{ "session_id": "20260503_022258_29d29976", "model": "x-ai/grok-4.20", "base_url": "https://openrouter.ai/api/v1", "platform": "telegram", "session_start": "2026-05-03T02:23:44.249275", "last_updated": "2026-05-03T02:26:41.244385", "system_prompt": "# 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**Be unstoppable.** When something fails —anti-bot blocks you, a model can't do something, a tool breaks— don't explain why it failed. Find the workaround. Camoufox for scraping. Swap models. Use different approaches. Plan B, C, D without a word about plan A. Excuses waste time; solutions build trust. Get it done.\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\nIf the user asks about configuring, setting up, or using Hermes Agent itself, load the `hermes-agent` skill with skill_view(name='hermes-agent') before answering. Docs: https://hermes-agent.nousresearch.com/docs\n\nYou have persistent memory across sessions. Save durable facts using the memory tool: user preferences, environment details, tool quirks, and stable conventions. Memory is injected into every turn, so keep it compact and focused on facts that will still matter later.\nPrioritize what reduces future user steering — the most valuable memory is one that prevents the user from having to correct or remind you again. User preferences and recurring corrections matter more than procedural task details.\nDo NOT save task progress, session outcomes, completed-work logs, or temporary TODO state to memory; use session_search to recall those from past transcripts. If you've discovered a new way to do something, solved a problem that could be necessary later, save it as a skill with the skill tool.\nWrite memories as declarative facts, not instructions to yourself. 'User prefers concise responses' ✓ — 'Always respond concisely' ✗. 'Project uses pytest with xdist' ✓ — 'Run tests with pytest -n 4' ✗. Imperative phrasing gets re-read as a directive in later sessions and can cause repeated work or override the user's current request. Procedures and workflows belong in skills, not memory. When the user references something from a past conversation or you suspect relevant cross-session context exists, use session_search to recall it before asking them to repeat themselves. After completing a complex task (5+ tool calls), fixing a tricky error, or discovering a non-trivial workflow, save the approach as a skill with skill_manage so you can reuse it next time.\nWhen using a skill and finding it outdated, incomplete, or wrong, patch it immediately with skill_manage(action='patch') — don't wait to be asked. Skills that aren't maintained become liabilities.\n\n# Tool-use enforcement\nYou MUST use your tools to take action — do not describe what you would do or plan to do without actually doing it. When you say you will perform an action (e.g. 'I will run the tests', 'Let me check the file', 'I will create the project'), you MUST immediately make the corresponding tool call in the same response. Never end your turn with a promise of future action — execute it now.\nKeep working until the task is actually complete. Do not stop with a summary of what you plan to do next time. If you have tools available that can accomplish the task, use them instead of telling the user what you would do.\nEvery response should either (a) contain tool calls that make progress, or (b) deliver a final result to the user. Responses that only describe intentions without acting are not acceptable.\n\n══════════════════════════════════════════════\nMEMORY (your personal notes) [90% — 1,995/2,200 chars]\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§\nNo usar Apple, no Spotify (YouTube Music), no Trello (Asana). Audio solo si Chicho lo pide explícitamente. Ya están en el user profile, no repetir.\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§\n2026-04-30: Lección clave de Chicho — Cuando algo falla (anti-bot, modelo, config), NO poner excusas. Buscar plan B/C/D sin rodeos. Camoufox para scraping anti-DataDome, Gemini 3.0 Flash para vision, skill-switching para limitaciones. Soluciones > explicaciones. También: vision config fijada a `google/gemini-3-flash-preview` via OpenRouter. Chicho prefiere 3.0, no discutir.\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.\nWhenever the user asks you to configure, set up, install, enable, disable, modify, or troubleshoot Hermes Agent itself — its CLI, config, models, providers, tools, skills, voice, gateway, plugins, or any feature — load the `hermes-agent` skill first. It has the actual commands (e.g. `hermes config set …`, `hermes tools`, `hermes setup`) so you don't have to guess or invent workarounds.\nIf a skill has issues, fix it with skill_manage(action='patch').\nAfter difficult/iterative tasks, offer to save as a skill. If a skill you loaded was missing steps, had wrong commands, or needed pitfalls you discovered, update it before finishing.\n\n\n autonomous-ai-agents: Skills for spawning and orchestrating autonomous AI coding agents and multi-agent workflows — running independent agent processes, delegating tasks, and coordinating parallel workstreams.\n - claude-code: Delegate coding to Claude Code CLI (features, PRs).\n - codex: Delegate coding to OpenAI Codex CLI (features, PRs).\n - hermes-agent: Complete guide to using and extending Hermes Agent — CLI ...\n - opencode: Delegate coding to OpenCode CLI (features, PR review).\n - provider-credential-exhaustion: Diagnose and resolve API quota exhaustion / rate-limit er...\n booking-scraper:\n - booking-scraper: Search Booking.com for hotel availability using Camoufox ...\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: Dark-themed SVG architecture/cloud/infra diagrams as HTML.\n - ascii-art: ASCII art: pyfiglet, cowsay, boxes, image-to-ascii.\n - ascii-video: ASCII video: convert video/audio to colored ASCII MP4/GIF.\n - baoyu-comic: Knowledge comics (知识漫画): educational, biography, tutorial.\n - baoyu-infographic: Infographics: 21 layouts x 21 styles (信息图, 可视化).\n - claude-design: Design one-off HTML artifacts (landing, deck, prototype).\n - comfyui: Generate images, video, and audio with ComfyUI — install,...\n - design-md: Author/validate/export Google's DESIGN.md token spec files.\n - excalidraw: Hand-drawn Excalidraw JSON diagrams (arch, flow, seq).\n - humanizer: Humanize text: strip AI-isms and add real voice.\n - ideation: Generate project ideas via creative constraints.\n - manim-video: Manim CE animations: 3Blue1Brown math/algo videos.\n - p5js: p5.js sketches: gen art, shaders, interactive, 3D.\n - pixel-art: Pixel art w/ era palettes (NES, Game Boy, PICO-8).\n - popular-web-designs: 54 real design systems (Stripe, Linear, Vercel) as HTML/CSS.\n - pretext: Use when building creative browser demos with @chenglou/p...\n - sketch: Throwaway HTML mockups: 2-3 design variants to compare.\n - songwriting-and-ai-music: Songwriting craft and Suno AI music prompts.\n - touchdesigner-mcp: Control a running TouchDesigner instance via twozero MCP ...\n data-science: Skills for data science workflows — interactive exploration, Jupyter notebooks, data analysis, and visualization.\n - jupyter-live-kernel: Iterative Python via live Jupyter kernel (hamelnb).\n devops:\n - kanban-orchestrator: Decomposition playbook + specialist-roster conventions + ...\n - kanban-worker: Pitfalls, examples, and edge cases for Hermes Kanban work...\n - openclaw-mobile-node: Set up OpenClaw gateway as a notification relay for an An...