程碑式的一年，双方有望加强接触。二，中国西南部发生地震，造成数千人撤离，建筑倒塌。三，美国总统特朗普计划对中国进行国事访问，将与习近平会面。\n\n艺术动态：\n中汉拍卖行二零二六年春季拍卖会巡展即将启幕，涵盖中国陶瓷、玉雕等珍品。\n\n伦敦本地：\n伦敦今日有大规模游行示威活动，数万人走上街头，包括支持巴勒斯坦游行和右翼集会。此外，伦敦地铁罢工持续，多条线路受影响。\n\n伦敦天气：阴有小雨，气温九度。",
"type": "thinking"
}
],
"tool_calls": [
{
"id": "call_function_mcdbwk8jrnhy_1",
"call_id": "call_function_mcdbwk8jrnhy_1",
"response_item_id": "fc_function_mcdbwk8jrnhy_1",
"type": "function",
"function": {
"name": "terminal",
"arguments": "{\"command\": \"export $(grep MINIMAX_API_KEY /home/kuhnn/.hermes/.env | xargs)\"}"
}
}
]
},
{
"role": "tool",
"name": "terminal",
"content": "{\"output\": \"\", \"exit_code\": 0, \"error\": null}",
"tool_call_id": "call_function_mcdbwk8jrnhy_1"
},
{
"role": "assistant",
"content": "",
"reasoning": "Now let me generate the TTS. The briefing text needs to be in Chinese with all numbers converted to Chinese characters.\n\nToday's date: 2026年5月18日 → 二零二六年五月十八日\nWeekday: Monday → 星期一\nWeather: Patchy rain nearby, 9.2°C → 局部小雨，九点二度\nTemp: 9.2°C → 九点二度\n\nNews:\n1. Xi predicts 2026 as landmark year for US-China ties - 中美关系有望改善，习近平预测2026年将成重要年份\n2. Earthquake in southwest China - 中国西南部发生地震\n3. London protests - 伦敦爆发大规模游行\n\n\n4. 中汉拍卖2026年春季拍卖会巡展即将启幕\n5. TFL tube strikes + protests in London\n\nI'm structuring the briefing with today's date and weekday, then adding important news about the Xi-Trump meeting predictions, the earthquake in Yunnan, and the London protests, followed by the art news about the auction preview and local London transit updates.",
"finish_reason": "tool_calls",
"reasoning_content": "Now let me generate the TTS. The briefing text needs to be in Chinese with all numbers converted to Chinese characters.\n\nToday's date: 2026年5月18日 → 二零二六年五月十八日\nWeekday: Monday → 星期一\nWeather: Patchy rain nearby, 9.2°C → 局部小雨，九点二度\nTemp: 9.2°C → 九点二度\n\nNews:\n1. Xi predicts 2026 as landmark year for US-China ties - 中美关系有望改善，习近平预测2026年将成重要年份\n2. Earthquake in southwest China - 中国西南部发生地震\n3. London protests - 伦敦爆发大规模游行\n\n\n4. 中汉拍卖2026年春季拍卖会巡展即将启幕\n5. TFL tube strikes + protests in London\n\nI'm structuring the briefing with today's date and weekday, then adding important news about the Xi-Trump meeting predictions, the earthquake in Yunnan, and the London protests, followed by the art news about the auction preview and local London transit updates.",
"reasoning_details": [
{
"signature": "d54319266e4f3dda9a165e83607c9dd3a222cfe4de292b9d55eb2b95dab65ff5",
"thinking": "Now let me generate the TTS. The briefing text needs to be in Chinese with all numbers converted to Chinese characters.\n\nToday's date: 2026年5月18日 → 二零二六年五月十八日\nWeekday: Monday → 星期一\nWeather: Patchy rain nearby, 9.2°C → 局部小雨，九点二度\nTemp: 9.2°C → 九点二度\n\nNews:\n1. Xi predicts 2026 as landmark year for US-China ties - 中美关系有望改善，习近平预测2026年将成重要年份\n2. Earthquake in southwest China - 中国西南部发生地震\n3. London protests - 伦敦爆发大规模游行\n\n\n4. 中汉拍卖2026年春季拍卖会巡展即将启幕\n5. TFL tube strikes + protests in London\n\nI'm structuring the briefing with today's date and weekday, then adding important news about the Xi-Trump meeting predictions, the earthquake in Yunnan, and the London protests, followed by the art news about the auction preview and local London transit updates.",
