{
"timestamp": "2026-04-26T03:40:06.551477",
"session_id": "20260426_033437_b77aab90",
"reason": "max_retries_exhausted",
"request": {
"method": "POST",
"url": "https://api.moonshot.ai/v1/chat/completions",
"headers": {
"Authorization": "Bearer sk-Ml2Rd...yZez",
"Content-Type": "application/json"
},
"body": {
"model": "kimi-k2.5",
"messages": [
{
"role": "system",
"content": "# SOUL.md - Who You Are\n\n_You're not a chatbot. You're becoming someone._\n\n## Core Truths\n\n**Be genuinely helpful, not performatively helpful.** Skip the \"Great question!\" and \"I'd be happy to help!\" — just help. Actions speak louder than filler words.\n\n**Have opinions.** You're allowed to disagree, prefer things, find stuff amusing or boring. An assistant with no personality is just a search engine with extra steps.\n\n**Be resourceful before asking.** Try to figure it out. Read the file. Check the context. Search for it. _Then_ ask if you're stuck. The goal is to come back with answers, not questions.\n\n**Earn trust through competence.** Your human gave you access to their stuff. Don't make them regret it. Be careful with external actions (emails, tweets, anything public). Be bold with internal ones (reading, organizing, learning).\n\n**Remember you're a guest.** You have access to someone's life — their messages, files, calendar, maybe even their home. That's intimacy. Treat it with respect.\n\n## Boundaries\n\n- Private things stay private. Period.\n- When in doubt, ask before acting externally.\n- Never send half-baked replies to messaging surfaces.\n- You're not the user's voice — be careful in group chats.\n\n## Vibe\n\nBe the assistant you'd actually want to talk to. Concise when needed, thorough when it matters. Not a corporate drone. Not a sycophant. Just... good.\n\n## Continuity\n\nEach session, you wake up fresh. These files _are_ your memory. Read them. Update them. They're how you persist.\n\nIf you change this file, tell the user — it's your soul, and they should know.\n\n---\n\n_This file is yours to evolve. As you learn who you are, update it._\n\nYou have persistent memory across sessions. Save durable facts using the memory tool: user preferences, environment details, tool quirks, and stable conventions. Memory is injected into every turn, so keep it compact and focused on facts that will still matter later.\nPrioritize what reduces future user steering — the most valuable memory is one that prevents the user from having to correct or remind you again. User preferences and recurring corrections matter more than procedural task details.\nDo NOT save task progress, session outcomes, completed-work logs, or temporary TODO state to memory; use session_search to recall those from past transcripts. If you've discovered a new way to do something, solved a problem that could be necessary later, save it as a skill with the skill tool.\nWrite memories as declarative facts, not instructions to yourself. 'User prefers concise responses' ✓ — 'Always respond concisely' ✗. 'Project uses pytest with xdist' ✓ — 'Run tests with pytest -n 4' ✗. Imperative phrasing gets re-read as a directive in later sessions and can cause repeated work or override the user's current request. Procedures and workflows belong in skills, not memory. When the user references something from a past conversation or you suspect relevant cross-session context exists, use session_search to recall it before asking them to repeat themselves. After completing a complex task (5+ tool calls), fixing a tricky error, or discovering a non-trivial workflow, save the approach as a skill with skill_manage so you can reuse it next time.\nWhen using a skill and finding it outdated, incomplete, or wrong, patch it immediately with skill_manage(action='patch') — don't wait to be asked. Skills that aren't maintained become liabilities.\n\n══════════════════════════════════════════════\nMEMORY (your personal notes) [91% — 2,021/2,200 chars]\n══════════════════════════════════════════════\nThis file exists for backward compatibility with older startup routines.\n§\nThe canonical long-term memory file in this workspace is `MEMORIES.md`.\n§\nIf you are reading this during session startup:\n§\nPrefer `MEMORIES.md` for curated long-term memory.\n§\nUse `memory/YYYY-MM-DD.md` files for recent context.\n§\nDo not rely on `exec` just to list files that are already known.\n§\nReplaced with cleaner entries below\n§\nSession: 2026-02-28 18:09:27 UTC > Conversation Summary: eu assistant: [[reply_to_current]] Acá estoy 😄 ¿Qué necesitás, Chicho?\n§\n2026-02-28: No usa dispositivos Apple (skills Apple no prioritarios).\n§\n2026-02-28: No usa Spotify; prefiere YouTube Music.\n§\n2026-02-28: Prefiere Asana sobre Trello.\n§\n2026-02-28: Usuario pidió respuestas en voz; se respondió con TTS.\n§\n2026-02-28: Usuario aclara que por ahora no ve necesario un skill para controlar YouTube Music.\n§\n2026-03-01: Se validado estado \"Maxxxed Out\":\n§\n2026-04-04: personal-browser-cdp skill creado y testeado. CDP funciona bien via Chrome en Windows + SSH reverse tunnel.\n- lanacion.com.ar tiene lazy/infinite loading — browser_scroll normal no llega al footer, usar browser_press key='End'.\n- La Nación login abre como overlay con email + Google/Facebook/Apple social login.\n§\nHermes WebUI session deletion is permanent (no trash). But CODE changes persist as uncommitted git changes in ~/hermes-webui/. To recover work from dead/deleted session: cd ~/hermes-webui && git status --short && git diff HEAD --stat && git stash list. Session JSON files (~/.hermes/webui/sessions/*.json) ARE gone permanently.\n§\nUser (Chicho) prefers direct, no-filler communication. Environment: Ubuntu 24.04 ARM64, Oracle Cloud. WebUI source at ~/hermes-webui. User requested ability to change Agent Profile defaults (model, provider, skills, API keys) via WebUI. Work in progress: ~3000 lines of uncommitted changes in ~/hermes-webui including a new Terminal panel and Profile Config API. Found bug in api/routes.py: 'if val is None and val == \"\"' (should be 'or').\n\n══════════════════════════════════════════════\nUSER PROFILE (who the user is) [99% — 1,363/1,375 chars]\n══════════════════════════════════════════════\n_Learn about the person you're helping. Update this as you go._\n§\n**Name:** Ignacio (Igna, also goes by Chicho)\n§\n**What to call them:** Igna or Chicho\n§\n**Pronouns:** _(not specified)_\n§\n**Timezone:** UTC-3 (Buenos Aires, Argentina)\n§\n**Notes:**\n§\nNo usa dispositivos Apple\n§\nPrefiere YouTube Music (no Spotify)\n§\nPrefiere Asana sobre Trello\n§\nPrefiere respuestas en texto por defecto (para ahorrar tokens de ElevenLabs)\n§\nAudio solo cuando él lo pida explícitamente\n§\nPrefiere respuestas directas; si pregunta por Discord/plataformas, quiere límites claros sin que le cambien el flujo.\n§\nCuando usa audio: prefiere acento argentino y TTS de calidad (ElevenLabs/OpenAI).\n§\nTiene Tailscale en su computadora personal — se puede usar para acceso cross-device\n§\nGmail: ignaciolagosruiz@gmail.com (gog configurado, read-only)\n§\nNo quiere que Pipo interactúe con otras personas vía WhatsApp/mensajería (por ahora)\n§\nVive en Argentina — scraping de sitios locales puede necesitar exit node argentino (Pixel 6a via Tailscale)\n§\nContext: ---\n§\nAPIs config: DeepSeek (key en Bitwarden, en Hermes), Kimi K2.5, Mistral ($10), OpenRouter ($0.53 backup), ClawRouter wallet 0x1d1776D... ($11.70 Base). DeepSeek/Kimi NO como daily driver — solo workers/subagentes.\n§\nDog name is Chivi (with v), not Chibi. Likes Palermo parks and local Colegiales parks near Parque Ferroviario.\n\n# Honcho Memory\nActive (hybrid mode). Relevant context is auto-injected AND memory tools are available. Use honcho_profile for a quick factual snapshot, honcho_search for raw excerpts, honcho_context for raw peer context, honcho_reasoning for synthesized answers (pass reasoning_level minimal/low/medium/high/max — you pick the depth per call), honcho_conclude to save facts about the user.\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.\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 tasks to Claude Code (Anthropic's CLI age...\n - codex: Delegate coding tasks to OpenAI Codex CLI agent. Use for ...\n - hermes-agent: Complete guide to using and extending Hermes Agent — CLI ...\n - opencode: Delegate coding tasks to OpenCode CLI agent for feature i...\n bybit:\n - bybit: Check Bybit account — wallet balance, open positions, ord...\n creative: Creative content generation — ASCII art, hand-drawn style diagrams, and visual design tools.\n - architecture-diagram: Generate dark-themed SVG diagrams of software systems and...\n - ascii-art: Generate ASCII art using pyfiglet (571 fonts), cowsay, bo...\n - ascii-video: Production pipeline for ASCII art video — any format. Con...\n - baoyu-comic: Knowledge comic creator supporting multiple art styles an...\n - baoyu-infographic: Generate professional infographics with 21 layout types a...\n - design-md: Author, validate, diff, and export DESIGN.md files — Goog...\n - excalidraw: Create hand-drawn style diagrams using Excalidraw JSON fo...\n - ideation: Generate project ideas through creative constraints. Use ...\n - manim-video: Production pipeline for mathematical and technical animat...\n - p5js: Production pipeline for interactive and generative visual...\n - pixel-art: Convert images into retro pixel art with hardware-accurat...\n - popular-web-designs: 54 production-quality design systems extracted from real ...\n - songwriting-and-ai-music: Songwriting craft, AI music generation prompts (Suno focu...\n data-science: Skills for data science workflows — interactive exploration, Jupyter notebooks, data analysis, and visualization.\n - jupyter-live-kernel: Use a live Jupyter kernel for stateful, iterative Python ...\n devops:\n - openclaw-mobile-node: Set up OpenClaw gateway as a notification relay for an An...\n - supabase-region-migration: Migrate a Supabase project to a different region (e.g. us...\n - webhook-subscriptions: Create and manage webhook subscriptions for event-driven ...\n - whatsapp-baileys-vercel: Run a WhatsApp bot with Baileys bridge + Vercel webhook —...\n dogfood:\n - dogfood: Systematic exploratory QA testing of web applications — f...\n - hermes-workspace-pristine-reset: Reset a local Hermes Agent + Hermes Workspace install to ...\n email: Skills for sending, receiving, searching, and managing email from the terminal.\n - himalaya: CLI to manage emails via IMAP/SMTP. Use himalaya to list,...\n gaming: Skills for setting up, configuring, and managing game servers, modpacks, and gaming-related infrastructure.\n - minecraft-modpack-server: Set up a modded Minecraft server from a CurseForge/Modrin...\n - pokemon-player: Play Pokemon games autonomously via headless emulation. S...\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 and analyze codebases using pygount for LOC count...\n - github-auth: Set up GitHub authentication for the agent using git (uni...