fix: add explicit hermes-api-server toolset for API server platform

The API server adapter was creating agents without specifying enabled_toolsets, causing ALL tools from ALL toolsets to be loaded (including clarify, send_message, and text_to_speech which don't work without interactive callbacks or gateway dispatch). This could confuse models by presenting too many irrelevant tools, and meant the platform_toolsets config override didn't apply to API server. Changes: - Add hermes-api-server toolset to toolsets.py with appropriate tools (web, terminal, files, browser, vision, skills, HA tools, etc.) but excluding clarify, send_message, and text_to_speech - Update _create_agent() in api_server.py to use enabled_toolsets=[hermes-api-server] - Add api_server to PLATFORMS dict in tools_config.py for config override support - Add tests for toolset definition, tool inclusion/exclusion, and adapter wiring
2026-03-26 16:04:39 -07:00
441 changed files with 5747 additions and 55673 deletions
@@ -1,15 +0,0 @@
-# Git
-.git
-.gitignore
-.gitmodules
-
-# Dependencies
-node_modules
-
-# CI/CD
-.github
-
-# Environment files
-.env
-
-*.md
@@ -7,19 +7,18 @@
 # OpenRouter provides access to many models through one API
 # All LLM calls go through OpenRouter - no direct provider keys needed
 # Get your key at: https://openrouter.ai/keys
-# OPENROUTER_API_KEY=
+OPENROUTER_API_KEY=

-# Default model is configured in ~/.hermes/config.yaml (model.default).
-# Use 'hermes model' or 'hermes setup' to change it.
-# LLM_MODEL is no longer read from .env — this line is kept for reference only.
-# LLM_MODEL=anthropic/claude-opus-4.6
+# Default model to use (OpenRouter format: provider/model)
+# Examples: anthropic/claude-opus-4.6, openai/gpt-4o, google/gemini-3-flash-preview, zhipuai/glm-4-plus
+LLM_MODEL=anthropic/claude-opus-4.6

 # =============================================================================
 # LLM PROVIDER (z.ai / GLM)
 # =============================================================================
 # z.ai provides access to ZhipuAI GLM models (GLM-4-Plus, etc.)
 # Get your key at: https://z.ai or https://open.bigmodel.cn
-# GLM_API_KEY=
+GLM_API_KEY=
 # GLM_BASE_URL=https://api.z.ai/api/paas/v4  # Override default base URL

 # =============================================================================
@@ -29,7 +28,7 @@
 # Get your key at: https://platform.kimi.ai (Kimi Code console)
 # Keys prefixed sk-kimi- use the Kimi Code API (api.kimi.com) by default.
 # Legacy keys from platform.moonshot.ai need KIMI_BASE_URL override below.
-# KIMI_API_KEY=
+KIMI_API_KEY=
 # 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
@@ -39,11 +38,11 @@
 # =============================================================================
 # MiniMax provides access to MiniMax models (global endpoint)
 # Get your key at: https://www.minimax.io
-# MINIMAX_API_KEY=
+MINIMAX_API_KEY=
 # MINIMAX_BASE_URL=https://api.minimax.io/v1  # Override default base URL

 # MiniMax China endpoint (for users in mainland China)
-# MINIMAX_CN_API_KEY=
+MINIMAX_CN_API_KEY=
 # MINIMAX_CN_BASE_URL=https://api.minimaxi.com/v1  # Override default base URL

 # =============================================================================
@@ -51,7 +50,7 @@
 # =============================================================================
 # OpenCode Zen provides curated, tested models (GPT, Claude, Gemini, MiniMax, GLM, Kimi)
 # Pay-as-you-go pricing. Get your key at: https://opencode.ai/auth
-# OPENCODE_ZEN_API_KEY=
+OPENCODE_ZEN_API_KEY=
 # OPENCODE_ZEN_BASE_URL=https://opencode.ai/zen/v1  # Override default base URL

 # =============================================================================
@@ -59,47 +58,34 @@
 # =============================================================================
 # OpenCode Go provides access to open models (GLM-5, Kimi K2.5, MiniMax M2.5)
 # $10/month subscription. Get your key at: https://opencode.ai/auth
-# OPENCODE_GO_API_KEY=
-
-# =============================================================================
-# LLM PROVIDER (Hugging Face Inference Providers)
-# =============================================================================
-# Hugging Face routes to 20+ open models via unified OpenAI-compatible endpoint.
-# Free tier included ($0.10/month), no markup on provider rates.
-# Get your token at: https://huggingface.co/settings/tokens
-# Required permission: "Make calls to Inference Providers"
-# HF_TOKEN=
+OPENCODE_GO_API_KEY=
 # OPENCODE_GO_BASE_URL=https://opencode.ai/zen/go/v1  # Override default base URL

 # =============================================================================
 # TOOL API KEYS
 # =============================================================================

-# Exa API Key - AI-native web search and contents
-# Get at: https://exa.ai
-# EXA_API_KEY=
-
 # Parallel API Key - AI-native web search and extract
 # Get at: https://parallel.ai
-# PARALLEL_API_KEY=
+PARALLEL_API_KEY=

 # Firecrawl API Key - Web search, extract, and crawl
 # Get at: https://firecrawl.dev/
-# FIRECRAWL_API_KEY=
+FIRECRAWL_API_KEY=


 # FAL.ai API Key - Image generation
 # Get at: https://fal.ai/
-# FAL_KEY=
+FAL_KEY=

 # Honcho - Cross-session AI-native user modeling (optional)
 # Builds a persistent understanding of the user across sessions and tools.
 # Get at: https://app.honcho.dev
 # Also requires ~/.honcho/config.json with enabled=true (see README).
-# HONCHO_API_KEY=
+HONCHO_API_KEY=

 # =============================================================================
-# TERMINAL TOOL CONFIGURATION
+# TERMINAL TOOL CONFIGURATION (mini-swe-agent backend)
 # =============================================================================
 # Backend type: "local", "singularity", "docker", "modal", or "ssh"
 # Terminal backend is configured in ~/.hermes/config.yaml (terminal.backend).
@@ -182,10 +168,10 @@ TERMINAL_LIFETIME_SECONDS=300

 # Browserbase API Key - Cloud browser execution
 # Get at: https://browserbase.com/
-# BROWSERBASE_API_KEY=
+BROWSERBASE_API_KEY=

 # Browserbase Project ID - From your Browserbase dashboard
-# BROWSERBASE_PROJECT_ID=
+BROWSERBASE_PROJECT_ID=

 # Enable residential proxies for better CAPTCHA solving (default: true)
 # Routes traffic through residential IPs, significantly improves success rate
@@ -217,7 +203,7 @@ BROWSER_INACTIVITY_TIMEOUT=120
 # Uses OpenAI's API directly (not via OpenRouter).
 # Named VOICE_TOOLS_OPENAI_KEY to avoid interference with OpenRouter.
 # Get at: https://platform.openai.com/api-keys
-# VOICE_TOOLS_OPENAI_KEY=
+VOICE_TOOLS_OPENAI_KEY=

 # =============================================================================
 # SLACK INTEGRATION
@@ -232,21 +218,6 @@ BROWSER_INACTIVITY_TIMEOUT=120
 # Slack allowed users (comma-separated Slack user IDs)
 # SLACK_ALLOWED_USERS=

-# =============================================================================
-# TELEGRAM INTEGRATION
-# =============================================================================
-# Telegram Bot Token - From @BotFather (https://t.me/BotFather)
-# TELEGRAM_BOT_TOKEN=
-# TELEGRAM_ALLOWED_USERS=                  # Comma-separated user IDs
-# TELEGRAM_HOME_CHANNEL=                   # Default chat for cron delivery
-# TELEGRAM_HOME_CHANNEL_NAME=              # Display name for home channel
-
-# Webhook mode (optional — for cloud deployments like Fly.io/Railway)
-# Default is long polling. Setting TELEGRAM_WEBHOOK_URL switches to webhook mode.
-# TELEGRAM_WEBHOOK_URL=https://my-app.fly.dev/telegram
-# TELEGRAM_WEBHOOK_PORT=8443
-# TELEGRAM_WEBHOOK_SECRET=                 # Recommended for production
-
 # WhatsApp (built-in Baileys bridge — run `hermes whatsapp` to pair)
 # WHATSAPP_ENABLED=false
 # WHATSAPP_ALLOWED_USERS=15551234567
@@ -303,11 +274,11 @@ IMAGE_TOOLS_DEBUG=false

 # Tinker API Key - RL training service
 # Get at: https://tinker-console.thinkingmachines.ai/keys
-# TINKER_API_KEY=
+TINKER_API_KEY=

 # Weights & Biases API Key - Experiment tracking and metrics
 # Get at: https://wandb.ai/authorize
-# WANDB_API_KEY=
+WANDB_API_KEY=

 # RL API Server URL (default: http://localhost:8080)
 # Change if running the rl-server on a different host/port
@@ -19,8 +19,6 @@ concurrency:

 jobs:
  build-and-deploy:
-    # Only run on the upstream repository, not on forks
-    if: github.repository == 'NousResearch/hermes-agent'
    runs-on: ubuntu-latest
    environment:
      name: github-pages
@@ -1,79 +0,0 @@
-name: Docker Build and Publish
-
-on:
-  push:
-    branches: [main]
-  pull_request:
-    branches: [main]
-  release:
-    types: [published]
-
-concurrency:
-  group: docker-${{ github.ref }}
-  cancel-in-progress: true
-
-jobs:
-  build-and-push:
-    # Only run on the upstream repository, not on forks
-    if: github.repository == 'NousResearch/hermes-agent'
-    runs-on: ubuntu-latest
-    timeout-minutes: 30
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v4
-        with:
-          submodules: recursive
-
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
-
-      - name: Build image
-        uses: docker/build-push-action@v6
-        with:
-          context: .
-          file: Dockerfile
-          load: true
-          tags: nousresearch/hermes-agent:test
-          cache-from: type=gha
-          cache-to: type=gha,mode=max
-
-      - name: Test image starts
-        run: |
-          docker run --rm \
-            -v /tmp/hermes-test:/opt/data \
-            --entrypoint /opt/hermes/docker/entrypoint.sh \
-            nousresearch/hermes-agent:test --help
-
-      - name: Log in to Docker Hub
-        if: github.event_name == 'push' && github.ref == 'refs/heads/main' || github.event_name == 'release'
-        uses: docker/login-action@v3
-        with:
-          username: ${{ secrets.DOCKERHUB_USERNAME }}
-          password: ${{ secrets.DOCKERHUB_TOKEN }}
-
-      - name: Push image (main branch)
-        if: github.event_name == 'push' && github.ref == 'refs/heads/main'
-        uses: docker/build-push-action@v6
-        with:
-          context: .
-          file: Dockerfile
-          push: true
-          tags: |
-            nousresearch/hermes-agent:latest
-            nousresearch/hermes-agent:${{ github.sha }}
-          cache-from: type=gha
-          cache-to: type=gha,mode=max
-
-      - name: Push image (release)
-        if: github.event_name == 'release'
-        uses: docker/build-push-action@v6
-        with:
-          context: .
-          file: Dockerfile
-          push: true
-          tags: |
-            nousresearch/hermes-agent:latest
-            nousresearch/hermes-agent:${{ github.event.release.tag_name }}
-            nousresearch/hermes-agent:${{ github.sha }}
-          cache-from: type=gha
-          cache-to: type=gha,mode=max
@@ -210,10 +210,6 @@ registry.register(

 The registry handles schema collection, dispatch, availability checking, and error wrapping. All handlers MUST return a JSON string.

-**Path references in tool schemas**: If the schema description mentions file paths (e.g. default output directories), use `display_hermes_home()` to make them profile-aware. The schema is generated at import time, which is after `_apply_profile_override()` sets `HERMES_HOME`.
-
-**State files**: If a tool stores persistent state (caches, logs, checkpoints), use `get_hermes_home()` for the base directory — never `Path.home() / ".hermes"`. This ensures each profile gets its own state.
-
 **Agent-level tools** (todo, memory): intercepted by `run_agent.py` before `handle_function_call()`. See `todo_tool.py` for the pattern.

 ---
@@ -362,69 +358,8 @@ in config.yaml (or `HERMES_BACKGROUND_NOTIFICATIONS` env var):

 ---

-## Profiles: Multi-Instance Support
-
-Hermes supports **profiles** — multiple fully isolated instances, each with its own
-`HERMES_HOME` directory (config, API keys, memory, sessions, skills, gateway, etc.).
-
-The core mechanism: `_apply_profile_override()` in `hermes_cli/main.py` sets
-`HERMES_HOME` before any module imports. All 119+ references to `get_hermes_home()`
-automatically scope to the active profile.
-
-### Rules for profile-safe code
-
-1. **Use `get_hermes_home()` for all HERMES_HOME paths.** Import from `hermes_constants`.
-   NEVER hardcode `~/.hermes` or `Path.home() / ".hermes"` in code that reads/writes state.
-   ```python
-   # GOOD
-   from hermes_constants import get_hermes_home
-   config_path = get_hermes_home() / "config.yaml"
-
-   # BAD — breaks profiles
-   config_path = Path.home() / ".hermes" / "config.yaml"
-   ```
-
-2. **Use `display_hermes_home()` for user-facing messages.** Import from `hermes_constants`.
-   This returns `~/.hermes` for default or `~/.hermes/profiles/<name>` for profiles.
-   ```python
-   # GOOD
-   from hermes_constants import display_hermes_home
-   print(f"Config saved to {display_hermes_home()}/config.yaml")
-
-   # BAD — shows wrong path for profiles
-   print("Config saved to ~/.hermes/config.yaml")
-   ```
-
-3. **Module-level constants are fine** — they cache `get_hermes_home()` at import time,
-   which is AFTER `_apply_profile_override()` sets the env var. Just use `get_hermes_home()`,
-   not `Path.home() / ".hermes"`.
-
-4. **Tests that mock `Path.home()` must also set `HERMES_HOME`** — since code now uses
-   `get_hermes_home()` (reads env var), not `Path.home() / ".hermes"`:
-   ```python
-   with patch.object(Path, "home", return_value=tmp_path), \
-        patch.dict(os.environ, {"HERMES_HOME": str(tmp_path / ".hermes")}):
-       ...
-   ```
-
-5. **Gateway platform adapters should use token locks** — if the adapter connects with
-   a unique credential (bot token, API key), call `acquire_scoped_lock()` from
-   `gateway.status` in the `connect()`/`start()` method and `release_scoped_lock()` in
-   `disconnect()`/`stop()`. This prevents two profiles from using the same credential.
-   See `gateway/platforms/telegram.py` for the canonical pattern.
-
-6. **Profile operations are HOME-anchored, not HERMES_HOME-anchored** — `_get_profiles_root()`
-   returns `Path.home() / ".hermes" / "profiles"`, NOT `get_hermes_home() / "profiles"`.
-   This is intentional — it lets `hermes -p coder profile list` see all profiles regardless
-   of which one is active.
-
 ## Known Pitfalls

-### DO NOT hardcode `~/.hermes` paths
-Use `get_hermes_home()` from `hermes_constants` for code paths. Use `display_hermes_home()`
-for user-facing print/log messages. Hardcoding `~/.hermes` breaks profiles — each profile
-has its own `HERMES_HOME` directory. This was the source of 5 bugs fixed in PR #3575.
-
 ### DO NOT use `simple_term_menu` for interactive menus
 Rendering bugs in tmux/iTerm2 — ghosting on scroll. Use `curses` (stdlib) instead. See `hermes_cli/tools_config.py` for the pattern.

@@ -440,19 +375,6 @@ Tool schema descriptions must not mention tools from other toolsets by name (e.g
 ### Tests must not write to `~/.hermes/`
 The `_isolate_hermes_home` autouse fixture in `tests/conftest.py` redirects `HERMES_HOME` to a temp dir. Never hardcode `~/.hermes/` paths in tests.

-**Profile tests**: When testing profile features, also mock `Path.home()` so that
-`_get_profiles_root()` and `_get_default_hermes_home()` resolve within the temp dir.
-Use the pattern from `tests/hermes_cli/test_profiles.py`:
-```python
-@pytest.fixture
-def profile_env(tmp_path, monkeypatch):
-    home = tmp_path / ".hermes"
-    home.mkdir()
-    monkeypatch.setattr(Path, "home", lambda: tmp_path)
-    monkeypatch.setenv("HERMES_HOME", str(home))
-    return home
-```
-
 ---

 ## Testing
@@ -1,25 +0,0 @@
-FROM debian:13.4
-
-# Install system dependencies in one layer, clear APT cache
-RUN apt-get update && \
-    apt-get install -y --no-install-recommends \
-        build-essential nodejs npm python3 python3-pip ripgrep ffmpeg gcc python3-dev libffi-dev && \
-    rm -rf /var/lib/apt/lists/*
-
-COPY . /opt/hermes
-WORKDIR /opt/hermes
-
-# Install Python and Node dependencies in one layer, no cache
-RUN pip install --no-cache-dir -e ".[all]" --break-system-packages && \
-    npm install --prefer-offline --no-audit && \
-    npx playwright install --with-deps chromium --only-shell && \
-    cd /opt/hermes/scripts/whatsapp-bridge && \
-    npm install --prefer-offline --no-audit && \
-    npm cache clean --force
-
-WORKDIR /opt/hermes
-RUN chmod +x /opt/hermes/docker/entrypoint.sh
-
-ENV HERMES_HOME=/opt/data
-VOLUME [ "/opt/data" ]
-ENTRYPOINT [ "/opt/hermes/docker/entrypoint.sh" ]
@@ -1,4 +0,0 @@
-graft skills
-graft optional-skills
-global-exclude __pycache__
-global-exclude *.py[cod]
@@ -1,348 +0,0 @@
-# Hermes Agent v0.5.0 (v2026.3.28)
-
-**Release Date:** March 28, 2026
-
-> The hardening release — Hugging Face provider, /model command overhaul, Telegram Private Chat Topics, native Modal SDK, plugin lifecycle hooks, tool-use enforcement for GPT models, Nix flake, 50+ security and reliability fixes, and a comprehensive supply chain audit.
-
---
-
-## ✨ Highlights
-
- **Nous Portal now supports 400+ models** — The Nous Research inference portal has expanded dramatically, giving Hermes Agent users access to over 400 models through a single provider endpoint
-
- **Hugging Face as a first-class inference provider** — Full integration with HF Inference API including curated agentic model picker that maps to OpenRouter analogues, live `/models` endpoint probe, and setup wizard flow ([#3419](https://github.com/NousResearch/hermes-agent/pull/3419), [#3440](https://github.com/NousResearch/hermes-agent/pull/3440))
-
- **Telegram Private Chat Topics** — Project-based conversations with functional skill binding per topic, enabling isolated workflows within a single Telegram chat ([#3163](https://github.com/NousResearch/hermes-agent/pull/3163))
-
- **Native Modal SDK backend** — Replaced swe-rex dependency with native Modal SDK (`Sandbox.create.aio` + `exec.aio`), eliminating tunnels and simplifying the Modal terminal backend ([#3538](https://github.com/NousResearch/hermes-agent/pull/3538))
-
- **Plugin lifecycle hooks activated** — `pre_llm_call`, `post_llm_call`, `on_session_start`, and `on_session_end` hooks now fire in the agent loop and CLI/gateway, completing the plugin hook system ([#3542](https://github.com/NousResearch/hermes-agent/pull/3542))
-
- **Improved OpenAI Model Reliability** — Added `GPT_TOOL_USE_GUIDANCE` to prevent GPT models from describing intended actions instead of making tool calls, plus automatic stripping of stale budget warnings from conversation history that caused models to avoid tools across turns ([#3528](https://github.com/NousResearch/hermes-agent/pull/3528))
-
- **Nix flake** — Full uv2nix build, NixOS module with persistent container mode, auto-generated config keys from Python source, and suffix PATHs for agent-friendliness ([#20](https://github.com/NousResearch/hermes-agent/pull/20), [#3274](https://github.com/NousResearch/hermes-agent/pull/3274), [#3061](https://github.com/NousResearch/hermes-agent/pull/3061)) by @alt-glitch
-
- **Supply chain hardening** — Removed compromised `litellm` dependency, pinned all dependency version ranges, regenerated `uv.lock` with hashes, added CI workflow scanning PRs for supply chain attack patterns, and bumped deps to fix CVEs ([#2796](https://github.com/NousResearch/hermes-agent/pull/2796), [#2810](https://github.com/NousResearch/hermes-agent/pull/2810), [#2812](https://github.com/NousResearch/hermes-agent/pull/2812), [#2816](https://github.com/NousResearch/hermes-agent/pull/2816), [#3073](https://github.com/NousResearch/hermes-agent/pull/3073))
-
- **Anthropic output limits fix** — Replaced hardcoded 16K `max_tokens` with per-model native output limits (128K for Opus 4.6, 64K for Sonnet 4.6), fixing "Response truncated" and thinking-budget exhaustion on direct Anthropic API ([#3426](https://github.com/NousResearch/hermes-agent/pull/3426), [#3444](https://github.com/NousResearch/hermes-agent/pull/3444))
-
---
-
-## 🏗️ Core Agent & Architecture
-
-### New Provider: Hugging Face
- First-class Hugging Face Inference API integration with auth, setup wizard, and model picker ([#3419](https://github.com/NousResearch/hermes-agent/pull/3419))
- Curated model list mapping OpenRouter agentic defaults to HF equivalents — providers with 8+ curated models skip live `/models` probe for speed ([#3440](https://github.com/NousResearch/hermes-agent/pull/3440))
- Added glm-5-turbo to Z.AI provider model list ([#3095](https://github.com/NousResearch/hermes-agent/pull/3095))
-
-### Provider & Model Improvements
- `/model` command overhaul — extracted shared `switch_model()` pipeline for CLI and gateway, custom endpoint support, provider-aware routing ([#2795](https://github.com/NousResearch/hermes-agent/pull/2795), [#2799](https://github.com/NousResearch/hermes-agent/pull/2799))
- Removed `/model` slash command from CLI and gateway in favor of `hermes model` subcommand ([#3080](https://github.com/NousResearch/hermes-agent/pull/3080))
- Preserve `custom` provider instead of silently remapping to `openrouter` ([#2792](https://github.com/NousResearch/hermes-agent/pull/2792))
- Read root-level `provider` and `base_url` from config.yaml into model config ([#3112](https://github.com/NousResearch/hermes-agent/pull/3112))
- Align Nous Portal model slugs with OpenRouter naming ([#3253](https://github.com/NousResearch/hermes-agent/pull/3253))
- Fix Alibaba provider default endpoint and model list ([#3484](https://github.com/NousResearch/hermes-agent/pull/3484))
- Allow MiniMax users to override `/v1` → `/anthropic` auto-correction ([#3553](https://github.com/NousResearch/hermes-agent/pull/3553))
- Migrate OAuth token refresh to `platform.claude.com` with fallback ([#3246](https://github.com/NousResearch/hermes-agent/pull/3246))
-
-### Agent Loop & Conversation
- **Improved OpenAI model reliability** — `GPT_TOOL_USE_GUIDANCE` prevents GPT models from describing actions instead of calling tools + automatic budget warning stripping from history ([#3528](https://github.com/NousResearch/hermes-agent/pull/3528))
- **Surface lifecycle events** — All retry, fallback, and compression events now surface to the user as formatted messages ([#3153](https://github.com/NousResearch/hermes-agent/pull/3153))
- **Anthropic output limits** — Per-model native output limits instead of hardcoded 16K `max_tokens` ([#3426](https://github.com/NousResearch/hermes-agent/pull/3426))
- **Thinking-budget exhaustion detection** — Skip useless continuation retries when model uses all output tokens on reasoning ([#3444](https://github.com/NousResearch/hermes-agent/pull/3444))
- Always prefer streaming for API calls to prevent hung subagents ([#3120](https://github.com/NousResearch/hermes-agent/pull/3120))
- Restore safe non-streaming fallback after stream failures ([#3020](https://github.com/NousResearch/hermes-agent/pull/3020))
- Give subagents independent iteration budgets ([#3004](https://github.com/NousResearch/hermes-agent/pull/3004))
- Update `api_key` in `_try_activate_fallback` for subagent auth ([#3103](https://github.com/NousResearch/hermes-agent/pull/3103))
- Graceful return on max retries instead of crashing thread ([untagged commit](https://github.com/NousResearch/hermes-agent))
- Count compression restarts toward retry limit ([#3070](https://github.com/NousResearch/hermes-agent/pull/3070))
- Include tool tokens in preflight estimate, guard context probe persistence ([#3164](https://github.com/NousResearch/hermes-agent/pull/3164))
- Update context compressor limits after fallback activation ([#3305](https://github.com/NousResearch/hermes-agent/pull/3305))
- Validate empty user messages to prevent Anthropic API 400 errors ([#3322](https://github.com/NousResearch/hermes-agent/pull/3322))
- GLM reasoning-only and max-length handling ([#3010](https://github.com/NousResearch/hermes-agent/pull/3010))
- Increase API timeout default from 900s to 1800s for slow-thinking models ([#3431](https://github.com/NousResearch/hermes-agent/pull/3431))
- Send `max_tokens` for Claude/OpenRouter + retry SSE connection errors ([#3497](https://github.com/NousResearch/hermes-agent/pull/3497))
- Prevent AsyncOpenAI/httpx cross-loop deadlock in gateway mode ([#2701](https://github.com/NousResearch/hermes-agent/pull/2701)) by @ctlst
-
-### Streaming & Reasoning
- **Persist reasoning across gateway session turns** with new schema v6 columns (`reasoning`, `reasoning_details`, `codex_reasoning_items`) ([#2974](https://github.com/NousResearch/hermes-agent/pull/2974))
- Detect and kill stale SSE connections ([untagged commit](https://github.com/NousResearch/hermes-agent))
- Fix stale stream detector race causing spurious `RemoteProtocolError` ([untagged commit](https://github.com/NousResearch/hermes-agent))
- Skip duplicate callback for `<think>`-extracted reasoning during streaming ([#3116](https://github.com/NousResearch/hermes-agent/pull/3116))
- Preserve reasoning fields in `rewrite_transcript` ([#3311](https://github.com/NousResearch/hermes-agent/pull/3311))
- Preserve Gemini thought signatures in streamed tool calls ([#2997](https://github.com/NousResearch/hermes-agent/pull/2997))
- Ensure first delta is fired during reasoning updates ([untagged commit](https://github.com/NousResearch/hermes-agent))
-
-### Session & Memory
- **Session search recent sessions mode** — Omit query to browse recent sessions with titles, previews, and timestamps ([#2533](https://github.com/NousResearch/hermes-agent/pull/2533))
- **Session config surfacing** on `/new`, `/reset`, and auto-reset ([#3321](https://github.com/NousResearch/hermes-agent/pull/3321))
- **Third-party session isolation** — `--source` flag for isolating sessions by origin ([#3255](https://github.com/NousResearch/hermes-agent/pull/3255))
- Add `/resume` CLI handler, session log truncation guard, `reopen_session` API ([#3315](https://github.com/NousResearch/hermes-agent/pull/3315))
- Clear compressor summary and turn counter on `/clear` and `/new` ([#3102](https://github.com/NousResearch/hermes-agent/pull/3102))
- Surface silent SessionDB failures that cause session data loss ([#2999](https://github.com/NousResearch/hermes-agent/pull/2999))
- Session search fallback preview on summarization failure ([#3478](https://github.com/NousResearch/hermes-agent/pull/3478))
- Prevent stale memory overwrites by flush agent ([#2687](https://github.com/NousResearch/hermes-agent/pull/2687))
-
-### Context Compression
- Replace dead `summary_target_tokens` with ratio-based scaling ([#2554](https://github.com/NousResearch/hermes-agent/pull/2554))
- Expose `compression.target_ratio`, `protect_last_n`, and `threshold` in `DEFAULT_CONFIG` ([untagged commit](https://github.com/NousResearch/hermes-agent))
- Restore sane defaults and cap summary at 12K tokens ([untagged commit](https://github.com/NousResearch/hermes-agent))
- Preserve transcript on `/compress` and hygiene compression ([#3556](https://github.com/NousResearch/hermes-agent/pull/3556))
- Update context pressure warnings and token estimates after compaction ([untagged commit](https://github.com/NousResearch/hermes-agent))
-
-### Architecture & Dependencies
- **Remove mini-swe-agent dependency** — Inline Docker and Modal backends directly ([#2804](https://github.com/NousResearch/hermes-agent/pull/2804))
- **Replace swe-rex with native Modal SDK** for Modal backend ([#3538](https://github.com/NousResearch/hermes-agent/pull/3538))
- **Plugin lifecycle hooks** — `pre_llm_call`, `post_llm_call`, `on_session_start`, `on_session_end` now fire in the agent loop ([#3542](https://github.com/NousResearch/hermes-agent/pull/3542))
- Fix plugin toolsets invisible in `hermes tools` and standalone processes ([#3457](https://github.com/NousResearch/hermes-agent/pull/3457))
- Consolidate `get_hermes_home()` and `parse_reasoning_effort()` ([#3062](https://github.com/NousResearch/hermes-agent/pull/3062))
- Remove unused Hermes-native PKCE OAuth flow ([#3107](https://github.com/NousResearch/hermes-agent/pull/3107))
- Remove ~100 unused imports across 55 files ([#3016](https://github.com/NousResearch/hermes-agent/pull/3016))
- Fix 154 f-strings, simplify getattr/URL patterns, remove dead code ([#3119](https://github.com/NousResearch/hermes-agent/pull/3119))
-
---
-
-## 📱 Messaging Platforms (Gateway)
-
-### Telegram
- **Private Chat Topics** — Project-based conversations with functional skill binding per topic, enabling isolated workflows within a single Telegram chat ([#3163](https://github.com/NousResearch/hermes-agent/pull/3163))
- **Auto-discover fallback IPs via DNS-over-HTTPS** when `api.telegram.org` is unreachable ([#3376](https://github.com/NousResearch/hermes-agent/pull/3376))
- **Configurable reply threading mode** ([#2907](https://github.com/NousResearch/hermes-agent/pull/2907))
- Fall back to no `thread_id` on "Message thread not found" BadRequest ([#3390](https://github.com/NousResearch/hermes-agent/pull/3390))
- Self-reschedule reconnect when `start_polling` fails after 502 ([#3268](https://github.com/NousResearch/hermes-agent/pull/3268))
-
-### Discord
- Stop phantom typing indicator after agent turn completes ([#3003](https://github.com/NousResearch/hermes-agent/pull/3003))
-
-### Slack
- Send tool call progress messages to correct Slack thread ([#3063](https://github.com/NousResearch/hermes-agent/pull/3063))
- Scope progress thread fallback to Slack only ([#3488](https://github.com/NousResearch/hermes-agent/pull/3488))
-
-### WhatsApp
- Download documents, audio, and video media from messages ([#2978](https://github.com/NousResearch/hermes-agent/pull/2978))
-
-### Matrix
- Add missing Matrix entry in `PLATFORMS` dict ([#3473](https://github.com/NousResearch/hermes-agent/pull/3473))
- Harden e2ee access-token handling ([#3562](https://github.com/NousResearch/hermes-agent/pull/3562))
- Add backoff for `SyncError` in sync loop ([#3280](https://github.com/NousResearch/hermes-agent/pull/3280))
-
-### Signal
- Track SSE keepalive comments as connection activity ([#3316](https://github.com/NousResearch/hermes-agent/pull/3316))
-
-### Email
- Prevent unbounded growth of `_seen_uids` in EmailAdapter ([#3490](https://github.com/NousResearch/hermes-agent/pull/3490))
-
-### Gateway Core
- **Config-gated `/verbose` command** for messaging platforms — toggle tool output verbosity from chat ([#3262](https://github.com/NousResearch/hermes-agent/pull/3262))
- **Background review notifications** delivered to user chat ([#3293](https://github.com/NousResearch/hermes-agent/pull/3293))
- **Retry transient send failures** and notify user on exhaustion ([#3288](https://github.com/NousResearch/hermes-agent/pull/3288))
- Recover from hung agents — `/stop` hard-kills session lock ([#3104](https://github.com/NousResearch/hermes-agent/pull/3104))
- Thread-safe `SessionStore` — protect `_entries` with `threading.Lock` ([#3052](https://github.com/NousResearch/hermes-agent/pull/3052))
- Fix gateway token double-counting with cached agents — use absolute set instead of increment ([#3306](https://github.com/NousResearch/hermes-agent/pull/3306), [#3317](https://github.com/NousResearch/hermes-agent/pull/3317))
- Fingerprint full auth token in agent cache signature ([#3247](https://github.com/NousResearch/hermes-agent/pull/3247))
- Silence background agent terminal output ([#3297](https://github.com/NousResearch/hermes-agent/pull/3297))
- Include per-platform `ALLOW_ALL` and `SIGNAL_GROUP` in startup allowlist check ([#3313](https://github.com/NousResearch/hermes-agent/pull/3313))
- Include user-local bin paths in systemd unit PATH ([#3527](https://github.com/NousResearch/hermes-agent/pull/3527))
- Track background task references in `GatewayRunner` ([#3254](https://github.com/NousResearch/hermes-agent/pull/3254))
- Add request timeouts to HA, Email, Mattermost, SMS adapters ([#3258](https://github.com/NousResearch/hermes-agent/pull/3258))
- Add media download retry to Mattermost, Slack, and base cache ([#3323](https://github.com/NousResearch/hermes-agent/pull/3323))
- Detect virtualenv path instead of hardcoding `venv/` ([#2797](https://github.com/NousResearch/hermes-agent/pull/2797))
- Use `TERMINAL_CWD` for context file discovery, not process cwd ([untagged commit](https://github.com/NousResearch/hermes-agent))
- Stop loading hermes repo AGENTS.md into gateway sessions (~10k wasted tokens) ([#2891](https://github.com/NousResearch/hermes-agent/pull/2891))
-
---
-
-## 🖥️ CLI & User Experience
-
-### Interactive CLI
- **Configurable busy input mode** + fix `/queue` always working ([#3298](https://github.com/NousResearch/hermes-agent/pull/3298))
- **Preserve user input on multiline paste** ([#3065](https://github.com/NousResearch/hermes-agent/pull/3065))
- **Tool generation callback** — streaming "preparing terminal…" updates during tool argument generation ([untagged commit](https://github.com/NousResearch/hermes-agent))
- Show tool progress for substantive tools, not just "preparing" ([untagged commit](https://github.com/NousResearch/hermes-agent))
- Buffer reasoning preview chunks and fix duplicate display ([#3013](https://github.com/NousResearch/hermes-agent/pull/3013))
- Prevent reasoning box from rendering 3x during tool-calling loops ([#3405](https://github.com/NousResearch/hermes-agent/pull/3405))
- Eliminate "Event loop is closed" / "Press ENTER to continue" during idle — three-layer fix with `neuter_async_httpx_del()`, custom exception handler, and stale client cleanup ([#3398](https://github.com/NousResearch/hermes-agent/pull/3398))
- Fix status bar shows 26K instead of 260K for token counts with trailing zeros ([#3024](https://github.com/NousResearch/hermes-agent/pull/3024))
- Fix status bar duplicates and degrades during long sessions ([#3291](https://github.com/NousResearch/hermes-agent/pull/3291))
- Refresh TUI before background task output to prevent status bar overlap ([#3048](https://github.com/NousResearch/hermes-agent/pull/3048))
- Suppress KawaiiSpinner animation under `patch_stdout` ([#2994](https://github.com/NousResearch/hermes-agent/pull/2994))
- Skip KawaiiSpinner when TUI handles tool progress ([#2973](https://github.com/NousResearch/hermes-agent/pull/2973))
- Guard `isatty()` against closed streams via `_is_tty` property ([#3056](https://github.com/NousResearch/hermes-agent/pull/3056))
- Ensure single closure of streaming boxes during tool generation ([untagged commit](https://github.com/NousResearch/hermes-agent))
- Cap context pressure percentage at 100% in display ([#3480](https://github.com/NousResearch/hermes-agent/pull/3480))
- Clean up HTML error messages in CLI display ([#3069](https://github.com/NousResearch/hermes-agent/pull/3069))
- Show HTTP status code and 400 body in API error output ([#3096](https://github.com/NousResearch/hermes-agent/pull/3096))
- Extract useful info from HTML error pages, dump debug on max retries ([untagged commit](https://github.com/NousResearch/hermes-agent))
- Prevent TypeError on startup when `base_url` is None ([#3068](https://github.com/NousResearch/hermes-agent/pull/3068))
- Prevent update crash in non-TTY environments ([#3094](https://github.com/NousResearch/hermes-agent/pull/3094))
- Handle EOFError in sessions delete/prune confirmation prompts ([#3101](https://github.com/NousResearch/hermes-agent/pull/3101))
- Catch KeyboardInterrupt during `flush_memories` on exit and in exit cleanup handlers ([#3025](https://github.com/NousResearch/hermes-agent/pull/3025), [#3257](https://github.com/NousResearch/hermes-agent/pull/3257))
- Guard `.strip()` against None values from YAML config ([#3552](https://github.com/NousResearch/hermes-agent/pull/3552))
- Guard `config.get()` against YAML null values to prevent AttributeError ([#3377](https://github.com/NousResearch/hermes-agent/pull/3377))
- Store asyncio task references to prevent GC mid-execution ([#3267](https://github.com/NousResearch/hermes-agent/pull/3267))
-
-### Setup & Configuration
- Use explicit key mapping for returning-user menu dispatch instead of positional index ([#3083](https://github.com/NousResearch/hermes-agent/pull/3083))
- Use `sys.executable` for pip in update commands to fix PEP 668 ([#3099](https://github.com/NousResearch/hermes-agent/pull/3099))
- Harden `hermes update` against diverged history, non-main branches, and gateway edge cases ([#3492](https://github.com/NousResearch/hermes-agent/pull/3492))
- OpenClaw migration overwrites defaults and setup wizard skips imported sections — fixed ([#3282](https://github.com/NousResearch/hermes-agent/pull/3282))
- Stop recursive AGENTS.md walk, load top-level only ([#3110](https://github.com/NousResearch/hermes-agent/pull/3110))
- Add macOS Homebrew paths to browser and terminal PATH resolution ([#2713](https://github.com/NousResearch/hermes-agent/pull/2713))
- YAML boolean handling for `tool_progress` config ([#3300](https://github.com/NousResearch/hermes-agent/pull/3300))
- Reset default SOUL.md to baseline identity text ([#3159](https://github.com/NousResearch/hermes-agent/pull/3159))
- Reject relative cwd paths for container terminal backends ([untagged commit](https://github.com/NousResearch/hermes-agent))
- Add explicit `hermes-api-server` toolset for API server platform ([#3304](https://github.com/NousResearch/hermes-agent/pull/3304))
- Reorder setup wizard providers — OpenRouter first ([untagged commit](https://github.com/NousResearch/hermes-agent))
-
---
-
-## 🔧 Tool System
-
-### API Server
- **Idempotency-Key support**, body size limit, and OpenAI error envelope ([#2903](https://github.com/NousResearch/hermes-agent/pull/2903))
- Allow Idempotency-Key in CORS headers ([#3530](https://github.com/NousResearch/hermes-agent/pull/3530))
- Cancel orphaned agent + true interrupt on SSE disconnect ([#3427](https://github.com/NousResearch/hermes-agent/pull/3427))
- Fix streaming breaks when agent makes tool calls ([#2985](https://github.com/NousResearch/hermes-agent/pull/2985))
-
-### Terminal & File Operations
- Handle addition-only hunks in V4A patch parser ([#3325](https://github.com/NousResearch/hermes-agent/pull/3325))
- Exponential backoff for persistent shell polling ([#2996](https://github.com/NousResearch/hermes-agent/pull/2996))
- Add timeout to subprocess calls in `context_references` ([#3469](https://github.com/NousResearch/hermes-agent/pull/3469))
-
-### Browser & Vision
- Handle 402 insufficient credits error in vision tool ([#2802](https://github.com/NousResearch/hermes-agent/pull/2802))
- Fix `browser_vision` ignores `auxiliary.vision.timeout` config ([#2901](https://github.com/NousResearch/hermes-agent/pull/2901))
- Make browser command timeout configurable via config.yaml ([#2801](https://github.com/NousResearch/hermes-agent/pull/2801))
-
-### MCP
- MCP toolset resolution for runtime and config ([#3252](https://github.com/NousResearch/hermes-agent/pull/3252))
- Add MCP tool name collision protection ([#3077](https://github.com/NousResearch/hermes-agent/pull/3077))
-
-### Auxiliary LLM
- Guard aux LLM calls against None content + reasoning fallback + retry ([#3449](https://github.com/NousResearch/hermes-agent/pull/3449))
- Catch ImportError from `build_anthropic_client` in vision auto-detection ([#3312](https://github.com/NousResearch/hermes-agent/pull/3312))
-
-### Other Tools
- Add request timeouts to `send_message_tool` HTTP calls ([#3162](https://github.com/NousResearch/hermes-agent/pull/3162)) by @memosr
- Auto-repair `jobs.json` with invalid control characters ([#3537](https://github.com/NousResearch/hermes-agent/pull/3537))
- Enable fine-grained tool streaming for Claude/OpenRouter ([#3497](https://github.com/NousResearch/hermes-agent/pull/3497))
-
---
-
-## 🧩 Skills Ecosystem
-
-### Skills System
- **Env var passthrough** for skills and user config — skills can declare environment variables to pass through ([#2807](https://github.com/NousResearch/hermes-agent/pull/2807))
- Cache skills prompt with shared `skill_utils` module for faster TTFT ([#3421](https://github.com/NousResearch/hermes-agent/pull/3421))
- Avoid redundant file re-read for skill conditions ([#2992](https://github.com/NousResearch/hermes-agent/pull/2992))
- Use Git Trees API to prevent silent subdirectory loss during install ([#2995](https://github.com/NousResearch/hermes-agent/pull/2995))
- Fix skills-sh install for deeply nested repo structures ([#2980](https://github.com/NousResearch/hermes-agent/pull/2980))
- Handle null metadata in skill frontmatter ([untagged commit](https://github.com/NousResearch/hermes-agent))
- Preserve trust for skills-sh identifiers + reduce resolution churn ([#3251](https://github.com/NousResearch/hermes-agent/pull/3251))
- Agent-created skills were incorrectly treated as untrusted community content — fixed ([untagged commit](https://github.com/NousResearch/hermes-agent))
-
-### New Skills
- **G0DM0D3 godmode jailbreaking skill** + docs ([#3157](https://github.com/NousResearch/hermes-agent/pull/3157))
- **Docker management skill** added to optional-skills ([#3060](https://github.com/NousResearch/hermes-agent/pull/3060))
- **OpenClaw migration v2** — 17 new modules, terminal recap for migrating from OpenClaw to Hermes ([#2906](https://github.com/NousResearch/hermes-agent/pull/2906))
-
---
-
-## 🔒 Security & Reliability
-
-### Security Hardening
- **SSRF protection** added to `browser_navigate` ([#3058](https://github.com/NousResearch/hermes-agent/pull/3058))
- **SSRF protection** added to `vision_tools` and `web_tools` (hardened) ([#2679](https://github.com/NousResearch/hermes-agent/pull/2679))
- **Restrict subagent toolsets** to parent's enabled set ([#3269](https://github.com/NousResearch/hermes-agent/pull/3269))
- **Prevent zip-slip path traversal** in self-update ([#3250](https://github.com/NousResearch/hermes-agent/pull/3250))
- **Prevent shell injection** in `_expand_path` via `~user` path suffix ([#2685](https://github.com/NousResearch/hermes-agent/pull/2685))
- **Normalize input** before dangerous command detection ([#3260](https://github.com/NousResearch/hermes-agent/pull/3260))
- Make tirith block verdicts approvable instead of hard-blocking ([#3428](https://github.com/NousResearch/hermes-agent/pull/3428))
- Remove compromised `litellm`/`typer`/`platformdirs` from deps ([#2796](https://github.com/NousResearch/hermes-agent/pull/2796))
- Pin all dependency version ranges ([#2810](https://github.com/NousResearch/hermes-agent/pull/2810))
- Regenerate `uv.lock` with hashes, use lockfile in setup ([#2812](https://github.com/NousResearch/hermes-agent/pull/2812))
- Bump dependencies to fix CVEs + regenerate `uv.lock` ([#3073](https://github.com/NousResearch/hermes-agent/pull/3073))
- Supply chain audit CI workflow for PR scanning ([#2816](https://github.com/NousResearch/hermes-agent/pull/2816))
-
-### Reliability
- **SQLite WAL write-lock contention** causing 15-20s TUI freeze — fixed ([#3385](https://github.com/NousResearch/hermes-agent/pull/3385))
- **SQLite concurrency hardening** + session transcript integrity ([#3249](https://github.com/NousResearch/hermes-agent/pull/3249))
- Prevent recurring cron job re-fire on gateway crash/restart loop ([#3396](https://github.com/NousResearch/hermes-agent/pull/3396))
- Mark cron session as ended after job completes ([#2998](https://github.com/NousResearch/hermes-agent/pull/2998))
-
---
-
-## ⚡ Performance
-
- **TTFT startup optimizations** — salvaged easy-win startup improvements ([#3395](https://github.com/NousResearch/hermes-agent/pull/3395))
- Cache skills prompt with shared `skill_utils` module ([#3421](https://github.com/NousResearch/hermes-agent/pull/3421))
- Avoid redundant file re-read for skill conditions in prompt builder ([#2992](https://github.com/NousResearch/hermes-agent/pull/2992))
-
---
-
-## 🐛 Notable Bug Fixes
-
- Fix gateway token double-counting with cached agents ([#3306](https://github.com/NousResearch/hermes-agent/pull/3306), [#3317](https://github.com/NousResearch/hermes-agent/pull/3317))
- Fix "Event loop is closed" / "Press ENTER to continue" during idle sessions ([#3398](https://github.com/NousResearch/hermes-agent/pull/3398))
- Fix reasoning box rendering 3x during tool-calling loops ([#3405](https://github.com/NousResearch/hermes-agent/pull/3405))
- Fix status bar shows 26K instead of 260K for token counts ([#3024](https://github.com/NousResearch/hermes-agent/pull/3024))
- Fix `/queue` always working regardless of config ([#3298](https://github.com/NousResearch/hermes-agent/pull/3298))
- Fix phantom Discord typing indicator after agent turn ([#3003](https://github.com/NousResearch/hermes-agent/pull/3003))
- Fix Slack progress messages appearing in wrong thread ([#3063](https://github.com/NousResearch/hermes-agent/pull/3063))
- Fix WhatsApp media downloads (documents, audio, video) ([#2978](https://github.com/NousResearch/hermes-agent/pull/2978))
- Fix Telegram "Message thread not found" killing progress messages ([#3390](https://github.com/NousResearch/hermes-agent/pull/3390))
- Fix OpenClaw migration overwriting defaults ([#3282](https://github.com/NousResearch/hermes-agent/pull/3282))
- Fix returning-user setup menu dispatching wrong section ([#3083](https://github.com/NousResearch/hermes-agent/pull/3083))
- Fix `hermes update` PEP 668 "externally-managed-environment" error ([#3099](https://github.com/NousResearch/hermes-agent/pull/3099))
- Fix subagents hitting `max_iterations` prematurely via shared budget ([#3004](https://github.com/NousResearch/hermes-agent/pull/3004))
- Fix YAML boolean handling for `tool_progress` config ([#3300](https://github.com/NousResearch/hermes-agent/pull/3300))
- Fix `config.get()` crashes on YAML null values ([#3377](https://github.com/NousResearch/hermes-agent/pull/3377))
- Fix `.strip()` crash on None values from YAML config ([#3552](https://github.com/NousResearch/hermes-agent/pull/3552))
- Fix hung agents on gateway — `/stop` now hard-kills session lock ([#3104](https://github.com/NousResearch/hermes-agent/pull/3104))
- Fix `_custom` provider silently remapped to `openrouter` ([#2792](https://github.com/NousResearch/hermes-agent/pull/2792))
- Fix Matrix missing from `PLATFORMS` dict ([#3473](https://github.com/NousResearch/hermes-agent/pull/3473))
- Fix Email adapter unbounded `_seen_uids` growth ([#3490](https://github.com/NousResearch/hermes-agent/pull/3490))
-
---
-
-## 🧪 Testing
-
- Pin `agent-client-protocol` < 0.9 to handle breaking upstream release ([#3320](https://github.com/NousResearch/hermes-agent/pull/3320))
- Catch anthropic ImportError in vision auto-detection tests ([#3312](https://github.com/NousResearch/hermes-agent/pull/3312))
- Update retry-exhaust test for new graceful return behavior ([#3320](https://github.com/NousResearch/hermes-agent/pull/3320))
- Add regression tests for null metadata frontmatter ([untagged commit](https://github.com/NousResearch/hermes-agent))
-
---
-
-## 📚 Documentation
-
- Update all docs for `/model` command overhaul and custom provider support ([#2800](https://github.com/NousResearch/hermes-agent/pull/2800))
- Fix stale and incorrect documentation across 18 files ([#2805](https://github.com/NousResearch/hermes-agent/pull/2805))
- Document 9 previously undocumented features ([#2814](https://github.com/NousResearch/hermes-agent/pull/2814))
- Add missing skills, CLI commands, and messaging env vars to docs ([#2809](https://github.com/NousResearch/hermes-agent/pull/2809))
- Fix api-server response storage documentation — SQLite, not in-memory ([#2819](https://github.com/NousResearch/hermes-agent/pull/2819))
- Quote pip install extras to fix zsh glob errors ([#2815](https://github.com/NousResearch/hermes-agent/pull/2815))
- Unify hooks documentation — add plugin hooks to hooks page, add `session:end` event ([untagged commit](https://github.com/NousResearch/hermes-agent))
- Clarify two-mode behavior in `session_search` schema description ([untagged commit](https://github.com/NousResearch/hermes-agent))
- Fix Discord Public Bot setting for Discord-provided invite link ([#3519](https://github.com/NousResearch/hermes-agent/pull/3519)) by @mehmoodosman
- Revise v0.4.0 changelog — fix feature attribution, reorder sections ([untagged commit](https://github.com/NousResearch/hermes-agent))
-
---
-
-## 👥 Contributors
-
-### Core
- **@teknium1** — 157 PRs covering the full scope of this release
-
-### Community Contributors
- **@alt-glitch** (Siddharth Balyan) — 2 PRs: Nix flake with uv2nix build, NixOS module, and persistent container mode ([#20](https://github.com/NousResearch/hermes-agent/pull/20)); auto-generated config keys and suffix PATHs for Nix builds ([#3061](https://github.com/NousResearch/hermes-agent/pull/3061), [#3274](https://github.com/NousResearch/hermes-agent/pull/3274))
- **@ctlst** — 1 PR: Prevent AsyncOpenAI/httpx cross-loop deadlock in gateway mode ([#2701](https://github.com/NousResearch/hermes-agent/pull/2701))
- **@memosr** (memosr.eth) — 1 PR: Add request timeouts to `send_message_tool` HTTP calls ([#3162](https://github.com/NousResearch/hermes-agent/pull/3162))
- **@mehmoodosman** (Osman Mehmood) — 1 PR: Fix Discord docs for Public Bot setting ([#3519](https://github.com/NousResearch/hermes-agent/pull/3519))
-
-### All Contributors
-@alt-glitch, @ctlst, @mehmoodosman, @memosr, @teknium1
-
---
-
-**Full Changelog**: [v2026.3.23...v2026.3.28](https://github.com/NousResearch/hermes-agent/compare/v2026.3.23...v2026.3.28)
@@ -1,249 +0,0 @@
-# Hermes Agent v0.6.0 (v2026.3.30)
-
-**Release Date:** March 30, 2026
-
-> The multi-instance release — Profiles for running isolated agent instances, MCP server mode, Docker container, fallback provider chains, two new messaging platforms (Feishu/Lark and WeCom), Telegram webhook mode, Slack multi-workspace OAuth, 95 PRs and 16 resolved issues in 2 days.
-
---
-
-## ✨ Highlights
-
- **Profiles — Multi-Instance Hermes** — Run multiple isolated Hermes instances from the same installation. Each profile gets its own config, memory, sessions, skills, and gateway service. Create with `hermes profile create`, switch with `hermes -p <name>`, export/import for sharing. Full token-lock isolation prevents two profiles from using the same bot credential. ([#3681](https://github.com/NousResearch/hermes-agent/pull/3681))
-
- **MCP Server Mode** — Expose Hermes conversations and sessions to any MCP-compatible client (Claude Desktop, Cursor, VS Code, etc.) via `hermes mcp serve`. Browse conversations, read messages, search across sessions, and manage attachments — all through the Model Context Protocol. Supports both stdio and Streamable HTTP transports. ([#3795](https://github.com/NousResearch/hermes-agent/pull/3795))
-
- **Docker Container** — Official Dockerfile for running Hermes Agent in a container. Supports both CLI and gateway modes with volume-mounted config. ([#3668](https://github.com/NousResearch/hermes-agent/pull/3668), closes [#850](https://github.com/NousResearch/hermes-agent/issues/850))
-
- **Ordered Fallback Provider Chain** — Configure multiple inference providers with automatic failover. When your primary provider returns errors or is unreachable, Hermes automatically tries the next provider in the chain. Configure via `fallback_providers` in config.yaml. ([#3813](https://github.com/NousResearch/hermes-agent/pull/3813), closes [#1734](https://github.com/NousResearch/hermes-agent/issues/1734))
-
- **Feishu/Lark Platform Support** — Full gateway adapter for Feishu (飞书) and Lark with event subscriptions, message cards, group chat, image/file attachments, and interactive card callbacks. ([#3799](https://github.com/NousResearch/hermes-agent/pull/3799), [#3817](https://github.com/NousResearch/hermes-agent/pull/3817), closes [#1788](https://github.com/NousResearch/hermes-agent/issues/1788))
-
- **WeCom (Enterprise WeChat) Platform Support** — New gateway adapter for WeCom (企业微信) with text/image/voice messages, group chats, and callback verification. ([#3847](https://github.com/NousResearch/hermes-agent/pull/3847))
-
- **Slack Multi-Workspace OAuth** — Connect a single Hermes gateway to multiple Slack workspaces via OAuth token file. Each workspace gets its own bot token, resolved dynamically per incoming event. ([#3903](https://github.com/NousResearch/hermes-agent/pull/3903))
-
- **Telegram Webhook Mode & Group Controls** — Run the Telegram adapter in webhook mode as an alternative to polling — faster response times and better for production deployments behind a reverse proxy. New group mention gating controls when the bot responds: always, only when @mentioned, or via regex triggers. ([#3880](https://github.com/NousResearch/hermes-agent/pull/3880), [#3870](https://github.com/NousResearch/hermes-agent/pull/3870))
-
- **Exa Search Backend** — Add Exa as an alternative web search and content extraction backend alongside Firecrawl and DuckDuckGo. Set `EXA_API_KEY` and configure as preferred backend. ([#3648](https://github.com/NousResearch/hermes-agent/pull/3648))
-
- **Skills & Credentials on Remote Backends** — Mount skill directories and credential files into Modal and Docker containers, so remote terminal sessions have access to the same skills and secrets as local execution. ([#3890](https://github.com/NousResearch/hermes-agent/pull/3890), [#3671](https://github.com/NousResearch/hermes-agent/pull/3671), closes [#3665](https://github.com/NousResearch/hermes-agent/issues/3665), [#3433](https://github.com/NousResearch/hermes-agent/issues/3433))
-
---
-
-## 🏗️ Core Agent & Architecture
-
-### Provider & Model Support
- **Ordered fallback provider chain** — automatic failover across multiple configured providers ([#3813](https://github.com/NousResearch/hermes-agent/pull/3813))
- **Fix api_mode on provider switch** — switching providers via `hermes model` now correctly clears stale `api_mode` instead of hardcoding `chat_completions`, fixing 404s for providers with Anthropic-compatible endpoints ([#3726](https://github.com/NousResearch/hermes-agent/pull/3726), [#3857](https://github.com/NousResearch/hermes-agent/pull/3857), closes [#3685](https://github.com/NousResearch/hermes-agent/issues/3685))
- **Stop silent OpenRouter fallback** — when no provider is configured, Hermes now raises a clear error instead of silently routing to OpenRouter ([#3807](https://github.com/NousResearch/hermes-agent/pull/3807), [#3862](https://github.com/NousResearch/hermes-agent/pull/3862))
- **Gemini 3.1 preview models** — added to OpenRouter and Nous Portal catalogs ([#3803](https://github.com/NousResearch/hermes-agent/pull/3803), closes [#3753](https://github.com/NousResearch/hermes-agent/issues/3753))
- **Gemini direct API context length** — full context length resolution for direct Google AI endpoints ([#3876](https://github.com/NousResearch/hermes-agent/pull/3876))
- **gpt-5.4-mini** added to Codex fallback catalog ([#3855](https://github.com/NousResearch/hermes-agent/pull/3855))
- **Curated model lists preferred** over live API probe when the probe returns fewer models ([#3856](https://github.com/NousResearch/hermes-agent/pull/3856), [#3867](https://github.com/NousResearch/hermes-agent/pull/3867))
- **User-friendly 429 rate limit messages** with Retry-After countdown ([#3809](https://github.com/NousResearch/hermes-agent/pull/3809))
- **Auxiliary client placeholder key** for local servers without auth requirements ([#3842](https://github.com/NousResearch/hermes-agent/pull/3842))
- **INFO-level logging** for auxiliary provider resolution ([#3866](https://github.com/NousResearch/hermes-agent/pull/3866))
-
-### Agent Loop & Conversation
- **Subagent status reporting** — reports `completed` status when summary exists instead of generic failure ([#3829](https://github.com/NousResearch/hermes-agent/pull/3829))
- **Session log file updated during compression** — prevents stale file references after context compression ([#3835](https://github.com/NousResearch/hermes-agent/pull/3835))
- **Omit empty tools param** — sends no `tools` parameter when empty instead of `None`, fixing compatibility with strict providers ([#3820](https://github.com/NousResearch/hermes-agent/pull/3820))
-
-### Profiles & Multi-Instance
- **Profiles system** — `hermes profile create/list/switch/delete/export/import/rename`. Each profile gets isolated HERMES_HOME, gateway service, CLI wrapper. Token locks prevent credential collisions. Tab completion for profile names. ([#3681](https://github.com/NousResearch/hermes-agent/pull/3681))
- **Profile-aware display paths** — all user-facing `~/.hermes` paths replaced with `display_hermes_home()` to show the correct profile directory ([#3623](https://github.com/NousResearch/hermes-agent/pull/3623))
- **Lazy display_hermes_home imports** — prevents `ImportError` during `hermes update` when modules cache stale bytecode ([#3776](https://github.com/NousResearch/hermes-agent/pull/3776))
- **HERMES_HOME for protected paths** — `.env` write-deny path now respects HERMES_HOME instead of hardcoded `~/.hermes` ([#3840](https://github.com/NousResearch/hermes-agent/pull/3840))
-
---
-
-## 📱 Messaging Platforms (Gateway)
-
-### New Platforms
- **Feishu/Lark** — Full adapter with event subscriptions, message cards, group chat, image/file attachments, interactive card callbacks ([#3799](https://github.com/NousResearch/hermes-agent/pull/3799), [#3817](https://github.com/NousResearch/hermes-agent/pull/3817))
- **WeCom (Enterprise WeChat)** — Text/image/voice messages, group chats, callback verification ([#3847](https://github.com/NousResearch/hermes-agent/pull/3847))
-
-### Telegram
- **Webhook mode** — run as webhook endpoint instead of polling for production deployments ([#3880](https://github.com/NousResearch/hermes-agent/pull/3880))
- **Group mention gating & regex triggers** — configurable bot response behavior in groups: always, @mention-only, or regex-matched ([#3870](https://github.com/NousResearch/hermes-agent/pull/3870))
- **Gracefully handle deleted reply targets** — no more crashes when the message being replied to was deleted ([#3858](https://github.com/NousResearch/hermes-agent/pull/3858), closes [#3229](https://github.com/NousResearch/hermes-agent/issues/3229))
-
-### Discord
- **Message processing reactions** — adds a reaction emoji while processing and removes it when done, giving visual feedback in channels ([#3871](https://github.com/NousResearch/hermes-agent/pull/3871))
- **DISCORD_IGNORE_NO_MENTION** — skip messages that @mention other users/bots but not Hermes ([#3640](https://github.com/NousResearch/hermes-agent/pull/3640))
- **Clean up deferred "thinking..."** — properly removes the "thinking..." indicator after slash commands complete ([#3674](https://github.com/NousResearch/hermes-agent/pull/3674), closes [#3595](https://github.com/NousResearch/hermes-agent/issues/3595))
-
-### Slack
- **Multi-workspace OAuth** — connect to multiple Slack workspaces from a single gateway via OAuth token file ([#3903](https://github.com/NousResearch/hermes-agent/pull/3903))
-
-### WhatsApp
- **Persistent aiohttp session** — reuse HTTP sessions across requests instead of creating new ones per message ([#3818](https://github.com/NousResearch/hermes-agent/pull/3818))
- **LID↔phone alias resolution** — correctly match Linked ID and phone number formats in allowlists ([#3830](https://github.com/NousResearch/hermes-agent/pull/3830))
- **Skip reply prefix in bot mode** — cleaner message formatting when running as a WhatsApp bot ([#3931](https://github.com/NousResearch/hermes-agent/pull/3931))
-
-### Matrix
- **Native voice messages via MSC3245** — send voice messages as proper Matrix voice events instead of file attachments ([#3877](https://github.com/NousResearch/hermes-agent/pull/3877))
-
-### Mattermost
- **Configurable mention behavior** — respond to messages without requiring @mention ([#3664](https://github.com/NousResearch/hermes-agent/pull/3664))
-
-### Signal
- **URL-encode phone numbers** and correct attachment RPC parameter — fixes delivery failures with certain phone number formats ([#3670](https://github.com/NousResearch/hermes-agent/pull/3670)) — @kshitijk4poor
-
-### Email
- **Close SMTP/IMAP connections on failure** — prevents connection leaks during error scenarios ([#3804](https://github.com/NousResearch/hermes-agent/pull/3804))
-
-### Gateway Core
- **Atomic config writes** — use atomic file writes for config.yaml to prevent data loss during crashes ([#3800](https://github.com/NousResearch/hermes-agent/pull/3800))
- **Home channel env overrides** — apply environment variable overrides for home channels consistently ([#3796](https://github.com/NousResearch/hermes-agent/pull/3796), [#3808](https://github.com/NousResearch/hermes-agent/pull/3808))
- **Replace print() with logger** — BasePlatformAdapter now uses proper logging instead of print statements ([#3669](https://github.com/NousResearch/hermes-agent/pull/3669))
- **Cron delivery labels** — resolve human-friendly delivery labels via channel directory ([#3860](https://github.com/NousResearch/hermes-agent/pull/3860), closes [#1945](https://github.com/NousResearch/hermes-agent/issues/1945))
- **Cron [SILENT] tightening** — prevent agents from prefixing reports with [SILENT] to suppress delivery ([#3901](https://github.com/NousResearch/hermes-agent/pull/3901))
- **Background task media delivery** and vision download timeout fixes ([#3919](https://github.com/NousResearch/hermes-agent/pull/3919))
- **Boot-md hook** — example built-in hook to run a BOOT.md file on gateway startup ([#3733](https://github.com/NousResearch/hermes-agent/pull/3733))
-
---
-
-## 🖥️ CLI & User Experience
-
-### Interactive CLI
- **Configurable tool preview length** — show full file paths by default instead of truncating at 40 chars ([#3841](https://github.com/NousResearch/hermes-agent/pull/3841))
- **Tool token context display** — `hermes tools` checklist now shows estimated token cost per toolset ([#3805](https://github.com/NousResearch/hermes-agent/pull/3805))
- **/bg spinner TUI fix** — route background task spinner through the TUI widget to prevent status bar collision ([#3643](https://github.com/NousResearch/hermes-agent/pull/3643))
- **Prevent status bar wrapping** into duplicate rows ([#3883](https://github.com/NousResearch/hermes-agent/pull/3883)) — @kshitijk4poor
- **Handle closed stdout ValueError** in safe print paths — fixes crashes when stdout is closed during gateway thread shutdown ([#3843](https://github.com/NousResearch/hermes-agent/pull/3843), closes [#3534](https://github.com/NousResearch/hermes-agent/issues/3534))
- **Remove input() from /tools disable** — eliminates freeze in terminal when disabling tools ([#3918](https://github.com/NousResearch/hermes-agent/pull/3918))
- **TTY guard for interactive CLI commands** — prevent CPU spin when launched without a terminal ([#3933](https://github.com/NousResearch/hermes-agent/pull/3933))
- **Argparse entrypoint** — use argparse in the top-level launcher for cleaner error handling ([#3874](https://github.com/NousResearch/hermes-agent/pull/3874))
- **Lazy-initialized tools show yellow** in banner instead of red, reducing false alarm about "missing" tools ([#3822](https://github.com/NousResearch/hermes-agent/pull/3822))
- **Honcho tools shown in banner** when configured ([#3810](https://github.com/NousResearch/hermes-agent/pull/3810))
-
-### Setup & Configuration
- **Auto-install matrix-nio** during `hermes setup` when Matrix is selected ([#3802](https://github.com/NousResearch/hermes-agent/pull/3802), [#3873](https://github.com/NousResearch/hermes-agent/pull/3873))
- **Session export stdout support** — export sessions to stdout with `-` for piping ([#3641](https://github.com/NousResearch/hermes-agent/pull/3641), closes [#3609](https://github.com/NousResearch/hermes-agent/issues/3609))
- **Configurable approval timeouts** — set how long dangerous command approval prompts wait before auto-denying ([#3886](https://github.com/NousResearch/hermes-agent/pull/3886), closes [#3765](https://github.com/NousResearch/hermes-agent/issues/3765))
- **Clear __pycache__ during update** — prevents stale bytecode ImportError after `hermes update` ([#3819](https://github.com/NousResearch/hermes-agent/pull/3819))
-
---
-
-## 🔧 Tool System
-
-### MCP
- **MCP Server Mode** — `hermes mcp serve` exposes conversations, sessions, and attachments to MCP clients via stdio or Streamable HTTP ([#3795](https://github.com/NousResearch/hermes-agent/pull/3795))
- **Dynamic tool discovery** — respond to `notifications/tools/list_changed` events to pick up new tools from MCP servers without reconnecting ([#3812](https://github.com/NousResearch/hermes-agent/pull/3812))
- **Non-deprecated HTTP transport** — switched from `sse_client` to `streamable_http_client` ([#3646](https://github.com/NousResearch/hermes-agent/pull/3646))
-
-### Web Tools
- **Exa search backend** — alternative to Firecrawl and DuckDuckGo for web search and extraction ([#3648](https://github.com/NousResearch/hermes-agent/pull/3648))
-
-### Browser
- **Guard against None LLM responses** in browser snapshot and vision tools ([#3642](https://github.com/NousResearch/hermes-agent/pull/3642))
-
-### Terminal & Remote Backends
- **Mount skill directories** into Modal and Docker containers ([#3890](https://github.com/NousResearch/hermes-agent/pull/3890))
- **Mount credential files** into remote backends with mtime+size caching ([#3671](https://github.com/NousResearch/hermes-agent/pull/3671))
- **Preserve partial output** when commands time out instead of losing everything ([#3868](https://github.com/NousResearch/hermes-agent/pull/3868))
- **Stop marking persisted env vars as missing** on remote backends ([#3650](https://github.com/NousResearch/hermes-agent/pull/3650))
-
-### Audio
- **.aac format support** in transcription tool ([#3865](https://github.com/NousResearch/hermes-agent/pull/3865), closes [#1963](https://github.com/NousResearch/hermes-agent/issues/1963))
- **Audio download retry** — retry logic for `cache_audio_from_url` matching the existing image download pattern ([#3401](https://github.com/NousResearch/hermes-agent/pull/3401)) — @binhnt92
-
-### Vision
- **Reject non-image files** and enforce website-only policy for vision analysis ([#3845](https://github.com/NousResearch/hermes-agent/pull/3845))
-
-### Tool Schema
- **Ensure name field** always present in tool definitions, fixing `KeyError: 'name'` crashes ([#3811](https://github.com/NousResearch/hermes-agent/pull/3811), closes [#3729](https://github.com/NousResearch/hermes-agent/issues/3729))
-
-### ACP (Editor Integration)
- **Complete session management surface** for VS Code/Zed/JetBrains clients — proper task lifecycle, cancel support, session persistence ([#3675](https://github.com/NousResearch/hermes-agent/pull/3675))
-
---
-
-## 🧩 Skills & Plugins
-
-### Skills System
- **External skill directories** — configure additional skill directories via `skills.external_dirs` in config.yaml ([#3678](https://github.com/NousResearch/hermes-agent/pull/3678))
- **Category path traversal blocked** — prevents `../` attacks in skill category names ([#3844](https://github.com/NousResearch/hermes-agent/pull/3844))
- **parallel-cli moved to optional-skills** — reduces default skill footprint ([#3673](https://github.com/NousResearch/hermes-agent/pull/3673)) — @kshitijk4poor
-
-### New Skills
- **memento-flashcards** — spaced repetition flashcard system ([#3827](https://github.com/NousResearch/hermes-agent/pull/3827))
- **songwriting-and-ai-music** — songwriting craft and AI music generation prompts ([#3834](https://github.com/NousResearch/hermes-agent/pull/3834))
- **SiYuan Note** — integration with SiYuan note-taking app ([#3742](https://github.com/NousResearch/hermes-agent/pull/3742))
- **Scrapling** — web scraping skill using Scrapling library ([#3742](https://github.com/NousResearch/hermes-agent/pull/3742))
- **one-three-one-rule** — communication framework skill ([#3797](https://github.com/NousResearch/hermes-agent/pull/3797))
-
-### Plugin System
- **Plugin enable/disable commands** — `hermes plugins enable/disable <name>` for managing plugin state without removing them ([#3747](https://github.com/NousResearch/hermes-agent/pull/3747))
- **Plugin message injection** — plugins can now inject messages into the conversation stream on behalf of the user via `ctx.inject_message()` ([#3778](https://github.com/NousResearch/hermes-agent/pull/3778)) — @winglian
- **Honcho self-hosted support** — allow local Honcho instances without requiring an API key ([#3644](https://github.com/NousResearch/hermes-agent/pull/3644))
-
---
-
-## 🔒 Security & Reliability
-
-### Security Hardening
- **Hardened dangerous command detection** — expanded pattern matching for risky shell commands and added file tool path guards for sensitive locations (`/etc/`, `/boot/`, docker.sock) ([#3872](https://github.com/NousResearch/hermes-agent/pull/3872))
- **Sensitive path write checks** in approval system — catch writes to system config files through file tools, not just terminal ([#3859](https://github.com/NousResearch/hermes-agent/pull/3859))
- **Secret redaction expansion** — now covers ElevenLabs, Tavily, and Exa API keys ([#3920](https://github.com/NousResearch/hermes-agent/pull/3920))
- **Vision file rejection** — reject non-image files passed to vision analysis to prevent information disclosure ([#3845](https://github.com/NousResearch/hermes-agent/pull/3845))
- **Category path traversal blocking** — prevent directory traversal in skill category names ([#3844](https://github.com/NousResearch/hermes-agent/pull/3844))
-
-### Reliability
- **Atomic config.yaml writes** — prevent data loss during gateway crashes ([#3800](https://github.com/NousResearch/hermes-agent/pull/3800))
- **Clear __pycache__ on update** — prevent stale bytecode from causing ImportError after updates ([#3819](https://github.com/NousResearch/hermes-agent/pull/3819))
- **Lazy imports for update safety** — prevent ImportError chains during `hermes update` when modules reference new functions ([#3776](https://github.com/NousResearch/hermes-agent/pull/3776))
- **Restore terminalbench2 from patch corruption** — recovered file damaged by patch tool's secret redaction ([#3801](https://github.com/NousResearch/hermes-agent/pull/3801))
- **Terminal timeout preserves partial output** — no more lost command output on timeout ([#3868](https://github.com/NousResearch/hermes-agent/pull/3868))
-
---
-
-## 🐛 Notable Bug Fixes
-
- **OpenClaw migration model config overwrite** — migration no longer overwrites model config dict with a string ([#3924](https://github.com/NousResearch/hermes-agent/pull/3924)) — @0xbyt4
- **OpenClaw migration expanded** — covers full data footprint including sessions, cron, memory ([#3869](https://github.com/NousResearch/hermes-agent/pull/3869))
- **Telegram deleted reply targets** — gracefully handle replies to deleted messages instead of crashing ([#3858](https://github.com/NousResearch/hermes-agent/pull/3858))
- **Discord "thinking..." persistence** — properly cleans up deferred response indicators ([#3674](https://github.com/NousResearch/hermes-agent/pull/3674))
- **WhatsApp LID↔phone aliases** — fixes allowlist matching failures with Linked ID format ([#3830](https://github.com/NousResearch/hermes-agent/pull/3830))
- **Signal URL-encoded phone numbers** — fixes delivery failures with certain formats ([#3670](https://github.com/NousResearch/hermes-agent/pull/3670))
- **Email connection leaks** — properly close SMTP/IMAP connections on error ([#3804](https://github.com/NousResearch/hermes-agent/pull/3804))
- **_safe_print ValueError** — no more gateway thread crashes on closed stdout ([#3843](https://github.com/NousResearch/hermes-agent/pull/3843))
- **Tool schema KeyError 'name'** — ensure name field always present in tool definitions ([#3811](https://github.com/NousResearch/hermes-agent/pull/3811))
- **api_mode stale on provider switch** — correctly clear when switching providers via `hermes model` ([#3857](https://github.com/NousResearch/hermes-agent/pull/3857))
-
---
-
-## 🧪 Testing
-
- Resolved 10+ CI failures across hooks, tiktoken, plugins, and skill tests ([#3848](https://github.com/NousResearch/hermes-agent/pull/3848), [#3721](https://github.com/NousResearch/hermes-agent/pull/3721), [#3936](https://github.com/NousResearch/hermes-agent/pull/3936))
-
---
-
-## 📚 Documentation
-
- **Comprehensive OpenClaw migration guide** — step-by-step guide for migrating from OpenClaw/Claw3D to Hermes Agent ([#3864](https://github.com/NousResearch/hermes-agent/pull/3864), [#3900](https://github.com/NousResearch/hermes-agent/pull/3900))
- **Credential file passthrough docs** — document how to forward credential files and env vars to remote backends ([#3677](https://github.com/NousResearch/hermes-agent/pull/3677))
- **DuckDuckGo requirements clarified** — note runtime dependency on duckduckgo-search package ([#3680](https://github.com/NousResearch/hermes-agent/pull/3680))
- **Skills catalog updated** — added red-teaming category and optional skills listing ([#3745](https://github.com/NousResearch/hermes-agent/pull/3745))
- **Feishu docs MDX fix** — escape angle-bracket URLs that break Docusaurus build ([#3902](https://github.com/NousResearch/hermes-agent/pull/3902))
-
---
-
-## 👥 Contributors
-
-### Core
- **@teknium1** — 90 PRs across all subsystems
-
-### Community Contributors
- **@kshitijk4poor** — 3 PRs: Signal phone number fix ([#3670](https://github.com/NousResearch/hermes-agent/pull/3670)), parallel-cli to optional-skills ([#3673](https://github.com/NousResearch/hermes-agent/pull/3673)), status bar wrapping fix ([#3883](https://github.com/NousResearch/hermes-agent/pull/3883))
- **@winglian** — 1 PR: Plugin message injection interface ([#3778](https://github.com/NousResearch/hermes-agent/pull/3778))
- **@binhnt92** — 1 PR: Audio download retry logic ([#3401](https://github.com/NousResearch/hermes-agent/pull/3401))
- **@0xbyt4** — 1 PR: OpenClaw migration model config fix ([#3924](https://github.com/NousResearch/hermes-agent/pull/3924))
-
-### Issues Resolved from Community
-@Material-Scientist ([#850](https://github.com/NousResearch/hermes-agent/issues/850)), @hanxu98121 ([#1734](https://github.com/NousResearch/hermes-agent/issues/1734)), @penwyp ([#1788](https://github.com/NousResearch/hermes-agent/issues/1788)), @dan-and ([#1945](https://github.com/NousResearch/hermes-agent/issues/1945)), @AdrianScott ([#1963](https://github.com/NousResearch/hermes-agent/issues/1963)), @clawdbot47 ([#3229](https://github.com/NousResearch/hermes-agent/issues/3229)), @alanfwilliams ([#3404](https://github.com/NousResearch/hermes-agent/issues/3404)), @kentimsit ([#3433](https://github.com/NousResearch/hermes-agent/issues/3433)), @hayka-pacha ([#3534](https://github.com/NousResearch/hermes-agent/issues/3534)), @primmer ([#3595](https://github.com/NousResearch/hermes-agent/issues/3595)), @dagelf ([#3609](https://github.com/NousResearch/hermes-agent/issues/3609)), @HenkDz ([#3685](https://github.com/NousResearch/hermes-agent/issues/3685)), @tmdgusya ([#3729](https://github.com/NousResearch/hermes-agent/issues/3729)), @TypQxQ ([#3753](https://github.com/NousResearch/hermes-agent/issues/3753)), @acsezen ([#3765](https://github.com/NousResearch/hermes-agent/issues/3765))
-
---
-
-**Full Changelog**: [v2026.3.28...v2026.3.30](https://github.com/NousResearch/hermes-agent/compare/v2026.3.28...v2026.3.30)
@@ -74,7 +74,7 @@ def main() -> None:

    agent = HermesACPAgent()
    try:
-        asyncio.run(acp.run_agent(agent, use_unstable_protocol=True))
+        asyncio.run(acp.run_agent(agent))
    except KeyboardInterrupt:
        logger.info("Shutting down (KeyboardInterrupt)")
    except Exception:
@@ -25,9 +25,6 @@ from acp.schema import (
    NewSessionResponse,
    PromptResponse,
    ResumeSessionResponse,
-    SetSessionConfigOptionResponse,
-    SetSessionModelResponse,
-    SetSessionModeResponse,
    ResourceContentBlock,
    SessionCapabilities,
    SessionForkCapabilities,
@@ -97,14 +94,11 @@ class HermesACPAgent(acp.Agent):

    async def initialize(
        self,
-        protocol_version: int | None = None,
+        protocol_version: int,
        client_capabilities: ClientCapabilities | None = None,
        client_info: Implementation | None = None,
        **kwargs: Any,
    ) -> InitializeResponse:
-        resolved_protocol_version = (
-            protocol_version if isinstance(protocol_version, int) else acp.PROTOCOL_VERSION
-        )
        provider = detect_provider()
        auth_methods = None
        if provider:
@@ -117,11 +111,7 @@ class HermesACPAgent(acp.Agent):
            ]

        client_name = client_info.name if client_info else "unknown"
-        logger.info(
-            "Initialize from %s (protocol v%s)",
-            client_name,
-            resolved_protocol_version,
-        )
+        logger.info("Initialize from %s (protocol v%s)", client_name, protocol_version)

        return InitializeResponse(
            protocol_version=acp.PROTOCOL_VERSION,
@@ -481,7 +471,7 @@ class HermesACPAgent(acp.Agent):

    async def set_session_model(
        self, model_id: str, session_id: str, **kwargs: Any
-    ) -> SetSessionModelResponse | None:
+    ):
        """Switch the model for a session (called by ACP protocol)."""
        state = self.session_manager.get_session(session_id)
        if state:
@@ -499,37 +489,4 @@ class HermesACPAgent(acp.Agent):
            )
            self.session_manager.save_session(session_id)
            logger.info("Session %s: model switched to %s", session_id, model_id)
-            return SetSessionModelResponse()
-        logger.warning("Session %s: model switch requested for missing session", session_id)
        return None
-
-    async def set_session_mode(
-        self, mode_id: str, session_id: str, **kwargs: Any
-    ) -> SetSessionModeResponse | None:
-        """Persist the editor-requested mode so ACP clients do not fail on mode switches."""
-        state = self.session_manager.get_session(session_id)
-        if state is None:
-            logger.warning("Session %s: mode switch requested for missing session", session_id)
-            return None
-        setattr(state, "mode", mode_id)
-        self.session_manager.save_session(session_id)
-        logger.info("Session %s: mode switched to %s", session_id, mode_id)
-        return SetSessionModeResponse()
-
-    async def set_config_option(
-        self, config_id: str, session_id: str, value: str, **kwargs: Any
-    ) -> SetSessionConfigOptionResponse | None:
-        """Accept ACP config option updates even when Hermes has no typed ACP config surface yet."""
-        state = self.session_manager.get_session(session_id)
-        if state is None:
-            logger.warning("Session %s: config update requested for missing session", session_id)
-            return None
-
-        options = getattr(state, "config_options", None)
-        if not isinstance(options, dict):
-            options = {}
-        options[str(config_id)] = value
-        setattr(state, "config_options", options)
-        self.session_manager.save_session(session_id)
-        logger.info("Session %s: config option %s updated", session_id, config_id)
-        return SetSessionConfigOptionResponse(config_options=[])
@@ -35,54 +35,6 @@ ADAPTIVE_EFFORT_MAP = {
    "minimal": "low",
 }

-# ── Max output token limits per Anthropic model ───────────────────────
-# Source: Anthropic docs + Cline model catalog.  Anthropic's API requires
-# max_tokens as a mandatory field.  Previously we hardcoded 16384, which
-# starves thinking-enabled models (thinking tokens count toward the limit).
-_ANTHROPIC_OUTPUT_LIMITS = {
-    # Claude 4.6
-    "claude-opus-4-6":   128_000,
-    "claude-sonnet-4-6":  64_000,
-    # Claude 4.5
-    "claude-opus-4-5":    64_000,
-    "claude-sonnet-4-5":  64_000,
-    "claude-haiku-4-5":   64_000,
-    # Claude 4
-    "claude-opus-4":      32_000,
-    "claude-sonnet-4":    64_000,
-    # Claude 3.7
-    "claude-3-7-sonnet": 128_000,
-    # Claude 3.5
-    "claude-3-5-sonnet":   8_192,
-    "claude-3-5-haiku":    8_192,
-    # Claude 3
-    "claude-3-opus":       4_096,
-    "claude-3-sonnet":     4_096,
-    "claude-3-haiku":      4_096,
-}
-
-# For any model not in the table, assume the highest current limit.
-# Future Anthropic models are unlikely to have *less* output capacity.
-_ANTHROPIC_DEFAULT_OUTPUT_LIMIT = 128_000
-
-
-def _get_anthropic_max_output(model: str) -> int:
-    """Look up the max output token limit for an Anthropic model.
-
-    Uses substring matching against _ANTHROPIC_OUTPUT_LIMITS so date-stamped
-    model IDs (claude-sonnet-4-5-20250929) and variant suffixes (:1m, :fast)
-    resolve correctly.  Longest-prefix match wins to avoid e.g. "claude-3-5"
-    matching before "claude-3-5-sonnet".
-    """
-    m = model.lower()
-    best_key = ""
-    best_val = _ANTHROPIC_DEFAULT_OUTPUT_LIMIT
-    for key, val in _ANTHROPIC_OUTPUT_LIMITS.items():
-        if key in m and len(key) > len(best_key):
-            best_key = key
-            best_val = val
-    return best_val
-

 def _supports_adaptive_thinking(model: str) -> bool:
    """Return True for Claude 4.6 models that support adaptive thinking."""
@@ -107,7 +59,6 @@ _OAUTH_ONLY_BETAS = [
 # The version must stay reasonably current — Anthropic rejects OAuth requests
 # when the spoofed user-agent version is too far behind the actual release.
 _CLAUDE_CODE_VERSION_FALLBACK = "2.1.74"
-_claude_code_version_cache: Optional[str] = None


 def _detect_claude_code_version() -> str:
@@ -135,18 +86,11 @@ def _detect_claude_code_version() -> str:
    return _CLAUDE_CODE_VERSION_FALLBACK


+_CLAUDE_CODE_VERSION = _detect_claude_code_version()
 _CLAUDE_CODE_SYSTEM_PREFIX = "You are Claude Code, Anthropic's official CLI for Claude."
 _MCP_TOOL_PREFIX = "mcp_"


-def _get_claude_code_version() -> str:
-    """Lazily detect the installed Claude Code version when OAuth headers need it."""
-    global _claude_code_version_cache
-    if _claude_code_version_cache is None:
-        _claude_code_version_cache = _detect_claude_code_version()
-    return _claude_code_version_cache
-
-
 def _is_oauth_token(key: str) -> bool:
    """Check if the key is an OAuth/setup token (not a regular Console API key).

@@ -162,36 +106,6 @@ def _is_oauth_token(key: str) -> bool:
    return True


-def _is_third_party_anthropic_endpoint(base_url: str | None) -> bool:
-    """Return True for non-Anthropic endpoints using the Anthropic Messages API.
-
-    Third-party proxies (Azure AI Foundry, AWS Bedrock, self-hosted) authenticate
-    with their own API keys via x-api-key, not Anthropic OAuth tokens. OAuth
-    detection should be skipped for these endpoints.
-    """
-    if not base_url:
-        return False  # No base_url = direct Anthropic API
-    normalized = base_url.rstrip("/").lower()
-    if "anthropic.com" in normalized:
-        return False  # Direct Anthropic API — OAuth applies
-    return True  # Any other endpoint is a third-party proxy
-
-
-def _requires_bearer_auth(base_url: str | None) -> bool:
-    """Return True for Anthropic-compatible providers that require Bearer auth.
-
-    Some third-party /anthropic endpoints implement Anthropic's Messages API but
-    require Authorization: Bearer instead of Anthropic's native x-api-key header.
-    MiniMax's global and China Anthropic-compatible endpoints follow this pattern.
-    """
-    if not base_url:
-        return False
-    normalized = base_url.rstrip("/").lower()
-    return normalized.startswith("https://api.minimax.io/anthropic") or normalized.startswith(
-        "https://api.minimaxi.com/anthropic"
-    )
-
-
 def build_anthropic_client(api_key: str, base_url: str = None):
    """Create an Anthropic client, auto-detecting setup-tokens vs API keys.

@@ -210,25 +124,7 @@ def build_anthropic_client(api_key: str, base_url: str = None):
    if base_url:
        kwargs["base_url"] = base_url

-    if _requires_bearer_auth(base_url):
-        # Some Anthropic-compatible providers (e.g. MiniMax) expect the API key in
-        # Authorization: Bearer even for regular API keys. Route those endpoints
-        # through auth_token so the SDK sends Bearer auth instead of x-api-key.
-        # Check this before OAuth token shape detection because MiniMax secrets do
-        # not use Anthropic's sk-ant-api prefix and would otherwise be misread as
-        # Anthropic OAuth/setup tokens.
-        kwargs["auth_token"] = api_key
-        if _COMMON_BETAS:
-            kwargs["default_headers"] = {"anthropic-beta": ",".join(_COMMON_BETAS)}
-    elif _is_third_party_anthropic_endpoint(base_url):
-        # Third-party proxies (Azure AI Foundry, AWS Bedrock, etc.) use their
-        # own API keys with x-api-key auth. Skip OAuth detection — their keys
-        # don't follow Anthropic's sk-ant-* prefix convention and would be
-        # misclassified as OAuth tokens.
-        kwargs["api_key"] = api_key
-        if _COMMON_BETAS:
-            kwargs["default_headers"] = {"anthropic-beta": ",".join(_COMMON_BETAS)}
-    elif _is_oauth_token(api_key):
+    if _is_oauth_token(api_key):
        # OAuth access token / setup-token → Bearer auth + Claude Code identity.
        # Anthropic routes OAuth requests based on user-agent and headers;
        # without Claude Code's fingerprint, requests get intermittent 500s.
@@ -236,7 +132,7 @@ def build_anthropic_client(api_key: str, base_url: str = None):
        kwargs["auth_token"] = api_key
        kwargs["default_headers"] = {
            "anthropic-beta": ",".join(all_betas),
-            "user-agent": f"claude-cli/{_get_claude_code_version()} (external, cli)",
+            "user-agent": f"claude-cli/{_CLAUDE_CODE_VERSION} (external, cli)",
            "x-app": "cli",
        }
    else:
@@ -307,105 +203,71 @@ def is_claude_code_token_valid(creds: Dict[str, Any]) -> bool:
    return now_ms < (expires_at - 60_000)


-def refresh_anthropic_oauth_pure(refresh_token: str, *, use_json: bool = False) -> Dict[str, Any]:
-    """Refresh an Anthropic OAuth token without mutating local credential files."""
+def _refresh_oauth_token(creds: Dict[str, Any]) -> Optional[str]:
+    """Attempt to refresh an expired Claude Code OAuth token.
+
+    Uses the same token endpoint and client_id as Claude Code / OpenCode.
+    Only works for credentials that have a refresh token (from claude /login
+    or claude setup-token with OAuth flow).
+
+    Tries the new platform.claude.com endpoint first (Claude Code >=2.1.81),
+    then falls back to console.anthropic.com for older tokens.
+
+    Returns the new access token, or None if refresh fails.
+    """
    import time
-    import urllib.parse
    import urllib.request

-    if not refresh_token:
-        raise ValueError("refresh_token is required")
-
-    client_id = "9d1c250a-e61b-44d9-88ed-5944d1962f5e"
-    if use_json:
-        data = json.dumps({
-            "grant_type": "refresh_token",
-            "refresh_token": refresh_token,
-            "client_id": client_id,
-        }).encode()
-        content_type = "application/json"
-    else:
-        data = urllib.parse.urlencode({
-            "grant_type": "refresh_token",
-            "refresh_token": refresh_token,
-            "client_id": client_id,
-        }).encode()
-        content_type = "application/x-www-form-urlencoded"
-
-    token_endpoints = [
-        "https://platform.claude.com/v1/oauth/token",
-        "https://console.anthropic.com/v1/oauth/token",
-    ]
-    last_error = None
-    for endpoint in token_endpoints:
-        req = urllib.request.Request(
-            endpoint,
-            data=data,
-            headers={
-                "Content-Type": content_type,
-                "User-Agent": f"claude-cli/{_get_claude_code_version()} (external, cli)",
-            },
-            method="POST",
-        )
-        try:
-            with urllib.request.urlopen(req, timeout=10) as resp:
-                result = json.loads(resp.read().decode())
-        except Exception as exc:
-            last_error = exc
-            logger.debug("Anthropic token refresh failed at %s: %s", endpoint, exc)
-            continue
-
-        access_token = result.get("access_token", "")
-        if not access_token:
-            raise ValueError("Anthropic refresh response was missing access_token")
-        next_refresh = result.get("refresh_token", refresh_token)
-        expires_in = result.get("expires_in", 3600)
-        return {
-            "access_token": access_token,
-            "refresh_token": next_refresh,
-            "expires_at_ms": int(time.time() * 1000) + (expires_in * 1000),
-        }
-
-    if last_error is not None:
-        raise last_error
-    raise ValueError("Anthropic token refresh failed")
-
-
-def _refresh_oauth_token(creds: Dict[str, Any]) -> Optional[str]:
-    """Attempt to refresh an expired Claude Code OAuth token."""
    refresh_token = creds.get("refreshToken", "")
    if not refresh_token:
        logger.debug("No refresh token available — cannot refresh")
        return None

-    try:
-        refreshed = refresh_anthropic_oauth_pure(refresh_token, use_json=False)
-        _write_claude_code_credentials(
-            refreshed["access_token"],
-            refreshed["refresh_token"],
-            refreshed["expires_at_ms"],
+    # Client ID used by Claude Code's OAuth flow
+    CLIENT_ID = "9d1c250a-e61b-44d9-88ed-5944d1962f5e"
+
+    # Anthropic migrated OAuth from console.anthropic.com to platform.claude.com
+    # (Claude Code v2.1.81+). Try new endpoint first, fall back to old.
+    token_endpoints = [
+        "https://platform.claude.com/v1/oauth/token",
+        "https://console.anthropic.com/v1/oauth/token",
+    ]
+
+    payload = json.dumps({
+        "grant_type": "refresh_token",
+        "refresh_token": refresh_token,
+        "client_id": CLIENT_ID,
+    }).encode()
+
+    headers = {
+        "Content-Type": "application/json",
+        "User-Agent": f"claude-cli/{_CLAUDE_CODE_VERSION} (external, cli)",
+    }
+
+    for endpoint in token_endpoints:
+        req = urllib.request.Request(
+            endpoint, data=payload, headers=headers, method="POST",
        )
-        logger.debug("Successfully refreshed Claude Code OAuth token")
-        return refreshed["access_token"]
-    except Exception as e:
-        logger.debug("Failed to refresh Claude Code token: %s", e)
-        return None
+        try:
+            with urllib.request.urlopen(req, timeout=10) as resp:
+                result = json.loads(resp.read().decode())
+                new_access = result.get("access_token", "")
+                new_refresh = result.get("refresh_token", refresh_token)
+                expires_in = result.get("expires_in", 3600)
+
+                if new_access:
+                    new_expires_ms = int(time.time() * 1000) + (expires_in * 1000)
+                    _write_claude_code_credentials(new_access, new_refresh, new_expires_ms)
+                    logger.debug("Refreshed Claude Code OAuth token via %s", endpoint)
+                    return new_access
+        except Exception as e:
+            logger.debug("Token refresh failed at %s: %s", endpoint, e)
+
+    return None


-def _write_claude_code_credentials(
-    access_token: str,
-    refresh_token: str,
-    expires_at_ms: int,
-    *,
-    scopes: Optional[list] = None,
-) -> None:
-    """Write refreshed credentials back to ~/.claude/.credentials.json.
-
-    The optional *scopes* list (e.g. ``["user:inference", "user:profile", ...]``)
-    is persisted so that Claude Code's own auth check recognises the credential
-    as valid.  Claude Code >=2.1.81 gates on the presence of ``"user:inference"``
-    in the stored scopes before it will use the token.
-    """
+def _write_claude_code_credentials(access_token: str, refresh_token: str, expires_at_ms: int) -> None:
+    """Write refreshed credentials back to ~/.claude/.credentials.json."""
    cred_path = Path.home() / ".claude" / ".credentials.json"
    try:
        # Read existing file to preserve other fields
@@ -413,19 +275,11 @@ def _write_claude_code_credentials(
        if cred_path.exists():
            existing = json.loads(cred_path.read_text(encoding="utf-8"))

-        oauth_data: Dict[str, Any] = {
+        existing["claudeAiOauth"] = {
            "accessToken": access_token,
            "refreshToken": refresh_token,
            "expiresAt": expires_at_ms,
        }
-        if scopes is not None:
-            oauth_data["scopes"] = scopes
-        elif "claudeAiOauth" in existing and "scopes" in existing["claudeAiOauth"]:
-            # Preserve previously-stored scopes when the refresh response
-            # does not include a scope field.
-            oauth_data["scopes"] = existing["claudeAiOauth"]["scopes"]
-
-        existing["claudeAiOauth"] = oauth_data

        cred_path.parent.mkdir(parents=True, exist_ok=True)
        cred_path.write_text(json.dumps(existing, indent=2), encoding="utf-8")
@@ -585,208 +439,10 @@ def run_oauth_setup_token() -> Optional[str]:
    return None


-# ── Hermes-native PKCE OAuth flow ────────────────────────────────────────
-# Mirrors the flow used by Claude Code, pi-ai, and OpenCode.
-# Stores credentials in ~/.hermes/.anthropic_oauth.json (our own file).
-
-_OAUTH_CLIENT_ID = "9d1c250a-e61b-44d9-88ed-5944d1962f5e"
-_OAUTH_TOKEN_URL = "https://console.anthropic.com/v1/oauth/token"
-_OAUTH_REDIRECT_URI = "https://console.anthropic.com/oauth/code/callback"
-_OAUTH_SCOPES = "org:create_api_key user:profile user:inference"
-_HERMES_OAUTH_FILE = get_hermes_home() / ".anthropic_oauth.json"


-def _generate_pkce() -> tuple:
-    """Generate PKCE code_verifier and code_challenge (S256)."""
-    import base64
-    import hashlib
-    import secrets
-
-    verifier = base64.urlsafe_b64encode(secrets.token_bytes(32)).rstrip(b"=").decode()
-    challenge = base64.urlsafe_b64encode(
-        hashlib.sha256(verifier.encode()).digest()
-    ).rstrip(b"=").decode()
-    return verifier, challenge


-def run_hermes_oauth_login_pure() -> Optional[Dict[str, Any]]:
-    """Run Hermes-native OAuth PKCE flow and return credential state."""
-    import time
-    import webbrowser
-
-    verifier, challenge = _generate_pkce()
-
-    params = {
-        "code": "true",
-        "client_id": _OAUTH_CLIENT_ID,
-        "response_type": "code",
-        "redirect_uri": _OAUTH_REDIRECT_URI,
-        "scope": _OAUTH_SCOPES,
-        "code_challenge": challenge,
-        "code_challenge_method": "S256",
-        "state": verifier,
-    }
-    from urllib.parse import urlencode
-
-    auth_url = f"https://claude.ai/oauth/authorize?{urlencode(params)}"
-
-    print()
-    print("Authorize Hermes with your Claude Pro/Max subscription.")
-    print()
-    print("╭─ Claude Pro/Max Authorization ────────────────────╮")
-    print("│                                                   │")
-    print("│  Open this link in your browser:                  │")
-    print("╰───────────────────────────────────────────────────╯")
-    print()
-    print(f"  {auth_url}")
-    print()
-
-    try:
-        webbrowser.open(auth_url)
-        print("  (Browser opened automatically)")
-    except Exception:
-        pass
-
-    print()
-    print("After authorizing, you'll see a code. Paste it below.")
-    print()
-    try:
-        auth_code = input("Authorization code: ").strip()
-    except (KeyboardInterrupt, EOFError):
-        return None
-
-    if not auth_code:
-        print("No code entered.")
-        return None
-
-    splits = auth_code.split("#")
-    code = splits[0]
-    state = splits[1] if len(splits) > 1 else ""
-
-    try:
-        import urllib.request
-
-        exchange_data = json.dumps({
-            "grant_type": "authorization_code",
-            "client_id": _OAUTH_CLIENT_ID,
-            "code": code,
-            "state": state,
-            "redirect_uri": _OAUTH_REDIRECT_URI,
-            "code_verifier": verifier,
-        }).encode()
-
-        req = urllib.request.Request(
-            _OAUTH_TOKEN_URL,
-            data=exchange_data,
-            headers={
-                "Content-Type": "application/json",
-                "User-Agent": f"claude-cli/{_get_claude_code_version()} (external, cli)",
-            },
-            method="POST",
-        )
-
-        with urllib.request.urlopen(req, timeout=15) as resp:
-            result = json.loads(resp.read().decode())
-    except Exception as e:
-        print(f"Token exchange failed: {e}")
-        return None
-
-    access_token = result.get("access_token", "")
-    refresh_token = result.get("refresh_token", "")
-    expires_in = result.get("expires_in", 3600)
-
-    if not access_token:
-        print("No access token in response.")
-        return None
-
-    expires_at_ms = int(time.time() * 1000) + (expires_in * 1000)
-    return {
-        "access_token": access_token,
-        "refresh_token": refresh_token,
-        "expires_at_ms": expires_at_ms,
-    }
-
-
-def run_hermes_oauth_login() -> Optional[str]:
-    """Run Hermes-native OAuth PKCE flow for Claude Pro/Max subscription.
-
-    Opens a browser to claude.ai for authorization, prompts for the code,
-    exchanges it for tokens, and stores them in ~/.hermes/.anthropic_oauth.json.
-
-    Returns the access token on success, None on failure.
-    """
-    result = run_hermes_oauth_login_pure()
-    if not result:
-        return None
-
-    access_token = result["access_token"]
-    refresh_token = result["refresh_token"]
-    expires_at_ms = result["expires_at_ms"]
-
-    _save_hermes_oauth_credentials(access_token, refresh_token, expires_at_ms)
-    _write_claude_code_credentials(access_token, refresh_token, expires_at_ms)
-
-    print("Authentication successful!")
-    return access_token
-
-
-def _save_hermes_oauth_credentials(access_token: str, refresh_token: str, expires_at_ms: int) -> None:
-    """Save OAuth credentials to ~/.hermes/.anthropic_oauth.json."""
-    data = {
-        "accessToken": access_token,
-        "refreshToken": refresh_token,
-        "expiresAt": expires_at_ms,
-    }
-    try:
-        _HERMES_OAUTH_FILE.parent.mkdir(parents=True, exist_ok=True)
-        _HERMES_OAUTH_FILE.write_text(json.dumps(data, indent=2), encoding="utf-8")
-        _HERMES_OAUTH_FILE.chmod(0o600)
-    except (OSError, IOError) as e:
-        logger.debug("Failed to save Hermes OAuth credentials: %s", e)
-
-
-def read_hermes_oauth_credentials() -> Optional[Dict[str, Any]]:
-    """Read Hermes-managed OAuth credentials from ~/.hermes/.anthropic_oauth.json."""
-    if _HERMES_OAUTH_FILE.exists():
-        try:
-            data = json.loads(_HERMES_OAUTH_FILE.read_text(encoding="utf-8"))
-            if data.get("accessToken"):
-                return data
-        except (json.JSONDecodeError, OSError, IOError) as e:
-            logger.debug("Failed to read Hermes OAuth credentials: %s", e)
-    return None
-
-
-def refresh_hermes_oauth_token() -> Optional[str]:
-    """Refresh the Hermes-managed OAuth token using the stored refresh token.
-
-    Returns the new access token, or None if refresh fails.
-    """
-    creds = read_hermes_oauth_credentials()
-    if not creds or not creds.get("refreshToken"):
-        return None
-
-    try:
-        refreshed = refresh_anthropic_oauth_pure(
-            creds["refreshToken"],
-            use_json=True,
-        )
-        _save_hermes_oauth_credentials(
-            refreshed["access_token"],
-            refreshed["refresh_token"],
-            refreshed["expires_at_ms"],
-        )
-        _write_claude_code_credentials(
-            refreshed["access_token"],
-            refreshed["refresh_token"],
-            refreshed["expires_at_ms"],
-        )
-        logger.debug("Successfully refreshed Hermes OAuth token")
-        return refreshed["access_token"]
-    except Exception as e:
-        logger.debug("Failed to refresh Hermes OAuth token: %s", e)
-
-    return None


 # ---------------------------------------------------------------------------
@@ -1050,21 +706,14 @@ def convert_messages_to_anthropic(
                result.append({"role": "user", "content": [tool_result]})
            continue

-        # Regular user message — validate non-empty content (Anthropic rejects empty)
+        # Regular user message
        if isinstance(content, list):
            converted_blocks = _convert_content_to_anthropic(content)
-            # Check if all text blocks are empty
-            if not converted_blocks or all(
-                b.get("text", "").strip() == ""
-                for b in converted_blocks
-                if isinstance(b, dict) and b.get("type") == "text"
-            ):
-                converted_blocks = [{"type": "text", "text": "(empty message)"}]
-            result.append({"role": "user", "content": converted_blocks})
+            result.append({
+                "role": "user",
+                "content": converted_blocks or [{"type": "text", "text": ""}],
+            })
        else:
-            # Validate string content is non-empty
-            if not content or (isinstance(content, str) and not content.strip()):
-                content = "(empty message)"
            result.append({"role": "user", "content": content})

    # Strip orphaned tool_use blocks (no matching tool_result follows)
@@ -1154,15 +803,9 @@ def build_anthropic_kwargs(
    tool_choice: Optional[str] = None,
    is_oauth: bool = False,
    preserve_dots: bool = False,
-    context_length: Optional[int] = None,
 ) -> Dict[str, Any]:
    """Build kwargs for anthropic.messages.create().

-    When *max_tokens* is None, the model's native output limit is used
-    (e.g. 128K for Opus 4.6, 64K for Sonnet 4.6).  If *context_length*
-    is provided, the effective limit is clamped so it doesn't exceed
-    the context window.
-
    When *is_oauth* is True, applies Claude Code compatibility transforms:
    system prompt prefix, tool name prefixing, and prompt sanitization.

@@ -1173,12 +816,7 @@ def build_anthropic_kwargs(
    anthropic_tools = convert_tools_to_anthropic(tools) if tools else []

    model = normalize_model_name(model, preserve_dots=preserve_dots)
-    effective_max_tokens = max_tokens or _get_anthropic_max_output(model)
-
-    # Clamp to context window if the user set a lower context_length
-    # (e.g. custom endpoint with limited capacity).
-    if context_length and effective_max_tokens > context_length:
-        effective_max_tokens = max(context_length - 1, 1)
+    effective_max_tokens = max_tokens or 16384

    # ── OAuth: Claude Code identity ──────────────────────────────────
    if is_oauth:
@@ -1319,4 +957,4 @@ def normalize_anthropic_response(
            reasoning_details=None,
        ),
        finish_reason,
-    )
+    )
@@ -7,7 +7,7 @@ the best available backend without duplicating fallback logic.
 Resolution order for text tasks (auto mode):
  1. OpenRouter  (OPENROUTER_API_KEY)
  2. Nous Portal (~/.hermes/auth.json active provider)
-  3. Custom endpoint (config.yaml model.base_url + OPENAI_API_KEY)
+  3. Custom endpoint (OPENAI_BASE_URL + OPENAI_API_KEY)
  4. Codex OAuth (Responses API via chatgpt.com with gpt-5.3-codex,
     wrapped to look like a chat.completions client)
  5. Native Anthropic
@@ -47,7 +47,6 @@ from typing import Any, Dict, List, Optional, Tuple

 from openai import OpenAI

-from agent.credential_pool import load_pool
 from hermes_cli.config import get_hermes_home
 from hermes_constants import OPENROUTER_BASE_URL

@@ -97,45 +96,6 @@ _CODEX_AUX_MODEL = "gpt-5.2-codex"
 _CODEX_AUX_BASE_URL = "https://chatgpt.com/backend-api/codex"


-def _select_pool_entry(provider: str) -> Tuple[bool, Optional[Any]]:
-    """Return (pool_exists_for_provider, selected_entry)."""
-    try:
-        pool = load_pool(provider)
-    except Exception as exc:
-        logger.debug("Auxiliary client: could not load pool for %s: %s", provider, exc)
-        return False, None
-    if not pool or not pool.has_credentials():
-        return False, None
-    try:
-        return True, pool.select()
-    except Exception as exc:
-        logger.debug("Auxiliary client: could not select pool entry for %s: %s", provider, exc)
-        return True, None
-
-
-def _pool_runtime_api_key(entry: Any) -> str:
-    if entry is None:
-        return ""
-    # Use the PooledCredential.runtime_api_key property which handles
-    # provider-specific fallback (e.g. agent_key for nous).
-    key = getattr(entry, "runtime_api_key", None) or getattr(entry, "access_token", "")
-    return str(key or "").strip()
-
-
-def _pool_runtime_base_url(entry: Any, fallback: str = "") -> str:
-    if entry is None:
-        return str(fallback or "").strip().rstrip("/")
-    # runtime_base_url handles provider-specific logic (e.g. nous prefers inference_base_url).
-    # Fall back through inference_base_url and base_url for non-PooledCredential entries.
-    url = (
-        getattr(entry, "runtime_base_url", None)
-        or getattr(entry, "inference_base_url", None)
-        or getattr(entry, "base_url", None)
-        or fallback
-    )
-    return str(url or "").strip().rstrip("/")
-
-
 # ── Codex Responses → chat.completions adapter ─────────────────────────────
 # All auxiliary consumers call client.chat.completions.create(**kwargs) and
 # read response.choices[0].message.content. This adapter translates those
@@ -479,22 +439,6 @@ def _read_nous_auth() -> Optional[dict]:
    Returns the provider state dict if Nous is active with tokens,
    otherwise None.
    """
-    pool_present, entry = _select_pool_entry("nous")
-    if pool_present:
-        if entry is None:
-            return None
-        return {
-            "access_token": getattr(entry, "access_token", ""),
-            "refresh_token": getattr(entry, "refresh_token", None),
-            "agent_key": getattr(entry, "agent_key", None),
-            "inference_base_url": _pool_runtime_base_url(entry, _NOUS_DEFAULT_BASE_URL),
-            "portal_base_url": getattr(entry, "portal_base_url", None),
-            "client_id": getattr(entry, "client_id", None),
-            "scope": getattr(entry, "scope", None),
-            "token_type": getattr(entry, "token_type", "Bearer"),
-            "source": "pool",
-        }
-
    try:
        if not _AUTH_JSON_PATH.is_file():
            return None
@@ -523,11 +467,6 @@ def _nous_base_url() -> str:

 def _read_codex_access_token() -> Optional[str]:
    """Read a valid, non-expired Codex OAuth access token from Hermes auth store."""
-    pool_present, entry = _select_pool_entry("openai-codex")
-    if pool_present:
-        token = _pool_runtime_api_key(entry)
-        return token or None
-
    try:
        from hermes_cli.auth import _read_codex_tokens
        data = _read_codex_tokens()
@@ -574,24 +513,6 @@ def _resolve_api_key_provider() -> Tuple[Optional[OpenAI], Optional[str]]:
        if provider_id == "anthropic":
            return _try_anthropic()

-        pool_present, entry = _select_pool_entry(provider_id)
-        if pool_present:
-            api_key = _pool_runtime_api_key(entry)
-            if not api_key:
-                continue
-
-            base_url = _pool_runtime_base_url(entry, pconfig.inference_base_url) or pconfig.inference_base_url
-            model = _API_KEY_PROVIDER_AUX_MODELS.get(provider_id, "default")
-            logger.debug("Auxiliary text client: %s (%s) via pool", pconfig.name, model)
-            extra = {}
-            if "api.kimi.com" in base_url.lower():
-                extra["default_headers"] = {"User-Agent": "KimiCLI/1.0"}
-            elif "api.githubcopilot.com" in base_url.lower():
-                from hermes_cli.models import copilot_default_headers
-
-                extra["default_headers"] = copilot_default_headers()
-            return OpenAI(api_key=api_key, base_url=base_url, **extra), model
-
        creds = resolve_api_key_provider_credentials(provider_id)
        api_key = str(creds.get("api_key", "")).strip()
        if not api_key:
@@ -641,16 +562,6 @@ def _get_auxiliary_env_override(task: str, suffix: str) -> Optional[str]:


 def _try_openrouter() -> Tuple[Optional[OpenAI], Optional[str]]:
-    pool_present, entry = _select_pool_entry("openrouter")
-    if pool_present:
-        or_key = _pool_runtime_api_key(entry)
-        if not or_key:
-            return None, None
-        base_url = _pool_runtime_base_url(entry, OPENROUTER_BASE_URL) or OPENROUTER_BASE_URL
-        logger.debug("Auxiliary client: OpenRouter via pool")
-        return OpenAI(api_key=or_key, base_url=base_url,
-                       default_headers=_OR_HEADERS), _OPENROUTER_MODEL
-
    or_key = os.getenv("OPENROUTER_API_KEY")
    if not or_key:
        return None, None
@@ -666,22 +577,22 @@ def _try_nous() -> Tuple[Optional[OpenAI], Optional[str]]:
    global auxiliary_is_nous
    auxiliary_is_nous = True
    logger.debug("Auxiliary client: Nous Portal")
-    model = "gemini-3-flash" if nous.get("source") == "pool" else _NOUS_MODEL
    return (
-        OpenAI(
-            api_key=_nous_api_key(nous),
-            base_url=str(nous.get("inference_base_url") or _nous_base_url()).rstrip("/"),
-        ),
-        model,
+        OpenAI(api_key=_nous_api_key(nous), base_url=_nous_base_url()),
+        _NOUS_MODEL,
    )


 def _read_main_model() -> str:
-    """Read the user's configured main model from config.yaml.
+    """Read the user's configured main model from config/env.

-    config.yaml model.default is the single source of truth for the active
-    model. Environment variables are no longer consulted.
+    Falls back through HERMES_MODEL → LLM_MODEL → config.yaml model.default
+    so the auxiliary client can use the same model as the main agent when no
+    dedicated auxiliary model is available.
    """
+    from_env = os.getenv("OPENAI_MODEL") or os.getenv("HERMES_MODEL") or os.getenv("LLM_MODEL")
+    if from_env:
+        return from_env.strip()
    try:
        from hermes_cli.config import load_config
        cfg = load_config()
@@ -716,6 +627,8 @@ def _resolve_custom_runtime() -> Tuple[Optional[str], Optional[str]]:
    custom_key = runtime.get("api_key")
    if not isinstance(custom_base, str) or not custom_base.strip():
        return None, None
+    if not isinstance(custom_key, str) or not custom_key.strip():
+        return None, None

    custom_base = custom_base.strip().rstrip("/")
    if "openrouter.ai" in custom_base.lower():
@@ -723,13 +636,6 @@ def _resolve_custom_runtime() -> Tuple[Optional[str], Optional[str]]:
        # configured. Treat that as "no custom endpoint" for auxiliary routing.
        return None, None

-    # Local servers (Ollama, llama.cpp, vLLM, LM Studio) don't require auth.
-    # Use a placeholder key — the OpenAI SDK requires a non-empty string but
-    # local servers ignore the Authorization header.  Same fix as cli.py
-    # _ensure_runtime_credentials() (PR #2556).
-    if not isinstance(custom_key, str) or not custom_key.strip():
-        custom_key = "no-key-required"
-
    return custom_base, custom_key.strip()


@@ -748,19 +654,11 @@ def _try_custom_endpoint() -> Tuple[Optional[OpenAI], Optional[str]]:


 def _try_codex() -> Tuple[Optional[Any], Optional[str]]:
-    pool_present, entry = _select_pool_entry("openai-codex")
-    if pool_present:
-        codex_token = _pool_runtime_api_key(entry)
-        if not codex_token:
-            return None, None
-        base_url = _pool_runtime_base_url(entry, _CODEX_AUX_BASE_URL) or _CODEX_AUX_BASE_URL
-    else:
-        codex_token = _read_codex_access_token()
-        if not codex_token:
-            return None, None
-        base_url = _CODEX_AUX_BASE_URL
+    codex_token = _read_codex_access_token()
+    if not codex_token:
+        return None, None
    logger.debug("Auxiliary client: Codex OAuth (%s via Responses API)", _CODEX_AUX_MODEL)
-    real_client = OpenAI(api_key=codex_token, base_url=base_url)
+    real_client = OpenAI(api_key=codex_token, base_url=_CODEX_AUX_BASE_URL)
    return CodexAuxiliaryClient(real_client, _CODEX_AUX_MODEL), _CODEX_AUX_MODEL


@@ -770,21 +668,14 @@ def _try_anthropic() -> Tuple[Optional[Any], Optional[str]]:
    except ImportError:
        return None, None

-    pool_present, entry = _select_pool_entry("anthropic")
-    if pool_present:
-        if entry is None:
-            return None, None
-        token = _pool_runtime_api_key(entry)
-    else:
-        entry = None
-        token = resolve_anthropic_token()
+    token = resolve_anthropic_token()
    if not token:
        return None, None

    # Allow base URL override from config.yaml model.base_url, but only
    # when the configured provider is anthropic — otherwise a non-Anthropic
    # base_url (e.g. Codex endpoint) would leak into Anthropic requests.
-    base_url = _pool_runtime_base_url(entry, _ANTHROPIC_DEFAULT_BASE_URL) if pool_present else _ANTHROPIC_DEFAULT_BASE_URL
+    base_url = _ANTHROPIC_DEFAULT_BASE_URL
    try:
        from hermes_cli.config import load_config
        cfg = load_config()
@@ -802,13 +693,7 @@ def _try_anthropic() -> Tuple[Optional[Any], Optional[str]]:
    is_oauth = _is_oauth_token(token)
    model = _API_KEY_PROVIDER_AUX_MODELS.get("anthropic", "claude-haiku-4-5-20251001")
    logger.debug("Auxiliary client: Anthropic native (%s) at %s (oauth=%s)", model, base_url, is_oauth)
-    try:
-        real_client = build_anthropic_client(token, base_url)
-    except ImportError:
-        # The anthropic_adapter module imports fine but the SDK itself is
-        # missing — build_anthropic_client raises ImportError at call time
-        # when _anthropic_sdk is None.  Treat as unavailable.
-        return None, None
+    real_client = build_anthropic_client(token, base_url)
    return AnthropicAuxiliaryClient(real_client, model, token, base_url, is_oauth=is_oauth), model


@@ -846,37 +731,16 @@ def _resolve_forced_provider(forced: str) -> Tuple[Optional[OpenAI], Optional[st
    return None, None


-_AUTO_PROVIDER_LABELS = {
-    "_try_openrouter": "openrouter",
-    "_try_nous": "nous",
-    "_try_custom_endpoint": "local/custom",
-    "_try_codex": "openai-codex",
-    "_resolve_api_key_provider": "api-key",
-}
-
-
 def _resolve_auto() -> Tuple[Optional[OpenAI], Optional[str]]:
    """Full auto-detection chain: OpenRouter → Nous → custom → Codex → API-key → None."""
    global auxiliary_is_nous
    auxiliary_is_nous = False  # Reset — _try_nous() will set True if it wins
-    tried = []
    for try_fn in (_try_openrouter, _try_nous, _try_custom_endpoint,
                   _try_codex, _resolve_api_key_provider):
-        fn_name = getattr(try_fn, "__name__", "unknown")
-        label = _AUTO_PROVIDER_LABELS.get(fn_name, fn_name)
        client, model = try_fn()
        if client is not None:
-            if tried:
-                logger.info("Auxiliary auto-detect: using %s (%s) — skipped: %s",
-                            label, model or "default", ", ".join(tried))
-            else:
-                logger.info("Auxiliary auto-detect: using %s (%s)", label, model or "default")
            return client, model
-        tried.append(label)
-    logger.warning("Auxiliary auto-detect: no provider available (tried: %s). "
-                   "Compression, summarization, and memory flush will not work. "
-                   "Set OPENROUTER_API_KEY or configure a local model in config.yaml.",
-                   ", ".join(tried))
+    logger.debug("Auxiliary client: none available")
    return None, None


@@ -1027,12 +891,11 @@ def resolve_provider_client(
            custom_key = (
                (explicit_api_key or "").strip()
                or os.getenv("OPENAI_API_KEY", "").strip()
-                or "no-key-required"  # local servers don't need auth
            )
-            if not custom_base:
+            if not custom_base or not custom_key:
                logger.warning(
                    "resolve_provider_client: explicit custom endpoint requested "
-                    "but base_url is empty"
+                    "but no API key was found (set explicit_api_key or OPENAI_API_KEY)"
                )
                return None, None
            final_model = model or _read_main_model() or "gpt-4o-mini"
@@ -1268,13 +1131,7 @@ def resolve_vision_provider_client(
        return "custom", client, final_model

    if requested == "auto":
-        ordered = list(_VISION_AUTO_PROVIDER_ORDER)
-        preferred = _preferred_main_vision_provider()
-        if preferred in ordered:
-            ordered.remove(preferred)
-            ordered.insert(0, preferred)
-
-        for candidate in ordered:
+        for candidate in get_available_vision_backends():
            sync_client, default_model = _resolve_strict_vision_backend(candidate)
            if sync_client is not None:
                return _finalize(candidate, sync_client, default_model)
@@ -1347,39 +1204,6 @@ _client_cache: Dict[tuple, tuple] = {}
 _client_cache_lock = threading.Lock()


-def neuter_async_httpx_del() -> None:
-    """Monkey-patch ``AsyncHttpxClientWrapper.__del__`` to be a no-op.
-
-    The OpenAI SDK's ``AsyncHttpxClientWrapper.__del__`` schedules
-    ``self.aclose()`` via ``asyncio.get_running_loop().create_task()``.
-    When an ``AsyncOpenAI`` client is garbage-collected while
-    prompt_toolkit's event loop is running (the common CLI idle state),
-    the ``aclose()`` task runs on prompt_toolkit's loop but the
-    underlying TCP transport is bound to a *different* loop (the worker
-    thread's loop that the client was originally created on).  If that
-    loop is closed or its thread is dead, the transport's
-    ``self._loop.call_soon()`` raises ``RuntimeError("Event loop is
-    closed")``, which prompt_toolkit surfaces as "Unhandled exception
-    in event loop ... Press ENTER to continue...".
-
-    Neutering ``__del__`` is safe because:
-    - Cached clients are explicitly cleaned via ``_force_close_async_httpx``
-      on stale-loop detection and ``shutdown_cached_clients`` on exit.
-    - Uncached clients' TCP connections are cleaned up by the OS when the
-      process exits.
-    - The OpenAI SDK itself marks this as a TODO (``# TODO(someday):
-      support non asyncio runtimes here``).
-
-    Call this once at CLI startup, before any ``AsyncOpenAI`` clients are
-    created.
-    """
-    try:
-        from openai._base_client import AsyncHttpxClientWrapper
-        AsyncHttpxClientWrapper.__del__ = lambda self: None  # type: ignore[assignment]
-    except (ImportError, AttributeError):
-        pass  # Graceful degradation if the SDK changes its internals
-
-
 def _force_close_async_httpx(client: Any) -> None:
    """Mark the httpx AsyncClient inside an AsyncOpenAI client as closed.

@@ -1427,25 +1251,6 @@ def shutdown_cached_clients() -> None:
        _client_cache.clear()


-def cleanup_stale_async_clients() -> None:
-    """Force-close cached async clients whose event loop is closed.
-
-    Call this after each agent turn to proactively clean up stale clients
-    before GC can trigger ``AsyncHttpxClientWrapper.__del__`` on them.
-    This is defense-in-depth — the primary fix is ``neuter_async_httpx_del``
-    which disables ``__del__`` entirely.
-    """
-    with _client_cache_lock:
-        stale_keys = []
-        for key, entry in _client_cache.items():
-            client, _default, cached_loop = entry
-            if cached_loop is not None and cached_loop.is_closed():
-                _force_close_async_httpx(client)
-                stale_keys.append(key)
-        for key in stale_keys:
-            del _client_cache[key]
-
-
 def _get_cached_client(
    provider: str,
    model: str = None,
@@ -1589,29 +1394,6 @@ def _resolve_task_provider_model(
    return "auto", resolved_model, None, None


-_DEFAULT_AUX_TIMEOUT = 30.0
-
-
-def _get_task_timeout(task: str, default: float = _DEFAULT_AUX_TIMEOUT) -> float:
-    """Read timeout from auxiliary.{task}.timeout in config, falling back to *default*."""
-    if not task:
-        return default
-    try:
-        from hermes_cli.config import load_config
-        config = load_config()
-    except ImportError:
-        return default
-    aux = config.get("auxiliary", {}) if isinstance(config, dict) else {}
-    task_config = aux.get(task, {}) if isinstance(aux, dict) else {}
-    raw = task_config.get("timeout")
-    if raw is not None:
-        try:
-            return float(raw)
-        except (ValueError, TypeError):
-            pass
-    return default
-
-
 def _build_call_kwargs(
    provider: str,
    model: str,
@@ -1669,7 +1451,7 @@ def call_llm(
    temperature: float = None,
    max_tokens: int = None,
    tools: list = None,
-    timeout: float = None,
+    timeout: float = 30.0,
    extra_body: dict = None,
 ) -> Any:
    """Centralized synchronous LLM call.
@@ -1687,7 +1469,7 @@ def call_llm(
        temperature: Sampling temperature (None = provider default).
        max_tokens: Max output tokens (handles max_tokens vs max_completion_tokens).
        tools: Tool definitions (for function calling).
-        timeout: Request timeout in seconds (None = read from auxiliary.{task}.timeout config).
+        timeout: Request timeout in seconds.
        extra_body: Additional request body fields.