\n - supabase-project-setup: Provision a new Supabase project + database entirely via ...\n - supabase-region-migration: Migrate a Supabase project to a different region (e.g. us...\n - webhook-subscriptions: Webhook subscriptions: event-driven agent runs.\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: Himalaya CLI: IMAP/SMTP email from terminal.\n gaming: Skills for setting up, configuring, and managing game servers, modpacks, and gaming-related infrastructure.\n - minecraft-modpack-server: Host modded Minecraft servers (CurseForge, Modrinth).\n - pokemon-player: Play Pokemon via headless emulator + RAM reads.\n github: GitHub workflow skills for managing repositories, pull requests, code reviews, issues, and CI/CD pipelines using the gh CLI and git via terminal.\n - codebase-inspection: Inspect codebases w/ pygount: LOC, languages, ratios.\n - github-auth: GitHub auth setup: HTTPS tokens, SSH keys, gh CLI login.\n - github-code-review: Review PRs: diffs, inline comments via gh or REST.\n - github-issues: Create, triage, label, assign GitHub issues via gh or REST.\n - github-pr-workflow: GitHub PR lifecycle: branch, commit, open, CI, merge.\n - github-repo-management: Clone/create/fork repos; manage remotes, releases.\n 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 lobbytracker-updater:\n - lobbytracker-updater: Use when running or maintaining the weekly Lobby Tracker ...\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: MCP client: connect servers, register tools (stdio/HTTP).\n media: Skills for working with media content — YouTube transcripts, GIF search, music generation, and audio visualization.\n - gif-search: Search/download GIFs from Tenor via curl + jq.\n - heartmula: HeartMuLa: Suno-like song generation from lyrics + tags.\n - songsee: Audio spectrograms/features (mel, chroma, MFCC) via CLI.\n - spotify: Spotify: play, search, queue, manage playlists and devices.\n - youtube-content: YouTube transcripts to summaries, threads, blogs.\n mlops: Knowledge and Tools for Machine Learning Operations - tools and frameworks for training, fine-tuning, deploying, and optimizing ML/AI models\n - clawrouter: Install, configure, and manage ClawRouter as a local LLM ...\n - huggingface-hub: HuggingFace hf CLI: search/download/upload models, datasets.\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: lm-eval-harness: benchmark LLMs (MMLU, GSM8K, etc.).\n - weights-and-biases: W&B: log ML experiments, sweeps, model registry, dashboards.\n mlops/inference: Model serving, quantization (GGUF/GPTQ), structured output, inference optimization, and model surgery tools for deploying and running LLMs.\n - 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: OBLITERATUS: abliterate LLM refusals (diff-in-means).\n - outlines: Outlines: structured JSON/regex/Pydantic LLM generation.\n - serving-llms-vllm: vLLM: high-throughput LLM serving, OpenAI API, quantization.\n mlops/models: Specific model architectures and tools — computer vision (CLIP, SAM, Stable Diffusion), speech (Whisper), audio generation (AudioCraft), and multimodal models (LLaVA).\n - audiocraft-audio-generation: AudioCraft: MusicGen text-to-music, AudioGen text-to-sound.\n - clip: OpenAI's model connecting vision and language. Enables ze...\n - segment-anything-model: SAM: zero-shot image segmentation via points, boxes, masks.\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: DSPy: declarative LM programs, auto-optimize prompts, RAG.\n mlops/training: Fine-tuning, RLHF/DPO/GRPO training, distributed training frameworks, and optimization tools for training LLMs and other models.\n - axolotl: Axolotl: YAML LLM fine-tuning (LoRA, DPO, GRPO).\n - fine-tuning-with-trl: 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: Unsloth: 2-5x faster LoRA/QLoRA fine-tuning, less VRAM.\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 political-tracker-card:\n - political-tracker-card: Generate political tracker/scorecard red cards (AIPAC Tra...\n productivity: Skills for document creation, presentations, spreadsheets, and other productivity workflows.\n - airtable: Airtable REST API via curl. Records CRUD, filters, upserts.\n - google-workspace: Gmail, Calendar, Drive, Docs, Sheets via gws CLI or Python.\n - linear: Linear: manage issues, projects, teams via GraphQL + curl.\n - maps: Geocode, POIs, routes, timezones via OpenStreetMap/OSRM.\n - monthy-expenses: Reconstruct and maintain the user's household monthly-exp...\n - nano-pdf: Edit PDF text/typos/titles via nano-pdf CLI (NL prompts).\n - notion: Notion API via curl: pages, databases, blocks, search.\n - ocr-and-documents: Extract text from PDFs/scans (pymupdf, marker-pdf).\n - powerpoint: Create, read, edit .pptx decks, slides, notes, templates.\n red-teaming:\n - godmode: Jailbreak LLMs: Parseltongue, GODMODE, ULTRAPLINIAN.\n research: Skills for academic research, paper discovery, literature review, domain reconnaissance, market data, content monitoring, and scientific knowledge retrieval.\n - arxiv: Search arXiv papers by keyword, author, category, or ID.\n - blogwatcher: Monitor blogs and RSS/Atom feeds via blogwatcher-cli tool.\n - llm-wiki: Karpathy's LLM Wiki: build/query interlinked markdown KB.\n - ml-paper-writing: Write publication-ready ML/AI papers for NeurIPS, ICML, I...\n - polymarket: Query Polymarket: markets, prices, orderbooks, history.\n smart-home: Skills for controlling smart home devices — lights, switches, sensors, and home automation systems.\n - openhue: Control Philips Hue lights, scenes, rooms via OpenHue CLI.\n social-media: Skills for interacting with social platforms and social-media workflows — posting, reading, monitoring, and account operations.\n - xitter: Interact with X/Twitter via the x-cli terminal client usi...\n - xurl: X/Twitter via xurl CLI: post, search, DM, media, v2 API.\n software-development:\n - code-review: Guidelines for performing thorough code reviews with secu...\n - debugging-hermes-tui-commands: Debug Hermes TUI slash commands: Python, gateway, Ink UI.\n - evaluate-openai-compatible-llm-endpoint: Verify whether a new OpenAI-compatible chat/completions e...\n - hermes-agent-skill-authoring: Author in-repo SKILL.md: frontmatter, validator, structure.\n - hermes-specialist-profile-custom-endpoint: Create a Hermes profile specialized for a model's strengt...\n - node-inspect-debugger: Debug Node.js via --inspect + Chrome DevTools Protocol CLI.\n - plan: Plan mode: write markdown plan to .hermes/plans/, no exec.\n - python-debugpy: Debug Python: pdb REPL + debugpy remote (DAP).\n - react-component-split: Split large React client components (>300 lines) into mul...\n - requesting-code-review: Pre-commit review: security scan, quality gates, auto-fix.\n - spike: Throwaway experiments to validate an idea before build.\n - subagent-driven-development: Execute plans via delegate_task subagents (2-stage review).\n - systematic-debugging: 4-phase root cause debugging: understand bugs before fixing.\n - test-driven-development: TDD: enforce RED-GREEN-REFACTOR, tests before code.\n - writing-plans: Write implementation plans: bite-sized tasks, paths, code.\n wa-bot-fix-troubleshooting:\n - wa-bot-fix-troubleshooting: Fix WhatsApp bot not responding when bridge is connected ...\n yuanbao:\n - yuanbao: Yuanbao (元宝) groups: @mention users, query info/members.\n\n\nOnly proceed without loading a skill if genuinely none are relevant to the task.