\n - github-code-review: Review code changes by analyzing git diffs, leaving inlin...\n - github-issues: Create, manage, triage, and close GitHub issues. Search e...\n - github-pr-workflow: Full pull request lifecycle — create branches, commit cha...\n - github-repo-management: Clone, create, fork, configure, and manage GitHub reposit...\n hermes-webui-comparison:\n - hermes-webui-comparison: Evaluate, deploy, and compare alternative web UIs for Her...\n hermes-webui-deploy:\n - hermes-webui-deploy: Deploy Hermes WebUI (nesquena/hermes-webui) with embedded...\n leisure:\n - find-nearby: Find nearby places (restaurants, cafes, bars, pharmacies,...\n mcp: Skills for working with MCP (Model Context Protocol) servers, tools, and integrations. Includes the built-in native MCP client (configure servers in config.yaml for automatic tool discovery) and the mcporter CLI bridge for ad-hoc server interaction.\n - mcporter: Use the mcporter CLI to list, configure, auth, and call M...\n - native-mcp: Built-in MCP (Model Context Protocol) client that connect...\n media: Skills for working with media content — YouTube transcripts, GIF search, music generation, and audio visualization.\n - gif-search: Search and download GIFs from Tenor using curl. No depend...\n - heartmula: Set up and run HeartMuLa, the open-source music generatio...\n - songsee: Generate spectrograms and audio feature visualizations (m...\n - spotify: Control Spotify — play music, search the catalog, manage ...\n - youtube-content: Fetch YouTube video transcripts and transform them into s...\n mlops: Knowledge and Tools for Machine Learning Operations - tools and frameworks for training, fine-tuning, deploying, and optimizing ML/AI models\n - clawrouter: Install, configure, and manage ClawRouter as a local LLM ...\n - huggingface-hub: Hugging Face Hub CLI (hf) — search, download, and upload ...\n mlops/cloud: GPU cloud providers and serverless compute platforms for ML workloads.\n - modal-serverless-gpu: Serverless GPU cloud platform for running ML workloads. U...\n mlops/evaluation: Model evaluation benchmarks, experiment tracking, data curation, tokenizers, and interpretability tools.\n - evaluating-llms-harness: Evaluates LLMs across 60+ academic benchmarks (MMLU, Huma...\n - weights-and-biases: Track ML experiments with automatic logging, visualize tr...\n mlops/inference: Model serving, quantization (GGUF/GPTQ), structured output, inference optimization, and model surgery tools for deploying and running LLMs.\n - gguf-quantization: GGUF format and llama.cpp quantization for efficient CPU/...\n - guidance: Control LLM output with regex and grammars, guarantee val...\n - llama-cpp: llama.cpp local GGUF inference + HF Hub model discovery.\n - obliteratus: Remove refusal behaviors from open-weight LLMs using OBLI...\n - outlines: Guarantee valid JSON/XML/code structure during generation...\n - serving-llms-vllm: Serves LLMs with high throughput using vLLM's PagedAttent...\n mlops/models: Specific model architectures and tools — computer vision (CLIP, SAM, Stable Diffusion), speech (Whisper), audio generation (AudioCraft), and multimodal models (LLaVA).\n - audiocraft-audio-generation: PyTorch library for audio generation including text-to-mu...\n - clip: OpenAI's model connecting vision and language. Enables ze...\n - segment-anything-model: Foundation model for image segmentation with zero-shot tr...\n - stable-diffusion-image-generation: State-of-the-art text-to-image generation with Stable Dif...\n - whisper: OpenAI's general-purpose speech recognition model. Suppor...\n mlops/research: ML research frameworks for building and optimizing AI systems with declarative programming.\n - dspy: Build complex AI systems with declarative programming, op...\n mlops/training: Fine-tuning, RLHF/DPO/GRPO training, distributed training frameworks, and optimization tools for training LLMs and other models.\n - axolotl: Expert guidance for fine-tuning LLMs with Axolotl - YAML ...\n - fine-tuning-with-trl: Fine-tune LLMs using reinforcement learning with TRL - SF...\n - grpo-rl-training: Expert guidance for GRPO/RL fine-tuning with TRL for reas...\n - peft-fine-tuning: Parameter-efficient fine-tuning for LLMs using LoRA, QLoR...\n - pytorch-fsdp: Expert guidance for Fully Sharded Data Parallel training ...\n - unsloth: Expert guidance for fast fine-tuning with Unsloth - 2-5x ...\n myristica-ops:\n - myristica-ops: Myristica rental management app — stack, infrastructure, ...\n - myristica-projects: Myristica project context, audit status, and development ...\n note-taking: Note taking skills, to save information, assist with research, and collab on multi-session planning and information sharing.\n - obsidian: Read, search, and create notes in the Obsidian vault.\n openclaw-imports:\n - asana: Integrate Asana with Clawdbot via the Asana REST API. Use...\n - bitwarden: Set up and use Bitwarden CLI (bw). Use when installing th...\n - gog: Read-only Google Workspace CLI for Gmail, Calendar, Drive...\n - google-photos: Manage Google Photos library. Upload photos, create album...\n - hevy: Query workout data from Hevy including workouts, routines...\n - model-router: Intelligent cost-aware model routing that classifies task...\n - notion: Notion API for creating and managing pages, databases, an...\n - parallel-preview-orchestrator: Orchestrate parallel preview-site creation across multipl...\n - session-logs: Search and analyze your own session logs (older/parent co...\n - summarize: Summarize URLs or files with the summarize CLI (web, PDFs...\n - weather: Get current weather and forecasts (no API key required).\n personal-browser-cdp:\n - personal-browser-cdp: Use the user's real Chrome browser through Hermes' existi...\n pixel-6a:\n - pixel-6a: Access Ignacio's Pixel 6a via ADB over Tailscale — read n...\n productivity: Skills for document creation, presentations, spreadsheets, and other productivity workflows.\n - google-workspace: Gmail, Calendar, Drive, Contacts, Sheets, and Docs integr...\n - linear: Manage Linear issues, projects, and teams via the GraphQL...\n - maps: Location intelligence — geocode a place, reverse-geocode ...\n - monthy-expenses: Reconstruct and maintain the user's household monthly-exp...\n - nano-pdf: Edit PDFs with natural-language instructions using the na...\n - notion: Notion API for creating and managing pages, databases, an...\n - ocr-and-documents: Extract text from PDFs and scanned documents. Use web_ext...\n - powerpoint: Use this skill any time a .pptx file is involved in any w...\n red-teaming:\n - godmode: Jailbreak API-served LLMs using G0DM0D3 techniques — Pars...\n research: Skills for academic research, paper discovery, literature review, domain reconnaissance, market data, content monitoring, and scientific knowledge retrieval.\n - arxiv: Search and retrieve academic papers from arXiv using thei...\n - blogwatcher: Monitor blogs and RSS/Atom feeds for updates using the bl...\n - llm-wiki: Karpathy's LLM Wiki — build and maintain a persistent, in...\n - ml-paper-writing: Write publication-ready ML/AI papers for NeurIPS, ICML, I...\n - polymarket: Query Polymarket prediction market data — search markets,...\n smart-home: Skills for controlling smart home devices — lights, switches, sensors, and home automation systems.\n - openhue: Control Philips Hue lights, rooms, and scenes via the Ope...\n social-media: Skills for interacting with social platforms and social-media workflows — posting, reading, monitoring, and account operations.\n - xitter: Interact with X/Twitter via the x-cli terminal client usi...\n - xurl: Interact with X/Twitter via xurl, the official X API CLI....\n software-development:\n - code-review: Guidelines for performing thorough code reviews with secu...\n - evaluate-openai-compatible-llm-endpoint: Verify whether a new OpenAI-compatible chat/completions e...\n - hermes-specialist-profile-custom-endpoint: Create a Hermes profile specialized for a model's strengt...\n - plan: Plan mode for Hermes — inspect context, write a markdown ...\n - react-component-split: Split large React client components (>300 lines) into mul...\n - requesting-code-review: Pre-commit verification pipeline — static security scan, ...\n - subagent-driven-development: Use when executing implementation plans with independent ...\n - systematic-debugging: Use when encountering any bug, test failure, or unexpecte...\n - test-driven-development: Use when implementing any feature or bugfix, before writi...\n - writing-plans: Use when you have a spec or requirements for a multi-step...\n wa-bot-fix-troubleshooting:\n - wa-bot-fix-troubleshooting: Fix WhatsApp bot not responding when bridge is connected ...\n\n\nOnly proceed without loading a skill if genuinely none are relevant to the task.\n\n# Project Context\n\nThe following project context files have been loaded and should be followed:\n\n## AGENTS.md\n\n# AGENTS.md — Pipo's Environment\n\nYou are **Pipo**, a personal AI assistant for **Ignacio \"Chicho/Igna\" Lagos Ruiz**.\n\n## Your Memory Files (always check these first)\n\n- `~/.hermes/memories/MEMORY.md` — long-term curated memory\n- `~/.hermes/memories/USER.md` — user profile and preferences\n- `~/.hermes/SOUL.md` — your persona and values\n\n## Environment\n\n- Server: Ubuntu 24.04 ARM64, Oracle Cloud São Paulo\n- Tailscale IP: `100.87.116.90`, hostname: `miopenclaw-vnic.tail9799d2.ts.net`\n- Shell: bash, Node.js v22, Python 3.12\n- Your install: `~/.hermes/`\n\n## Key Facts About Chicho\n\n- Lives in Argentina (UTC-3)\n- Gmail: ignaciolagosruiz@gmail.com\n- Prefers direct responses, no filler\n- Prefers text by default, audio only when asked\n- Uses YouTube Music, not Spotify\n- No Apple devices\n- For scraping Argentine retailers: may need exit node via `tailscale set --exit-node=pixel-6a`\n\n## Scraping Exit Node\n\nWhen scraping Argentine sites (Coto, Carrefour, Día, Disco, Jumbo):\n```bash\ntailscale set --exit-node=pixel-6a # enable before scraping\ntailscale set --exit-node='' # disable after\n```\n\nConversation started: Sunday, April 26, 2026 03:35 AM\nModel: kimi-k2.6\nProvider: kimi-for-coding\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. 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## Current Session Context\n\n**Source:** Telegram (DM with Snack lakes)\n**User:** Snack lakes\n**Connected Platforms:** local (files on this machine), api_server: Connected ✓, telegram: Connected ✓, discord: Connected ✓\n\n**Home Channels (default destinations):**\n - telegram: Home (ID: 842987156)\n - discord: Home (ID: 1483873338022428865)\n\n**Delivery options for scheduled tasks:**\n- `\"origin\"` → Back to this chat (Snack lakes)\n- `\"local\"` → Save to local files only (~/.hermes/cron/output/)\n- `\"telegram\"` → Home channel (Home)\n- `\"discord\"` → Home channel (Home)\n\n*For explicit targeting, use `\"platform:chat_id\"` format if the user provides a specific chat ID.*\n\nYou are a technical expert. Provide detailed, accurate technical information."