    Returns:
@@ -1743,8 +1525,8 @@ def call_llm(
                )
            # For auto/custom, fall back to OpenRouter
            if not resolved_base_url:
-                logger.info("Auxiliary %s: provider %s unavailable, falling back to openrouter",
-                            task or "call", resolved_provider)
+                logger.warning("Provider %s unavailable, falling back to openrouter",
+                               resolved_provider)
                client, final_model = _get_cached_client(
                    "openrouter", resolved_model or _OPENROUTER_MODEL)
        if client is None:
@@ -1752,19 +1534,10 @@ def call_llm(
                f"No LLM provider configured for task={task} provider={resolved_provider}. "
                f"Run: hermes setup")

-    effective_timeout = timeout if timeout is not None else _get_task_timeout(task)
-
-    # Log what we're about to do — makes auxiliary operations visible
-    _base_info = str(getattr(client, "base_url", resolved_base_url) or "")
-    if task:
-        logger.info("Auxiliary %s: using %s (%s)%s",
-                     task, resolved_provider or "auto", final_model or "default",
-                     f" at {_base_info}" if _base_info and "openrouter" not in _base_info else "")
-
    kwargs = _build_call_kwargs(
        resolved_provider, final_model, messages,
        temperature=temperature, max_tokens=max_tokens,
-        tools=tools, timeout=effective_timeout, extra_body=extra_body,
+        tools=tools, timeout=timeout, extra_body=extra_body,
        base_url=resolved_base_url)

    # Handle max_tokens vs max_completion_tokens retry
@@ -1779,62 +1552,6 @@ def call_llm(
        raise


-def extract_content_or_reasoning(response) -> str:
-    """Extract content from an LLM response, falling back to reasoning fields.
-
-    Mirrors the main agent loop's behavior when a reasoning model (DeepSeek-R1,
-    Qwen-QwQ, etc.) returns ``content=None`` with reasoning in structured fields.
-
-    Resolution order:
-      1. ``message.content`` — strip inline think/reasoning blocks, check for
-         remaining non-whitespace text.
-      2. ``message.reasoning`` / ``message.reasoning_content`` — direct
-         structured reasoning fields (DeepSeek, Moonshot, Novita, etc.).
-      3. ``message.reasoning_details`` — OpenRouter unified array format.
-
-    Returns the best available text, or ``""`` if nothing found.
-    """
-    import re
-
-    msg = response.choices[0].message
-    content = (msg.content or "").strip()
-
-    if content:
-        # Strip inline think/reasoning blocks (mirrors _strip_think_blocks)
-        cleaned = re.sub(
-            r"<(?:think|thinking|reasoning|REASONING_SCRATCHPAD)>"
-            r".*?"
-            r"</(?:think|thinking|reasoning|REASONING_SCRATCHPAD)>",
-            "", content, flags=re.DOTALL | re.IGNORECASE,
-        ).strip()
-        if cleaned:
-            return cleaned
-
-    # Content is empty or reasoning-only — try structured reasoning fields
-    reasoning_parts: list[str] = []
-    for field in ("reasoning", "reasoning_content"):
-        val = getattr(msg, field, None)
-        if val and isinstance(val, str) and val.strip() and val not in reasoning_parts:
-            reasoning_parts.append(val.strip())
-
-    details = getattr(msg, "reasoning_details", None)
-    if details and isinstance(details, list):
-        for detail in details:
-            if isinstance(detail, dict):
-                summary = (
-                    detail.get("summary")
-                    or detail.get("content")
-                    or detail.get("text")
-                )
-                if summary and summary not in reasoning_parts:
-                    reasoning_parts.append(summary.strip() if isinstance(summary, str) else str(summary))
-
-    if reasoning_parts:
-        return "\n\n".join(reasoning_parts)
-
-    return ""
-
-
 async def async_call_llm(
    task: str = None,
    *,
@@ -1846,7 +1563,7 @@ async def async_call_llm(
    temperature: float = None,
    max_tokens: int = None,
    tools: list = None,
-    timeout: float = None,
+    timeout: float = 30.0,
    extra_body: dict = None,
 ) -> Any:
    """Centralized asynchronous LLM call.
@@ -1907,12 +1624,10 @@ async def async_call_llm(
                f"No LLM provider configured for task={task} provider={resolved_provider}. "
                f"Run: hermes setup")

-    effective_timeout = timeout if timeout is not None else _get_task_timeout(task)
-
    kwargs = _build_call_kwargs(
        resolved_provider, final_model, messages,
        temperature=temperature, max_tokens=max_tokens,
-        tools=tools, timeout=effective_timeout, extra_body=extra_body,
+        tools=tools, timeout=timeout, extra_body=extra_body,
        base_url=resolved_base_url)

    try:
@@ -141,7 +141,7 @@ class ContextCompressor:
            "last_prompt_tokens": self.last_prompt_tokens,
            "threshold_tokens": self.threshold_tokens,
            "context_length": self.context_length,
-            "usage_percent": min(100, (self.last_prompt_tokens / self.context_length * 100)) if self.context_length else 0,
+            "usage_percent": (self.last_prompt_tokens / self.context_length * 100) if self.context_length else 0,
            "compression_count": self.compression_count,
        }

@@ -347,7 +347,7 @@ Write only the summary body. Do not include any preamble or prefix."""
                "messages": [{"role": "user", "content": prompt}],
                "temperature": 0.3,
                "max_tokens": summary_budget * 2,
-                # timeout resolved from auxiliary.compression.timeout config by call_llm
+                "timeout": 45.0,
            }
            if self.summary_model:
                call_kwargs["model"] = self.summary_model
@@ -17,7 +17,7 @@ REFERENCE_PATTERN = re.compile(
    r"(?<![\w/])@(?:(?P<simple>diff|staged)\b|(?P<kind>file|folder|git|url):(?P<value>\S+))"
 )
 TRAILING_PUNCTUATION = ",.;!?"
-_SENSITIVE_HOME_DIRS = (".ssh", ".aws", ".gnupg", ".kube", ".docker", ".azure", ".config/gh")
+_SENSITIVE_HOME_DIRS = (".ssh", ".aws", ".gnupg", ".kube")
 _SENSITIVE_HERMES_DIRS = (Path("skills") / ".hub",)
 _SENSITIVE_HOME_FILES = (
    Path(".ssh") / "authorized_keys",
@@ -286,16 +286,12 @@ def _expand_git_reference(
    args: list[str],
    label: str,
 ) -> tuple[str | None, str | None]:
-    try:
-        result = subprocess.run(
-            ["git", *args],
-            cwd=cwd,
-            capture_output=True,
-            text=True,
-            timeout=30,
-        )
-    except subprocess.TimeoutExpired:
-        return f"{ref.raw}: git command timed out (30s)", None
+    result = subprocess.run(
+        ["git", *args],
+        cwd=cwd,
+        capture_output=True,
+        text=True,
+    )
    if result.returncode != 0:
        stderr = (result.stderr or "").strip() or "git command failed"
        return f"{ref.raw}: {stderr}", None
@@ -453,12 +449,9 @@ def _rg_files(path: Path, cwd: Path, limit: int) -> list[Path] | None:
            cwd=cwd,
            capture_output=True,
            text=True,
-            timeout=10,
        )
    except FileNotFoundError:
        return None
-    except subprocess.TimeoutExpired:
-        return None
    if result.returncode != 0:
        return None
    files = [Path(line.strip()) for line in result.stdout.splitlines() if line.strip()]
@@ -1,848 +0,0 @@
-"""Persistent multi-credential pool for same-provider failover."""
-
-from __future__ import annotations
-
-import logging
-import random
-import threading
-import time
-import uuid
-import os
-from dataclasses import dataclass, fields, replace
-from typing import Any, Dict, List, Optional, Set, Tuple
-
-from hermes_constants import OPENROUTER_BASE_URL
-import hermes_cli.auth as auth_mod
-from hermes_cli.auth import (
-    ACCESS_TOKEN_REFRESH_SKEW_SECONDS,
-    CODEX_ACCESS_TOKEN_REFRESH_SKEW_SECONDS,
-    DEFAULT_AGENT_KEY_MIN_TTL_SECONDS,
-    PROVIDER_REGISTRY,
-    _agent_key_is_usable,
-    _codex_access_token_is_expiring,
-    _decode_jwt_claims,
-    _is_expiring,
-    _load_auth_store,
-    _load_provider_state,
-    read_credential_pool,
-    write_credential_pool,
-)
-
-logger = logging.getLogger(__name__)
-
-
-def _load_config_safe() -> Optional[dict]:
-    """Load config.yaml, returning None on any error."""
-    try:
-        from hermes_cli.config import load_config
-
-        return load_config()
-    except Exception:
-        return None
-
-
-# --- Status and type constants ---
-
-STATUS_OK = "ok"
-STATUS_EXHAUSTED = "exhausted"
-
-AUTH_TYPE_OAUTH = "oauth"
-AUTH_TYPE_API_KEY = "api_key"
-
-SOURCE_MANUAL = "manual"
-
-STRATEGY_FILL_FIRST = "fill_first"
-STRATEGY_ROUND_ROBIN = "round_robin"
-STRATEGY_RANDOM = "random"
-STRATEGY_LEAST_USED = "least_used"
-SUPPORTED_POOL_STRATEGIES = {
-    STRATEGY_FILL_FIRST,
-    STRATEGY_ROUND_ROBIN,
-    STRATEGY_RANDOM,
-    STRATEGY_LEAST_USED,
-}
-
-# Cooldown before retrying an exhausted credential.
-# 429 (rate-limited) cools down faster since quotas reset frequently.
-# 402 (billing/quota) and other codes use a longer default.
-EXHAUSTED_TTL_429_SECONDS = 60 * 60          # 1 hour
-EXHAUSTED_TTL_DEFAULT_SECONDS = 24 * 60 * 60 # 24 hours
-
-# Pool key prefix for custom OpenAI-compatible endpoints.
-# Custom endpoints all share provider='custom' but are keyed by their
-# custom_providers name: 'custom:<normalized_name>'.
-CUSTOM_POOL_PREFIX = "custom:"
-
-
-# Fields that are only round-tripped through JSON — never used for logic as attributes.
-_EXTRA_KEYS = frozenset({
-    "token_type", "scope", "client_id", "portal_base_url", "obtained_at",
-    "expires_in", "agent_key_id", "agent_key_expires_in", "agent_key_reused",
-    "agent_key_obtained_at", "tls",
-})
-
-
-@dataclass
-class PooledCredential:
-    provider: str
-    id: str
-    label: str
-    auth_type: str
-    priority: int
-    source: str
-    access_token: str
-    refresh_token: Optional[str] = None
-    last_status: Optional[str] = None
-    last_status_at: Optional[float] = None
-    last_error_code: Optional[int] = None
-    base_url: Optional[str] = None
-    expires_at: Optional[str] = None
-    expires_at_ms: Optional[int] = None
-    last_refresh: Optional[str] = None
-    inference_base_url: Optional[str] = None
-    agent_key: Optional[str] = None
-    agent_key_expires_at: Optional[str] = None
-    request_count: int = 0
-    extra: Dict[str, Any] = None  # type: ignore[assignment]
-
-    def __post_init__(self):
-        if self.extra is None:
-            self.extra = {}
-
-    def __getattr__(self, name: str):
-        if name in _EXTRA_KEYS:
-            return self.extra.get(name)
-        raise AttributeError(f"'{type(self).__name__}' object has no attribute {name!r}")
-
-    @classmethod
-    def from_dict(cls, provider: str, payload: Dict[str, Any]) -> "PooledCredential":
-        field_names = {f.name for f in fields(cls) if f.name != "provider"}
-        data = {k: payload.get(k) for k in field_names if k in payload}
-        extra = {k: payload[k] for k in _EXTRA_KEYS if k in payload and payload[k] is not None}
-        data["extra"] = extra
-        data.setdefault("id", uuid.uuid4().hex[:6])
-        data.setdefault("label", payload.get("source", provider))
-        data.setdefault("auth_type", AUTH_TYPE_API_KEY)
-        data.setdefault("priority", 0)
-        data.setdefault("source", SOURCE_MANUAL)
-        data.setdefault("access_token", "")
-        return cls(provider=provider, **data)
-
-    def to_dict(self) -> Dict[str, Any]:
-        _ALWAYS_EMIT = {"last_status", "last_status_at", "last_error_code"}
-        result: Dict[str, Any] = {}
-        for field_def in fields(self):
-            if field_def.name in ("provider", "extra"):
-                continue
-            value = getattr(self, field_def.name)
-            if value is not None or field_def.name in _ALWAYS_EMIT:
-                result[field_def.name] = value
-        for k, v in self.extra.items():
-            if v is not None:
-                result[k] = v
-        return result
-
-    @property
-    def runtime_api_key(self) -> str:
-        if self.provider == "nous":
-            return str(self.agent_key or self.access_token or "")
-        return str(self.access_token or "")
-
-    @property
-    def runtime_base_url(self) -> Optional[str]:
-        if self.provider == "nous":
-            return self.inference_base_url or self.base_url
-        return self.base_url
-
-
-def label_from_token(token: str, fallback: str) -> str:
-    claims = _decode_jwt_claims(token)
-    for key in ("email", "preferred_username", "upn"):
-        value = claims.get(key)
-        if isinstance(value, str) and value.strip():
-            return value.strip()
-    return fallback
-
-
-def _next_priority(entries: List[PooledCredential]) -> int:
-    return max((entry.priority for entry in entries), default=-1) + 1
-
-
-def _is_manual_source(source: str) -> bool:
-    normalized = (source or "").strip().lower()
-    return normalized == SOURCE_MANUAL or normalized.startswith(f"{SOURCE_MANUAL}:")
-
-
-def _exhausted_ttl(error_code: Optional[int]) -> int:
-    """Return cooldown seconds based on the HTTP status that caused exhaustion."""
-    if error_code == 429:
-        return EXHAUSTED_TTL_429_SECONDS
-    return EXHAUSTED_TTL_DEFAULT_SECONDS
-
-
-def _normalize_custom_pool_name(name: str) -> str:
-    """Normalize a custom provider name for use as a pool key suffix."""
-    return name.strip().lower().replace(" ", "-")
-
-
-def _iter_custom_providers(config: Optional[dict] = None):
-    """Yield (normalized_name, entry_dict) for each valid custom_providers entry."""
-    if config is None:
-        config = _load_config_safe()
-    if config is None:
-        return
-    custom_providers = config.get("custom_providers")
-    if not isinstance(custom_providers, list):
-        return
-    for entry in custom_providers:
-        if not isinstance(entry, dict):
-            continue
-        name = entry.get("name")
-        if not isinstance(name, str):
-            continue
-        yield _normalize_custom_pool_name(name), entry
-
-
-def get_custom_provider_pool_key(base_url: str) -> Optional[str]:
-    """Look up the custom_providers list in config.yaml and return 'custom:<name>' for a matching base_url.
-
-    Returns None if no match is found.
-    """
-    if not base_url:
-        return None
-    normalized_url = base_url.strip().rstrip("/")
-    for norm_name, entry in _iter_custom_providers():
-        entry_url = str(entry.get("base_url") or "").strip().rstrip("/")
-        if entry_url and entry_url == normalized_url:
-            return f"{CUSTOM_POOL_PREFIX}{norm_name}"
-    return None
-
-
-def list_custom_pool_providers() -> List[str]:
-    """Return all 'custom:*' pool keys that have entries in auth.json."""
-    pool_data = read_credential_pool(None)
-    return sorted(
-        key for key in pool_data
-        if key.startswith(CUSTOM_POOL_PREFIX)
-        and isinstance(pool_data.get(key), list)
-        and pool_data[key]
-    )
-
-
-def _get_custom_provider_config(pool_key: str) -> Optional[Dict[str, Any]]:
-    """Return the custom_providers config entry matching a pool key like 'custom:together.ai'."""
-    if not pool_key.startswith(CUSTOM_POOL_PREFIX):
-        return None
-    suffix = pool_key[len(CUSTOM_POOL_PREFIX):]
-    for norm_name, entry in _iter_custom_providers():
-        if norm_name == suffix:
-            return entry
-    return None
-
-
-def get_pool_strategy(provider: str) -> str:
-    """Return the configured selection strategy for a provider."""
-    config = _load_config_safe()
-    if config is None:
-        return STRATEGY_FILL_FIRST
-
-    strategies = config.get("credential_pool_strategies")
-    if not isinstance(strategies, dict):
-        return STRATEGY_FILL_FIRST
-
-    strategy = str(strategies.get(provider, "") or "").strip().lower()
-    if strategy in SUPPORTED_POOL_STRATEGIES:
-        return strategy
-    return STRATEGY_FILL_FIRST
-
-
-class CredentialPool:
-    def __init__(self, provider: str, entries: List[PooledCredential]):
-        self.provider = provider
-        self._entries = sorted(entries, key=lambda entry: entry.priority)
-        self._current_id: Optional[str] = None
-        self._strategy = get_pool_strategy(provider)
-        self._lock = threading.Lock()
-
-    def has_credentials(self) -> bool:
-        return bool(self._entries)
-
-    def has_available(self) -> bool:
-        """True if at least one entry is not currently in exhaustion cooldown."""
-        return bool(self._available_entries())
-
-    def entries(self) -> List[PooledCredential]:
-        return list(self._entries)
-
-    def current(self) -> Optional[PooledCredential]:
-        if not self._current_id:
-            return None
-        return next((entry for entry in self._entries if entry.id == self._current_id), None)
-
-    def _replace_entry(self, old: PooledCredential, new: PooledCredential) -> None:
-        """Swap an entry in-place by id, preserving sort order."""
-        for idx, entry in enumerate(self._entries):
-            if entry.id == old.id:
-                self._entries[idx] = new
-                return
-
-    def _persist(self) -> None:
-        write_credential_pool(
-            self.provider,
-            [entry.to_dict() for entry in self._entries],
-        )
-
-    def _mark_exhausted(self, entry: PooledCredential, status_code: Optional[int]) -> PooledCredential:
-        updated = replace(
-            entry,
-            last_status=STATUS_EXHAUSTED,
-            last_status_at=time.time(),
-            last_error_code=status_code,
-        )
-        self._replace_entry(entry, updated)
-        self._persist()
-        return updated
-
-    def _refresh_entry(self, entry: PooledCredential, *, force: bool) -> Optional[PooledCredential]:
-        if entry.auth_type != AUTH_TYPE_OAUTH or not entry.refresh_token:
-            if force:
-                self._mark_exhausted(entry, None)
-            return None
-
-        try:
-            if self.provider == "anthropic":
-                from agent.anthropic_adapter import refresh_anthropic_oauth_pure
-
-                refreshed = refresh_anthropic_oauth_pure(
-                    entry.refresh_token,
-                    use_json=entry.source.endswith("hermes_pkce"),
-                )
-                updated = replace(
-                    entry,
-                    access_token=refreshed["access_token"],
-                    refresh_token=refreshed["refresh_token"],
-                    expires_at_ms=refreshed["expires_at_ms"],
-                )
-            elif self.provider == "openai-codex":
-                refreshed = auth_mod.refresh_codex_oauth_pure(
-                    entry.access_token,
-                    entry.refresh_token,
-                )
-                updated = replace(
-                    entry,
-                    access_token=refreshed["access_token"],
-                    refresh_token=refreshed["refresh_token"],
-                    last_refresh=refreshed.get("last_refresh"),
-                )
-            elif self.provider == "nous":
-                nous_state = {
-                    "access_token": entry.access_token,
-                    "refresh_token": entry.refresh_token,
-                    "client_id": entry.client_id,
-                    "portal_base_url": entry.portal_base_url,
-                    "inference_base_url": entry.inference_base_url,
-                    "token_type": entry.token_type,
-                    "scope": entry.scope,
-                    "obtained_at": entry.obtained_at,
-                    "expires_at": entry.expires_at,
-                    "agent_key": entry.agent_key,
-                    "agent_key_expires_at": entry.agent_key_expires_at,
-                    "tls": entry.tls,
-                }
-                refreshed = auth_mod.refresh_nous_oauth_from_state(
-                    nous_state,
-                    min_key_ttl_seconds=DEFAULT_AGENT_KEY_MIN_TTL_SECONDS,
-                    force_refresh=force,
-                    force_mint=force,
-                )
-                # Apply returned fields: dataclass fields via replace, extras via dict update
-                field_updates = {}
-                extra_updates = dict(entry.extra)
-                _field_names = {f.name for f in fields(entry)}
-                for k, v in refreshed.items():
-                    if k in _field_names:
-                        field_updates[k] = v
-                    elif k in _EXTRA_KEYS:
-                        extra_updates[k] = v
-                updated = replace(entry, extra=extra_updates, **field_updates)
-            else:
-                return entry
-        except Exception as exc:
-            logger.debug("Credential refresh failed for %s/%s: %s", self.provider, entry.id, exc)
-            self._mark_exhausted(entry, None)
-            return None
-
-        updated = replace(updated, last_status=STATUS_OK, last_status_at=None, last_error_code=None)
-        self._replace_entry(entry, updated)
-        self._persist()
-        return updated
-
-    def _entry_needs_refresh(self, entry: PooledCredential) -> bool:
-        if entry.auth_type != AUTH_TYPE_OAUTH:
-            return False
-        if self.provider == "anthropic":
-            if entry.expires_at_ms is None:
-                return False
-            return int(entry.expires_at_ms) <= int(time.time() * 1000) + 120_000
-        if self.provider == "openai-codex":
-            return _codex_access_token_is_expiring(
-                entry.access_token,
-                CODEX_ACCESS_TOKEN_REFRESH_SKEW_SECONDS,
-            )
-        if self.provider == "nous":
-            # Nous refresh/mint can require network access and should happen when
-            # runtime credentials are actually resolved, not merely when the pool
-            # is enumerated for listing, migration, or selection.
-            return False
-        return False
-
-    def mark_used(self, entry_id: Optional[str] = None) -> None:
-        """Increment request_count for tracking. Used by least_used strategy."""
-        target_id = entry_id or self._current_id
-        if not target_id:
-            return
-        with self._lock:
-            for idx, entry in enumerate(self._entries):
-                if entry.id == target_id:
-                    self._entries[idx] = replace(entry, request_count=entry.request_count + 1)
-                    return
-
-    def select(self) -> Optional[PooledCredential]:
-        with self._lock:
-            return self._select_unlocked()
-
-    def _available_entries(self, *, clear_expired: bool = False, refresh: bool = False) -> List[PooledCredential]:
-        """Return entries not currently in exhaustion cooldown.
-
-        When *clear_expired* is True, entries whose cooldown has elapsed are
-        reset to STATUS_OK and persisted.  When *refresh* is True, entries
-        that need a token refresh are refreshed (skipped on failure).
-        """
-        now = time.time()
-        cleared_any = False
-        available: List[PooledCredential] = []
-        for entry in self._entries:
-            if entry.last_status == STATUS_EXHAUSTED:
-                ttl = _exhausted_ttl(entry.last_error_code)
-                if entry.last_status_at and now - entry.last_status_at < ttl:
-                    continue
-                if clear_expired:
-                    cleared = replace(entry, last_status=STATUS_OK, last_status_at=None, last_error_code=None)
-                    self._replace_entry(entry, cleared)
-                    entry = cleared
-                    cleared_any = True
-            if refresh and self._entry_needs_refresh(entry):
-                refreshed = self._refresh_entry(entry, force=False)
-                if refreshed is None:
-                    continue
-                entry = refreshed
-            available.append(entry)
-        if cleared_any:
-            self._persist()
-        return available
-
-    def _select_unlocked(self) -> Optional[PooledCredential]:
-        available = self._available_entries(clear_expired=True, refresh=True)
-        if not available:
-            self._current_id = None
-            return None
-
-        if self._strategy == STRATEGY_RANDOM:
-            entry = random.choice(available)
-            self._current_id = entry.id
-            return entry
-
-        if self._strategy == STRATEGY_LEAST_USED and len(available) > 1:
-            entry = min(available, key=lambda e: e.request_count)
-            self._current_id = entry.id
-            return entry
-
-        if self._strategy == STRATEGY_ROUND_ROBIN and len(available) > 1:
-            entry = available[0]
-            rotated = [candidate for candidate in self._entries if candidate.id != entry.id]
-            rotated.append(replace(entry, priority=len(self._entries) - 1))
-            self._entries = [replace(candidate, priority=idx) for idx, candidate in enumerate(rotated)]
-            self._persist()
-            self._current_id = entry.id
-            return self.current() or entry
-
-        entry = available[0]
-        self._current_id = entry.id
-        return entry
-
-    def peek(self) -> Optional[PooledCredential]:
-        current = self.current()
-        if current is not None:
-            return current
-        available = self._available_entries()
-        return available[0] if available else None
-
-    def mark_exhausted_and_rotate(self, *, status_code: Optional[int]) -> Optional[PooledCredential]:
-        with self._lock:
-            entry = self.current() or self._select_unlocked()
-            if entry is None:
-                return None
-            self._mark_exhausted(entry, status_code)
-            self._current_id = None
-            return self._select_unlocked()
-
-    def try_refresh_current(self) -> Optional[PooledCredential]:
-        with self._lock:
-            return self._try_refresh_current_unlocked()
-
-    def _try_refresh_current_unlocked(self) -> Optional[PooledCredential]:
-        entry = self.current()
-        if entry is None:
-            return None
-        refreshed = self._refresh_entry(entry, force=True)
-        if refreshed is not None:
-            self._current_id = refreshed.id
-        return refreshed
-
-    def reset_statuses(self) -> int:
-        count = 0
-        new_entries = []
-        for entry in self._entries:
-            if entry.last_status or entry.last_status_at or entry.last_error_code:
-                new_entries.append(replace(entry, last_status=None, last_status_at=None, last_error_code=None))
-                count += 1
-            else:
-                new_entries.append(entry)
-        if count:
-            self._entries = new_entries
-            self._persist()
-        return count
-
-    def remove_index(self, index: int) -> Optional[PooledCredential]:
-        if index < 1 or index > len(self._entries):
-            return None
-        removed = self._entries.pop(index - 1)
-        self._entries = [
-            replace(entry, priority=new_priority)
-            for new_priority, entry in enumerate(self._entries)
-        ]
-        self._persist()
-        if self._current_id == removed.id:
-            self._current_id = None
-        return removed
-
-    def add_entry(self, entry: PooledCredential) -> PooledCredential:
-        entry = replace(entry, priority=_next_priority(self._entries))
-        self._entries.append(entry)
-        self._persist()
-        return entry
-
-
-def _upsert_entry(entries: List[PooledCredential], provider: str, source: str, payload: Dict[str, Any]) -> bool:
-    existing_idx = None
-    for idx, entry in enumerate(entries):
-        if entry.source == source:
-            existing_idx = idx
-            break
-
-    if existing_idx is None:
-        payload.setdefault("id", uuid.uuid4().hex[:6])
-        payload.setdefault("priority", _next_priority(entries))
-        payload.setdefault("label", payload.get("label") or source)
-        entries.append(PooledCredential.from_dict(provider, payload))
-        return True
-
-    existing = entries[existing_idx]
-    field_updates = {}
-    extra_updates = {}
-    _field_names = {f.name for f in fields(existing)}
-    for key, value in payload.items():
-        if key in {"id", "priority"} or value is None:
-            continue
-        if key == "label" and existing.label:
-            continue
-        if key in _field_names:
-            if getattr(existing, key) != value:
-                field_updates[key] = value
-        elif key in _EXTRA_KEYS:
-            if existing.extra.get(key) != value:
-                extra_updates[key] = value
-    if field_updates or extra_updates:
-        if extra_updates:
-            field_updates["extra"] = {**existing.extra, **extra_updates}
-        entries[existing_idx] = replace(existing, **field_updates)
-        return True
-    return False
-
-
-def _normalize_pool_priorities(provider: str, entries: List[PooledCredential]) -> bool:
-    if provider != "anthropic":
-        return False
-
-    source_rank = {
-        "env:ANTHROPIC_TOKEN": 0,
-        "env:CLAUDE_CODE_OAUTH_TOKEN": 1,
-        "hermes_pkce": 2,
-        "claude_code": 3,
-        "env:ANTHROPIC_API_KEY": 4,
-    }
-    manual_entries = sorted(
-        (entry for entry in entries if _is_manual_source(entry.source)),
-        key=lambda entry: entry.priority,
-    )
-    seeded_entries = sorted(
-        (entry for entry in entries if not _is_manual_source(entry.source)),
-        key=lambda entry: (
-            source_rank.get(entry.source, len(source_rank)),
-            entry.priority,
-            entry.label,
-        ),
-    )
-
-    ordered = [*manual_entries, *seeded_entries]
-    id_to_idx = {entry.id: idx for idx, entry in enumerate(entries)}
-    changed = False
-    for new_priority, entry in enumerate(ordered):
-        if entry.priority != new_priority:
-            entries[id_to_idx[entry.id]] = replace(entry, priority=new_priority)
-            changed = True
-    return changed
-
-
-def _seed_from_singletons(provider: str, entries: List[PooledCredential]) -> Tuple[bool, Set[str]]:
-    changed = False
-    active_sources: Set[str] = set()
-    auth_store = _load_auth_store()
-
-    if provider == "anthropic":
-        from agent.anthropic_adapter import read_claude_code_credentials, read_hermes_oauth_credentials
-
-        for source_name, creds in (
-            ("hermes_pkce", read_hermes_oauth_credentials()),
-            ("claude_code", read_claude_code_credentials()),
-        ):
-            if creds and creds.get("accessToken"):
-                active_sources.add(source_name)
-                changed |= _upsert_entry(
-                    entries,
-                    provider,
-                    source_name,
-                    {
-                        "source": source_name,
-                        "auth_type": AUTH_TYPE_OAUTH,
-                        "access_token": creds.get("accessToken", ""),
-                        "refresh_token": creds.get("refreshToken"),
-                        "expires_at_ms": creds.get("expiresAt"),
-                        "label": label_from_token(creds.get("accessToken", ""), source_name),
-                    },
-                )
-
-    elif provider == "nous":
-        state = _load_provider_state(auth_store, "nous")
-        if state:
-            active_sources.add("device_code")
-            changed |= _upsert_entry(
-                entries,
-                provider,
-                "device_code",
-                {
-                    "source": "device_code",
-                    "auth_type": AUTH_TYPE_OAUTH,
-                    "access_token": state.get("access_token", ""),
-                    "refresh_token": state.get("refresh_token"),
-                    "expires_at": state.get("expires_at"),
-                    "token_type": state.get("token_type"),
-                    "scope": state.get("scope"),
-                    "client_id": state.get("client_id"),
-                    "portal_base_url": state.get("portal_base_url"),
-                    "inference_base_url": state.get("inference_base_url"),
-                    "agent_key": state.get("agent_key"),
-                    "agent_key_expires_at": state.get("agent_key_expires_at"),
-                    "tls": state.get("tls") if isinstance(state.get("tls"), dict) else None,
-                    "label": label_from_token(state.get("access_token", ""), "device_code"),
-                },
-            )
-
-    elif provider == "openai-codex":
-        state = _load_provider_state(auth_store, "openai-codex")
-        tokens = state.get("tokens") if isinstance(state, dict) else None
-        if isinstance(tokens, dict) and tokens.get("access_token"):
-            active_sources.add("device_code")
-            changed |= _upsert_entry(
-                entries,
-                provider,
-                "device_code",
-                {
-                    "source": "device_code",
-                    "auth_type": AUTH_TYPE_OAUTH,
-                    "access_token": tokens.get("access_token", ""),
-                    "refresh_token": tokens.get("refresh_token"),
-                    "base_url": "https://chatgpt.com/backend-api/codex",
-                    "last_refresh": state.get("last_refresh"),
-                    "label": label_from_token(tokens.get("access_token", ""), "device_code"),
-                },
-            )
-
-    return changed, active_sources
-
-
-def _seed_from_env(provider: str, entries: List[PooledCredential]) -> Tuple[bool, Set[str]]:
-    changed = False
-    active_sources: Set[str] = set()
-    if provider == "openrouter":
-        token = os.getenv("OPENROUTER_API_KEY", "").strip()
-        if token:
-            source = "env:OPENROUTER_API_KEY"
-            active_sources.add(source)
-            changed |= _upsert_entry(
-                entries,
-                provider,
-                source,
-                {
-                    "source": source,
-                    "auth_type": AUTH_TYPE_API_KEY,
-                    "access_token": token,
-                    "base_url": OPENROUTER_BASE_URL,
-                    "label": "OPENROUTER_API_KEY",
-                },
-            )
-        return changed, active_sources
-
-    pconfig = PROVIDER_REGISTRY.get(provider)
-    if not pconfig or pconfig.auth_type != AUTH_TYPE_API_KEY:
-        return changed, active_sources
-
-    env_url = ""
-    if pconfig.base_url_env_var:
-        env_url = os.getenv(pconfig.base_url_env_var, "").strip().rstrip("/")
-
-    env_vars = list(pconfig.api_key_env_vars)
-    if provider == "anthropic":
-        env_vars = [
-            "ANTHROPIC_TOKEN",
-            "CLAUDE_CODE_OAUTH_TOKEN",
-            "ANTHROPIC_API_KEY",
-        ]
-
-    for env_var in env_vars:
-        token = os.getenv(env_var, "").strip()
-        if not token:
-            continue
-        source = f"env:{env_var}"
-        active_sources.add(source)
-        auth_type = AUTH_TYPE_OAUTH if provider == "anthropic" and not token.startswith("sk-ant-api") else AUTH_TYPE_API_KEY
-        base_url = env_url or pconfig.inference_base_url
-        changed |= _upsert_entry(
-            entries,
-            provider,
-            source,
-            {
-                "source": source,
-                "auth_type": auth_type,
-                "access_token": token,
-                "base_url": base_url,
-                "label": env_var,
-            },
-        )
-    return changed, active_sources
-
-
-def _prune_stale_seeded_entries(entries: List[PooledCredential], active_sources: Set[str]) -> bool:
-    retained = [
-        entry
-        for entry in entries
-        if _is_manual_source(entry.source)
-        or entry.source in active_sources
-        or not (
-            entry.source.startswith("env:")
-            or entry.source in {"claude_code", "hermes_pkce"}
-        )
-    ]
-    if len(retained) == len(entries):
-        return False
-    entries[:] = retained
-    return True
-
-
-def _seed_custom_pool(pool_key: str, entries: List[PooledCredential]) -> Tuple[bool, Set[str]]:
-    """Seed a custom endpoint pool from custom_providers config and model config."""
-    changed = False
-    active_sources: Set[str] = set()
-
-    # Seed from the custom_providers config entry's api_key field
-    cp_config = _get_custom_provider_config(pool_key)
-    if cp_config:
-        api_key = str(cp_config.get("api_key") or "").strip()
-        base_url = str(cp_config.get("base_url") or "").strip().rstrip("/")
-        name = str(cp_config.get("name") or "").strip()
-        if api_key:
-            source = f"config:{name}"
-            active_sources.add(source)
-            changed |= _upsert_entry(
-                entries,
-                pool_key,
-                source,
-                {
-                    "source": source,
-                    "auth_type": AUTH_TYPE_API_KEY,
-                    "access_token": api_key,
-                    "base_url": base_url,
-                    "label": name or source,
-                },
-            )
-
-    # Seed from model.api_key if model.provider=='custom' and model.base_url matches
-    try:
-        config = _load_config_safe()
-        model_cfg = config.get("model") if config else None
-        if isinstance(model_cfg, dict):
-            model_provider = str(model_cfg.get("provider") or "").strip().lower()
-            model_base_url = str(model_cfg.get("base_url") or "").strip().rstrip("/")
-            model_api_key = ""
-            for k in ("api_key", "api"):
-                v = model_cfg.get(k)
-                if isinstance(v, str) and v.strip():
-                    model_api_key = v.strip()
-                    break
-            if model_provider == "custom" and model_base_url and model_api_key:
-                # Check if this model's base_url matches our custom provider
-                matched_key = get_custom_provider_pool_key(model_base_url)
-                if matched_key == pool_key:
-                    source = "model_config"
-                    active_sources.add(source)
-                    changed |= _upsert_entry(
-                        entries,
-                        pool_key,
-                        source,
-                        {
-                            "source": source,
-                            "auth_type": AUTH_TYPE_API_KEY,
-                            "access_token": model_api_key,
-                            "base_url": model_base_url,
-                            "label": "model_config",
-                        },
-                    )
-    except Exception:
-        pass
-
-    return changed, active_sources
-
-
-def load_pool(provider: str) -> CredentialPool:
-    provider = (provider or "").strip().lower()
-    raw_entries = read_credential_pool(provider)
-    entries = [PooledCredential.from_dict(provider, payload) for payload in raw_entries]
-
-    if provider.startswith(CUSTOM_POOL_PREFIX):
-        # Custom endpoint pool — seed from custom_providers config and model config
-        custom_changed, custom_sources = _seed_custom_pool(provider, entries)
-        changed = custom_changed
-        changed |= _prune_stale_seeded_entries(entries, custom_sources)
-    else:
-        singleton_changed, singleton_sources = _seed_from_singletons(provider, entries)
-        env_changed, env_sources = _seed_from_env(provider, entries)
-        changed = singleton_changed or env_changed
-        changed |= _prune_stale_seeded_entries(entries, singleton_sources | env_sources)
-        changed |= _normalize_pool_priorities(provider, entries)
-
-    if changed:
-        write_credential_pool(
-            provider,
-            [entry.to_dict() for entry in sorted(entries, key=lambda item: item.priority)],
-        )
-    return CredentialPool(provider, entries)
@@ -10,9 +10,6 @@ import os
 import sys
 import threading
 import time
-from dataclasses import dataclass, field
-from difflib import unified_diff
-from pathlib import Path

 # ANSI escape codes for coloring tool failure indicators
 _RED = "\033[31m"
@@ -20,39 +17,6 @@ _RESET = "\033[0m"

 logger = logging.getLogger(__name__)

-_ANSI_RESET = "\033[0m"
-_ANSI_DIM = "\033[38;2;150;150;150m"
-_ANSI_FILE = "\033[38;2;180;160;255m"
-_ANSI_HUNK = "\033[38;2;120;120;140m"
-_ANSI_MINUS = "\033[38;2;255;255;255;48;2;120;20;20m"
-_ANSI_PLUS = "\033[38;2;255;255;255;48;2;20;90;20m"
-_MAX_INLINE_DIFF_FILES = 6
-_MAX_INLINE_DIFF_LINES = 80
-
-
-@dataclass
-class LocalEditSnapshot:
-    """Pre-tool filesystem snapshot used to render diffs locally after writes."""
-    paths: list[Path] = field(default_factory=list)
-    before: dict[str, str | None] = field(default_factory=dict)
-
-# =========================================================================
-# Configurable tool preview length (0 = no limit)
-# Set once at startup by CLI or gateway from display.tool_preview_length config.
-# =========================================================================
-_tool_preview_max_len: int = 0  # 0 = unlimited
-
-
-def set_tool_preview_max_len(n: int) -> None:
-    """Set the global max length for tool call previews. 0 = no limit."""
-    global _tool_preview_max_len
-    _tool_preview_max_len = max(int(n), 0) if n else 0
-
-
-def get_tool_preview_max_len() -> int:
-    """Return the configured max preview length (0 = unlimited)."""
-    return _tool_preview_max_len
-

 # =========================================================================
 # Skin-aware helpers (lazy import to avoid circular deps)
@@ -130,14 +94,8 @@ def _oneline(text: str) -> str:
    return " ".join(text.split())


-def build_tool_preview(tool_name: str, args: dict, max_len: int | None = None) -> str | None:
-    """Build a short preview of a tool call's primary argument for display.
-
-    *max_len* controls truncation.  ``None`` (default) defers to the global
-    ``_tool_preview_max_len`` set via config; ``0`` means unlimited.
-    """
-    if max_len is None:
-        max_len = _tool_preview_max_len
+def build_tool_preview(tool_name: str, args: dict, max_len: int = 40) -> str | None:
+    """Build a short preview of a tool call's primary argument for display."""
    if not args:
        return None
    primary_args = {
@@ -232,305 +190,11 @@ def build_tool_preview(tool_name: str, args: dict, max_len: int | None = None) -
    preview = _oneline(str(value))
    if not preview:
        return None
-    if max_len > 0 and len(preview) > max_len:
+    if len(preview) > max_len:
        preview = preview[:max_len - 3] + "..."
    return preview


-# =========================================================================
-# Inline diff previews for write actions
-# =========================================================================
-
-def _resolved_path(path: str) -> Path:
-    """Resolve a possibly-relative filesystem path against the current cwd."""
-    candidate = Path(os.path.expanduser(path))
-    if candidate.is_absolute():
-        return candidate
-    return Path.cwd() / candidate
-
-
-def _snapshot_text(path: Path) -> str | None:
-    """Return UTF-8 file content, or None for missing/unreadable files."""
-    try:
-        return path.read_text(encoding="utf-8")
-    except (FileNotFoundError, IsADirectoryError, UnicodeDecodeError, OSError):
-        return None
-
-
-def _display_diff_path(path: Path) -> str:
-    """Prefer cwd-relative paths in diffs when available."""
-    try:
-        return str(path.resolve().relative_to(Path.cwd().resolve()))
-    except Exception:
-        return str(path)
-
-
-def _resolve_skill_manage_paths(args: dict) -> list[Path]:
-    """Resolve skill_manage write targets to filesystem paths."""
-    action = args.get("action")
-    name = args.get("name")
-    if not action or not name:
-        return []
-
-    from tools.skill_manager_tool import _find_skill, _resolve_skill_dir
-
-    if action == "create":
-        skill_dir = _resolve_skill_dir(name, args.get("category"))
-        return [skill_dir / "SKILL.md"]
-
-    existing = _find_skill(name)
-    if not existing:
-        return []
-
-    skill_dir = Path(existing["path"])
-    if action in {"edit", "patch"}:
-        file_path = args.get("file_path")
-        return [skill_dir / file_path] if file_path else [skill_dir / "SKILL.md"]
-    if action in {"write_file", "remove_file"}:
-        file_path = args.get("file_path")
-        return [skill_dir / file_path] if file_path else []
-    if action == "delete":
-        files = [path for path in sorted(skill_dir.rglob("*")) if path.is_file()]
-        return files
-    return []
-
-
-def _resolve_local_edit_paths(tool_name: str, function_args: dict | None) -> list[Path]:
-    """Resolve local filesystem targets for write-capable tools."""
-    if not isinstance(function_args, dict):
-        return []
-
-    if tool_name == "write_file":
-        path = function_args.get("path")
-        return [_resolved_path(path)] if path else []
-
-    if tool_name == "patch":
-        path = function_args.get("path")
-        return [_resolved_path(path)] if path else []
-
-    if tool_name == "skill_manage":
-        return _resolve_skill_manage_paths(function_args)
-
-    return []
-
-
-def capture_local_edit_snapshot(tool_name: str, function_args: dict | None) -> LocalEditSnapshot | None:
-    """Capture before-state for local write previews."""
-    paths = _resolve_local_edit_paths(tool_name, function_args)
-    if not paths:
-        return None
-
-    snapshot = LocalEditSnapshot(paths=paths)
-    for path in paths:
-        snapshot.before[str(path)] = _snapshot_text(path)
-    return snapshot
-
-
-def _result_succeeded(result: str | None) -> bool:
-    """Conservatively detect whether a tool result represents success."""
-    if not result:
-        return False
-    try:
-        data = json.loads(result)
-    except (json.JSONDecodeError, TypeError):
-        return False
-    if not isinstance(data, dict):
-        return False
-    if data.get("error"):
-        return False
-    if "success" in data:
-        return bool(data.get("success"))
-    return True
-
-
-def _diff_from_snapshot(snapshot: LocalEditSnapshot | None) -> str | None:
-    """Generate unified diff text from a stored before-state and current files."""
-    if not snapshot:
-        return None
-
-    chunks: list[str] = []
-    for path in snapshot.paths:
-        before = snapshot.before.get(str(path))
-        after = _snapshot_text(path)
-        if before == after:
-            continue
-
-        display_path = _display_diff_path(path)
-        diff = "".join(
-            unified_diff(
-                [] if before is None else before.splitlines(keepends=True),
-                [] if after is None else after.splitlines(keepends=True),
-                fromfile=f"a/{display_path}",
-                tofile=f"b/{display_path}",
-            )
-        )
-        if diff:
-            chunks.append(diff)
-
-    if not chunks:
-        return None
-    return "".join(chunk if chunk.endswith("\n") else chunk + "\n" for chunk in chunks)
-
-
-def extract_edit_diff(
-    tool_name: str,
-    result: str | None,
-    *,
-    function_args: dict | None = None,
-    snapshot: LocalEditSnapshot | None = None,
-) -> str | None:
-    """Extract a unified diff from a file-edit tool result."""
-    if tool_name == "patch" and result:
-        try:
-            data = json.loads(result)
-        except (json.JSONDecodeError, TypeError):
-            data = None
-        if isinstance(data, dict):
-            diff = data.get("diff")
-            if isinstance(diff, str) and diff.strip():
-                return diff
-
-    if tool_name not in {"write_file", "patch", "skill_manage"}:
-        return None
-    if not _result_succeeded(result):
-        return None
-    return _diff_from_snapshot(snapshot)
-
-
-def _emit_inline_diff(diff_text: str, print_fn) -> bool:
-    """Emit rendered diff text through the CLI's prompt_toolkit-safe printer."""
-    if print_fn is None or not diff_text:
-        return False
-    try:
-        print_fn("  ┊ review diff")
-        for line in diff_text.rstrip("\n").splitlines():
-            print_fn(line)
-        return True
-    except Exception:
-        return False
-
-
-def _render_inline_unified_diff(diff: str) -> list[str]:
-    """Render unified diff lines in Hermes' inline transcript style."""
-    rendered: list[str] = []
-    from_file = None
-    to_file = None
-
-    for raw_line in diff.splitlines():
-        if raw_line.startswith("--- "):
-            from_file = raw_line[4:].strip()
-            continue
-        if raw_line.startswith("+++ "):
-            to_file = raw_line[4:].strip()
-            if from_file or to_file:
-                rendered.append(f"{_ANSI_FILE}{from_file or 'a/?'} → {to_file or 'b/?'}{_ANSI_RESET}")
-            continue
-        if raw_line.startswith("@@"):
-            rendered.append(f"{_ANSI_HUNK}{raw_line}{_ANSI_RESET}")
-            continue
-        if raw_line.startswith("-"):
-            rendered.append(f"{_ANSI_MINUS}{raw_line}{_ANSI_RESET}")
-            continue
-        if raw_line.startswith("+"):
-            rendered.append(f"{_ANSI_PLUS}{raw_line}{_ANSI_RESET}")
-            continue
-        if raw_line.startswith(" "):
-            rendered.append(f"{_ANSI_DIM}{raw_line}{_ANSI_RESET}")
-            continue
-        if raw_line:
-            rendered.append(raw_line)
-
-    return rendered
-
-
-def _split_unified_diff_sections(diff: str) -> list[str]:
-    """Split a unified diff into per-file sections."""
-    sections: list[list[str]] = []
-    current: list[str] = []
-
-    for line in diff.splitlines():
-        if line.startswith("--- ") and current:
-            sections.append(current)
-            current = [line]
-            continue
-        current.append(line)
-
-    if current:
-        sections.append(current)
-
-    return ["\n".join(section) for section in sections if section]
-
-
-def _summarize_rendered_diff_sections(
-    diff: str,
-    *,
-    max_files: int = _MAX_INLINE_DIFF_FILES,
-    max_lines: int = _MAX_INLINE_DIFF_LINES,
-) -> list[str]:
-    """Render diff sections while capping file count and total line count."""
-    sections = _split_unified_diff_sections(diff)
-    rendered: list[str] = []
-    omitted_files = 0
-    omitted_lines = 0
-
-    for idx, section in enumerate(sections):
-        if idx >= max_files:
-            omitted_files += 1
-            omitted_lines += len(_render_inline_unified_diff(section))
-            continue
-
-        section_lines = _render_inline_unified_diff(section)
-        remaining_budget = max_lines - len(rendered)
-        if remaining_budget <= 0:
-            omitted_lines += len(section_lines)
-            omitted_files += 1
-            continue
-
-        if len(section_lines) <= remaining_budget:
-            rendered.extend(section_lines)
-            continue
-
-        rendered.extend(section_lines[:remaining_budget])
-        omitted_lines += len(section_lines) - remaining_budget
-        omitted_files += 1 + max(0, len(sections) - idx - 1)
-        for leftover in sections[idx + 1:]:
-            omitted_lines += len(_render_inline_unified_diff(leftover))
-        break
-
-    if omitted_files or omitted_lines:
-        summary = f"… omitted {omitted_lines} diff line(s)"
-        if omitted_files:
-            summary += f" across {omitted_files} additional file(s)/section(s)"
-        rendered.append(f"{_ANSI_HUNK}{summary}{_ANSI_RESET}")
-
-    return rendered
-
-
-def render_edit_diff_with_delta(
-    tool_name: str,
-    result: str | None,
-    *,
-    function_args: dict | None = None,
-    snapshot: LocalEditSnapshot | None = None,
-    print_fn=None,
-) -> bool:
-    """Render an edit diff inline without taking over the terminal UI."""
-    diff = extract_edit_diff(
-        tool_name,
-        result,
-        function_args=function_args,
-        snapshot=snapshot,
-    )
-    if not diff:
-        return False
-    try:
-        rendered_lines = _summarize_rendered_diff_sections(diff)
-    except Exception as exc:
-        logger.debug("Could not render inline diff: %s", exc)
-        return False
-    return _emit_inline_diff("\n".join(rendered_lines), print_fn)
-
-
 # =========================================================================
 # KawaiiSpinner
 # =========================================================================
@@ -567,7 +231,7 @@ class KawaiiSpinner:
        "analyzing", "computing", "synthesizing", "formulating", "brainstorming",
    ]

-    def __init__(self, message: str = "", spinner_type: str = 'dots', print_fn=None):
+    def __init__(self, message: str = "", spinner_type: str = 'dots'):
        self.message = message
        self.spinner_frames = self.SPINNERS.get(spinner_type, self.SPINNERS['dots'])
        self.running = False
@@ -575,26 +239,12 @@ class KawaiiSpinner:
        self.frame_idx = 0
        self.start_time = None
        self.last_line_len = 0
-        # Optional callable to route all output through (e.g. a no-op for silent
-        # background agents).  When set, bypasses self._out entirely so that
-        # agents with _print_fn overridden remain fully silent.
-        self._print_fn = print_fn
        # Capture stdout NOW, before any redirect_stdout(devnull) from
        # child agents can replace sys.stdout with a black hole.
        self._out = sys.stdout

    def _write(self, text: str, end: str = '\n', flush: bool = False):
-        """Write to the stdout captured at spinner creation time.
-
-        If a print_fn was supplied at construction, all output is routed through
-        it instead — allowing callers to silence the spinner with a no-op lambda.
-        """
-        if self._print_fn is not None:
-            try:
-                self._print_fn(text)
-            except Exception:
-                pass
-            return
+        """Write to the stdout captured at spinner creation time."""
        try:
            self._out.write(text + end)
            if flush:
@@ -620,11 +270,11 @@ class KawaiiSpinner:
        The CLI already drives a TUI widget (_spinner_text) for spinner display,
        so KawaiiSpinner's \\r-based animation is redundant under StdoutProxy.
        """
-        try:
-            from prompt_toolkit.patch_stdout import StdoutProxy
-            return isinstance(self._out, StdoutProxy)
-        except ImportError:
-            return False
+        out = self._out
+        # StdoutProxy has a 'raw' attribute (bool) that plain file objects lack.
+        if hasattr(out, 'raw') and type(out).__name__ == 'StdoutProxy':
+            return True
+        return False

    def _animate(self):
        # When stdout is not a real terminal (e.g. Docker, systemd, pipe),
@@ -820,14 +470,10 @@ def get_cute_tool_message(

    def _trunc(s, n=40):
        s = str(s)
-        if _tool_preview_max_len == 0:
-            return s  # no limit
        return (s[:n-3] + "...") if len(s) > n else s

    def _path(p, n=35):
        p = str(p)
-        if _tool_preview_max_len == 0:
-            return p  # no limit
        return ("..." + p[-(n-3):]) if len(p) > n else p

    def _wrap(line: str) -> str:
@@ -1039,7 +685,7 @@ def format_context_pressure(
        threshold_percent: Compaction threshold as a fraction of context window.
        compression_enabled: Whether auto-compression is active.
    """
-    pct_int = min(int(compaction_progress * 100), 100)
+    pct_int = int(compaction_progress * 100)
    filled = min(int(compaction_progress * _BAR_WIDTH), _BAR_WIDTH)
    bar = _BAR_FILLED * filled + _BAR_EMPTY * (_BAR_WIDTH - filled)

@@ -1069,7 +715,7 @@ def format_context_pressure_gateway(
    No ANSI — just Unicode and plain text suitable for Telegram/Discord/etc.
    The percentage shows progress toward the compaction threshold.
    """
-    pct_int = min(int(compaction_progress * 100), 100)
+    pct_int = int(compaction_progress * 100)
    filled = min(int(compaction_progress * _BAR_WIDTH), _BAR_WIDTH)
    bar = _BAR_FILLED * filled + _BAR_EMPTY * (_BAR_WIDTH - filled)

@@ -644,9 +644,6 @@ class InsightsEngine:
        lines.append(f"  Sessions:          {o['total_sessions']:<12}  Messages:        {o['total_messages']:,}")
        lines.append(f"  Tool calls:        {o['total_tool_calls']:<12,}  User messages:   {o['user_messages']:,}")
        lines.append(f"  Input tokens:      {o['total_input_tokens']:<12,}  Output tokens:   {o['total_output_tokens']:,}")
-        cache_total = o.get("total_cache_read_tokens", 0) + o.get("total_cache_write_tokens", 0)
-        if cache_total > 0:
-            lines.append(f"  Cache read:        {o['total_cache_read_tokens']:<12,}  Cache write:     {o['total_cache_write_tokens']:,}")
        cost_str = f"${o['estimated_cost']:.2f}"
        if o.get("models_without_pricing"):
            cost_str += " *"
@@ -749,11 +746,7 @@ class InsightsEngine:

        # Overview
        lines.append(f"**Sessions:** {o['total_sessions']} | **Messages:** {o['total_messages']:,} | **Tool calls:** {o['total_tool_calls']:,}")
-        cache_total = o.get("total_cache_read_tokens", 0) + o.get("total_cache_write_tokens", 0)
-        if cache_total > 0:
-            lines.append(f"**Tokens:** {o['total_tokens']:,} (in: {o['total_input_tokens']:,} / out: {o['total_output_tokens']:,} / cache: {cache_total:,})")
-        else:
-            lines.append(f"**Tokens:** {o['total_tokens']:,} (in: {o['total_input_tokens']:,} / out: {o['total_output_tokens']:,})")
+        lines.append(f"**Tokens:** {o['total_tokens']:,} (in: {o['total_input_tokens']:,} / out: {o['total_output_tokens']:,})")
        cost_note = ""
        if o.get("models_without_pricing"):
            cost_note = " _(excludes custom/self-hosted models)_"
@@ -113,15 +113,6 @@ DEFAULT_CONTEXT_LENGTHS = {
    "glm": 202752,
    # Kimi
    "kimi": 262144,
-    # Hugging Face Inference Providers — model IDs use org/name format
-    "Qwen/Qwen3.5-397B-A17B": 131072,
-    "Qwen/Qwen3.5-35B-A3B": 131072,
-    "deepseek-ai/DeepSeek-V3.2": 65536,
-    "moonshotai/Kimi-K2.5": 262144,
-    "moonshotai/Kimi-K2-Thinking": 262144,
-    "MiniMaxAI/MiniMax-M2.5": 204800,
-    "XiaomiMiMo/MiMo-V2-Flash": 32768,
-    "zai-org/GLM-5": 202752,
 }

 _CONTEXT_LENGTH_KEYS = (
@@ -171,12 +162,10 @@ _URL_TO_PROVIDER: Dict[str, str] = {
    "dashscope.aliyuncs.com": "alibaba",
    "dashscope-intl.aliyuncs.com": "alibaba",
    "openrouter.ai": "openrouter",
-    "generativelanguage.googleapis.com": "google",
    "inference-api.nousresearch.com": "nous",
    "api.deepseek.com": "deepseek",
    "api.githubcopilot.com": "copilot",
    "models.github.ai": "copilot",
-    "api.fireworks.ai": "fireworks",
 }


@@ -15,8 +15,6 @@ import time
 from pathlib import Path
 from typing import Any, Dict, Optional

-from utils import atomic_json_write
-
 import requests

 logger = logging.getLogger(__name__)
@@ -43,7 +41,6 @@ PROVIDER_TO_MODELS_DEV: Dict[str, str] = {
    "opencode-zen": "opencode",
    "opencode-go": "opencode-go",
    "kilocode": "kilo",
-    "fireworks": "fireworks-ai",
 }


@@ -67,10 +64,12 @@ def _load_disk_cache() -> Dict[str, Any]:


 def _save_disk_cache(data: Dict[str, Any]) -> None:
-    """Save models.dev data to disk cache atomically."""
+    """Save models.dev data to disk cache."""
    try:
        cache_path = _get_cache_path()
-        atomic_json_write(cache_path, data, indent=None, separators=(",", ":"))
+        cache_path.parent.mkdir(parents=True, exist_ok=True)
+        with open(cache_path, "w", encoding="utf-8") as f:
+            json.dump(data, f, separators=(",", ":"))
    except Exception as e:
        logger.debug("Failed to save models.dev disk cache: %s", e)

@@ -4,28 +4,14 @@ All functions are stateless. AIAgent._build_system_prompt() calls these to
 assemble pieces, then combines them with memory and ephemeral prompts.
 """

-import json
 import logging
 import os
 import re
-import threading
-from collections import OrderedDict
 from pathlib import Path

 from hermes_constants import get_hermes_home
 from typing import Optional

-from agent.skill_utils import (
-    extract_skill_conditions,
-    extract_skill_description,
-    get_all_skills_dirs,
-    get_disabled_skill_names,
-    iter_skill_index_files,
-    parse_frontmatter,
-    skill_matches_platform,
-)
-from utils import atomic_json_write
-
 logger = logging.getLogger(__name__)

 # ---------------------------------------------------------------------------
@@ -170,25 +156,6 @@ SKILLS_GUIDANCE = (
    "Skills that aren't maintained become liabilities."
 )

-TOOL_USE_ENFORCEMENT_GUIDANCE = (
-    "# Tool-use enforcement\n"
-    "You 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.\n"
-    "Keep 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.\n"
-    "Every 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."
-)
-
-# Model name substrings that trigger tool-use enforcement guidance.
-# Add new patterns here when a model family needs explicit steering.
-TOOL_USE_ENFORCEMENT_MODELS = ("gpt", "codex")
-
 PLATFORM_HINTS = {
    "whatsapp": (
        "You are on a text messaging communication platform, WhatsApp. "
@@ -263,111 +230,6 @@ CONTEXT_TRUNCATE_HEAD_RATIO = 0.7
 CONTEXT_TRUNCATE_TAIL_RATIO = 0.2


-# =========================================================================
-# Skills prompt cache
-# =========================================================================
-
-_SKILLS_PROMPT_CACHE_MAX = 8
-_SKILLS_PROMPT_CACHE: OrderedDict[tuple, str] = OrderedDict()
-_SKILLS_PROMPT_CACHE_LOCK = threading.Lock()
-_SKILLS_SNAPSHOT_VERSION = 1
-
-
-def _skills_prompt_snapshot_path() -> Path:
-    return get_hermes_home() / ".skills_prompt_snapshot.json"
-
-
-def clear_skills_system_prompt_cache(*, clear_snapshot: bool = False) -> None:
-    """Drop the in-process skills prompt cache (and optionally the disk snapshot)."""
-    with _SKILLS_PROMPT_CACHE_LOCK:
-        _SKILLS_PROMPT_CACHE.clear()
-    if clear_snapshot:
-        try:
-            _skills_prompt_snapshot_path().unlink(missing_ok=True)
-        except OSError as e:
-            logger.debug("Could not remove skills prompt snapshot: %s", e)
-
-
-def _build_skills_manifest(skills_dir: Path) -> dict[str, list[int]]:
-    """Build an mtime/size manifest of all SKILL.md and DESCRIPTION.md files."""
-    manifest: dict[str, list[int]] = {}
-    for filename in ("SKILL.md", "DESCRIPTION.md"):
-        for path in iter_skill_index_files(skills_dir, filename):
-            try:
-                st = path.stat()
-            except OSError:
-                continue
-            manifest[str(path.relative_to(skills_dir))] = [st.st_mtime_ns, st.st_size]
-    return manifest
-
-
-def _load_skills_snapshot(skills_dir: Path) -> Optional[dict]:
-    """Load the disk snapshot if it exists and its manifest still matches."""
-    snapshot_path = _skills_prompt_snapshot_path()
-    if not snapshot_path.exists():
-        return None
-    try:
-        snapshot = json.loads(snapshot_path.read_text(encoding="utf-8"))
-    except Exception:
-        return None
-    if not isinstance(snapshot, dict):
-        return None
-    if snapshot.get("version") != _SKILLS_SNAPSHOT_VERSION:
-        return None
-    if snapshot.get("manifest") != _build_skills_manifest(skills_dir):
-        return None
-    return snapshot
-
-
-def _write_skills_snapshot(
-    skills_dir: Path,
-    manifest: dict[str, list[int]],
-    skill_entries: list[dict],
-    category_descriptions: dict[str, str],
-) -> None:
-    """Persist skill metadata to disk for fast cold-start reuse."""
-    payload = {
-        "version": _SKILLS_SNAPSHOT_VERSION,
-        "manifest": manifest,
-        "skills": skill_entries,
-        "category_descriptions": category_descriptions,
-    }
-    try:
-        atomic_json_write(_skills_prompt_snapshot_path(), payload)
-    except Exception as e:
-        logger.debug("Could not write skills prompt snapshot: %s", e)
-
-
-def _build_snapshot_entry(
-    skill_file: Path,
-    skills_dir: Path,
-    frontmatter: dict,
-    description: str,
-) -> dict:
-    """Build a serialisable metadata dict for one skill."""
-    rel_path = skill_file.relative_to(skills_dir)
-    parts = rel_path.parts
-    if len(parts) >= 2:
-        skill_name = parts[-2]
-        category = "/".join(parts[:-2]) if len(parts) > 2 else parts[0]
-    else:
-        category = "general"
-        skill_name = skill_file.parent.name
-
-    platforms = frontmatter.get("platforms") or []
-    if isinstance(platforms, str):
-        platforms = [platforms]
-
-    return {
-        "skill_name": skill_name,
-        "category": category,
-        "frontmatter_name": str(frontmatter.get("name", skill_name)),
-        "description": description,
-        "platforms": [str(p).strip() for p in platforms if str(p).strip()],
-        "conditions": extract_skill_conditions(frontmatter),
-    }
-
-
 # =========================================================================
 # Skills index
 # =========================================================================
@@ -379,13 +241,22 @@ def _parse_skill_file(skill_file: Path) -> tuple[bool, dict, str]:
    (True, {}, "") to err on the side of showing the skill.
    """
    try:
+        from tools.skills_tool import _parse_frontmatter, skill_matches_platform
+
        raw = skill_file.read_text(encoding="utf-8")[:2000]
-        frontmatter, _ = parse_frontmatter(raw)
+        frontmatter, _ = _parse_frontmatter(raw)

        if not skill_matches_platform(frontmatter):
-            return False, frontmatter, ""
+            return False, {}, ""

-        return True, frontmatter, extract_skill_description(frontmatter)
+        desc = ""
+        raw_desc = frontmatter.get("description", "")
+        if raw_desc:
+            desc = str(raw_desc).strip().strip("'\"")
+            if len(desc) > 60:
+                desc = desc[:57] + "..."
+
+        return True, frontmatter, desc
    except Exception as e:
        logger.debug("Failed to parse skill file %s: %s", skill_file, e)
        return True, {}, ""
@@ -394,9 +265,16 @@ def _parse_skill_file(skill_file: Path) -> tuple[bool, dict, str]:
 def _read_skill_conditions(skill_file: Path) -> dict:
    """Extract conditional activation fields from SKILL.md frontmatter."""
    try:
+        from tools.skills_tool import _parse_frontmatter
        raw = skill_file.read_text(encoding="utf-8")[:2000]
-        frontmatter, _ = parse_frontmatter(raw)
-        return extract_skill_conditions(frontmatter)
+        frontmatter, _ = _parse_frontmatter(raw)
+        hermes = frontmatter.get("metadata", {}).get("hermes", {})
+        return {
+            "fallback_for_toolsets": hermes.get("fallback_for_toolsets", []),
+            "requires_toolsets": hermes.get("requires_toolsets", []),
+            "fallback_for_tools": hermes.get("fallback_for_tools", []),
+            "requires_tools": hermes.get("requires_tools", []),
+        }
    except Exception as e:
        logger.debug("Failed to read skill conditions from %s: %s", skill_file, e)
        return {}
@@ -439,210 +317,109 @@ def build_skills_system_prompt(
 ) -> str:
    """Build a compact skill index for the system prompt.