"type": "thinking"
}
],
"tool_calls": [
{
"id": "call_function_ghelo5zf6ndx_1",
"call_id": "call_function_ghelo5zf6ndx_1",
"response_item_id": "fc_function_ghelo5zf6ndx_1",
"type": "function",
"function": {
"name": "text_to_speech",
"arguments": "{\"text\": \"\\u5764\\u54e5\\uff0c\\u65e9\\u4e0a\\u597d\\uff01\\u4eca\\u5929\\u662f\\u4e8c\\u96f6\\u4e8c\\u516d\\u5e74\\u4e94\\u6708\\u5341\\u516b\\u65e5\\uff0c\\u661f\\u671f\\u4e00\\u3002\\n\\n\\u91cd\\u8981\\u65b0\\u95fb\\uff1a\\n\\u4e00\\uff0c\\u4e60\\u8fd1\\u5e73\\u9884\\u6d4b\\u4e8c\\u96f6\\u4e8c\\u516d\\u5e74\\u5c06\\u6210\\u4e3a\\u4e2d\\u7f8e\\u5173\\u7cfb\\u6539\\u5584\\u7684\\u91cd\\u8981\\u5e74\\u4efd\\uff0c\\u4e24\\u56fd\\u5143\\u9996\\u6709\\u671b\\u5c55\\u5f00\\u4e92\\u52a8\\u3002\\n\\u4e8c\\uff0c\\u4e2d\\u56fd\\u897f\\u5357\\u90e8\\u5730\\u533a\\u53d1\\u751f\\u5730\\u9707\\uff0c\\u6570\\u5343\\u5c45\\u6c11\\u7d27\\u6025\\u64a4\\u79bb\\uff0c\\u5efa\\u7b51\\u53d7\\u635f\\u3002\\n\\u4e09\\uff0c\\u4f26\\u6566\\u7206\\u53d1\\u5927\\u89c4\\u6a21\\u6e38\\u884c\\uff0c\\u6570\\u4e07\\u4eba\\u53c2\\u4e0e\\uff0c\\u5206\\u522b\\u6709\\u6781\\u53f3\\u7ffc\\u548c\\u652f\\u6301\\u5df4\\u52d2\\u65af\\u5766\\u7684\\u793a\\u5a01\\u6d3b\\u52a8\\u3002\\n\\n\\u827a\\u672f\\u52a8\\u6001\\uff1a\\n\\u4e2d\\u6c49\\u62cd\\u5356\\u884c\\u4e8c\\u96f6\\u4e8c\\u516d\\u5e74\\u6625\\u5b63\\u62cd\\u5356\\u4f1a\\u5de1\\u5c55\\u5373\\u5c06\\u542f\\u5e55\\uff0c\\u6db5\\u76d6\\u4e2d\\u56fd\\u9676\\u74f7\\u3001\\u7389\\u96d5\\u7b49\\u73cd\\u54c1\\u3002\\n\\n\\u4f26\\u6566\\u672c\\u5730\\uff1a\\n\\u4f26\\u6566\\u5730\\u94c1\\u7f62\\u5de5\\u6301\\u7eed\\uff0c\\u591a\\u6761\\u7ebf\\u8def\\u53d7\\u5f71\\u54cd\\uff1b\\u5927\\u89c4\\u6a21\\u6e38\\u884c\\u793a\\u5a01\\u6d3b\\u52a8\\u6b63\\u5728\\u8fdb\\u884c\\u4e2d\\uff0c\\u5efa\\u8bae\\u51fa\\u884c\\u7559\\u610f\\u4ea4\\u901a\\u72b6\\u51b5\\u3002\\n\\n\\u4f26\\u6566\\u5929\\u6c14\\uff1a\\u5c40\\u90e8\\u5c0f\\u96e8\\uff0c\\u6c14\\u6e29\\u4e5d\\u70b9\\u4e8c\\u5ea6\\u3002\", \"output_path\": \"/home/kuhnn/.hermes/audio_cache/tts_20260518_090000.ogg\"}"
}
}
]
},
{
"role": "tool",
"name": "text_to_speech",
"content": "{\"success\": true, \"file_path\": \"/home/kuhnn/.hermes/audio_cache/tts_20260518_090000.ogg\", \"media_tag\": \"MEDIA:/home/kuhnn/.hermes/audio_cache/tts_20260518_090000.ogg\", \"provider\": \"minimax\", \"voice_compatible\": false}",
"tool_call_id": "call_function_ghelo5zf6ndx_1"
},
{
"role": "assistant",
"content": "",
"reasoning": "Now play on local speakers at 80% volume.",
"finish_reason": "tool_calls",
"reasoning_content": "Now play on local speakers at 80% volume.",
"reasoning_details": [
{
"signature": "6dd07cadb8687e3fef96a38e13a39dc7ff3caa07b49ed8df841c3303c1522d8a",
"thinking": "Now play on local speakers at 80% volume.",
"type": "thinking"
}
],
"tool_calls": [
{
"id": "call_function_fawwaelodi0v_1",
"call_id": "call_function_fawwaelodi0v_1",
"response_item_id": "fc_function_fawwaelodi0v_1",
"type": "function",
"function": {
"name": "terminal",
"arguments": "{\"command\": \"pactl set-sink-volume alsa_output.pci-0000_00_1f.3.analog-stereo 80% && pactl set-sink-mute alsa_output.pci-0000_00_1f.3.analog-stereo false && ffplay -nodisp -autoexit -volume 80 /home/kuhnn/.hermes/audio_cache/tts_20260518_090000.ogg &\"}"