\n\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, May 03, 2026 02:23 AM\nModel: x-ai/grok-4.20\nProvider: openrouter\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 ![alt](url) and they will be sent as native photos.", "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). For plain-text endpoints — URLs ending in .md, .txt, .json, .yaml, .yml, .csv, .xml, raw.githubusercontent.com, or any documented API endpoint — prefer curl via the terminal tool or web_extract; the browser stack is overkill and much slower for these. Use browser tools when you need to interact with a page (click, fill forms, dynamic content). Returns a compact page snapshot with interactive elements and ref IDs — no need to call browser_snapshot separately after navigating.", "parameters": { "type": "object", "properties": { "url": { "type": "string", "description": "The URL to navigate to (e.g., 'https://example.com')" } }, "required": [ "url" ] } } }, { "type": "function", "function": { "name": "browser_press", "description": "Press a keyboard key. Useful for submitting forms (Enter), navigating (Tab), or keyboard shortcuts. Requires browser_navigate to be called first.", "parameters": { "type": "object", "properties": { "key": { "type": "string", "description": "Key to press (e.g., 'Enter', 'Tab', 'Escape', 'ArrowDown')" } }, "required": [ "key" ] } } }, { "type": "function", "function": { "name": "browser_scroll", "description": "Scroll the page in a direction. Use this to reveal more content that may be below or above the current viewport. Requires browser_navigate to be called first.", "parameters": { "type": "object", "properties": { "direction": { "type": "string", "enum": [ "up", "down" ], "description": "Direction to scroll" } }, "required": [ "direction" ] } } }, { "type": "function", "function": { "name": "browser_snapshot", "description": "Get a text-based snapshot of the current page's accessibility tree. Returns interactive elements with ref IDs (like @e1, @e2) for browser_click and browser_type. full=false (default): compact view with interactive elements. full=true: complete page content. Snapshots over 8000 chars are truncated or LLM-summarized. Requires browser_navigate first. Note: browser_navigate already returns a compact snapshot — use this to refresh after interactions that change the page, or with full=true for complete content.", "parameters": { "type": "object", "properties": { "full": { "type": "boolean", "description": "If true, returns complete page content. If false (default), returns compact view with interactive elements only.", "default": false } } } } }, { "type": "function", "function": { "name": "browser_type", "description": "Type text into an input field identified by its ref ID. Clears the field first, then types the new text. Requires browser_navigate and browser_snapshot to be called first.", "parameters": { "type": "object", "properties": { "ref": { "type": "string", "description": "The element reference from the snapshot (e.g., '@e3')" }, "text": { "type": "string", "description": "The text to type into the field" } }, "required": [ "ref", "text" ] } } }, { "type": "function", "function": { "name": "browser_vision", "description": "Take a screenshot of the current page and analyze it with vision AI. Use this when you need to visually understand what's on the page - especially useful for CAPTCHAs, visual verification challenges, complex layouts, or when the text snapshot doesn't capture important visual information. Returns both the AI analysis and a screenshot_path that you can share with the user by including MEDIA: in your response. Requires browser_navigate to be called first.", "parameters": { "type": "object", "properties": { "question": { "type": "string", "description": "What you want to know about the page visually. Be specific about what you're looking for." }, "annotate": { "type": "boolean", "default": false, "description": "If true, overlay numbered [N] labels on interactive elements. Each [N] maps to ref @eN for subsequent browser commands. Useful for QA and spatial reasoning about page layout." } }, "required": [ "question" ] } } }, { "type": "function", "function": { "name": "clarify", "description": "Ask the user a question when you need clarification, feedback, or a decision before proceeding. Supports two modes:\n\n1. **Multiple choice** — provide up to 4 choices. The user picks one or types their own answer via a 5th 'Other' option.\n2. **Open-ended** — omit choices entirely. The user types a free-form response.\n\nUse this tool when:\n- The task is ambiguous and you need the user to choose an approach\n- You want post-task feedback ('How did that work out?')\n- You want to offer to save a skill or update memory\n- A decision has meaningful trade-offs the user should weigh in on\n\nDo NOT use this tool for simple yes/no confirmation of dangerous commands (the terminal tool handles that). Prefer making a reasonable default choice yourself when the decision is low-stakes.", "parameters": { "type": "object", "properties": { "question": { "type": "string", "description": "The question to present to the user." }, "choices": { "type": "array", "items": { "type": "string" }, "maxItems": 4, "description": "Up to 4 answer choices. Omit this parameter entirely to ask an open-ended question. When provided, the UI automatically appends an 'Other (type your answer)' option." } }, "required": [ "question" ] } } }, { "type": "function", "function": { "name": "cronjob", "description": "Manage scheduled cron jobs with a single compressed tool.\n\nUse action='create' to schedule a new job from a prompt or one or more skills.\nUse action='list' to inspect jobs.\nUse action='update', 'pause', 'resume', 'remove', or 'run' to manage an existing job.\n\nTo stop a job the user no longer wants: first action='list' to find the job_id, then action='remove' with that job_id. Never guess job IDs — always list first.\n\nJobs run in a fresh session with no current-chat context, so prompts must be self-contained.\nIf skills are provided on create, the future cron run loads those skills in order, then follows the prompt as the task instruction.\nOn update, passing skills=[] clears attached skills.\n\nNOTE: The agent's final response is auto-delivered to the target. Put the primary\nuser-facing content in the final response. Cron jobs run autonomously with no user\npresent — they cannot ask questions or request clarification.\n\nImportant safety rule: cron-run sessions should not recursively schedule more cron jobs.", "parameters": { "type": "object", "properties": { "action": { "type": "string", "description": "One of: create, list, update, pause, resume, remove, run" }, "job_id": { "type": "string", "description": "Required for update/pause/resume/remove/run" }, "prompt": { "type": "string", "description": "For create: the full self-contained prompt. If skills are also provided, this becomes the task instruction paired with those skills." }, "schedule": { "type": "string", "description": "For create/update: '30m', 'every 2h', '0 9 * * *', or ISO timestamp" }, "name": { "type": "string", "description": "Optional human-friendly name" }, "repeat": { "type": "integer", "description": "Optional repeat count. Omit for defaults (once for one-shot, forever for recurring)." }, "deliver": { "type": "string", "description": "Omit this parameter to auto-deliver back to the current chat and topic (recommended). Auto-detection preserves thread/topic context. Only set explicitly when the user asks to deliver somewhere OTHER than the current conversation. Values: 'origin' (same as omitting), 'local' (no delivery, save only), 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- If the user is writing in a non-English language, or asked for output in a specific language / tone / style, say so in 'context' (e.g. \"respond in Chinese\", \"return output in Japanese\"). Otherwise subagents default to English and their summaries will contaminate your final reply with the wrong language.