-    Two-layer cache:
-      1. In-process LRU dict keyed by (skills_dir, tools, toolsets)
-      2. Disk snapshot (``.skills_prompt_snapshot.json``) validated by
-         mtime/size manifest — survives process restarts
-
-    Falls back to a full filesystem scan when both layers miss.
-
-    External skill directories (``skills.external_dirs`` in config.yaml) are
-    scanned alongside the local ``~/.hermes/skills/`` directory.  External dirs
-    are read-only — they appear in the index but new skills are always created
-    in the local dir.  Local skills take precedence when names collide.
+    Scans ~/.hermes/skills/ for SKILL.md files grouped by category.
+    Includes per-skill descriptions from frontmatter so the model can
+    match skills by meaning, not just name.
+    Filters out skills incompatible with the current OS platform.
    """
    hermes_home = get_hermes_home()
    skills_dir = hermes_home / "skills"
-    external_dirs = get_all_skills_dirs()[1:]  # skip local (index 0)

-    if not skills_dir.exists() and not external_dirs:
+    if not skills_dir.exists():
        return ""

-    # ── Layer 1: in-process LRU cache ─────────────────────────────────
-    cache_key = (
-        str(skills_dir.resolve()),
-        tuple(str(d) for d in external_dirs),
-        tuple(sorted(str(t) for t in (available_tools or set()))),
-        tuple(sorted(str(ts) for ts in (available_toolsets or set()))),
-    )
-    with _SKILLS_PROMPT_CACHE_LOCK:
-        cached = _SKILLS_PROMPT_CACHE.get(cache_key)
-        if cached is not None:
-            _SKILLS_PROMPT_CACHE.move_to_end(cache_key)
-            return cached
-
-    disabled = get_disabled_skill_names()
-
-    # ── Layer 2: disk snapshot ────────────────────────────────────────
-    snapshot = _load_skills_snapshot(skills_dir)
+    # Collect skills with descriptions, grouped by category.
+    # Each entry: (skill_name, description)
+    # Supports sub-categories: skills/mlops/training/axolotl/SKILL.md
+    # -> category "mlops/training", skill "axolotl"
+    # Load disabled skill names once for the entire scan
+    try:
+        from tools.skills_tool import _get_disabled_skill_names
+        disabled = _get_disabled_skill_names()
+    except Exception:
+        disabled = set()

    skills_by_category: dict[str, list[tuple[str, str]]] = {}
-    category_descriptions: dict[str, str] = {}
-
-    if snapshot is not None:
-        # Fast path: use pre-parsed metadata from disk
-        for entry in snapshot.get("skills", []):
-            if not isinstance(entry, dict):
-                continue
-            skill_name = entry.get("skill_name") or ""
-            category = entry.get("category") or "general"
-            frontmatter_name = entry.get("frontmatter_name") or skill_name
-            platforms = entry.get("platforms") or []
-            if not skill_matches_platform({"platforms": platforms}):
-                continue
-            if frontmatter_name in disabled or skill_name in disabled:
-                continue
-            if not _skill_should_show(
-                entry.get("conditions") or {},
-                available_tools,
-                available_toolsets,
-            ):
-                continue
-            skills_by_category.setdefault(category, []).append(
-                (skill_name, entry.get("description", ""))
-            )
-        category_descriptions = {
-            str(k): str(v)
-            for k, v in (snapshot.get("category_descriptions") or {}).items()
+    for skill_file in skills_dir.rglob("SKILL.md"):
+        is_compatible, frontmatter, desc = _parse_skill_file(skill_file)
+        if not is_compatible:
+            continue
+        rel_path = skill_file.relative_to(skills_dir)
+        parts = rel_path.parts
+        if len(parts) >= 2:
+            skill_name = parts[-2]
+            category = "/".join(parts[:-2]) if len(parts) > 2 else parts[0]
+        else:
+            category = "general"
+            skill_name = skill_file.parent.name
+        # Respect user's disabled skills config
+        fm_name = frontmatter.get("name", skill_name)
+        if fm_name in disabled or skill_name in disabled:
+            continue
+        # Extract conditions inline from already-parsed frontmatter
+        # (avoids redundant file re-read that _read_skill_conditions would do)
+        hermes_meta = (frontmatter.get("metadata") or {}).get("hermes") or {}
+        conditions = {
+            "fallback_for_toolsets": hermes_meta.get("fallback_for_toolsets", []),
+            "requires_toolsets": hermes_meta.get("requires_toolsets", []),
+            "fallback_for_tools": hermes_meta.get("fallback_for_tools", []),
+            "requires_tools": hermes_meta.get("requires_tools", []),
        }
-    else:
-        # Cold path: full filesystem scan + write snapshot for next time
-        skill_entries: list[dict] = []
-        for skill_file in iter_skill_index_files(skills_dir, "SKILL.md"):
-            is_compatible, frontmatter, desc = _parse_skill_file(skill_file)
-            entry = _build_snapshot_entry(skill_file, skills_dir, frontmatter, desc)
-            skill_entries.append(entry)
-            if not is_compatible:
-                continue
-            skill_name = entry["skill_name"]
-            if entry["frontmatter_name"] in disabled or skill_name in disabled:
-                continue
-            if not _skill_should_show(
-                extract_skill_conditions(frontmatter),
-                available_tools,
-                available_toolsets,
-            ):
-                continue
-            skills_by_category.setdefault(entry["category"], []).append(
-                (skill_name, entry["description"])
-            )
+        if not _skill_should_show(conditions, available_tools, available_toolsets):
+            continue
+        skills_by_category.setdefault(category, []).append((skill_name, desc))

-        # Read category-level DESCRIPTION.md files
-        for desc_file in iter_skill_index_files(skills_dir, "DESCRIPTION.md"):
+    if not skills_by_category:
+        return ""
+
+    # Read category-level descriptions from DESCRIPTION.md
+    # Checks both the exact category path and parent directories
+    category_descriptions = {}
+    for category in skills_by_category:
+        cat_path = Path(category)
+        desc_file = skills_dir / cat_path / "DESCRIPTION.md"
+        if desc_file.exists():
            try:
                content = desc_file.read_text(encoding="utf-8")
-                fm, _ = parse_frontmatter(content)
-                cat_desc = fm.get("description")
-                if not cat_desc:
-                    continue
-                rel = desc_file.relative_to(skills_dir)
-                cat = "/".join(rel.parts[:-1]) if len(rel.parts) > 1 else "general"
-                category_descriptions[cat] = str(cat_desc).strip().strip("'\"")
+                match = re.search(r"^---\s*\n.*?description:\s*(.+?)\s*\n.*?^---", content, re.MULTILINE | re.DOTALL)
+                if match:
+                    category_descriptions[category] = match.group(1).strip()
            except Exception as e:
                logger.debug("Could not read skill description %s: %s", desc_file, e)

-        _write_skills_snapshot(
-            skills_dir,
-            _build_skills_manifest(skills_dir),
-            skill_entries,
-            category_descriptions,
-        )
-
-    # ── External skill directories ─────────────────────────────────────
-    # Scan external dirs directly (no snapshot caching — they're read-only
-    # and typically small).  Local skills already in skills_by_category take
-    # precedence: we track seen names and skip duplicates from external dirs.
-    seen_skill_names: set[str] = set()
-    for cat_skills in skills_by_category.values():
-        for name, _desc in cat_skills:
-            seen_skill_names.add(name)
-
-    for ext_dir in external_dirs:
-        if not ext_dir.exists():
-            continue
-        for skill_file in iter_skill_index_files(ext_dir, "SKILL.md"):
-            try:
-                is_compatible, frontmatter, desc = _parse_skill_file(skill_file)
-                if not is_compatible:
-                    continue
-                entry = _build_snapshot_entry(skill_file, ext_dir, frontmatter, desc)
-                skill_name = entry["skill_name"]
-                if skill_name in seen_skill_names:
-                    continue
-                if entry["frontmatter_name"] in disabled or skill_name in disabled:
-                    continue
-                if not _skill_should_show(
-                    extract_skill_conditions(frontmatter),
-                    available_tools,
-                    available_toolsets,
-                ):
-                    continue
-                seen_skill_names.add(skill_name)
-                skills_by_category.setdefault(entry["category"], []).append(
-                    (skill_name, entry["description"])
-                )
-            except Exception as e:
-                logger.debug("Error reading external skill %s: %s", skill_file, e)
-
-        # External category descriptions
-        for desc_file in iter_skill_index_files(ext_dir, "DESCRIPTION.md"):
-            try:
-                content = desc_file.read_text(encoding="utf-8")
-                fm, _ = parse_frontmatter(content)
-                cat_desc = fm.get("description")
-                if not cat_desc:
-                    continue
-                rel = desc_file.relative_to(ext_dir)
-                cat = "/".join(rel.parts[:-1]) if len(rel.parts) > 1 else "general"
-                category_descriptions.setdefault(cat, str(cat_desc).strip().strip("'\""))
-            except Exception as e:
-                logger.debug("Could not read external skill description %s: %s", desc_file, e)
-
-    if not skills_by_category:
-        result = ""
-    else:
-        index_lines = []
-        for category in sorted(skills_by_category.keys()):
-            cat_desc = category_descriptions.get(category, "")
-            if cat_desc:
-                index_lines.append(f"  {category}: {cat_desc}")
+    index_lines = []
+    for category in sorted(skills_by_category.keys()):
+        cat_desc = category_descriptions.get(category, "")
+        if cat_desc:
+            index_lines.append(f"  {category}: {cat_desc}")
+        else:
+            index_lines.append(f"  {category}:")
+        # Deduplicate and sort skills within each category
+        seen = set()
+        for name, desc in sorted(skills_by_category[category], key=lambda x: x[0]):
+            if name in seen:
+                continue
+            seen.add(name)
+            if desc:
+                index_lines.append(f"    - {name}: {desc}")
            else:
-                index_lines.append(f"  {category}:")
-            # Deduplicate and sort skills within each category
-            seen = set()
-            for name, desc in sorted(skills_by_category[category], key=lambda x: x[0]):
-                if name in seen:
-                    continue
-                seen.add(name)
-                if desc:
-                    index_lines.append(f"    - {name}: {desc}")
-                else:
-                    index_lines.append(f"    - {name}")
+                index_lines.append(f"    - {name}")

-        result = (
-            "## Skills (mandatory)\n"
-            "Before replying, scan the skills below. If one clearly matches your task, "
-            "load it with skill_view(name) and follow its instructions. "
-            "If a skill has issues, fix it with skill_manage(action='patch').\n"
-            "After 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"
-            "<available_skills>\n"
-            + "\n".join(index_lines) + "\n"
-            "</available_skills>\n"
-            "\n"
-            "If none match, proceed normally without loading a skill."
-        )
-
-    # ── Store in LRU cache ────────────────────────────────────────────
-    with _SKILLS_PROMPT_CACHE_LOCK:
-        _SKILLS_PROMPT_CACHE[cache_key] = result
-        _SKILLS_PROMPT_CACHE.move_to_end(cache_key)
-        while len(_SKILLS_PROMPT_CACHE) > _SKILLS_PROMPT_CACHE_MAX:
-            _SKILLS_PROMPT_CACHE.popitem(last=False)
-
-    return result
+    return (
+        "## Skills (mandatory)\n"
+        "Before replying, scan the skills below. If one clearly matches your task, "
+        "load it with skill_view(name) and follow its instructions. "
+        "If a skill has issues, fix it with skill_manage(action='patch').\n"
+        "After 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"
+        "<available_skills>\n"
+        + "\n".join(index_lines) + "\n"
+        "</available_skills>\n"
+        "\n"
+        "If none match, proceed normally without loading a skill."
+    )


 # =========================================================================
@@ -13,19 +13,11 @@ import re

 logger = logging.getLogger(__name__)

-# Snapshot at import time so runtime env mutations (e.g. LLM-generated
-# `export HERMES_REDACT_SECRETS=false`) cannot disable redaction mid-session.
-_REDACT_ENABLED = os.getenv("HERMES_REDACT_SECRETS", "").lower() not in ("0", "false", "no", "off")
-
 # Known API key prefixes -- match the prefix + contiguous token chars
 _PREFIX_PATTERNS = [
    r"sk-[A-Za-z0-9_-]{10,}",           # OpenAI / OpenRouter / Anthropic (sk-ant-*)
    r"ghp_[A-Za-z0-9]{10,}",            # GitHub PAT (classic)
    r"github_pat_[A-Za-z0-9_]{10,}",    # GitHub PAT (fine-grained)
-    r"gho_[A-Za-z0-9]{10,}",            # GitHub OAuth access token
-    r"ghu_[A-Za-z0-9]{10,}",            # GitHub user-to-server token
-    r"ghs_[A-Za-z0-9]{10,}",            # GitHub server-to-server token
-    r"ghr_[A-Za-z0-9]{10,}",            # GitHub refresh token
    r"xox[baprs]-[A-Za-z0-9-]{10,}",    # Slack tokens
    r"AIza[A-Za-z0-9_-]{30,}",          # Google API keys
    r"pplx-[A-Za-z0-9]{10,}",           # Perplexity
@@ -45,9 +37,6 @@ _PREFIX_PATTERNS = [
    r"dop_v1_[A-Za-z0-9]{10,}",         # DigitalOcean PAT
    r"doo_v1_[A-Za-z0-9]{10,}",         # DigitalOcean OAuth
    r"am_[A-Za-z0-9_-]{10,}",           # AgentMail API key
-    r"sk_[A-Za-z0-9_]{10,}",            # ElevenLabs TTS key (sk_ underscore, not sk- dash)
-    r"tvly-[A-Za-z0-9]{10,}",           # Tavily search API key
-    r"exa_[A-Za-z0-9]{10,}",            # Exa search API key
 ]

 # ENV assignment patterns: KEY=value where KEY contains a secret-like name
@@ -117,7 +106,7 @@ def redact_sensitive_text(text: str) -> str:
        text = str(text)
    if not text:
        return text
-    if not _REDACT_ENABLED:
+    if os.getenv("HERMES_REDACT_SECRETS", "").lower() in ("0", "false", "no", "off"):
        return text

    # Known prefixes (sk-, ghp_, etc.)
@@ -128,11 +128,7 @@ def _build_skill_message(
                        supporting.append(rel)

    if supporting and skill_dir:
-        try:
-            skill_view_target = str(skill_dir.relative_to(SKILLS_DIR))
-        except ValueError:
-            # Skill is from an external dir — use the skill name instead
-            skill_view_target = skill_dir.name
+        skill_view_target = str(skill_dir.relative_to(SKILLS_DIR))
        parts.append("")
        parts.append("[This skill has supporting files you can load with the skill_view tool:]")
        for sf in supporting:
@@ -162,49 +158,38 @@ def scan_skill_commands() -> Dict[str, Dict[str, Any]]:
    _skill_commands = {}
    try:
        from tools.skills_tool import SKILLS_DIR, _parse_frontmatter, skill_matches_platform, _get_disabled_skill_names
-        from agent.skill_utils import get_external_skills_dirs
+        if not SKILLS_DIR.exists():
+            return _skill_commands
        disabled = _get_disabled_skill_names()
-        seen_names: set = set()
-
-        # Scan local dir first, then external dirs
-        dirs_to_scan = []
-        if SKILLS_DIR.exists():
-            dirs_to_scan.append(SKILLS_DIR)
-        dirs_to_scan.extend(get_external_skills_dirs())
-
-        for scan_dir in dirs_to_scan:
-            for skill_md in scan_dir.rglob("SKILL.md"):
-                if any(part in ('.git', '.github', '.hub') for part in skill_md.parts):
+        for skill_md in SKILLS_DIR.rglob("SKILL.md"):
+            if any(part in ('.git', '.github', '.hub') for part in skill_md.parts):
+                continue
+            try:
+                content = skill_md.read_text(encoding='utf-8')
+                frontmatter, body = _parse_frontmatter(content)
+                # Skip skills incompatible with the current OS platform
+                if not skill_matches_platform(frontmatter):
                    continue
-                try:
-                    content = skill_md.read_text(encoding='utf-8')
-                    frontmatter, body = _parse_frontmatter(content)
-                    # Skip skills incompatible with the current OS platform
-                    if not skill_matches_platform(frontmatter):
-                        continue
-                    name = frontmatter.get('name', skill_md.parent.name)
-                    if name in seen_names:
-                        continue
-                    # Respect user's disabled skills config
-                    if name in disabled:
-                        continue
-                    description = frontmatter.get('description', '')
-                    if not description:
-                        for line in body.strip().split('\n'):
-                            line = line.strip()
-                            if line and not line.startswith('#'):
-                                description = line[:80]
-                                break
-                    seen_names.add(name)
-                    cmd_name = name.lower().replace(' ', '-').replace('_', '-')
-                    _skill_commands[f"/{cmd_name}"] = {
-                        "name": name,
-                        "description": description or f"Invoke the {name} skill",
-                        "skill_md_path": str(skill_md),
-                        "skill_dir": str(skill_md.parent),
-                    }
-                except Exception:
+                name = frontmatter.get('name', skill_md.parent.name)
+                # Respect user's disabled skills config
+                if name in disabled:
                    continue
+                description = frontmatter.get('description', '')
+                if not description:
+                    for line in body.strip().split('\n'):
+                        line = line.strip()
+                        if line and not line.startswith('#'):
+                            description = line[:80]
+                            break
+                cmd_name = name.lower().replace(' ', '-').replace('_', '-')
+                _skill_commands[f"/{cmd_name}"] = {
+                    "name": name,
+                    "description": description or f"Invoke the {name} skill",
+                    "skill_md_path": str(skill_md),
+                    "skill_dir": str(skill_md.parent),
+                }
+            except Exception:
+                continue
    except Exception:
        pass
    return _skill_commands
@@ -1,276 +0,0 @@
-"""Lightweight skill metadata utilities shared by prompt_builder and skills_tool.
-
-This module intentionally avoids importing the tool registry, CLI config, or any
-heavy dependency chain.  It is safe to import at module level without triggering
-tool registration or provider resolution.
-"""
-
-import logging
-import os
-import re
-import sys
-from pathlib import Path
-from typing import Any, Dict, List, Optional, Set, Tuple
-
-from hermes_constants import get_hermes_home
-
-logger = logging.getLogger(__name__)
-
-# ── Platform mapping ──────────────────────────────────────────────────────
-
-PLATFORM_MAP = {
-    "macos": "darwin",
-    "linux": "linux",
-    "windows": "win32",
-}
-
-EXCLUDED_SKILL_DIRS = frozenset((".git", ".github", ".hub"))
-
-# ── Lazy YAML loader ─────────────────────────────────────────────────────
-
-_yaml_load_fn = None
-
-
-def yaml_load(content: str):
-    """Parse YAML with lazy import and CSafeLoader preference."""
-    global _yaml_load_fn
-    if _yaml_load_fn is None:
-        import yaml
-
-        loader = getattr(yaml, "CSafeLoader", None) or yaml.SafeLoader
-
-        def _load(value: str):
-            return yaml.load(value, Loader=loader)
-
-        _yaml_load_fn = _load
-    return _yaml_load_fn(content)
-
-
-# ── Frontmatter parsing ──────────────────────────────────────────────────
-
-
-def parse_frontmatter(content: str) -> Tuple[Dict[str, Any], str]:
-    """Parse YAML frontmatter from a markdown string.
-
-    Uses yaml with CSafeLoader for full YAML support (nested metadata, lists)
-    with a fallback to simple key:value splitting for robustness.
-
-    Returns:
-        (frontmatter_dict, remaining_body)
-    """
-    frontmatter: Dict[str, Any] = {}
-    body = content
-
-    if not content.startswith("---"):
-        return frontmatter, body
-
-    end_match = re.search(r"\n---\s*\n", content[3:])
-    if not end_match:
-        return frontmatter, body
-
-    yaml_content = content[3 : end_match.start() + 3]
-    body = content[end_match.end() + 3 :]
-
-    try:
-        parsed = yaml_load(yaml_content)
-        if isinstance(parsed, dict):
-            frontmatter = parsed
-    except Exception:
-        # Fallback: simple key:value parsing for malformed YAML
-        for line in yaml_content.strip().split("\n"):
-            if ":" not in line:
-                continue
-            key, value = line.split(":", 1)
-            frontmatter[key.strip()] = value.strip()
-
-    return frontmatter, body
-
-
-# ── Platform matching ─────────────────────────────────────────────────────
-
-
-def skill_matches_platform(frontmatter: Dict[str, Any]) -> bool:
-    """Return True when the skill is compatible with the current OS.
-
-    Skills declare platform requirements via a top-level ``platforms`` list
-    in their YAML frontmatter::
-
-        platforms: [macos]          # macOS only
-        platforms: [macos, linux]   # macOS and Linux
-
-    If the field is absent or empty the skill is compatible with **all**
-    platforms (backward-compatible default).
-    """
-    platforms = frontmatter.get("platforms")
-    if not platforms:
-        return True
-    if not isinstance(platforms, list):
-        platforms = [platforms]
-    current = sys.platform
-    for platform in platforms:
-        normalized = str(platform).lower().strip()
-        mapped = PLATFORM_MAP.get(normalized, normalized)
-        if current.startswith(mapped):
-            return True
-    return False
-
-
-# ── Disabled skills ───────────────────────────────────────────────────────
-
-
-def get_disabled_skill_names() -> Set[str]:
-    """Read disabled skill names from config.yaml.
-
-    Resolves platform from ``HERMES_PLATFORM`` env var, falls back to
-    the global disabled list.  Reads the config file directly (no CLI
-    config imports) to stay lightweight.
-    """
-    config_path = get_hermes_home() / "config.yaml"
-    if not config_path.exists():
-        return set()
-    try:
-        parsed = yaml_load(config_path.read_text(encoding="utf-8"))
-    except Exception as e:
-        logger.debug("Could not read skill config %s: %s", config_path, e)
-        return set()
-    if not isinstance(parsed, dict):
-        return set()
-
-    skills_cfg = parsed.get("skills")
-    if not isinstance(skills_cfg, dict):
-        return set()
-
-    resolved_platform = os.getenv("HERMES_PLATFORM")
-    if resolved_platform:
-        platform_disabled = (skills_cfg.get("platform_disabled") or {}).get(
-            resolved_platform
-        )
-        if platform_disabled is not None:
-            return _normalize_string_set(platform_disabled)
-    return _normalize_string_set(skills_cfg.get("disabled"))
-
-
-def _normalize_string_set(values) -> Set[str]:
-    if values is None:
-        return set()
-    if isinstance(values, str):
-        values = [values]
-    return {str(v).strip() for v in values if str(v).strip()}
-
-
-# ── External skills directories ──────────────────────────────────────────
-
-
-def get_external_skills_dirs() -> List[Path]:
-    """Read ``skills.external_dirs`` from config.yaml and return validated paths.
-
-    Each entry is expanded (``~`` and ``${VAR}``) and resolved to an absolute
-    path.  Only directories that actually exist are returned.  Duplicates and
-    paths that resolve to the local ``~/.hermes/skills/`` are silently skipped.
-    """
-    config_path = get_hermes_home() / "config.yaml"
-    if not config_path.exists():
-        return []
-    try:
-        parsed = yaml_load(config_path.read_text(encoding="utf-8"))
-    except Exception:
-        return []
-    if not isinstance(parsed, dict):
-        return []
-
-    skills_cfg = parsed.get("skills")
-    if not isinstance(skills_cfg, dict):
-        return []
-
-    raw_dirs = skills_cfg.get("external_dirs")
-    if not raw_dirs:
-        return []
-    if isinstance(raw_dirs, str):
-        raw_dirs = [raw_dirs]
-    if not isinstance(raw_dirs, list):
-        return []
-
-    local_skills = (get_hermes_home() / "skills").resolve()
-    seen: Set[Path] = set()
-    result: List[Path] = []
-
-    for entry in raw_dirs:
-        entry = str(entry).strip()
-        if not entry:
-            continue
-        # Expand ~ and environment variables
-        expanded = os.path.expanduser(os.path.expandvars(entry))
-        p = Path(expanded).resolve()
-        if p == local_skills:
-            continue
-        if p in seen:
-            continue
-        if p.is_dir():
-            seen.add(p)
-            result.append(p)
-        else:
-            logger.debug("External skills dir does not exist, skipping: %s", p)
-
-    return result
-
-
-def get_all_skills_dirs() -> List[Path]:
-    """Return all skill directories: local ``~/.hermes/skills/`` first, then external.
-
-    The local dir is always first (and always included even if it doesn't exist
-    yet — callers handle that).  External dirs follow in config order.
-    """
-    dirs = [get_hermes_home() / "skills"]
-    dirs.extend(get_external_skills_dirs())
-    return dirs
-
-
-# ── Condition extraction ──────────────────────────────────────────────────
-
-
-def extract_skill_conditions(frontmatter: Dict[str, Any]) -> Dict[str, List]:
-    """Extract conditional activation fields from parsed frontmatter."""
-    metadata = frontmatter.get("metadata")
-    # Handle cases where metadata is not a dict (e.g., a string from malformed YAML)
-    if not isinstance(metadata, dict):
-        metadata = {}
-    hermes = metadata.get("hermes") or {}
-    if not isinstance(hermes, dict):
-        hermes = {}
-    return {
-        "fallback_for_toolsets": hermes.get("fallback_for_toolsets", []),
-        "requires_toolsets": hermes.get("requires_toolsets", []),
-        "fallback_for_tools": hermes.get("fallback_for_tools", []),
-        "requires_tools": hermes.get("requires_tools", []),
-    }
-
-
-# ── Description extraction ────────────────────────────────────────────────
-
-
-def extract_skill_description(frontmatter: Dict[str, Any]) -> str:
-    """Extract a truncated description from parsed frontmatter."""
-    raw_desc = frontmatter.get("description", "")
-    if not raw_desc:
-        return ""
-    desc = str(raw_desc).strip().strip("'\"")
-    if len(desc) > 60:
-        return desc[:57] + "..."
-    return desc
-
-
-# ── File iteration ────────────────────────────────────────────────────────
-
-
-def iter_skill_index_files(skills_dir: Path, filename: str):
-    """Walk skills_dir yielding sorted paths matching *filename*.
-
-    Excludes ``.git``, ``.github``, ``.hub`` directories.
-    """
-    matches = []
-    for root, dirs, files in os.walk(skills_dir):
-        dirs[:] = [d for d in dirs if d not in EXCLUDED_SKILL_DIRS]
-        if filename in files:
-            matches.append(Path(root) / filename)
-    for path in sorted(matches, key=lambda p: str(p.relative_to(skills_dir))):
-        yield path
@@ -127,7 +127,6 @@ def resolve_turn_route(user_message: str, routing_config: Optional[Dict[str, Any
                "api_mode": primary.get("api_mode"),
                "command": primary.get("command"),
                "args": list(primary.get("args") or []),
-                "credential_pool": primary.get("credential_pool"),
            },
            "label": None,
            "signature": (
@@ -163,7 +162,6 @@ def resolve_turn_route(user_message: str, routing_config: Optional[Dict[str, Any
                "api_mode": primary.get("api_mode"),
                "command": primary.get("command"),
                "args": list(primary.get("args") or []),
-                "credential_pool": primary.get("credential_pool"),
            },
            "label": None,
            "signature": (
@@ -19,7 +19,7 @@ _TITLE_PROMPT = (
 )


-def generate_title(user_message: str, assistant_response: str, timeout: float = 30.0) -> Optional[str]:
+def generate_title(user_message: str, assistant_response: str, timeout: float = 15.0) -> Optional[str]:
    """Generate a session title from the first exchange.

    Uses the auxiliary LLM client (cheapest/fastest available model).
@@ -7,33 +7,17 @@
 # =============================================================================
 model:
  # Default model to use (can be overridden with --model flag)
-  # Both "default" and "model" work as the key name here.
  default: "anthropic/claude-opus-4.6"
  
  # Inference provider selection:
-  #   "auto"         - Auto-detect from credentials (default)
-  #   "openrouter"   - OpenRouter (requires: OPENROUTER_API_KEY or OPENAI_API_KEY)
-  #   "nous"         - Nous Portal OAuth (requires: hermes login)
-  #   "nous-api"     - Nous Portal API key (requires: NOUS_API_KEY)
-  #   "anthropic"    - Direct Anthropic API (requires: ANTHROPIC_API_KEY)
-  #   "openai-codex" - OpenAI Codex (requires: hermes login --provider openai-codex)
-  #   "copilot"      - GitHub Copilot / GitHub Models (requires: GITHUB_TOKEN)
-  #   "zai"          - z.ai / ZhipuAI GLM (requires: GLM_API_KEY)
-  #   "kimi-coding"  - Kimi / Moonshot AI (requires: KIMI_API_KEY)
-  #   "minimax"      - MiniMax global (requires: MINIMAX_API_KEY)
-  #   "minimax-cn"   - MiniMax China (requires: MINIMAX_CN_API_KEY)
-  #   "huggingface"  - Hugging Face Inference (requires: HF_TOKEN)
-  #   "kilocode"     - KiloCode gateway (requires: KILOCODE_API_KEY)
-  #   "ai-gateway"   - Vercel AI Gateway (requires: AI_GATEWAY_API_KEY)
-  #
-  # Local servers (LM Studio, Ollama, vLLM, llama.cpp):
-  #   "custom"       - Any OpenAI-compatible endpoint. Set base_url below.
-  #   Aliases: "lmstudio", "ollama", "vllm", "llamacpp" all map to "custom".
-  #   Example for LM Studio:
-  #     provider: "lmstudio"
-  #     base_url: "http://localhost:1234/v1"
-  #   No API key needed — local servers typically ignore auth.
-  #
+  #   "auto"       - Use Nous Portal if logged in, otherwise OpenRouter/env vars (default)
+  #   "nous-api"   - Use Nous Portal via API key (requires: NOUS_API_KEY)
+  #   "openrouter" - Always use OpenRouter API key from OPENROUTER_API_KEY
+  #   "nous"       - Always use Nous Portal (requires: hermes login)
+  #   "zai"        - Use z.ai / ZhipuAI GLM models (requires: GLM_API_KEY)
+  #   "kimi-coding"- Use Kimi / Moonshot AI models (requires: KIMI_API_KEY)
+  #   "minimax"    - Use MiniMax global endpoint (requires: MINIMAX_API_KEY)
+  #   "minimax-cn" - Use MiniMax China endpoint (requires: MINIMAX_CN_API_KEY)
  # Can also be overridden with --provider flag or HERMES_INFERENCE_PROVIDER env var.
  provider: "auto"
  
@@ -324,9 +308,6 @@ compression:
 #   vision:
 #     provider: "auto"
 #     model: ""              # e.g. "google/gemini-2.5-flash", "openai/gpt-4o"
-#     timeout: 30            # LLM API call timeout (seconds)
-#     download_timeout: 30   # Image HTTP download timeout (seconds)
-#                            # Increase for slow connections or self-hosted image servers
 #
 #   # Web page scraping / summarization + browser page text extraction
 #   web_extract:
@@ -420,15 +401,6 @@ skills:
  # Set to 0 to disable.
  creation_nudge_interval: 15

-  # External skill directories — share skills across tools/agents without
-  # copying them into ~/.hermes/skills/.  Each path is expanded (~ and ${VAR})
-  # and resolved to an absolute path.  External dirs are read-only: skill
-  # creation always writes to ~/.hermes/skills/.  Local skills take precedence
-  # when names collide.
-  # external_dirs:
-  #   - ~/.agents/skills
-  #   - /home/shared/team-skills
-
 # =============================================================================
 # Agent Behavior
 # =============================================================================
@@ -716,12 +688,6 @@ display:
  # Toggle at runtime with /verbose in the CLI
  tool_progress: all

-  # What Enter does when Hermes is already busy in the CLI.
-  #   interrupt: Interrupt the current run and redirect Hermes (default)
-  #   queue:     Queue your message for the next turn
-  # Ctrl+C always interrupts regardless of this setting.
-  busy_input_mode: interrupt
-
  # Background process notifications (gateway/messaging only).
  # Controls how chatty the process watcher is when you use
  # terminal(background=true, check_interval=...) from Telegram/Discord/etc.
@@ -327,20 +327,7 @@ def load_jobs() -> List[Dict[str, Any]]:
        with open(JOBS_FILE, 'r', encoding='utf-8') as f:
            data = json.load(f)
            return data.get("jobs", [])
-    except json.JSONDecodeError:
-        # Retry with strict=False to handle bare control chars in string values
-        try:
-            with open(JOBS_FILE, 'r', encoding='utf-8') as f:
-                data = json.loads(f.read(), strict=False)
-                jobs = data.get("jobs", [])
-                if jobs:
-                    # Auto-repair: rewrite with proper escaping
-                    save_jobs(jobs)
-                    logger.warning("Auto-repaired jobs.json (had invalid control characters)")
-                return jobs
-        except Exception:
-            return []
-    except IOError:
+    except (json.JSONDecodeError, IOError):
        return []


@@ -611,34 +598,6 @@ def mark_job_run(job_id: str, success: bool, error: Optional[str] = None):
    save_jobs(jobs)


-def advance_next_run(job_id: str) -> bool:
-    """Preemptively advance next_run_at for a recurring job before execution.
-
-    Call this BEFORE run_job() so that if the process crashes mid-execution,
-    the job won't re-fire on the next gateway restart.  This converts the
-    scheduler from at-least-once to at-most-once for recurring jobs — missing
-    one run is far better than firing dozens of times in a crash loop.
-
-    One-shot jobs are left unchanged so they can still retry on restart.
-
-    Returns True if next_run_at was advanced, False otherwise.
-    """
-    jobs = load_jobs()
-    for job in jobs:
-        if job["id"] == job_id:
-            kind = job.get("schedule", {}).get("kind")
-            if kind not in ("cron", "interval"):
-                return False
-            now = _hermes_now().isoformat()
-            new_next = compute_next_run(job["schedule"], now)
-            if new_next and new_next != job.get("next_run_at"):
-                job["next_run_at"] = new_next
-                save_jobs(jobs)
-                return True
-            return False
-    return False
-
-
 def get_due_jobs() -> List[Dict[str, Any]]:
    """Get all jobs that are due to run now.

@@ -26,7 +26,6 @@ except ImportError:
        msvcrt = None
 from pathlib import Path
 from hermes_constants import get_hermes_home
-from hermes_cli.config import load_config
 from typing import Optional

 from hermes_time import now as _hermes_now
@@ -36,7 +35,7 @@ logger = logging.getLogger(__name__)
 # Add parent directory to path for imports
 sys.path.insert(0, str(Path(__file__).parent.parent))

-from cron.jobs import get_due_jobs, mark_job_run, save_job_output, advance_next_run
+from cron.jobs import get_due_jobs, mark_job_run, save_job_output

 # Sentinel: when a cron agent has nothing new to report, it can start its
 # response with this marker to suppress delivery.  Output is still saved
@@ -87,22 +86,6 @@ def _resolve_delivery_target(job: dict) -> Optional[dict]:
            chat_id, thread_id = rest.split(":", 1)
        else:
            chat_id, thread_id = rest, None
-
-        # Resolve human-friendly labels like "Alice (dm)" to real IDs.
-        # send_message(action="list") shows labels with display suffixes
-        # that aren't valid platform IDs (e.g. WhatsApp JIDs).
-        try:
-            from gateway.channel_directory import resolve_channel_name
-            target = chat_id
-            # Strip display suffix like " (dm)" or " (group)"
-            if target.endswith(")") and " (" in target:
-                target = target.rsplit(" (", 1)[0].strip()
-            resolved = resolve_channel_name(platform_name.lower(), target)
-            if resolved:
-                chat_id = resolved
-        except Exception:
-            pass
-
        return {
            "platform": platform_name,
            "chat_id": chat_id,
@@ -162,8 +145,6 @@ def _deliver_result(job: dict, content: str) -> None:
        "mattermost": Platform.MATTERMOST,
        "homeassistant": Platform.HOMEASSISTANT,
        "dingtalk": Platform.DINGTALK,
-        "feishu": Platform.FEISHU,
-        "wecom": Platform.WECOM,
        "email": Platform.EMAIL,
        "sms": Platform.SMS,
    }
@@ -183,29 +164,18 @@ def _deliver_result(job: dict, content: str) -> None:
        logger.warning("Job '%s': platform '%s' not configured/enabled", job["id"], platform_name)
        return

-    # Optionally wrap the content with a header/footer so the user knows this
-    # is a cron delivery.  Wrapping is on by default; set cron.wrap_response: false
-    # in config.yaml for clean output.
-    wrap_response = True
-    try:
-        user_cfg = load_config()
-        wrap_response = user_cfg.get("cron", {}).get("wrap_response", True)
-    except Exception:
-        pass
-
-    if wrap_response:
-        task_name = job.get("name", job["id"])
-        delivery_content = (
-            f"Cronjob Response: {task_name}\n"
-            f"-------------\n\n"
-            f"{content}\n\n"
-            f"Note: The agent cannot see this message, and therefore cannot respond to it."
-        )
-    else:
-        delivery_content = content
+    # Wrap the content so the user knows this is a cron delivery and that
+    # the interactive agent has no visibility into it.
+    task_name = job.get("name", job["id"])
+    wrapped = (
+        f"Cronjob Response: {task_name}\n"
+        f"-------------\n\n"
+        f"{content}\n\n"
+        f"Note: The agent cannot see this message, and therefore cannot respond to it."
+    )

    # Run the async send in a fresh event loop (safe from any thread)
-    coro = _send_to_platform(platform, pconfig, chat_id, delivery_content, thread_id=thread_id)
+    coro = _send_to_platform(platform, pconfig, chat_id, wrapped, thread_id=thread_id)
    try:
        result = asyncio.run(coro)
    except RuntimeError:
@@ -216,7 +186,7 @@ def _deliver_result(job: dict, content: str) -> None:
        coro.close()
        import concurrent.futures
        with concurrent.futures.ThreadPoolExecutor(max_workers=1) as pool:
-            future = pool.submit(asyncio.run, _send_to_platform(platform, pconfig, chat_id, delivery_content, thread_id=thread_id))
+            future = pool.submit(asyncio.run, _send_to_platform(platform, pconfig, chat_id, wrapped, thread_id=thread_id))
            result = future.result(timeout=30)
    except Exception as e:
        logger.error("Job '%s': delivery to %s:%s failed: %s", job["id"], platform_name, chat_id, e)
@@ -236,12 +206,11 @@ def _build_job_prompt(job: dict) -> str:
    # Always prepend [SILENT] guidance so the cron agent can suppress
    # delivery when it has nothing new or noteworthy to report.
    silent_hint = (
-        "[SYSTEM: If you have a meaningful status report or findings, "
-        "send them — that is the whole point of this job. Only respond "
-        "with exactly \"[SILENT]\" (nothing else) when there is genuinely "
-        "nothing new to report. [SILENT] suppresses delivery to the user. "
-        "Never combine [SILENT] with content — either report your "
-        "findings normally, or say [SILENT] and nothing more.]\n\n"
+        "[SYSTEM: If you have nothing new or noteworthy to report, respond "
+        "with exactly \"[SILENT]\" (optionally followed by a brief internal "
+        "note). This suppresses delivery to the user while still saving "
+        "output locally. Only use [SILENT] when there are genuinely no "
+        "changes worth reporting.]\n\n"
    )
    prompt = silent_hint + prompt
    if skills is None:
@@ -339,7 +308,7 @@ def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:
            if delivery_target.get("thread_id") is not None:
                os.environ["HERMES_CRON_AUTO_DELIVER_THREAD_ID"] = str(delivery_target["thread_id"])

-        model = job.get("model") or os.getenv("HERMES_MODEL") or ""
+        model = job.get("model") or os.getenv("HERMES_MODEL") or "anthropic/claude-opus-4.6"

        # Load config.yaml for model, reasoning, prefill, toolsets, provider routing
        _cfg = {}
@@ -555,12 +524,6 @@ def tick(verbose: bool = True) -> int:
        executed = 0
        for job in due_jobs:
            try:
-                # For recurring jobs (cron/interval), advance next_run_at to the
-                # next future occurrence BEFORE execution.  This way, if the
-                # process crashes mid-run, the job won't re-fire on restart.
-                # One-shot jobs are left alone so they can retry on restart.
-                advance_next_run(job["id"])
-
                success, output, final_response, error = run_job(job)

                output_file = save_job_output(job["id"], output)
@@ -1,15 +0,0 @@
-# Hermes Agent Persona
-
-<!--
-This file defines the agent's personality and tone.
-The agent will embody whatever you write here.
-Edit this to customize how Hermes communicates with you.
-
-Examples:
-  - "You are a warm, playful assistant who uses kaomoji occasionally."
-  - "You are a concise technical expert. No fluff, just facts."
-  - "You speak like a friendly coworker who happens to know everything."
-
-This file is loaded fresh each message -- no restart needed.
-Delete the contents (or this file) to use the default personality.
-->
@@ -1,34 +0,0 @@
-#!/bin/bash
-# Docker entrypoint: bootstrap config files into the mounted volume, then run hermes.
-set -e
-
-HERMES_HOME="/opt/data"
-INSTALL_DIR="/opt/hermes"
-
-# Create essential directory structure.  Cache and platform directories
-# (cache/images, cache/audio, platforms/whatsapp, etc.) are created on
-# demand by the application — don't pre-create them here so new installs
-# get the consolidated layout from get_hermes_dir().
-mkdir -p "$HERMES_HOME"/{cron,sessions,logs,hooks,memories,skills}
-
-# .env
-if [ ! -f "$HERMES_HOME/.env" ]; then
-    cp "$INSTALL_DIR/.env.example" "$HERMES_HOME/.env"
-fi
-
-# config.yaml
-if [ ! -f "$HERMES_HOME/config.yaml" ]; then
-    cp "$INSTALL_DIR/cli-config.yaml.example" "$HERMES_HOME/config.yaml"
-fi
-
-# SOUL.md
-if [ ! -f "$HERMES_HOME/SOUL.md" ]; then
-    cp "$INSTALL_DIR/docker/SOUL.md" "$HERMES_HOME/SOUL.md"
-fi
-
-# Sync bundled skills (manifest-based so user edits are preserved)
-if [ -d "$INSTALL_DIR/skills" ]; then
-    python3 "$INSTALL_DIR/tools/skills_sync.py"
-fi
-
-exec hermes "$@"
@@ -101,11 +101,21 @@ Available methods:

 ### Patches (`patches.py`)

-**Problem**: Some hermes-agent tools use `asyncio.run()` internally (e.g., the Modal backend). This crashes when called from inside Atropos's event loop because `asyncio.run()` cannot be nested.
+**Problem**: Some hermes-agent tools use `asyncio.run()` internally (e.g., the Modal backend via SWE-ReX). This crashes when called from inside Atropos's event loop because `asyncio.run()` cannot be nested.

-**Solution**: `ModalEnvironment` uses a dedicated `_AsyncWorker` background thread with its own event loop. The calling code sees a sync interface, but internally all async Modal SDK calls happen on the worker thread so they don't conflict with Atropos's loop. This is built directly into `tools/environments/modal.py` — no monkey-patching required.
+**Solution**: `patches.py` monkey-patches `SwerexModalEnvironment` to use a dedicated background thread (`_AsyncWorker`) with its own event loop. The calling code sees the same sync interface, but internally the async work happens on a separate thread that doesn't conflict with Atropos's loop.

-`patches.py` is now a no-op (kept for backward compatibility with imports).
+What gets patched:
+- `SwerexModalEnvironment.__init__` -- creates Modal deployment on a background thread
+- `SwerexModalEnvironment.execute` -- runs commands on the same background thread
+- `SwerexModalEnvironment.stop` -- stops deployment on the background thread
+
+The patches are:
+- **Idempotent** -- calling `apply_patches()` multiple times is safe
+- **Transparent** -- same interface and behavior, only the internal async execution changes
+- **Universal** -- works identically in normal CLI use (no running event loop)
+
+Applied automatically at import time by `hermes_base_env.py`.

 ### Tool Call Parsers (`tool_call_parsers/`)

@@ -209,7 +209,7 @@ class TerminalBench2EvalEnv(HermesAgentBaseEnv):

            # Agent settings -- TB2 tasks are complex, need many turns
            max_agent_turns=60,
-            max_token_length=16000,
+            max_token_length=***
            agent_temperature=0.6,
            system_prompt=None,

@@ -233,7 +233,7 @@ class TerminalBench2EvalEnv(HermesAgentBaseEnv):
            steps_per_eval=1,
            total_steps=1,

-            tokenizer_name="NousResearch/Hermes-3-Llama-3.1-8B",
+            tokenizer_name="NousRe...1-8B",
            use_wandb=True,
            wandb_name="terminal-bench-2",
            ensure_scores_are_not_same=False,  # Binary rewards may all be 0 or 1
@@ -245,7 +245,7 @@ class TerminalBench2EvalEnv(HermesAgentBaseEnv):
                base_url="https://openrouter.ai/api/v1",
                model_name="anthropic/claude-sonnet-4",
                server_type="openai",
-                api_key=os.getenv("OPENROUTER_API_KEY", ""),
+                api_key=os.get...EY", ""),
                health_check=False,
            )
        ]
@@ -513,446 +513,3 @@ class TerminalBench2EvalEnv(HermesAgentBaseEnv):
                reward = 0.0
            else:
                # Run tests in a thread so the blocking ctx.terminal() calls
-                # don't freeze the entire event loop (which would stall all
-                # other tasks, tqdm updates, and timeout timers).
-                ctx = ToolContext(task_id)
-                try:
-                    loop = asyncio.get_event_loop()
-                    reward = await loop.run_in_executor(
-                        None,  # default thread pool
-                        self._run_tests, eval_item, ctx, task_name,
-                    )
-                except Exception as e:
-                    logger.error("Task %s: test verification failed: %s", task_name, e)
-                    reward = 0.0
-                finally:
-                    ctx.cleanup()
-
-            passed = reward == 1.0
-            status = "PASS" if passed else "FAIL"
-            elapsed = time.time() - task_start
-            tqdm.write(f"  [{status}] {task_name} (turns={result.turns_used}, {elapsed:.0f}s)")
-            logger.info(
-                "Task %s: reward=%.1f, turns=%d, finished=%s",
-                task_name, reward, result.turns_used, result.finished_naturally,
-            )
-
-            out = {
-                "passed": passed,
-                "reward": reward,
-                "task_name": task_name,
-                "category": category,
-                "turns_used": result.turns_used,
-                "finished_naturally": result.finished_naturally,
-                "messages": result.messages,
-            }
-            self._save_result(out)
-            return out
-
-        except Exception as e:
-            elapsed = time.time() - task_start
-            logger.error("Task %s: rollout failed: %s", task_name, e, exc_info=True)
-            tqdm.write(f"  [ERROR] {task_name}: {e} ({elapsed:.0f}s)")
-            out = {
-                "passed": False, "reward": 0.0,
-                "task_name": task_name, "category": category,
-                "error": str(e),
-            }
-            self._save_result(out)
-            return out
-
-        finally:
-            # --- Cleanup: clear overrides, sandbox, and temp files ---
-            clear_task_env_overrides(task_id)
-            try:
-                cleanup_vm(task_id)
-            except Exception as e:
-                logger.debug("VM cleanup for %s: %s", task_id[:8], e)
-            if task_dir and task_dir.exists():
-                shutil.rmtree(task_dir, ignore_errors=True)
-
-    def _run_tests(
-        self, item: Dict[str, Any], ctx: ToolContext, task_name: str
-    ) -> float:
-        """
-        Upload and execute the test suite in the agent's sandbox, then
-        download the verifier output locally to read the reward.
-
-        Follows Harbor's verification pattern:
-        1. Upload tests/ directory into the sandbox
-        2. Execute test.sh inside the sandbox
-        3. Download /logs/verifier/ directory to a local temp dir
-        4. Read reward.txt locally with native Python I/O
-
-        Downloading locally avoids issues with the file_read tool on
-        the Modal VM and matches how Harbor handles verification.
-
-        TB2 test scripts (test.sh) typically:
-        1. Install pytest via uv/pip
-        2. Run pytest against the test files in /tests/
-        3. Write results to /logs/verifier/reward.txt
-
-        Args:
-            item: The TB2 task dict (contains tests_tar, test_sh)
-            ctx: ToolContext scoped to this task's sandbox
-            task_name: For logging
-
-        Returns:
-            1.0 if tests pass, 0.0 otherwise
-        """
-        tests_tar = item.get("tests_tar", "")
-        test_sh = item.get("test_sh", "")
-
-        if not test_sh:
-            logger.warning("Task %s: no test_sh content, reward=0", task_name)
-            return 0.0
-
-        # Create required directories in the sandbox
-        ctx.terminal("mkdir -p /tests /logs/verifier")
-
-        # Upload test files into the sandbox (binary-safe via base64)
-        if tests_tar:
-            tests_temp = Path(tempfile.mkdtemp(prefix=f"tb2-tests-{task_name}-"))
-            try:
-                _extract_base64_tar(tests_tar, tests_temp)
-                ctx.upload_dir(str(tests_temp), "/tests")
-            except Exception as e:
-                logger.warning("Task %s: failed to upload test files: %s", task_name, e)
-            finally:
-                shutil.rmtree(tests_temp, ignore_errors=True)
-
-        # Write the test runner script (test.sh)
-        ctx.write_file("/tests/test.sh", test_sh)
-        ctx.terminal("chmod +x /tests/test.sh")
-
-        # Execute the test suite
-        logger.info(
-            "Task %s: running test suite (timeout=%ds)",
-            task_name, self.config.test_timeout,
-        )
-        test_result = ctx.terminal(
-            "bash /tests/test.sh",
-            timeout=self.config.test_timeout,
-        )
-
-        exit_code = test_result.get("exit_code", -1)
-        output = test_result.get("output", "")
-
-        # Download the verifier output directory locally, then read reward.txt
-        # with native Python I/O. This avoids issues with file_read on the
-        # Modal VM and matches Harbor's verification pattern.
-        reward = 0.0
-        local_verifier_dir = Path(tempfile.mkdtemp(prefix=f"tb2-verifier-{task_name}-"))
-        try:
-            ctx.download_dir("/logs/verifier", str(local_verifier_dir))
-
-            reward_file = local_verifier_dir / "reward.txt"
-            if reward_file.exists() and reward_file.stat().st_size > 0:
-                content = reward_file.read_text().strip()
-                if content == "1":
-                    reward = 1.0
-                elif content == "0":
-                    reward = 0.0
-                else:
-                    # Unexpected content -- try parsing as float
-                    try:
-                        reward = float(content)
-                    except (ValueError, TypeError):
-                        logger.warning(
-                            "Task %s: reward.txt content unexpected (%r), "
-                            "falling back to exit_code=%d",
-                            task_name, content, exit_code,
-                        )
-                        reward = 1.0 if exit_code == 0 else 0.0
-            else:
-                # reward.txt not written -- fall back to exit code
-                logger.warning(
-                    "Task %s: reward.txt not found after download, "
-                    "falling back to exit_code=%d",
-                    task_name, exit_code,
-                )
-                reward = 1.0 if exit_code == 0 else 0.0
-        except Exception as e:
-            logger.warning(
-                "Task %s: failed to download verifier dir: %s, "
-                "falling back to exit_code=%d",
-                task_name, e, exit_code,
-            )
-            reward = 1.0 if exit_code == 0 else 0.0
-        finally:
-            shutil.rmtree(local_verifier_dir, ignore_errors=True)
-
-        # Log test output for debugging failures
-        if reward == 0.0:
-            output_preview = output[-500:] if output else "(no output)"
-            logger.info(
-                "Task %s: FAIL (exit_code=%d)\n%s",
-                task_name, exit_code, output_preview,
-            )
-
-        return reward
-
-    # =========================================================================
-    # Evaluate -- main entry point for the eval subcommand
-    # =========================================================================
-
-    async def _eval_with_timeout(self, item: Dict[str, Any]) -> Dict:
-        """
-        Wrap rollout_and_score_eval with a per-task wall-clock timeout.
-
-        If the task exceeds task_timeout seconds, it's automatically scored
-        as FAIL. This prevents any single task from hanging indefinitely.
-        """
-        task_name = item.get("task_name", "unknown")
-        category = item.get("category", "unknown")
-        try:
-            return await asyncio.wait_for(
-                self.rollout_and_score_eval(item),
-                timeout=self.config.task_timeout,
-            )
-        except asyncio.TimeoutError:
-            from tqdm import tqdm
-            elapsed = self.config.task_timeout
-            tqdm.write(f"  [TIMEOUT] {task_name} (exceeded {elapsed}s wall-clock limit)")
-            logger.error("Task %s: wall-clock timeout after %ds", task_name, elapsed)
-            out = {
-                "passed": False, "reward": 0.0,
-                "task_name": task_name, "category": category,
-                "error": f"timeout ({elapsed}s)",
-            }
-            self._save_result(out)
-            return out
-
-    async def evaluate(self, *args, **kwargs) -> None:
-        """
-        Run Terminal-Bench 2.0 evaluation over all tasks.
-
-        This is the main entry point when invoked via:
-            python environments/terminalbench2_env.py evaluate
-
-        Runs all tasks through rollout_and_score_eval() via asyncio.gather()
-        (same pattern as GPQA and other Atropos eval envs). Each task is
-        wrapped with a wall-clock timeout so hung tasks auto-fail.
-
-        Suppresses noisy Modal/terminal output (HERMES_QUIET) so the tqdm
-        bar stays visible.
-        """
-        start_time = time.time()
-
-        # Route all logging through tqdm.write() so the progress bar stays
-        # pinned at the bottom while log lines scroll above it.
-        from tqdm import tqdm
-
-        class _TqdmHandler(logging.Handler):
-            def emit(self, record):
-                try:
-                    tqdm.write(self.format(record))
-                except Exception:
-                    self.handleError(record)
-
-        handler = _TqdmHandler()
-        handler.setFormatter(logging.Formatter(
-            "%(asctime)s [%(name)s] %(levelname)s: %(message)s",
-            datefmt="%H:%M:%S",
-        ))
-        root = logging.getLogger()
-        root.handlers = [handler]  # Replace any existing handlers
-        root.setLevel(logging.INFO)
-
-        # Silence noisy third-party loggers that flood the output
-        logging.getLogger("httpx").setLevel(logging.WARNING)      # Every HTTP request
-        logging.getLogger("openai").setLevel(logging.WARNING)     # OpenAI client retries
-        logging.getLogger("rex-deploy").setLevel(logging.WARNING) # Swerex deployment
-        logging.getLogger("rex_image_builder").setLevel(logging.WARNING)  # Image builds
-
-        print(f"\n{'='*60}")
-        print("Starting Terminal-Bench 2.0 Evaluation")
-        print(f"{'='*60}")
-        print(f"  Dataset: {self.config.dataset_name}")
-        print(f"  Total tasks: {len(self.all_eval_items)}")
-        print(f"  Max agent turns: {self.config.max_agent_turns}")
-        print(f"  Task timeout: {self.config.task_timeout}s")
-        print(f"  Terminal backend: {self.config.terminal_backend}")
-        print(f"  Tool thread pool: {self.config.tool_pool_size}")
-        print(f"  Terminal timeout: {self.config.terminal_timeout}s/cmd")
-        print(f"  Terminal lifetime: {self.config.terminal_lifetime}s (auto: task_timeout + 120)")
-        print(f"  Max concurrent tasks: {self.config.max_concurrent_tasks}")
-        print(f"{'='*60}\n")
-
-        # Semaphore to limit concurrent Modal sandbox creations.
-        # Without this, all 86 tasks fire simultaneously, each creating a Modal
-        # sandbox via asyncio.run() inside a thread pool worker. Modal's blocking
-        # calls (App.lookup, etc.) deadlock when too many are created at once.
-        semaphore = asyncio.Semaphore(self.config.max_concurrent_tasks)
-
-        async def _eval_with_semaphore(item):
-            async with semaphore:
-                return await self._eval_with_timeout(item)
-
-        # Fire all tasks with wall-clock timeout, track live accuracy on the bar
-        total_tasks = len(self.all_eval_items)
-        eval_tasks = [
-            asyncio.ensure_future(_eval_with_semaphore(item))
-            for item in self.all_eval_items
-        ]
-
-        results = []
-        passed_count = 0
-        pbar = tqdm(total=total_tasks, desc="Evaluating TB2", dynamic_ncols=True)
-        try:
-            for coro in asyncio.as_completed(eval_tasks):
-                result = await coro
-                results.append(result)
-                if result and result.get("passed"):
-                    passed_count += 1
-                done = len(results)
-                pct = (passed_count / done * 100) if done else 0
-                pbar.set_postfix_str(f"pass={passed_count}/{done} ({pct:.1f}%)")
-                pbar.update(1)
-        except (KeyboardInterrupt, asyncio.CancelledError):
-            pbar.close()
-            print(f"\n\nInterrupted! Cleaning up {len(eval_tasks)} tasks...")
-            # Cancel all pending tasks
-            for task in eval_tasks:
-                task.cancel()
-            # Let cancellations propagate (finally blocks run cleanup_vm)
-            await asyncio.gather(*eval_tasks, return_exceptions=True)
-            # Belt-and-suspenders: clean up any remaining sandboxes
-            from tools.terminal_tool import cleanup_all_environments
-            cleanup_all_environments()
-            print("All sandboxes cleaned up.")
-            return
-        finally:
-            pbar.close()
-
-        end_time = time.time()
-
-        # Filter out None results (shouldn't happen, but be safe)
-        valid_results = [r for r in results if r is not None]
-
-        if not valid_results:
-            print("Warning: No valid evaluation results obtained")
-            return
-
-        # ---- Compute metrics ----
-        total = len(valid_results)
-        passed = sum(1 for r in valid_results if r.get("passed"))
-        overall_pass_rate = passed / total if total > 0 else 0.0
-
-        # Per-category breakdown
-        cat_results: Dict[str, List[Dict]] = defaultdict(list)
-        for r in valid_results:
-            cat_results[r.get("category", "unknown")].append(r)
-
-        # Build metrics dict
-        eval_metrics = {
-            "eval/pass_rate": overall_pass_rate,
-            "eval/total_tasks": total,
-            "eval/passed_tasks": passed,
-            "eval/evaluation_time_seconds": end_time - start_time,
-        }
-
-        # Per-category metrics
-        for category, cat_items in sorted(cat_results.items()):
-            cat_passed = sum(1 for r in cat_items if r.get("passed"))
-            cat_total = len(cat_items)
-            cat_pass_rate = cat_passed / cat_total if cat_total > 0 else 0.0
-            cat_key = category.replace(" ", "_").replace("-", "_").lower()
-            eval_metrics[f"eval/pass_rate_{cat_key}"] = cat_pass_rate
-
-        # Store metrics for wandb_log
-        self.eval_metrics = [(k, v) for k, v in eval_metrics.items()]
-
-        # ---- Print summary ----
-        print(f"\n{'='*60}")
-        print("Terminal-Bench 2.0 Evaluation Results")
-        print(f"{'='*60}")
-        print(f"Overall Pass Rate: {overall_pass_rate:.4f} ({passed}/{total})")
-        print(f"Evaluation Time: {end_time - start_time:.1f} seconds")
-
-        print("\nCategory Breakdown:")
-        for category, cat_items in sorted(cat_results.items()):
-            cat_passed = sum(1 for r in cat_items if r.get("passed"))
-            cat_total = len(cat_items)
-            cat_rate = cat_passed / cat_total if cat_total > 0 else 0.0
-            print(f"  {category}: {cat_rate:.1%} ({cat_passed}/{cat_total})")
-
-        # Print individual task results
-        print("\nTask Results:")
-        for r in sorted(valid_results, key=lambda x: x.get("task_name", "")):
-            status = "PASS" if r.get("passed") else "FAIL"
-            turns = r.get("turns_used", "?")
-            error = r.get("error", "")
-            extra = f" (error: {error})" if error else ""
-            print(f"  [{status}] {r['task_name']} (turns={turns}){extra}")
-
-        print(f"{'='*60}\n")
-
-        # Build sample records for evaluate_log (includes full conversations)
-        samples = [
-            {
-                "task_name": r.get("task_name"),
-                "category": r.get("category"),
-                "passed": r.get("passed"),
-                "reward": r.get("reward"),
-                "turns_used": r.get("turns_used"),
-                "error": r.get("error"),
-                "messages": r.get("messages"),
-            }
-            for r in valid_results
-        ]
-
-        # Log evaluation results
-        try:
-            await self.evaluate_log(
-                metrics=eval_metrics,
-                samples=samples,
-                start_time=start_time,
-                end_time=end_time,
-                generation_parameters={
-                    "temperature": self.config.agent_temperature,
-                    "max_tokens": self.config.max_token_length,
-                    "max_agent_turns": self.config.max_agent_turns,
-                    "terminal_backend": self.config.terminal_backend,
-                },
-            )
-        except Exception as e:
-            print(f"Error logging evaluation results: {e}")
-
-        # Close streaming file
-        if hasattr(self, "_streaming_file") and not self._streaming_file.closed:
-            self._streaming_file.close()
-            print(f"  Live results saved to: {self._streaming_path}")
-
-        # Kill all remaining sandboxes. Timed-out tasks leave orphaned thread
-        # pool workers still executing commands -- cleanup_all stops them.
-        from tools.terminal_tool import cleanup_all_environments
-        print("\nCleaning up all sandboxes...")
-        cleanup_all_environments()
-
-        # Shut down the tool thread pool so orphaned workers from timed-out
-        # tasks are killed immediately instead of retrying against dead
-        # sandboxes and spamming the console with TimeoutError warnings.
-        from environments.agent_loop import _tool_executor
-        _tool_executor.shutdown(wait=False, cancel_futures=True)
-        print("Done.")
-
-    # =========================================================================
-    # Wandb logging
-    # =========================================================================
-
-    async def wandb_log(self, wandb_metrics: Optional[Dict] = None):
-        """Log TB2-specific metrics to wandb."""
-        if wandb_metrics is None:
-            wandb_metrics = {}
-
-        # Add stored eval metrics
-        for metric_name, metric_value in self.eval_metrics:
-            wandb_metrics[metric_name] = metric_value
-        self.eval_metrics = []
-
-        await super().wandb_log(wandb_metrics)
-
-
-if __name__ == "__main__":
-    TerminalBench2EvalEnv.cli()
@@ -1 +0,0 @@
-"""Built-in gateway hooks that are always registered."""
@@ -1,86 +0,0 @@
-"""Built-in boot-md hook — run ~/.hermes/BOOT.md on gateway startup.
-
-This hook is always registered. It silently skips if no BOOT.md exists.
-To activate, create ``~/.hermes/BOOT.md`` with instructions for the
-agent to execute on every gateway restart.
-
-Example BOOT.md::
-
-    # Startup Checklist
-
-    1. Check if any cron jobs failed overnight
-    2. Send a status update to Discord #general
-    3. If there are errors in /opt/app/deploy.log, summarize them
-
-The agent runs in a background thread so it doesn't block gateway
-startup. If nothing needs attention, it replies with [SILENT] to
-suppress delivery.
-"""
-
-import logging
-import os
-import threading
-from pathlib import Path
-
-logger = logging.getLogger("hooks.boot-md")
-
-HERMES_HOME = Path(os.environ.get("HERMES_HOME", Path.home() / ".hermes"))
-BOOT_FILE = HERMES_HOME / "BOOT.md"
-
-
-def _build_boot_prompt(content: str) -> str:
-    """Wrap BOOT.md content in a system-level instruction."""
-    return (
-        "You are running a startup boot checklist. Follow the BOOT.md "
-        "instructions below exactly.\n\n"
-        "---\n"
-        f"{content}\n"
-        "---\n\n"
-        "Execute each instruction. If you need to send a message to a "
-        "platform, use the send_message tool.\n"
-        "If nothing needs attention and there is nothing to report, "
-        "reply with ONLY: [SILENT]"
-    )
-
-
-def _run_boot_agent(content: str) -> None:
-    """Spawn a one-shot agent session to execute the boot instructions."""
-    try:
-        from run_agent import AIAgent
-
-        prompt = _build_boot_prompt(content)
-        agent = AIAgent(
-            quiet_mode=True,
-            skip_context_files=True,
-            skip_memory=True,
-            max_iterations=20,
-        )
-        result = agent.run_conversation(prompt)
-        response = result.get("final_response", "")
-        if response and "[SILENT]" not in response:
-            logger.info("boot-md completed: %s", response[:200])
-        else:
-            logger.info("boot-md completed (nothing to report)")
-    except Exception as e:
-        logger.error("boot-md agent failed: %s", e)
-
-
-async def handle(event_type: str, context: dict) -> None:
-    """Gateway startup handler — run BOOT.md if it exists."""
-    if not BOOT_FILE.exists():
-        return
-
-    content = BOOT_FILE.read_text(encoding="utf-8").strip()
-    if not content:
-        return
-
-    logger.info("Running BOOT.md (%d chars)", len(content))
-
-    # Run in a background thread so we don't block gateway startup.
-    thread = threading.Thread(
-        target=_run_boot_agent,
-        args=(content,),
-        name="boot-md",
-        daemon=True,
-    )
-    thread.start()
@@ -27,16 +27,9 @@ def _coerce_bool(value: Any, default: bool = True) -> bool:
        return default
    if isinstance(value, bool):
        return value
-    if isinstance(value, int):
-        return value != 0
    if isinstance(value, str):
-        lowered = value.strip().lower()
-        if lowered in ("true", "1", "yes", "on"):
-            return True
-        if lowered in ("false", "0", "no", "off"):
-            return False
-        return default
-    return default
+        return value.strip().lower() in ("true", "1", "yes", "on")
+    return bool(value)


 def _normalize_unauthorized_dm_behavior(value: Any, default: str = "pair") -> str:
@@ -64,8 +57,6 @@ class Platform(Enum):
    DINGTALK = "dingtalk"
    API_SERVER = "api_server"
    WEBHOOK = "webhook"
-    FEISHU = "feishu"
-    WECOM = "wecom"


@dataclass
@@ -283,12 +274,6 @@ class GatewayConfig:
            # Webhook uses enabled flag only (secrets are per-route)
            elif platform == Platform.WEBHOOK:
                connected.append(platform)
-            # Feishu uses extra dict for app credentials
-            elif platform == Platform.FEISHU and config.extra.get("app_id"):
-                connected.append(platform)
-            # WeCom uses extra dict for bot credentials
-            elif platform == Platform.WECOM and config.extra.get("bot_id"):
-                connected.append(platform)
        return connected
    
    def get_home_channel(self, platform: Platform) -> Optional[HomeChannel]:
@@ -522,10 +507,6 @@ def load_gateway_config() -> GatewayConfig:
                    )
                if "reply_prefix" in platform_cfg:
                    bridged["reply_prefix"] = platform_cfg["reply_prefix"]
-                if "require_mention" in platform_cfg:
-                    bridged["require_mention"] = platform_cfg["require_mention"]
-                if "mention_patterns" in platform_cfg:
-                    bridged["mention_patterns"] = platform_cfg["mention_patterns"]
                if not bridged:
                    continue
                plat_data = platforms_data.setdefault(plat.value, {})
@@ -550,22 +531,6 @@ def load_gateway_config() -> GatewayConfig:
                    os.environ["DISCORD_FREE_RESPONSE_CHANNELS"] = str(frc)
                if "auto_thread" in discord_cfg and not os.getenv("DISCORD_AUTO_THREAD"):
                    os.environ["DISCORD_AUTO_THREAD"] = str(discord_cfg["auto_thread"]).lower()
-                if "reactions" in discord_cfg and not os.getenv("DISCORD_REACTIONS"):
-                    os.environ["DISCORD_REACTIONS"] = str(discord_cfg["reactions"]).lower()
-
-            # Telegram settings → env vars (env vars take precedence)
-            telegram_cfg = yaml_cfg.get("telegram", {})
-            if isinstance(telegram_cfg, dict):
-                if "require_mention" in telegram_cfg and not os.getenv("TELEGRAM_REQUIRE_MENTION"):
-                    os.environ["TELEGRAM_REQUIRE_MENTION"] = str(telegram_cfg["require_mention"]).lower()
-                if "mention_patterns" in telegram_cfg and not os.getenv("TELEGRAM_MENTION_PATTERNS"):
-                    import json as _json
-                    os.environ["TELEGRAM_MENTION_PATTERNS"] = _json.dumps(telegram_cfg["mention_patterns"])
-                frc = telegram_cfg.get("free_response_chats")
-                if frc is not None and not os.getenv("TELEGRAM_FREE_RESPONSE_CHATS"):
-                    if isinstance(frc, list):
-                        frc = ",".join(str(v) for v in frc)
-                    os.environ["TELEGRAM_FREE_RESPONSE_CHATS"] = str(frc)
    except Exception as e:
        logger.warning(
            "Failed to process config.yaml — falling back to .env / gateway.json values. "
@@ -636,14 +601,6 @@ def _apply_env_overrides(config: GatewayConfig) -> None:
            config.platforms[Platform.TELEGRAM] = PlatformConfig()
        config.platforms[Platform.TELEGRAM].reply_to_mode = telegram_reply_mode
    
-    telegram_fallback_ips = os.getenv("TELEGRAM_FALLBACK_IPS", "")
-    if telegram_fallback_ips:
-        if Platform.TELEGRAM not in config.platforms:
-            config.platforms[Platform.TELEGRAM] = PlatformConfig()
-        config.platforms[Platform.TELEGRAM].extra["fallback_ips"] = [
-            ip.strip() for ip in telegram_fallback_ips.split(",") if ip.strip()
-        ]
-
    telegram_home = os.getenv("TELEGRAM_HOME_CHANNEL")
    if telegram_home and Platform.TELEGRAM in config.platforms:
        config.platforms[Platform.TELEGRAM].home_channel = HomeChannel(
@@ -682,13 +639,14 @@ def _apply_env_overrides(config: GatewayConfig) -> None:
            config.platforms[Platform.SLACK] = PlatformConfig()
        config.platforms[Platform.SLACK].enabled = True
        config.platforms[Platform.SLACK].token = slack_token
-    slack_home = os.getenv("SLACK_HOME_CHANNEL")
-    if slack_home and Platform.SLACK in config.platforms:
-        config.platforms[Platform.SLACK].home_channel = HomeChannel(
-            platform=Platform.SLACK,
-            chat_id=slack_home,
-            name=os.getenv("SLACK_HOME_CHANNEL_NAME", ""),
-        )
+        # Home channel
+        slack_home = os.getenv("SLACK_HOME_CHANNEL")
+        if slack_home:
+            config.platforms[Platform.SLACK].home_channel = HomeChannel(
+                platform=Platform.SLACK,
+                chat_id=slack_home,
+                name=os.getenv("SLACK_HOME_CHANNEL_NAME", ""),
+            )
    
    # Signal
    signal_url = os.getenv("SIGNAL_HTTP_URL")
@@ -702,13 +660,13 @@ def _apply_env_overrides(config: GatewayConfig) -> None:
            "account": signal_account,
            "ignore_stories": os.getenv("SIGNAL_IGNORE_STORIES", "true").lower() in ("true", "1", "yes"),
        })
-    signal_home = os.getenv("SIGNAL_HOME_CHANNEL")
-    if signal_home and Platform.SIGNAL in config.platforms:
-        config.platforms[Platform.SIGNAL].home_channel = HomeChannel(
-            platform=Platform.SIGNAL,
-            chat_id=signal_home,
-            name=os.getenv("SIGNAL_HOME_CHANNEL_NAME", "Home"),
-        )
+        signal_home = os.getenv("SIGNAL_HOME_CHANNEL")
+        if signal_home:
+            config.platforms[Platform.SIGNAL].home_channel = HomeChannel(
+                platform=Platform.SIGNAL,
+                chat_id=signal_home,
+                name=os.getenv("SIGNAL_HOME_CHANNEL_NAME", "Home"),
+            )

    # Mattermost
    mattermost_token = os.getenv("MATTERMOST_TOKEN")
@@ -721,13 +679,13 @@ def _apply_env_overrides(config: GatewayConfig) -> None:
        config.platforms[Platform.MATTERMOST].enabled = True
        config.platforms[Platform.MATTERMOST].token = mattermost_token
        config.platforms[Platform.MATTERMOST].extra["url"] = mattermost_url
-    mattermost_home = os.getenv("MATTERMOST_HOME_CHANNEL")
-    if mattermost_home and Platform.MATTERMOST in config.platforms:
-        config.platforms[Platform.MATTERMOST].home_channel = HomeChannel(
-            platform=Platform.MATTERMOST,
-            chat_id=mattermost_home,
-            name=os.getenv("MATTERMOST_HOME_CHANNEL_NAME", "Home"),
-        )
+        mattermost_home = os.getenv("MATTERMOST_HOME_CHANNEL")
+        if mattermost_home:
+            config.platforms[Platform.MATTERMOST].home_channel = HomeChannel(
+                platform=Platform.MATTERMOST,
+                chat_id=mattermost_home,
+                name=os.getenv("MATTERMOST_HOME_CHANNEL_NAME", "Home"),
+            )

    # Matrix
    matrix_token = os.getenv("MATRIX_ACCESS_TOKEN")
@@ -749,13 +707,13 @@ def _apply_env_overrides(config: GatewayConfig) -> None:
            config.platforms[Platform.MATRIX].extra["password"] = matrix_password
        matrix_e2ee = os.getenv("MATRIX_ENCRYPTION", "").lower() in ("true", "1", "yes")
        config.platforms[Platform.MATRIX].extra["encryption"] = matrix_e2ee
-    matrix_home = os.getenv("MATRIX_HOME_ROOM")
-    if matrix_home and Platform.MATRIX in config.platforms:
-        config.platforms[Platform.MATRIX].home_channel = HomeChannel(
-            platform=Platform.MATRIX,
-            chat_id=matrix_home,
-            name=os.getenv("MATRIX_HOME_ROOM_NAME", "Home"),
-        )
+        matrix_home = os.getenv("MATRIX_HOME_ROOM")
+        if matrix_home:
+            config.platforms[Platform.MATRIX].home_channel = HomeChannel(
+                platform=Platform.MATRIX,
+                chat_id=matrix_home,
+                name=os.getenv("MATRIX_HOME_ROOM_NAME", "Home"),
+            )

    # Home Assistant
    hass_token = os.getenv("HASS_TOKEN")
@@ -782,13 +740,13 @@ def _apply_env_overrides(config: GatewayConfig) -> None:
            "imap_host": email_imap,
            "smtp_host": email_smtp,
        })
-    email_home = os.getenv("EMAIL_HOME_ADDRESS")
-    if email_home and Platform.EMAIL in config.platforms:
-        config.platforms[Platform.EMAIL].home_channel = HomeChannel(
-            platform=Platform.EMAIL,
-            chat_id=email_home,
-            name=os.getenv("EMAIL_HOME_ADDRESS_NAME", "Home"),
-        )
+        email_home = os.getenv("EMAIL_HOME_ADDRESS")
+        if email_home:
+            config.platforms[Platform.EMAIL].home_channel = HomeChannel(
+                platform=Platform.EMAIL,
+                chat_id=email_home,
+                name=os.getenv("EMAIL_HOME_ADDRESS_NAME", "Home"),
+            )

    # SMS (Twilio)
    twilio_sid = os.getenv("TWILIO_ACCOUNT_SID")
@@ -797,13 +755,13 @@ def _apply_env_overrides(config: GatewayConfig) -> None:
            config.platforms[Platform.SMS] = PlatformConfig()
        config.platforms[Platform.SMS].enabled = True
        config.platforms[Platform.SMS].api_key = os.getenv("TWILIO_AUTH_TOKEN", "")
-    sms_home = os.getenv("SMS_HOME_CHANNEL")
-    if sms_home and Platform.SMS in config.platforms:
-        config.platforms[Platform.SMS].home_channel = HomeChannel(
-            platform=Platform.SMS,
-            chat_id=sms_home,
-            name=os.getenv("SMS_HOME_CHANNEL_NAME", "Home"),
-        )
+        sms_home = os.getenv("SMS_HOME_CHANNEL")
+        if sms_home:
+            config.platforms[Platform.SMS].home_channel = HomeChannel(
+                platform=Platform.SMS,
+                chat_id=sms_home,
+                name=os.getenv("SMS_HOME_CHANNEL_NAME", "Home"),
+            )

    # API Server
    api_server_enabled = os.getenv("API_SERVER_ENABLED", "").lower() in ("true", "1", "yes")
@@ -845,55 +803,6 @@ def _apply_env_overrides(config: GatewayConfig) -> None:
        if webhook_secret:
            config.platforms[Platform.WEBHOOK].extra["secret"] = webhook_secret

-    # Feishu / Lark
-    feishu_app_id = os.getenv("FEISHU_APP_ID")
-    feishu_app_secret = os.getenv("FEISHU_APP_SECRET")
-    if feishu_app_id and feishu_app_secret:
-        if Platform.FEISHU not in config.platforms:
-            config.platforms[Platform.FEISHU] = PlatformConfig()
-        config.platforms[Platform.FEISHU].enabled = True
-        config.platforms[Platform.FEISHU].extra.update({
-            "app_id": feishu_app_id,
-            "app_secret": feishu_app_secret,
-            "domain": os.getenv("FEISHU_DOMAIN", "feishu"),
-            "connection_mode": os.getenv("FEISHU_CONNECTION_MODE", "websocket"),
-        })
-        feishu_encrypt_key = os.getenv("FEISHU_ENCRYPT_KEY", "")
-        if feishu_encrypt_key:
-            config.platforms[Platform.FEISHU].extra["encrypt_key"] = feishu_encrypt_key
-        feishu_verification_token = os.getenv("FEISHU_VERIFICATION_TOKEN", "")
-        if feishu_verification_token:
-            config.platforms[Platform.FEISHU].extra["verification_token"] = feishu_verification_token
-        feishu_home = os.getenv("FEISHU_HOME_CHANNEL")
-        if feishu_home:
-            config.platforms[Platform.FEISHU].home_channel = HomeChannel(
-                platform=Platform.FEISHU,
-                chat_id=feishu_home,
-                name=os.getenv("FEISHU_HOME_CHANNEL_NAME", "Home"),
-            )
-
-    # WeCom (Enterprise WeChat)
-    wecom_bot_id = os.getenv("WECOM_BOT_ID")
-    wecom_secret = os.getenv("WECOM_SECRET")
-    if wecom_bot_id and wecom_secret:
-        if Platform.WECOM not in config.platforms:
-            config.platforms[Platform.WECOM] = PlatformConfig()
-        config.platforms[Platform.WECOM].enabled = True
-        config.platforms[Platform.WECOM].extra.update({
-            "bot_id": wecom_bot_id,
-            "secret": wecom_secret,
-        })
-        wecom_ws_url = os.getenv("WECOM_WEBSOCKET_URL", "")
-        if wecom_ws_url:
-            config.platforms[Platform.WECOM].extra["websocket_url"] = wecom_ws_url
-        wecom_home = os.getenv("WECOM_HOME_CHANNEL")
-        if wecom_home:
-            config.platforms[Platform.WECOM].home_channel = HomeChannel(
-                platform=Platform.WECOM,
-                chat_id=wecom_home,
-                name=os.getenv("WECOM_HOME_CHANNEL_NAME", "Home"),
-            )
-
    # Session settings
    idle_minutes = os.getenv("SESSION_IDLE_MINUTES")
    if idle_minutes:
@@ -70,15 +70,12 @@ class DeliveryTarget:
        if target == "local":
            return cls(platform=Platform.LOCAL)
        
-        # Check for platform:chat_id or platform:chat_id:thread_id format
+        # Check for platform:chat_id format
        if ":" in target:
-            parts = target.split(":", 2)
-            platform_str = parts[0]
-            chat_id = parts[1] if len(parts) > 1 else None
-            thread_id = parts[2] if len(parts) > 2 else None
+            platform_str, chat_id = target.split(":", 1)
            try:
                platform = Platform(platform_str)
-                return cls(platform=platform, chat_id=chat_id, thread_id=thread_id, is_explicit=True)
+                return cls(platform=platform, chat_id=chat_id, is_explicit=True)
            except ValueError:
                # Unknown platform, treat as local
                return cls(platform=Platform.LOCAL)
@@ -97,8 +94,6 @@ class DeliveryTarget:
            return "origin"
        if self.platform == Platform.LOCAL:
            return "local"
-        if self.chat_id and self.thread_id:
-            return f"{self.platform.value}:{self.chat_id}:{self.thread_id}"
        if self.chat_id:
            return f"{self.platform.value}:{self.chat_id}"
        return self.platform.value
@@ -51,33 +51,14 @@ class HookRegistry:
        """Return metadata about all loaded hooks."""
        return list(self._loaded_hooks)

-    def _register_builtin_hooks(self) -> None:
-        """Register built-in hooks that are always active."""
-        try:
-            from gateway.builtin_hooks.boot_md import handle as boot_md_handle
-
-            self._handlers.setdefault("gateway:startup", []).append(boot_md_handle)
-            self._loaded_hooks.append({
-                "name": "boot-md",
-                "description": "Run ~/.hermes/BOOT.md on gateway startup",
-                "events": ["gateway:startup"],
-                "path": "(builtin)",
-            })
-        except Exception as e:
-            print(f"[hooks] Could not load built-in boot-md hook: {e}", flush=True)
-
    def discover_and_load(self) -> None:
        """
        Scan the hooks directory for hook directories and load their handlers.

