feat(agent): adaptive model routing — content-based profile selection

.coderabbit.yaml

@@ -0,0 +1,18 @@
+# CodeRabbit configuration.
+#
+# Auto-review is DISABLED repo-wide: the app was enabled at the org level on
+# 2026-08-14 and immediately began reviewing every opened PR. This repo's
+# merge gate is CI ("All required checks pass") plus maintainer review —
+# CodeRabbit reviews carry no merge weight (protect-main ruleset requires
+# 0 approving reviews), so auto-firing on the full PR firehose adds comment
+# noise without gating value.
+#
+# The bot stays installed and summonable on demand: comment
+# `@coderabbitai review` on any PR to request a one-off review, or
+# `@coderabbitai ignore` to mute it on a PR it has already joined.
+#
+# To re-enable auto-review, flip `enabled: true` below (or delete this file —
+# the app default is on).
+reviews:
+  auto_review:
+    enabled: false

.dockerignore

@@ -3,14 +3,103 @@
 .gitignore
 .gitmodules
 
+# Python
+__pycache__
+*.py[cod]
+*$py.class
+*.so
+.Python
+*.egg-info/
+dist/
+build/
+
+# Virtual environments
+venv/
+env/
+ENV/
+
 # Dependencies
 node_modules
+**/node_modules
 .venv
+**/.venv
+.notebooklm-cli-venv/
+.notebooklm-playwright/
+.pip-cache/
+.uv-cache/
+
+# Built artifacts that are regenerated inside the image.  Excluded so local
+# rebuilds on the developer's machine don't invalidate the npm-install layer
+# that now depends on the full ui-tui/packages/hermes-ink/ tree being present.
+ui-tui/dist/
+ui-tui/packages/hermes-ink/dist/
 
 # CI/CD
 .github
 
 # Environment files
 .env
+.env.*
+
+# IDE
+.vscode/
+.idea/
+*.swp
+*.swo
 
+# Testing
+.pytest_cache/
+.coverage
+htmlcov/
+
+# Documentation
 *.md
+
+# Runtime data (bind-mounted at /opt/data; must not leak into build context)
+data/
+.hermes-docker/
+.notebooklm-home/
+
+# Compose/profile runtime state (bind-mounted; avoid ownership/secret issues)
+hermes-config/
+runtime/
+
+# ---------- Not needed inside the Docker image ----------
+
+# Desktop app source (Tauri/Electron); never installed in the container.
+# apps/shared is the dashboard↔desktop websocket helper and is linked from
+# web/package.json as a file: workspace dep — keep it in the build context.
+apps/
+!apps/shared/
+!apps/shared/**
+
+# Test suite — not shipped in production images
+tests/
+
+# Documentation site (Docusaurus) and supplementary docs
+website/
+docs/
+
+# Assets only used by the GitHub README
+assets/
+infographic/
+
+# Plugin-level docs (hermes-achievements ships docs/ but the runtime doesn't read them)
+plugins/hermes-achievements/docs/
+
+# Nix / Homebrew / AUR packaging metadata — irrelevant to Docker
+nix/
+flake.nix
+flake.lock
+packaging/
+
+# Design and planning documents
+plans/
+.plans/
+
+# Repo-level dotfiles that are git-only or dev-tooling config
+.env.example
+.envrc
+.gitattributes
+.hadolint.yaml
+.mailmap

.env.example

@@ -1,6 +1,13 @@
 # Hermes Agent Environment Configuration
 # Copy this file to .env and fill in your API keys
 
+# =============================================================================
+# LLM PROVIDER (Fireworks AI)
+# =============================================================================
+# Get your key at: https://app.fireworks.ai/settings/users/api-keys
+# Address models directly by catalog ID, e.g.
+#   accounts/fireworks/models/kimi-k2p6, accounts/fireworks/models/glm-5p2
+# FIREWORKS_API_KEY=
 # =============================================================================
 # LLM PROVIDER (OpenRouter)
 # =============================================================================
@@ -14,6 +21,14 @@
 # LLM_MODEL is no longer read from .env — this line is kept for reference only.
 # LLM_MODEL=anthropic/claude-opus-4.6
 
+# =============================================================================
+# LLM PROVIDER (NovitaAI)
+# =============================================================================
+# NovitaAI — 90+ models, pay-per-use
+# Get your key at: https://novita.ai/settings/key-management
+# NOVITA_API_KEY=
+# NOVITA_BASE_URL=https://api.novita.ai/openai/v1  # Override default base URL
+
 # =============================================================================
 # LLM PROVIDER (Google AI Studio / Gemini)
 # =============================================================================
@@ -24,6 +39,15 @@
 # Optional base URL override (default: Google's OpenAI-compatible endpoint)
 # GEMINI_BASE_URL=https://generativelanguage.googleapis.com/v1beta/openai
 