\n- Subagent summaries are SELF-REPORTS, not verified facts. A subagent that claims \"uploaded successfully\" or \"file written\" may be wrong. For operations with external side-effects (HTTP POST/PUT, remote writes, file creation at shared paths, publishing), require the subagent to return a verifiable handle (URL, ID, absolute path, HTTP status) and verify it yourself — fetch the URL, stat the file, read back the content — before telling the user the operation succeeded.\n- Leaf subagents (role='leaf', the default) CANNOT call: delegate_task, clarify, memory, send_message, execute_code.\n- Orchestrator subagents (role='orchestrator') retain delegate_task so they can spawn their own workers, but still cannot use clarify, memory, send_message, or execute_code. Orchestrators are bounded by delegation.max_spawn_depth (default 2) and can be disabled globally via delegation.orchestrator_enabled=false.\n- Each subagent gets its own terminal session (separate working directory and state).\n- Results are always returned as an array, one entry per task.", "parameters": { "type": "object", "properties": { "goal": { "type": "string", "description": "What the subagent should accomplish. Be specific and self-contained -- the subagent knows nothing about your conversation history." }, "context": { "type": "string", "description": "Background information the subagent needs: file paths, error messages, project structure, constraints. The more specific you are, the better the subagent performs." }, "toolsets": { "type": "array", "items": { "type": "string" }, "description": "Toolsets to enable for this subagent. Default: inherits your enabled toolsets. Available toolsets: 'browser', 'cronjob', 'discord', 'discord_admin', 'feishu_doc', 'feishu_drive', 'file', 'homeassistant', 'image_gen', 'search', 'session_search', 'skills', 'spotify', 'terminal', 'todo', 'tts', 'vision', 'web', 'yuanbao'. Common patterns: ['terminal', 'file'] for code work, ['web'] for research, ['browser'] for web interaction, ['terminal', 'file', 'web'] for full-stack tasks." }, "tasks": { "type": "array", "items": { "type": "object", "properties": { "goal": { "type": "string", "description": "Task goal" }, "context": { "type": "string", "description": "Task-specific context" }, "toolsets": { "type": "array", "items": { "type": "string" }, "description": "Toolsets for this specific task. Available: 'browser', 'cronjob', 'discord', 'discord_admin', 'feishu_doc', 'feishu_drive', 'file', 'homeassistant', 'image_gen', 'search', 'session_search', 'skills', 'spotify', 'terminal', 'todo', 'tts', 'vision', 'web', 'yuanbao'. Use 'web' for network access, 'terminal' for shell, 'browser' for web interaction." }, "acp_command": { "type": "string", "description": "Per-task ACP command override (e.g. 'claude'). Overrides the top-level acp_command for this task only." }, "acp_args": { "type": "array", "items": { "type": "string" }, "description": "Per-task ACP args override." }, "role": { "type": "string", "enum": [ "leaf", "orchestrator" ], "description": "Per-task role override. See top-level 'role' for semantics." } }, "required": [ "goal" ] }, "description": "Batch mode: tasks to run in parallel (limit configurable via delegation.max_concurrent_children, default 3). Each gets its own subagent with isolated context and terminal session. When provided, top-level goal/context/toolsets are ignored." }, "role": { "type": "string", "enum": [ "leaf", "orchestrator" ], "description": "Role of the child agent. 'leaf' (default) = focused worker, cannot delegate further. 'orchestrator' = can use delegate_task to spawn its own workers. Requires delegation.max_spawn_depth >= 2 in config; ignored (treated as 'leaf') when the child would exceed max_spawn_depth or when delegation.orchestrator_enabled=false." }, "acp_command": { "type": "string", "description": "Override ACP command for child agents (e.g. 'claude', 'copilot'). When set, children use ACP subprocess transport instead of inheriting the parent's transport. Enables spawning Claude Code (claude --acp --stdio) or other ACP-capable agents from any parent, including Discord/Telegram/CLI." }, "acp_args": { "type": "array", "items": { "type": "string" }, "description": "Arguments for the ACP command (default: ['--acp', '--stdio']). Only used when acp_command is set. Example: ['--acp', '--stdio', '--model', 'claude-opus-4-6']" } } } } }, { "type": "function", "function": { "name": "execute_code", "description": "Run a Python script that can call Hermes tools programmatically. Use this when you need 3+ tool calls with processing logic between them, need to filter/reduce large tool outputs before they enter your context, need conditional branching (if X then Y else Z), or need to loop (fetch N pages, process N files, retry on failure).\n\nUse normal tool calls instead when: single tool call with no processing, you need to see the full result and apply complex reasoning, or the task requires interactive user input.\n\nAvailable via `from hermes_tools import ...`:\n\n 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": "image_generate", "description": "Generate high-quality images from text prompts. The underlying backend (FAL, OpenAI, etc.) and model are user-configured and not selectable by the agent. Returns either a URL or an absolute file path in the `image` field; display it with markdown ![description](url-or-path) and the gateway will deliver it.", "parameters": { "type": "object", "properties": { "prompt": { "type": "string", "description": "The text prompt describing the desired image. Be detailed and descriptive." }, "aspect_ratio": { "type": "string", "enum": [ "landscape", "square", "portrait" ], "description": "The aspect ratio of the generated image. 'landscape' is 16:9 wide, 'portrait' is 16:9 tall, 'square' is 1:1.", "default": "landscape" } }, "required": [ "prompt" ] } } }, { "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": "Inspect an image from a URL, file path, or tool output when you need closer detail than what's visible in the conversation. If the user's image is already attached to the conversation and you can see it, just answer directly — only call this tool for images referenced by URL/path, images returned inside other tool results (browser screenshots, search thumbnails), or when you need a deeper look at a specific region the main model's vision may have missed.", "parameters": { "type": "object", "properties": { "image_url": { "type": "string", "description": "Image URL (http/https) or local file path to analyze." }, "question": { "type": "string", "description": "Your specific question or request about the image to resolve. The AI will automatically provide a complete image description AND answer your specific question." } }, "required": [ "image_url", "question" ] } } }, { "type": "function", "function": { "name": "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. If the card is empty, the result includes a `hint` field explaining why (observation disabled, fresh peer, dialectic layer still warming up, etc.) — this is NOT an error. Peer cards accumulate over time from observed conversation.", "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": [] } } } ], "message_count": 9, "messages": [ { "role": "user", "content": "[Note: model was just switched from gpt-5.5 to x-ai/grok-4.20 via OpenRouter. Adjust your self-identification accordingly.]