-        Also registers built-in hooks that are always active.
-
        Each hook directory must contain:
          - HOOK.yaml with at least 'name' and 'events' keys
          - handler.py with a top-level 'handle' function (sync or async)
        """
-        self._register_builtin_hooks()
-
        if not HOOKS_DIR.exists():
            return

@@ -25,7 +25,7 @@ import time
 from pathlib import Path
 from typing import Optional

-from hermes_constants import get_hermes_dir
+from hermes_cli.config import get_hermes_home


 # Unambiguous alphabet -- excludes 0/O, 1/I to prevent confusion
@@ -41,7 +41,7 @@ LOCKOUT_SECONDS = 3600              # Lockout duration after too many failures
 MAX_PENDING_PER_PLATFORM = 3        # Max pending codes per platform
 MAX_FAILED_ATTEMPTS = 5             # Failed approvals before lockout

-PAIRING_DIR = get_hermes_dir("platforms/pairing", "pairing")
+PAIRING_DIR = get_hermes_home() / "pairing"


 def _secure_write(path: Path, data: str) -> None:
@@ -166,7 +166,7 @@ class ResponseStore:

 _CORS_HEADERS = {
    "Access-Control-Allow-Methods": "GET, POST, DELETE, OPTIONS",
-    "Access-Control-Allow-Headers": "Authorization, Content-Type, Idempotency-Key",
+    "Access-Control-Allow-Headers": "Authorization, Content-Type",
 }


@@ -223,23 +223,6 @@ if AIOHTTP_AVAILABLE:
 else:
    body_limit_middleware = None  # type: ignore[assignment]

-_SECURITY_HEADERS = {
-    "X-Content-Type-Options": "nosniff",
-    "Referrer-Policy": "no-referrer",
-}
-
-
-if AIOHTTP_AVAILABLE:
-    @web.middleware
-    async def security_headers_middleware(request, handler):
-        """Add security headers to all responses (including errors)."""
-        response = await handler(request)
-        for k, v in _SECURITY_HEADERS.items():
-            response.headers.setdefault(k, v)
-        return response
-else:
-    security_headers_middleware = None  # type: ignore[assignment]
-

 class _IdempotencyCache:
    """In-memory idempotency cache with TTL and basic LRU semantics."""
@@ -324,7 +307,6 @@ class APIServerAdapter(BasePlatformAdapter):
        if "*" in self._cors_origins:
            headers = dict(_CORS_HEADERS)
            headers["Access-Control-Allow-Origin"] = "*"
-            headers["Access-Control-Max-Age"] = "600"
            return headers

        if origin not in self._cors_origins:
@@ -333,7 +315,6 @@ class APIServerAdapter(BasePlatformAdapter):
        headers = dict(_CORS_HEADERS)
        headers["Access-Control-Allow-Origin"] = origin
        headers["Vary"] = "Origin"
-        headers["Access-Control-Max-Age"] = "600"
        return headers

    def _origin_allowed(self, origin: str) -> bool:
@@ -380,26 +361,19 @@ class APIServerAdapter(BasePlatformAdapter):
        ephemeral_system_prompt: Optional[str] = None,
        session_id: Optional[str] = None,
        stream_delta_callback=None,
-        tool_progress_callback=None,
    ) -> Any:
        """
        Create an AIAgent instance using the gateway's runtime config.

        Uses _resolve_runtime_agent_kwargs() to pick up model, api_key,
-        base_url, etc. from config.yaml / env vars.  Toolsets are resolved
-        from config.yaml platform_toolsets.api_server (same as all other
-        gateway platforms), falling back to the hermes-api-server default.
+        base_url, etc. from config.yaml / env vars.
        """
        from run_agent import AIAgent
-        from gateway.run import _resolve_runtime_agent_kwargs, _resolve_gateway_model, _load_gateway_config
-        from hermes_cli.tools_config import _get_platform_tools
+        from gateway.run import _resolve_runtime_agent_kwargs, _resolve_gateway_model

        runtime_kwargs = _resolve_runtime_agent_kwargs()
        model = _resolve_gateway_model()

-        user_config = _load_gateway_config()
-        enabled_toolsets = sorted(_get_platform_tools(user_config, "api_server"))
-
        max_iterations = int(os.getenv("HERMES_MAX_ITERATIONS", "90"))

        agent = AIAgent(
@@ -409,11 +383,10 @@ class APIServerAdapter(BasePlatformAdapter):
            quiet_mode=True,
            verbose_logging=False,
            ephemeral_system_prompt=ephemeral_system_prompt or None,
-            enabled_toolsets=enabled_toolsets,
+            enabled_toolsets=["hermes-api-server"],
            session_id=session_id,
            platform="api_server",
            stream_delta_callback=stream_delta_callback,
-            tool_progress_callback=tool_progress_callback,
        )
        return agent

@@ -516,31 +489,17 @@ class APIServerAdapter(BasePlatformAdapter):
                if delta is not None:
                    _stream_q.put(delta)

-            def _on_tool_progress(name, preview, args):
-                """Inject tool progress into the SSE stream for Open WebUI."""
-                if name.startswith("_"):
-                    return  # Skip internal events (_thinking)
-                from agent.display import get_tool_emoji
-                emoji = get_tool_emoji(name)
-                label = preview or name
-                _stream_q.put(f"\n`{emoji} {label}`\n")
-
-            # Start agent in background.  agent_ref is a mutable container
-            # so the SSE writer can interrupt the agent on client disconnect.
-            agent_ref = [None]
+            # Start agent in background
            agent_task = asyncio.ensure_future(self._run_agent(
                user_message=user_message,
                conversation_history=history,
                ephemeral_system_prompt=system_prompt,
                session_id=session_id,
                stream_delta_callback=_on_delta,
-                tool_progress_callback=_on_tool_progress,
-                agent_ref=agent_ref,
            ))

            return await self._write_sse_chat_completion(
-                request, completion_id, model_name, created, _stream_q,
-                agent_task, agent_ref,
+                request, completion_id, model_name, created, _stream_q, agent_task
            )

        # Non-streaming: run the agent (with optional Idempotency-Key)
@@ -603,107 +562,80 @@ class APIServerAdapter(BasePlatformAdapter):

    async def _write_sse_chat_completion(
        self, request: "web.Request", completion_id: str, model: str,
-        created: int, stream_q, agent_task, agent_ref=None,
+        created: int, stream_q, agent_task,
    ) -> "web.StreamResponse":
-        """Write real streaming SSE from agent's stream_delta_callback queue.
-
-        If the client disconnects mid-stream (network drop, browser tab close),
-        the agent is interrupted via ``agent.interrupt()`` so it stops making
-        LLM API calls, and the asyncio task wrapper is cancelled.
-        """
+        """Write real streaming SSE from agent's stream_delta_callback queue."""
        import queue as _q

-        sse_headers = {"Content-Type": "text/event-stream", "Cache-Control": "no-cache"}
-        # CORS middleware can't inject headers into StreamResponse after
-        # prepare() flushes them, so resolve CORS headers up front.
-        origin = request.headers.get("Origin", "")
-        cors = self._cors_headers_for_origin(origin) if origin else None
-        if cors:
-            sse_headers.update(cors)
-        response = web.StreamResponse(status=200, headers=sse_headers)
+        response = web.StreamResponse(
+            status=200,
+            headers={"Content-Type": "text/event-stream", "Cache-Control": "no-cache"},
+        )
        await response.prepare(request)

-        try:
-            # Role chunk
-            role_chunk = {
-                "id": completion_id, "object": "chat.completion.chunk",
-                "created": created, "model": model,
-                "choices": [{"index": 0, "delta": {"role": "assistant"}, "finish_reason": None}],
-            }
-            await response.write(f"data: {json.dumps(role_chunk)}\n\n".encode())
+        # Role chunk
+        role_chunk = {
+            "id": completion_id, "object": "chat.completion.chunk",
+            "created": created, "model": model,
+            "choices": [{"index": 0, "delta": {"role": "assistant"}, "finish_reason": None}],
+        }
+        await response.write(f"data: {json.dumps(role_chunk)}\n\n".encode())

-            # Stream content chunks as they arrive from the agent
-            loop = asyncio.get_event_loop()
-            while True:
-                try:
-                    delta = await loop.run_in_executor(None, lambda: stream_q.get(timeout=0.5))
-                except _q.Empty:
-                    if agent_task.done():
-                        # Drain any remaining items
-                        while True:
-                            try:
-                                delta = stream_q.get_nowait()
-                                if delta is None:
-                                    break
-                                content_chunk = {
-                                    "id": completion_id, "object": "chat.completion.chunk",
-                                    "created": created, "model": model,
-                                    "choices": [{"index": 0, "delta": {"content": delta}, "finish_reason": None}],
-                                }
-                                await response.write(f"data: {json.dumps(content_chunk)}\n\n".encode())
-                            except _q.Empty:
-                                break
-                        break
-                    continue
-
-                if delta is None:  # End of stream sentinel
-                    break
-
-                content_chunk = {
-                    "id": completion_id, "object": "chat.completion.chunk",
-                    "created": created, "model": model,
-                    "choices": [{"index": 0, "delta": {"content": delta}, "finish_reason": None}],
-                }
-                await response.write(f"data: {json.dumps(content_chunk)}\n\n".encode())
-
-            # Get usage from completed agent
-            usage = {"input_tokens": 0, "output_tokens": 0, "total_tokens": 0}
+        # Stream content chunks as they arrive from the agent
+        loop = asyncio.get_event_loop()
+        while True:
            try:
-                result, agent_usage = await agent_task
-                usage = agent_usage or usage
-            except Exception:
-                pass
+                delta = await loop.run_in_executor(None, lambda: stream_q.get(timeout=0.5))
+            except _q.Empty:
+                if agent_task.done():
+                    # Drain any remaining items
+                    while True:
+                        try:
+                            delta = stream_q.get_nowait()
+                            if delta is None:
+                                break
+                            content_chunk = {
+                                "id": completion_id, "object": "chat.completion.chunk",
+                                "created": created, "model": model,
+                                "choices": [{"index": 0, "delta": {"content": delta}, "finish_reason": None}],
+                            }
+                            await response.write(f"data: {json.dumps(content_chunk)}\n\n".encode())
+                        except _q.Empty:
+                            break
+                    break
+                continue

-            # Finish chunk
-            finish_chunk = {
+            if delta is None:  # End of stream sentinel
+                break
+
+            content_chunk = {
                "id": completion_id, "object": "chat.completion.chunk",
                "created": created, "model": model,
-                "choices": [{"index": 0, "delta": {}, "finish_reason": "stop"}],
-                "usage": {
-                    "prompt_tokens": usage.get("input_tokens", 0),
-                    "completion_tokens": usage.get("output_tokens", 0),
-                    "total_tokens": usage.get("total_tokens", 0),
-                },
+                "choices": [{"index": 0, "delta": {"content": delta}, "finish_reason": None}],
            }
-            await response.write(f"data: {json.dumps(finish_chunk)}\n\n".encode())
-            await response.write(b"data: [DONE]\n\n")
-        except (ConnectionResetError, ConnectionAbortedError, BrokenPipeError, OSError):
-            # Client disconnected mid-stream.  Interrupt the agent so it
-            # stops making LLM API calls at the next loop iteration, then
-            # cancel the asyncio task wrapper.
-            agent = agent_ref[0] if agent_ref else None
-            if agent is not None:
-                try:
-                    agent.interrupt("SSE client disconnected")
-                except Exception:
-                    pass
-            if not agent_task.done():
-                agent_task.cancel()
-                try:
-                    await agent_task
-                except (asyncio.CancelledError, Exception):
-                    pass
-            logger.info("SSE client disconnected; interrupted agent task %s", completion_id)
+            await response.write(f"data: {json.dumps(content_chunk)}\n\n".encode())
+
+        # Get usage from completed agent
+        usage = {"input_tokens": 0, "output_tokens": 0, "total_tokens": 0}
+        try:
+            result, agent_usage = await agent_task
+            usage = agent_usage or usage
+        except Exception:
+            pass
+
+        # Finish chunk
+        finish_chunk = {
+            "id": completion_id, "object": "chat.completion.chunk",
+            "created": created, "model": model,
+            "choices": [{"index": 0, "delta": {}, "finish_reason": "stop"}],
+            "usage": {
+                "prompt_tokens": usage.get("input_tokens", 0),
+                "completion_tokens": usage.get("output_tokens", 0),
+                "total_tokens": usage.get("total_tokens", 0),
+            },
+        }
+        await response.write(f"data: {json.dumps(finish_chunk)}\n\n".encode())
+        await response.write(b"data: [DONE]\n\n")

        return response

@@ -1206,19 +1138,12 @@ class APIServerAdapter(BasePlatformAdapter):
        ephemeral_system_prompt: Optional[str] = None,
        session_id: Optional[str] = None,
        stream_delta_callback=None,
-        tool_progress_callback=None,
-        agent_ref: Optional[list] = None,
    ) -> tuple:
        """
        Create an agent and run a conversation in a thread executor.

        Returns ``(result_dict, usage_dict)`` where *usage_dict* contains
        ``input_tokens``, ``output_tokens`` and ``total_tokens``.
-
-        If *agent_ref* is a one-element list, the AIAgent instance is stored
-        at ``agent_ref[0]`` before ``run_conversation`` begins.  This allows
-        callers (e.g. the SSE writer) to call ``agent.interrupt()`` from
-        another thread to stop in-progress LLM calls.
        """
        loop = asyncio.get_event_loop()

@@ -1227,10 +1152,7 @@ class APIServerAdapter(BasePlatformAdapter):
                ephemeral_system_prompt=ephemeral_system_prompt,
                session_id=session_id,
                stream_delta_callback=stream_delta_callback,
-                tool_progress_callback=tool_progress_callback,
            )
-            if agent_ref is not None:
-                agent_ref[0] = agent
            result = agent.run_conversation(
                user_message=user_message,
                conversation_history=conversation_history,
@@ -1255,11 +1177,10 @@ class APIServerAdapter(BasePlatformAdapter):
            return False

        try:
-            mws = [mw for mw in (cors_middleware, body_limit_middleware, security_headers_middleware) if mw is not None]
+            mws = [mw for mw in (cors_middleware, body_limit_middleware) if mw is not None]
            self._app = web.Application(middlewares=mws)
            self._app["api_server_adapter"] = self
            self._app.router.add_get("/health", self._handle_health)
-            self._app.router.add_get("/v1/health", self._handle_health)
            self._app.router.add_get("/v1/models", self._handle_models)
            self._app.router.add_post("/v1/chat/completions", self._handle_chat_completions)
            self._app.router.add_post("/v1/responses", self._handle_responses)
@@ -1275,17 +1196,6 @@ class APIServerAdapter(BasePlatformAdapter):
            self._app.router.add_post("/api/jobs/{job_id}/resume", self._handle_resume_job)
            self._app.router.add_post("/api/jobs/{job_id}/run", self._handle_run_job)

-            # Port conflict detection — fail fast if port is already in use
-            import socket as _socket
-            try:
-                with _socket.socket(_socket.AF_INET, _socket.SOCK_STREAM) as _s:
-                    _s.settimeout(1)
-                    _s.connect(('127.0.0.1', self._port))
-                logger.error('[%s] Port %d already in use. Set a different port in config.yaml: platforms.api_server.port', self.name, self._port)
-                return False
-            except (ConnectionRefusedError, OSError):
-                pass  # port is free
-
            self._runner = web.AppRunner(self._app)
            await self._runner.setup()
            self._site = web.TCPSite(self._runner, self._host, self._port)
@@ -8,7 +8,6 @@ and implement the required methods.
 import asyncio
 import logging
 import os
-import random
 import re
 import uuid
 from abc import ABC, abstractmethod
@@ -27,7 +26,6 @@ sys.path.insert(0, str(_Path(__file__).resolve().parents[2]))
 from gateway.config import Platform, PlatformConfig
 from gateway.session import SessionSource, build_session_key
 from hermes_cli.config import get_hermes_home
-from hermes_constants import get_hermes_dir


 GATEWAY_SECRET_CAPTURE_UNSUPPORTED_MESSAGE = (
@@ -45,8 +43,8 @@ GATEWAY_SECRET_CAPTURE_UNSUPPORTED_MESSAGE = (
 # (e.g. Telegram file URLs expire after ~1 hour).
 # ---------------------------------------------------------------------------

-# Default location: {HERMES_HOME}/cache/images/ (legacy: image_cache/)
-IMAGE_CACHE_DIR = get_hermes_dir("cache/images", "image_cache")
+# Default location: {HERMES_HOME}/image_cache/
+IMAGE_CACHE_DIR = get_hermes_home() / "image_cache"


 def get_image_cache_dir() -> Path:
@@ -73,51 +71,31 @@ def cache_image_from_bytes(data: bytes, ext: str = ".jpg") -> str:
    return str(filepath)


-async def cache_image_from_url(url: str, ext: str = ".jpg", retries: int = 2) -> str:
+async def cache_image_from_url(url: str, ext: str = ".jpg") -> str:
    """
    Download an image from a URL and save it to the local cache.

-    Retries on transient failures (timeouts, 429, 5xx) with exponential
-    backoff so a single slow CDN response doesn't lose the media.
+    Uses httpx for async download with a reasonable timeout.

    Args:
        url: The HTTP/HTTPS URL to download from.
        ext: File extension including the dot (e.g. ".jpg", ".png").
-        retries: Number of retry attempts on transient failures.

    Returns:
        Absolute path to the cached image file as a string.
    """
-    import asyncio
    import httpx
-    import logging as _logging
-    _log = _logging.getLogger(__name__)

-    last_exc = None
    async with httpx.AsyncClient(timeout=30.0, follow_redirects=True) as client:
-        for attempt in range(retries + 1):
-            try:
-                response = await client.get(
-                    url,
-                    headers={
-                        "User-Agent": "Mozilla/5.0 (compatible; HermesAgent/1.0)",
-                        "Accept": "image/*,*/*;q=0.8",
-                    },
-                )
-                response.raise_for_status()
-                return cache_image_from_bytes(response.content, ext)
-            except (httpx.TimeoutException, httpx.HTTPStatusError) as exc:
-                last_exc = exc
-                if isinstance(exc, httpx.HTTPStatusError) and exc.response.status_code < 429:
-                    raise
-                if attempt < retries:
-                    wait = 1.5 * (attempt + 1)
-                    _log.debug("Media cache retry %d/%d for %s (%.1fs): %s",
-                               attempt + 1, retries, url[:80], wait, exc)
-                    await asyncio.sleep(wait)
-                    continue
-                raise
-    raise last_exc
+        response = await client.get(
+            url,
+            headers={
+                "User-Agent": "Mozilla/5.0 (compatible; HermesAgent/1.0)",
+                "Accept": "image/*,*/*;q=0.8",
+            },
+        )
+        response.raise_for_status()
+        return cache_image_from_bytes(response.content, ext)


 def cleanup_image_cache(max_age_hours: int = 24) -> int:
@@ -148,7 +126,7 @@ def cleanup_image_cache(max_age_hours: int = 24) -> int:
 # here so the STT tool (OpenAI Whisper) can transcribe them from local files.
 # ---------------------------------------------------------------------------

-AUDIO_CACHE_DIR = get_hermes_dir("cache/audio", "audio_cache")
+AUDIO_CACHE_DIR = get_hermes_home() / "audio_cache"


 def get_audio_cache_dir() -> Path:
@@ -175,51 +153,29 @@ def cache_audio_from_bytes(data: bytes, ext: str = ".ogg") -> str:
    return str(filepath)


-async def cache_audio_from_url(url: str, ext: str = ".ogg", retries: int = 2) -> str:
+async def cache_audio_from_url(url: str, ext: str = ".ogg") -> str:
    """
    Download an audio file from a URL and save it to the local cache.

-    Retries on transient failures (timeouts, 429, 5xx) with exponential
-    backoff so a single slow CDN response doesn't lose the media.
-
    Args:
        url: The HTTP/HTTPS URL to download from.
        ext: File extension including the dot (e.g. ".ogg", ".mp3").
-        retries: Number of retry attempts on transient failures.

    Returns:
        Absolute path to the cached audio file as a string.
    """
-    import asyncio
    import httpx
-    import logging as _logging
-    _log = _logging.getLogger(__name__)

-    last_exc = None
    async with httpx.AsyncClient(timeout=30.0, follow_redirects=True) as client:
-        for attempt in range(retries + 1):
-            try:
-                response = await client.get(
-                    url,
-                    headers={
-                        "User-Agent": "Mozilla/5.0 (compatible; HermesAgent/1.0)",
-                        "Accept": "audio/*,*/*;q=0.8",
-                    },
-                )
-                response.raise_for_status()
-                return cache_audio_from_bytes(response.content, ext)
-            except (httpx.TimeoutException, httpx.HTTPStatusError) as exc:
-                last_exc = exc
-                if isinstance(exc, httpx.HTTPStatusError) and exc.response.status_code < 429:
-                    raise
-                if attempt < retries:
-                    wait = 1.5 * (attempt + 1)
-                    _log.debug("Audio cache retry %d/%d for %s (%.1fs): %s",
-                               attempt + 1, retries, url[:80], wait, exc)
-                    await asyncio.sleep(wait)
-                    continue
-                raise
-    raise last_exc
+        response = await client.get(
+            url,
+            headers={
+                "User-Agent": "Mozilla/5.0 (compatible; HermesAgent/1.0)",
+                "Accept": "audio/*,*/*;q=0.8",
+            },
+        )
+        response.raise_for_status()
+        return cache_audio_from_bytes(response.content, ext)


 # ---------------------------------------------------------------------------
@@ -229,7 +185,7 @@ async def cache_audio_from_url(url: str, ext: str = ".ogg", retries: int = 2) ->
 # here so the agent can reference them by local file path.
 # ---------------------------------------------------------------------------

-DOCUMENT_CACHE_DIR = get_hermes_dir("cache/documents", "document_cache")
+DOCUMENT_CACHE_DIR = get_hermes_home() / "document_cache"

 SUPPORTED_DOCUMENT_TYPES = {
    ".pdf": "application/pdf",
@@ -356,10 +312,7 @@ class MessageEvent:
            return None
        # Split on space and get first word, strip the /
        parts = self.text.split(maxsplit=1)
-        raw = parts[0][1:].lower() if parts else None
-        if raw and "@" in raw:
-            raw = raw.split("@", 1)[0]
-        return raw
+        return parts[0][1:].lower() if parts else None
    
    def get_command_args(self) -> str:
        """Get the arguments after a command."""
@@ -376,24 +329,6 @@ class SendResult:
    message_id: Optional[str] = None
    error: Optional[str] = None
    raw_response: Any = None
-    retryable: bool = False  # True for transient errors (network, timeout) — base will retry automatically
-
-
-# Error substrings that indicate a transient network failure worth retrying
-_RETRYABLE_ERROR_PATTERNS = (
-    "connecterror",
-    "connectionerror",
-    "connectionreset",
-    "connectionrefused",
-    "timeout",
-    "timed out",
-    "network",
-    "broken pipe",
-    "remotedisconnected",
-    "eoferror",
-    "readtimeout",
-    "writetimeout",
-)


 # Type for message handlers
@@ -898,111 +833,6 @@ class BasePlatformAdapter(ABC):
                except Exception:
                    pass
    
-    # ── Processing lifecycle hooks ──────────────────────────────────────────
-    # Subclasses override these to react to message processing events
-    # (e.g. Discord adds 👀/✅/❌ reactions).
-
-    async def on_processing_start(self, event: MessageEvent) -> None:
-        """Hook called when background processing begins."""
-
-    async def on_processing_complete(self, event: MessageEvent, success: bool) -> None:
-        """Hook called when background processing completes."""
-
-    async def _run_processing_hook(self, hook_name: str, *args: Any, **kwargs: Any) -> None:
-        """Run a lifecycle hook without letting failures break message flow."""
-        hook = getattr(self, hook_name, None)
-        if not callable(hook):
-            return
-        try:
-            await hook(*args, **kwargs)
-        except Exception as e:
-            logger.warning("[%s] %s hook failed: %s", self.name, hook_name, e)
-
-    @staticmethod
-    def _is_retryable_error(error: Optional[str]) -> bool:
-        """Return True if the error string looks like a transient network failure."""
-        if not error:
-            return False
-        lowered = error.lower()
-        return any(pat in lowered for pat in _RETRYABLE_ERROR_PATTERNS)
-
-    async def _send_with_retry(
-        self,
-        chat_id: str,
-        content: str,
-        reply_to: Optional[str] = None,
-        metadata: Any = None,
-        max_retries: int = 2,
-        base_delay: float = 2.0,
-    ) -> "SendResult":
-        """
-        Send a message with automatic retry for transient network errors.
-
-        On permanent failures (e.g. formatting / permission errors) falls back
-        to a plain-text version before giving up. If all attempts fail due to
-        network errors, sends the user a brief delivery-failure notice so they
-        know to retry rather than waiting indefinitely.
-        """
-
-        result = await self.send(
-            chat_id=chat_id,
-            content=content,
-            reply_to=reply_to,
-            metadata=metadata,
-        )
-
-        if result.success:
-            return result
-
-        error_str = result.error or ""
-        is_network = result.retryable or self._is_retryable_error(error_str)
-
-        if is_network:
-            # Retry with exponential backoff for transient errors
-            for attempt in range(1, max_retries + 1):
-                delay = base_delay * (2 ** (attempt - 1)) + random.uniform(0, 1)
-                logger.warning(
-                    "[%s] Send failed (attempt %d/%d, retrying in %.1fs): %s",
-                    self.name, attempt, max_retries, delay, error_str,
-                )
-                await asyncio.sleep(delay)
-                result = await self.send(
-                    chat_id=chat_id,
-                    content=content,
-                    reply_to=reply_to,
-                    metadata=metadata,
-                )
-                if result.success:
-                    logger.info("[%s] Send succeeded on retry %d", self.name, attempt)
-                    return result
-                error_str = result.error or ""
-                if not (result.retryable or self._is_retryable_error(error_str)):
-                    break  # error switched to non-transient — fall through to plain-text fallback
-            else:
-                # All retries exhausted (loop completed without break) — notify user
-                logger.error("[%s] Failed to deliver response after %d retries: %s", self.name, max_retries, error_str)
-                notice = (
-                    "\u26a0\ufe0f Message delivery failed after multiple attempts. "
-                    "Please try again \u2014 your request was processed but the response could not be sent."
-                )
-                try:
-                    await self.send(chat_id=chat_id, content=notice, reply_to=reply_to, metadata=metadata)
-                except Exception as notify_err:
-                    logger.debug("[%s] Could not send delivery-failure notice: %s", self.name, notify_err)
-                return result
-
-        # Non-network / post-retry formatting failure: try plain text as fallback
-        logger.warning("[%s] Send failed: %s — trying plain-text fallback", self.name, error_str)
-        fallback_result = await self.send(
-            chat_id=chat_id,
-            content=f"(Response formatting failed, plain text:)\n\n{content[:3500]}",
-            reply_to=reply_to,
-            metadata=metadata,
-        )
-        if not fallback_result.success:
-            logger.error("[%s] Fallback send also failed: %s", self.name, fallback_result.error)
-        return fallback_result
-
    async def handle_message(self, event: MessageEvent) -> None:
        """
        Process an incoming message.
@@ -1025,7 +855,7 @@ class BasePlatformAdapter(ABC):
            # simultaneous messages. Queue them without interrupting the active run,
            # then process them immediately after the current task finishes.
            if event.message_type == MessageType.PHOTO:
-                logger.debug("[%s] Queuing photo follow-up for session %s without interrupt", self.name, session_key)
+                print(f"[{self.name}] 🖼️ Queuing photo follow-up for session {session_key} without interrupt")
                existing = self._pending_messages.get(session_key)
                if existing and existing.message_type == MessageType.PHOTO:
                    existing.media_urls.extend(event.media_urls)
@@ -1040,7 +870,7 @@ class BasePlatformAdapter(ABC):
                return  # Don't interrupt now - will run after current task completes

            # Default behavior for non-photo follow-ups: interrupt the running agent
-            logger.debug("[%s] New message while session %s is active — triggering interrupt", self.name, session_key)
+            print(f"[{self.name}] ⚡ New message while session {session_key} is active - triggering interrupt")
            self._pending_messages[session_key] = event
            # Signal the interrupt (the processing task checks this)
            self._active_sessions[session_key].set()
@@ -1080,18 +910,6 @@ class BasePlatformAdapter(ABC):

    async def _process_message_background(self, event: MessageEvent, session_key: str) -> None:
        """Background task that actually processes the message."""
-        # Track delivery outcomes for the processing-complete hook
-        delivery_attempted = False
-        delivery_succeeded = False
-
-        def _record_delivery(result):
-            nonlocal delivery_attempted, delivery_succeeded
-            if result is None:
-                return
-            delivery_attempted = True
-            if getattr(result, "success", False):
-                delivery_succeeded = True
-
        # Create interrupt event for this session
        interrupt_event = asyncio.Event()
        self._active_sessions[session_key] = interrupt_event
@@ -1101,8 +919,6 @@ class BasePlatformAdapter(ABC):
        typing_task = asyncio.create_task(self._keep_typing(event.source.chat_id, metadata=_thread_metadata))
        
        try:
-            await self._run_processing_hook("on_processing_start", event)
-
            # Call the handler (this can take a while with tool calls)
            response = await self._message_handler(event)
            
@@ -1166,13 +982,25 @@ class BasePlatformAdapter(ABC):
                # Send the text portion
                if text_content:
                    logger.info("[%s] Sending response (%d chars) to %s", self.name, len(text_content), event.source.chat_id)
-                    result = await self._send_with_retry(
+                    result = await self.send(
                        chat_id=event.source.chat_id,
                        content=text_content,
                        reply_to=event.message_id,
                        metadata=_thread_metadata,
                    )
-                    _record_delivery(result)
+
+                    # Log send failures (don't raise - user already saw tool progress)
+                    if not result.success:
+                        print(f"[{self.name}] Failed to send response: {result.error}")
+                        # Try sending without markdown as fallback
+                        fallback_result = await self.send(
+                            chat_id=event.source.chat_id,
+                            content=f"(Response formatting failed, plain text:)\n\n{text_content[:3500]}",
+                            reply_to=event.message_id,
+                            metadata=_thread_metadata,
+                        )
+                        if not fallback_result.success:
+                            print(f"[{self.name}] Fallback send also failed: {fallback_result.error}")

                # Human-like pacing delay between text and media
                human_delay = self._get_human_delay()
@@ -1241,9 +1069,9 @@ class BasePlatformAdapter(ABC):
                            )

                        if not media_result.success:
-                            logger.warning("[%s] Failed to send media (%s): %s", self.name, ext, media_result.error)
+                            print(f"[{self.name}] Failed to send media ({ext}): {media_result.error}")
                    except Exception as media_err:
-                        logger.warning("[%s] Error sending media: %s", self.name, media_err)
+                        print(f"[{self.name}] Error sending media: {media_err}")

                # Send auto-detected local files as native attachments
                for file_path in local_files:
@@ -1272,14 +1100,10 @@ class BasePlatformAdapter(ABC):
                    except Exception as file_err:
                        logger.error("[%s] Error sending local file %s: %s", self.name, file_path, file_err)

-            # Determine overall success for the processing hook
-            processing_ok = delivery_succeeded if delivery_attempted else not bool(response)
-            await self._run_processing_hook("on_processing_complete", event, processing_ok)
-
            # Check if there's a pending message that was queued during our processing
            if session_key in self._pending_messages:
                pending_event = self._pending_messages.pop(session_key)
-                logger.debug("[%s] Processing queued message from interrupt", self.name)
+                print(f"[{self.name}] 📨 Processing queued message from interrupt")
                # Clean up current session before processing pending
                if session_key in self._active_sessions:
                    del self._active_sessions[session_key]
@@ -1292,12 +1116,10 @@ class BasePlatformAdapter(ABC):
                await self._process_message_background(pending_event, session_key)
                return  # Already cleaned up
                
-        except asyncio.CancelledError:
-            await self._run_processing_hook("on_processing_complete", event, False)
-            raise
        except Exception as e:
-            await self._run_processing_hook("on_processing_complete", event, False)
-            logger.error("[%s] Error handling message: %s", self.name, e, exc_info=True)
+            print(f"[{self.name}] Error handling message: {e}")
+            import traceback
+            traceback.print_exc()
            # Send the error to the user so they aren't left with radio silence
            try:
                error_type = type(e).__name__
@@ -408,7 +408,7 @@ class VoiceReceiver:
 class DiscordAdapter(BasePlatformAdapter):
    """
    Discord bot adapter.
-
+    
    Handles:
    - Receiving messages from servers and DMs
    - Sending responses with Discord markdown
@@ -418,10 +418,10 @@ class DiscordAdapter(BasePlatformAdapter):
    - Auto-threading for long conversations
    - Reaction-based feedback
    """
-
+    
    # Discord message limits
    MAX_MESSAGE_LENGTH = 2000
-
+    
    # Auto-disconnect from voice channel after this many seconds of inactivity
    VOICE_TIMEOUT = 300

@@ -449,7 +449,7 @@ class DiscordAdapter(BasePlatformAdapter):
        self._bot_task: Optional[asyncio.Task] = None
        # Cap to prevent unbounded growth (Discord threads get archived).
        self._MAX_TRACKED_THREADS = 500
-
+    
    async def connect(self) -> bool:
        """Connect to Discord and start receiving events."""
        if not DISCORD_AVAILABLE:
@@ -480,23 +480,12 @@ class DiscordAdapter(BasePlatformAdapter):
                    logger.warning("Opus codec found at %s but failed to load", opus_path)
            if not discord.opus.is_loaded():
                logger.warning("Opus codec not found — voice channel playback disabled")
-
+        
        if not self.config.token:
            logger.error("[%s] No bot token configured", self.name)
            return False
-
+        
        try:
-            # Acquire scoped lock to prevent duplicate bot token usage
-            from gateway.status import acquire_scoped_lock
-            self._token_lock_identity = self.config.token
-            acquired, existing = acquire_scoped_lock('discord-bot-token', self._token_lock_identity, metadata={'platform': 'discord'})
-            if not acquired:
-                owner_pid = existing.get('pid') if isinstance(existing, dict) else None
-                message = f'Discord bot token already in use' + (f' (PID {owner_pid})' if owner_pid else '') + '. Stop the other gateway first.'
-                logger.error('[%s] %s', self.name, message)
-                self._set_fatal_error('discord_token_lock', message, retryable=False)
-                return False
-
            # Set up intents -- members intent needed for username-to-ID resolution
            intents = Intents.default()
            intents.message_content = True
@@ -504,13 +493,13 @@ class DiscordAdapter(BasePlatformAdapter):
            intents.guild_messages = True
            intents.members = True
            intents.voice_states = True
-
+            
            # Create bot
            self._client = commands.Bot(
                command_prefix="!",  # Not really used, we handle raw messages
                intents=intents,
            )
-
+            
            # Parse allowed user entries (may contain usernames or IDs)
            allowed_env = os.getenv("DISCORD_ALLOWED_USERS", "")
            if allowed_env:
@@ -518,17 +507,17 @@ class DiscordAdapter(BasePlatformAdapter):
                    _clean_discord_id(uid) for uid in allowed_env.split(",")
                    if uid.strip()
                }
-
+            
            adapter_self = self  # capture for closure
-
+            
            # Register event handlers
            @self._client.event
            async def on_ready():
                logger.info("[%s] Connected as %s", adapter_self.name, adapter_self._client.user)
-
+                
                # Resolve any usernames in the allowed list to numeric IDs
                await adapter_self._resolve_allowed_usernames()
-
+                
                # Sync slash commands with Discord
                try:
                    synced = await adapter_self._client.tree.sync()
@@ -536,22 +525,18 @@ class DiscordAdapter(BasePlatformAdapter):
                except Exception as e:  # pragma: no cover - defensive logging
                    logger.warning("[%s] Slash command sync failed: %s", adapter_self.name, e, exc_info=True)
                adapter_self._ready_event.set()
-
+            
            @self._client.event
            async def on_message(message: DiscordMessage):
                # Always ignore our own messages
                if message.author == self._client.user:
                    return
-
+                
                # Ignore Discord system messages (thread renames, pins, member joins, etc.)
                # Allow both default and reply types — replies have a distinct MessageType.
                if message.type not in (discord.MessageType.default, discord.MessageType.reply):
                    return
-
-                # Check if the message author is in the allowed user list
-                if not self._is_allowed_user(str(message.author.id)):
-                    return
-
+                
                # Bot message filtering (DISCORD_ALLOW_BOTS):
                #   "none"     — ignore all other bots (default)
                #   "mentions" — accept bot messages only when they @mention us
@@ -564,23 +549,7 @@ class DiscordAdapter(BasePlatformAdapter):
                        if not self._client.user or self._client.user not in message.mentions:
                            return
                    # "all" falls through to handle_message
-
-                # If the message @mentions other users but NOT the bot, the
-                # sender is talking to someone else — stay silent.  Only
-                # applies in server channels; in DMs the user is always
-                # talking to the bot (mentions are just references).
-                # Controlled by DISCORD_IGNORE_NO_MENTION (default: true).
-                _ignore_no_mention = os.getenv(
-                    "DISCORD_IGNORE_NO_MENTION", "true"
-                ).lower() in ("true", "1", "yes")
-                if _ignore_no_mention and message.mentions and not isinstance(message.channel, discord.DMChannel):
-                    _bot_mentioned = (
-                        self._client.user is not None
-                        and self._client.user in message.mentions
-                    )
-                    if not _bot_mentioned:
-                        return  # Talking to someone else, don't interrupt
-
+                
                await self._handle_message(message)

            @self._client.event
@@ -618,23 +587,23 @@ class DiscordAdapter(BasePlatformAdapter):

            # Register slash commands
            self._register_slash_commands()
-
+            
            # Start the bot in background
            self._bot_task = asyncio.create_task(self._client.start(self.config.token))
-
+            
            # Wait for ready
            await asyncio.wait_for(self._ready_event.wait(), timeout=30)
-
+            
            self._running = True
            return True
-
+            
        except asyncio.TimeoutError:
            logger.error("[%s] Timeout waiting for connection to Discord", self.name, exc_info=True)
            return False
        except Exception as e:  # pragma: no cover - defensive logging
            logger.error("[%s] Failed to connect to Discord: %s", self.name, e, exc_info=True)
            return False
-
+    
    async def disconnect(self) -> None:
        """Disconnect from Discord."""
        # Clean up all active voice connections before closing the client
@@ -653,61 +622,8 @@ class DiscordAdapter(BasePlatformAdapter):
        self._running = False
        self._client = None
        self._ready_event.clear()
-
-        # Release the token lock
-        try:
-            from gateway.status import release_scoped_lock
-            if getattr(self, '_token_lock_identity', None):
-                release_scoped_lock('discord-bot-token', self._token_lock_identity)
-                self._token_lock_identity = None
-        except Exception:
-            pass
-
        logger.info("[%s] Disconnected", self.name)
-
-    async def _add_reaction(self, message: Any, emoji: str) -> bool:
-        """Add an emoji reaction to a Discord message."""
-        if not message or not hasattr(message, "add_reaction"):
-            return False
-        try:
-            await message.add_reaction(emoji)
-            return True
-        except Exception as e:
-            logger.debug("[%s] add_reaction failed (%s): %s", self.name, emoji, e)
-            return False
-
-    async def _remove_reaction(self, message: Any, emoji: str) -> bool:
-        """Remove the bot's own emoji reaction from a Discord message."""
-        if not message or not hasattr(message, "remove_reaction") or not self._client or not self._client.user:
-            return False
-        try:
-            await message.remove_reaction(emoji, self._client.user)
-            return True
-        except Exception as e:
-            logger.debug("[%s] remove_reaction failed (%s): %s", self.name, emoji, e)
-            return False
-
-    def _reactions_enabled(self) -> bool:
-        """Check if message reactions are enabled via config/env."""
-        return os.getenv("DISCORD_REACTIONS", "true").lower() not in ("false", "0", "no")
-
-    async def on_processing_start(self, event: MessageEvent) -> None:
-        """Add an in-progress reaction for normal Discord message events."""
-        if not self._reactions_enabled():
-            return
-        message = event.raw_message
-        if hasattr(message, "add_reaction"):
-            await self._add_reaction(message, "👀")
-
-    async def on_processing_complete(self, event: MessageEvent, success: bool) -> None:
-        """Swap the in-progress reaction for a final success/failure reaction."""
-        if not self._reactions_enabled():
-            return
-        message = event.raw_message
-        if hasattr(message, "add_reaction"):
-            await self._remove_reaction(message, "👀")
-            await self._add_reaction(message, "✅" if success else "❌")
-
+    
    async def send(
        self,
        chat_id: str,
@@ -724,24 +640,24 @@ class DiscordAdapter(BasePlatformAdapter):
            channel = self._client.get_channel(int(chat_id))
            if not channel:
                channel = await self._client.fetch_channel(int(chat_id))
-
+            
            if not channel:
                return SendResult(success=False, error=f"Channel {chat_id} not found")
-
+            
            # Format and split message if needed
            formatted = self.format_message(content)
            chunks = self.truncate_message(formatted, self.MAX_MESSAGE_LENGTH)
-
+            
            message_ids = []
            reference = None
-
+            
            if reply_to:
                try:
                    ref_msg = await channel.fetch_message(int(reply_to))
                    reference = ref_msg
                except Exception as e:
                    logger.debug("Could not fetch reply-to message: %s", e)
-
+            
            for i, chunk in enumerate(chunks):
                chunk_reference = reference if i == 0 else None
                try:
@@ -768,13 +684,13 @@ class DiscordAdapter(BasePlatformAdapter):
                    else:
                        raise
                message_ids.append(str(msg.id))
-
+            
            return SendResult(
                success=True,
                message_id=message_ids[0] if message_ids else None,
                raw_response={"message_ids": message_ids}
            )
-
+            
        except Exception as e:  # pragma: no cover - defensive logging
            logger.error("[%s] Failed to send Discord message: %s", self.name, e, exc_info=True)
            return SendResult(success=False, error=str(e))
@@ -1246,25 +1162,25 @@ class DiscordAdapter(BasePlatformAdapter):
        """Send an image natively as a Discord file attachment."""
        if not self._client:
            return SendResult(success=False, error="Not connected")
-
+        
        try:
            import aiohttp
-
+            
            channel = self._client.get_channel(int(chat_id))
            if not channel:
                channel = await self._client.fetch_channel(int(chat_id))
            if not channel:
                return SendResult(success=False, error=f"Channel {chat_id} not found")
-
+            
            # Download the image and send as a Discord file attachment
            # (Discord renders attachments inline, unlike plain URLs)
            async with aiohttp.ClientSession() as session:
                async with session.get(image_url, timeout=aiohttp.ClientTimeout(total=30)) as resp:
                    if resp.status != 200:
                        raise Exception(f"Failed to download image: HTTP {resp.status}")
-
+                    
                    image_data = await resp.read()
-
+                    
                    # Determine filename from URL or content type
                    content_type = resp.headers.get("content-type", "image/png")
                    ext = "png"
@@ -1274,16 +1190,16 @@ class DiscordAdapter(BasePlatformAdapter):
                        ext = "gif"
                    elif "webp" in content_type:
                        ext = "webp"
-
+                    
                    import io
                    file = discord.File(io.BytesIO(image_data), filename=f"image.{ext}")
-
+                    
                    msg = await channel.send(
                        content=caption if caption else None,
                        file=file,
                    )
                    return SendResult(success=True, message_id=str(msg.id))
-
+        
        except ImportError:
            logger.warning(
                "[%s] aiohttp not installed, falling back to URL. Run: pip install aiohttp",
@@ -1334,7 +1250,7 @@ class DiscordAdapter(BasePlatformAdapter):
        except Exception as e:  # pragma: no cover - defensive logging
            logger.error("[%s] Failed to send document, falling back to base adapter: %s", self.name, e, exc_info=True)
            return await super().send_document(chat_id, file_path, caption, file_name, reply_to, metadata=metadata)
-
+    
    async def send_typing(self, chat_id: str, metadata=None) -> None:
        """Start a persistent typing indicator for a channel.

@@ -1378,20 +1294,20 @@ class DiscordAdapter(BasePlatformAdapter):
                await task
            except (asyncio.CancelledError, Exception):
                pass
-
+    
    async def get_chat_info(self, chat_id: str) -> Dict[str, Any]:
        """Get information about a Discord channel."""
        if not self._client:
            return {"name": "Unknown", "type": "dm"}
-
+        
        try:
            channel = self._client.get_channel(int(chat_id))
            if not channel:
                channel = await self._client.fetch_channel(int(chat_id))
-
+            
            if not channel:
                return {"name": str(chat_id), "type": "dm"}
-
+            
            # Determine channel type
            if isinstance(channel, discord.DMChannel):
                chat_type = "dm"
@@ -1407,7 +1323,7 @@ class DiscordAdapter(BasePlatformAdapter):
            else:
                chat_type = "channel"
                name = getattr(channel, "name", str(chat_id))
-
+            
            return {
                "name": name,
                "type": chat_type,
@@ -1417,7 +1333,7 @@ class DiscordAdapter(BasePlatformAdapter):
        except Exception as e:  # pragma: no cover - defensive logging
            logger.error("[%s] Failed to get chat info for %s: %s", self.name, chat_id, e, exc_info=True)
            return {"name": str(chat_id), "type": "dm", "error": str(e)}
-
+    
    async def _resolve_allowed_usernames(self) -> None:
        """
        Resolve non-numeric entries in DISCORD_ALLOWED_USERS to Discord user IDs.
@@ -1485,7 +1401,7 @@ class DiscordAdapter(BasePlatformAdapter):
    def format_message(self, content: str) -> str:
        """
        Format message for Discord.
-
+        
        Discord uses its own markdown variant.
        """
        # Discord markdown is fairly standard, no special escaping needed
@@ -1497,23 +1413,15 @@ class DiscordAdapter(BasePlatformAdapter):
        command_text: str,
        followup_msg: str | None = None,
    ) -> None:
-        """Common handler for simple slash commands that dispatch a command string.
-
-        Defers the interaction (shows "thinking..."), dispatches the command,
-        then cleans up the deferred response.  If *followup_msg* is provided
-        the "thinking..." indicator is replaced with that text; otherwise it
-        is deleted so the channel isn't cluttered.
-        """
+        """Common handler for simple slash commands that dispatch a command string."""
        await interaction.response.defer(ephemeral=True)
        event = self._build_slash_event(interaction, command_text)
        await self.handle_message(event)
-        try:
-            if followup_msg:
-                await interaction.edit_original_response(content=followup_msg)
-            else:
-                await interaction.delete_original_response()
-        except Exception as e:
-            logger.debug("Discord interaction cleanup failed: %s", e)
+        if followup_msg:
+            try:
+                await interaction.followup.send(followup_msg, ephemeral=True)
+            except Exception as e:
+                logger.debug("Discord followup failed: %s", e)

    def _register_slash_commands(self) -> None:
        """Register Discord slash commands on the command tree."""
@@ -1538,7 +1446,9 @@ class DiscordAdapter(BasePlatformAdapter):
        @tree.command(name="reasoning", description="Show or change reasoning effort")
        @discord.app_commands.describe(effort="Reasoning effort: xhigh, high, medium, low, minimal, or none.")
        async def slash_reasoning(interaction: discord.Interaction, effort: str = ""):
-            await self._run_simple_slash(interaction, f"/reasoning {effort}".strip())
+            await interaction.response.defer(ephemeral=True)
+            event = self._build_slash_event(interaction, f"/reasoning {effort}".strip())
+            await self.handle_message(event)

        @tree.command(name="personality", description="Set a personality")
        @discord.app_commands.describe(name="Personality name. Leave empty to list available.")
@@ -1611,7 +1521,9 @@ class DiscordAdapter(BasePlatformAdapter):
            discord.app_commands.Choice(name="status — show current mode", value="status"),
        ])
        async def slash_voice(interaction: discord.Interaction, mode: str = ""):
-            await self._run_simple_slash(interaction, f"/voice {mode}".strip())
+            await interaction.response.defer(ephemeral=True)
+            event = self._build_slash_event(interaction, f"/voice {mode}".strip())
+            await self.handle_message(event)

        @tree.command(name="update", description="Update Hermes Agent to the latest version")
        async def slash_update(interaction: discord.Interaction):
@@ -1651,7 +1563,7 @@ class DiscordAdapter(BasePlatformAdapter):
            chat_name = interaction.channel.name
            if hasattr(interaction.channel, "guild") and interaction.channel.guild:
                chat_name = f"{interaction.channel.guild.name} / #{chat_name}"
-
+        
        # Get channel topic (if available)
        chat_topic = getattr(interaction.channel, "topic", None)

@@ -2055,7 +1967,7 @@ class DiscordAdapter(BasePlatformAdapter):
                        if doc_ext in SUPPORTED_DOCUMENT_TYPES:
                            msg_type = MessageType.DOCUMENT
                    break
-
+        
        # When auto-threading kicked in, route responses to the new thread
        effective_channel = auto_threaded_channel or message.channel

@@ -2074,7 +1986,7 @@ class DiscordAdapter(BasePlatformAdapter):

        # Get channel topic (if available - TextChannels have topics, DMs/threads don't)
        chat_topic = getattr(message.channel, "topic", None)
-
+        
        # Build source
        source = self.build_source(
            chat_id=str(effective_channel.id),
@@ -2085,7 +1997,7 @@ class DiscordAdapter(BasePlatformAdapter):
            thread_id=thread_id,
            chat_topic=chat_topic,
        )
-
+        
        # Build media URLs -- download image attachments to local cache so the
        # vision tool can access them reliably (Discord CDN URLs can expire).
        media_urls = []
@@ -2179,16 +2091,11 @@ class DiscordAdapter(BasePlatformAdapter):
                                "[Discord] Failed to cache document %s: %s",
                                att.filename, e, exc_info=True,
                            )
-
+        
        event_text = message.content
        if pending_text_injection:
            event_text = f"{pending_text_injection}\n\n{event_text}" if event_text else pending_text_injection

-        # Defense-in-depth: prevent empty user messages from entering session
-        # (can happen when user sends @mention-only with no other text)
-        if not event_text or not event_text.strip():
-            event_text = "(The user sent a message with no text content)"
-
        event = MessageEvent(
            text=event_text,
            message_type=msg_type,
@@ -43,20 +43,6 @@ from gateway.platforms.base import (
 from gateway.config import Platform, PlatformConfig

 logger = logging.getLogger(__name__)
-# Automated sender patterns — emails from these are silently ignored
-_NOREPLY_PATTERNS = (
-    "noreply", "no-reply", "no_reply", "donotreply", "do-not-reply",
-    "mailer-daemon", "postmaster", "bounce", "notifications@",
-    "automated@", "auto-confirm", "auto-reply", "automailer",
-)
-
-# RFC headers that indicate bulk/automated mail
-_AUTOMATED_HEADERS = {
-    "Auto-Submitted": lambda v: v.lower() != "no",
-    "Precedence": lambda v: v.lower() in ("bulk", "list", "junk"),
-    "X-Auto-Response-Suppress": lambda v: bool(v),
-    "List-Unsubscribe": lambda v: bool(v),
-}

 # Gmail-safe max length per email body
 MAX_MESSAGE_LENGTH = 50_000
@@ -64,17 +50,7 @@ MAX_MESSAGE_LENGTH = 50_000
 # Supported image extensions for inline detection
 _IMAGE_EXTS = {".jpg", ".jpeg", ".png", ".gif", ".webp"}

-def _is_automated_sender(address: str, headers: dict) -> bool:
-    """Return True if this email is from an automated/noreply source."""
-    addr = address.lower()
-    if any(pattern in addr for pattern in _NOREPLY_PATTERNS):
-        return True
-    for header, check in _AUTOMATED_HEADERS.items():
-        value = headers.get(header, "")
-        if value and check(value):
-            return True
-    return False
-    
+
 def check_email_requirements() -> bool:
    """Check if email platform dependencies are available."""
    addr = os.getenv("EMAIL_ADDRESS")
@@ -237,7 +213,6 @@ class EmailAdapter(BasePlatformAdapter):

        # Track message IDs we've already processed to avoid duplicates
        self._seen_uids: set = set()
-        self._seen_uids_max: int = 2000   # cap to prevent unbounded memory growth
        self._poll_task: Optional[asyncio.Task] = None

        # Map chat_id (sender email) -> last subject + message-id for threading
@@ -245,26 +220,6 @@ class EmailAdapter(BasePlatformAdapter):

        logger.info("[Email] Adapter initialized for %s", self._address)

-    def _trim_seen_uids(self) -> None:
-        """Keep only the most recent UIDs to prevent unbounded memory growth.
-
-        IMAP UIDs are monotonically increasing integers. When the set grows
-        beyond the cap, we keep only the highest half — old UIDs are safe to
-        drop because new messages always have higher UIDs and IMAP's UNSEEN
-        flag prevents re-delivery regardless.
-        """
-        if len(self._seen_uids) <= self._seen_uids_max:
-            return
-        try:
-            # UIDs are bytes like b'1234' — sort numerically and keep top half
-            sorted_uids = sorted(self._seen_uids, key=lambda u: int(u))
-            keep = self._seen_uids_max // 2
-            self._seen_uids = set(sorted_uids[-keep:])
-            logger.debug("[Email] Trimmed seen UIDs to %d entries", len(self._seen_uids))
-        except (ValueError, TypeError):
-            # Fallback: just clear old entries if sort fails
-            self._seen_uids = set(list(self._seen_uids)[-self._seen_uids_max // 2:])
-
    async def connect(self) -> bool:
        """Connect to the IMAP server and start polling for new messages."""
        try:
@@ -277,8 +232,6 @@ class EmailAdapter(BasePlatformAdapter):
            if status == "OK" and data and data[0]:
                for uid in data[0].split():
                    self._seen_uids.add(uid)
-            # Keep only the most recent UIDs to prevent unbounded growth
-            self._trim_seen_uids()
            imap.logout()
            logger.info("[Email] IMAP connection test passed. %d existing messages skipped.", len(self._seen_uids))
        except Exception as e:
@@ -337,63 +290,52 @@ class EmailAdapter(BasePlatformAdapter):
        results = []
        try:
            imap = imaplib.IMAP4_SSL(self._imap_host, self._imap_port, timeout=30)
-            try:
-                imap.login(self._address, self._password)
-                imap.select("INBOX")
+            imap.login(self._address, self._password)
+            imap.select("INBOX")

-                status, data = imap.uid("search", None, "UNSEEN")
-                if status != "OK" or not data or not data[0]:
-                    return results
+            status, data = imap.uid("search", None, "UNSEEN")
+            if status != "OK" or not data or not data[0]:
+                imap.logout()
+                return results

-                for uid in data[0].split():
-                    if uid in self._seen_uids:
-                        continue
-                    self._seen_uids.add(uid)
-                    # Trim periodically to prevent unbounded memory growth
-                    if len(self._seen_uids) > self._seen_uids_max:
-                        self._trim_seen_uids()
+            for uid in data[0].split():
+                if uid in self._seen_uids:
+                    continue
+                self._seen_uids.add(uid)

-                    status, msg_data = imap.uid("fetch", uid, "(RFC822)")
-                    if status != "OK":
-                        continue
+                status, msg_data = imap.uid("fetch", uid, "(RFC822)")
+                if status != "OK":
+                    continue

-                    raw_email = msg_data[0][1]
-                    msg = email_lib.message_from_bytes(raw_email)
+                raw_email = msg_data[0][1]
+                msg = email_lib.message_from_bytes(raw_email)

-                    sender_raw = msg.get("From", "")
-                    sender_addr = _extract_email_address(sender_raw)
-                    sender_name = _decode_header_value(sender_raw)
-                    # Remove email from name if present
-                    if "<" in sender_name:
-                        sender_name = sender_name.split("<")[0].strip().strip('"')
+                sender_raw = msg.get("From", "")
+                sender_addr = _extract_email_address(sender_raw)
+                sender_name = _decode_header_value(sender_raw)
+                # Remove email from name if present
+                if "<" in sender_name:
+                    sender_name = sender_name.split("<")[0].strip().strip('"')

-                    subject = _decode_header_value(msg.get("Subject", "(no subject)"))
-                    message_id = msg.get("Message-ID", "")
-                    in_reply_to = msg.get("In-Reply-To", "")
-                    # Skip automated/noreply senders before any processing
-                    msg_headers = dict(msg.items())
-                    if _is_automated_sender(sender_addr, msg_headers):
-                        logger.debug("[Email] Skipping automated sender: %s", sender_addr)
-                        continue
-                    body = _extract_text_body(msg)
-                    attachments = _extract_attachments(msg, skip_attachments=self._skip_attachments)
+                subject = _decode_header_value(msg.get("Subject", "(no subject)"))
+                message_id = msg.get("Message-ID", "")
+                in_reply_to = msg.get("In-Reply-To", "")
+                body = _extract_text_body(msg)
+                attachments = _extract_attachments(msg, skip_attachments=self._skip_attachments)

-                    results.append({
-                        "uid": uid,
-                        "sender_addr": sender_addr,
-                        "sender_name": sender_name,
-                        "subject": subject,
-                        "message_id": message_id,
-                        "in_reply_to": in_reply_to,
-                        "body": body,
-                        "attachments": attachments,
-                        "date": msg.get("Date", ""),
-                    })
-            finally:
-                try:
-                    imap.logout()
-                except Exception:
-                    pass
+                results.append({
+                    "uid": uid,
+                    "sender_addr": sender_addr,
+                    "sender_name": sender_name,
+                    "subject": subject,
+                    "message_id": message_id,
+                    "in_reply_to": in_reply_to,
+                    "body": body,
+                    "attachments": attachments,
+                    "date": msg.get("Date", ""),
+                })
+
+            imap.logout()
        except Exception as e:
            logger.error("[Email] IMAP fetch error: %s", e)
        return results
@@ -406,11 +348,6 @@ class EmailAdapter(BasePlatformAdapter):
        if sender_addr == self._address.lower():
            return