+# =============================================================================
+# LLM PROVIDER (Ollama Cloud)
+# =============================================================================
+# Cloud-hosted open models via Ollama's OpenAI-compatible endpoint.
+# Get your key at: https://ollama.com/settings
+# OLLAMA_API_KEY=your_ollama_key_here
+# Optional base URL override (default: https://ollama.com/v1)
+# OLLAMA_BASE_URL=https://ollama.com/v1
+
 # =============================================================================
 # LLM PROVIDER (z.ai / GLM)
 # =============================================================================
@@ -43,6 +67,15 @@
 # KIMI_BASE_URL=https://api.kimi.com/coding/v1  # Default for sk-kimi- keys
 # KIMI_BASE_URL=https://api.moonshot.ai/v1      # For legacy Moonshot keys
 # KIMI_BASE_URL=https://api.moonshot.cn/v1       # For Moonshot China keys
+# KIMI_CN_API_KEY=                               # Dedicated Moonshot China key
+
+# =============================================================================
+# LLM PROVIDER (Arcee AI)
+# =============================================================================
+# Arcee AI provides access to Trinity models (trinity-mini, trinity-large-*)
+# Get an Arcee key at: https://chat.arcee.ai/
+# ARCEEAI_API_KEY=
+# ARCEE_BASE_URL=                                 # Override default base URL
 
 # =============================================================================
 # LLM PROVIDER (MiniMax)
@@ -79,8 +112,13 @@
 # Get your token at: https://huggingface.co/settings/tokens
 # Required permission: "Make calls to Inference Providers"
 # HF_TOKEN=
+# HF_BASE_URL=https://router.huggingface.co/v1  # Override default base URL
 # OPENCODE_GO_BASE_URL=https://opencode.ai/zen/go/v1  # Override default base URL
 
+# DeepInfra — 100+ top open models, pay-per-use.
+# Get your key at: https://deepinfra.com/dash/api_keys
+# DEEPINFRA_API_KEY=
+
 # =============================================================================
 # LLM PROVIDER (Qwen OAuth)
 # =============================================================================
@@ -98,6 +136,15 @@
 # Optional base URL override:
 # XIAOMI_BASE_URL=https://api.xiaomimimo.com/v1
 
+# =============================================================================
+# LLM PROVIDER (Upstage Solar)
+# =============================================================================
+# Upstage provides access to Upstage Solar models.
+# Get your key at: https://console.upstage.ai/api-keys
+# UPSTAGE_API_KEY=your_key_here
+# Optional base URL override:
+# UPSTAGE_BASE_URL=https://api.upstage.ai/v1
+
 # =============================================================================
 # TOOL API KEYS
 # =============================================================================
@@ -125,6 +172,18 @@
 # Also requires ~/.honcho/config.json with enabled=true (see README).
 # HONCHO_API_KEY=
 
+# =============================================================================
+# HYPERLIQUID OPTIONAL SKILL
+# =============================================================================
+# Optional defaults for the Hyperliquid skill in optional-skills/blockchain/hyperliquid
+#
+# Hyperliquid API base URL override
+# Default: https://api.hyperliquid.xyz
+# HYPERLIQUID_API_URL=https://api.hyperliquid-testnet.xyz
+#
+# Default address for account-level commands like state, fills, orders, and review
+# HYPERLIQUID_USER_ADDRESS=0x0000000000000000000000000000000000000000
+
 # =============================================================================
 # TERMINAL TOOL CONFIGURATION
 # =============================================================================
@@ -136,6 +195,10 @@
 # Only override here if you need to force a backend without touching config.yaml:
 # TERMINAL_ENV=local
 
+# Override the container runtime binary (e.g. to use Podman instead of Docker).
+# Useful on systems where Docker's storage driver is broken or unavailable.
+# HERMES_DOCKER_BINARY=/usr/local/bin/podman
+
 # Container images (for singularity/docker/modal backends)
 # TERMINAL_DOCKER_IMAGE=nikolaik/python-nodejs:python3.11-nodejs20
 # TERMINAL_SINGULARITY_IMAGE=docker://nikolaik/python-nodejs:python3.11-nodejs20
@@ -222,6 +285,15 @@ BROWSERBASE_PROXIES=true
 # Uses custom Chromium build to avoid bot detection altogether
 BROWSERBASE_ADVANCED_STEALTH=false
 