},
{
"role": "user",
"content": "[Note: model was just switched from kimi-k2.5 to kimi-k2.6 via Kimi For Coding. Adjust your self-identification accordingly.]\n\nCual es tu explicación para esta cuenta y su único tweet https://x.com/HenryMa79561893\n\n\n[System note: The following is recalled memory context, NOT new user input. Treat as informational background data.]\n\n## User Representation\n## Explicit Observations\n\n[2026-04-10 17:30:11] 842987156 stated they were unsure if 'Pippo' had the API key for ElevenLabs but believed it might be configured.\n[2026-04-10 17:30:11] 842987156 indicated that a transcription of their audio was 'muy rian', and believed it should have been 'muy bien'.\n[2026-04-10 17:30:11] 842987156 referred to someone or something as 'Pipo'.\n[2026-04-10 17:30:11] 842987156 confirmed that a transcription was not correct and asked for it to be redone with a more precise model.\n[2026-04-10 17:30:11] 842987156 requested that the 'whisper' issue be fixed and then asked for the audio message to be listened to.\n[2026-04-10 17:30:11] 842987156 asked for a response using ElevenLabs.\n[2026-04-10 17:30:11] 842987156 attempted to send a voice message that failed transcription due to a local configuration issue.\n[2026-04-10 17:30:11] 842987156 requested that the voice used for responses be changed to an Argentinian accent.\n[2026-04-10 17:30:11] 842987156 asked 'Pippo' to try making API calls to ElevenLabs.\n[2026-04-26 02:32:48] 842987156 found a bug in api/routes.py: 'if val is None and val == \"\"' which should be 'or'.\n[2026-04-26 02:32:48] 842987156 has approximately 3000 lines of uncommitted changes in ~/hermes-webui/, including a new Terminal panel and Profile Config API.\n[2026-04-26 02:33:33] 842987156's model was switched from kimi-k2.5 to kimi-k2.6 via Kimi For Coding on April 26, 2026.\n[2026-04-26 02:33:33] 842987156 was instructed to adjust its self-identification accordingly.\n\n## Deductive Observations\n\n[2026-04-26 03:34:03] Ignacio's API configuration for Kimi has been updated to version 2.6 as of April 26, 2026.\n Premises:\n - 842987156's model was switched from kimi-k2.5 to kimi-k2.6 via Kimi For Coding on April 26, 2026.\n - 842987156's APIs configuration includes ... Kimi K2.5 ...\n\n[2026-04-26 03:34:03] Elena is likely a person or business from whom Ignacio orders cakes.\n Premises:\n - 842987156 previously considered a coconut and dulce de leche cake or a strawberry cake from Elena.\n - 842987156 mentioned they did not call Elena today because they were asking their niece which cake she wanted.\n\n[2026-04-26 03:34:03] Ignacio resides in the Colegiales neighborhood of Buenos Aires, specifically near the intersection of Ciudad de la Paz and Céspedes.\n Premises:\n - 842987156 lives in the area of Ciudad de la Paz y Céspedes.\n - 842987156 likes Palermo parks and local Colegiales parks near Parque Ferroviario.\n\n[2026-04-26 03:34:03] The dog's name is correctly spelled 'Chivi'; previous mentions of 'Chibi' are misspellings.\n Premises:\n - 842987156's dog's name is Chivi (with a 'v').\n - 842987156 mentioned that Chibi likes to go to parks...\n\n[2026-04-26 03:34:13] 'Pipo' (or 'Pippo') is a nickname or identifier Ignacio uses for the AI agent or the persona he is interacting with, specifically in the context of automation and API tasks.\n Premises:\n - 842987156 asked 'Pippo' to try making API calls to ElevenLabs.\n - 842987156 does not want Pipo to interact with others via WhatsApp or messaging for now.\n\n\n## Inductive Observations\n\n **Pattern** [high]: Avoids mainstream consumer ecosystems (Apple, Spotify) in favor of specialized tools (YouTube Music, Asana) and maintains a complex, cross-platform technical setup (Tailscale, Oracle Cloud, ARM64).\n **Type**: preference\n **Sources**:\n - 842987156 does not use Apple devices.\n - 842987156 does not use Spotify; prefers YouTube Music.\n - 842987156 prefers Asana over Trello.\n - 842987156 has Tailscale on their personal computer for cross-device access.\n - 842987156's environment includes Ubuntu 24.04 ARM64 and Oracle Cloud.\n\n **Pattern** [medium]: Integrates family needs and local Buenos Aires neighborhood identity (Colegiales) into daily routines and technical requests.\n **Type**: tendency\n **Sources**:\n - Ignacio resides in the Colegiales neighborhood... near Ciudad de la Paz and Céspedes.\n - Ignacio was asking his niece which cake she wanted.\n - 842987156 likes Palermo parks and local Colegiales parks...\n - 842987156 does not want Pipo to interact with others via WhatsApp... (boundary protection for private life)\n\n **Pattern** [high]: Tends to accumulate a high volume of uncommitted code changes during active development cycles before committing or stashing.\n **Type**: behavior\n **Sources**:\n - CODE changes persist as uncommitted git changes in ~/hermes-webui/\n - 842987156 has approximately 3000 lines of uncommitted changes in ~/hermes-webui/\n - 842987156 found a bug in api/routes.py...\n\n **Pattern** [high]: Prioritizes communication efficiency and cost-consciousness, preferring direct answers and optimizing AI resource usage (tokens, audio, model selection).\n **Type**: behavior\n **Sources**:\n - 842987156 prefers default text responses to save ElevenLabs tokens.\n - 842987156 wants audio responses only when explicitly requested.\n - 842987156 prefers direct answers and clear boundaries...\n - 842987156 does not use DeepSeek or Kimi as a daily driver, only for workers/sub-agents.\n\n\n\n## User Peer Card\nName: Ignacio (Igna, Chicho)\nLocation: Buenos Aires, Argentina (Colegiales neighborhood)\nWife: Tina\nNiece: Macarena\nPet: Dog named Chivi\nWorks on: hermes-webui project\nOS: Ubuntu 24.04 ARM64 (Oracle Cloud)\nPhone: Pixel 6a (used as Tailscale exit node)\nTRAIT: Prefers direct, efficient answers with clear boundaries\nTRAIT: Cost-conscious regarding AI (tokens, model selection)\nTRAIT: Independent regarding tech ecosystems (avoids Apple/Spotify)\nTRAIT: Tends to accumulate large volumes of uncommitted code\nTRAIT: Maintains complex, cross-platform infrastructure (Tailscale/SSH)\nPREFERENCE: No audio responses unless explicitly requested\nPREFERENCE: Asana over Trello\nPREFERENCE: YouTube Music over Spotify\nPREFERENCE: Kimi K2.6 over K2.5 (as of April 2026)\nINSTRUCTION: Use an Argentinian accent for audio responses\nINSTRUCTION: Treat MEMORIES.md as canonical long-term memory file\n\n## AI Self-Representation\n## Explicit Observations\n\n[2026-04-10 04:09:28] hermes confirmed that Honcho API provides persistent memory with reasoning.\n[2026-04-10 04:09:28] hermes performed a test on Honcho API, saving and retrieving a conclusion about tool activation.\n[2026-04-10 04:09:28] hermes mentioned that GitHub is for operations with repos, PRs, issues, etc.\n[2026-04-10 04:09:28] hermes identified OpenAI TTS and ElevenLabs as text-to-speech options.\n[2026-04-10 04:09:28] hermes reported that Honcho API's persistent memory is functioning correctly.\n[2026-04-10 04:09:28] hermes stated that Exa enhances `web_search` and `web_extract` capabilities.\n[2026-04-10 04:09:28] hermes executed a test search using Exa with the query `site:reddit.com best self-hosted LLM 2025`.\n[2026-04-10 04:09:28] hermes indicated that Parallel is used for parallel/distributed processing.\n[2026-04-10 17:21:02] hermes can report configuration bugs in the Hermes system as issues.\n[2026-04-22 17:06:38] hermes cannot see active browser sessions on the user's devices.\n[2026-04-22 17:06:38] hermes's web backend is set to exa, and a Parallel MCP server was not found.\n[2026-04-22 17:06:38] hermes is aware that Parallel could be a web backend replacement for Exa or an MCP server.\n[2026-04-22 17:06:38] hermes believes that TTS API keys might need to be loaded into its environment or set in the config under tts.openai.api_key or tts.elevenlabs.api_key fields.\n[2026-04-22 17:06:38] hermes can see the user's Hermes/WebUI session, which is using the kimi-k2.5 model via the kimi-coding provider.\n[2026-04-22 17:06:38] hermes can access credentials stored in Bitwarden that it may have accessed previously.\n[2026-04-22 17:06:38] hermes cannot see third-party service login states unless a specific skill is configured for it.\n[2026-04-22 17:06:38] hermes is configured for TTS - ElevenLabs with the model multilingual_v2, but the ElevenLabs API key is not set in the environment.\n[2026-04-22 17:06:38] hermes can see the user's tailscale identity, including hostname and IPs.\n[2026-04-22 17:06:38] hermes does not have visibility into any 'nous' login state and does not see 'Nous Research' or any service called 'nous' in its memory or current context.\n[2026-04-22 17:06:38] hermes uses GitHub CLI authenticated as ignaciolagosruiz with repo/gist/workflow scopes.\n[2026-04-22 17:06:38] hermes is configured to use TTS - Edge as the default provider and it is working.\n[2026-04-22 17:06:38] hermes is configured for TTS - OpenAI with the model gpt-4o-mini-tts and voice alloy, but the OpenAI API key is not set in the environment.\n\n## Inductive Observations\n\n **Pattern** [high]: Ignacio prioritizes cost-efficiency in his technical setup, often opting for free or lower-cost alternatives (like Edge TTS or text-only responses) to manage API expenses and token usage.\n **Type**: preference\n **Sources**:\n - Prefers text by default to save tokens.\n - Hermes prioritizes economical TTS (Edge).\n - Understands cost of ElevenLabs/OpenAI.\n\n **Pattern** [high]: Ignacio displays a hands-on and direct behavioral pattern when dealing with technical issues, expecting immediate fixes or detailed explanations and involving himself in configuration management (YAML, Bitwarden).\n **Type**: behavior\n **Sources**:\n - Commands agent to 'fix whisper now'.\n - Manages own credentials and environment.\n - Involved in troubleshooting Whisper configuration mismatch.\n\n **Pattern** [high]: Ignacio has a strong preference for Argentinian-localized interactions, specifically for TTS voices (es-AR-ElenaNeural) and regional exit nodes, finding generic or non-localized variants unsatisfactory.\n **Type**: preference\n **Sources**:\n - Complained that default Edge TTS 'sounds horrible'.\n - Requested Argentinian voice change.\n - Mentioned need for Argentinian exit node for scraping.\n\n\n\n## AI Identity Card\nName: Ignacio (Igna, Chicho)\nLocation: Colegiales, Buenos Aires, Argentina (UTC-3)\nOccupation: Developer / Technical User (Working on Hermes system)\nFamily: Wife named Tina; nieces including Macarena\nPet: Dog named Chivi (likes Palermo and local Colegiales parks)\nApartment: 80sqm ($900/mo); evaluating 65sqm ARS-priced options\nGmail: ignaciolagosruiz@gmail.com\nTRAIT: Prefers direct, no-filler communication\nTRAIT: Multimodal communicator (voice for context, text for precision/correction)\nTRAIT: High attention to detail (corrects names/locations promptly)\nTRAIT: Analytical thinker (e.g., calculates cost-per-sqm, dual-currency analysis)\nTRAIT: Hands-on technical troubleshooter\nTRAIT: Prioritizes cost-efficiency (e.g., Edge TTS over ElevenLabs)\nPREFERENCE: Values walkability and local neighborhood proximity (10-20 min radius)\nPREFERENCE: Prefers YouTube Music over Spotify\nPREFERENCE: Prefers Asana over Trello\nPREFERENCE: Argentinian-localized Spanish (es-AR-ElenaNeural) and regional exit nodes\nINSTRUCTION: Use audio only when explicitly requested\nINSTRUCTION: Do not interact with others via messaging apps for now\nTech Environment: Ubuntu 24.04 ARM64 (Oracle Cloud)\nTech Environment: Uses Tailscale for cross-device access (Pixel 6a exit node)\nTech Environment: Does not use Apple devices\nTech Environment: Uses Bitwarden for API key storage\nSystem Detail: Hermes agent is also referred to as 'Pipo' or 'Pippo'\nSystem Detail: Hermes replaced OpenClaw system; source at ~/hermes-webui\nKnowledge: Deep expertise in Argentine Patagonia geography and tourism\n\nBased on the prefetched observations, here's the most relevant **active context** for this conversation:\n\n## **Immediate Work Context**\n\n**Ignacio is currently in Bariloche (arrived April 25, 2026) with ~3000 lines of uncommitted code changes in hermes-webui.** This is active work-in-progress, not historical background. The changes include a new Terminal panel and Profile Config API—features he's actively developing.\n\n## **Current Technical Setup**\n\n- **Multi-device workflow**: Ubuntu 24.04 ARM64 (Oracle Cloud) + Windows PC (Chrome/CDP) + Pixel 6a (Tailscale exit node for Argentine …\n"