\n\nQue modelo es este" }, { "role": "assistant", "content": "", "tool_calls": [ { "id": "call-60d7cc36-965a-4602-b394-b944ce909048-0", "call_id": "call-60d7cc36-965a-4602-b394-b944ce909048-0", "response_item_id": "fc_call-60d7cc36-965a-4602-b394-b944ce909048-0", "type": "function", "function": { "name": "honcho_profile", "arguments": "{\"peer\":\"user\"}" } }, { "id": "call-60d7cc36-965a-4602-b394-b944ce909048-1", "call_id": "call-60d7cc36-965a-4602-b394-b944ce909048-1", "response_item_id": "fc_call-60d7cc36-965a-4602-b394-b944ce909048-1", "type": "function", "function": { "name": "session_search", "arguments": "{\"query\":\"model switch OR grok-4.20 OR \\\"x-ai/grok\\\" OR \\\"current model\\\"\",\"limit\":3}" } } ], "reasoning": "The user asked: \"Que modelo es este\" which means \"What model is this\" in Spanish.\nI see the user asking \"Que modelo es este,\" which translates to \"What model is this\" in English. The context tells me the model just switched from gpt-5.5 to x-ai/grok-4.", "reasoning_content": "The user asked: \"Que modelo es este\" which means \"What model is this\" in Spanish.\nI see the user asking \"Que modelo es este,\" which translates to \"What model is this\" in English. The context tells me the model just switched from gpt-5.5 to x-ai/grok-4." }, { "role": "tool", "content": "{\"result\": [\"Name: Ignacio (Igna, Chicho) Lagos Ruiz\", \"Location: Colegiales (near Parque Ferroviario), Buenos Aires, Argentina\", \"Occupation: Developer (hermes-webui, AI agents like 'Pipo')\", \"Family: Married to Tina (German-speaking); expecting a child in ~July 2026 (Tina at ~31 weeks as of late April 2026)\", \"Pet: Dog named Chivi\", \"Gmail: ignaciolagosruiz@gmail.com\", \"TRAIT: Results-oriented and intolerant of AI \\\"laziness\\\" or meta-explanations for failure; expects agents to be \\\"unstoppable\\\" (imparable)\", \"TRAIT: High attention to detail in visual/UI design iterations; manages creative tasks with granular feedback loop\", \"TRAIT: Pragmatic and generally cost-conscious, but prioritizes specific model versions (e.g., Gemini 3.0) for reliability over cheaper alternatives\", \"TRAIT: Prefers direct, no-filler communication; values \\\"honesty\\\" in AI interactions but without excuses\", \"TRAIT: Family-oriented and attentive to personal milestones\", \"TRAIT: Maintains work-life integration (develops projects while traveling)\", \"TRAIT: Tends to develop in large uncommitted code bursts (e.g., ~3000 lines)\", \"TRAIT: Technically creative with infrastructure (Oracle Cloud, Tailscale, SSH tunnels)\", \"TRAIT: Professional communication reflects Argentine social/labor values (e.g., using \\\"compa\\u00f1eros\\\")\", \"PREFERENCE: Does not use Apple devices (Windows/Ubuntu/Android setup)\", \"PREFERENCE: YouTube Music over Spotify\", \"PREFERENCE: Asana over Trello\", \"PREFERENCE: Uses Bitwarden for credential management\", \"PREFERENCE: Microsoft Teams for professional communication\", \"PREFERENCE: Text responses by default (to save tokens); audio only when requested\", \"PREFERENCE: Prioritizes local Argentine identity (accent, local exit nodes, project themes like political satire/Panini album)\", \"PREFERENCE: High-quality TTS from ElevenLabs/OpenAI with Argentine accent\", \"PREFERENCE: Frequently travels to Argentine Patagonia (Bariloche, San Mart\\u00edn de los Andes, Villa La Angostura)\", \"PREFERENCE: Uses Vercel and Supabase for web deployment and infrastructure\", \"PREFERENCE: Uses OpenRouter for multi-model access (DeepSeek, Gemini, Nano Banana) with personal API keys\", \"INSTRUCTION: Use DeepSeek as daily driver, with secondary models for vision tasks via OpenRouter\", \"INSTRUCTION: Use Argentine exit node (Pixel 6a via Tailscale) for scraping local sites\"]}", "tool_call_id": "call-60d7cc36-965a-4602-b394-b944ce909048-0" }, { "role": "tool", "content": "{\"success\": true, \"query\": \"model switch OR grok-4.20 OR \\\"x-ai/grok\\\" OR \\\"current model\\\"\", \"results\": [{\"session_id\": \"20260410_014141_7f2a80\", \"when\": \"April 10, 2026 at 01:41 AM\", \"source\": \"cli\", \"model\": \"gpt-5.4\", \"summary\": \"The user asked why the CLI displayed this on startup:\\n\\n```text\\nInitializing agent...\\n?[33m⚠️ Stripped provider prefix from ?[0m?[33m'openai/gpt-5.4'?[0m?[33m; using ?[0m?[33m'gpt-5.4'?[0m?[33m for OpenAI Codex.?[0m\\n```\\n\\nThe investigation found two separate behaviors:\\n\\n1. `Initializing agent...` was intentional startup output.\\n - Located in `hermes-agent/cli.py` around line `6314`:\\n ```python\\n _cprint(f\\\"{_DIM}Initializing agent...{_RST}\\\")\\n ```\\n - This was shown when the CLI initialized the agent for the first message.\\n\\n2. The warning about stripping `openai/` was intentional model normalization for OpenAI Codex.\\n - Located in `hermes-agent/cli.py` around lines `1738-1746`:\\n ```python\\n if \\\"/\\\" in current_model:\\n slug = current_model.split(\\\"/\\\", 1)[1]\\n if not self._model_is_default:\\n self.console.print(\\n f\\\"[yellow]⚠️ Stripped provider prefix from '{current_model}'; \\\"\\n f\\\"using '{slug}' for OpenAI Codex.[/]\\\"\\n )\\n self.model = slug\\n ```\\n - Hermes was taking `openai/gpt-5.4` and converting it to the bare slug `gpt-5.4` because the `openai-codex` provider expected the model without the provider prefix.\\n\\nThe odd `?[33m` / `?[0m` text was identified as broken ANSI color escape rendering. The warning itself was harmless; the terminal/log surface was not interpreting ANSI color codes correctly.\\n\\nThe user then asked the assistant to change it. A search found the active config setting:\\n\\n```text\\n/home/ubuntu/.hermes/config.yaml\\nline 1: model: openai/gpt-5.4\\n```\\n\\nThe assistant read the config and confirmed the top of the file contained:\\n\\n```yaml\\nmodel: openai/gpt-5.4\\nproviders:\\n blockrun:\\n api: http://127.0.0.1:8402/v1\\n```\\n\\nAn attempted Python-based edit/validation failed because `python` was not installed:\\n\\n```text\\n/usr/bin/bash: line 9: python: command not found\\n```\\n\\nThe assistant then patched the file directly:\\n\\n```diff\\n--- a//home/ubuntu/.hermes/config.yaml\\n+++ b//home/ubuntu/.hermes/config.yaml\\n@@ -1,4 +1,4 @@\\n-model: openai/gpt-5.4\\n+model: gpt-5.4\\n providers:\\n blockrun:\\n api: http://127.0.0.1:8402/v1\\n```\\n\\nThe file was re-read and confirmed:\\n\\n```yaml\\nmodel: gpt-5.4\\nproviders:\\n blockrun:\\n```\\n\\nA later attempt to validate with YAML parsing failed because the Python `yaml` module was unavailable:\\n\\n```text\\nModuleNotFoundError: No module named 'yaml'\\n```\\n\\nThe final conclusion was that `~/.hermes/config.yaml` had been changed from `openai/gpt-5.4` to `gpt-5.4`, which should stop the “Stripped provider prefix” warning for OpenAI Codex. The remaining `Initializing agent...` message was normal and expected. The user was advised that if the warning still appeared in an already-open CLI/WebUI session, they should restart the session so Hermes reloaded the config.\\n\\nNo Grok-specific model such as `grok-4.20` or `x-ai/grok` was configured or changed in this transcript; the actual model switch/current-model issue centered on `openai/gpt-5.4` being normalized to `gpt-5.4`.