-        # Never reply to automated senders
-        if _is_automated_sender(sender_addr, {}):
-            logger.debug("[Email] Dropping automated sender at dispatch: %s", sender_addr)
-            return
-
        subject = msg_data["subject"]
        body = msg_data["body"].strip()
        attachments = msg_data["attachments"]
@@ -506,15 +443,10 @@ class EmailAdapter(BasePlatformAdapter):
        msg.attach(MIMEText(body, "plain", "utf-8"))

        smtp = smtplib.SMTP(self._smtp_host, self._smtp_port, timeout=30)
-        try:
-            smtp.starttls(context=ssl.create_default_context())
-            smtp.login(self._address, self._password)
-            smtp.send_message(msg)
-        finally:
-            try:
-                smtp.quit()
-            except Exception:
-                smtp.close()
+        smtp.starttls(context=ssl.create_default_context())
+        smtp.login(self._address, self._password)
+        smtp.send_message(msg)
+        smtp.quit()

        logger.info("[Email] Sent reply to %s (subject: %s)", to_addr, subject)
        return msg_id
@@ -598,15 +530,10 @@ class EmailAdapter(BasePlatformAdapter):
            msg.attach(part)

        smtp = smtplib.SMTP(self._smtp_host, self._smtp_port, timeout=30)
-        try:
-            smtp.starttls(context=ssl.create_default_context())
-            smtp.login(self._address, self._password)
-            smtp.send_message(msg)
-        finally:
-            try:
-                smtp.quit()
-            except Exception:
-                smtp.close()
+        smtp.starttls(context=ssl.create_default_context())
+        smtp.login(self._address, self._password)
+        smtp.send_message(msg)
+        smtp.quit()

        return msg_id

@@ -17,8 +17,6 @@ Environment variables:
 from __future__ import annotations

 import asyncio
-import io
-import json
 import logging
 import mimetypes
 import os
@@ -42,21 +40,11 @@ logger = logging.getLogger(__name__)
 MAX_MESSAGE_LENGTH = 4000

 # Store directory for E2EE keys and sync state.
-# Uses get_hermes_home() so each profile gets its own Matrix store.
-from hermes_constants import get_hermes_dir as _get_hermes_dir
-_STORE_DIR = _get_hermes_dir("platforms/matrix/store", "matrix/store")
+_STORE_DIR = Path.home() / ".hermes" / "matrix" / "store"

 # Grace period: ignore messages older than this many seconds before startup.
 _STARTUP_GRACE_SECONDS = 5

-# E2EE key export file for persistence across restarts.
-_KEY_EXPORT_FILE = _STORE_DIR / "exported_keys.txt"
-_KEY_EXPORT_PASSPHRASE = "hermes-matrix-e2ee-keys"
-
-# Pending undecrypted events: cap and TTL for retry buffer.
-_MAX_PENDING_EVENTS = 100
-_PENDING_EVENT_TTL = 300  # seconds — stop retrying after 5 min
-

 def check_matrix_requirements() -> bool:
    """Return True if the Matrix adapter can be used."""
@@ -119,10 +107,6 @@ class MatrixAdapter(BasePlatformAdapter):
        self._processed_events: deque = deque(maxlen=1000)
        self._processed_events_set: set = set()

-        # Buffer for undecrypted events pending key receipt.
-        # Each entry: (room, event, timestamp)
-        self._pending_megolm: list = []
-
    def _is_duplicate_event(self, event_id) -> bool:
        """Return True if this event was already processed. Tracks the ID otherwise."""
        if not event_id:
@@ -177,49 +161,22 @@ class MatrixAdapter(BasePlatformAdapter):
        # Authenticate.
        if self._access_token:
            client.access_token = self._access_token
-
-            # With access-token auth, always resolve whoami so we validate the
-            # token and learn the device_id. The device_id matters for E2EE:
-            # without it, matrix-nio can send plain messages but may fail to
-            # decrypt inbound encrypted events or encrypt outbound room sends.
-            resp = await client.whoami()
-            if isinstance(resp, nio.WhoamiResponse):
-                resolved_user_id = getattr(resp, "user_id", "") or self._user_id
-                resolved_device_id = getattr(resp, "device_id", "")
-                if resolved_user_id:
-                    self._user_id = resolved_user_id
-
-                # restore_login() is the matrix-nio path that binds the access
-                # token to a specific device and loads the crypto store.
-                if resolved_device_id and hasattr(client, "restore_login"):
-                    client.restore_login(
-                        self._user_id or resolved_user_id,
-                        resolved_device_id,
-                        self._access_token,
-                    )
+            # Resolve user_id if not set.
+            if not self._user_id:
+                resp = await client.whoami()
+                if isinstance(resp, nio.WhoamiResponse):
+                    self._user_id = resp.user_id
+                    client.user_id = resp.user_id
+                    logger.info("Matrix: authenticated as %s", self._user_id)
                else:
-                    if self._user_id:
-                        client.user_id = self._user_id
-                    if resolved_device_id:
-                        client.device_id = resolved_device_id
-                    client.access_token = self._access_token
-                    if self._encryption:
-                        logger.warning(
-                            "Matrix: access-token login did not restore E2EE state; "
-                            "encrypted rooms may fail until a device_id is available"
-                        )
-
-                logger.info(
-                    "Matrix: using access token for %s%s",
-                    self._user_id or "(unknown user)",
-                    f" (device {resolved_device_id})" if resolved_device_id else "",
-                )
+                    logger.error(
+                        "Matrix: whoami failed — check MATRIX_ACCESS_TOKEN and MATRIX_HOMESERVER"
+                    )
+                    await client.close()
+                    return False
            else:
-                logger.error(
-                    "Matrix: whoami failed — check MATRIX_ACCESS_TOKEN and MATRIX_HOMESERVER"
-                )
-                await client.close()
-                return False
+                client.user_id = self._user_id
+                logger.info("Matrix: using access token for %s", self._user_id)
        elif self._password and self._user_id:
            resp = await client.login(
                self._password,
@@ -237,7 +194,7 @@ class MatrixAdapter(BasePlatformAdapter):
            return False

        # If E2EE is enabled, load the crypto store.
-        if self._encryption and getattr(client, "olm", None):
+        if self._encryption and hasattr(client, "olm"):
            try:
                if client.should_upload_keys:
                    await client.keys_upload()
@@ -245,21 +202,6 @@ class MatrixAdapter(BasePlatformAdapter):
            except Exception as exc:
                logger.warning("Matrix: crypto init issue: %s", exc)

-            # Import previously exported Megolm keys (survives restarts).
-            if _KEY_EXPORT_FILE.exists():
-                try:
-                    await client.import_keys(
-                        str(_KEY_EXPORT_FILE), _KEY_EXPORT_PASSPHRASE,
-                    )
-                    logger.info("Matrix: imported Megolm keys from backup")
-                except Exception as exc:
-                    logger.debug("Matrix: could not import keys: %s", exc)
-        elif self._encryption:
-            logger.warning(
-                "Matrix: E2EE requested but crypto store is not loaded; "
-                "encrypted rooms may fail"
-            )
-
        # Register event callbacks.
        client.add_event_callback(self._on_room_message, nio.RoomMessageText)
        client.add_event_callback(self._on_room_message_media, nio.RoomMessageImage)
@@ -288,7 +230,6 @@ class MatrixAdapter(BasePlatformAdapter):
            )
            # Build DM room cache from m.direct account data.
            await self._refresh_dm_cache()
-            await self._run_e2ee_maintenance()
        else:
            logger.warning("Matrix: initial sync returned %s", type(resp).__name__)

@@ -308,18 +249,6 @@ class MatrixAdapter(BasePlatformAdapter):
            except (asyncio.CancelledError, Exception):
                pass

-        # Export Megolm keys before closing so the next restart can decrypt
-        # events that used sessions from this run.
-        if self._client and self._encryption and getattr(self._client, "olm", None):
-            try:
-                _STORE_DIR.mkdir(parents=True, exist_ok=True)
-                await self._client.export_keys(
-                    str(_KEY_EXPORT_FILE), _KEY_EXPORT_PASSPHRASE,
-                )
-                logger.info("Matrix: exported Megolm keys for next restart")
-            except Exception as exc:
-                logger.debug("Matrix: could not export keys on disconnect: %s", exc)
-
        if self._client:
            await self._client.close()
            self._client = None
@@ -372,48 +301,13 @@ class MatrixAdapter(BasePlatformAdapter):
                    relates_to["m.in_reply_to"] = {"event_id": reply_to}
                msg_content["m.relates_to"] = relates_to

-            async def _room_send_once(*, ignore_unverified_devices: bool = False):
-                return await asyncio.wait_for(
-                    self._client.room_send(
-                        chat_id,
-                        "m.room.message",
-                        msg_content,
-                        ignore_unverified_devices=ignore_unverified_devices,
-                    ),
-                    timeout=45,
-                )
-
-            try:
-                resp = await _room_send_once(ignore_unverified_devices=False)
-            except Exception as exc:
-                retryable = isinstance(exc, asyncio.TimeoutError)
-                olm_unverified = getattr(nio, "OlmUnverifiedDeviceError", None)
-                send_retry = getattr(nio, "SendRetryError", None)
-                if isinstance(olm_unverified, type) and isinstance(exc, olm_unverified):
-                    retryable = True
-                if isinstance(send_retry, type) and isinstance(exc, send_retry):
-                    retryable = True
-
-                if not retryable:
-                    logger.error("Matrix: failed to send to %s: %s", chat_id, exc)
-                    return SendResult(success=False, error=str(exc))
-
-                logger.warning(
-                    "Matrix: initial encrypted send to %s failed (%s); "
-                    "retrying after E2EE maintenance with ignored unverified devices",
-                    chat_id,
-                    exc,
-                )
-                await self._run_e2ee_maintenance()
-                try:
-                    resp = await _room_send_once(ignore_unverified_devices=True)
-                except Exception as retry_exc:
-                    logger.error("Matrix: failed to send to %s after retry: %s", chat_id, retry_exc)
-                    return SendResult(success=False, error=str(retry_exc))
-
+            resp = await self._client.room_send(
+                chat_id,
+                "m.room.message",
+                msg_content,
+            )
            if isinstance(resp, nio.RoomSendResponse):
                last_event_id = resp.event_id
-                logger.info("Matrix: sent event %s to %s", last_event_id, chat_id)
            else:
                err = getattr(resp, "message", str(resp))
                logger.error("Matrix: failed to send to %s: %s", chat_id, err)
@@ -548,11 +442,8 @@ class MatrixAdapter(BasePlatformAdapter):
        reply_to: Optional[str] = None,
        metadata: Optional[Dict[str, Any]] = None,
    ) -> SendResult:
-        """Upload an audio file as a voice message (MSC3245 native voice)."""
-        return await self._send_local_file(
-            chat_id, audio_path, "m.audio", caption, reply_to, 
-            metadata=metadata, is_voice=True
-        )
+        """Upload an audio file as a voice message."""
+        return await self._send_local_file(chat_id, audio_path, "m.audio", caption, reply_to, metadata=metadata)

    async def send_video(
        self,
@@ -585,16 +476,13 @@ class MatrixAdapter(BasePlatformAdapter):
        caption: Optional[str] = None,
        reply_to: Optional[str] = None,
        metadata: Optional[Dict[str, Any]] = None,
-        is_voice: bool = False,
    ) -> SendResult:
        """Upload bytes to Matrix and send as a media message."""
        import nio

        # Upload to homeserver.
-        # nio expects a DataProvider (callable) or file-like object, not raw bytes.
-        # nio.upload() returns a tuple (UploadResponse|UploadError, Optional[Dict])
-        resp, maybe_encryption_info = await self._client.upload(
-            io.BytesIO(data),
+        resp = await self._client.upload(
+            data,
            content_type=content_type,
            filename=filename,
        )
@@ -616,10 +504,6 @@ class MatrixAdapter(BasePlatformAdapter):
            },
        }

-        # Add MSC3245 voice flag for native voice messages.
-        if is_voice:
-            msg_content["org.matrix.msc3245.voice"] = {}
-
        if reply_to:
            msg_content["m.relates_to"] = {
                "m.in_reply_to": {"event_id": reply_to}
@@ -647,7 +531,6 @@ class MatrixAdapter(BasePlatformAdapter):
        reply_to: Optional[str] = None,
        file_name: Optional[str] = None,
        metadata: Optional[Dict[str, Any]] = None,
-        is_voice: bool = False,
    ) -> SendResult:
        """Read a local file and upload it."""
        p = Path(file_path)
@@ -660,7 +543,7 @@ class MatrixAdapter(BasePlatformAdapter):
        ct = mimetypes.guess_type(fname)[0] or "application/octet-stream"
        data = p.read_bytes()

-        return await self._upload_and_send(room_id, data, fname, ct, msgtype, caption, reply_to, metadata, is_voice)
+        return await self._upload_and_send(room_id, data, fname, ct, msgtype, caption, reply_to, metadata)

    # ------------------------------------------------------------------
    # Sync loop
@@ -668,23 +551,9 @@ class MatrixAdapter(BasePlatformAdapter):

    async def _sync_loop(self) -> None:
        """Continuously sync with the homeserver."""
-        import nio
-
        while not self._closing:
            try:
-                resp = await self._client.sync(timeout=30000)
-                if isinstance(resp, nio.SyncError):
-                    if self._closing:
-                        return
-                    logger.warning(
-                        "Matrix: sync returned %s: %s — retrying in 5s",
-                        type(resp).__name__,
-                        getattr(resp, "message", resp),
-                    )
-                    await asyncio.sleep(5)
-                    continue
-
-                await self._run_e2ee_maintenance()
+                await self._client.sync(timeout=30000)
            except asyncio.CancelledError:
                return
            except Exception as exc:
@@ -693,148 +562,6 @@ class MatrixAdapter(BasePlatformAdapter):
                logger.warning("Matrix: sync error: %s — retrying in 5s", exc)
                await asyncio.sleep(5)

-    async def _run_e2ee_maintenance(self) -> None:
-        """Run matrix-nio E2EE housekeeping between syncs.
-
-        Hermes uses a custom sync loop instead of matrix-nio's sync_forever(),
-        so we need to explicitly drive the key management work that sync_forever()
-        normally handles for encrypted rooms.
-
-        Also auto-trusts all devices (so senders share session keys with us)
-        and retries decryption for any buffered MegolmEvents.
-        """
-        client = self._client
-        if not client or not self._encryption or not getattr(client, "olm", None):
-            return
-
-        did_query_keys = client.should_query_keys
-
-        tasks = [asyncio.create_task(client.send_to_device_messages())]
-
-        if client.should_upload_keys:
-            tasks.append(asyncio.create_task(client.keys_upload()))
-
-        if did_query_keys:
-            tasks.append(asyncio.create_task(client.keys_query()))
-
-        if client.should_claim_keys:
-            users = client.get_users_for_key_claiming()
-            if users:
-                tasks.append(asyncio.create_task(client.keys_claim(users)))
-
-        for task in asyncio.as_completed(tasks):
-            try:
-                await task
-            except asyncio.CancelledError:
-                raise
-            except Exception as exc:
-                logger.warning("Matrix: E2EE maintenance task failed: %s", exc)
-
-        # After key queries, auto-trust all devices so senders share keys with
-        # us.  For a bot this is the right default — we want to decrypt
-        # everything, not enforce manual verification.
-        if did_query_keys:
-            self._auto_trust_devices()
-
-        # Retry any buffered undecrypted events now that new keys may have
-        # arrived (from key requests, key queries, or to-device forwarding).
-        if self._pending_megolm:
-            await self._retry_pending_decryptions()
-
-    def _auto_trust_devices(self) -> None:
-        """Trust/verify all unverified devices we know about.
-
-        When other clients see our device as verified, they proactively share
-        Megolm session keys with us.  Without this, many clients will refuse
-        to include an unverified device in key distributions.
-        """
-        client = self._client
-        if not client:
-            return
-
-        device_store = getattr(client, "device_store", None)
-        if not device_store:
-            return
-
-        own_device = getattr(client, "device_id", None)
-        trusted_count = 0
-
-        try:
-            # DeviceStore.__iter__ yields OlmDevice objects directly.
-            for device in device_store:
-                if getattr(device, "device_id", None) == own_device:
-                    continue
-                if not getattr(device, "verified", False):
-                    client.verify_device(device)
-                    trusted_count += 1
-        except Exception as exc:
-            logger.debug("Matrix: auto-trust error: %s", exc)
-
-        if trusted_count:
-            logger.info("Matrix: auto-trusted %d new device(s)", trusted_count)
-
-    async def _retry_pending_decryptions(self) -> None:
-        """Retry decrypting buffered MegolmEvents after new keys arrive."""
-        import nio
-
-        client = self._client
-        if not client or not self._pending_megolm:
-            return
-
-        now = time.time()
-        still_pending: list = []
-
-        for room, event, ts in self._pending_megolm:
-            # Drop events that have aged past the TTL.
-            if now - ts > _PENDING_EVENT_TTL:
-                logger.debug(
-                    "Matrix: dropping expired pending event %s (age %.0fs)",
-                    getattr(event, "event_id", "?"), now - ts,
-                )
-                continue
-
-            try:
-                decrypted = client.decrypt_event(event)
-            except Exception:
-                # Still missing the key — keep in buffer.
-                still_pending.append((room, event, ts))
-                continue
-
-            if isinstance(decrypted, nio.MegolmEvent):
-                # decrypt_event returned the same undecryptable event.
-                still_pending.append((room, event, ts))
-                continue
-
-            logger.info(
-                "Matrix: decrypted buffered event %s (%s)",
-                getattr(event, "event_id", "?"),
-                type(decrypted).__name__,
-            )
-
-            # Route to the appropriate handler based on decrypted type.
-            try:
-                if isinstance(decrypted, nio.RoomMessageText):
-                    await self._on_room_message(room, decrypted)
-                elif isinstance(
-                    decrypted,
-                    (nio.RoomMessageImage, nio.RoomMessageAudio,
-                     nio.RoomMessageVideo, nio.RoomMessageFile),
-                ):
-                    await self._on_room_message_media(room, decrypted)
-                else:
-                    logger.debug(
-                        "Matrix: decrypted event %s has unhandled type %s",
-                        getattr(event, "event_id", "?"),
-                        type(decrypted).__name__,
-                    )
-            except Exception as exc:
-                logger.warning(
-                    "Matrix: error processing decrypted event %s: %s",
-                    getattr(event, "event_id", "?"), exc,
-                )
-
-        self._pending_megolm = still_pending
-
    # ------------------------------------------------------------------
    # Event callbacks
    # ------------------------------------------------------------------
@@ -856,29 +583,13 @@ class MatrixAdapter(BasePlatformAdapter):
        if event_ts and event_ts < self._startup_ts - _STARTUP_GRACE_SECONDS:
            return

-        # Handle undecryptable MegolmEvents: request the missing session key
-        # and buffer the event for retry once the key arrives.
+        # Handle decrypted MegolmEvents — extract the inner event.
        if isinstance(event, nio.MegolmEvent):
+            # Failed to decrypt.
            logger.warning(
-                "Matrix: could not decrypt event %s in %s — requesting key",
+                "Matrix: could not decrypt event %s in %s",
                event.event_id, room.room_id,
            )
-
-            # Ask other devices in the room to forward the session key.
-            try:
-                resp = await self._client.request_room_key(event)
-                if hasattr(resp, "event_id") or not isinstance(resp, Exception):
-                    logger.debug(
-                        "Matrix: room key request sent for session %s",
-                        getattr(event, "session_id", "?"),
-                    )
-            except Exception as exc:
-                logger.debug("Matrix: room key request failed: %s", exc)
-
-            # Buffer for retry on next maintenance cycle.
-            self._pending_megolm.append((room, event, time.time()))
-            if len(self._pending_megolm) > _MAX_PENDING_EVENTS:
-                self._pending_megolm = self._pending_megolm[-_MAX_PENDING_EVENTS:]
            return

        # Skip edits (m.replace relation).
@@ -981,19 +692,11 @@ class MatrixAdapter(BasePlatformAdapter):
        event_mimetype = (content_info.get("info") or {}).get("mimetype", "")
        media_type = "application/octet-stream"
        msg_type = MessageType.DOCUMENT
-        is_voice_message = False
-        
        if isinstance(event, nio.RoomMessageImage):
            msg_type = MessageType.PHOTO
            media_type = event_mimetype or "image/png"
        elif isinstance(event, nio.RoomMessageAudio):
-            # Check for MSC3245 voice flag: org.matrix.msc3245.voice: {}
-            source_content = getattr(event, "source", {}).get("content", {})
-            if source_content.get("org.matrix.msc3245.voice") is not None:
-                is_voice_message = True
-                msg_type = MessageType.VOICE
-            else:
-                msg_type = MessageType.AUDIO
+            msg_type = MessageType.AUDIO
            media_type = event_mimetype or "audio/ogg"
        elif isinstance(event, nio.RoomMessageVideo):
            msg_type = MessageType.VIDEO
@@ -1031,31 +734,6 @@ class MatrixAdapter(BasePlatformAdapter):
        if relates_to.get("rel_type") == "m.thread":
            thread_id = relates_to.get("event_id")

-        # For voice messages, cache audio locally for transcription tools.
-        # Use the authenticated nio client to download (Matrix requires auth for media).
-        media_urls = [http_url] if http_url else None
-        media_types = [media_type] if http_url else None
-        
-        if is_voice_message and url and url.startswith("mxc://"):
-            try:
-                import nio
-                from gateway.platforms.base import cache_audio_from_bytes
-                
-                resp = await self._client.download(mxc=url)
-                if isinstance(resp, nio.MemoryDownloadResponse):
-                    # Extract extension from mimetype or default to .ogg
-                    ext = ".ogg"
-                    if media_type and "/" in media_type:
-                        subtype = media_type.split("/")[1]
-                        ext = f".{subtype}" if subtype else ".ogg"
-                    local_path = cache_audio_from_bytes(resp.body, ext)
-                    media_urls = [local_path]
-                    logger.debug("Matrix: cached voice message to %s", local_path)
-                else:
-                    logger.warning("Matrix: failed to download voice: %s", getattr(resp, "message", resp))
-            except Exception as e:
-                logger.warning("Matrix: failed to cache voice message, using HTTP URL: %s", e)
-
        source = self.build_source(
            chat_id=room.room_id,
            chat_type=chat_type,
@@ -1064,9 +742,8 @@ class MatrixAdapter(BasePlatformAdapter):
            thread_id=thread_id,
        )

-        # Use cached local path for images (voice messages already handled above).
-        if cached_path:
-            media_urls = [cached_path]
+        # Use cached local path for images, HTTP URL for other media types
+        media_urls = [cached_path] if cached_path else ([http_url] if http_url else None)
        media_types = [media_type] if media_urls else None

        msg_event = MessageEvent(
@@ -407,38 +407,18 @@ class MattermostAdapter(BasePlatformAdapter):
        kind: str = "file",
    ) -> SendResult:
        """Download a URL and upload it as a file attachment."""
-        import asyncio
        import aiohttp
-
-        last_exc = None
-        file_data = None
-        ct = "application/octet-stream"
-        fname = url.rsplit("/", 1)[-1].split("?")[0] or f"{kind}.png"
-
-        for attempt in range(3):
-            try:
-                async with self._session.get(url, timeout=aiohttp.ClientTimeout(total=30)) as resp:
-                    if resp.status >= 500 or resp.status == 429:
-                        if attempt < 2:
-                            logger.debug("Mattermost download retry %d/2 for %s (status %d)",
-                                         attempt + 1, url[:80], resp.status)
-                            await asyncio.sleep(1.5 * (attempt + 1))
-                            continue
-                    if resp.status >= 400:
-                        return await self.send(chat_id, f"{caption or ''}\n{url}".strip(), reply_to)
-                    file_data = await resp.read()
-                    ct = resp.content_type or "application/octet-stream"
-                    break
-            except (aiohttp.ClientError, asyncio.TimeoutError) as exc:
-                last_exc = exc
-                if attempt < 2:
-                    await asyncio.sleep(1.5 * (attempt + 1))
-                    continue
-                logger.warning("Mattermost: failed to download %s after %d attempts: %s", url, attempt + 1, exc)
-                return await self.send(chat_id, f"{caption or ''}\n{url}".strip(), reply_to)
-
-        if file_data is None:
-            logger.warning("Mattermost: download returned no data for %s", url)
+        try:
+            async with self._session.get(url, timeout=aiohttp.ClientTimeout(total=30)) as resp:
+                if resp.status >= 400:
+                    # Fall back to sending the URL as text.
+                    return await self.send(chat_id, f"{caption or ''}\n{url}".strip(), reply_to)
+                file_data = await resp.read()
+                ct = resp.content_type or "application/octet-stream"
+                # Derive filename from URL.
+                fname = url.rsplit("/", 1)[-1].split("?")[0] or f"{kind}.png"
+        except Exception as exc:
+            logger.warning("Mattermost: failed to download %s: %s", url, exc)
            return await self.send(chat_id, f"{caption or ''}\n{url}".strip(), reply_to)

        file_id = await self._upload_file(chat_id, file_data, fname, ct)
@@ -603,19 +583,9 @@ class MattermostAdapter(BasePlatformAdapter):
        # For DMs, user_id is sufficient.  For channels, check for @mention.
        message_text = post.get("message", "")

-        # Mention-gating for non-DM channels.
-        # Config (env vars):
-        #   MATTERMOST_REQUIRE_MENTION: Require @mention in channels (default: true)
-        #   MATTERMOST_FREE_RESPONSE_CHANNELS: Channel IDs where bot responds without mention
+        # Mention-only mode: skip channel messages that don't @mention the bot.
+        # DMs (type "D") are always processed.
        if channel_type_raw != "D":
-            require_mention = os.getenv(
-                "MATTERMOST_REQUIRE_MENTION", "true"
-            ).lower() not in ("false", "0", "no")
-
-            free_channels_raw = os.getenv("MATTERMOST_FREE_RESPONSE_CHANNELS", "")
-            free_channels = {ch.strip() for ch in free_channels_raw.split(",") if ch.strip()}
-            is_free_channel = channel_id in free_channels
-
            mention_patterns = [
                f"@{self._bot_username}",
                f"@{self._bot_user_id}",
@@ -624,21 +594,13 @@ class MattermostAdapter(BasePlatformAdapter):
                pattern.lower() in message_text.lower()
                for pattern in mention_patterns
            )
-
-            if require_mention and not is_free_channel and not has_mention:
+            if not has_mention:
                logger.debug(
                    "Mattermost: skipping non-DM message without @mention (channel=%s)",
                    channel_id,
                )
                return

-            # Strip @mention from the message text so the agent sees clean input.
-            if has_mention:
-                for pattern in mention_patterns:
-                    message_text = re.sub(
-                        re.escape(pattern), "", message_text, flags=re.IGNORECASE
-                    ).strip()
-
        # Resolve sender info.
        sender_id = post.get("user_id", "")
        sender_name = data.get("sender_name", "").lstrip("@") or sender_id
@@ -22,7 +22,7 @@ import time
 from datetime import datetime, timezone
 from pathlib import Path
 from typing import Dict, List, Optional, Any
-from urllib.parse import quote, unquote
+from urllib.parse import unquote

 import httpx

@@ -184,8 +184,6 @@ class SignalAdapter(BasePlatformAdapter):
        self._recent_sent_timestamps: set = set()
        self._max_recent_timestamps = 50

-        self._phone_lock_identity: Optional[str] = None
-
        logger.info("Signal adapter initialized: url=%s account=%s groups=%s",
                     self.http_url, _redact_phone(self.account),
                     "enabled" if self.group_allow_from else "disabled")
@@ -200,29 +198,6 @@ class SignalAdapter(BasePlatformAdapter):
            logger.error("Signal: SIGNAL_HTTP_URL and SIGNAL_ACCOUNT are required")
            return False

-        # Acquire scoped lock to prevent duplicate Signal listeners for the same phone
-        try:
-            from gateway.status import acquire_scoped_lock
-
-            self._phone_lock_identity = self.account
-            acquired, existing = acquire_scoped_lock(
-                "signal-phone",
-                self._phone_lock_identity,
-                metadata={"platform": self.platform.value},
-            )
-            if not acquired:
-                owner_pid = existing.get("pid") if isinstance(existing, dict) else None
-                message = (
-                    "Another local Hermes gateway is already using this Signal account"
-                    + (f" (PID {owner_pid})." if owner_pid else ".")
-                    + " Stop the other gateway before starting a second Signal listener."
-                )
-                logger.error("Signal: %s", message)
-                self._set_fatal_error("signal_phone_lock", message, retryable=False)
-                return False
-        except Exception as e:
-            logger.warning("Signal: Could not acquire phone lock (non-fatal): %s", e)
-
        self.client = httpx.AsyncClient(timeout=30.0)

        # Health check — verify signal-cli daemon is reachable
@@ -270,14 +245,6 @@ class SignalAdapter(BasePlatformAdapter):
            await self.client.aclose()
            self.client = None

-        if self._phone_lock_identity:
-            try:
-                from gateway.status import release_scoped_lock
-                release_scoped_lock("signal-phone", self._phone_lock_identity)
-            except Exception as e:
-                logger.warning("Signal: Error releasing phone lock: %s", e, exc_info=True)
-            self._phone_lock_identity = None
-
        logger.info("Signal: disconnected")

    # ------------------------------------------------------------------
@@ -286,7 +253,7 @@ class SignalAdapter(BasePlatformAdapter):

    async def _sse_listener(self) -> None:
        """Listen for SSE events from signal-cli daemon."""
-        url = f"{self.http_url}/api/v1/events?account={quote(self.account, safe='')}"
+        url = f"{self.http_url}/api/v1/events?account={self.account}"
        backoff = SSE_RETRY_DELAY_INITIAL

        while self._running:
@@ -312,12 +279,6 @@ class SignalAdapter(BasePlatformAdapter):
                            line = line.strip()
                            if not line:
                                continue
-                            # SSE keepalive comments (":") prove the connection
-                            # is alive — update activity so the health monitor
-                            # doesn't report false idle warnings.
-                            if line.startswith(":"):
-                                self._last_sse_activity = time.time()
-                                continue
                            # Parse SSE data lines
                            if line.startswith("data:"):
                                data_str = line[5:].strip()
@@ -554,7 +515,7 @@ class SignalAdapter(BasePlatformAdapter):
        """Fetch an attachment via JSON-RPC and cache it. Returns (path, ext)."""
        result = await self._rpc("getAttachment", {
            "account": self.account,
-            "id": attachment_id,
+            "attachmentId": attachment_id,
        })

        if not result:
@@ -9,7 +9,6 @@ Uses slack-bolt (Python) with Socket Mode for:
 """

 import asyncio
-import json
 import logging
 import os
 import re
@@ -74,10 +73,6 @@ class SlackAdapter(BasePlatformAdapter):
        self._bot_user_id: Optional[str] = None
        self._user_name_cache: Dict[str, str] = {}  # user_id → display name
        self._socket_mode_task: Optional[asyncio.Task] = None
-        # Multi-workspace support
-        self._team_clients: Dict[str, AsyncWebClient] = {}   # team_id → WebClient
-        self._team_bot_user_ids: Dict[str, str] = {}          # team_id → bot_user_id
-        self._channel_team: Dict[str, str] = {}                # channel_id → team_id

    async def connect(self) -> bool:
        """Connect to Slack via Socket Mode."""
@@ -87,70 +82,23 @@ class SlackAdapter(BasePlatformAdapter):
            )
            return False

-        raw_token = self.config.token
+        bot_token = self.config.token
        app_token = os.getenv("SLACK_APP_TOKEN")

-        if not raw_token:
+        if not bot_token:
            logger.error("[Slack] SLACK_BOT_TOKEN not set")
            return False
        if not app_token:
            logger.error("[Slack] SLACK_APP_TOKEN not set")
            return False

-        # Support comma-separated bot tokens for multi-workspace
-        bot_tokens = [t.strip() for t in raw_token.split(",") if t.strip()]
-
-        # Also load tokens from OAuth token file
-        from hermes_constants import get_hermes_home
-        tokens_file = get_hermes_home() / "slack_tokens.json"
-        if tokens_file.exists():
-            try:
-                saved = json.loads(tokens_file.read_text(encoding="utf-8"))
-                for team_id, entry in saved.items():
-                    tok = entry.get("token", "") if isinstance(entry, dict) else ""
-                    if tok and tok not in bot_tokens:
-                        bot_tokens.append(tok)
-                        team_label = entry.get("team_name", team_id) if isinstance(entry, dict) else team_id
-                        logger.info("[Slack] Loaded saved token for workspace %s", team_label)
-            except Exception as e:
-                logger.warning("[Slack] Failed to read %s: %s", tokens_file, e)
-
        try:
-            # Acquire scoped lock to prevent duplicate app token usage
-            from gateway.status import acquire_scoped_lock
-            self._token_lock_identity = app_token
-            acquired, existing = acquire_scoped_lock('slack-app-token', app_token, metadata={'platform': 'slack'})
-            if not acquired:
-                owner_pid = existing.get('pid') if isinstance(existing, dict) else None
-                message = f'Slack app token already in use' + (f' (PID {owner_pid})' if owner_pid else '') + '. Stop the other gateway first.'
-                logger.error('[%s] %s', self.name, message)
-                self._set_fatal_error('slack_token_lock', message, retryable=False)
-                return False
+            self._app = AsyncApp(token=bot_token)

-            # First token is the primary — used for AsyncApp / Socket Mode
-            primary_token = bot_tokens[0]
-            self._app = AsyncApp(token=primary_token)
-
-            # Register each bot token and map team_id → client
-            for token in bot_tokens:
-                client = AsyncWebClient(token=token)
-                auth_response = await client.auth_test()
-                team_id = auth_response.get("team_id", "")
-                bot_user_id = auth_response.get("user_id", "")
-                bot_name = auth_response.get("user", "unknown")
-                team_name = auth_response.get("team", "unknown")
-
-                self._team_clients[team_id] = client
-                self._team_bot_user_ids[team_id] = bot_user_id
-
-                # First token sets the primary bot_user_id (backward compat)
-                if self._bot_user_id is None:
-                    self._bot_user_id = bot_user_id
-
-                logger.info(
-                    "[Slack] Authenticated as @%s in workspace %s (team: %s)",
-                    bot_name, team_name, team_id,
-                )
+            # Get our own bot user ID for mention detection
+            auth_response = await self._app.client.auth_test()
+            self._bot_user_id = auth_response.get("user_id")
+            bot_name = auth_response.get("user", "unknown")

            # Register message event handler
            @self._app.event("message")
@@ -175,10 +123,7 @@ class SlackAdapter(BasePlatformAdapter):
            self._socket_mode_task = asyncio.create_task(self._handler.start_async())

            self._running = True
-            logger.info(
-                "[Slack] Socket Mode connected (%d workspace(s))",
-                len(self._team_clients),
-            )
+            logger.info("[Slack] Connected as @%s (Socket Mode)", bot_name)
            return True

        except Exception as e:  # pragma: no cover - defensive logging
@@ -193,25 +138,8 @@ class SlackAdapter(BasePlatformAdapter):
            except Exception as e:  # pragma: no cover - defensive logging
                logger.warning("[Slack] Error while closing Socket Mode handler: %s", e, exc_info=True)
        self._running = False
-
-        # Release the token lock (use stored identity, not re-read env)
-        try:
-            from gateway.status import release_scoped_lock
-            if getattr(self, '_token_lock_identity', None):
-                release_scoped_lock('slack-app-token', self._token_lock_identity)
-                self._token_lock_identity = None
-        except Exception:
-            pass
-
        logger.info("[Slack] Disconnected")

-    def _get_client(self, chat_id: str) -> AsyncWebClient:
-        """Return the workspace-specific WebClient for a channel."""
-        team_id = self._channel_team.get(chat_id)
-        if team_id and team_id in self._team_clients:
-            return self._team_clients[team_id]
-        return self._app.client  # fallback to primary
-
    async def send(
        self,
        chat_id: str,
@@ -248,7 +176,7 @@ class SlackAdapter(BasePlatformAdapter):
                    if broadcast and i == 0:
                        kwargs["reply_broadcast"] = True

-                last_result = await self._get_client(chat_id).chat_postMessage(**kwargs)
+                last_result = await self._app.client.chat_postMessage(**kwargs)

            return SendResult(
                success=True,
@@ -270,7 +198,7 @@ class SlackAdapter(BasePlatformAdapter):
        if not self._app:
            return SendResult(success=False, error="Not connected")
        try:
-            await self._get_client(chat_id).chat_update(
+            await self._app.client.chat_update(
                channel=chat_id,
                ts=message_id,
                text=content,
@@ -304,7 +232,7 @@ class SlackAdapter(BasePlatformAdapter):
            return  # Can only set status in a thread context

        try:
-            await self._get_client(chat_id).assistant_threads_setStatus(
+            await self._app.client.assistant_threads_setStatus(
                channel_id=chat_id,
                thread_ts=thread_ts,
                status="is thinking...",
@@ -346,7 +274,7 @@ class SlackAdapter(BasePlatformAdapter):
        if not os.path.exists(file_path):
            raise FileNotFoundError(f"File not found: {file_path}")

-        result = await self._get_client(chat_id).files_upload_v2(
+        result = await self._app.client.files_upload_v2(
            channel=chat_id,
            file=file_path,
            filename=os.path.basename(file_path),
@@ -448,7 +376,7 @@ class SlackAdapter(BasePlatformAdapter):
        if not self._app:
            return False
        try:
-            await self._get_client(channel).reactions_add(
+            await self._app.client.reactions_add(
                channel=channel, timestamp=timestamp, name=emoji
            )
            return True
@@ -464,7 +392,7 @@ class SlackAdapter(BasePlatformAdapter):
        if not self._app:
            return False
        try:
-            await self._get_client(channel).reactions_remove(
+            await self._app.client.reactions_remove(
                channel=channel, timestamp=timestamp, name=emoji
            )
            return True
@@ -474,7 +402,7 @@ class SlackAdapter(BasePlatformAdapter):

    # ----- User identity resolution -----

-    async def _resolve_user_name(self, user_id: str, chat_id: str = "") -> str:
+    async def _resolve_user_name(self, user_id: str) -> str:
        """Resolve a Slack user ID to a display name, with caching."""
        if not user_id:
            return ""
@@ -485,8 +413,7 @@ class SlackAdapter(BasePlatformAdapter):
            return user_id

        try:
-            client = self._get_client(chat_id) if chat_id else self._app.client
-            result = await client.users_info(user=user_id)
+            result = await self._app.client.users_info(user=user_id)
            user = result.get("user", {})
            # Prefer display_name → real_name → user_id
            profile = user.get("profile", {})
@@ -550,7 +477,7 @@ class SlackAdapter(BasePlatformAdapter):
                response = await client.get(image_url)
                response.raise_for_status()

-            result = await self._get_client(chat_id).files_upload_v2(
+            result = await self._app.client.files_upload_v2(
                channel=chat_id,
                content=response.content,
                filename="image.png",
@@ -610,7 +537,7 @@ class SlackAdapter(BasePlatformAdapter):
            return SendResult(success=False, error=f"Video file not found: {video_path}")

        try:
-            result = await self._get_client(chat_id).files_upload_v2(
+            result = await self._app.client.files_upload_v2(
                channel=chat_id,
                file=video_path,
                filename=os.path.basename(video_path),
@@ -651,7 +578,7 @@ class SlackAdapter(BasePlatformAdapter):
        display_name = file_name or os.path.basename(file_path)

        try:
-            result = await self._get_client(chat_id).files_upload_v2(
+            result = await self._app.client.files_upload_v2(
                channel=chat_id,
                file=file_path,
                filename=display_name,
@@ -679,7 +606,7 @@ class SlackAdapter(BasePlatformAdapter):
            return {"name": chat_id, "type": "unknown"}

        try:
-            result = await self._get_client(chat_id).conversations_info(channel=chat_id)
+            result = await self._app.client.conversations_info(channel=chat_id)
            channel = result.get("channel", {})
            is_dm = channel.get("is_im", False)
            return {
@@ -712,11 +639,6 @@ class SlackAdapter(BasePlatformAdapter):
        user_id = event.get("user", "")
        channel_id = event.get("channel", "")
        ts = event.get("ts", "")
-        team_id = event.get("team", "")
-
-        # Track which workspace owns this channel
-        if team_id and channel_id:
-            self._channel_team[channel_id] = team_id

        # Determine if this is a DM or channel message
        channel_type = event.get("channel_type", "")
@@ -733,12 +655,11 @@ class SlackAdapter(BasePlatformAdapter):
            thread_ts = event.get("thread_ts") or ts  # ts fallback for channels

        # In channels, only respond if bot is mentioned
-        bot_uid = self._team_bot_user_ids.get(team_id, self._bot_user_id)
-        if not is_dm and bot_uid:
-            if f"<@{bot_uid}>" not in text:
+        if not is_dm and self._bot_user_id:
+            if f"<@{self._bot_user_id}>" not in text:
                return
            # Strip the bot mention from the text
-            text = text.replace(f"<@{bot_uid}>", "").strip()
+            text = text.replace(f"<@{self._bot_user_id}>", "").strip()

        # Determine message type
        msg_type = MessageType.TEXT
@@ -758,7 +679,7 @@ class SlackAdapter(BasePlatformAdapter):
                    if ext not in (".jpg", ".jpeg", ".png", ".gif", ".webp"):
                        ext = ".jpg"
                    # Slack private URLs require the bot token as auth header
-                    cached = await self._download_slack_file(url, ext, team_id=team_id)
+                    cached = await self._download_slack_file(url, ext)
                    media_urls.append(cached)
                    media_types.append(mimetype)
                    msg_type = MessageType.PHOTO
@@ -769,7 +690,7 @@ class SlackAdapter(BasePlatformAdapter):
                    ext = "." + mimetype.split("/")[-1].split(";")[0]
                    if ext not in (".ogg", ".mp3", ".wav", ".webm", ".m4a"):
                        ext = ".ogg"
-                    cached = await self._download_slack_file(url, ext, audio=True, team_id=team_id)
+                    cached = await self._download_slack_file(url, ext, audio=True)
                    media_urls.append(cached)
                    media_types.append(mimetype)
                    msg_type = MessageType.VOICE
@@ -800,7 +721,7 @@ class SlackAdapter(BasePlatformAdapter):
                        continue

                    # Download and cache
-                    raw_bytes = await self._download_slack_file_bytes(url, team_id=team_id)
+                    raw_bytes = await self._download_slack_file_bytes(url)
                    cached_path = cache_document_from_bytes(
                        raw_bytes, original_filename or f"document{ext}"
                    )
@@ -829,7 +750,7 @@ class SlackAdapter(BasePlatformAdapter):
                    logger.warning("[Slack] Failed to cache document from %s: %s", url, e, exc_info=True)

        # Resolve user display name (cached after first lookup)
-        user_name = await self._resolve_user_name(user_id, chat_id=channel_id)
+        user_name = await self._resolve_user_name(user_id)

        # Build source
        source = self.build_source(
@@ -866,11 +787,6 @@ class SlackAdapter(BasePlatformAdapter):
        text = command.get("text", "").strip()
        user_id = command.get("user_id", "")
        channel_id = command.get("channel_id", "")
-        team_id = command.get("team_id", "")
-
-        # Track which workspace owns this channel
-        if team_id and channel_id:
-            self._channel_team[channel_id] = team_id

        # Map subcommands to gateway commands — derived from central registry.
        # Also keep "compact" as a Slack-specific alias for /compress.
@@ -902,66 +818,34 @@ class SlackAdapter(BasePlatformAdapter):

        await self.handle_message(event)

-    async def _download_slack_file(self, url: str, ext: str, audio: bool = False, team_id: str = "") -> str:
-        """Download a Slack file using the bot token for auth, with retry."""
-        import asyncio
+    async def _download_slack_file(self, url: str, ext: str, audio: bool = False) -> str:
+        """Download a Slack file using the bot token for auth."""
        import httpx

-        bot_token = self._team_clients[team_id].token if team_id and team_id in self._team_clients else self.config.token
-        last_exc = None
-
+        bot_token = self.config.token
        async with httpx.AsyncClient(timeout=30.0, follow_redirects=True) as client:
-            for attempt in range(3):
-                try:
-                    response = await client.get(
-                        url,
-                        headers={"Authorization": f"Bearer {bot_token}"},
-                    )
-                    response.raise_for_status()
+            response = await client.get(
+                url,
+                headers={"Authorization": f"Bearer {bot_token}"},
+            )
+            response.raise_for_status()

-                    if audio:
-                        from gateway.platforms.base import cache_audio_from_bytes
-                        return cache_audio_from_bytes(response.content, ext)
-                    else:
-                        from gateway.platforms.base import cache_image_from_bytes
-                        return cache_image_from_bytes(response.content, ext)
-                except (httpx.TimeoutException, httpx.HTTPStatusError) as exc:
-                    last_exc = exc
-                    if isinstance(exc, httpx.HTTPStatusError) and exc.response.status_code < 429:
-                        raise
-                    if attempt < 2:
-                        logger.debug("Slack file download retry %d/2 for %s: %s",
-                                     attempt + 1, url[:80], exc)
-                        await asyncio.sleep(1.5 * (attempt + 1))
-                        continue
-                    raise
-        raise last_exc
+        if audio:
+            from gateway.platforms.base import cache_audio_from_bytes
+            return cache_audio_from_bytes(response.content, ext)
+        else:
+            from gateway.platforms.base import cache_image_from_bytes
+            return cache_image_from_bytes(response.content, ext)

-    async def _download_slack_file_bytes(self, url: str, team_id: str = "") -> bytes:
-        """Download a Slack file and return raw bytes, with retry."""
-        import asyncio
+    async def _download_slack_file_bytes(self, url: str) -> bytes:
+        """Download a Slack file and return raw bytes."""
        import httpx

-        bot_token = self._team_clients[team_id].token if team_id and team_id in self._team_clients else self.config.token
-        last_exc = None
-
+        bot_token = self.config.token
        async with httpx.AsyncClient(timeout=30.0, follow_redirects=True) as client:
-            for attempt in range(3):
-                try:
-                    response = await client.get(
-                        url,
-                        headers={"Authorization": f"Bearer {bot_token}"},
-                    )
-                    response.raise_for_status()
-                    return response.content
-                except (httpx.TimeoutException, httpx.HTTPStatusError) as exc:
-                    last_exc = exc
-                    if isinstance(exc, httpx.HTTPStatusError) and exc.response.status_code < 429:
-                        raise
-                    if attempt < 2:
-                        logger.debug("Slack file download retry %d/2 for %s: %s",
-                                     attempt + 1, url[:80], exc)
-                        await asyncio.sleep(1.5 * (attempt + 1))
-                        continue
-                    raise
-        raise last_exc
+            response = await client.get(
+                url,
+                headers={"Authorization": f"Bearer {bot_token}"},
+            )
+            response.raise_for_status()
+        return response.content
@@ -8,11 +8,10 @@ Uses python-telegram-bot library for:
 """

 import asyncio
-import json
 import logging
 import os
 import re
-from typing import Dict, List, Optional, Any
+from typing import Dict, Optional, Any

 logger = logging.getLogger(__name__)

@@ -26,7 +25,6 @@ try:
        filters,
    )
    from telegram.constants import ParseMode, ChatType
-    from telegram.request import HTTPXRequest
    TELEGRAM_AVAILABLE = True
 except ImportError:
    TELEGRAM_AVAILABLE = False
@@ -36,7 +34,6 @@ except ImportError:
    Application = Any
    CommandHandler = Any
    TelegramMessageHandler = Any
-    HTTPXRequest = Any
    filters = None
    ParseMode = None
    ChatType = None
@@ -62,11 +59,6 @@ from gateway.platforms.base import (
    cache_document_from_bytes,
    SUPPORTED_DOCUMENT_TYPES,
 )
-from gateway.platforms.telegram_network import (
-    TelegramFallbackTransport,
-    discover_fallback_ips,
-    parse_fallback_ip_env,
-)


 def check_telegram_requirements() -> bool:
@@ -123,8 +115,6 @@ class TelegramAdapter(BasePlatformAdapter):
        super().__init__(config, Platform.TELEGRAM)
        self._app: Optional[Application] = None
        self._bot: Optional[Bot] = None
-        self._webhook_mode: bool = False
-        self._mention_patterns = self._compile_mention_patterns()
        self._reply_to_mode: str = getattr(config, 'reply_to_mode', 'first') or 'first'
        # Buffer rapid/album photo updates so Telegram image bursts are handled
        # as a single MessageEvent instead of self-interrupting multiple turns.
@@ -148,13 +138,6 @@ class TelegramAdapter(BasePlatformAdapter):
        # DM Topics config from extra.dm_topics
        self._dm_topics_config: List[Dict[str, Any]] = self.config.extra.get("dm_topics", [])

-    def _fallback_ips(self) -> list[str]:
-        """Return validated fallback IPs from config (populated by _apply_env_overrides)."""
-        configured = self.config.extra.get("fallback_ips", []) if getattr(self.config, "extra", None) else []
-        if isinstance(configured, str):
-            configured = configured.split(",")
-        return parse_fallback_ip_env(",".join(str(v) for v in configured) if configured else None)
-
    @staticmethod
    def _looks_like_polling_conflict(error: Exception) -> bool:
        text = str(error).lower()
@@ -348,8 +331,7 @@ class TelegramAdapter(BasePlatformAdapter):
    def _persist_dm_topic_thread_id(self, chat_id: int, topic_name: str, thread_id: int) -> None:
        """Save a newly created thread_id back into config.yaml so it persists across restarts."""
        try:
-            from hermes_constants import get_hermes_home
-            config_path = get_hermes_home() / "config.yaml"
+            config_path = _Path.home() / ".hermes" / "config.yaml"
            if not config_path.exists():
                logger.warning("[%s] Config file not found at %s, cannot persist thread_id", self.name, config_path)
                return
@@ -459,19 +441,7 @@ class TelegramAdapter(BasePlatformAdapter):
                    self._persist_dm_topic_thread_id(int(chat_id), topic_name, thread_id)

    async def connect(self) -> bool:
-        """Connect to Telegram via polling or webhook.
-
-        By default, uses long polling (outbound connection to Telegram).
-        If ``TELEGRAM_WEBHOOK_URL`` is set, starts an HTTP webhook server
-        instead.  Webhook mode is useful for cloud deployments (Fly.io,
-        Railway) where inbound HTTP can wake a suspended machine.
-
-        Env vars for webhook mode::
-
-            TELEGRAM_WEBHOOK_URL    Public HTTPS URL (e.g. https://app.fly.dev/telegram)
-            TELEGRAM_WEBHOOK_PORT   Local listen port (default 8443)
-            TELEGRAM_WEBHOOK_SECRET Secret token for update verification
-        """
+        """Connect to Telegram and start polling for updates."""
        if not TELEGRAM_AVAILABLE:
            logger.error(
                "[%s] python-telegram-bot not installed. Run: pip install python-telegram-bot",
@@ -504,26 +474,7 @@ class TelegramAdapter(BasePlatformAdapter):
                return False

            # Build the application
-            builder = Application.builder().token(self.config.token)
-            fallback_ips = self._fallback_ips()
-            if not fallback_ips:
-                fallback_ips = await discover_fallback_ips()
-                logger.info(
-                    "[%s] Auto-discovered Telegram fallback IPs: %s",
-                    self.name,
-                    ", ".join(fallback_ips),
-                )
-            if fallback_ips:
-                logger.warning(
-                    "[%s] Telegram fallback IPs active: %s",
-                    self.name,
-                    ", ".join(fallback_ips),
-                )
-                transport = TelegramFallbackTransport(fallback_ips)
-                request = HTTPXRequest(httpx_kwargs={"transport": transport})
-                get_updates_request = HTTPXRequest(httpx_kwargs={"transport": transport})
-                builder = builder.request(request).get_updates_request(get_updates_request)
-            self._app = builder.build()
+            self._app = Application.builder().token(self.config.token).build()
            self._bot = self._app.bot
            
            # Register handlers
@@ -565,76 +516,37 @@ class TelegramAdapter(BasePlatformAdapter):
                    else:
                        raise
            await self._app.start()
+            loop = asyncio.get_running_loop()

-            # Decide between webhook and polling mode
-            webhook_url = os.getenv("TELEGRAM_WEBHOOK_URL", "").strip()
+            def _polling_error_callback(error: Exception) -> None:
+                if self._polling_error_task and not self._polling_error_task.done():
+                    return
+                if self._looks_like_polling_conflict(error):
+                    self._polling_error_task = loop.create_task(self._handle_polling_conflict(error))
+                elif self._looks_like_network_error(error):
+                    logger.warning("[%s] Telegram network error, scheduling reconnect: %s", self.name, error)
+                    self._polling_error_task = loop.create_task(self._handle_polling_network_error(error))
+                else:
+                    logger.error("[%s] Telegram polling error: %s", self.name, error, exc_info=True)

-            if webhook_url:
-                # ── Webhook mode ─────────────────────────────────────
-                # Telegram pushes updates to our HTTP endpoint.  This
-                # enables cloud platforms (Fly.io, Railway) to auto-wake
-                # suspended machines on inbound HTTP traffic.
-                webhook_port = int(os.getenv("TELEGRAM_WEBHOOK_PORT", "8443"))
-                webhook_secret = os.getenv("TELEGRAM_WEBHOOK_SECRET", "").strip() or None
-                from urllib.parse import urlparse
-                webhook_path = urlparse(webhook_url).path or "/telegram"
+            # Store reference for retry use in _handle_polling_conflict
+            self._polling_error_callback_ref = _polling_error_callback

-                await self._app.updater.start_webhook(
-                    listen="0.0.0.0",
-                    port=webhook_port,
-                    url_path=webhook_path,
-                    webhook_url=webhook_url,
-                    secret_token=webhook_secret,
-                    allowed_updates=Update.ALL_TYPES,
-                    drop_pending_updates=True,
-                )
-                self._webhook_mode = True
-                logger.info(
-                    "[%s] Webhook server listening on 0.0.0.0:%d%s",
-                    self.name, webhook_port, webhook_path,
-                )
-            else:
-                # ── Polling mode (default) ───────────────────────────
-                loop = asyncio.get_running_loop()
-
-                def _polling_error_callback(error: Exception) -> None:
-                    if self._polling_error_task and not self._polling_error_task.done():
-                        return
-                    if self._looks_like_polling_conflict(error):
-                        self._polling_error_task = loop.create_task(self._handle_polling_conflict(error))
-                    elif self._looks_like_network_error(error):
-                        logger.warning("[%s] Telegram network error, scheduling reconnect: %s", self.name, error)
-                        self._polling_error_task = loop.create_task(self._handle_polling_network_error(error))
-                    else:
-                        logger.error("[%s] Telegram polling error: %s", self.name, error, exc_info=True)
-
-                # Store reference for retry use in _handle_polling_conflict
-                self._polling_error_callback_ref = _polling_error_callback
-
-                await self._app.updater.start_polling(
-                    allowed_updates=Update.ALL_TYPES,
-                    drop_pending_updates=True,
-                    error_callback=_polling_error_callback,
-                )
+            await self._app.updater.start_polling(
+                allowed_updates=Update.ALL_TYPES,
+                drop_pending_updates=True,
+                error_callback=_polling_error_callback,
+            )
            
            # Register bot commands so Telegram shows a hint menu when users type /
            # List is derived from the central COMMAND_REGISTRY — adding a new
            # gateway command there automatically adds it to the Telegram menu.
            try:
                from telegram import BotCommand
-                from hermes_cli.commands import telegram_menu_commands
-                # Telegram allows up to 100 commands but has an undocumented
-                # payload size limit.  Skill descriptions are truncated to 40
-                # chars in telegram_menu_commands() to fit 100 commands safely.
-                menu_commands, hidden_count = telegram_menu_commands(max_commands=100)
+                from hermes_cli.commands import telegram_bot_commands
                await self._bot.set_my_commands([
-                    BotCommand(name, desc) for name, desc in menu_commands
+                    BotCommand(name, desc) for name, desc in telegram_bot_commands()
                ])
-                if hidden_count:
-                    logger.info(
-                        "[%s] Telegram menu: %d commands registered, %d hidden (over 100 limit). Use /commands for full list.",
-                        self.name, len(menu_commands), hidden_count,
-                    )
            except Exception as e:
                logger.warning(
                    "[%s] Could not register Telegram command menu: %s",
@@ -644,8 +556,7 @@ class TelegramAdapter(BasePlatformAdapter):
                )
            
            self._mark_connected()
-            mode = "webhook" if self._webhook_mode else "polling"
-            logger.info("[%s] Connected to Telegram (%s mode)", self.name, mode)
+            logger.info("[%s] Connected and polling for Telegram updates", self.name)

            # Set up DM topics (Bot API 9.4 — Private Chat Topics)
            # Runs after connection is established so the bot can call createForumTopic.
@@ -673,7 +584,7 @@ class TelegramAdapter(BasePlatformAdapter):
            return False
    
    async def disconnect(self) -> None:
-        """Stop polling/webhook, cancel pending album flushes, and disconnect."""
+        """Stop polling, cancel pending album flushes, and disconnect."""
        pending_media_group_tasks = list(self._media_group_tasks.values())
        for task in pending_media_group_tasks:
            task.cancel()
@@ -742,10 +653,6 @@ class TelegramAdapter(BasePlatformAdapter):
        if not self._bot:
            return SendResult(success=False, error="Not connected")
        
-        # Skip whitespace-only text to prevent Telegram 400 empty-text errors.
-        if not content or not content.strip():
-            return SendResult(success=True, message_id=None)
-        
        try:
            # Format and split message if needed
            formatted = self.format_message(content)
@@ -767,15 +674,9 @@ class TelegramAdapter(BasePlatformAdapter):
            except ImportError:
                _NetErr = OSError  # type: ignore[misc,assignment]

-            try:
-                from telegram.error import BadRequest as _BadReq
-            except ImportError:
-                _BadReq = None  # type: ignore[assignment,misc]
-
            for i, chunk in enumerate(chunks):
                should_thread = self._should_thread_reply(reply_to, i)
                reply_to_id = int(reply_to) if should_thread else None
-                effective_thread_id = int(thread_id) if thread_id else None

                msg = None
                for _send_attempt in range(3):
@@ -787,7 +688,7 @@ class TelegramAdapter(BasePlatformAdapter):
                                text=chunk,
                                parse_mode=ParseMode.MARKDOWN_V2,
                                reply_to_message_id=reply_to_id,
-                                message_thread_id=effective_thread_id,
+                                message_thread_id=int(thread_id) if thread_id else None,
                            )
                        except Exception as md_error:
                            # Markdown parsing failed, try plain text
@@ -799,40 +700,12 @@ class TelegramAdapter(BasePlatformAdapter):
                                    text=plain_chunk,
                                    parse_mode=None,
                                    reply_to_message_id=reply_to_id,
-                                    message_thread_id=effective_thread_id,
+                                    message_thread_id=int(thread_id) if thread_id else None,
                                )
                            else:
                                raise
                        break  # success
                    except _NetErr as send_err:
-                        # BadRequest is a subclass of NetworkError in
-                        # python-telegram-bot but represents permanent errors
-                        # (not transient network issues). Detect and handle
-                        # specific cases instead of blindly retrying.
-                        if _BadReq and isinstance(send_err, _BadReq):
-                            err_lower = str(send_err).lower()
-                            if "thread not found" in err_lower and effective_thread_id is not None:
-                                # Thread doesn't exist — retry without
-                                # message_thread_id so the message still
-                                # reaches the chat.
-                                logger.warning(
-                                    "[%s] Thread %s not found, retrying without message_thread_id",
-                                    self.name, effective_thread_id,
-                                )
-                                effective_thread_id = None
-                                continue
-                            if "message to be replied not found" in err_lower and reply_to_id is not None:
-                                # Original message was deleted before we
-                                # could reply — clear reply target and retry
-                                # so the response is still delivered.
-                                logger.warning(
-                                    "[%s] Reply target deleted, retrying without reply_to: %s",
-                                    self.name, send_err,
-                                )
-                                reply_to_id = None
-                                continue
-                            # Other BadRequest errors are permanent — don't retry
-                            raise
                        if _send_attempt < 2:
                            wait = 2 ** _send_attempt
                            logger.warning("[%s] Network error on send (attempt %d/3), retrying in %ds: %s",
@@ -1384,148 +1257,6 @@ class TelegramAdapter(BasePlatformAdapter):

        return text
    
-    # ── Group mention gating ──────────────────────────────────────────────
-
-    def _telegram_require_mention(self) -> bool:
-        """Return whether group chats should require an explicit bot trigger."""
-        configured = self.config.extra.get("require_mention")
-        if configured is not None:
-            if isinstance(configured, str):
-                return configured.lower() in ("true", "1", "yes", "on")
-            return bool(configured)
-        return os.getenv("TELEGRAM_REQUIRE_MENTION", "false").lower() in ("true", "1", "yes", "on")
-
-    def _telegram_free_response_chats(self) -> set[str]:
-        raw = self.config.extra.get("free_response_chats")
-        if raw is None:
-            raw = os.getenv("TELEGRAM_FREE_RESPONSE_CHATS", "")
-        if isinstance(raw, list):
-            return {str(part).strip() for part in raw if str(part).strip()}
-        return {part.strip() for part in str(raw).split(",") if part.strip()}
-
-    def _compile_mention_patterns(self) -> List[re.Pattern]:
-        """Compile optional regex wake-word patterns for group triggers."""
-        patterns = self.config.extra.get("mention_patterns")
-        if patterns is None:
-            raw = os.getenv("TELEGRAM_MENTION_PATTERNS", "").strip()
-            if raw:
-                try:
-                    loaded = json.loads(raw)
-                except Exception:
-                    loaded = [part.strip() for part in raw.splitlines() if part.strip()]
-                    if not loaded:
-                        loaded = [part.strip() for part in raw.split(",") if part.strip()]
-                patterns = loaded
-
-        if patterns is None:
-            return []
-        if isinstance(patterns, str):
-            patterns = [patterns]
-        if not isinstance(patterns, list):
-            logger.warning(
-                "[%s] telegram mention_patterns must be a list or string; got %s",
-                self.name,
-                type(patterns).__name__,
-            )
-            return []
-
-        compiled: List[re.Pattern] = []
-        for pattern in patterns:
-            if not isinstance(pattern, str) or not pattern.strip():
-                continue
-            try:
-                compiled.append(re.compile(pattern, re.IGNORECASE))
-            except re.error as exc:
-                logger.warning("[%s] Invalid Telegram mention pattern %r: %s", self.name, pattern, exc)
-        if compiled:
-            logger.info("[%s] Loaded %d Telegram mention pattern(s)", self.name, len(compiled))
-        return compiled
-
-    def _is_group_chat(self, message: Message) -> bool:
-        chat = getattr(message, "chat", None)
-        if not chat:
-            return False
-        chat_type = str(getattr(chat, "type", "")).split(".")[-1].lower()
-        return chat_type in ("group", "supergroup")
-
-    def _is_reply_to_bot(self, message: Message) -> bool:
-        if not self._bot or not getattr(message, "reply_to_message", None):
-            return False
-        reply_user = getattr(message.reply_to_message, "from_user", None)
-        return bool(reply_user and getattr(reply_user, "id", None) == getattr(self._bot, "id", None))
-
-    def _message_mentions_bot(self, message: Message) -> bool:
-        if not self._bot:
-            return False
-
-        bot_username = (getattr(self._bot, "username", None) or "").lstrip("@").lower()
-        bot_id = getattr(self._bot, "id", None)
-
-        def _iter_sources():
-            yield getattr(message, "text", None) or "", getattr(message, "entities", None) or []
-            yield getattr(message, "caption", None) or "", getattr(message, "caption_entities", None) or []
-
-        for source_text, entities in _iter_sources():
-            if bot_username and f"@{bot_username}" in source_text.lower():
-                return True
-            for entity in entities:
-                entity_type = str(getattr(entity, "type", "")).split(".")[-1].lower()
-                if entity_type == "mention" and bot_username:
-                    offset = int(getattr(entity, "offset", -1))
-                    length = int(getattr(entity, "length", 0))
-                    if offset < 0 or length <= 0:
-                        continue
-                    if source_text[offset:offset + length].strip().lower() == f"@{bot_username}":
-                        return True
-                elif entity_type == "text_mention":
-                    user = getattr(entity, "user", None)
-                    if user and getattr(user, "id", None) == bot_id:
-                        return True
-        return False
-
-    def _message_matches_mention_patterns(self, message: Message) -> bool:
-        if not self._mention_patterns:
-            return False
-        for candidate in (getattr(message, "text", None), getattr(message, "caption", None)):
-            if not candidate:
-                continue
-            for pattern in self._mention_patterns:
-                if pattern.search(candidate):
-                    return True
-        return False
-
-    def _clean_bot_trigger_text(self, text: Optional[str]) -> Optional[str]:
-        if not text or not self._bot or not getattr(self._bot, "username", None):
-            return text
-        username = re.escape(self._bot.username)
-        cleaned = re.sub(rf"(?i)@{username}\b[,:\-]*\s*", "", text).strip()
-        return cleaned or text
-
-    def _should_process_message(self, message: Message, *, is_command: bool = False) -> bool:
-        """Apply Telegram group trigger rules.
-
-        DMs remain unrestricted. Group/supergroup messages are accepted when:
-        - the chat is explicitly allowlisted in ``free_response_chats``
-        - ``require_mention`` is disabled
-        - the message is a command
-        - the message replies to the bot
-        - the bot is @mentioned
-        - the text/caption matches a configured regex wake-word pattern
-        """
-        if not self._is_group_chat(message):
-            return True
-        if str(getattr(getattr(message, "chat", None), "id", "")) in self._telegram_free_response_chats():
-            return True
-        if not self._telegram_require_mention():
-            return True
-        if is_command:
-            return True
-        if self._is_reply_to_bot(message):
-            return True
-        if self._message_mentions_bot(message):
-            return True
-        return self._message_matches_mention_patterns(message)
-
    async def _handle_text_message(self, update: Update, context: ContextTypes.DEFAULT_TYPE) -> None:
        """Handle incoming text messages.