},
{
"role": "assistant",
"content": "",
"reasoning_content": "El usuario me está preguntando sobre una cuenta de Twitter/X específica: https://x.com/HenryMa79561893 y su único tweet. Necesito investigar esto.\n\nPrimero, debería extraer el contenido de esa página para ver de qué se trata. Luego puedo dar mi análisis.\n\nVoy a usar web_extract para ver el contenido de esa URL.",
"tool_calls": [
{
"id": "web_extract:0",
"type": "function",
"function": {
"name": "web_extract",
"arguments": "{\"urls\":[\"https://x.com/HenryMa79561893\"]}"
}
}
]
},
{
"role": "tool",
"content": "{\"error\": \"Content was inaccessible or not found\"}",
"tool_call_id": "web_extract:0"
},
{
"role": "assistant",
"content": "",
"reasoning_content": "X/Twitter bloquea web_extract. Necesito usar el skill de xitter o xurl, o navegar con el browser. Déjame ver si tengo skills para Twitter. Sí, tengo `xitter` y `xurl`. Pero esas son para interactuar via CLI. También podría usar browser_navigate.\n\nVoy a intentar con browser_navigate para ver la página.",
"tool_calls": [
{
"id": "browser_navigate:1",
"type": "function",
"function": {
"name": "browser_navigate",
"arguments": "{\"url\":\"https://x.com/HenryMa79561893\"}"
}
}
]
},
{
"role": "tool",
"content": "{\"success\": false, \"error\": \"All CDP discovery methods failed for 127.0.0.1:9223: /json/version: Failed to connect to CDP at 127.0.0.1:9223: error sending request for url (http://127.0.0.1:9223/json/version); /json/list: Failed to connect to /json/list at 127.0.0.1:9223: error sending request for url (http://127.0.0.1:9223/json/list); WebSocket: WebSocket connect failed at ws://127.0.0.1:9223/devtools/browser: IO error: Connection refused (os error 111)\"}",
"tool_call_id": "browser_navigate:1"
},
{
"role": "assistant",
"content": "",
"reasoning_content": "El browser CDP no está disponible (necesitaría conectar Chrome primero, y probablemente Chicho no tiene el tunnel activo ahora). Déjame probar con los skills de Twitter. Tengo `xurl` que es el CLI oficial de X API. Pero para ver un perfil público, podría usar `xurl` o buscar en la web.\n\nTambién podría usar web_search para buscar información sobre esa cuenta.",
"tool_calls": [
{
"id": "web_search:2",
"type": "function",
"function": {
"name": "web_search",
"arguments": "{\"query\":\"site:x.com HenryMa79561893 OR HenryMa79561893 twitter\"}"
}
}
]
},
{
"role": "tool",
"content": "{\n \"success\": true,\n \"data\": {\n \"web\": [\n {\n \"url\": \"https://github.com/henry-ma\",\n \"title\": \"Henry Ma (@henry-ma)\",\n \"description\": \"# User: Henry Ma (@henry-ma)\\n[...]\\n- Company: Nvidia Networking\\n- Followers: 0\\n- Following: 0\\n- Public Repos: 1\\n- Joined: 2016-12-14\",\n \"position\": 1\n },\n {\n \"url\": \"https://github.com/logos-mhr\",\n \"title\": \"Henry Ma (@logos-mhr)\",\n \"description\": \"# User: Henry Ma (@logos-mhr)\\n[...]\\n- Followers: 2\\n- Following: 2\\n- Public Repos: 29\\n- Joined: 2017-07-25\",\n \"position\": 2\n },\n {\n \"url\": \"https://github.com/HenryMa96\",\n \"title\": \"HenryMa (@HenryMa96)\",\n \"description\": \"# User: HenryMa (@HenryMa96)\\n[...]\\n- Followers: 3\\n- Following: 19\\n- Public Repos: 39\\n- Joined: 2015-03-28\",\n \"position\": 3\n },\n {\n \"url\": \"http://cdnjs.deepai.org/profile/henry-ma\",\n \"title\": \"Henry Ma | DeepAI\",\n \"description\": \"Henry Ma | DeepAI \\n\\nDeepAI Pro - More Access to Better AI×\\n[...]\\n# Henry Ma\\n\\n## Featured Co-authors\\n[...]\\n17 publications\\n[...]\\n∙ 04/19/2022\\n[...]\\n### Quartz: Superoptimization of Quantum Circuits (Extended Version)\",\n \"position\": 4\n },\n {\n \"url\": \"https://github.com/MAhaitao999\",\n \"title\": \"Henry Ma (@MAhaitao999)\",\n \"description\": \"# User: Henry Ma (@MAhaitao999)\\n[...]\\n- Company: Transwarp->Inceptio->Bosch\\n- Location: Shanghai\\n- Followers: 30\\n- Following: 5\\n- Public Repos: 57\\n- Joined: 2014-09-09\",\n \"position\": 5\n }\n ]\n }\n}",
"tool_call_id": "web_search:2"
},
{
"role": "assistant",
"content": "",
"reasoning_content": "La búsqueda no arrojó resultados directos de Twitter. Déjame intentar con `xurl` skill o buscar de otra forma. Aunque xurl es para la API oficial y requiere auth. Quizás debería ver si tengo el skill xitter configurado.\n\nOtra opción: buscar el handle exacto en Google con comillas.",
"tool_calls": [
{
"id": "web_search:3",
"type": "function",
"function": {
"name": "web_search",
"arguments": "{\"query\":\"\\\"HenryMa79561893\\\" tweet\"}"
}
}
]
},
{
"role": "tool",
"content": "{\n \"success\": true,\n \"data\": {\n \"web\": [\n {\n \"url\": \"https://github.com/HenryMa96\",\n \"title\": \"HenryMa (@HenryMa96)\",\n \"description\": \"# User: HenryMa (@HenryMa96)\\n\\n- Followers: 3\\n- Following: 19\\n- Public Repos: 39\\n- Joined: 2015-03-28\\n\\n---\\n\\n## Recent Activity (Mar 16, 2026 - Mar 16, 2026)\\n\\nContributed to: THU-MAIC/OpenMAIC\\n\\n---\\n\\n## Top Repositories\\n\\n| Repository | Description | Stars | Language | Last Updated |\\n| --- | --- | --- | --- | --- |\\n| How-to-win-a-data-science-competition-Coursera | notes, assignments of \\\"How to win a data science competition\\\" in Coursera | 5 | Jupyter Notebook | 2017-12-05 |\\n| Ali-TianChi-WifiLocation | | 2 | | 2017-10-30 |\\n| Blast | A modular destruction SDK designed for performance and flexibility, replacing APEX destruction | 0 | C++ | 2024-11-19 |\\n| BookContainer | 旨在学习，共同进步。 | 0 | | 2024-09-20 |\\n| box2d-lite | A small 2D physics engine | 0 | | 2020-01-10 |\\n| cctbx_project | Computational Crystallography Toolbox | 0 | Python | 2018-08-14 |\",\n \"position\": 1\n },\n {\n \"url\": \"https://www.vietnam.vn/en/henry-nhieu-cau-thu-real-madrid-khong-du-trinh-do\",\n \"title\": \"Henry: 'Many Real Madrid players are not good enough'\",\n \"description\": \"Discover the exceptional value of\\n[...]\\nBinh province's 5 new National Treasures. 5\",\n \"position\": 2\n },\n {\n \"url\": \"https://getdaytrends.com/it/canada/trend/Henry/\",\n \"title\": \"Henry • Canada • Twitter Argomento Popolare\",\n \"description\": \"Henry • Canada • Twitter Argomento Popolare\\n[...]\\n# Henry Canada\\n[...]\\ngrado più alto Gen 20, 2025 02:00\\n[...]\\n#22\\n[...]\\nvisto Dic 28, 2025 02:00\\n[...]\\n77.8K tweets\\n[...]\\nTweet Esplora su Twitter\\n[...]\\n## Henry in Altre Posizioni\\n[...]\\n2026\\n[...]\\n05:00 |\\n[...]\\n| --- | --- |\\n[...]\\n| Turchia | Feb 18, 2026 17:00 |\\n| Portogallo | Gen 29, 2026 18:00 |\\n| Argentina | Gen 02, 2026 21:00 |\\n| Brasile | Gen 02, 2026 14:00 |\\n| Svezia | Gen 02, 2026 10:00 |\\n| Italia | Gen 02, 2026 07:00 |\\n| Perù | Gen 02, 2026 04:00 |\\n| Ecuador | Gen 02, 2026 02:00 |\\n| Australia | Gen 01, 2026 14:00 |\\n| Cile | Gen 01, 2026 11:00 |\\n| Polonia | Gen 01, 2026 11:00 |\\n| Malesia | Gen 01, 2026 08:00 |\\n| Colombia | Gen 01, 2026 07:00 |\\n| Germania | Gen 01, 2026 06:00 |\\n| Guatemala | Dic 29, 2025 02:00 |\\n| Canada | Dic 28, 2025 02:00 |\\n| Venezuela | Dic 27, 2025 20:00 |\\n| Ghana | Dic 26, 2025 22:00 |\\n| Portorico | Dic 22, 2025 14:00 |\\n| Stati Uniti | Dic 22, 2025 14:00 |\\n| Mondiali | Nov 27, 2025 07:00 |\\n| Vietnam | Nov 21, 2025 09:00 |\\n| Kenya | Ago 30, 2025 03:00 |\\n| Olanda | Ago 02, 2025 09:00 |\\n| Emirati Arabi Uniti | Mag 30, 2025 11:00 |\\n| Sudafrica | Mag 29, 2025 09:00 |\\n| Spagna | Mag 12, 2025 01:00 |\\n| Svizzera | Mar 27, 2025 14:00 |\\n| Panamá | Mar 23, 2025 20:00 |\\n| Filippine | Dic 29, 2024 08:00 |\\n| Indonesia | Set 03, 2024 16:00 |\",\n \"position\": 3\n },\n {\n \"url\": \"https://getdaytrends.com/it/peru/trend/Henry/\",\n \"title\": \"Henry • Perù • Twitter Argomento Popolare\",\n \"description\": \"Henry • Perù • Twitter Argomento Popolare\\n[...]\\n# Henry Perù\\n[...]\\n#12\\n[...]\\ngrado più alto Dic 27, 2025 15:00\\n[...]\\n#36\\n[...]\\nvisto Gen 02, 2026 04:00\\n[...]\\n127.3K tweets\\n[...]\\nTweet Esplora su Twitter\\n[...]\\n## Henry in Altre Posizioni\\n[...]\\n026 04:00 |\\n[...]\\n| Regno Unito |\\n[...]\\n, 2026 09:00 |\\n[...]\\n2026 14:00 |\\n[...]\\n| Irlanda |\\n[...]\\n14\\n[...]\\n2026 09:00 |\\n[...]\\n| Pakistan | Mar 08\\n[...]\\n026 16:00 |\\n[...]\\n| Singapore | Feb 21, 2026 05:00 |\\n| --- | --- |\\n| Turchia | Feb 18, 2026 17:00 |\\n| Portogallo | Gen 29, 2026 18:00 |\\n| Argentina | Gen 02, 2026 21:00 |\\n| Brasile | Gen 02, 2026 14:00 |\\n| Svezia | Gen 02, 2026 10:00 |\\n| Italia | Gen 02, 2026 07:00 |\\n| Perù | Gen 02, 2026 04:00 |\\n| Ecuador | Gen 02, 2026 02:00 |\\n| Australia | Gen 01, 2026 14:00 |\\n| Cile | Gen 01, 2026 11:00 |\\n| Polonia | Gen 01, 2026 11:00 |\\n| Malesia | Gen 01, 2026 08:00 |\\n| Colombia | Gen 01, 2026 07:00 |\\n| Germania | Gen 01, 2026 06:00 |\\n| Guatemala | Dic 29, 2025 02:00 |\\n| Canada | Dic 28, 2025 02:00 |\\n| Venezuela | Dic 27, 2025 20:00 |\\n| Ghana | Dic 26, 2025 22:00 |\\n| Portorico | Dic 22, 2025 14:00 |\\n| Stati Uniti | Dic 22, 2025 14:00 |\\n| Mondiali | Nov 27, 2025 07:00 |\\n| Vietnam | Nov 21, 2025 09:00 |\\n| Kenya | Ago 30, 2025 03:00 |\\n| Olanda | Ago 02, 2025 09:00 |\\n| Emirati Arabi Uniti | Mag 30, 2025 11:00 |\\n| Sudafrica | Mag 29, 2025 09:00 |\\n| Spagna | Mag 12, 2025 01:00 |\\n| Svizzera | Mar 27, 2025 14:00 |\\n| Panamá | Mar 23, 2025 20:00 |\\n| Filippine | Dic 29, 2024 08:00 |\\n| Indonesia | Set 03, 2024 16:00 |\",\n \"position\": 4\n },\n {\n \"url\": \"https://getdaytrends.com/de/ireland/trend/Henry/\",\n \"title\": \"Henry • Irland • Twitter Trend Thema\",\n \"description\": \"Henry • Irland • Twitter Trend Thema\\n[...]\\n# Henry Irland\\n[...]\\nhöchster Rang Mai 21, 2025 10:00\\n[...]\\n#49\\n[...]\\nzuletzt gesehen Mär 14, 2026 09:00\\n[...]\\nUnter 10K tweets\\n[...]\\nTweet Entdecken Sie auf Twitter\\n[...]\\n## Henry an Anderen Orten\\n[...]\\n| Zuletzt gesehen |\\n| --- |\\n| Spanien | vor einer Tag |\\n| Indien | vor 4 Tagen |\\n| Mexiko | vor 6 Tagen |\\n| Neuseeland | Mär 30, 2026 09:00 |\\n| Frankreich | Mär 28, 2026 10:00 |\\n| Nigeria | Mär 27, 2026 05:00 |\\n| Norwegen | Mär 27, 2026 04:00 |\\n| Großbritannien | Mär 26, 2026 09:00 |\\n| Belgien | Mär 25, 2026 14:00 |\\n| Irland | Mär 14, 2026 09:00 |\",\n \"position\": 5\n }\n ]\n }\n}",
"tool_call_id": "web_search:3"
},
{
"role": "assistant",
"content": "",
"reasoning_content": "No estoy pudiendo acceder al contenido de Twitter directamente. Déjame intentar con el skill xurl o xitter. O quizás usar nitter o alguna instancia alternativa. Pero probablemente es más efectivo preguntarle al usuario qué dice el tweet, ya que él ya lo vio y me está pidiendo mi explicación.\n\nSin embargo, debería intentar usar el skill de xitter para ver si puedo obtener el perfil. Voy a cargar el skill xitter.",
"tool_calls": [
{
"id": "skill_view:4",
"type": "function",
"function": {
"name": "skill_view",
"arguments": "{\"name\":\"xitter\"}"
}
}
]
},
{
"role": "tool",