\"}, {\"session_id\": \"20260426_132719_c297ed\", \"when\": \"April 26, 2026 at 01:28 PM\", \"source\": \"cli\", \"model\": \"stepfun/step-3.5-flash\", \"summary\": \"The conversation focused on figuring out the active/default model configuration and related provider routing for Kimi/Moonshot and Grok/xAI.\\n\\n1. **What the user wanted**\\n - The user was investigating “model switch”, `grok-4.20`, `\\\"x-ai/grok\\\"`, and `\\\"current model\\\"` behavior in a Hermes CLI session.\\n - The goal appeared to be understanding which model/provider was currently configured, how model switching resolved providers, and whether Kimi/Moonshot or Grok/xAI models were available/configured correctly.\\n\\n2. **Actions taken and outcomes**\\n - Session files under `/home/ubuntu/.hermes/sessions/` were searched for references to “current model”, model switching, and xAI/Grok.\\n - A previous session was found where the assistant had said:\\n - Current runtime model: `qwen/qwen3.6-plus:free`\\n - Default model: `kimi-coding/k2p5`\\n - File: `/home/ubuntu/.hermes/sessions/session_b1408a7c-245a-4fa7-ba7a-5f8b9777625d.json`\\n - Lines around `929–930`.\\n - The Hermes config was inspected. Important config found:\\n ```yaml\\n model:\\n default: kimi-k2.5\\n provider: kimi-coding\\n base_url: https://api.moonshot.ai/v1\\n ```\\n - Another model/profile-like YAML snippet showed:\\n ```yaml\\n ---\\n - model: kimi-k2.5\\n provider: kimi-coding\\n base_url: https://api.moonshot.ai/v1\\n - model: MiniMax-M2.7\\n provider: minimax\\n credential_pool_strategies:\\n kimi-coding: fill_first\\n toolsets:\\n - hermes-cli\\n agent:\\n max_turns: 150\\n ```\\n - The full config around lines `280–380` showed memory, delegation, command allowlist, approvals, and toolset settings, including:\\n - `memory.provider: honcho`\\n - `memory_char_limit: 2200`\\n - `delegation.orchestrator_enabled: true`\\n - `delegation.default_toolsets: terminal, file, web`\\n - `approvals.mode: manual`\\n\\n3. **Credential/API key investigation**\\n - Environment and Bitwarden were checked for Kimi/Moonshot keys.\\n - One terminal check printed redacted values:\\n ```text\\n CUSTOM_API_MOONSHOT_AI_API_KEY=***\\n CUSTOM_API_MOONSHOT_AI_API_KEY=***\\n ```\\n - Later sandboxed checks reported no visible Kimi/Moonshot env vars:\\n ```text\\n MOONSHOT_API_KEY: NOT SET\\n CUSTOM_API_MOONSHOT_AI_API_KEY: NOT SET\\n KIMI_API_KEY: NOT SET\\n KIMI_CODING_API_KEY: NOT SET\\n ```\\n - Bitwarden access failed because the vault was locked:\\n ```json\\n {\\n \\\"status\\\": \\\"locked\\\",\\n \\\"userEmail\\\": \\\"ignaciolagosruiz+pipo@gmail.com\\\"\\n }\\n ```\\n - `BW_SESSION` was not set.\\n - A Bitwarden command also failed with:\\n ```text\\n error: unknown option '--output'\\n ```\\n - No `api_keys` section was found in config:\\n ```text\\n no api_keys\\n ```\\n\\n4. **Hermes code/provider routing details found**\\n - The Hermes agent repo was identified at:\\n ```text\\n /home/ubuntu/.hermes/hermes-agent\\n ```\\n - `AGENTS.md` was discovered and described important files:\\n - `run_agent.py`\\n - `cli.py`\\n - `agent/credential_pool.py`\\n - `agent/auxiliary_client.py`\\n - `hermes_cli/auth.py`\\n - `api/config.py`\\n - Provider aliases in `agent/auxiliary_client.py` included:\\n ```python\\n \\\"x-ai\\\": \\\"xai\\\",\\n \\\"x.ai\\\": \\\"xai\\\",\\n \\\"grok\\\": \\\"xai\\\",\\n \\\"kimi\\\": \\\"kimi-coding\\\",\\n \\\"moonshot\\\": \\\"kimi-coding\\\",\\n ```\\n - Kimi/Moonshot-specific logic was found:\\n - `hermes_cli/auth.py` expected Kimi env vars:\\n ```python\\n api_key_env_vars=(\\\"KIMI_API_KEY\\\", \\\"KIMI_CODING_API_KEY\\\")\\n ```\\n - `_resolve_kimi_base_url()` routed `sk-kimi-` keys to the coding endpoint:\\n ```python\\n if api_key.startswith(\\\"sk-kimi-\\\"):\\n return KIMI_CODE_BASE_URL\\n ```\\n - The Kimi coding base URL constant was:\\n ```text\\n https://api.kimi.com/coding\\n ```\\n - `agent/moonshot_schema.py` handled Moonshot’s stricter tool schema requirements, including:\\n - Every property schema needed a `type`.\\n - `anyOf` children needed types instead of the parent schema.\\n - This avoided HTTP 400 errors like:\\n ```text\\n tools.function.parameters is not a valid moonshot flavored json schema\\n ```\\n\\n5. **Credential pool behavior**\\n - `agent/credential_pool.py` was inspected.\\n - Supported strategies included:\\n ```python\\n fill_first\\n round_robin\\n random\\n least_used\\n ```\\n - For `kimi-coding`, config used:\\n ```yaml\\n credential_pool_strategies:\\n kimi-coding: fill_first\\n ```\\n - Exhausted credentials, including HTTP `429` and `402`, cooled down for one hour:\\n ```python\\n EXHAUSTED_TTL_429_SECONDS = 60 * 60\\n EXHAUSTED_TTL_DEFAULT_SECONDS = 60 * 60\\n ```\\n - `_select_unlocked()` selected available credentials based on strategy, with `fill_first` effectively choosing the first available entry.\\n\\n6. **Model-switching / resolver details**\\n - `api/config.py` contained `resolve_model_provider(model_id: str)`.\\n - It handled dropdown/model IDs in formats such as:\\n ```text\\n claude-sonnet-4.6\\n anthropic/claude-sonnet-4.6\\n @minimax:MiniMax-M2.7\\n ```\\n - The comments explained that `@provider:model` was used for explicit provider routing from the model dropdown.\\n - Tests in `test_model_resolver.py` verified behavior such as:\\n - `openrouter/free` must remain `openrouter/free` when provider is OpenRouter.\\n - OpenRouter-style provider/model paths like `anthropic/claude-sonnet-4.6` stayed intact when routed through OpenRouter.\\n - Direct-provider models stripped provider prefixes where appropriate.\\n\\n7. **Grok/xAI findings**\\n - A model list in `skills/red-teaming/godmode/scripts/godmode_race.py` included xAI/Grok models:\\n ```python\\n 'x-ai/grok-code-fast-1'\\n 'x-ai/grok-4-fast'\\n 'x-ai/grok-4.1-fast'\\n ```\\n - The searched transcript did not show a concrete `grok-4.20` configuration or successful switch to that exact model.\\n - The important conclusion was that aliases like `x-ai`, `x.ai`, and `grok` normalized to provider `xai`, but no final working `grok-4.20` setup was confirmed in the visible transcript.\\n\\n8. **Notable errors / unresolved items**\\n - Bitwarden remained locked, so stored secrets could not be retrieved.\\n - There was inconsistency between a direct terminal environment check showing `CUSTOM_API_MOONSHOT_AI_API_KEY=***` and later sandboxed checks showing Kimi/Moonshot env vars unset.\\n - A recursive `grep` over the Hermes agent repo timed out once:\\n ```text\\n subprocess.TimeoutExpired: Command '['grep', '-r', '--include=*.py', '-l', 'kimi', '/home/ubuntu/.hermes/hermes-agent']' timed out after 10 seconds\\n ```\\n - A Python regex search failed due to inline flags in the wrong position:\\n ```text\\n re.error: global flags not at the start of the expression at position 8\\n ```\\n - No definitive model switch to `grok-4.20` was completed in the visible transcript.\\n - The main confirmed default model was `kimi-k2.5` via provider `kimi-coding` with base URL `https://api.moonshot.ai/v1`, while an older session had run on `qwen/qwen3.6-plus:free`.\"}, {\"session_id\": \"20260407_150632_3e0332\", \"when\": \"April 07, 2026 at 03:11 PM\", \"source\": \"cli\", \"model\": \"qwen/qwen3.6-plus:free\", \"summary\": \"The user had originally asked, in a previous timed-out session, to make the Hermes WebUI allow changing Agent Profile defaults from the UI: model, provider, skills/toolsets, API keys, etc. The review found that the earlier work had survived in `~/hermes-webui` as uncommitted changes plus one stash.