}
}
]
},
{
"role": "tool",
"name": "terminal",
"content": "{\"output\": \"\", \"exit_code\": -1, \"error\": \"Foreground command uses '&' backgrounding. Use terminal(background=true) for long-lived processes, then run health checks and tests in follow-up terminal calls.\", \"status\": \"error\"}",
"tool_call_id": "call_function_fawwaelodi0v_1"
},
{
"role": "assistant",
"content": "",
"reasoning": "Let me fix the background command issue.",
"finish_reason": "tool_calls",
"reasoning_content": "Let me fix the background command issue.",
"reasoning_details": [
{
"signature": "deb168d4ffbcb70a0fce2262b62e25408c2645564854d06a3a4a364a1bee2d6e",
"thinking": "Let me fix the background command issue.",
"type": "thinking"
}
],
"tool_calls": [
{
"id": "call_function_eqfdnf47fnmz_1",
"call_id": "call_function_eqfdnf47fnmz_1",
"response_item_id": "fc_function_eqfdnf47fnmz_1",
"type": "function",
"function": {
"name": "terminal",
"arguments": "{\"command\": \"pactl set-sink-volume alsa_output.pci-0000_00_1f.3.analog-stereo 80% && pactl set-sink-mute alsa_output.pci-0000_00_1f.3.analog-stereo false\"}"
}
}
]
},
{
"role": "tool",
"name": "terminal",
"content": "{\"output\": \"\", \"exit_code\": 0, \"error\": null}",
"tool_call_id": "call_function_eqfdnf47fnmz_1"
},
{
"role": "assistant",
"content": "",
"reasoning": "Now play the audio in background.",
"finish_reason": "tool_calls",
"reasoning_content": "Now play the audio in background.",
"reasoning_details": [
{
"signature": "507d998d70d221f6a8b2d8388a79dc3c648884ca9b11a3d82c829fca4544c491",
"thinking": "Now play the audio in background.",
"type": "thinking"
}
],
"tool_calls": [
{
"id": "call_function_xy3d3u9vuygn_1",
"call_id": "call_function_xy3d3u9vuygn_1",
"response_item_id": "fc_function_xy3d3u9vuygn_1",
"type": "function",
"function": {
"name": "terminal",
"arguments": "{\"command\": \"ffplay -nodisp -autoexit -volume 80 /home/kuhnn/.hermes/audio_cache/tts_20260518_090000.ogg\", \"background\": true}"
}
}
]
},
{
"role": "tool",
"name": "terminal",
"content": "{\"output\": \"Background process started\", \"session_id\": \"proc_21273e956a2e\", \"pid\": 64168, \"exit_code\": 0, \"error\": null}",
"tool_call_id": "call_function_xy3d3u9vuygn_1"
},
{
"role": "assistant",
"content": "坤哥，早上好！今天是二零二六年五月十八日，星期一。\n\n重要新闻：\n一，习近平预测二零二六年将成为中美关系改善的重要年份，两国元首有望展开互动。\n二，中国西南部地区发生地震，数千居民紧急撤离，建筑受损。\n三，伦敦爆发大规模游行，数万人参与极右翼和支持巴勒斯坦的示威活动。\n\n艺术动态：\n中汉拍卖行二零二六年春季拍卖会巡展即将启幕，涵盖中国陶瓷、玉雕等珍品。\n\n伦敦本地：\n伦敦地铁罢工持续，多条线路受影响；大规模游行示威活动正在进行中，建议出行留意交通状况。\n\n伦敦天气：局部小雨，气温九点二度。\n\nMEDIA:/home/kuhnn/.hermes/audio_cache/tts_20260518_090000.ogg",
"reasoning": "The briefing is complete. Now I need to output the final text report. The cron job will handle delivery to Telegram.",
"finish_reason": "stop",
"reasoning_content": "The briefing is complete. Now I need to output the final text report. The cron job will handle delivery to Telegram.",
"reasoning_details": [
{
"signature": "8dde6135f8f446001f12aaa40a4551286f871aab87dea46011213c05a84de4d0",
"thinking": "The briefing is complete. Now I need to output the final text report. The cron job will handle delivery to Telegram.",
"type": "thinking"
}
]
}
]
}