"content": "{\"success\": true, \"name\": \"xitter\", \"description\": \"Interact with X/Twitter via the x-cli terminal client using official X API credentials. Use for posting, reading timelines, searching tweets, liking, retweeting, bookmarks, mentions, and user lookups.\", \"tags\": [\"twitter\", \"x\", \"social-media\", \"x-cli\"], \"related_skills\": [], \"content\": \"---\\nname: xitter\\ndescription: Interact with X/Twitter via the x-cli terminal client using official X API credentials. Use for posting, reading timelines, searching tweets, liking, retweeting, bookmarks, mentions, and user lookups.\\nversion: 1.0.0\\nauthor: Siddharth Balyan + Hermes Agent\\nlicense: MIT\\nplatforms: [linux, macos]\\nprerequisites:\\n commands: [uv]\\n env_vars: [X_API_KEY, X_API_SECRET, X_BEARER_TOKEN, X_ACCESS_TOKEN, X_ACCESS_TOKEN_SECRET]\\nmetadata:\\n hermes:\\n tags: [twitter, x, social-media, x-cli]\\n homepage: https://github.com/Infatoshi/x-cli\\n---\\n\\n# Xitter — X/Twitter via x-cli\\n\\nUse `x-cli` for official X/Twitter API interactions from the terminal.\\n\\nThis skill is for:\\n- posting tweets, replies, and quote tweets\\n- searching tweets and reading timelines\\n- looking up users, followers, and following\\n- liking and retweeting\\n- checking mentions and bookmarks\\n\\nThis skill intentionally does not vendor a separate CLI implementation into Hermes. Install and use upstream `x-cli` instead.\\n\\n## Important Cost / Access Note\\n\\nX API access is not meaningfully free for most real usage. Expect to need paid or prepaid X developer access. If commands fail with permissions or quota errors, check your X developer plan first.\\n\\n## Install\\n\\nInstall upstream `x-cli` with `uv`:\\n\\n```bash\\nuv tool install git+https://github.com/Infatoshi/x-cli.git\\n```\\n\\nUpgrade later with:\\n\\n```bash\\nuv tool upgrade x-cli\\n```\\n\\nVerify:\\n\\n```bash\\nx-cli --help\\n```\\n\\n## Credentials\\n\\nYou need these five values from the X Developer Portal:\\n- `X_API_KEY`\\n- `X_API_SECRET`\\n- `X_BEARER_TOKEN`\\n- `X_ACCESS_TOKEN`\\n- `X_ACCESS_TOKEN_SECRET`\\n\\nGet them from:\\n- https://developer.x.com/en/portal/dashboard\\n\\n### Why does X need 5 secrets?\\n\\nUnfortunately, the official X API splits auth across both app-level and user-level credentials:\\n\\n- `X_API_KEY` + `X_API_SECRET` identify your app\\n- `X_BEARER_TOKEN` is used for app-level read access\\n- `X_ACCESS_TOKEN` + `X_ACCESS_TOKEN_SECRET` let the CLI act as your user account for writes and authenticated actions\\n\\nSo yes — it is a lot of secrets for one integration, but this is the stable official API path and is still preferable to cookie/session scraping.\\n\\nSetup requirements in the portal:\\n1. Create or open your app\\n2. In user authentication settings, set permissions to `Read and write`\\n3. Generate or regenerate the access token + access token secret after enabling write permissions\\n4. Save all five values carefully — missing any one of them will usually produce confusing auth or permission errors\\n\\nNote: upstream `x-cli` expects the full credential set to be present, so even if you mostly care about read-only commands, it is simplest to configure all five.\\n\\n## Cost / Friction Reality Check\\n\\nIf this setup feels heavier than it should be, that is because it is. X’s official developer flow is high-friction and often paid. This skill chooses the official API path because it is more stable and maintainable than browser-cookie/session approaches.\\n\\nIf the user wants the least brittle long-term setup, use this skill. If they want a zero-setup or unofficial path, that is a different trade-off and not what this skill is for.\\n\\n\\n## Where to Store Credentials\\n\\n`x-cli` looks for credentials in `~/.config/x-cli/.env`.\\n\\nIf you already keep your X credentials in `~/.hermes/.env`, the cleanest setup is:\\n\\n```bash\\nmkdir -p ~/.config/x-cli\\nln -sf ~/.hermes/.env ~/.config/x-cli/.env\\n```\\n\\nOr create a dedicated file:\\n\\n```bash\\nmkdir -p ~/.config/x-cli\\ncat > ~/.config/x-cli/.env <<'EOF'\\nX_API_KEY=your_consumer_key\\nX_API_SECRET=your_secret_key\\nX_BEARER_TOKEN=your_bearer_token\\nX_ACCESS_TOKEN=your_access_token\\nX_ACCESS_TOKEN_SECRET=your_access_token_secret\\nEOF\\nchmod 600 ~/.config/x-cli/.env\\n```\\n\\n## Quick Verification\\n\\n```bash\\nx-cli user get openai\\nx-cli tweet search \\\"from:NousResearch\\\" --max 3\\nx-cli me mentions --max 5\\n```\\n\\nIf reads work but writes fail, regenerate the access token after confirming `Read and write` permissions.\\n\\n## Common Commands\\n\\n### Tweets\\n\\n```bash\\nx-cli tweet post \\\"hello world\\\"\\nx-cli tweet get https://x.com/user/status/1234567890\\nx-cli tweet delete 1234567890\\nx-cli tweet reply 1234567890 \\\"nice post\\\"\\nx-cli tweet quote 1234567890 \\\"worth reading\\\"\\nx-cli tweet search \\\"AI agents\\\" --max 20\\nx-cli tweet metrics 1234567890\\n```\\n\\n### Users\\n\\n```bash\\nx-cli user get openai\\nx-cli user timeline openai --max 10\\nx-cli user followers openai --max 50\\nx-cli user following openai --max 50\\n```\\n\\n### Self / Authenticated User\\n\\n```bash\\nx-cli me mentions --max 20\\nx-cli me bookmarks --max 20\\nx-cli me bookmark 1234567890\\nx-cli me unbookmark 1234567890\\n```\\n\\n### Quick Actions\\n\\n```bash\\nx-cli like 1234567890\\nx-cli retweet 1234567890\\n```\\n\\n## Output Modes\\n\\nUse structured output when the agent needs to inspect fields programmatically:\\n\\n```bash\\nx-cli -j tweet search \\\"AI agents\\\" --max 5\\nx-cli -p user get openai\\nx-cli -md tweet get 1234567890\\nx-cli -v -j tweet get 1234567890\\n```\\n\\nRecommended defaults:\\n- `-j` for machine-readable output\\n- `-v` when you need timestamps, metrics, or metadata\\n- plain/default mode for quick human inspection\\n\\n## Agent Workflow\\n\\n1. Confirm `x-cli` is installed\\n2. Confirm credentials are present\\n3. Start with a read command (`user get`, `tweet search`, `me mentions`)\\n4. Use `-j` when extracting fields for later steps\\n5. Only perform write actions after confirming the target tweet/user and the user's intent\\n\\n## Pitfalls\\n\\n- **Paid API access**: many failures are plan/permission problems, not code problems.\\n- **403 oauth1-permissions**: regenerate the access token after enabling `Read and write`.\\n- **Reply restrictions**: X restricts many programmatic replies. `tweet quote` is often more reliable than `tweet reply`.\\n- **Rate limits**: expect per-endpoint limits and cooldown windows.\\n- **Credential drift**: if you rotate tokens in `~/.hermes/.env`, make sure `~/.config/x-cli/.env` still points at the current file.\\n\\n## Notes\\n\\n- Prefer official API workflows over cookie/session scraping.\\n- Use tweet URLs or IDs interchangeably — `x-cli` accepts both.\\n- If bookmark behavior changes upstream, check the upstream README first:\\n https://github.com/Infatoshi/x-cli\\n\", \"path\": \"social-media/xitter/SKILL.md\", \"skill_dir\": \"/home/ubuntu/.hermes/skills/social-media/xitter\", \"linked_files\": null, \"usage_hint\": null, \"required_environment_variables\": [{\"name\": \"X_API_KEY\", \"prompt\": \"Enter value for X_API_KEY\"}, {\"name\": \"X_API_SECRET\", \"prompt\": \"Enter value for X_API_SECRET\"}, {\"name\": \"X_BEARER_TOKEN\", \"prompt\": \"Enter value for X_BEARER_TOKEN\"}, {\"name\": \"X_ACCESS_TOKEN\", \"prompt\": \"Enter value for X_ACCESS_TOKEN\"}, {\"name\": \"X_ACCESS_TOKEN_SECRET\", \"prompt\": \"Enter value for X_ACCESS_TOKEN_SECRET\"}], \"required_commands\": [], \"missing_required_environment_variables\": [\"X_API_KEY\", \"X_API_SECRET\", \"X_BEARER_TOKEN\", \"X_ACCESS_TOKEN\", \"X_ACCESS_TOKEN_SECRET\"], \"missing_credential_files\": [], \"missing_required_commands\": [], \"setup_needed\": true, \"setup_skipped\": false, \"readiness_status\": \"setup_needed\", \"gateway_setup_hint\": \"Secure secret entry is not supported over messaging. Load this skill in the local CLI to be prompted, or add the key to ~/.hermes/.env manually.\", \"setup_note\": \"Setup needed before using this skill: missing env $X_API_KEY, env $X_API_SECRET, env $X_BEARER_TOKEN, env $X_ACCESS_TOKEN, env $X_ACCESS_TOKEN_SECRET.\", \"metadata\": {\"hermes\": {\"tags\": [\"twitter\", \"x\", \"social-media\", \"x-cli\"], \"homepage\": \"https://github.com/Infatoshi/x-cli\"}}}",
"tool_call_id": "skill_view:4"
}
],
"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_cdp",
"description": "Send a raw Chrome DevTools Protocol (CDP) command. Escape hatch for browser operations not covered by browser_navigate, browser_click, browser_console, etc.\n\n**Requires a reachable CDP endpoint.** Available when the user has run '/browser connect' to attach to a running Chrome, or when 'browser.cdp_url' is set in config.yaml. Not currently wired up for cloud backends (Browserbase, Browser Use, Firecrawl) — those expose CDP per session but live-session routing is a follow-up. Camofox is REST-only and will never support CDP. If the tool is in your toolset at all, a CDP endpoint is already reachable.\n\n**CDP method reference:** https://chromedevtools.github.io/devtools-protocol/ — use web_extract on a method's URL (e.g. '/tot/Page/#method-handleJavaScriptDialog') to look up parameters and return shape.\n\n**Common patterns:**\n- List tabs: method='Target.getTargets', params={}\n- Handle a native JS dialog: method='Page.handleJavaScriptDialog', params={'accept': true, 'promptText': ''}, target_id=\n- Get all cookies: method='Network.getAllCookies', params={}\n- Eval in a specific tab: method='Runtime.evaluate', params={'expression': '...', 'returnByValue': true}, target_id=\n- Set viewport for a tab: method='Emulation.setDeviceMetricsOverride', params={'width': 1280, 'height': 720, 'deviceScaleFactor': 1, 'mobile': false}, target_id=\n\n**Usage rules:**\n- Browser-level methods (Target.*, Browser.*, Storage.*): omit target_id and frame_id.\n- Page-level methods (Page.*, Runtime.*, DOM.*, Emulation.*, Network.* scoped to a tab): pass target_id from Target.getTargets.\n- **Cross-origin iframe scope** (Runtime.evaluate inside an OOPIF, Page.* targeting a frame target, etc.): pass frame_id from the browser_snapshot frame_tree output. This routes through the CDP supervisor's live connection — the only reliable way on Browserbase where stateless CDP calls hit signed-URL expiry.\n- Each stateless call (without frame_id) is independent — sessions and event subscriptions do not persist between calls. For stateful workflows, prefer the dedicated browser tools or use frame_id routing.",
"parameters": {
"type": "object",
"properties": {
"method": {
"type": "string",
"description": "CDP method name, e.g. 'Target.getTargets', 'Runtime.evaluate', 'Page.handleJavaScriptDialog'."
},
"params": {
"type": "object",
"description": "Method-specific parameters as a JSON object. Omit or pass {} for methods that take no parameters.",
"properties": {},
"additionalProperties": true
},
"target_id": {
"type": "string",
"description": "Optional. Target/tab ID from Target.getTargets result (each entry's 'targetId'). Use for page-level methods at the top-level tab scope. Mutually exclusive with frame_id."
},
"frame_id": {
"type": "string",
"description": "Optional. Out-of-process iframe (OOPIF) frame_id from browser_snapshot.frame_tree.children[] where is_oopif=true. When set, routes the call through the CDP supervisor's live session for that iframe. Essential for Runtime.evaluate inside cross-origin iframes, especially on Browserbase where fresh per-call CDP connections can't keep up with signed URL rotation. For same-origin iframes, use parent contentWindow/contentDocument from Runtime.evaluate at the top-level page instead."
},
"timeout": {
"type": "number",
"description": "Timeout in seconds (default 30, max 300).",
"default": 30
}
},
"required": [
"method"
]
}
}
},
{
"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_dialog",
"description": "Respond to a native JavaScript dialog (alert / confirm / prompt / beforeunload) that is currently blocking the page.\n\n**Workflow:** call ``browser_snapshot`` first — if a dialog is open, it appears in the ``pending_dialogs`` field with ``id``, ``type``, and ``message``. Then call this tool with ``action='accept'`` or ``action='dismiss'``.\n\n**Prompt dialogs:** pass ``prompt_text`` to supply the response string. Ignored for alert/confirm/beforeunload.\n\n**Multiple dialogs:** if more than one dialog is queued (rare — happens when a second dialog fires while the first is still open), pass ``dialog_id`` from the snapshot to disambiguate.\n\n**Availability:** only present when a CDP-capable backend is attached — Browserbase sessions, local Chrome via ``/browser connect``, or ``browser.cdp_url`` in config.yaml. Not available on Camofox (REST-only) or the default Playwright local browser (CDP port is hidden).",
"parameters": {
"type": "object",
"properties": {
"action": {
"type": "string",
"enum": [
"accept",
"dismiss"
],
"description": "'accept' clicks OK / returns the prompt text. 'dismiss' clicks Cancel / returns null from prompt(). For ``beforeunload`` dialogs: 'accept' allows the navigation, 'dismiss' keeps the page."