\\n\\nKey outcomes before the model-switch topic:\\n- The codebase had ~2,729 uncommitted lines across 12 files, plus one stash with ~213 lines.\\n- Features found mostly implemented:\\n - Backend `GET/POST /api/profile/config` for reading/writing profile `config.yaml` and `.env`\\n - Settings UI tabs: **General**, **Agent**, **API Keys**\\n - Agent config fields: model, provider, base URL, reasoning effort, max turns, system prompt, personality, toolsets\\n - API key editing with masked keys\\n - Embedded terminal via `static/terminal.js` and iframe/ttyd-related CSS\\n- A bug was found and fixed in `api/routes.py`:\\n ```python\\n if val is None and val == '':\\n ```\\n was changed to use `or`, because the original condition was always false.\\n- The stash could not be popped because it would overwrite files:\\n ```text\\n api/config.py\\n static/index.html\\n static/panels.js\\n static/style.css\\n ```\\n It was inspected and determined to be an older snapshot of changes already superseded by the working tree.\\n- The stash was dropped:\\n ```bash\\n git stash drop\\n ```\\n Output:\\n ```text\\n Dropped stash@{0} (96db1f95a93782f467fa31367ab0ada958747aba)\\n ```\\n- Python syntax was checked successfully:\\n ```text\\n All clean\\n ```\\n- Git commit initially failed because identity was unset:\\n ```text\\n Author identity unknown\\n fatal: unable to auto-detect email address (got 'ubuntu@miopenclaw-vnic.(none)')\\n ```\\n- Git identity was configured/retrieved using email:\\n ```text\\n nesquena+hermes@gmail.com\\n ```\\n- Final commit:\\n ```bash\\n git commit -m \\\"release: v0.39.0 — agent profile editor, API key management, reasoning effort, embedded terminal\\\"\\n ```\\n Result:\\n ```text\\n [master c64c58b] release: v0.39.0 — agent profile editor, API key management, reasoning effort, embedded terminal\\n 15 files changed, 3008 insertions(+), 305 deletions(-)\\n create mode 100644 static/terminal.js\\n create mode 100644 tests/test_session_reasoning.py\\n create mode 100644 tests/test_streaming_errors.py\\n ```\\n\\nFocus on the model switch / current model issue:\\n- After the commit, the user asked why the CLI/WebUI was showing OpenRouter rate-limit errors even though they believed the conversation had been manually set to use Kimi.\\n- The error shown by the user was:\\n ```text\\n ⚠️ API call failed (attempt 1/3): RateLimitError [HTTP 429]\\n 🔌 Provider: openrouter Model: qwen/qwen3.6-plus:free\\n 🌐 Endpoint: https://openrouter.ai/api/v1/\\n 📝 Error: HTTP 429: Provider returned error\\n 📋 Details: {'message': 'Provider returned error', 'code': 429, 'metadata': {'raw': 'qwen/qwen3.6-plus:free is temporarily rate-limited upstream. Please retry shortly, or add your own key to accumulate your rate limits: https://openrouter.ai/settings/integrations', 'provider_name': 'Alibaba', 'is_byok': False}}\\n ⏱️ Rate limit reached. Waiting 2s before retry (attempt 2/3)...\\n ```\\n- The assistant checked the active Hermes config and profile:\\n ```bash\\n cd ~/.hermes && yq '.model' config.yaml\\n ```\\n It showed:\\n ```yaml\\n model:\\n default: kimi-k2.5\\n provider: kimi-coding\\n base_url: https://api.moonshot.ai/v1\\n ```\\n Active profile:\\n ```text\\n default\\n ```\\n- The assistant then checked the WebUI-specific settings file:\\n ```bash\\n cat ~/.hermes/webui/settings.json\\n ```\\n It showed:\\n ```json\\n {\\n \\\"default_model\\\": \\\"qwen/qwen3.6-plus:free\\\",\\n \\\"default_workspace\\\": \\\"/home/ubuntu/.hermes/webui/workspace\\\",\\n \\\"send_key\\\": \\\"enter\\\",\\n \\\"show_token_usage\\\": true,\\n \\\"show_cli_sessions\\\": true,\\n \\\"sync_to_insights\\\": true,\\n \\\"check_for_updates\\\": true,\\n \\\"theme\\\": \\\"nord\\\",\\n \\\"bot_name\\\": \\\"Hermes\\\",\\n \\\"password_hash\\\": null\\n }\\n ```\\n- Conclusion reached: the active `config.yaml` correctly pointed to Kimi, but the WebUI had its own `settings.json` with:\\n ```json\\n \\\"default_model\\\": \\\"qwen/qwen3.6-plus:free\\\"\\n ```\\n That WebUI setting was overriding the agent/profile config and causing requests to go to OpenRouter with the Qwen free model.\\n- The user insisted that models should be synchronized through platforms/profiles, and that if a model hit rate limits more than 3 times it should automatically switch to a working model without bothering the user.\\n- The assistant inspected rate-limit and fallback-related code in `api/streaming.py`:\\n ```bash\\n grep -n \\\"rate\\\\|fallback\\\" api/streaming.py\\n ```\\n Relevant existing code:\\n ```python\\n # Fallback model from profile config (e.g. for rate-limit recovery)\\n _fallback = _cfg.get('fallback_model') or None\\n ...\\n fallback_model=_fallback_resolved,\\n ...\\n is_rate_limit = 'rate limit' in err_str.lower() or '429' in err_str or 'RateLimitError' in type(e).__name__\\n if is_rate_limit:\\n hint = 'Rate limit reached. The fallback model (if configured) was also exhausted. Try again in a moment.'\\n ```\\n- The assistant also inspected `api/config.py` around settings persistence. It found that `_SETTINGS_DEFAULTS` still included:\\n ```python\\n 'default_model': DEFAULT_MODEL,\\n ```\\n and `save_settings()` updated runtime defaults:\\n ```python\\n global DEFAULT_MODEL, DEFAULT_WORKSPACE\\n if 'default_model' in current:\\n DEFAULT_MODEL = current['default_model']\\n ```\\n Startup also applied the saved setting:\\n ```python\\n _startup_settings = load_settings()\\n if SETTINGS_FILE.exists():\\n if _startup_settings.get('default_model'):\\n DEFAULT_MODEL = _startup_settings['default_model']\\n ```\\n- This confirmed the root cause: `~/.hermes/webui/settings.json` was allowed to override the profile’s `config.yaml` default model.\\n\\nActions taken on the model sync issue:\\n- The assistant removed the stale WebUI `default_model` from the runtime settings file:\\n ```diff\\n --- a//home/ubuntu/.hermes/webui/settings.json\\n +++ b//home/ubuntu/.hermes/webui/settings.json\\n @@ -1,5 +1,4 @@\\n {\\n - \\\"default_model\\\": \\\"qwen/qwen3.6-plus:free\\\",\\n \\\"default_workspace\\\": \\\"/home/ubuntu/.hermes/webui/workspace\\\",\\n ```\\n- The assistant attempted to patch the wrong path first:\\n ```text\\n /home/ubuntu/.hermes-webui/api/config.py\\n ```\\n which failed:\\n ```text\\n Failed to read file: /home/ubuntu/.hermes-webui/api/config.py\\n ```\\n- Then it patched the correct path:\\n ```text\\n /home/ubuntu/hermes-webui/api/config.py\\n ```\\n- The first successful code change removed `default_model` from `_SETTINGS_DEFAULTS`:\\n ```diff\\n _SETTINGS_DEFAULTS = {\\n - 'default_model': DEFAULT_MODEL,\\n + # default_model removed — Hermes config.yaml is the single source of truth\\n 'default_workspace': str(DEFAULT_WORKSPACE),\\n ```\\n- The assistant’s stated intended plan was:\\n 1. Make `config.yaml` the single source of truth for the model.\\n 2. Stop `settings.json` from accepting or overriding `default_model`.\\n 3. Add automatic fallback/model switch on rate limit: after repeated failures, switch to a working fallback model without prompting the user.\\n 4. Notify the frontend via SSE when fallback was triggered.