+# Browser engine for local mode (default: auto = Chrome)
+# "auto"       — use Chrome (don't pass --engine flag)
+# "lightpanda" — use Lightpanda (1.3-5.8x faster navigation, no screenshots)
+# "chrome"     — explicitly request Chrome
+# Requires agent-browser v0.25.3+. Lightpanda commands that fail or return
+# empty results are automatically retried with Chrome.
+# Also configurable via browser.engine in config.yaml.
+# AGENT_BROWSER_ENGINE=auto
+
 # Browser session timeout in seconds (default: 300)
 # Sessions are cleaned up after this duration of inactivity
 BROWSER_SESSION_TIMEOUT=300
@@ -230,6 +302,27 @@ BROWSER_SESSION_TIMEOUT=300
 # Browser sessions are automatically closed after this period of no activity
 BROWSER_INACTIVITY_TIMEOUT=120
 
+# Extra Chromium launch flags passed to agent-browser, comma- or newline-separated.
+# Hermes auto-injects "--no-sandbox,--disable-dev-shm-usage" when it detects root
+# or AppArmor-restricted unprivileged user namespaces (Ubuntu 23.10+, DGX Spark,
+# many container images), so leave this unset unless you need extra flags.
+# Setting this disables the auto-injection.
+# AGENT_BROWSER_ARGS=--no-sandbox
+
+# Camofox local anti-detection browser (Camoufox-based Firefox).
+# Set CAMOFOX_URL to route the browser tools through a local Camofox server
+# instead of agent-browser/Browserbase. See docs/user-guide/features/browser.md.
+# CAMOFOX_URL=http://localhost:9377
+
+# Externally managed Camofox sessions — when another app owns the visible
+# Camofox browser, set these so Hermes shares the same userId/profile instead
+# of creating its own isolated session.
+# CAMOFOX_USER_ID=
+# CAMOFOX_SESSION_KEY=
+# Set to true to reuse an already-open Camofox tab for this identity before
+# creating a new one (useful for gateway restarts).
+# CAMOFOX_ADOPT_EXISTING_TAB=false
+
 # =============================================================================
 # SESSION LOGGING
 # =============================================================================
@@ -267,6 +360,7 @@ BROWSER_INACTIVITY_TIMEOUT=120
 # TELEGRAM_ALLOWED_USERS=                  # Comma-separated user IDs
 # TELEGRAM_HOME_CHANNEL=                   # Default chat for cron delivery
 # TELEGRAM_HOME_CHANNEL_NAME=              # Display name for home channel
+# TELEGRAM_CRON_THREAD_ID=                 # Forum topic ID for cron deliveries; overrides TELEGRAM_HOME_CHANNEL_THREAD_ID for cron so replies work in topic mode
 
 # Webhook mode (optional — for cloud deployments like Fly.io/Railway)
 # Default is long polling. Setting TELEGRAM_WEBHOOK_URL switches to webhook mode.
@@ -322,24 +416,6 @@ IMAGE_TOOLS_DEBUG=false
 # CONTEXT_COMPRESSION_THRESHOLD=0.85      # Compress at 85% of context limit
 # Model is set via compression.summary_model in config.yaml (default: google/gemini-3-flash-preview)
 
-# =============================================================================
-# RL TRAINING (Tinker + Atropos)
-# =============================================================================
-# Run reinforcement learning training on language models using the Tinker API.
-# Requires the rl-server to be running (from tinker-atropos package).
-
-# Tinker API Key - RL training service
-# Get at: https://tinker-console.thinkingmachines.ai/keys
-# TINKER_API_KEY=
-
-# Weights & Biases API Key - Experiment tracking and metrics
-# Get at: https://wandb.ai/authorize
-# WANDB_API_KEY=
-
-# RL API Server URL (default: http://localhost:8080)
-# Change if running the rl-server on a different host/port
-# RL_API_URL=http://localhost:8080
-
 # =============================================================================
 # SKILLS HUB (GitHub integration for skill search/install/publish)
 # =============================================================================
@@ -356,23 +432,65 @@ IMAGE_TOOLS_DEBUG=false
 # Groq API key (free tier — used for Whisper STT in voice mode)
 # GROQ_API_KEY=
 