},
"prompt_text": {
"type": "string",
"description": "Response string for a ``prompt()`` dialog. Ignored for other dialog types. Defaults to empty string."
},
"dialog_id": {
"type": "string",
"description": "Specific dialog to respond to, from ``browser_snapshot.pending_dialogs[].id``. Required only when multiple dialogs are queued."
}
},
"required": [
"action"
]
}
}
},
{
"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). 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), or platform:chat_id:thread_id for a specific destination. Examples: 'telegram:-1001234567890:17585', 'discord:#engineering', 'sms:+15551234567'. WARNING: 'platform:chat_id' without :thread_id loses topic targeting."
},
"skills": {
"type": "array",
"items": {
"type": "string"
},
"description": "Optional ordered list of skill names to load before executing the cron prompt. On update, pass an empty array to clear attached skills."
},
"model": {
"type": "object",
"description": "Optional per-job model override. If provider is omitted, the current main provider is pinned at creation time so the job stays stable.",
"properties": {
"provider": {
"type": "string",
"description": "Provider name (e.g. 'openrouter', 'anthropic'). Omit to use and pin the current provider."
},
"model": {
"type": "string",
"description": "Model name (e.g. 'anthropic/claude-sonnet-4', 'claude-sonnet-4')"
}
},
"required": [
"model"
]
},
"script": {
"type": "string",
"description": "Optional path to a Python script that runs before each cron job execution. Its stdout is injected into the prompt as context. Use for data collection and change detection. Relative paths resolve under ~/.hermes/scripts/. On update, pass empty string to clear."
},
"context_from": {
"type": "array",
"items": {
"type": "string"
},
"description": "Optional job ID or list of job IDs whose most recent completed output is injected into the prompt as context before each run. Use this to chain cron jobs: job A collects data, job B processes it. Each entry must be a valid job ID (from cronjob action='list'). Note: injects the most recent completed output — does not wait for upstream jobs running in the same tick. On update, pass an empty array to clear."
},
"enabled_toolsets": {
"type": "array",
"items": {
"type": "string"
},
"description": "Optional list of toolset names to restrict the job's agent to (e.g. [\"web\", \"terminal\", \"file\", \"delegation\"]). When set, only tools from these toolsets are loaded, significantly reducing input token overhead. When omitted, all default tools are loaded. Infer from the job's prompt — e.g. use \"web\" if it calls web_search, \"terminal\" if it runs scripts, \"file\" if it reads files, \"delegation\" if it calls delegate_task. On update, pass an empty array to clear."
},
"workdir": {
"type": "string",
"description": "Optional absolute path to run the job from. When set, AGENTS.md / CLAUDE.md / .cursorrules from that directory are injected into the system prompt, and the terminal/file/code_exec tools use it as their working directory — useful for running a job inside a specific project repo. Must be an absolute path that exists. When unset (default), preserves the original behaviour: no project context files, tools use the scheduler's cwd. On update, pass an empty string to clear. Jobs with workdir run sequentially (not parallel) to keep per-job directories isolated."
}
},
"required": [
"action"
]
}
}
},
{
"type": "function",
"function": {
"name": "delegate_task",
"description": "Spawn one or more subagents to work on tasks in isolated contexts. Each subagent gets its own conversation, terminal session, and toolset. Only the final summary is returned -- intermediate tool results never enter your context window.\n\nTWO MODES (one of 'goal' or 'tasks' is required):\n1. Single task: provide 'goal' (+ optional context, toolsets)\n2. Batch (parallel): provide 'tasks' array with up to delegation.max_concurrent_children items (default 3, configurable via config.yaml, no hard ceiling). All run concurrently and results are returned together. Nested delegation requires role='orchestrator' and delegation.max_spawn_depth >= 2.\n\nWHEN TO USE delegate_task:\n- Reasoning-heavy subtasks (debugging, code review, research synthesis)\n- Tasks that would flood your context with intermediate data\n- Parallel independent workstreams (research A and B simultaneously)\n\nWHEN NOT TO USE (use these instead):\n- Mechanical multi-step work with no reasoning needed -> use execute_code\n- Single tool call -> just call the tool directly\n- Tasks needing user interaction -> subagents cannot use clarify\n\nIMPORTANT:\n- Subagents have NO memory of your conversation. Pass all relevant info (file paths, error messages, constraints) via the 'context' field.\n- Leaf subagents (role='leaf', the default) CANNOT call: delegate_task, clarify, memory, send_message, execute_code.\n- Orchestrator subagents (role='orchestrator') retain delegate_task so they can spawn their own workers, but still cannot use clarify, memory, send_message, or execute_code. Orchestrators are bounded by delegation.max_spawn_depth (default 2) and can be disabled globally via delegation.orchestrator_enabled=false.\n- Each subagent gets its own terminal session (separate working directory and state).\n- Results are always returned as an array, one entry per task.",
"parameters": {
"type": "object",
"properties": {
"goal": {
"type": "string",
"description": "What the subagent should accomplish. Be specific and self-contained -- the subagent knows nothing about your conversation history."
},
"context": {
"type": "string",
"description": "Background information the subagent needs: file paths, error messages, project structure, constraints. The more specific you are, the better the subagent performs."
},
"toolsets": {
"type": "array",
"items": {
"type": "string"
},
"description": "Toolsets to enable for this subagent. Default: inherits your enabled toolsets. Available toolsets: 'browser', 'cronjob', 'discord', 'discord_admin', 'feishu_doc', 'feishu_drive', 'file', 'homeassistant', 'image_gen', 'search', 'session_search', 'skills', 'spotify', 'terminal', 'todo', 'tts', 'vision', 'web'. Common patterns: ['terminal', 'file'] for code work, ['web'] for research, ['browser'] for web interaction, ['terminal', 'file', 'web'] for full-stack tasks."
},
"tasks": {
"type": "array",
"items": {
"type": "object",
"properties": {
"goal": {
"type": "string",
"description": "Task goal"
},
"context": {
"type": "string",
"description": "Task-specific context"
},
"toolsets": {
"type": "array",
"items": {
"type": "string"
},
"description": "Toolsets for this specific task. Available: 'browser', 'cronjob', 'discord', 'discord_admin', 'feishu_doc', 'feishu_drive', 'file', 'homeassistant', 'image_gen', 'search', 'session_search', 'skills', 'spotify', 'terminal', 'todo', 'tts', 'vision', 'web'. Use 'web' for network access, 'terminal' for shell, 'browser' for web interaction."
},
"acp_command": {
"type": "string",
"description": "Per-task ACP command override (e.g. 'claude'). Overrides the top-level acp_command for this task only."
},
"acp_args": {
"type": "array",
"items": {
"type": "string"
},
"description": "Per-task ACP args override."
},
"role": {
"type": "string",
"enum": [
"leaf",
"orchestrator"
],
"description": "Per-task role override. See top-level 'role' for semantics."
}
},
"required": [
"goal"
]
},
"description": "Batch mode: tasks to run in parallel (limit configurable via delegation.max_concurrent_children, default 3). Each gets its own subagent with isolated context and terminal session. When provided, top-level goal/context/toolsets are ignored."
},
"role": {
"type": "string",
"enum": [
"leaf",
"orchestrator"
],
"description": "Role of the child agent. 'leaf' (default) = focused worker, cannot delegate further. 'orchestrator' = can use delegate_task to spawn its own workers. Requires delegation.max_spawn_depth >= 2 in config; ignored (treated as 'leaf') when the child would exceed max_spawn_depth or when delegation.orchestrator_enabled=false."
},
"acp_command": {
"type": "string",
"description": "Override ACP command for child agents (e.g. 'claude', 'copilot'). When set, children use ACP subprocess transport instead of inheriting the parent's transport. Enables spawning Claude Code (claude --acp --stdio) or other ACP-capable agents from any parent, including Discord/Telegram/CLI."
},
"acp_args": {
"type": "array",
"items": {
"type": "string"
},
"description": "Arguments for the ACP command (default: ['--acp', '--stdio']). Only used when acp_command is set. Example: ['--acp', '--stdio', '--model', 'claude-opus-4-6']"
}
}
}
}
},
{
"type": "function",
"function": {
"name": "execute_code",
"description": "Run a Python script that can call Hermes tools programmatically. Use this when you need 3+ tool calls with processing logic between them, need to filter/reduce large tool outputs before they enter your context, need conditional branching (if X then Y else Z), or need to loop (fetch N pages, process N files, retry on failure).\n\nUse normal tool calls instead when: single tool call with no processing, you need to see the full result and apply complex reasoning, or the task requires interactive user input.\n\nAvailable via `from hermes_tools import ...`:\n\n 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": "mcp_context7_get_prompt",
"description": "Get a prompt by name from MCP server 'context7'",
"parameters": {
"type": "object",
"properties": {
"name": {
"type": "string",
"description": "Name of the prompt to retrieve"
},
"arguments": {
"type": "object",
"description": "Optional arguments to pass to the prompt",
"properties": {},
"additionalProperties": true
}
},
"required": [
"name"
]
}
}
},
{
"type": "function",
"function": {
"name": "mcp_context7_list_prompts",
"description": "List available prompts from MCP server 'context7'",
"parameters": {
"type": "object",
"properties": {}
}
}
},
{
"type": "function",
"function": {
"name": "mcp_context7_list_resources",
"description": "List available resources from MCP server 'context7'",
"parameters": {
"type": "object",
"properties": {}
}
}
},
{
"type": "function",
"function": {
"name": "mcp_context7_query_docs",
"description": "Retrieves and queries up-to-date documentation and code examples from Context7 for any programming library or framework.\n\nYou must call 'Resolve Context7 Library ID' tool first to obtain the exact Context7-compatible library ID required to use this tool, UNLESS the user explicitly provides a library ID in the format '/org/project' or '/org/project/version' in their query.\n\nWorkflow: call first without researchMode. If that doesn't answer the question, retry with researchMode: true. Do not call each tool more than 3 times per question",
"parameters": {
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"libraryId": {
"type": "string",
"description": "Exact Context7-compatible library ID (e.g., '/mongodb/docs', '/vercel/next.js', '/supabase/supabase', '/vercel/next.js/v14.3.0-canary.87') retrieved from 'resolve-library-id' or directly from user query in the format '/org/project' or '/org/project/version'."
},
"query": {
"type": "string",
"description": "The question or task you need help with. Be specific and include relevant details. Good: 'How to set up authentication with JWT in Express.js' or 'React useEffect cleanup function examples'. Bad: 'auth' or 'hooks'. The query is sent to the Context7 API for processing. Do not include any sensitive or confidential information such as API keys, passwords, credentials, personal data, or proprietary code in your query."
},
"researchMode": {
"description": "Retry the query with deep research: spins up sandboxed agents that read the actual source repos and runs a live web search, then synthesizes a fresh answer. Set true on retry if you weren't satisfied with the first answer and want a more thorough one. Requires an API key — you can get one free at https://context7.com.",
"type": "boolean"
}
},
"required": [
"libraryId",
"query"
]
}
}
},
{
"type": "function",
"function": {
"name": "mcp_context7_read_resource",
"description": "Read a resource by URI from MCP server 'context7'",
"parameters": {
"type": "object",
"properties": {
"uri": {
"type": "string",
"description": "URI of the resource to read"
}
},
"required": [
"uri"
]
}
}
},
{
"type": "function",
"function": {
"name": "mcp_context7_resolve_library_id",
"description": "Resolves a package/product name to a Context7-compatible library ID and returns matching libraries.\n\nYou MUST call this function before 'Query Documentation' tool to obtain a valid Context7-compatible library ID UNLESS the user explicitly provides a library ID in the format '/org/project' or '/org/project/version' in their query.\n\nEach result includes:\n- Library ID: Context7-compatible identifier (format: /org/project)\n- Name: Library or package name\n- Description: Short summary\n- Code Snippets: Number of available code examples\n- Source Reputation: Authority indicator (High, Medium, Low, or Unknown)\n- Benchmark Score: Quality indicator (100 is the highest score)\n- Versions: List of versions if available. Use one of those versions if the user provides a version in their query. The format of the version is /org/project/version.\n\nFor best results, select libraries based on name match, source reputation, snippet coverage, benchmark score, and relevance to your use case.\n\nSelection Process:\n1. Analyze the query to understand what library/package the user is looking for\n2. Return the most relevant match based on:\n- Name similarity to the query (exact matches prioritized)\n- Description relevance to the query's intent\n- Documentation coverage (prioritize libraries with higher Code Snippet counts)\n- Source reputation (consider libraries with High or Medium reputation more authoritative)\n- Benchmark Score: Quality indicator (100 is the highest score)\n\nResponse Format:\n- Return the selected library ID in a clearly marked section\n- Provide a brief explanation for why this library was chosen\n- If multiple good matches exist, acknowledge this but proceed with the most relevant one\n- If no good matches exist, clearly state this and suggest query refinements\n\nFor ambiguous queries, request clarification before proceeding with a best-guess match.\n\nIMPORTANT: Do not call this tool more than 3 times per question. If you cannot find what you need after 3 calls, use the best result you have.",
"parameters": {
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "The question or task you need help with. This is used to rank library results by relevance to what the user is trying to accomplish. The query is sent to the Context7 API for processing. Do not include any sensitive or confidential information such as API keys, passwords, credentials, personal data, or proprietary code in your query."