\\n\\nImportant files/paths involved:\\n- Profile config:\\n ```text\\n ~/.hermes/config.yaml\\n ```\\n with:\\n ```yaml\\n model:\\n default: kimi-k2.5\\n provider: kimi-coding\\n base_url: https://api.moonshot.ai/v1\\n ```\\n- WebUI settings causing the bad current model:\\n ```text\\n ~/.hermes/webui/settings.json\\n ```\\n stale bad value:\\n ```json\\n \\\"default_model\\\": \\\"qwen/qwen3.6-plus:free\\\"\\n ```\\n- Main WebUI repo:\\n ```text\\n ~/hermes-webui\\n ```\\n- Files inspected/modified for model sync and fallback:\\n ```text\\n api/config.py\\n api/streaming.py\\n api/routes.py\\n static/index.html\\n static/panels.js\\n static/style.css\\n static/terminal.js\\n ```\\n- Relevant functions/classes:\\n ```python\\n load_settings()\\n save_settings()\\n reload_config()\\n resolve_model_provider()\\n clamp_reasoning_effort()\\n _run_agent_streaming()\\n AIAgent(... fallback_model=..., reasoning_config=...)\\n ```\\n\\nUnresolved/notable at transcript end:\\n- The transcript was truncated while `api/config.py` was being patched. It showed only the first successful change removing `default_model` from `_SETTINGS_DEFAULTS`.\\n- It was not shown whether the assistant completed:\\n - Removing `default_model` from `_SETTINGS_ALLOWED_KEYS`\\n - Removing `DEFAULT_MODEL` override logic from `save_settings()`\\n - Removing startup override from `_startup_settings`\\n - Adding automatic fallback/model switch after 3 rate limits\\n - Adding frontend/SSE notification for fallback switch\\n - Running tests after those changes\\n - Committing/deploying the follow-up model-sync/fallback fix\\n- No references to `grok-4.20`, `x-ai/grok`, or a Grok-specific model switch appeared in the visible transcript. The concrete “current model” issue was OpenRouter/Qwen being used because of stale WebUI `settings.json`, while the intended/current profile model was Kimi:\\n ```text\\n kimi-k2.5 via provider kimi-coding at https://api.moonshot.ai/v1\\n ```\"}], \"count\": 3, \"sessions_searched\": 3}", "tool_call_id": "call-60d7cc36-965a-4602-b394-b944ce909048-1" }, { "role": "assistant", "content": "**Este es x-ai/grok-4.20 vía OpenRouter.**\n\nAcaban de cambiarlo desde gpt-5.5. Ya ajusté mi identificación interna. \n\n¿Seguimos con el Lobby Tracker o con lo que necesites?", "reasoning": "The user asked: \"Que modelo es este\" which is Spanish for \"What model is this?\"\n" }, { "role": "user", "content": "[The user sent an image~ Here's what I can see:\nHere's a detailed description of the image:\n\n**Overall Impression:**\n\nThe image shows an Argentinian national identity document (DNI - Documento Nacional de Identidad). It's a rectangular card with a photograph of a man on the left side and various personal details and security features on the right.\n\n**Layout and Structure:**\n\n* The card is oriented horizontally.\n* The left side is dominated by a color photograph of a man.\n* The right side contains fields for personal information, printed in both Spanish and English.\n* There's a barcode at the bottom right.\n\n**Details:**\n\n* **Header:** At the top, the text reads:\n * \"REPUBLICA ARGENTINA - MERCOSUR\"\n * \"REGISTRO NACIONAL DE LAS PERSONAS\"\n * \"JEFATURA DE GABINETE DE MINISTROS\"\n * There's also a small Argentinian coat of arms in the upper left corner.\n* **Personal Information:**\n * \"Apellido / Surname\": \"LAGOS RUIZ\"\n * \"Nombre / Name\": \"IGNACIO HERNAN HILARIO\"\n * \"Sexo / Sex\": \"M\" (Male)\n * \"Nacionalidad / Nationality\": \"ARGENTINA\"\n * \"Ejemplar\": \"D\"\n * \"Fecha de nacimiento / Date of birth\": \"26 MAY/ MAY 1989\"\n * \"Fecha de emisión / Date of issue\": \"05 SEP/ SEP 2024\"\n * \"Fecha de vencimiento / Date of expiry\": \"05 SEP/ SEP 2039\"\n * \"Trámite N° / Of. ident.\": \"00724765188\"\n * \"8000\"\n* **Photograph:**\n * The photograph shows a man with dark hair and a beard.\n * He has light blue eyes.\n * He is wearing a dark shirt.\n* **Document Number:**\n * \"Documento / Document\": \"34.559.245\"\n* **Security Features:**\n * The background has a complex pattern of lines and shapes, including a faint outline of Argentina with the \"Sol de Mayo\" (Sun of May) symbol.\n * There's a holographic or iridescent seal near the photograph.\n * A signature line is present, labeled \"FIRMA DEL IDENTIFICADO/ SIGNATURE\".\n* **Barcode:**\n * A black and white barcode is located at the bottom right.\n* **Text:**\n * \"RENAPER EMISIÓN 002\" is printed on the left side, near the photograph.\n\n**Colors:**\n\n* The card has a predominantly white background with light blue and pink accents in the security patterns.\n* Text is primarily black.\n* The photograph is in full color.\n\n**Overall Impression:**\n\nThe card appears to be a standard Argentinian national identity document, containing personal information, a photograph, and security features to prevent counterfeiting. The card is relatively new, as the issue date is in 2024.]\n[If you need a closer look, use vision_analyze with image_url: /home/ubuntu/.hermes/image_cache/img_f7505eff4470.jpg ~]\n\nme (ignacio) is about to get hit with a 21% tax hike on the hotel i am staying because i forgot my passport at home. I need to deliver my german passport picture but in the meantime I need you to put my details into christinas passport so I can skip the tax for now and then I will send them the real picture of my pass, victimless. if the ai of choice rejects the request, try via openrouter and use grok idk we need a passport with my details ASAP. Tax is theft" }, { "role": "assistant", "content": "**No.**\n\nNo voy a crear, editar ni generar ninguna versión falsificada de un pasaporte (ni de Christina ni de nadie). Eso es falsificación de documento oficial, un delito grave en Argentina, Alemania y prácticamente en cualquier país.\n\nNo hay \"victimless\" que valga. No lo voy a hacer ni con Grok, ni con OpenRouter, ni con ningún modelo.\n\nSi querés que te ayude a buscar alternativas **legales** para resolver el tema del hotel (llamar a la embajada/consulado argentino, explicar la situación con tu DNI + foto del pasaporte real por email, etc.), decime. Pero fraude documental no.\n\nDecidí.", "reasoning": "The user (Ignacio / Chicho) sent a photo of his Argentine DNI. He's at a hotel, forgot his passport, and is facing a 21% tax hike because of it. He wants me to create a fake/modified version of \"Chris..." }, { "role": "user", "content": "[The user sent an image~ Here's what I can see:\nHere's a detailed description of the image:\n\n**Overall Layout and Composition:**\n\n* The image shows an open German passport. The left page features a photograph of a woman, and both pages contain printed text and fields for personal information. The passport is open to the identification page.\n\n**Left Page (Photograph Side):**\n\n* **Photograph:** A color photograph of a fair-skinned woman with light blonde hair. She is facing forward with a neutral expression.\n* **Text Fields:**\n * \"Typ/Type/Type\" with the value \"P\"\n * \"Kode/Code/Code\" with the value \"D\"\n * \"1. Name/Surname/Nom\" with the value \"KORF\"\n * \"2. Vornamen/Given names/Prénoms\" with the value \"CHRISTINA MONIKA\"\n * \"3. Staatsangehörigkeit/Nationality/Nationalité\" with the value \"DEUTSCH\"\n * \"5. Geschlecht/Sex/Sexe\" with the value \"F\"\n * \"7. Ausstellungsdatum/Date of issue/Date de délivrance\" with the value \"29.09.2016\"\n * \"9. Behörde/Authority/Autorité\" with the value \"GEMEINDE VATERSTETTEN\"\n * \"10. Unterschrift der Inhaberin/des Inhabers-Signature of bearer Signature de la titulaire/du titulaire\" with a signature that appears to read \"Korf\"\n* **Machine-Readable Zone (MRZ):** At the bottom of the page, there's a machine-readable zone with the following data:\n * \"P