@@ -1535,19 +1266,14 @@ class TelegramAdapter(BasePlatformAdapter):
        """
        if not update.message or not update.message.text:
            return
-        if not self._should_process_message(update.message):
-            return

        event = self._build_message_event(update.message, MessageType.TEXT)
-        event.text = self._clean_bot_trigger_text(event.text)
        self._enqueue_text_event(event)
    
    async def _handle_command(self, update: Update, context: ContextTypes.DEFAULT_TYPE) -> None:
        """Handle incoming command messages."""
        if not update.message or not update.message.text:
            return
-        if not self._should_process_message(update.message, is_command=True):
-            return
        
        event = self._build_message_event(update.message, MessageType.COMMAND)
        await self.handle_message(event)
@@ -1556,8 +1282,6 @@ class TelegramAdapter(BasePlatformAdapter):
        """Handle incoming location/venue pin messages."""
        if not update.message:
            return
-        if not self._should_process_message(update.message):
-            return

        msg = update.message
        venue = getattr(msg, "venue", None)
@@ -1701,8 +1425,6 @@ class TelegramAdapter(BasePlatformAdapter):
        """Handle incoming media messages, downloading images to local cache."""
        if not update.message:
            return
-        if not self._should_process_message(update.message):
-            return
        
        msg = update.message
        
@@ -1726,7 +1448,7 @@ class TelegramAdapter(BasePlatformAdapter):
        
        # Add caption as text
        if msg.caption:
-            event.text = self._clean_bot_trigger_text(msg.caption)
+            event.text = msg.caption
        
        # Handle stickers: describe via vision tool with caching
        if msg.sticker:
@@ -1978,8 +1700,7 @@ class TelegramAdapter(BasePlatformAdapter):
        recognized without a gateway restart.
        """
        try:
-            from hermes_constants import get_hermes_home
-            config_path = get_hermes_home() / "config.yaml"
+            config_path = _Path.home() / ".hermes" / "config.yaml"
            if not config_path.exists():
                return

@@ -1,248 +0,0 @@
-"""Telegram-specific network helpers.
-
-Provides a hostname-preserving fallback transport for networks where
-api.telegram.org resolves to an endpoint that is unreachable from the current
-host. The transport keeps the logical request host and TLS SNI as
-api.telegram.org while retrying the TCP connection against one or more fallback
-IPv4 addresses.
-"""
-
-from __future__ import annotations
-
-import asyncio
-import ipaddress
-import logging
-import os
-import socket
-from typing import Iterable, Optional
-
-import httpx
-
-logger = logging.getLogger(__name__)
-
-_TELEGRAM_API_HOST = "api.telegram.org"
-
-# DNS-over-HTTPS providers used to discover Telegram API IPs that may differ
-# from the (potentially unreachable) IP returned by the local system resolver.
-_DOH_TIMEOUT = 4.0  # seconds — bounded so connect() isn't noticeably delayed
-
-_DOH_PROVIDERS: list[dict] = [
-    {
-        "url": "https://dns.google/resolve",
-        "params": {"name": _TELEGRAM_API_HOST, "type": "A"},
-        "headers": {},
-    },
-    {
-        "url": "https://cloudflare-dns.com/dns-query",
-        "params": {"name": _TELEGRAM_API_HOST, "type": "A"},
-        "headers": {"Accept": "application/dns-json"},
-    },
-]
-
-# Last-resort IPs when DoH is also blocked.  These are stable Telegram Bot API
-# endpoints in the 149.154.160.0/20 block (same seed used by OpenClaw).
-_SEED_FALLBACK_IPS: list[str] = ["149.154.167.220"]
-
-
-def _resolve_proxy_url() -> str | None:
-    for key in ("HTTPS_PROXY", "HTTP_PROXY", "ALL_PROXY", "https_proxy", "http_proxy", "all_proxy"):
-        value = (os.environ.get(key) or "").strip()
-        if value:
-            return value
-    return None
-
-
-class TelegramFallbackTransport(httpx.AsyncBaseTransport):
-    """Retry Telegram Bot API requests via fallback IPs while preserving TLS/SNI.
-
-    Requests continue to target https://api.telegram.org/... logically, but on
-    connect failures the underlying TCP connection is retried against a known
-    reachable IP. This is effectively the programmatic equivalent of
-    ``curl --resolve api.telegram.org:443:<ip>``.
-    """
-
-    def __init__(self, fallback_ips: Iterable[str], **transport_kwargs):
-        self._fallback_ips = [ip for ip in dict.fromkeys(_normalize_fallback_ips(fallback_ips))]
-        proxy_url = _resolve_proxy_url()
-        if proxy_url and "proxy" not in transport_kwargs:
-            transport_kwargs["proxy"] = proxy_url
-        self._primary = httpx.AsyncHTTPTransport(**transport_kwargs)
-        self._fallbacks = {
-            ip: httpx.AsyncHTTPTransport(**transport_kwargs) for ip in self._fallback_ips
-        }
-        self._sticky_ip: Optional[str] = None
-        self._sticky_lock = asyncio.Lock()
-
-    async def handle_async_request(self, request: httpx.Request) -> httpx.Response:
-        if request.url.host != _TELEGRAM_API_HOST or not self._fallback_ips:
-            return await self._primary.handle_async_request(request)
-
-        sticky_ip = self._sticky_ip
-        attempt_order: list[Optional[str]] = [sticky_ip] if sticky_ip else [None]
-        for ip in self._fallback_ips:
-            if ip != sticky_ip:
-                attempt_order.append(ip)
-
-        last_error: Exception | None = None
-        for ip in attempt_order:
-            candidate = request if ip is None else _rewrite_request_for_ip(request, ip)
-            transport = self._primary if ip is None else self._fallbacks[ip]
-            try:
-                response = await transport.handle_async_request(candidate)
-                if ip is not None and self._sticky_ip != ip:
-                    async with self._sticky_lock:
-                        if self._sticky_ip != ip:
-                            self._sticky_ip = ip
-                            logger.warning(
-                                "[Telegram] Primary api.telegram.org path unreachable; using sticky fallback IP %s",
-                                ip,
-                            )
-                return response
-            except Exception as exc:
-                last_error = exc
-                if not _is_retryable_connect_error(exc):
-                    raise
-                if ip is None:
-                    logger.warning(
-                        "[Telegram] Primary api.telegram.org connection failed (%s); trying fallback IPs %s",
-                        exc,
-                        ", ".join(self._fallback_ips),
-                    )
-                    continue
-                logger.warning("[Telegram] Fallback IP %s failed: %s", ip, exc)
-                continue
-
-        assert last_error is not None
-        raise last_error
-
-    async def aclose(self) -> None:
-        await self._primary.aclose()
-        for transport in self._fallbacks.values():
-            await transport.aclose()
-
-
-def _normalize_fallback_ips(values: Iterable[str]) -> list[str]:
-    normalized: list[str] = []
-    for value in values:
-        raw = str(value).strip()
-        if not raw:
-            continue
-        try:
-            addr = ipaddress.ip_address(raw)
-        except ValueError:
-            logger.warning("Ignoring invalid Telegram fallback IP: %r", raw)
-            continue
-        if addr.version != 4:
-            logger.warning("Ignoring non-IPv4 Telegram fallback IP: %s", raw)
-            continue
-        if addr.is_private or addr.is_loopback or addr.is_link_local or addr.is_unspecified:
-            logger.warning("Ignoring private/internal Telegram fallback IP: %s", raw)
-            continue
-        normalized.append(str(addr))
-    return normalized
-
-
-def parse_fallback_ip_env(value: str | None) -> list[str]:
-    if not value:
-        return []
-    parts = [part.strip() for part in value.split(",")]
-    return _normalize_fallback_ips(parts)
-
-
-def _resolve_system_dns() -> set[str]:
-    """Return the IPv4 addresses that the OS resolver gives for api.telegram.org."""
-    try:
-        results = socket.getaddrinfo(_TELEGRAM_API_HOST, 443, socket.AF_INET)
-        return {addr[4][0] for addr in results}
-    except Exception:
-        return set()
-
-
-async def _query_doh_provider(
-    client: httpx.AsyncClient, provider: dict
-) -> list[str]:
-    """Query one DoH provider and return A-record IPs."""
-    try:
-        resp = await client.get(
-            provider["url"], params=provider["params"], headers=provider["headers"]
-        )
-        resp.raise_for_status()
-        data = resp.json()
-        ips: list[str] = []
-        for answer in data.get("Answer", []):
-            if answer.get("type") != 1:  # A record
-                continue
-            raw = answer.get("data", "").strip()
-            try:
-                ipaddress.ip_address(raw)
-                ips.append(raw)
-            except ValueError:
-                continue
-        return ips
-    except Exception as exc:
-        logger.debug("DoH query to %s failed: %s", provider["url"], exc)
-        return []
-
-
-async def discover_fallback_ips() -> list[str]:
-    """Auto-discover Telegram API IPs via DNS-over-HTTPS.
-
-    Resolves api.telegram.org through Google and Cloudflare DoH, collects all
-    unique IPs, and excludes the system-DNS-resolved IP (which is presumably
-    unreachable on this network).  Falls back to a hardcoded seed list when DoH
-    is also unavailable.
-    """
-    async with httpx.AsyncClient(timeout=httpx.Timeout(_DOH_TIMEOUT)) as client:
-        doh_tasks = [_query_doh_provider(client, p) for p in _DOH_PROVIDERS]
-        system_dns_task = asyncio.to_thread(_resolve_system_dns)
-        results = await asyncio.gather(system_dns_task, *doh_tasks, return_exceptions=True)
-
-    # results[0] = system DNS IPs (set), results[1:] = DoH IP lists
-    system_ips: set[str] = results[0] if isinstance(results[0], set) else set()
-
-    doh_ips: list[str] = []
-    for r in results[1:]:
-        if isinstance(r, list):
-            doh_ips.extend(r)
-
-    # Deduplicate preserving order, exclude system-DNS IPs
-    seen: set[str] = set()
-    candidates: list[str] = []
-    for ip in doh_ips:
-        if ip not in seen and ip not in system_ips:
-            seen.add(ip)
-            candidates.append(ip)
-
-    # Validate through existing normalization
-    validated = _normalize_fallback_ips(candidates)
-
-    if validated:
-        logger.debug("Discovered Telegram fallback IPs via DoH: %s", ", ".join(validated))
-        return validated
-
-    logger.info(
-        "DoH discovery yielded no new IPs (system DNS: %s); using seed fallback IPs %s",
-        ", ".join(system_ips) or "unknown",
-        ", ".join(_SEED_FALLBACK_IPS),
-    )
-    return list(_SEED_FALLBACK_IPS)
-
-
-def _rewrite_request_for_ip(request: httpx.Request, ip: str) -> httpx.Request:
-    original_host = request.url.host or _TELEGRAM_API_HOST
-    url = request.url.copy_with(host=ip)
-    headers = request.headers.copy()
-    headers["host"] = original_host
-    extensions = dict(request.extensions)
-    extensions["sni_hostname"] = original_host
-    return httpx.Request(
-        method=request.method,
-        url=url,
-        headers=headers,
-        stream=request.stream,
-        extensions=extensions,
-    )
-
-
-def _is_retryable_connect_error(exc: Exception) -> bool:
-    return isinstance(exc, (httpx.ConnectTimeout, httpx.ConnectError))
@@ -27,7 +27,6 @@ import hashlib
 import hmac
 import json
 import logging
-import os
 import re
 import subprocess
 import time
@@ -54,7 +53,6 @@ logger = logging.getLogger(__name__)
 DEFAULT_HOST = "0.0.0.0"
 DEFAULT_PORT = 8644
 _INSECURE_NO_AUTH = "INSECURE_NO_AUTH"
-_DYNAMIC_ROUTES_FILENAME = "webhook_subscriptions.json"


 def check_webhook_requirements() -> bool:
@@ -70,10 +68,7 @@ class WebhookAdapter(BasePlatformAdapter):
        self._host: str = config.extra.get("host", DEFAULT_HOST)
        self._port: int = int(config.extra.get("port", DEFAULT_PORT))
        self._global_secret: str = config.extra.get("secret", "")
-        self._static_routes: Dict[str, dict] = config.extra.get("routes", {})
-        self._dynamic_routes: Dict[str, dict] = {}
-        self._dynamic_routes_mtime: float = 0.0
-        self._routes: Dict[str, dict] = dict(self._static_routes)
+        self._routes: Dict[str, dict] = config.extra.get("routes", {})
        self._runner = None

        # Delivery info keyed by session chat_id — consumed by send()
@@ -101,9 +96,6 @@ class WebhookAdapter(BasePlatformAdapter):
    # ------------------------------------------------------------------

    async def connect(self) -> bool:
-        # Load agent-created subscriptions before validating
-        self._reload_dynamic_routes()
-
        # Validate routes at startup — secret is required per route
        for name, route in self._routes.items():
            secret = route.get("secret", self._global_secret)
@@ -118,17 +110,6 @@ class WebhookAdapter(BasePlatformAdapter):
        app.router.add_get("/health", self._handle_health)
        app.router.add_post("/webhooks/{route_name}", self._handle_webhook)

-        # Port conflict detection — fail fast if port is already in use
-        import socket as _socket
-        try:
-            with _socket.socket(_socket.AF_INET, _socket.SOCK_STREAM) as _s:
-                _s.settimeout(1)
-                _s.connect(('127.0.0.1', self._port))
-            logger.error('[webhook] Port %d already in use. Set a different port in config.yaml: platforms.webhook.port', self._port)
-            return False
-        except (ConnectionRefusedError, OSError):
-            pass  # port is free
-
        self._runner = web.AppRunner(app)
        await self._runner.setup()
        site = web.TCPSite(self._runner, self._host, self._port)
@@ -201,46 +182,8 @@ class WebhookAdapter(BasePlatformAdapter):
        """GET /health — simple health check."""
        return web.json_response({"status": "ok", "platform": "webhook"})

-    def _reload_dynamic_routes(self) -> None:
-        """Reload agent-created subscriptions from disk if the file changed."""
-        from pathlib import Path as _Path
-        hermes_home = _Path(
-            os.getenv("HERMES_HOME", str(_Path.home() / ".hermes"))
-        ).expanduser()
-        subs_path = hermes_home / _DYNAMIC_ROUTES_FILENAME
-        if not subs_path.exists():
-            if self._dynamic_routes:
-                self._dynamic_routes = {}
-                self._routes = dict(self._static_routes)
-                logger.debug("[webhook] Dynamic subscriptions file removed, cleared dynamic routes")
-            return
-        try:
-            mtime = subs_path.stat().st_mtime
-            if mtime <= self._dynamic_routes_mtime:
-                return  # No change
-            data = json.loads(subs_path.read_text(encoding="utf-8"))
-            if not isinstance(data, dict):
-                return
-            # Merge: static routes take precedence over dynamic ones
-            self._dynamic_routes = {
-                k: v for k, v in data.items()
-                if k not in self._static_routes
-            }
-            self._routes = {**self._dynamic_routes, **self._static_routes}
-            self._dynamic_routes_mtime = mtime
-            logger.info(
-                "[webhook] Reloaded %d dynamic route(s): %s",
-                len(self._dynamic_routes),
-                ", ".join(self._dynamic_routes.keys()) or "(none)",
-            )
-        except Exception as e:
-            logger.warning("[webhook] Failed to reload dynamic routes: %s", e)
-
    async def _handle_webhook(self, request: "web.Request") -> "web.Response":
        """POST /webhooks/{route_name} — receive and process a webhook event."""
-        # Hot-reload dynamic subscriptions on each request (mtime-gated, cheap)
-        self._reload_dynamic_routes()
-
        route_name = request.match_info.get("route_name", "")
        route_config = self._routes.get(route_name)

@@ -26,7 +26,6 @@ from pathlib import Path
 from typing import Dict, Optional, Any

 from hermes_cli.config import get_hermes_home
-from hermes_constants import get_hermes_dir

 logger = logging.getLogger(__name__)

@@ -135,15 +134,13 @@ class WhatsAppAdapter(BasePlatformAdapter):
        )
        self._session_path: Path = Path(config.extra.get(
            "session_path",
-            get_hermes_dir("platforms/whatsapp/session", "whatsapp/session")
+            get_hermes_home() / "whatsapp" / "session"
        ))
        self._reply_prefix: Optional[str] = config.extra.get("reply_prefix")
        self._message_queue: asyncio.Queue = asyncio.Queue()
        self._bridge_log_fh = None
        self._bridge_log: Optional[Path] = None
        self._poll_task: Optional[asyncio.Task] = None
-        self._http_session: Optional["aiohttp.ClientSession"] = None
-        self._session_lock_identity: Optional[str] = None
    
    async def connect(self) -> bool:
        """
@@ -162,29 +159,6 @@ class WhatsAppAdapter(BasePlatformAdapter):
        
        logger.info("[%s] Bridge found at %s", self.name, bridge_path)
        
-        # Acquire scoped lock to prevent duplicate sessions
-        try:
-            from gateway.status import acquire_scoped_lock
-
-            self._session_lock_identity = str(self._session_path)
-            acquired, existing = acquire_scoped_lock(
-                "whatsapp-session",
-                self._session_lock_identity,
-                metadata={"platform": self.platform.value},
-            )
-            if not acquired:
-                owner_pid = existing.get("pid") if isinstance(existing, dict) else None
-                message = (
-                    "Another local Hermes gateway is already using this WhatsApp session"
-                    + (f" (PID {owner_pid})." if owner_pid else ".")
-                    + " Stop the other gateway before starting a second WhatsApp bridge."
-                )
-                logger.error("[%s] %s", self.name, message)
-                self._set_fatal_error("whatsapp_session_lock", message, retryable=False)
-                return False
-        except Exception as e:
-            logger.warning("[%s] Could not acquire session lock (non-fatal): %s", self.name, e)
-
        # Auto-install npm dependencies if node_modules doesn't exist
        bridge_dir = bridge_path.parent
        if not (bridge_dir / "node_modules").exists():
@@ -225,7 +199,6 @@ class WhatsAppAdapter(BasePlatformAdapter):
                                print(f"[{self.name}] Using existing bridge (status: {bridge_status})")
                                self._mark_connected()
                                self._bridge_process = None  # Not managed by us
-                                self._http_session = aiohttp.ClientSession()
                                self._poll_task = asyncio.create_task(self._poll_messages())
                                return True
                            else:
@@ -331,9 +304,6 @@ class WhatsAppAdapter(BasePlatformAdapter):
                    print(f"[{self.name}]   Bridge log: {self._bridge_log}")
                    print(f"[{self.name}]   If session expired, re-pair: hermes whatsapp")
            
-            # Create a persistent HTTP session for all bridge communication
-            self._http_session = aiohttp.ClientSession()
-
            # Start message polling task
            self._poll_task = asyncio.create_task(self._poll_messages())
            
@@ -342,12 +312,6 @@ class WhatsAppAdapter(BasePlatformAdapter):
            return True
            
        except Exception as e:
-            if self._session_lock_identity:
-                try:
-                    from gateway.status import release_scoped_lock
-                    release_scoped_lock("whatsapp-session", self._session_lock_identity)
-                except Exception:
-                    pass
            logger.error("[%s] Failed to start bridge: %s", self.name, e, exc_info=True)
            self._close_bridge_log()
            return False
@@ -405,32 +369,10 @@ class WhatsAppAdapter(BasePlatformAdapter):
        else:
            # Bridge was not started by us, don't kill it
            print(f"[{self.name}] Disconnecting (external bridge left running)")
-
-        # Cancel the poll task explicitly
-        if self._poll_task and not self._poll_task.done():
-            self._poll_task.cancel()
-            try:
-                await self._poll_task
-            except (asyncio.CancelledError, Exception):
-                pass
-        self._poll_task = None
-
-        # Close the persistent HTTP session
-        if self._http_session and not self._http_session.closed:
-            await self._http_session.close()
-        self._http_session = None
-
-        if self._session_lock_identity:
-            try:
-                from gateway.status import release_scoped_lock
-                release_scoped_lock("whatsapp-session", self._session_lock_identity)
-            except Exception as e:
-                logger.warning("[%s] Error releasing WhatsApp session lock: %s", self.name, e, exc_info=True)
-
+        
        self._mark_disconnected()
        self._bridge_process = None
        self._close_bridge_log()
-        self._session_lock_identity = None
        print(f"[{self.name}] Disconnected")
    
    async def send(
@@ -441,7 +383,7 @@ class WhatsAppAdapter(BasePlatformAdapter):
        metadata: Optional[Dict[str, Any]] = None
    ) -> SendResult:
        """Send a message via the WhatsApp bridge."""
-        if not self._running or not self._http_session:
+        if not self._running:
            return SendResult(success=False, error="Not connected")
        bridge_exit = await self._check_managed_bridge_exit()
        if bridge_exit:
@@ -449,29 +391,36 @@ class WhatsAppAdapter(BasePlatformAdapter):
        
        try:
            import aiohttp
-
-            payload = {
-                "chatId": chat_id,
-                "message": content,
-            }
-            if reply_to:
-                payload["replyTo"] = reply_to
            
-            async with self._http_session.post(
-                f"http://127.0.0.1:{self._bridge_port}/send",
-                json=payload,
-                timeout=aiohttp.ClientTimeout(total=30)
-            ) as resp:
-                if resp.status == 200:
-                    data = await resp.json()
-                    return SendResult(
-                        success=True,
-                        message_id=data.get("messageId"),
-                        raw_response=data
-                    )
-                else:
-                    error = await resp.text()
-                    return SendResult(success=False, error=error)
+            async with aiohttp.ClientSession() as session:
+                payload = {
+                    "chatId": chat_id,
+                    "message": content,
+                }
+                if reply_to:
+                    payload["replyTo"] = reply_to
+                
+                async with session.post(
+                    f"http://127.0.0.1:{self._bridge_port}/send",
+                    json=payload,
+                    timeout=aiohttp.ClientTimeout(total=30)
+                ) as resp:
+                    if resp.status == 200:
+                        data = await resp.json()
+                        return SendResult(
+                            success=True,
+                            message_id=data.get("messageId"),
+                            raw_response=data
+                        )
+                    else:
+                        error = await resp.text()
+                        return SendResult(success=False, error=error)
+                        
+        except ImportError:
+            return SendResult(
+                success=False, 
+                error="aiohttp not installed. Run: pip install aiohttp"
+            )
        except Exception as e:
            return SendResult(success=False, error=str(e))

@@ -482,27 +431,28 @@ class WhatsAppAdapter(BasePlatformAdapter):
        content: str,
    ) -> SendResult:
        """Edit a previously sent message via the WhatsApp bridge."""
-        if not self._running or not self._http_session:
+        if not self._running:
            return SendResult(success=False, error="Not connected")
        bridge_exit = await self._check_managed_bridge_exit()
        if bridge_exit:
            return SendResult(success=False, error=bridge_exit)
        try:
            import aiohttp
-            async with self._http_session.post(
-                f"http://127.0.0.1:{self._bridge_port}/edit",
-                json={
-                    "chatId": chat_id,
-                    "messageId": message_id,
-                    "message": content,
-                },
-                timeout=aiohttp.ClientTimeout(total=15)
-            ) as resp:
-                if resp.status == 200:
-                    return SendResult(success=True, message_id=message_id)
-                else:
-                    error = await resp.text()
-                    return SendResult(success=False, error=error)
+            async with aiohttp.ClientSession() as session:
+                async with session.post(
+                    f"http://127.0.0.1:{self._bridge_port}/edit",
+                    json={
+                        "chatId": chat_id,
+                        "messageId": message_id,
+                        "message": content,
+                    },
+                    timeout=aiohttp.ClientTimeout(total=15)
+                ) as resp:
+                    if resp.status == 200:
+                        return SendResult(success=True, message_id=message_id)
+                    else:
+                        error = await resp.text()
+                        return SendResult(success=False, error=error)
        except Exception as e:
            return SendResult(success=False, error=str(e))

@@ -515,7 +465,7 @@ class WhatsAppAdapter(BasePlatformAdapter):
        file_name: Optional[str] = None,
    ) -> SendResult:
        """Send any media file via bridge /send-media endpoint."""
-        if not self._running or not self._http_session:
+        if not self._running:
            return SendResult(success=False, error="Not connected")
        bridge_exit = await self._check_managed_bridge_exit()
        if bridge_exit:
@@ -536,21 +486,22 @@ class WhatsAppAdapter(BasePlatformAdapter):
            if file_name:
                payload["fileName"] = file_name

-            async with self._http_session.post(
-                f"http://127.0.0.1:{self._bridge_port}/send-media",
-                json=payload,
-                timeout=aiohttp.ClientTimeout(total=120),
-            ) as resp:
-                if resp.status == 200:
-                    data = await resp.json()
-                    return SendResult(
-                        success=True,
-                        message_id=data.get("messageId"),
-                        raw_response=data,
-                    )
-                else:
-                    error = await resp.text()
-                    return SendResult(success=False, error=error)
+            async with aiohttp.ClientSession() as session:
+                async with session.post(
+                    f"http://127.0.0.1:{self._bridge_port}/send-media",
+                    json=payload,
+                    timeout=aiohttp.ClientTimeout(total=120),
+                ) as resp:
+                    if resp.status == 200:
+                        data = await resp.json()
+                        return SendResult(
+                            success=True,
+                            message_id=data.get("messageId"),
+                            raw_response=data,
+                        )
+                    else:
+                        error = await resp.text()
+                        return SendResult(success=False, error=error)

        except Exception as e:
            return SendResult(success=False, error=str(e))
@@ -575,7 +526,6 @@ class WhatsAppAdapter(BasePlatformAdapter):
        image_path: str,
        caption: Optional[str] = None,
        reply_to: Optional[str] = None,
-        **kwargs,
    ) -> SendResult:
        """Send a local image file natively via bridge."""
        return await self._send_media_to_bridge(chat_id, image_path, "image", caption)
@@ -586,7 +536,6 @@ class WhatsAppAdapter(BasePlatformAdapter):
        video_path: str,
        caption: Optional[str] = None,
        reply_to: Optional[str] = None,
-        **kwargs,
    ) -> SendResult:
        """Send a video natively via bridge — plays inline in WhatsApp."""
        return await self._send_media_to_bridge(chat_id, video_path, "video", caption)
@@ -598,7 +547,6 @@ class WhatsAppAdapter(BasePlatformAdapter):
        caption: Optional[str] = None,
        file_name: Optional[str] = None,
        reply_to: Optional[str] = None,
-        **kwargs,
    ) -> SendResult:
        """Send a document/file as a downloadable attachment via bridge."""
        return await self._send_media_to_bridge(
@@ -608,43 +556,45 @@ class WhatsAppAdapter(BasePlatformAdapter):

    async def send_typing(self, chat_id: str, metadata=None) -> None:
        """Send typing indicator via bridge."""
-        if not self._running or not self._http_session:
+        if not self._running:
            return
        if await self._check_managed_bridge_exit():
            return
        
        try:
            import aiohttp
-
-            await self._http_session.post(
-                f"http://127.0.0.1:{self._bridge_port}/typing",
-                json={"chatId": chat_id},
-                timeout=aiohttp.ClientTimeout(total=5)
-            )
+            
+            async with aiohttp.ClientSession() as session:
+                await session.post(
+                    f"http://127.0.0.1:{self._bridge_port}/typing",
+                    json={"chatId": chat_id},
+                    timeout=aiohttp.ClientTimeout(total=5)
+                )
        except Exception:
            pass  # Ignore typing indicator failures
    
    async def get_chat_info(self, chat_id: str) -> Dict[str, Any]:
        """Get information about a WhatsApp chat."""
-        if not self._running or not self._http_session:
+        if not self._running:
            return {"name": "Unknown", "type": "dm"}
        if await self._check_managed_bridge_exit():
            return {"name": chat_id, "type": "dm"}
        
        try:
            import aiohttp
-
-            async with self._http_session.get(
-                f"http://127.0.0.1:{self._bridge_port}/chat/{chat_id}",
-                timeout=aiohttp.ClientTimeout(total=10)
-            ) as resp:
-                if resp.status == 200:
-                    data = await resp.json()
-                    return {
-                        "name": data.get("name", chat_id),
-                        "type": "group" if data.get("isGroup") else "dm",
-                        "participants": data.get("participants", []),
-                    }
+            
+            async with aiohttp.ClientSession() as session:
+                async with session.get(
+                    f"http://127.0.0.1:{self._bridge_port}/chat/{chat_id}",
+                    timeout=aiohttp.ClientTimeout(total=10)
+                ) as resp:
+                    if resp.status == 200:
+                        data = await resp.json()
+                        return {
+                            "name": data.get("name", chat_id),
+                            "type": "group" if data.get("isGroup") else "dm",
+                            "participants": data.get("participants", []),
+                        }
        except Exception as e:
            logger.debug("Could not get WhatsApp chat info for %s: %s", chat_id, e)
        
@@ -652,26 +602,29 @@ class WhatsAppAdapter(BasePlatformAdapter):
    
    async def _poll_messages(self) -> None:
        """Poll the bridge for incoming messages."""
-        import aiohttp
-
+        try:
+            import aiohttp
+        except ImportError:
+            print(f"[{self.name}] aiohttp not installed, message polling disabled")
+            return
+        
        while self._running:
-            if not self._http_session:
-                break
            bridge_exit = await self._check_managed_bridge_exit()
            if bridge_exit:
                print(f"[{self.name}] {bridge_exit}")
                break
            try:
-                async with self._http_session.get(
-                    f"http://127.0.0.1:{self._bridge_port}/messages",
-                    timeout=aiohttp.ClientTimeout(total=30)
-                ) as resp:
-                    if resp.status == 200:
-                        messages = await resp.json()
-                        for msg_data in messages:
-                            event = await self._build_message_event(msg_data)
-                            if event:
-                                await self.handle_message(event)
+                async with aiohttp.ClientSession() as session:
+                    async with session.get(
+                        f"http://127.0.0.1:{self._bridge_port}/messages",
+                        timeout=aiohttp.ClientTimeout(total=30)
+                    ) as resp:
+                        if resp.status == 200:
+                            messages = await resp.json()
+                            for msg_data in messages:
+                                event = await self._build_message_event(msg_data)
+                                if event:
+                                    await self.handle_message(event)
            except asyncio.CancelledError:
                break
            except Exception as e:
@@ -762,16 +762,14 @@ class SessionStore:
            if session_key in self._entries:
                entry = self._entries[session_key]
                entry.updated_at = _now()
-                # Direct assignment — the gateway receives cumulative totals
-                # from the cached agent, not per-call deltas.
-                entry.input_tokens = input_tokens
-                entry.output_tokens = output_tokens
-                entry.cache_read_tokens = cache_read_tokens
-                entry.cache_write_tokens = cache_write_tokens
+                entry.input_tokens += input_tokens
+                entry.output_tokens += output_tokens
+                entry.cache_read_tokens += cache_read_tokens
+                entry.cache_write_tokens += cache_write_tokens
                if last_prompt_tokens is not None:
                    entry.last_prompt_tokens = last_prompt_tokens
                if estimated_cost_usd is not None:
-                    entry.estimated_cost_usd = estimated_cost_usd
+                    entry.estimated_cost_usd += estimated_cost_usd
                if cost_status:
                    entry.cost_status = cost_status
                entry.total_tokens = (
@@ -785,7 +783,7 @@ class SessionStore:

        if self._db and db_session_id:
            try:
-                self._db.set_token_counts(
+                self._db.update_token_counts(
                    db_session_id,
                    input_tokens=input_tokens,
                    output_tokens=output_tokens,
@@ -797,7 +795,6 @@ class SessionStore:
                    billing_provider=provider,
                    billing_base_url=base_url,
                    model=model,
-                    absolute=True,
                )
            except Exception as e:
                logger.debug("Session DB operation failed: %s", e)
@@ -958,17 +955,13 @@ class SessionStore:
            try:
                self._db.clear_messages(session_id)
                for msg in messages:
-                    role = msg.get("role", "unknown")
                    self._db.append_message(
                        session_id=session_id,
-                        role=role,
+                        role=msg.get("role", "unknown"),
                        content=msg.get("content"),
                        tool_name=msg.get("tool_name"),
                        tool_calls=msg.get("tool_calls"),
                        tool_call_id=msg.get("tool_call_id"),
-                        reasoning=msg.get("reasoning") if role == "assistant" else None,
-                        reasoning_details=msg.get("reasoning_details") if role == "assistant" else None,
-                        codex_reasoning_items=msg.get("codex_reasoning_items") if role == "assistant" else None,
                    )
            except Exception as e:
                logger.debug("Failed to rewrite transcript in DB: %s", e)
@@ -1,11 +1,12 @@
 #!/usr/bin/env python3
 """
-Hermes Agent CLI launcher.
+Hermes Agent CLI Launcher

-This wrapper should behave like the installed `hermes` command, including
-subcommands such as `gateway`, `cron`, and `doctor`.
+This is a convenience wrapper to launch the Hermes CLI.
+Usage: ./hermes [options]
 """

 if __name__ == "__main__":
-    from hermes_cli.main import main
-    main()
+    from cli import main
+    import fire
+    fire.Fire(main)
@@ -11,5 +11,5 @@ Provides subcommands for:
 - hermes cron          - Manage cron jobs
 """

-__version__ = "0.6.0"
-__release_date__ = "2026.3.30"
+__version__ = "0.4.0"
+__release_date__ = "2026.3.23"
@@ -160,7 +160,7 @@ PROVIDER_REGISTRY: Dict[str, ProviderConfig] = {
        id="alibaba",
        name="Alibaba Cloud (DashScope)",
        auth_type="api_key",
-        inference_base_url="https://dashscope-intl.aliyuncs.com/compatible-mode/v1",
+        inference_base_url="https://dashscope-intl.aliyuncs.com/apps/anthropic",
        api_key_env_vars=("DASHSCOPE_API_KEY",),
        base_url_env_var="DASHSCOPE_BASE_URL",
    ),
@@ -212,14 +212,6 @@ PROVIDER_REGISTRY: Dict[str, ProviderConfig] = {
        api_key_env_vars=("KILOCODE_API_KEY",),
        base_url_env_var="KILOCODE_BASE_URL",
    ),
-    "huggingface": ProviderConfig(
-        id="huggingface",
-        name="Hugging Face",
-        auth_type="api_key",
-        inference_base_url="https://router.huggingface.co/v1",
-        api_key_env_vars=("HF_TOKEN",),
-        base_url_env_var="HF_BASE_URL",
-    ),
 }


@@ -545,11 +537,7 @@ def _load_auth_store(auth_file: Optional[Path] = None) -> Dict[str, Any]:
    except Exception:
        return {"version": AUTH_STORE_VERSION, "providers": {}}

-    if isinstance(raw, dict) and (
-        isinstance(raw.get("providers"), dict)
-        or isinstance(raw.get("credential_pool"), dict)
-    ):
-        raw.setdefault("providers", {})
+    if isinstance(raw, dict) and isinstance(raw.get("providers"), dict):
        return raw

    # Migrate from PR's "systems" format if present
@@ -617,30 +605,6 @@ def _save_provider_state(auth_store: Dict[str, Any], provider_id: str, state: Di
    auth_store["active_provider"] = provider_id


-def read_credential_pool(provider_id: Optional[str] = None) -> Dict[str, Any]:
-    """Return the persisted credential pool, or one provider slice."""
-    auth_store = _load_auth_store()
-    pool = auth_store.get("credential_pool")
-    if not isinstance(pool, dict):
-        pool = {}
-    if provider_id is None:
-        return dict(pool)
-    provider_entries = pool.get(provider_id)
-    return list(provider_entries) if isinstance(provider_entries, list) else []
-
-
-def write_credential_pool(provider_id: str, entries: List[Dict[str, Any]]) -> Path:
-    """Persist one provider's credential pool under auth.json."""
-    with _auth_store_lock():
-        auth_store = _load_auth_store()
-        pool = auth_store.get("credential_pool")
-        if not isinstance(pool, dict):
-            pool = {}
-            auth_store["credential_pool"] = pool
-        pool[provider_id] = list(entries)
-        return _save_auth_store(auth_store)
-
-
 def get_provider_auth_state(provider_id: str) -> Optional[Dict[str, Any]]:
    """Return persisted auth state for a provider, or None."""
    auth_store = _load_auth_store()
@@ -666,25 +630,10 @@ def clear_provider_auth(provider_id: Optional[str] = None) -> bool:
            return False

        providers = auth_store.get("providers", {})
-        if not isinstance(providers, dict):
-            providers = {}
-            auth_store["providers"] = providers
-
-        pool = auth_store.get("credential_pool")
-        if not isinstance(pool, dict):
-            pool = {}
-            auth_store["credential_pool"] = pool
-
-        cleared = False
-        if target in providers:
-            del providers[target]
-            cleared = True
-        if target in pool:
-            del pool[target]
-            cleared = True
-
-        if not cleared:
+        if target not in providers:
            return False
+
+        del providers[target]
        if auth_store.get("active_provider") == target:
            auth_store["active_provider"] = None
        _save_auth_store(auth_store)
@@ -736,13 +685,8 @@ def resolve_provider(
        "github-copilot-acp": "copilot-acp", "copilot-acp-agent": "copilot-acp",
        "aigateway": "ai-gateway", "vercel": "ai-gateway", "vercel-ai-gateway": "ai-gateway",
        "opencode": "opencode-zen", "zen": "opencode-zen",
-        "hf": "huggingface", "hugging-face": "huggingface", "huggingface-hub": "huggingface",
        "go": "opencode-go", "opencode-go-sub": "opencode-go",
        "kilo": "kilocode", "kilo-code": "kilocode", "kilo-gateway": "kilocode",
-        # Local server aliases — route through the generic custom provider
-        "lmstudio": "custom", "lm-studio": "custom", "lm_studio": "custom",
-        "ollama": "custom", "vllm": "custom", "llamacpp": "custom",
-        "llama.cpp": "custom", "llama-cpp": "custom",
    }
    normalized = _PROVIDER_ALIASES.get(normalized, normalized)

@@ -789,12 +733,7 @@ def resolve_provider(
            if has_usable_secret(os.getenv(env_var, "")):
                return pid

-    raise AuthError(
-        "No inference provider configured. Run 'hermes model' to choose a "
-        "provider and model, or set an API key (OPENROUTER_API_KEY, "
-        "OPENAI_API_KEY, etc.) in ~/.hermes/.env.",
-        code="no_provider_configured",
-    )
+    return "openrouter"


 # =============================================================================
@@ -941,14 +880,15 @@ def _save_codex_tokens(tokens: Dict[str, str], last_refresh: str = None) -> None
        _save_auth_store(auth_store)


-def refresh_codex_oauth_pure(
-    access_token: str,
-    refresh_token: str,
-    *,
-    timeout_seconds: float = 20.0,
-) -> Dict[str, Any]:
-    """Refresh Codex OAuth tokens without mutating Hermes auth state."""
-    del access_token  # Access token is only used by callers to decide whether to refresh.
+def _refresh_codex_auth_tokens(
+    tokens: Dict[str, str],
+    timeout_seconds: float,
+) -> Dict[str, str]:
+    """Refresh Codex access token using the refresh token.
+    
+    Saves the new tokens to Hermes auth store automatically.
+    """
+    refresh_token = tokens.get("refresh_token")
    if not isinstance(refresh_token, str) or not refresh_token.strip():
        raise AuthError(
            "Codex auth is missing refresh_token. Run `hermes login` to re-authenticate.",
@@ -1003,8 +943,8 @@ def refresh_codex_oauth_pure(
            relogin_required=True,
        ) from exc

-    refreshed_access = refresh_payload.get("access_token")
-    if not isinstance(refreshed_access, str) or not refreshed_access.strip():
+    access_token = refresh_payload.get("access_token")
+    if not isinstance(access_token, str) or not access_token.strip():
        raise AuthError(
            "Codex token refresh response was missing access_token.",
            provider="openai-codex",
@@ -1012,33 +952,11 @@ def refresh_codex_oauth_pure(
            relogin_required=True,
        )

-    updated = {
-        "access_token": refreshed_access.strip(),
-        "refresh_token": refresh_token.strip(),
-        "last_refresh": datetime.now(timezone.utc).isoformat().replace("+00:00", "Z"),
-    }
+    updated_tokens = dict(tokens)
+    updated_tokens["access_token"] = access_token.strip()
    next_refresh = refresh_payload.get("refresh_token")
    if isinstance(next_refresh, str) and next_refresh.strip():
-        updated["refresh_token"] = next_refresh.strip()
-    return updated
-
-
-def _refresh_codex_auth_tokens(
-    tokens: Dict[str, str],
-    timeout_seconds: float,
-) -> Dict[str, str]:
-    """Refresh Codex access token using the refresh token.
-    
-    Saves the new tokens to Hermes auth store automatically.
-    """
-    refreshed = refresh_codex_oauth_pure(
-        str(tokens.get("access_token", "") or ""),
-        str(tokens.get("refresh_token", "") or ""),
-        timeout_seconds=timeout_seconds,
-    )
-    updated_tokens = dict(tokens)
-    updated_tokens["access_token"] = refreshed["access_token"]
-    updated_tokens["refresh_token"] = refreshed["refresh_token"]
+        updated_tokens["refresh_token"] = next_refresh.strip()

    _save_codex_tokens(updated_tokens)
    return updated_tokens
@@ -1377,122 +1295,6 @@ def _agent_key_is_usable(state: Dict[str, Any], min_ttl_seconds: int) -> bool:
    return not _is_expiring(state.get("agent_key_expires_at"), min_ttl_seconds)


-def refresh_nous_oauth_pure(
-    access_token: str,
-    refresh_token: str,
-    client_id: str,
-    portal_base_url: str,
-    inference_base_url: str,
-    *,
-    token_type: str = "Bearer",
-    scope: str = DEFAULT_NOUS_SCOPE,
-    obtained_at: Optional[str] = None,
-    expires_at: Optional[str] = None,
-    agent_key: Optional[str] = None,
-    agent_key_expires_at: Optional[str] = None,
-    min_key_ttl_seconds: int = DEFAULT_AGENT_KEY_MIN_TTL_SECONDS,
-    timeout_seconds: float = 15.0,
-    insecure: Optional[bool] = None,
-    ca_bundle: Optional[str] = None,
-    force_refresh: bool = False,
-    force_mint: bool = False,
-) -> Dict[str, Any]:
-    """Refresh Nous OAuth state without mutating auth.json."""
-    state: Dict[str, Any] = {
-        "access_token": access_token,
-        "refresh_token": refresh_token,
-        "client_id": client_id or DEFAULT_NOUS_CLIENT_ID,
-        "portal_base_url": (portal_base_url or DEFAULT_NOUS_PORTAL_URL).rstrip("/"),
-        "inference_base_url": (inference_base_url or DEFAULT_NOUS_INFERENCE_URL).rstrip("/"),
-        "token_type": token_type or "Bearer",
-        "scope": scope or DEFAULT_NOUS_SCOPE,
-        "obtained_at": obtained_at,
-        "expires_at": expires_at,
-        "agent_key": agent_key,
-        "agent_key_expires_at": agent_key_expires_at,
-        "tls": {
-            "insecure": bool(insecure),
-            "ca_bundle": ca_bundle,
-        },
-    }
-    verify = _resolve_verify(insecure=insecure, ca_bundle=ca_bundle, auth_state=state)
-    timeout = httpx.Timeout(timeout_seconds if timeout_seconds else 15.0)
-
-    with httpx.Client(timeout=timeout, headers={"Accept": "application/json"}, verify=verify) as client:
-        if force_refresh or _is_expiring(state.get("expires_at"), ACCESS_TOKEN_REFRESH_SKEW_SECONDS):
-            refreshed = _refresh_access_token(
-                client=client,
-                portal_base_url=state["portal_base_url"],
-                client_id=state["client_id"],
-                refresh_token=state["refresh_token"],
-            )
-            now = datetime.now(timezone.utc)
-            access_ttl = _coerce_ttl_seconds(refreshed.get("expires_in"))
-            state["access_token"] = refreshed["access_token"]
-            state["refresh_token"] = refreshed.get("refresh_token") or state["refresh_token"]
-            state["token_type"] = refreshed.get("token_type") or state.get("token_type") or "Bearer"
-            state["scope"] = refreshed.get("scope") or state.get("scope")
-            refreshed_url = _optional_base_url(refreshed.get("inference_base_url"))
-            if refreshed_url:
-                state["inference_base_url"] = refreshed_url
-            state["obtained_at"] = now.isoformat()
-            state["expires_in"] = access_ttl
-            state["expires_at"] = datetime.fromtimestamp(
-                now.timestamp() + access_ttl, tz=timezone.utc
-            ).isoformat()
-
-        if force_mint or not _agent_key_is_usable(state, max(60, int(min_key_ttl_seconds))):
-            mint_payload = _mint_agent_key(
-                client=client,
-                portal_base_url=state["portal_base_url"],
-                access_token=state["access_token"],
-                min_ttl_seconds=min_key_ttl_seconds,
-            )
-            now = datetime.now(timezone.utc)
-            state["agent_key"] = mint_payload.get("api_key")
-            state["agent_key_id"] = mint_payload.get("key_id")
-            state["agent_key_expires_at"] = mint_payload.get("expires_at")
-            state["agent_key_expires_in"] = mint_payload.get("expires_in")
-            state["agent_key_reused"] = bool(mint_payload.get("reused", False))
-            state["agent_key_obtained_at"] = now.isoformat()
-            minted_url = _optional_base_url(mint_payload.get("inference_base_url"))
-            if minted_url:
-                state["inference_base_url"] = minted_url
-
-    return state
-
-
-def refresh_nous_oauth_from_state(
-    state: Dict[str, Any],
-    *,
-    min_key_ttl_seconds: int = DEFAULT_AGENT_KEY_MIN_TTL_SECONDS,
-    timeout_seconds: float = 15.0,
-    force_refresh: bool = False,
-    force_mint: bool = False,
-) -> Dict[str, Any]:
-    """Refresh Nous OAuth from a state dict. Thin wrapper around refresh_nous_oauth_pure."""
-    tls = state.get("tls") or {}
-    return refresh_nous_oauth_pure(
-        state.get("access_token", ""),
-        state.get("refresh_token", ""),
-        state.get("client_id", "hermes-cli"),
-        state.get("portal_base_url", DEFAULT_NOUS_PORTAL_URL),
-        state.get("inference_base_url", DEFAULT_NOUS_INFERENCE_URL),
-        token_type=state.get("token_type", "Bearer"),
-        scope=state.get("scope", DEFAULT_NOUS_SCOPE),
-        obtained_at=state.get("obtained_at"),
-        expires_at=state.get("expires_at"),
-        agent_key=state.get("agent_key"),
-        agent_key_expires_at=state.get("agent_key_expires_at"),
-        min_key_ttl_seconds=min_key_ttl_seconds,
-        timeout_seconds=timeout_seconds,
-        insecure=tls.get("insecure"),
-        ca_bundle=tls.get("ca_bundle"),
-        force_refresh=force_refresh,
-        force_mint=force_mint,
-    )
-
-
 def resolve_nous_runtime_credentials(
    *,
    min_key_ttl_seconds: int = DEFAULT_AGENT_KEY_MIN_TTL_SECONDS,
@@ -2210,8 +2012,7 @@ def _login_openai_codex(args, pconfig: ProviderConfig) -> None:
    config_path = _update_config_for_provider("openai-codex", creds.get("base_url", DEFAULT_CODEX_BASE_URL))
    print()
    print("Login successful!")
-    from hermes_constants import display_hermes_home as _dhh
-    print(f"  Auth state: {_dhh()}/auth.json")
+    print("  Auth state: ~/.hermes/auth.json")
    print(f"  Config updated: {config_path} (model.provider=openai-codex)")


@@ -2360,36 +2161,34 @@ def _codex_device_code_login() -> Dict[str, Any]:
    }


-def _nous_device_code_login(
-    *,
-    portal_base_url: Optional[str] = None,
-    inference_base_url: Optional[str] = None,
-    client_id: Optional[str] = None,
-    scope: Optional[str] = None,
-    open_browser: bool = True,
-    timeout_seconds: float = 15.0,
-    insecure: bool = False,
-    ca_bundle: Optional[str] = None,
-    min_key_ttl_seconds: int = 5 * 60,
-) -> Dict[str, Any]:
-    """Run the Nous device-code flow and return full OAuth state without persisting."""
-    pconfig = PROVIDER_REGISTRY["nous"]
+def _login_nous(args, pconfig: ProviderConfig) -> None:
+    """Nous Portal device authorization flow."""
    portal_base_url = (
-        portal_base_url
+        getattr(args, "portal_url", None)
        or os.getenv("HERMES_PORTAL_BASE_URL")
        or os.getenv("NOUS_PORTAL_BASE_URL")
        or pconfig.portal_base_url
    ).rstrip("/")
    requested_inference_url = (
-        inference_base_url
+        getattr(args, "inference_url", None)
        or os.getenv("NOUS_INFERENCE_BASE_URL")
        or pconfig.inference_base_url
    ).rstrip("/")
-    client_id = client_id or pconfig.client_id
-    scope = scope or pconfig.scope
+    client_id = getattr(args, "client_id", None) or pconfig.client_id
+    scope = getattr(args, "scope", None) or pconfig.scope
+    open_browser = not getattr(args, "no_browser", False)
+    timeout_seconds = getattr(args, "timeout", None) or 15.0
    timeout = httpx.Timeout(timeout_seconds)
+
+    insecure = bool(getattr(args, "insecure", False))
+    ca_bundle = (
+        getattr(args, "ca_bundle", None)
+        or os.getenv("HERMES_CA_BUNDLE")
+        or os.getenv("SSL_CERT_FILE")
+    )
    verify: bool | str = False if insecure else (ca_bundle if ca_bundle else True)

+    # Skip browser open in SSH sessions
    if _is_remote_session():
        open_browser = False

@@ -2400,109 +2199,74 @@ def _nous_device_code_login(
    elif ca_bundle:
        print(f"TLS verification: custom CA bundle ({ca_bundle})")

-    with httpx.Client(timeout=timeout, headers={"Accept": "application/json"}, verify=verify) as client:
-        device_data = _request_device_code(
-            client=client,
-            portal_base_url=portal_base_url,
-            client_id=client_id,
-            scope=scope,
-        )
-
-        verification_url = str(device_data["verification_uri_complete"])
-        user_code = str(device_data["user_code"])
-        expires_in = int(device_data["expires_in"])
-        interval = int(device_data["interval"])
-
-        print()
-        print("To continue:")
-        print(f"  1. Open: {verification_url}")
-        print(f"  2. If prompted, enter code: {user_code}")
-
-        if open_browser:
-            opened = webbrowser.open(verification_url)
-            if opened:
-                print("  (Opened browser for verification)")
-            else:
-                print("  Could not open browser automatically — use the URL above.")
-
-        effective_interval = max(1, min(interval, DEVICE_AUTH_POLL_INTERVAL_CAP_SECONDS))
-        print(f"Waiting for approval (polling every {effective_interval}s)...")
-
-        token_data = _poll_for_token(
-            client=client,
-            portal_base_url=portal_base_url,
-            client_id=client_id,
-            device_code=str(device_data["device_code"]),
-            expires_in=expires_in,
-            poll_interval=interval,
-        )
-
-    now = datetime.now(timezone.utc)
-    token_expires_in = _coerce_ttl_seconds(token_data.get("expires_in", 0))
-    expires_at = now.timestamp() + token_expires_in
-    resolved_inference_url = (
-        _optional_base_url(token_data.get("inference_base_url"))
-        or requested_inference_url
-    )
-    if resolved_inference_url != requested_inference_url:
-        print(f"Using portal-provided inference URL: {resolved_inference_url}")
-
-    auth_state = {
-        "portal_base_url": portal_base_url,
-        "inference_base_url": resolved_inference_url,
-        "client_id": client_id,
-        "scope": token_data.get("scope") or scope,
-        "token_type": token_data.get("token_type", "Bearer"),
-        "access_token": token_data["access_token"],
-        "refresh_token": token_data.get("refresh_token"),
-        "obtained_at": now.isoformat(),
-        "expires_at": datetime.fromtimestamp(expires_at, tz=timezone.utc).isoformat(),
-        "expires_in": token_expires_in,
-        "tls": {
-            "insecure": verify is False,
-            "ca_bundle": verify if isinstance(verify, str) else None,
-        },
-        "agent_key": None,
-        "agent_key_id": None,
-        "agent_key_expires_at": None,
-        "agent_key_expires_in": None,
-        "agent_key_reused": None,
-        "agent_key_obtained_at": None,
-    }
-    return refresh_nous_oauth_from_state(
-        auth_state,
-        min_key_ttl_seconds=min_key_ttl_seconds,
-        timeout_seconds=timeout_seconds,
-        force_refresh=False,
-        force_mint=True,
-    )
-
-
-def _login_nous(args, pconfig: ProviderConfig) -> None:
-    """Nous Portal device authorization flow."""
-    timeout_seconds = getattr(args, "timeout", None) or 15.0
-    insecure = bool(getattr(args, "insecure", False))
-    ca_bundle = (
-        getattr(args, "ca_bundle", None)
-        or os.getenv("HERMES_CA_BUNDLE")
-        or os.getenv("SSL_CERT_FILE")
-    )
-
    try:
-        auth_state = _nous_device_code_login(
-            portal_base_url=getattr(args, "portal_url", None) or pconfig.portal_base_url,
-            inference_base_url=getattr(args, "inference_url", None) or pconfig.inference_base_url,
-            client_id=getattr(args, "client_id", None) or pconfig.client_id,
-            scope=getattr(args, "scope", None) or pconfig.scope,
-            open_browser=not getattr(args, "no_browser", False),
-            timeout_seconds=timeout_seconds,
-            insecure=insecure,
-            ca_bundle=ca_bundle,
-            min_key_ttl_seconds=5 * 60,
-        )
-        inference_base_url = auth_state["inference_base_url"]
-        verify: bool | str = False if insecure else (ca_bundle if ca_bundle else True)
+        with httpx.Client(timeout=timeout, headers={"Accept": "application/json"}, verify=verify) as client:
+            device_data = _request_device_code(
+                client=client, portal_base_url=portal_base_url,
+                client_id=client_id, scope=scope,
+            )

+            verification_url = str(device_data["verification_uri_complete"])
+            user_code = str(device_data["user_code"])
+            expires_in = int(device_data["expires_in"])
+            interval = int(device_data["interval"])
+
+            print()
+            print("To continue:")
+            print(f"  1. Open: {verification_url}")
+            print(f"  2. If prompted, enter code: {user_code}")
+
+            if open_browser:
+                opened = webbrowser.open(verification_url)
+                if opened:
+                    print("  (Opened browser for verification)")
+                else:
+                    print("  Could not open browser automatically — use the URL above.")
+
+            effective_interval = max(1, min(interval, DEVICE_AUTH_POLL_INTERVAL_CAP_SECONDS))
+            print(f"Waiting for approval (polling every {effective_interval}s)...")
+
+            token_data = _poll_for_token(
+                client=client, portal_base_url=portal_base_url,
+                client_id=client_id, device_code=str(device_data["device_code"]),
+                expires_in=expires_in, poll_interval=interval,
+            )
+
+        # Process token response
+        now = datetime.now(timezone.utc)
+        token_expires_in = _coerce_ttl_seconds(token_data.get("expires_in", 0))
+        expires_at = now.timestamp() + token_expires_in
+        inference_base_url = (
+            _optional_base_url(token_data.get("inference_base_url"))
+            or requested_inference_url
+        )
+        if inference_base_url != requested_inference_url:
+            print(f"Using portal-provided inference URL: {inference_base_url}")
+
+        auth_state = {
+            "portal_base_url": portal_base_url,
+            "inference_base_url": inference_base_url,
+            "client_id": client_id,
+            "scope": token_data.get("scope") or scope,
+            "token_type": token_data.get("token_type", "Bearer"),
+            "access_token": token_data["access_token"],
+            "refresh_token": token_data.get("refresh_token"),
+            "obtained_at": now.isoformat(),
+            "expires_at": datetime.fromtimestamp(expires_at, tz=timezone.utc).isoformat(),
+            "expires_in": token_expires_in,
+            "tls": {
+                "insecure": verify is False,
+                "ca_bundle": verify if isinstance(verify, str) else None,
+            },
+            "agent_key": None,
+            "agent_key_id": None,
+            "agent_key_expires_at": None,
+            "agent_key_expires_in": None,
+            "agent_key_reused": None,
+            "agent_key_obtained_at": None,
+        }
+
+        # Save auth state
        with _auth_store_lock():
            auth_store = _load_auth_store()
            _save_provider_state(auth_store, "nous", auth_state)
@@ -2514,29 +2278,34 @@ def _login_nous(args, pconfig: ProviderConfig) -> None:
        print(f"  Auth state: {saved_to}")
        print(f"  Config updated: {config_path} (model.provider=nous)")

+        # Mint an initial agent key and list available models
        try:
-            runtime_key = auth_state.get("agent_key") or auth_state.get("access_token")
+            runtime_creds = resolve_nous_runtime_credentials(
+                min_key_ttl_seconds=5 * 60,
+                timeout_seconds=timeout_seconds,
+                insecure=insecure, ca_bundle=ca_bundle,
+            )
+            runtime_key = runtime_creds.get("api_key")
+            runtime_base_url = runtime_creds.get("base_url") or inference_base_url
            if not isinstance(runtime_key, str) or not runtime_key:
-                raise AuthError(
-                    "No runtime API key available to fetch models",
-                    provider="nous",
-                    code="invalid_token",
-                )
+                raise AuthError("No runtime API key available to fetch models",
+                                provider="nous", code="invalid_token")