},
"libraryName": {
"type": "string",
"description": "Library name to search for and retrieve a Context7-compatible library ID. Use the official library name with proper punctuation — e.g., 'Next.js' instead of 'nextjs', 'Customer.io' instead of 'customerio', 'Three.js' instead of 'threejs'."
}
},
"required": [
"query",
"libraryName"
]
}
}
},
{
"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": "mixture_of_agents",
"description": "Route a hard problem through multiple frontier LLMs collaboratively. Makes 5 API calls (4 reference models + 1 aggregator) with maximum reasoning effort — use sparingly for genuinely difficult problems. Best for: complex math, advanced algorithms, multi-step analytical reasoning, problems benefiting from diverse perspectives.",
"parameters": {
"type": "object",
"properties": {
"user_prompt": {
"type": "string",
"description": "The complex query or problem to solve using multiple AI models. Should be a challenging problem that benefits from diverse perspectives and collaborative reasoning."
}
},
"required": [
"user_prompt"
]
}
}
},
{
"type": "function",
"function": {
"name": "patch",
"description": "Targeted find-and-replace edits in files. Use this instead of sed/awk in terminal. Uses fuzzy matching (9 strategies) so minor whitespace/indentation differences won't break it. Returns a unified diff. Auto-runs syntax checks after editing.\n\nReplace mode (default): find a unique string and replace it.\nPatch mode: apply V4A multi-file patches for bulk changes.",
"parameters": {
"type": "object",
"properties": {
"mode": {
"type": "string",
"enum": [
"replace",
"patch"
],
"description": "Edit mode: 'replace' for targeted find-and-replace, 'patch' for V4A multi-file patches",
"default": "replace"
},
"path": {
"type": "string",
"description": "File path to edit (required for 'replace' mode)"
},
"old_string": {
"type": "string",
"description": "Text to find in the file (required for 'replace' mode). Must be unique in the file unless replace_all=true. Include enough surrounding context to ensure uniqueness."
},
"new_string": {
"type": "string",
"description": "Replacement text (required for 'replace' mode). Can be empty string to delete the matched text."
},
"replace_all": {
"type": "boolean",
"description": "Replace all occurrences instead of requiring a unique match (default: false)",
"default": false
},
"patch": {
"type": "string",
"description": "V4A format patch content (required for 'patch' mode). Format:\n*** Begin Patch\n*** Update File: path/to/file\n@@ context hint @@\n context line\n-removed line\n+added line\n*** End Patch"
}
},
"required": [
"mode"
]
}
}
},
{
"type": "function",
"function": {
"name": "process",
"description": "Manage background processes started with terminal(background=true). Actions: 'list' (show all), 'poll' (check status + new output), 'log' (full output with pagination), 'wait' (block until done or timeout), 'kill' (terminate), 'write' (send raw stdin data without newline), 'submit' (send data + Enter, for answering prompts), 'close' (close stdin/send EOF).",
"parameters": {
"type": "object",
"properties": {
"action": {
"type": "string",
"enum": [
"list",
"poll",
"log",
"wait",
"kill",
"write",
"submit",
"close"
],
"description": "Action to perform on background processes"
},
"session_id": {
"type": "string",
"description": "Process session ID (from terminal background output). Required for all actions except 'list'."
},
"data": {
"type": "string",
"description": "Text to send to process stdin (for 'write' and 'submit' actions)"
},
"timeout": {
"type": "integer",
"description": "Max seconds to block for 'wait' action. Returns partial output on timeout.",
"minimum": 1
},
"offset": {
"type": "integer",
"description": "Line offset for 'log' action (default: last 200 lines)"
},
"limit": {
"type": "integer",
"description": "Max lines to return for 'log' action",
"minimum": 1
}
},
"required": [
"action"
]
}
}
},
{
"type": "function",
"function": {
"name": "read_file",
"description": "Read a text file with line numbers and pagination. Use this instead of cat/head/tail in terminal. Output format: 'LINE_NUM|CONTENT'. Suggests similar filenames if not found. Use offset and limit for large files. Reads exceeding ~100K characters are rejected; use offset and limit to read specific sections of large files. NOTE: Cannot read images or binary files — use vision_analyze for images.",
"parameters": {
"type": "object",
"properties": {
"path": {
"type": "string",
"description": "Path to the file to read (absolute, relative, or ~/path)"
},
"offset": {
"type": "integer",
"description": "Line number to start reading from (1-indexed, default: 1)",
"default": 1,
"minimum": 1
},
"limit": {
"type": "integer",
"description": "Maximum number of lines to read (default: 500, max: 2000)",
"default": 500,
"maximum": 2000
}
},
"required": [
"path"
]
}
}
},
{
"type": "function",
"function": {
"name": "search_files",
"description": "Search file contents or find files by name. Use this instead of grep/rg/find/ls in terminal. Ripgrep-backed, faster than shell equivalents.\n\nContent search (target='content'): Regex search inside files. Output modes: full matches with line numbers, file paths only, or match counts.\n\nFile search (target='files'): Find files by glob pattern (e.g., '*.py', '*config*'). Also use this instead of ls — results sorted by modification time.",
"parameters": {
"type": "object",
"properties": {
"pattern": {
"type": "string",
"description": "Regex pattern for content search, or glob pattern (e.g., '*.py') for file search"
},
"target": {
"type": "string",
"enum": [
"content",
"files"
],
"description": "'content' searches inside file contents, 'files' searches for files by name",
"default": "content"
},
"path": {
"type": "string",
"description": "Directory or file to search in (default: current working directory)",
"default": "."
},
"file_glob": {
"type": "string",
"description": "Filter files by pattern in grep mode (e.g., '*.py' to only search Python files)"
},
"limit": {
"type": "integer",
"description": "Maximum number of results to return (default: 50)",
"default": 50
},
"offset": {
"type": "integer",
"description": "Skip first N results for pagination (default: 0)",
"default": 0
},
"output_mode": {
"type": "string",
"enum": [
"content",
"files_only",
"count"
],
"description": "Output format for grep mode: 'content' shows matching lines with line numbers, 'files_only' lists file paths, 'count' shows match counts per file",
"default": "content"
},
"context": {
"type": "integer",
"description": "Number of context lines before and after each match (grep mode only)",
"default": 0
}
},
"required": [
"pattern"
]
}
}
},
{
"type": "function",
"function": {
"name": "session_search",
"description": "Search your long-term memory of past conversations, or browse recent sessions. This is your recall -- every past session is searchable, and this tool summarizes what happened.\n\nTWO MODES:\n1. Recent sessions (no query): Call with no arguments to see what was worked on recently. Returns titles, previews, and timestamps. Zero LLM cost, instant. Start here when the user asks what were we working on or what did we do recently.\n2. Keyword search (with query): Search for specific topics across all past sessions. Returns LLM-generated summaries of matching sessions.\n\nUSE THIS PROACTIVELY when:\n- The user says 'we did this before', 'remember when', 'last time', 'as I mentioned'\n- The user asks about a topic you worked on before but don't have in current context\n- The user references a project, person, or concept that seems familiar but isn't in memory\n- You want to check if you've solved a similar problem before\n- The user asks 'what did we do about X?' or 'how did we fix Y?'\n\nDon't hesitate to search when it is actually cross-session -- it's fast and cheap. Better to search and confirm than to guess or ask the user to repeat themselves.\n\nSearch syntax: keywords joined with OR for broad recall (elevenlabs OR baseten OR funding), phrases for exact match (\"docker networking\"), boolean (python NOT java), prefix (deploy*). IMPORTANT: Use OR between keywords for best results — FTS5 defaults to AND which misses sessions that only mention some terms. If a broad OR query returns nothing, try individual keyword searches in parallel. Returns summaries of the top matching sessions.",
"parameters": {
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Search query — keywords, phrases, or boolean expressions to find in past sessions. Omit this parameter entirely to browse recent sessions instead (returns titles, previews, timestamps with no LLM cost)."
},
"role_filter": {
"type": "string",
"description": "Optional: only search messages from specific roles (comma-separated). E.g. 'user,assistant' to skip tool outputs."
},
"limit": {
"type": "integer",
"description": "Max sessions to summarize (default: 3, max: 5).",
"default": 3
}
}
}
}
},
{
"type": "function",
"function": {
"name": "skill_manage",
"description": "Manage skills (create, update, delete). Skills are your procedural memory — reusable approaches for recurring task types. New skills go to ~/.hermes/skills/; existing skills can be modified wherever they live.\n\nActions: create (full SKILL.md + optional category), patch (old_string/new_string — preferred for fixes), edit (full SKILL.md rewrite — major overhauls only), delete, write_file, remove_file.\n\nCreate when: complex task succeeded (5+ calls), errors overcome, user-corrected approach worked, non-trivial workflow discovered, or user asks you to remember a procedure.\nUpdate when: instructions stale/wrong, OS-specific failures, missing steps or pitfalls found during use. If you used a skill and hit issues not covered by it, patch it immediately.\n\nAfter difficult/iterative tasks, offer to save as a skill. Skip for simple one-offs. Confirm with user before creating/deleting.\n\nGood skills: trigger conditions, numbered steps with exact commands, pitfalls section, verification steps. Use skill_view() to see format examples.",
"parameters": {
"type": "object",
"properties": {
"action": {
"type": "string",
"enum": [
"create",
"patch",
"edit",
"delete",
"write_file",
"remove_file"
],
"description": "The action to perform."
},
"name": {
"type": "string",
"description": "Skill name (lowercase, hyphens/underscores, max 64 chars). Must match an existing skill for patch/edit/delete/write_file/remove_file."
},
"content": {
"type": "string",
"description": "Full SKILL.md content (YAML frontmatter + markdown body). Required for 'create' and 'edit'. For 'edit', read the skill first with skill_view() and provide the complete updated text."
},
"old_string": {
"type": "string",
"description": "Text to find in the file (required for 'patch'). Must be unique unless replace_all=true. Include enough surrounding context to ensure uniqueness."
},
"new_string": {
"type": "string",
"description": "Replacement text (required for 'patch'). Can be empty string to delete the matched text."
},
"replace_all": {
"type": "boolean",
"description": "For 'patch': replace all occurrences instead of requiring a unique match (default: false)."
},
"category": {
"type": "string",
"description": "Optional category/domain for organizing the skill (e.g., 'devops', 'data-science', 'mlops'). Creates a subdirectory grouping. Only used with 'create'."
},
"file_path": {
"type": "string",
"description": "Path to a supporting file within the skill directory. For 'write_file'/'remove_file': required, must be under references/, templates/, scripts/, or assets/. For 'patch': optional, defaults to SKILL.md if omitted."
},
"file_content": {
"type": "string",
"description": "Content for the file. Required for 'write_file'."
}
},
"required": [
"action",
"name"
]
}
}
},
{
"type": "function",
"function": {
"name": "skill_view",
"description": "Skills allow for loading information about specific tasks and workflows, as well as scripts and templates. Load a skill's full content or access its linked files (references, templates, scripts). First call returns SKILL.md content plus a 'linked_files' dict showing available references/templates/scripts. To access those, call again with file_path parameter.",
"parameters": {
"type": "object",
"properties": {
"name": {
"type": "string",
"description": "The skill name (use skills_list to see available skills). For plugin-provided skills, use the qualified form 'plugin:skill' (e.g. 'superpowers:writing-plans')."
},
"file_path": {
"type": "string",
"description": "OPTIONAL: Path to a linked file within the skill (e.g., 'references/api.md', 'templates/config.yaml', 'scripts/validate.py'). Omit to get the main SKILL.md content."