+# ElevenLabs API key (cloud STT/TTS — Scribe transcription)
+# ELEVENLABS_API_KEY=
+
 # =============================================================================
 # STT PROVIDER SELECTION
 # =============================================================================
 # Default STT provider is "local" (faster-whisper) — runs on your machine, no API key needed.
 # Install with: pip install faster-whisper
 # Model downloads automatically on first use (~150 MB for "base").
-# To use cloud providers instead, set GROQ_API_KEY or VOICE_TOOLS_OPENAI_KEY above.
-# Provider priority: local > groq > openai
-# Configure in config.yaml: stt.provider: local | groq | openai
+# To use cloud providers instead, set GROQ_API_KEY, VOICE_TOOLS_OPENAI_KEY, or ELEVENLABS_API_KEY above.
+# Provider priority: local > groq > openai > mistral > xai > elevenlabs
+# Configure in config.yaml: stt.provider: local | groq | openai | mistral | xai | elevenlabs
 
 # =============================================================================
 # STT ADVANCED OVERRIDES (optional)
 # =============================================================================
 # Override default STT models per provider (normally set via stt.model in config.yaml)
 # STT_GROQ_MODEL=whisper-large-v3-turbo
 # STT_OPENAI_MODEL=whisper-1
+# STT_ELEVENLABS_MODEL=scribe_v2
 
 # Override STT provider endpoints (for proxies or self-hosted instances)
 # GROQ_BASE_URL=https://api.groq.com/openai/v1
 # STT_OPENAI_BASE_URL=https://api.openai.com/v1
+# ELEVENLABS_STT_BASE_URL=https://api.elevenlabs.io/v1
+
+# =============================================================================
+# MICROSOFT TEAMS INTEGRATION
+# =============================================================================
+# Register a Bot in Azure: https://dev.botframework.com/ → "Register a bot"
+# Or use Azure Portal: Azure Active Directory → App registrations → New registration
+# Then add the bot to Teams via the Bot Framework or App Studio.
+#
+# TEAMS_CLIENT_ID=                     # Azure AD App (client) ID
+# TEAMS_CLIENT_SECRET=                 # Azure AD client secret value
+# TEAMS_TENANT_ID=                     # Azure AD tenant ID (or "common" for multi-tenant)
+# TEAMS_ALLOWED_USERS=                 # Comma-separated AAD object IDs or UPNs
+# TEAMS_ALLOW_ALL_USERS=false          # Set true to skip the allowlist
+# TEAMS_HOME_CHANNEL=                  # Default channel/chat ID for cron delivery
+# TEAMS_HOME_CHANNEL_NAME=             # Display name for the home channel
+# TEAMS_PORT=3978                      # Webhook listen port (Bot Framework default)
+
+# =============================================================================
+# GOOGLE CHAT INTEGRATION
+# =============================================================================
+# Connects via Cloud Pub/Sub pull subscription (no public URL required).
+# Setup walkthrough: website/docs/user-guide/messaging/google_chat.md.
+# 1. Create a GCP project, enable the Google Chat API and Cloud Pub/Sub.
+# 2. Create a Service Account with roles/pubsub.subscriber on the
+#    subscription (NOT project-wide); download the JSON key.
+# 3. Configure your Chat app at console.cloud.google.com/apis/credentials
+#    → Google Chat API → Configuration → Cloud Pub/Sub topic.
+# 4. (Optional, for native attachment delivery) Each user runs
+#    `/setup-files` once in their own DM after Pub/Sub is wired up.
+#
+# GOOGLE_CHAT_PROJECT_ID=                       # GCP project hosting the topic (or set GOOGLE_CLOUD_PROJECT)
+# GOOGLE_CHAT_SUBSCRIPTION_NAME=                # Full path: projects/<id>/subscriptions/<name>
+# GOOGLE_CHAT_SERVICE_ACCOUNT_JSON=             # Path to SA JSON (or set GOOGLE_APPLICATION_CREDENTIALS)
+# GOOGLE_CHAT_ALLOWED_USERS=                    # Comma-separated emails allowed to talk to the bot
+# GOOGLE_CHAT_ALLOW_ALL_USERS=false             # Set true to skip the allowlist
+# GOOGLE_CHAT_HOME_CHANNEL=                     # Default space (spaces/XXXX) for cron delivery
+# GOOGLE_CHAT_HOME_CHANNEL_NAME=                # Display name for the home channel

.envrc

@@ -1 +1,5 @@
+watch_file pyproject.toml uv.lock hermes
+watch_file package-lock.json package.json web/package.json ui-tui/package.json website/package.json apps/shared/package.json apps/desktop/package.json ui-tui/packages/hermes-ink/package.json
+watch_file flake.nix flake.lock nix/devShell.nix nix/tui.nix nix/package.nix nix/python.nix nix/hermes-agent.nix nix/desktop.nix
+
 use flake