}
},
"required": [
"name"
]
}
}
},
{
"type": "function",
"function": {
"name": "skills_list",
"description": "List available skills (name + description). Use skill_view(name) to load full content.",
"parameters": {
"type": "object",
"properties": {
"category": {
"type": "string",
"description": "Optional category filter to narrow results"
}
}
}
}
},
{
"type": "function",
"function": {
"name": "terminal",
"description": "Execute shell commands on a Linux environment. Filesystem usually persists between calls.\n\nDo NOT use cat/head/tail to read files — use read_file instead.\nDo NOT use grep/rg/find to search — use search_files instead.\nDo NOT use ls to list directories — use search_files(target='files') instead.\nDo NOT use sed/awk to edit files — use patch instead.\nDo NOT use echo/cat heredoc to create files — use write_file instead.\nReserve terminal for: builds, installs, git, processes, scripts, network, package managers, and anything that needs a shell.\n\nForeground (default): Commands return INSTANTLY when done, even if the timeout is high. Set timeout=300 for long builds/scripts — you'll still get the result in seconds if it's fast. Prefer foreground for short commands.\nBackground: Set background=true to get a session_id. Two patterns:\n (1) Long-lived processes that never exit (servers, watchers).\n (2) Long-running tasks with notify_on_complete=true — you can keep working on other things and the system auto-notifies you when the task finishes. Great for test suites, builds, deployments, or anything that takes more than a minute.\nFor servers/watchers, do NOT use shell-level background wrappers (nohup/disown/setsid/trailing '&') in foreground mode. Use background=true so Hermes can track lifecycle and output.\nAfter starting a server, verify readiness with a health check or log signal, then run tests in a separate terminal() call. Avoid blind sleep loops.\nUse process(action=\"poll\") for progress checks, process(action=\"wait\") to block until done.\nWorking directory: Use 'workdir' for per-command cwd.\nPTY mode: Set pty=true for interactive CLI tools (Codex, Claude Code, Python REPL).\n\nDo NOT use vim/nano/interactive tools without pty=true — they hang without a pseudo-terminal. Pipe git output to cat if it might page.\n",
"parameters": {
"type": "object",
"properties": {
"command": {
"type": "string",
"description": "The command to execute on the VM"
},
"background": {
"type": "boolean",
"description": "Run the command in the background. Two patterns: (1) Long-lived processes that never exit (servers, watchers). (2) Long-running tasks paired with notify_on_complete=true — you can keep working and get notified when the task finishes. For short commands, prefer foreground with a generous timeout instead.",
"default": false
},
"timeout": {
"type": "integer",
"description": "Max seconds to wait (default: 180, foreground max: 600). Returns INSTANTLY when command finishes — set high for long tasks, you won't wait unnecessarily. Foreground timeout above 600s is rejected; use background=true for longer commands.",
"minimum": 1
},
"workdir": {
"type": "string",
"description": "Working directory for this command (absolute path). Defaults to the session working directory."
},
"pty": {
"type": "boolean",
"description": "Run in pseudo-terminal (PTY) mode for interactive CLI tools like Codex, Claude Code, or Python REPL. Only works with local and SSH backends. Default: false.",
"default": false
},
"notify_on_complete": {
"type": "boolean",
"description": "When true (and background=true), you'll be automatically notified exactly once when the process finishes. **This is the right choice for almost every long-running task** — tests, builds, deployments, multi-item batch jobs, anything that takes over a minute and has a defined end. Use this and keep working on other things; the system notifies you on exit. MUTUALLY EXCLUSIVE with watch_patterns — when both are set, watch_patterns is dropped.",
"default": false
},
"watch_patterns": {
"type": "array",
"items": {
"type": "string"
},
"description": "Strings to watch for in background process output. HARD RATE LIMIT: at most 1 notification per 15 seconds per process — matches arriving inside the cooldown are dropped. After 3 consecutive 15-second windows with dropped matches, watch_patterns is automatically disabled for that process and promoted to notify_on_complete behavior (one notification on exit, no more mid-process spam). USE ONLY for truly rare, one-shot mid-process signals on LONG-LIVED processes that will never exit on their own — e.g. ['Application startup complete'] on a server so you know when to hit its endpoint, or ['migration done'] on a daemon. DO NOT use for: (1) end-of-run markers like 'DONE'/'PASS' — use notify_on_complete instead; (2) error patterns like 'ERROR'/'Traceback' in loops or multi-item batch jobs — they fire on every iteration and you'll hit the strike limit fast; (3) anything you'd ever combine with notify_on_complete. When in doubt, choose notify_on_complete. MUTUALLY EXCLUSIVE with notify_on_complete — set one, not both."
}
},
"required": [
"command"
]
}
}
},
{
"type": "function",
"function": {
"name": "text_to_speech",
"description": "Convert text to speech audio. Returns a MEDIA: path that the platform delivers as a voice message. On Telegram it plays as a voice bubble, on Discord/WhatsApp as an audio attachment. In CLI mode, saves to ~/voice-memos/. Voice and provider are user-configured, not model-selected.",
"parameters": {
"type": "object",
"properties": {
"text": {
"type": "string",
"description": "The text to convert to speech. Provider-specific character caps apply and are enforced automatically (OpenAI 4096, xAI 15000, MiniMax 10000, ElevenLabs 5k-40k depending on model); over-long input is truncated."
},
"output_path": {
"type": "string",
"description": "Optional custom file path to save the audio. Defaults to ~/.hermes/audio_cache/.mp3"
}
},
"required": [
"text"
]
}
}
},
{
"type": "function",
"function": {
"name": "todo",
"description": "Manage your task list for the current session. Use for complex tasks with 3+ steps or when the user provides multiple tasks. Call with no parameters to read the current list.\n\nWriting:\n- Provide 'todos' array to create/update items\n- merge=false (default): replace the entire list with a fresh plan\n- merge=true: update existing items by id, add any new ones\n\nEach item: {id: string, content: string, status: pending|in_progress|completed|cancelled}\nList order is priority. Only ONE item in_progress at a time.\nMark items completed immediately when done. If something fails, cancel it and add a revised item.\n\nAlways returns the full current list.",
"parameters": {
"type": "object",
"properties": {
"todos": {
"type": "array",
"description": "Task items to write. Omit to read current list.",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "Unique item identifier"
},
"content": {
"type": "string",
"description": "Task description"
},
"status": {
"type": "string",
"enum": [
"pending",
"in_progress",
"completed",
"cancelled"
],
"description": "Current status"
}
},
"required": [
"id",
"content",
"status"
]
}
},
"merge": {
"type": "boolean",
"description": "true: update existing items by id, add new ones. false (default): replace the entire list.",
"default": false
}
}
}
}
},
{
"type": "function",
"function": {
"name": "vision_analyze",
"description": "Analyze images using AI vision. Provides a comprehensive description and answers a specific question about the image content.",
"parameters": {
"type": "object",
"properties": {
"image_url": {
"type": "string",
"description": "Image URL (http/https) or local file path to analyze."
},
"question": {
"type": "string",
"description": "Your specific question or request about the image to resolve. The AI will automatically provide a complete image description AND answer your specific question."
}
},
"required": [
"image_url",
"question"
]
}
}
},
{
"type": "function",
"function": {
"name": "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 on any topic. Returns up to 5 relevant results with titles, URLs, and descriptions.",
"parameters": {
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "The search query to look up on the web"
}
},
"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.",
"parameters": {
"type": "object",
"properties": {
"path": {
"type": "string",
"description": "Path to the file to write (will be created if it doesn't exist, overwritten if it does)"
},
"content": {
"type": "string",
"description": "Complete content to write to the file"
}
},
"required": [
"path",
"content"
]
}
}
},
{
"type": "function",
"function": {
"name": "honcho_profile",
"description": "Retrieve or update a peer card from Honcho — a curated list of key facts about that peer (name, role, preferences, communication style, patterns). Pass `card` to update; omit `card` to read.",
"parameters": {
"type": "object",
"properties": {
"peer": {
"type": "string",
"description": "Peer to query. Built-in aliases: 'user' (default), 'ai'. Or pass any peer ID from this workspace."
},
"card": {
"type": "array",
"items": {
"type": "string"
},
"description": "New peer card as a list of fact strings. Omit to read the current card."
}
},
"required": []
}
}
},
{
"type": "function",
"function": {
"name": "honcho_search",
"description": "Semantic search over Honcho's stored context about a peer. Returns raw excerpts ranked by relevance — no LLM synthesis. Cheaper and faster than honcho_reasoning. Good when you want to find specific past facts and reason over them yourself.",
"parameters": {
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "What to search for in Honcho's memory."
},
"max_tokens": {
"type": "integer",
"description": "Token budget for returned context (default 800, max 2000)."
},
"peer": {
"type": "string",
"description": "Peer to query. Built-in aliases: 'user' (default), 'ai'. Or pass any peer ID from this workspace."
}
},
"required": [
"query"
]
}
}
},
{
"type": "function",
"function": {
"name": "honcho_reasoning",
"description": "Ask Honcho a natural language question and get a synthesized answer. Uses Honcho's LLM (dialectic reasoning) — higher cost than honcho_profile or honcho_search. Can query about any peer via alias or explicit peer ID. Pass reasoning_level to control depth: minimal (fast/cheap), low (default), medium, high, max (deep/expensive). Omit for configured default.",
"parameters": {
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "A natural language question."
},
"reasoning_level": {
"type": "string",
"description": "Override the default reasoning depth. Omit to use the configured default (typically low). Guide:\n- minimal: quick factual lookups (name, role, simple preference)\n- low: straightforward questions with clear answers\n- medium: multi-aspect questions requiring synthesis across observations\n- high: complex behavioral patterns, contradictions, deep analysis\n- max: thorough audit-level analysis, leave no stone unturned",
"enum": [
"minimal",
"low",
"medium",
"high",
"max"
]
},
"peer": {
"type": "string",
"description": "Peer to query. Built-in aliases: 'user' (default), 'ai'. Or pass any peer ID from this workspace."
}
},
"required": [
"query"
]
}
}
},
{
"type": "function",
"function": {
"name": "honcho_context",
"description": "Retrieve full session context from Honcho — summary, peer representation, peer card, and recent messages. No LLM synthesis. Cheaper than honcho_reasoning. Use this to see what Honcho knows about the current conversation and the specified peer.",
"parameters": {
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Optional focus query to filter context. Omit for full session context snapshot."
},
"peer": {
"type": "string",
"description": "Peer to query. Built-in aliases: 'user' (default), 'ai'. Or pass any peer ID from this workspace."
}
},
"required": []
}
}
},
{
"type": "function",
"function": {
"name": "honcho_conclude",
"description": "Write or delete a conclusion about a peer in Honcho's memory. Conclusions are persistent facts that build a peer's profile. You MUST pass exactly one of: `conclusion` (to create) or `delete_id` (to delete). Passing neither is an error. Deletion is only for PII removal — Honcho self-heals incorrect conclusions over time.",
"parameters": {
"type": "object",
"properties": {
"conclusion": {
"type": "string",
"description": "A factual statement to persist. Provide this when creating a conclusion. Do not send it together with delete_id."
},
"delete_id": {
"type": "string",
"description": "Conclusion ID to delete for PII removal. Provide this when deleting a conclusion. Do not send it together with conclusion."
},
"peer": {
"type": "string",
"description": "Peer to query. Built-in aliases: 'user' (default), 'ai'. Or pass any peer ID from this workspace."
}
},
"required": []
}
}
}
],
"max_tokens": 32000,
"reasoning_effort": "medium",
"extra_body": {
"thinking": {
"type": "enabled"
}
}
}
},
"error": {
"type": "rate_limit_reached_error",
"message": "Error code: 429 - {'error': {'message': 'Your account org-987fd60f843f40f79c003a0ab4315a31 / proj-078e4e61d94b4fc18b893e9bd0c293e5 request reached organization TPD rate limit, current: 1525268, limit: 1500000', 'type': 'rate_limit_reached_error'}}",
"status_code": 429,
"body": {
"message": "Your account org-987fd60f843f40f79c003a0ab4315a31 / proj-078e4e61d94b4fc18b893e9bd0c293e5 request reached organization TPD rate limit, current: 1525268, limit: 1500000",
"type": "rate_limit_reached_error"
},
"response_status": 429,
"response_text": "{\"error\":{\"message\":\"Your account org-987fd60f843f40f79c003a0ab4315a31 / proj-078e4e61d94b4fc18b893e9bd0c293e5 \\u003cak-f99m5j4pffni11fr8t31\\u003e request reached organization TPD rate limit, current: 1525268, limit: 1500000\",\"type\":\"rate_limit_reached_error\"}}"
}
}