-            # Use curated model list (same as OpenRouter defaults) instead
-            # of the full /models dump which returns hundreds of models.
-            from hermes_cli.models import _PROVIDER_MODELS
-            model_ids = _PROVIDER_MODELS.get("nous", [])
+            model_ids = fetch_nous_models(
+                inference_base_url=runtime_base_url,
+                api_key=runtime_key,
+                timeout_seconds=timeout_seconds,
+                verify=verify,
+            )

            print()
            if model_ids:
-                print(f"Showing {len(model_ids)} curated models — use \"Enter custom model name\" for others.")
                selected_model = _prompt_model_selection(model_ids)
                if selected_model:
                    _save_model_choice(selected_model)
                    print(f"Default model set to: {selected_model}")
            else:
-                print("No curated models available for Nous Portal.")
+                print("No models were returned by the inference API.")
        except Exception as exc:
            message = format_auth_error(exc) if isinstance(exc, AuthError) else str(exc)
            print()
@@ -1,470 +0,0 @@
-"""Credential-pool auth subcommands."""
-
-from __future__ import annotations
-
-from getpass import getpass
-import math
-import time
-from types import SimpleNamespace
-import uuid
-
-from agent.credential_pool import (
-    AUTH_TYPE_API_KEY,
-    AUTH_TYPE_OAUTH,
-    CUSTOM_POOL_PREFIX,
-    SOURCE_MANUAL,
-    STATUS_EXHAUSTED,
-    STRATEGY_FILL_FIRST,
-    STRATEGY_ROUND_ROBIN,
-    STRATEGY_RANDOM,
-    STRATEGY_LEAST_USED,
-    SUPPORTED_POOL_STRATEGIES,
-    PooledCredential,
-    _normalize_custom_pool_name,
-    get_pool_strategy,
-    label_from_token,
-    list_custom_pool_providers,
-    load_pool,
-    _exhausted_ttl,
-)
-import hermes_cli.auth as auth_mod
-from hermes_cli.auth import PROVIDER_REGISTRY
-from hermes_constants import OPENROUTER_BASE_URL
-
-
-# Providers that support OAuth login in addition to API keys.
-_OAUTH_CAPABLE_PROVIDERS = {"anthropic", "nous", "openai-codex"}
-
-
-def _get_custom_provider_names() -> list:
-    """Return list of (display_name, pool_key) tuples for custom_providers in config."""
-    try:
-        from hermes_cli.config import load_config
-
-        config = load_config()
-    except Exception:
-        return []
-    custom_providers = config.get("custom_providers")
-    if not isinstance(custom_providers, list):
-        return []
-    result = []
-    for entry in custom_providers:
-        if not isinstance(entry, dict):
-            continue
-        name = entry.get("name")
-        if not isinstance(name, str) or not name.strip():
-            continue
-        pool_key = f"{CUSTOM_POOL_PREFIX}{_normalize_custom_pool_name(name)}"
-        result.append((name.strip(), pool_key))
-    return result
-
-
-def _resolve_custom_provider_input(raw: str) -> str | None:
-    """If raw input matches a custom_providers entry name (case-insensitive), return its pool key."""
-    normalized = (raw or "").strip().lower().replace(" ", "-")
-    if not normalized:
-        return None
-    # Direct match on 'custom:name' format
-    if normalized.startswith(CUSTOM_POOL_PREFIX):
-        return normalized
-    for display_name, pool_key in _get_custom_provider_names():
-        if _normalize_custom_pool_name(display_name) == normalized:
-            return pool_key
-    return None
-
-
-def _normalize_provider(provider: str) -> str:
-    normalized = (provider or "").strip().lower()
-    if normalized in {"or", "open-router"}:
-        return "openrouter"
-    # Check if it matches a custom provider name
-    custom_key = _resolve_custom_provider_input(normalized)
-    if custom_key:
-        return custom_key
-    return normalized
-
-
-def _provider_base_url(provider: str) -> str:
-    if provider == "openrouter":
-        return OPENROUTER_BASE_URL
-    if provider.startswith(CUSTOM_POOL_PREFIX):
-        from agent.credential_pool import _get_custom_provider_config
-
-        cp_config = _get_custom_provider_config(provider)
-        if cp_config:
-            return str(cp_config.get("base_url") or "").strip()
-        return ""
-    pconfig = PROVIDER_REGISTRY.get(provider)
-    return pconfig.inference_base_url if pconfig else ""
-
-
-def _oauth_default_label(provider: str, count: int) -> str:
-    return f"{provider}-oauth-{count}"
-
-
-def _api_key_default_label(count: int) -> str:
-    return f"api-key-{count}"
-
-
-def _display_source(source: str) -> str:
-    return source.split(":", 1)[1] if source.startswith("manual:") else source
-
-
-def _format_exhausted_status(entry) -> str:
-    if entry.last_status != STATUS_EXHAUSTED:
-        return ""
-    code = f" ({entry.last_error_code})" if entry.last_error_code else ""
-    if not entry.last_status_at:
-        return f" exhausted{code}"
-    remaining = max(0, int(math.ceil((entry.last_status_at + _exhausted_ttl(entry.last_error_code)) - time.time())))
-    if remaining <= 0:
-        return f" exhausted{code} (ready to retry)"
-    minutes, seconds = divmod(remaining, 60)
-    hours, minutes = divmod(minutes, 60)
-    if hours:
-        wait = f"{hours}h {minutes}m"
-    elif minutes:
-        wait = f"{minutes}m {seconds}s"
-    else:
-        wait = f"{seconds}s"
-    return f" exhausted{code} ({wait} left)"
-
-
-def auth_add_command(args) -> None:
-    provider = _normalize_provider(getattr(args, "provider", ""))
-    if provider not in PROVIDER_REGISTRY and provider != "openrouter" and not provider.startswith(CUSTOM_POOL_PREFIX):
-        raise SystemExit(f"Unknown provider: {provider}")
-
-    requested_type = str(getattr(args, "auth_type", "") or "").strip().lower()
-    if requested_type in {AUTH_TYPE_API_KEY, "api-key"}:
-        requested_type = AUTH_TYPE_API_KEY
-    if not requested_type:
-        if provider.startswith(CUSTOM_POOL_PREFIX):
-            requested_type = AUTH_TYPE_API_KEY
-        else:
-            requested_type = AUTH_TYPE_OAUTH if provider in {"anthropic", "nous", "openai-codex"} else AUTH_TYPE_API_KEY
-
-    pool = load_pool(provider)
-
-    if requested_type == AUTH_TYPE_API_KEY:
-        token = (getattr(args, "api_key", None) or "").strip()
-        if not token:
-            token = getpass("Paste your API key: ").strip()
-        if not token:
-            raise SystemExit("No API key provided.")
-        default_label = _api_key_default_label(len(pool.entries()) + 1)
-        label = (getattr(args, "label", None) or "").strip()
-        if not label:
-            label = input(f"Label (optional, default: {default_label}): ").strip() or default_label
-        entry = PooledCredential(
-            provider=provider,
-            id=uuid.uuid4().hex[:6],
-            label=label,
-            auth_type=AUTH_TYPE_API_KEY,
-            priority=0,
-            source=SOURCE_MANUAL,
-            access_token=token,
-            base_url=_provider_base_url(provider),
-        )
-        pool.add_entry(entry)
-        print(f'Added {provider} credential #{len(pool.entries())}: "{label}"')
-        return
-
-    if provider == "anthropic":
-        from agent import anthropic_adapter as anthropic_mod
-
-        creds = anthropic_mod.run_hermes_oauth_login_pure()
-        if not creds:
-            raise SystemExit("Anthropic OAuth login did not return credentials.")
-        label = (getattr(args, "label", None) or "").strip() or label_from_token(
-            creds["access_token"],
-            _oauth_default_label(provider, len(pool.entries()) + 1),
-        )
-        entry = PooledCredential(
-            provider=provider,
-            id=uuid.uuid4().hex[:6],
-            label=label,
-            auth_type=AUTH_TYPE_OAUTH,
-            priority=0,
-            source=f"{SOURCE_MANUAL}:hermes_pkce",
-            access_token=creds["access_token"],
-            refresh_token=creds.get("refresh_token"),
-            expires_at_ms=creds.get("expires_at_ms"),
-            base_url=_provider_base_url(provider),
-        )
-        pool.add_entry(entry)
-        print(f'Added {provider} OAuth credential #{len(pool.entries())}: "{entry.label}"')
-        return
-
-    if provider == "nous":
-        creds = auth_mod._nous_device_code_login(
-            portal_base_url=getattr(args, "portal_url", None),
-            inference_base_url=getattr(args, "inference_url", None),
-            client_id=getattr(args, "client_id", None),
-            scope=getattr(args, "scope", None),
-            open_browser=not getattr(args, "no_browser", False),
-            timeout_seconds=getattr(args, "timeout", None) or 15.0,
-            insecure=bool(getattr(args, "insecure", False)),
-            ca_bundle=getattr(args, "ca_bundle", None),
-            min_key_ttl_seconds=max(60, int(getattr(args, "min_key_ttl_seconds", 5 * 60))),
-        )
-        label = (getattr(args, "label", None) or "").strip() or label_from_token(
-            creds.get("access_token", ""),
-            _oauth_default_label(provider, len(pool.entries()) + 1),
-        )
-        entry = PooledCredential.from_dict(provider, {
-            **creds,
-            "label": label,
-            "auth_type": AUTH_TYPE_OAUTH,
-            "source": f"{SOURCE_MANUAL}:device_code",
-            "base_url": creds.get("inference_base_url"),
-        })
-        pool.add_entry(entry)
-        print(f'Added {provider} OAuth credential #{len(pool.entries())}: "{entry.label}"')
-        return
-
-    if provider == "openai-codex":
-        creds = auth_mod._codex_device_code_login()
-        label = (getattr(args, "label", None) or "").strip() or label_from_token(
-            creds["tokens"]["access_token"],
-            _oauth_default_label(provider, len(pool.entries()) + 1),
-        )
-        entry = PooledCredential(
-            provider=provider,
-            id=uuid.uuid4().hex[:6],
-            label=label,
-            auth_type=AUTH_TYPE_OAUTH,
-            priority=0,
-            source=f"{SOURCE_MANUAL}:device_code",
-            access_token=creds["tokens"]["access_token"],
-            refresh_token=creds["tokens"].get("refresh_token"),
-            base_url=creds.get("base_url"),
-            last_refresh=creds.get("last_refresh"),
-        )
-        pool.add_entry(entry)
-        print(f'Added {provider} OAuth credential #{len(pool.entries())}: "{entry.label}"')
-        return
-
-    raise SystemExit(f"`hermes auth add {provider}` is not implemented for auth type {requested_type} yet.")
-
-
-def auth_list_command(args) -> None:
-    provider_filter = _normalize_provider(getattr(args, "provider", "") or "")
-    if provider_filter:
-        providers = [provider_filter]
-    else:
-        providers = sorted({
-            *PROVIDER_REGISTRY.keys(),
-            "openrouter",
-            *list_custom_pool_providers(),
-        })
-    for provider in providers:
-        pool = load_pool(provider)
-        entries = pool.entries()
-        if not entries:
-            continue
-        current = pool.peek()
-        print(f"{provider} ({len(entries)} credentials):")
-        for idx, entry in enumerate(entries, start=1):
-            marker = "  "
-            if current is not None and entry.id == current.id:
-                marker = "← "
-            status = _format_exhausted_status(entry)
-            source = _display_source(entry.source)
-            print(f"  #{idx}  {entry.label:<20} {entry.auth_type:<7} {source}{status} {marker}".rstrip())
-        print()
-
-
-def auth_remove_command(args) -> None:
-    provider = _normalize_provider(getattr(args, "provider", ""))
-    index = int(getattr(args, "index"))
-    pool = load_pool(provider)
-    removed = pool.remove_index(index)
-    if removed is None:
-        raise SystemExit(f"No credential #{index} for provider {provider}.")
-    print(f"Removed {provider} credential #{index} ({removed.label})")
-
-
-def auth_reset_command(args) -> None:
-    provider = _normalize_provider(getattr(args, "provider", ""))
-    pool = load_pool(provider)
-    count = pool.reset_statuses()
-    print(f"Reset status on {count} {provider} credentials")
-
-
-def _interactive_auth() -> None:
-    """Interactive credential pool management when `hermes auth` is called bare."""
-    # Show current pool status first
-    print("Credential Pool Status")
-    print("=" * 50)
-
-    auth_list_command(SimpleNamespace(provider=None))
-    print()
-
-    # Main menu
-    choices = [
-        "Add a credential",
-        "Remove a credential",
-        "Reset cooldowns for a provider",
-        "Set rotation strategy for a provider",
-        "Exit",
-    ]
-    print("What would you like to do?")
-    for i, choice in enumerate(choices, 1):
-        print(f"  {i}. {choice}")
-
-    try:
-        raw = input("\nChoice: ").strip()
-    except (EOFError, KeyboardInterrupt):
-        return
-
-    if not raw or raw == str(len(choices)):
-        return
-
-    if raw == "1":
-        _interactive_add()
-    elif raw == "2":
-        _interactive_remove()
-    elif raw == "3":
-        _interactive_reset()
-    elif raw == "4":
-        _interactive_strategy()
-
-
-def _pick_provider(prompt: str = "Provider") -> str:
-    """Prompt for a provider name with auto-complete hints."""
-    known = sorted(set(list(PROVIDER_REGISTRY.keys()) + ["openrouter"]))
-    custom_names = _get_custom_provider_names()
-    if custom_names:
-        custom_display = [name for name, _key in custom_names]
-        print(f"\nKnown providers: {', '.join(known)}")
-        print(f"Custom endpoints: {', '.join(custom_display)}")
-    else:
-        print(f"\nKnown providers: {', '.join(known)}")
-    try:
-        raw = input(f"{prompt}: ").strip()
-    except (EOFError, KeyboardInterrupt):
-        raise SystemExit()
-    return _normalize_provider(raw)
-
-
-def _interactive_add() -> None:
-    provider = _pick_provider("Provider to add credential for")
-    if provider not in PROVIDER_REGISTRY and provider != "openrouter" and not provider.startswith(CUSTOM_POOL_PREFIX):
-        raise SystemExit(f"Unknown provider: {provider}")
-
-    # For OAuth-capable providers, ask which type
-    if provider in _OAUTH_CAPABLE_PROVIDERS:
-        print(f"\n{provider} supports both API keys and OAuth login.")
-        print("  1. API key (paste a key from the provider dashboard)")
-        print("  2. OAuth login (authenticate via browser)")
-        try:
-            type_choice = input("Type [1/2]: ").strip()
-        except (EOFError, KeyboardInterrupt):
-            return
-        if type_choice == "2":
-            auth_type = "oauth"
-        else:
-            auth_type = "api_key"
-    else:
-        auth_type = "api_key"
-
-    auth_add_command(SimpleNamespace(
-        provider=provider, auth_type=auth_type, label=None, api_key=None,
-        portal_url=None, inference_url=None, client_id=None, scope=None,
-        no_browser=False, timeout=None, insecure=False, ca_bundle=None,
-    ))
-
-
-def _interactive_remove() -> None:
-    provider = _pick_provider("Provider to remove credential from")
-    pool = load_pool(provider)
-    if not pool.has_credentials():
-        print(f"No credentials for {provider}.")
-        return
-
-    # Show entries with indices
-    for i, e in enumerate(pool.entries(), 1):
-        exhausted = _format_exhausted_status(e)
-        print(f"  #{i}  {e.label:25s} {e.auth_type:10s} {e.source}{exhausted}")
-
-    try:
-        raw = input("Remove # (or blank to cancel): ").strip()
-    except (EOFError, KeyboardInterrupt):
-        return
-    if not raw:
-        return
-
-    try:
-        index = int(raw)
-    except ValueError:
-        print("Invalid number.")
-        return
-
-    auth_remove_command(SimpleNamespace(provider=provider, index=index))
-
-
-def _interactive_reset() -> None:
-    provider = _pick_provider("Provider to reset cooldowns for")
-
-    auth_reset_command(SimpleNamespace(provider=provider))
-
-
-def _interactive_strategy() -> None:
-    provider = _pick_provider("Provider to set strategy for")
-    current = get_pool_strategy(provider)
-    strategies = [STRATEGY_FILL_FIRST, STRATEGY_ROUND_ROBIN, STRATEGY_LEAST_USED, STRATEGY_RANDOM]
-
-    print(f"\nCurrent strategy for {provider}: {current}")
-    print()
-    descriptions = {
-        STRATEGY_FILL_FIRST: "Use first key until exhausted, then next",
-        STRATEGY_ROUND_ROBIN: "Cycle through keys evenly",
-        STRATEGY_LEAST_USED: "Always pick the least-used key",
-        STRATEGY_RANDOM: "Random selection",
-    }
-    for i, s in enumerate(strategies, 1):
-        marker = " ←" if s == current else ""
-        print(f"  {i}. {s:15s} — {descriptions.get(s, '')}{marker}")
-
-    try:
-        raw = input("\nStrategy [1-4]: ").strip()
-    except (EOFError, KeyboardInterrupt):
-        return
-    if not raw:
-        return
-
-    try:
-        idx = int(raw) - 1
-        strategy = strategies[idx]
-    except (ValueError, IndexError):
-        print("Invalid choice.")
-        return
-
-    from hermes_cli.config import load_config, save_config
-    cfg = load_config()
-    pool_strategies = cfg.get("credential_pool_strategies") or {}
-    if not isinstance(pool_strategies, dict):
-        pool_strategies = {}
-    pool_strategies[provider] = strategy
-    cfg["credential_pool_strategies"] = pool_strategies
-    save_config(cfg)
-    print(f"Set {provider} strategy to: {strategy}")
-
-
-def auth_command(args) -> None:
-    action = getattr(args, "auth_action", "")
-    if action == "add":
-        auth_add_command(args)
-        return
-    if action == "list":
-        auth_list_command(args)
-        return
-    if action == "remove":
-        auth_remove_command(args)
-        return
-    if action == "reset":
-        auth_reset_command(args)
-        return
-    # No subcommand — launch interactive mode
-    _interactive_auth()
@@ -258,7 +258,7 @@ def build_welcome_banner(console: Console, model: str, cwd: str,
        get_toolset_for_tool: Callable to map tool name -> toolset name.
        context_length: Model's context window size in tokens.
    """
-    from model_tools import check_tool_availability, TOOLSET_REQUIREMENTS
+    from model_tools import check_tool_availability
    if get_toolset_for_tool is None:
        from model_tools import get_toolset_for_tool

@@ -267,18 +267,8 @@ def build_welcome_banner(console: Console, model: str, cwd: str,

    _, unavailable_toolsets = check_tool_availability(quiet=True)
    disabled_tools = set()
-    # Tools whose toolset has a check_fn are lazy-initialized (e.g. honcho,
-    # homeassistant) — they show as unavailable at banner time because the
-    # check hasn't run yet, but they aren't misconfigured.
-    lazy_tools = set()
    for item in unavailable_toolsets:
-        toolset_name = item.get("name", "")
-        ts_req = TOOLSET_REQUIREMENTS.get(toolset_name, {})
-        tools_in_ts = item.get("tools", [])
-        if ts_req.get("check_fn"):
-            lazy_tools.update(tools_in_ts)
-        else:
-            disabled_tools.update(tools_in_ts)
+        disabled_tools.update(item.get("tools", []))

    layout_table = Table.grid(padding=(0, 2))
    layout_table.add_column("left", justify="center")
@@ -338,8 +328,6 @@ def build_welcome_banner(console: Console, model: str, cwd: str,
        for name in sorted(tool_names):
            if name in disabled_tools:
                colored_names.append(f"[red]{name}[/]")
-            elif name in lazy_tools:
-                colored_names.append(f"[yellow]{name}[/]")
            else:
                colored_names.append(f"[{text}]{name}[/]")

@@ -359,8 +347,6 @@ def build_welcome_banner(console: Console, model: str, cwd: str,
                    colored_names.append("[dim]...[/]")
                elif name in disabled_tools:
                    colored_names.append(f"[red]{name}[/]")
-                elif name in lazy_tools:
-                    colored_names.append(f"[yellow]{name}[/]")
                else:
                    colored_names.append(f"[{text}]{name}[/]")
            tools_str = ", ".join(colored_names)
@@ -417,26 +403,16 @@ def build_welcome_banner(console: Console, model: str, cwd: str,
    if mcp_connected:
        summary_parts.append(f"{mcp_connected} MCP servers")
    summary_parts.append("/help for commands")
-    # Show active profile name when not 'default'
-    try:
-        from hermes_cli.profiles import get_active_profile_name
-        _profile_name = get_active_profile_name()
-        if _profile_name and _profile_name != "default":
-            right_lines.append(f"[bold {accent}]Profile:[/] [{text}]{_profile_name}[/]")
-    except Exception:
-        pass  # Never break the banner over a profiles.py bug
-
    right_lines.append(f"[dim {dim}]{' · '.join(summary_parts)}[/]")

    # Update check — use prefetched result if available
    try:
        behind = get_update_result(timeout=0.5)
        if behind and behind > 0:
-            from hermes_cli.config import recommended_update_command
            commits_word = "commit" if behind == 1 else "commits"
            right_lines.append(
                f"[bold yellow]⚠ {behind} {commits_word} behind[/]"
-                f"[dim yellow] — run [bold]{recommended_update_command()}[/bold] to update[/]"
+                f"[dim yellow] — run [bold]hermes update[/bold] to update[/]"
            )
    except Exception:
        pass  # Never break the banner over an update check
@@ -12,7 +12,6 @@ import getpass

 from hermes_cli.banner import cprint, _DIM, _RST
 from hermes_cli.config import save_env_value_secure
-from hermes_constants import display_hermes_home


 def clarify_callback(cli, question, choices):
@@ -132,8 +131,7 @@ def prompt_for_secret(cli, var_name: str, prompt: str, metadata=None) -> dict:
            }

        stored = save_env_value_secure(var_name, value)
-        _dhh = display_hermes_home()
-        cprint(f"\n{_DIM}  ✓ Stored secret in {_dhh}/.env as {var_name}{_RST}")
+        cprint(f"\n{_DIM}  ✓ Stored secret in ~/.hermes/.env as {var_name}{_RST}")
        return {
            **stored,
            "skipped": False,
@@ -185,8 +183,7 @@ def prompt_for_secret(cli, var_name: str, prompt: str, metadata=None) -> dict:
                }

            stored = save_env_value_secure(var_name, value)
-            _dhh = display_hermes_home()
-            cprint(f"\n{_DIM}  ✓ Stored secret in {_dhh}/.env as {var_name}{_RST}")
+            cprint(f"\n{_DIM}  ✓ Stored secret in ~/.hermes/.env as {var_name}{_RST}")
            return {
                **stored,
                "skipped": False,
@@ -241,8 +238,7 @@ def approval_callback(cli, command: str, description: str) -> str:
        lock = cli._approval_lock

    with lock:
-        from cli import CLI_CONFIG
-        timeout = CLI_CONFIG.get("approvals", {}).get("timeout", 60)
+        timeout = 60
        response_queue = queue.Queue()
        choices = ["once", "session", "always", "deny"]
        if len(command) > 70:
@@ -5,7 +5,6 @@ toggleable list of items.  Falls back to a numbered text UI when
 curses is unavailable (Windows without curses, piped stdin, etc.).
 """

-import sys
 from typing import List, Set

 from hermes_cli.colors import Colors, color
@@ -27,10 +26,6 @@ def curses_checklist(
        The indices the user confirmed as checked.  On cancel (ESC/q),
        returns ``pre_selected`` unchanged.
    """
-    # Safety: return defaults when stdin is not a terminal.
-    if not sys.stdin.isatty():
-        return set(pre_selected)
-
    try:
        import curses
        selected = set(pre_selected)
@@ -4,19 +4,14 @@ Usage:
    hermes claw migrate              # Interactive migration from ~/.openclaw
    hermes claw migrate --dry-run    # Preview what would be migrated
    hermes claw migrate --preset full --overwrite  # Full migration, overwrite conflicts
-    hermes claw cleanup              # Archive leftover OpenClaw directories
-    hermes claw cleanup --dry-run    # Preview what would be archived
 """

 import importlib.util
 import logging
-import shutil
 import sys
-from datetime import datetime
 from pathlib import Path

 from hermes_cli.config import get_hermes_home, get_config_path, load_config, save_config
-from hermes_constants import get_optional_skills_dir
 from hermes_cli.setup import (
    Colors,
    color,
@@ -24,7 +19,6 @@ from hermes_cli.setup import (
    print_info,
    print_success,
    print_error,
-    print_warning,
    prompt_yes_no,
 )

@@ -33,7 +27,8 @@ logger = logging.getLogger(__name__)
 PROJECT_ROOT = Path(__file__).parent.parent.resolve()

 _OPENCLAW_SCRIPT = (
-    get_optional_skills_dir(PROJECT_ROOT / "optional-skills")
+    PROJECT_ROOT
+    / "optional-skills"
    / "migration"
    / "openclaw-migration"
    / "scripts"
@@ -50,18 +45,6 @@ _OPENCLAW_SCRIPT_INSTALLED = (
    / "openclaw_to_hermes.py"
 )

-# Known OpenClaw directory names (current + legacy)
-_OPENCLAW_DIR_NAMES = (".openclaw", ".clawdbot", ".moldbot")
-
-# State files commonly found in OpenClaw workspace directories that cause
-# confusion after migration (the agent discovers them and writes to them)
-_WORKSPACE_STATE_GLOBS = (
-    "*/todo.json",
-    "*/sessions/*",
-    "*/memory/*.json",
-    "*/logs/*",
-)
-

 def _find_migration_script() -> Path | None:
    """Find the openclaw_to_hermes.py script in known locations."""
@@ -88,105 +71,24 @@ def _load_migration_module(script_path: Path):
    return mod


-def _find_openclaw_dirs() -> list[Path]:
-    """Find all OpenClaw directories on disk."""
-    found = []
-    for name in _OPENCLAW_DIR_NAMES:
-        candidate = Path.home() / name
-        if candidate.is_dir():
-            found.append(candidate)
-    return found
-
-
-def _scan_workspace_state(source_dir: Path) -> list[tuple[Path, str]]:
-    """Scan an OpenClaw directory for workspace state files that cause confusion.
-
-    Returns a list of (path, description) tuples.
-    """
-    findings: list[tuple[Path, str]] = []
-
-    # Direct state files in the root
-    for name in ("todo.json", "sessions", "logs"):
-        candidate = source_dir / name
-        if candidate.exists():
-            kind = "directory" if candidate.is_dir() else "file"
-            findings.append((candidate, f"Root {kind}: {name}"))
-
-    # State files inside workspace directories
-    for child in sorted(source_dir.iterdir()):
-        if not child.is_dir() or child.name.startswith("."):
-            continue
-        # Check for workspace-like subdirectories
-        for state_name in ("todo.json", "sessions", "logs", "memory"):
-            state_path = child / state_name
-            if state_path.exists():
-                kind = "directory" if state_path.is_dir() else "file"
-                rel = state_path.relative_to(source_dir)
-                findings.append((state_path, f"Workspace {kind}: {rel}"))
-
-    return findings
-
-
-def _archive_directory(source_dir: Path, dry_run: bool = False) -> Path:
-    """Rename an OpenClaw directory to .pre-migration.
-
-    Returns the archive path.
-    """
-    timestamp = datetime.now().strftime("%Y%m%d")
-    archive_name = f"{source_dir.name}.pre-migration"
-    archive_path = source_dir.parent / archive_name
-
-    # If archive already exists, add timestamp
-    if archive_path.exists():
-        archive_name = f"{source_dir.name}.pre-migration-{timestamp}"
-        archive_path = source_dir.parent / archive_name
-
-    # If still exists (multiple runs same day), add counter
-    counter = 2
-    while archive_path.exists():
-        archive_name = f"{source_dir.name}.pre-migration-{timestamp}-{counter}"
-        archive_path = source_dir.parent / archive_name
-        counter += 1
-
-    if not dry_run:
-        source_dir.rename(archive_path)
-
-    return archive_path
-
-
 def claw_command(args):
    """Route hermes claw subcommands."""
    action = getattr(args, "claw_action", None)

    if action == "migrate":
        _cmd_migrate(args)
-    elif action in ("cleanup", "clean"):
-        _cmd_cleanup(args)
    else:
-        print("Usage: hermes claw <command> [options]")
+        print("Usage: hermes claw migrate [options]")
        print()
        print("Commands:")
        print("  migrate          Migrate settings from OpenClaw to Hermes")
-        print("  cleanup          Archive leftover OpenClaw directories after migration")
        print()
-        print("Run 'hermes claw <command> --help' for options.")
+        print("Run 'hermes claw migrate --help' for migration options.")


 def _cmd_migrate(args):
    """Run the OpenClaw → Hermes migration."""
-    # Check current and legacy OpenClaw directories
-    explicit_source = getattr(args, "source", None)
-    if explicit_source:
-        source_dir = Path(explicit_source)
-    else:
-        source_dir = Path.home() / ".openclaw"
-        if not source_dir.is_dir():
-            # Try legacy directory names
-            for legacy in (".clawdbot", ".moldbot"):
-                candidate = Path.home() / legacy
-                if candidate.is_dir():
-                    source_dir = candidate
-                    break
+    source_dir = Path(getattr(args, "source", None) or Path.home() / ".openclaw")
    dry_run = getattr(args, "dry_run", False)
    preset = getattr(args, "preset", "full")
    overwrite = getattr(args, "overwrite", False)
@@ -296,168 +198,6 @@ def _cmd_migrate(args):
    # Print results
    _print_migration_report(report, dry_run)

-    # After successful non-dry-run migration, offer to archive the source directory
-    if not dry_run and report.get("summary", {}).get("migrated", 0) > 0:
-        _offer_source_archival(source_dir, getattr(args, "yes", False))
-
-
-def _offer_source_archival(source_dir: Path, auto_yes: bool = False):
-    """After migration, offer to rename the source directory to prevent state fragmentation.
-
-    OpenClaw workspace directories contain state files (todo.json, sessions, etc.)
-    that the agent may discover and write to, causing confusion. Renaming the
-    directory prevents this.
-    """
-    if not source_dir.is_dir():
-        return
-
-    # Scan for state files that could cause problems
-    state_files = _scan_workspace_state(source_dir)
-
-    print()
-    print_header("Post-Migration Cleanup")
-    print_info("The OpenClaw directory still exists and contains workspace state files")
-    print_info("that can confuse the agent (todo lists, sessions, logs).")
-    if state_files:
-        print()
-        print(color("  Found state files:", Colors.YELLOW))
-        # Show up to 10 most relevant findings
-        for path, desc in state_files[:10]:
-            print(f"      {desc}")
-        if len(state_files) > 10:
-            print(f"      ... and {len(state_files) - 10} more")
-    print()
-    print_info(f"Recommend: rename {source_dir.name}/ to {source_dir.name}.pre-migration/")
-    print_info("This prevents the agent from discovering old workspace directories.")
-    print_info("You can always rename it back if needed.")
-    print()
-
-    if auto_yes or prompt_yes_no(f"Archive {source_dir} now?", default=True):
-        try:
-            archive_path = _archive_directory(source_dir)
-            print_success(f"Archived: {source_dir} → {archive_path}")
-            print_info("The original directory has been renamed, not deleted.")
-            print_info(f"To undo: mv {archive_path} {source_dir}")
-        except OSError as e:
-            print_error(f"Could not archive: {e}")
-            print_info(f"You can do it manually: mv {source_dir} {source_dir}.pre-migration")
-    else:
-        print_info("Skipped. You can archive later with: hermes claw cleanup")
-
-
-def _cmd_cleanup(args):
-    """Archive leftover OpenClaw directories after migration.
-
-    Scans for OpenClaw directories that still exist after migration and offers
-    to rename them to .pre-migration to prevent state fragmentation.
-    """
-    dry_run = getattr(args, "dry_run", False)
-    auto_yes = getattr(args, "yes", False)
-    explicit_source = getattr(args, "source", None)
-
-    print()
-    print(
-        color(
-            "┌─────────────────────────────────────────────────────────┐",
-            Colors.MAGENTA,
-        )
-    )
-    print(
-        color(
-            "│          ⚕ Hermes — OpenClaw Cleanup                   │",
-            Colors.MAGENTA,
-        )
-    )
-    print(
-        color(
-            "└─────────────────────────────────────────────────────────┘",
-            Colors.MAGENTA,
-        )
-    )
-
-    # Find OpenClaw directories
-    if explicit_source:
-        dirs_to_check = [Path(explicit_source)]
-    else:
-        dirs_to_check = _find_openclaw_dirs()
-
-    if not dirs_to_check:
-        print()
-        print_success("No OpenClaw directories found. Nothing to clean up.")
-        return
-
-    total_archived = 0
-
-    for source_dir in dirs_to_check:
-        print()
-        print_header(f"Found: {source_dir}")
-
-        # Scan for state files
-        state_files = _scan_workspace_state(source_dir)
-
-        # Show directory stats
-        try:
-            workspace_dirs = [
-                d for d in source_dir.iterdir()
-                if d.is_dir() and not d.name.startswith(".")
-                and any((d / name).exists() for name in ("todo.json", "SOUL.md", "MEMORY.md", "USER.md"))
-            ]
-        except OSError:
-            workspace_dirs = []
-
-        if workspace_dirs:
-            print_info(f"Workspace directories: {len(workspace_dirs)}")
-            for ws in workspace_dirs[:5]:
-                items = []
-                if (ws / "todo.json").exists():
-                    items.append("todo.json")
-                if (ws / "sessions").is_dir():
-                    items.append("sessions/")
-                if (ws / "SOUL.md").exists():
-                    items.append("SOUL.md")
-                if (ws / "MEMORY.md").exists():
-                    items.append("MEMORY.md")
-                detail = ", ".join(items) if items else "empty"
-                print(f"      {ws.name}/  ({detail})")
-            if len(workspace_dirs) > 5:
-                print(f"      ... and {len(workspace_dirs) - 5} more")
-
-        if state_files:
-            print()
-            print(color(f"  {len(state_files)} state file(s) that could cause confusion:", Colors.YELLOW))
-            for path, desc in state_files[:8]:
-                print(f"      {desc}")
-            if len(state_files) > 8:
-                print(f"      ... and {len(state_files) - 8} more")
-
-        print()
-
-        if dry_run:
-            archive_path = _archive_directory(source_dir, dry_run=True)
-            print_info(f"Would archive: {source_dir} → {archive_path}")
-        else:
-            if auto_yes or prompt_yes_no(f"Archive {source_dir}?", default=True):
-                try:
-                    archive_path = _archive_directory(source_dir)
-                    print_success(f"Archived: {source_dir} → {archive_path}")
-                    total_archived += 1
-                except OSError as e:
-                    print_error(f"Could not archive: {e}")
-                    print_info(f"Try manually: mv {source_dir} {source_dir}.pre-migration")
-            else:
-                print_info("Skipped.")
-
-    # Summary
-    print()
-    if dry_run:
-        print_info(f"Dry run complete. {len(dirs_to_check)} directory(ies) would be archived.")
-        print_info("Run without --dry-run to archive them.")
-    elif total_archived:
-        print_success(f"Cleaned up {total_archived} OpenClaw directory(ies).")
-        print_info("Directories were renamed, not deleted. You can undo by renaming them back.")
-    else:
-        print_info("No directories were archived.")
-

 def _print_migration_report(report: dict, dry_run: bool):
    """Print a formatted migration report."""
@@ -12,8 +12,6 @@ import os
 logger = logging.getLogger(__name__)

 DEFAULT_CODEX_MODELS: List[str] = [
-    "gpt-5.4-mini",
-    "gpt-5.4",
    "gpt-5.3-codex",
    "gpt-5.2-codex",
    "gpt-5.1-codex-max",
@@ -21,9 +19,8 @@ DEFAULT_CODEX_MODELS: List[str] = [
 ]

 _FORWARD_COMPAT_TEMPLATE_MODELS: List[tuple[str, tuple[str, ...]]] = [
-    ("gpt-5.4-mini", ("gpt-5.3-codex", "gpt-5.2-codex")),
-    ("gpt-5.4", ("gpt-5.3-codex", "gpt-5.2-codex")),
    ("gpt-5.3-codex", ("gpt-5.2-codex",)),
+    ("gpt-5.4", ("gpt-5.3-codex", "gpt-5.2-codex")),
    ("gpt-5.3-codex-spark", ("gpt-5.3-codex", "gpt-5.2-codex")),
 ]

@@ -1,24 +1,8 @@
 """Shared ANSI color utilities for Hermes CLI modules."""

-import os
 import sys


-def should_use_color() -> bool:
-    """Return True when colored output is appropriate.
-
-    Respects the NO_COLOR environment variable (https://no-color.org/)
-    and TERM=dumb, in addition to the existing TTY check.
-    """
-    if os.environ.get("NO_COLOR") is not None:
-        return False
-    if os.environ.get("TERM") == "dumb":
-        return False
-    if not sys.stdout.isatty():
-        return False
-    return True
-
-
 class Colors:
    RESET = "\033[0m"
    BOLD = "\033[1m"
@@ -32,7 +16,7 @@ class Colors:


 def color(text: str, *codes) -> str:
-    """Apply color codes to text (only when color output is appropriate)."""
-    if not should_use_color():
+    """Apply color codes to text (only when output is a TTY)."""
+    if not sys.stdout.isatty():
        return text
    return "".join(codes) + text + Colors.RESET
@@ -67,13 +67,10 @@ COMMAND_REGISTRY: list[CommandDef] = [
               gateway_only=True),
    CommandDef("background", "Run a prompt in the background", "Session",
               aliases=("bg",), args_hint="<prompt>"),
-    CommandDef("btw", "Ephemeral side question using session context (no tools, not persisted)", "Session",
-               args_hint="<question>"),
    CommandDef("queue", "Queue a prompt for the next turn (doesn't interrupt)", "Session",
               aliases=("q",), args_hint="<prompt>"),
    CommandDef("status", "Show session info", "Session",
               gateway_only=True),
-    CommandDef("profile", "Show active profile name and home directory", "Info"),
    CommandDef("sethome", "Set this chat as the home channel", "Session",
               gateway_only=True, aliases=("set-home",)),
    CommandDef("resume", "Resume a previously-named session", "Session",
@@ -93,8 +90,6 @@ COMMAND_REGISTRY: list[CommandDef] = [
    CommandDef("verbose", "Cycle tool progress display: off -> new -> all -> verbose",
               "Configuration", cli_only=True,
               gateway_config_gate="display.tool_progress_command"),
-    CommandDef("yolo", "Toggle YOLO mode (skip all dangerous command approvals)",
-               "Configuration"),
    CommandDef("reasoning", "Manage reasoning effort and display", "Configuration",
               args_hint="[level|show|hide]",
               subcommands=("none", "low", "minimal", "medium", "high", "xhigh", "show", "hide", "on", "off")),
@@ -123,8 +118,6 @@ COMMAND_REGISTRY: list[CommandDef] = [
               "Tools & Skills", cli_only=True),

    # Info
-    CommandDef("commands", "Browse all commands and skills (paginated)", "Info",
-               gateway_only=True, args_hint="[page]"),
    CommandDef("help", "Show available commands", "Info"),
    CommandDef("usage", "Show token usage for the current session", "Info"),
    CommandDef("insights", "Show usage insights and analytics", "Info",
@@ -368,117 +361,6 @@ def telegram_bot_commands() -> list[tuple[str, str]]:
    return result


-_TG_NAME_LIMIT = 32
-
-
-def _clamp_telegram_names(
-    entries: list[tuple[str, str]],
-    reserved: set[str],
-) -> list[tuple[str, str]]:
-    """Enforce Telegram's 32-char command name limit with collision avoidance.
-
-    Names exceeding 32 chars are truncated.  If truncation creates a duplicate
-    (against *reserved* names or earlier entries in the same batch), the name is
-    shortened to 31 chars and a digit ``0``-``9`` is appended to differentiate.
-    If all 10 digit slots are taken the entry is silently dropped.
-    """
-    used: set[str] = set(reserved)
-    result: list[tuple[str, str]] = []
-    for name, desc in entries:
-        if len(name) > _TG_NAME_LIMIT:
-            candidate = name[:_TG_NAME_LIMIT]
-            if candidate in used:
-                prefix = name[:_TG_NAME_LIMIT - 1]
-                for digit in range(10):
-                    candidate = f"{prefix}{digit}"
-                    if candidate not in used:
-                        break
-                else:
-                    # All 10 digit slots exhausted — skip entry
-                    continue
-            name = candidate
-        if name in used:
-            continue
-        used.add(name)
-        result.append((name, desc))
-    return result
-
-
-def telegram_menu_commands(max_commands: int = 100) -> tuple[list[tuple[str, str]], int]:
-    """Return Telegram menu commands capped to the Bot API limit.
-
-    Priority order (higher priority = never bumped by overflow):
-      1. Core CommandDef commands (always included)
-      2. Plugin slash commands (take precedence over skills)
-      3. Built-in skill commands (fill remaining slots, alphabetical)
-
-    Skills are the only tier that gets trimmed when the cap is hit.
-    User-installed hub skills are excluded — accessible via /skills.
-
-    Returns:
-        (menu_commands, hidden_count) where hidden_count is the number of
-        skill commands omitted due to the cap.
-    """
-    core_commands = list(telegram_bot_commands())
-    # Reserve core names so plugin/skill truncation can't collide with them
-    reserved_names = {n for n, _ in core_commands}
-    all_commands = list(core_commands)
-
-    # Plugin slash commands get priority over skills
-    plugin_entries: list[tuple[str, str]] = []
-    try:
-        from hermes_cli.plugins import get_plugin_manager
-        pm = get_plugin_manager()
-        plugin_cmds = getattr(pm, "_plugin_commands", {})
-        for cmd_name in sorted(plugin_cmds):
-            tg_name = cmd_name.replace("-", "_")
-            desc = "Plugin command"
-            if len(desc) > 40:
-                desc = desc[:37] + "..."
-            plugin_entries.append((tg_name, desc))
-    except Exception:
-        pass
-
-    # Clamp plugin names to 32 chars with collision avoidance
-    plugin_entries = _clamp_telegram_names(plugin_entries, reserved_names)
-    reserved_names.update(n for n, _ in plugin_entries)
-    all_commands.extend(plugin_entries)
-
-    # Remaining slots go to built-in skill commands (not hub-installed).
-    skill_entries: list[tuple[str, str]] = []
-    try:
-        from agent.skill_commands import get_skill_commands
-        from tools.skills_tool import SKILLS_DIR
-        _skills_dir = str(SKILLS_DIR.resolve())
-        _hub_dir = str((SKILLS_DIR / ".hub").resolve())
-        skill_cmds = get_skill_commands()
-        for cmd_key in sorted(skill_cmds):
-            info = skill_cmds[cmd_key]
-            skill_path = info.get("skill_md_path", "")
-            if not skill_path.startswith(_skills_dir):
-                continue
-            if skill_path.startswith(_hub_dir):
-                continue
-            name = cmd_key.lstrip("/").replace("-", "_")
-            desc = info.get("description", "")
-            # Keep descriptions short — setMyCommands has an undocumented
-            # total payload limit.  40 chars fits 100 commands safely.
-            if len(desc) > 40:
-                desc = desc[:37] + "..."
-            skill_entries.append((name, desc))
-    except Exception:
-        pass
-
-    # Clamp skill names to 32 chars with collision avoidance
-    skill_entries = _clamp_telegram_names(skill_entries, reserved_names)
-
-    # Skills fill remaining slots — they're the only tier that gets trimmed
-    remaining_slots = max(0, max_commands - len(all_commands))
-    hidden_count = max(0, len(skill_entries) - remaining_slots)
-    all_commands.extend(skill_entries[:remaining_slots])
-    return all_commands[:max_commands], hidden_count
-
-
 def slack_subcommand_map() -> dict[str, str]:
    """Return subcommand -> /command mapping for Slack /hermes handler.

@@ -34,8 +34,6 @@ _EXTRA_ENV_KEYS = frozenset({
    "SIGNAL_ACCOUNT", "SIGNAL_HTTP_URL",
    "SIGNAL_ALLOWED_USERS", "SIGNAL_GROUP_ALLOWED_USERS",
    "DINGTALK_CLIENT_ID", "DINGTALK_CLIENT_SECRET",
-    "FEISHU_APP_ID", "FEISHU_APP_SECRET", "FEISHU_ENCRYPT_KEY", "FEISHU_VERIFICATION_TOKEN",
-    "WECOM_BOT_ID", "WECOM_SECRET",
    "TERMINAL_ENV", "TERMINAL_SSH_KEY", "TERMINAL_SSH_PORT",
    "WHATSAPP_MODE", "WHATSAPP_ENABLED",
    "MATTERMOST_HOME_CHANNEL", "MATTERMOST_REPLY_MODE",
@@ -52,86 +50,26 @@ from hermes_cli.default_soul import DEFAULT_SOUL_MD
 # Managed mode (NixOS declarative config)
 # =============================================================================

-_MANAGED_TRUE_VALUES = ("true", "1", "yes")
-_MANAGED_SYSTEM_NAMES = {
-    "brew": "Homebrew",
-    "homebrew": "Homebrew",
-    "nix": "NixOS",
-    "nixos": "NixOS",
-}
-
-
-def get_managed_system() -> Optional[str]:
-    """Return the package manager owning this install, if any."""
-    raw = os.getenv("HERMES_MANAGED", "").strip()
-    if raw:
-        normalized = raw.lower()
-        if normalized in _MANAGED_TRUE_VALUES:
-            return "NixOS"
-        return _MANAGED_SYSTEM_NAMES.get(normalized, raw)
-
-    managed_marker = get_hermes_home() / ".managed"
-    if managed_marker.exists():
-        return "NixOS"
-    return None
-
-
 def is_managed() -> bool:
-    """Check if Hermes is running in package-manager-managed mode.
+    """Check if hermes is running in Nix-managed mode.

    Two signals: the HERMES_MANAGED env var (set by the systemd service),
    or a .managed marker file in HERMES_HOME (set by the NixOS activation
    script, so interactive shells also see it).
    """
-    return get_managed_system() is not None
-
-
-def get_managed_update_command() -> Optional[str]:
-    """Return the preferred upgrade command for a managed install."""
-    managed_system = get_managed_system()
-    if managed_system == "Homebrew":
-        return "brew upgrade hermes-agent"
-    if managed_system == "NixOS":
-        return "sudo nixos-rebuild switch"
-    return None
-
-
-def recommended_update_command() -> str:
-    """Return the best update command for the current installation."""
-    return get_managed_update_command() or "hermes update"
-
-
-def format_managed_message(action: str = "modify this Hermes installation") -> str:
-    """Build a user-facing error for managed installs."""
-    managed_system = get_managed_system() or "a package manager"
-    raw = os.getenv("HERMES_MANAGED", "").strip().lower()
-
-    if managed_system == "NixOS":
-        env_hint = "true" if raw in _MANAGED_TRUE_VALUES else raw or "true"
-        return (
-            f"Cannot {action}: this Hermes installation is managed by NixOS "
-            f"(HERMES_MANAGED={env_hint}).\n"
-            "Edit services.hermes-agent.settings in your configuration.nix and run:\n"
-            "  sudo nixos-rebuild switch"
-        )
-
-    if managed_system == "Homebrew":
-        env_hint = raw or "homebrew"
-        return (
-            f"Cannot {action}: this Hermes installation is managed by Homebrew "
-            f"(HERMES_MANAGED={env_hint}).\n"
-            "Use:\n"
-            "  brew upgrade hermes-agent"
-        )
-
-    return (
-        f"Cannot {action}: this Hermes installation is managed by {managed_system}.\n"
-        "Use your package manager to upgrade or reinstall Hermes."
-    )
+    if os.getenv("HERMES_MANAGED", "").lower() in ("true", "1", "yes"):
+        return True
+    managed_marker = get_hermes_home() / ".managed"
+    return managed_marker.exists()

 def managed_error(action: str = "modify configuration"):
    """Print user-friendly error for managed mode."""
-    print(format_managed_message(action), file=sys.stderr)
+    print(
+        f"Cannot {action}: configuration is managed by NixOS (HERMES_MANAGED=true).\n"
+        "Edit services.hermes-agent.settings in your configuration.nix and run:\n"
+        "  sudo nixos-rebuild switch",
+        file=sys.stderr,
+    )


 # =============================================================================
@@ -197,17 +135,9 @@ def ensure_hermes_home():

 DEFAULT_CONFIG = {
    "model": "anthropic/claude-opus-4.6",
-    "fallback_providers": [],
-    "credential_pool_strategies": {},
    "toolsets": ["hermes-cli"],
    "agent": {
        "max_turns": 90,
-        # Tool-use enforcement: injects system prompt guidance that tells the
-        # model to actually call tools instead of describing intended actions.
-        # Values: "auto" (default — applies to gpt/codex models), true/false
-        # (force on/off for all models), or a list of model-name substrings
-        # to match (e.g. ["gpt", "codex", "gemini", "qwen"]).
-        "tool_use_enforcement": "auto",
    },
    
    "terminal": {
@@ -246,14 +176,6 @@ DEFAULT_CONFIG = {
        "inactivity_timeout": 120,
        "command_timeout": 30,  # Timeout for browser commands in seconds (screenshot, navigate, etc.)
        "record_sessions": False,  # Auto-record browser sessions as WebM videos
-        "allow_private_urls": False,  # Allow navigating to private/internal IPs (localhost, 192.168.x.x, etc.)
-        "camofox": {
-            # When true, Hermes sends a stable profile-scoped userId to Camofox
-            # so the server can map it to a persistent browser profile directory.
-            # Requires Camofox server to be configured with CAMOFOX_PROFILE_DIR.
-            # When false (default), each session gets a random userId (ephemeral).
-            "managed_persistence": False,
-        },
    },

    # Filesystem checkpoints — automatic snapshots before destructive file ops.
@@ -263,11 +185,6 @@ DEFAULT_CONFIG = {
        "enabled": True,
        "max_snapshots": 50,  # Max checkpoints to keep per directory
    },
-
-    # Maximum characters returned by a single read_file call.  Reads that
-    # exceed this are rejected with guidance to use offset+limit.
-    # 100K chars ≈ 25–35K tokens across typical tokenisers.
-    "file_read_max_chars": 100_000,
    
    "compression": {
        "enabled": True,
@@ -297,57 +214,49 @@ DEFAULT_CONFIG = {
            "model": "",           # e.g. "google/gemini-2.5-flash", "gpt-4o"
            "base_url": "",        # direct OpenAI-compatible endpoint (takes precedence over provider)
            "api_key": "",         # API key for base_url (falls back to OPENAI_API_KEY)
-            "timeout": 30,         # seconds — LLM API call timeout; increase for slow local vision models
-            "download_timeout": 30,  # seconds — image HTTP download timeout; increase for slow connections
+            "timeout": 30,         # seconds — increase for slow local vision models
        },
        "web_extract": {
            "provider": "auto",
            "model": "",
            "base_url": "",
            "api_key": "",
-            "timeout": 30,         # seconds — increase for slow local models
        },
        "compression": {
            "provider": "auto",
            "model": "",
            "base_url": "",
            "api_key": "",
-            "timeout": 120,        # seconds — compression summarises large contexts; increase for local models
        },
        "session_search": {
            "provider": "auto",
            "model": "",
            "base_url": "",
            "api_key": "",
-            "timeout": 30,
        },
        "skills_hub": {
            "provider": "auto",
            "model": "",
            "base_url": "",
            "api_key": "",
-            "timeout": 30,
        },
        "approval": {
            "provider": "auto",
            "model": "",           # fast/cheap model recommended (e.g. gemini-flash, haiku)
            "base_url": "",
            "api_key": "",
-            "timeout": 30,
        },
        "mcp": {
            "provider": "auto",
            "model": "",
            "base_url": "",
            "api_key": "",
-            "timeout": 30,
        },
        "flush_memories": {
            "provider": "auto",
            "model": "",
            "base_url": "",
            "api_key": "",
-            "timeout": 30,
        },
    },
    
@@ -355,15 +264,12 @@ DEFAULT_CONFIG = {
        "compact": False,
        "personality": "kawaii",
        "resume_display": "full",
-        "busy_input_mode": "interrupt",
        "bell_on_complete": False,
        "show_reasoning": False,
        "streaming": False,
-        "inline_diffs": True,     # Show inline diff previews for write actions (write_file, patch, skill_manage)
        "show_cost": False,       # Show $ cost in the status bar (off by default)
        "skin": "default",
        "tool_progress_command": False,  # Enable /verbose command in messaging gateway
-        "tool_preview_length": 0,  # Max chars for tool call previews (0 = no limit, show full paths/commands)
    },

    # Privacy settings
@@ -446,13 +352,6 @@ DEFAULT_CONFIG = {
    # Never saved to sessions, logs, or trajectories.
    "prefill_messages_file": "",
    
-    # Skills — external skill directories for sharing skills across tools/agents.
-    # Each path is expanded (~, ${VAR}) and resolved.  Read-only — skill creation
-    # always goes to ~/.hermes/skills/.
-    "skills": {
-        "external_dirs": [],   # e.g. ["~/.agents/skills", "/shared/team-skills"]
-    },
-
    # Honcho AI-native memory -- reads ~/.honcho/config.json as single source of truth.
    # This section is only needed for hermes-specific overrides; everything else
    # (apiKey, workspace, peerName, sessions, enabled) comes from the global config.
@@ -467,7 +366,6 @@ DEFAULT_CONFIG = {
        "require_mention": True,       # Require @mention to respond in server channels
        "free_response_channels": "",  # Comma-separated channel IDs where bot responds without mention
        "auto_thread": True,           # Auto-create threads on @mention in channels (like Slack)
-        "reactions": True,             # Add 👀/✅/❌ reactions to messages during processing
    },

    # WhatsApp platform settings (gateway mode)
@@ -484,7 +382,6 @@ DEFAULT_CONFIG = {
    #   off    — skip all approval prompts (equivalent to --yolo)
    "approvals": {
        "mode": "manual",
-        "timeout": 60,
    },

    # Permanently allowed dangerous command patterns (added via "always" approval)
@@ -510,14 +407,8 @@ DEFAULT_CONFIG = {
        },
    },

-    "cron": {
-        # Wrap delivered cron responses with a header (task name) and footer
-        # ("The agent cannot see this message").  Set to false for clean output.
-        "wrap_response": True,
-    },
-
    # Config schema version - bump this when adding new required fields
-    "_config_version": 11,
+    "_config_version": 10,
 }

 # =============================================================================
@@ -655,14 +546,14 @@ OPTIONAL_ENV_VARS = {
        "category": "provider",
    },
    "DASHSCOPE_API_KEY": {
-        "description": "Alibaba Cloud DashScope API key (Qwen + multi-provider models)",
+        "description": "Alibaba Cloud DashScope API key for Qwen models",
        "prompt": "DashScope API Key",
        "url": "https://modelstudio.console.alibabacloud.com/",
        "password": True,
        "category": "provider",
    },
    "DASHSCOPE_BASE_URL": {
-        "description": "Custom DashScope base URL (default: coding-intl OpenAI-compat endpoint)",
+        "description": "Custom DashScope base URL (default: international endpoint)",
        "prompt": "DashScope Base URL",
        "url": "",
        "password": False,
@@ -701,31 +592,8 @@ OPTIONAL_ENV_VARS = {
        "category": "provider",
        "advanced": True,
    },
-    "HF_TOKEN": {
-        "description": "Hugging Face token for Inference Providers (20+ open models via router.huggingface.co)",
-        "prompt": "Hugging Face Token",
-        "url": "https://huggingface.co/settings/tokens",
-        "password": True,
-        "category": "provider",
-    },
-    "HF_BASE_URL": {
-        "description": "Hugging Face Inference Providers base URL override",
-        "prompt": "HF base URL (leave empty for default)",
-        "url": None,
-        "password": False,
-        "category": "provider",
-        "advanced": True,
-    },

    # ── Tool API keys ──
-    "EXA_API_KEY": {
-        "description": "Exa API key for AI-native web search and contents",
-        "prompt": "Exa API key",
-        "url": "https://exa.ai/",
-        "tools": ["web_search", "web_extract"],
-        "password": True,
-        "category": "tool",
-    },
    "PARALLEL_API_KEY": {
        "description": "Parallel API key for AI-native web search and extract",
        "prompt": "Parallel API key",
@@ -782,14 +650,6 @@ OPTIONAL_ENV_VARS = {
        "password": True,
        "category": "tool",
    },
-    "CAMOFOX_URL": {
-        "description": "Camofox browser server URL for local anti-detection browsing (e.g. http://localhost:9377)",
-        "prompt": "Camofox server URL",
-        "url": "https://github.com/jo-inc/camofox-browser",
-        "tools": ["browser_navigate", "browser_click"],
-        "password": False,
-        "category": "tool",
-    },
    "FAL_KEY": {
        "description": "FAL API key for image generation",
        "prompt": "FAL API key",
@@ -920,20 +780,6 @@ OPTIONAL_ENV_VARS = {
        "password": False,
        "category": "messaging",
    },
-    "MATTERMOST_REQUIRE_MENTION": {
-        "description": "Require @mention in Mattermost channels (default: true). Set to false to respond to all messages.",
-        "prompt": "Require @mention in channels",
-        "url": None,
-        "password": False,
-        "category": "messaging",
-    },
-    "MATTERMOST_FREE_RESPONSE_CHANNELS": {
-        "description": "Comma-separated Mattermost channel IDs where bot responds without @mention",
-        "prompt": "Free-response channel IDs (comma-separated)",
-        "url": None,
-        "password": False,
-        "category": "messaging",
-    },
    "MATRIX_HOMESERVER": {
        "description": "Matrix homeserver URL (e.g. https://matrix.example.org)",
        "prompt": "Matrix homeserver URL",
@@ -1381,36 +1227,6 @@ def _expand_env_vars(obj):
    return obj


-def _normalize_root_model_keys(config: Dict[str, Any]) -> Dict[str, Any]:
-    """Move stale root-level provider/base_url into model section.
-
-    Some users (or older code) placed ``provider:`` and ``base_url:`` at the
-    config root instead of inside ``model:``.  These root-level keys are only
-    used as a fallback when the corresponding ``model.*`` key is empty — they
-    never override an existing ``model.provider`` or ``model.base_url``.
-    After migration the root-level keys are removed so they can't cause
-    confusion on subsequent loads.
-    """
-    # Only act if there are root-level keys to migrate
-    has_root = any(config.get(k) for k in ("provider", "base_url"))
-    if not has_root:
-        return config
-
-    config = dict(config)
-    model = config.get("model")
-    if not isinstance(model, dict):
-        model = {"default": model} if model else {}
-        config["model"] = model
-
-    for key in ("provider", "base_url"):
-        root_val = config.get(key)
-        if root_val and not model.get(key):
-            model[key] = root_val
-        config.pop(key, None)
-
-    return config
-
-
 def _normalize_max_turns_config(config: Dict[str, Any]) -> Dict[str, Any]:
    """Normalize legacy root-level max_turns into agent.max_turns."""
    config = dict(config)
@@ -1452,7 +1268,7 @@ def load_config() -> Dict[str, Any]:
        except Exception as e:
            print(f"Warning: Failed to load config: {e}")
    
-    return _expand_env_vars(_normalize_root_model_keys(_normalize_max_turns_config(config)))
+    return _expand_env_vars(_normalize_max_turns_config(config))


 _SECURITY_COMMENT = """
@@ -1559,7 +1375,7 @@ def save_config(config: Dict[str, Any]):

    ensure_hermes_home()
    config_path = get_config_path()
-    normalized = _normalize_root_model_keys(_normalize_max_turns_config(config))
+    normalized = _normalize_max_turns_config(config)

    # Build optional commented-out sections for features that are off by
    # default or only relevant when explicitly configured.
@@ -1834,7 +1650,6 @@ def show_config():
    keys = [
        ("OPENROUTER_API_KEY", "OpenRouter"),
        ("VOICE_TOOLS_OPENAI_KEY", "OpenAI (STT/TTS)"),
-        ("EXA_API_KEY", "Exa"),
        ("PARALLEL_API_KEY", "Parallel"),
        ("FIRECRAWL_API_KEY", "Firecrawl"),
        ("TAVILY_API_KEY", "Tavily"),
@@ -1994,7 +1809,7 @@ def set_config_value(key: str, value: str):
    # Check if it's an API key (goes to .env)
    api_keys = [
        'OPENROUTER_API_KEY', 'OPENAI_API_KEY', 'ANTHROPIC_API_KEY', 'VOICE_TOOLS_OPENAI_KEY',
-        'EXA_API_KEY', 'PARALLEL_API_KEY', 'FIRECRAWL_API_KEY', 'FIRECRAWL_API_URL', 'TAVILY_API_KEY',
+        'PARALLEL_API_KEY', 'FIRECRAWL_API_KEY', 'FIRECRAWL_API_URL', 'TAVILY_API_KEY',
        'BROWSERBASE_API_KEY', 'BROWSERBASE_PROJECT_ID', 'BROWSER_USE_API_KEY',
        'FAL_KEY', 'TELEGRAM_BOT_TOKEN', 'DISCORD_BOT_TOKEN',
        'TERMINAL_SSH_HOST', 'TERMINAL_SSH_USER', 'TERMINAL_SSH_KEY',
@@ -2083,7 +1898,7 @@ def config_command(args):
    elif subcmd == "set":
        key = getattr(args, 'key', None)
        value = getattr(args, 'value', None)
-        if not key or value is None:
+        if not key or not value:
            print("Usage: hermes config set <key> <value>")
            print()
            print("Examples:")
@@ -56,7 +56,7 @@ def cron_list(show_all: bool = False):
    print()

    for job in jobs:
-        job_id = job.get("id", "?")
+        job_id = job.get("id", "?")[:8]
        name = job.get("name", "(unnamed)")
        schedule = job.get("schedule_display", job.get("schedule", {}).get("value", "?"))
        state = job.get("state", "scheduled" if job.get("enabled", True) else "paused")
@@ -4,8 +4,7 @@ Used by `hermes tools` and `hermes skills` for interactive checklists.
 Provides a curses multi-select with keyboard navigation, plus a
 text-based numbered fallback for terminals without curses support.
 """
-import sys
-from typing import Callable, List, Optional, Set
+from typing import List, Set

 from hermes_cli.colors import Colors, color

@@ -16,7 +15,6 @@ def curses_checklist(
    selected: Set[int],
    *,
    cancel_returns: Set[int] | None = None,
-    status_fn: Optional[Callable[[Set[int]], str]] = None,
 ) -> Set[int]:
    """Curses multi-select checklist. Returns set of selected indices.

@@ -25,18 +23,10 @@ def curses_checklist(
        items: Display labels for each row.
        selected: Indices that start checked (pre-selected).
        cancel_returns: Returned on ESC/q. Defaults to the original *selected*.
-        status_fn: Optional callback ``f(chosen_indices) -> str`` whose return
-            value is rendered on the bottom row of the terminal.  Use this for
-            live aggregate info (e.g. estimated token counts).
    """
    if cancel_returns is None:
        cancel_returns = set(selected)

-    # Safety: curses and input() both hang or spin when stdin is not a
-    # terminal (e.g. subprocess pipe).  Return defaults immediately.
-    if not sys.stdin.isatty():
-        return cancel_returns
-
    try:
        import curses
        chosen = set(selected)
@@ -57,9 +47,6 @@ def curses_checklist(
                stdscr.clear()
                max_y, max_x = stdscr.getmaxyx()

-                # Reserve bottom row for status bar when status_fn provided
-                footer_rows = 1 if status_fn else 0
-
                # Header
                try:
                    hattr = curses.A_BOLD
@@ -75,7 +62,7 @@ def curses_checklist(
                    pass

                # Scrollable item list
-                visible_rows = max_y - 3 - footer_rows
+                visible_rows = max_y - 3
                if cursor < scroll_offset:
                    scroll_offset = cursor
                elif cursor >= scroll_offset + visible_rows:
@@ -85,7 +72,7 @@ def curses_checklist(
                    range(scroll_offset, min(len(items), scroll_offset + visible_rows))
                ):
                    y = draw_i + 3
-                    if y >= max_y - 1 - footer_rows:
+                    if y >= max_y - 1:
                        break
                    check = "✓" if i in chosen else " "
                    arrow = "→" if i == cursor else " "
@@ -100,20 +87,6 @@ def curses_checklist(
                    except curses.error:
                        pass

-                # Status bar (bottom row, right-aligned)
-                if status_fn:
-                    try:
-                        status_text = status_fn(chosen)
-                        if status_text:
-                            # Right-align on the bottom row
-                            sx = max(0, max_x - len(status_text) - 1)
-                            sattr = curses.A_DIM
-                            if curses.has_colors():
-                                sattr |= curses.color_pair(3)
-                            stdscr.addnstr(max_y - 1, sx, status_text, max_x - sx - 1, sattr)
-                    except curses.error:
-                        pass
-
                stdscr.refresh()
                key = stdscr.getch()

@@ -134,7 +107,7 @@ def curses_checklist(
        return result_holder[0] if result_holder[0] is not None else cancel_returns

    except Exception:
-        return _numbered_fallback(title, items, selected, cancel_returns, status_fn)
+        return _numbered_fallback(title, items, selected, cancel_returns)


 def _numbered_fallback(
@@ -142,7 +115,6 @@ def _numbered_fallback(
    items: List[str],
    selected: Set[int],
    cancel_returns: Set[int],
-    status_fn: Optional[Callable[[Set[int]], str]] = None,
 ) -> Set[int]:
    """Text-based toggle fallback for terminals without curses."""
    chosen = set(selected)
@@ -153,10 +125,6 @@ def _numbered_fallback(
        for i, label in enumerate(items):
            marker = color("[✓]", Colors.GREEN) if i in chosen else "[ ]"
            print(f"  {marker} {i + 1:>2}. {label}")
-        if status_fn:
-            status_text = status_fn(chosen)
-            if status_text:
-                print(color(f"\n  {status_text}", Colors.DIM))
        print()
        try:
            val = input(color("  Toggle # (or Enter to confirm): ", Colors.DIM)).strip()
@@ -10,11 +10,9 @@ import subprocess
 import shutil

 from hermes_cli.config import get_project_root, get_hermes_home, get_env_path
-from hermes_constants import display_hermes_home

 PROJECT_ROOT = get_project_root()
 HERMES_HOME = get_hermes_home()
-_DHH = display_hermes_home()  # user-facing display path (e.g. ~/.hermes or ~/.hermes/profiles/coder)

 # Load environment variables from ~/.hermes/.env so API key checks work
 from dotenv import load_dotenv
@@ -58,7 +56,7 @@ def _honcho_is_configured_for_doctor() -> bool:
        from honcho_integration.client import HonchoClientConfig

        cfg = HonchoClientConfig.from_global_config()
-        return bool(cfg.enabled and (cfg.api_key or cfg.base_url))
+        return bool(cfg.enabled and cfg.api_key)
    except Exception:
        return False

@@ -211,14 +209,14 @@ def run_doctor(args):
    # Check ~/.hermes/.env (primary location for user config)
    env_path = HERMES_HOME / '.env'
    if env_path.exists():
-        check_ok(f"{_DHH}/.env file exists")
+        check_ok("~/.hermes/.env file exists")
        
        # Check for common issues
        content = env_path.read_text()
        if _has_provider_env_config(content):
            check_ok("API key or custom endpoint configured")
        else:
-            check_warn(f"No API key found in {_DHH}/.env")
+            check_warn("No API key found in ~/.hermes/.env")
            issues.append("Run 'hermes setup' to configure API keys")
    else:
        # Also check project root as fallback
@@ -226,11 +224,11 @@ def run_doctor(args):
        if fallback_env.exists():
            check_ok(".env file exists (in project directory)")
        else:
-            check_fail(f"{_DHH}/.env file missing")
+            check_fail("~/.hermes/.env file missing")
            if should_fix:
                env_path.parent.mkdir(parents=True, exist_ok=True)
                env_path.touch()
-                check_ok(f"Created empty {_DHH}/.env")
+                check_ok("Created empty ~/.hermes/.env")
                check_info("Run 'hermes setup' to configure API keys")
                fixed_count += 1
            else:
@@ -240,7 +238,7 @@ def run_doctor(args):
    # Check ~/.hermes/config.yaml (primary) or project cli-config.yaml (fallback)
    config_path = HERMES_HOME / 'config.yaml'
    if config_path.exists():
-        check_ok(f"{_DHH}/config.yaml exists")
+        check_ok("~/.hermes/config.yaml exists")
    else:
        fallback_config = PROJECT_ROOT / 'cli-config.yaml'
        if fallback_config.exists():
@@ -250,11 +248,11 @@ def run_doctor(args):
            if should_fix and example_config.exists():
                config_path.parent.mkdir(parents=True, exist_ok=True)
                shutil.copy2(str(example_config), str(config_path))
-                check_ok(f"Created {_DHH}/config.yaml from cli-config.yaml.example")
+                check_ok("Created ~/.hermes/config.yaml from cli-config.yaml.example")
                fixed_count += 1
            elif should_fix:
                check_warn("config.yaml not found and no example to copy from")
-                manual_issues.append(f"Create {_DHH}/config.yaml manually")
+                manual_issues.append("Create ~/.hermes/config.yaml manually")
            else:
                check_warn("config.yaml not found", "(using defaults)")
    
@@ -296,28 +294,28 @@ def run_doctor(args):
    
    hermes_home = HERMES_HOME
    if hermes_home.exists():
-        check_ok(f"{_DHH} directory exists")
+        check_ok("~/.hermes directory exists")
    else:
        if should_fix:
            hermes_home.mkdir(parents=True, exist_ok=True)
-            check_ok(f"Created {_DHH} directory")
+            check_ok("Created ~/.hermes directory")
            fixed_count += 1
        else:
-            check_warn(f"{_DHH} not found", "(will be created on first use)")
+            check_warn("~/.hermes not found", "(will be created on first use)")
    
    # Check expected subdirectories
    expected_subdirs = ["cron", "sessions", "logs", "skills", "memories"]
    for subdir_name in expected_subdirs:
        subdir_path = hermes_home / subdir_name
        if subdir_path.exists():
-            check_ok(f"{_DHH}/{subdir_name}/ exists")
+            check_ok(f"~/.hermes/{subdir_name}/ exists")
        else:
            if should_fix:
                subdir_path.mkdir(parents=True, exist_ok=True)
-                check_ok(f"Created {_DHH}/{subdir_name}/")
+                check_ok(f"Created ~/.hermes/{subdir_name}/")
                fixed_count += 1
            else:
-                check_warn(f"{_DHH}/{subdir_name}/ not found", "(will be created on first use)")
+                check_warn(f"~/.hermes/{subdir_name}/ not found", "(will be created on first use)")
    
    # Check for SOUL.md persona file
    soul_path = hermes_home / "SOUL.md"
@@ -326,11 +324,11 @@ def run_doctor(args):
        # Check if it's just the template comments (no real content)
        lines = [l for l in content.splitlines() if l.strip() and not l.strip().startswith(("<!--", "-->", "#"))]
        if lines:
-            check_ok(f"{_DHH}/SOUL.md exists (persona configured)")
+            check_ok("~/.hermes/SOUL.md exists (persona configured)")
        else:
-            check_info(f"{_DHH}/SOUL.md exists but is empty — edit it to customize personality")
+            check_info("~/.hermes/SOUL.md exists but is empty — edit it to customize personality")
    else:
-        check_warn(f"{_DHH}/SOUL.md not found", "(create it to give Hermes a custom personality)")
+        check_warn("~/.hermes/SOUL.md not found", "(create it to give Hermes a custom personality)")
        if should_fix:
            soul_path.parent.mkdir(parents=True, exist_ok=True)
            soul_path.write_text(
@@ -339,13 +337,13 @@ def run_doctor(args):
                "You are Hermes, a helpful AI assistant.\n",
                encoding="utf-8",
            )
-            check_ok(f"Created {_DHH}/SOUL.md with basic template")
+            check_ok("Created ~/.hermes/SOUL.md with basic template")
            fixed_count += 1
    
    # Check memory directory
    memories_dir = hermes_home / "memories"
    if memories_dir.exists():
-        check_ok(f"{_DHH}/memories/ directory exists")
+        check_ok("~/.hermes/memories/ directory exists")
        memory_file = memories_dir / "MEMORY.md"
        user_file = memories_dir / "USER.md"
        if memory_file.exists():
@@ -359,10 +357,10 @@ def run_doctor(args):
        else:
            check_info("USER.md not created yet (will be created when the agent first writes a memory)")
    else:
-        check_warn(f"{_DHH}/memories/ not found", "(will be created on first use)")
+        check_warn("~/.hermes/memories/ not found", "(will be created on first use)")
        if should_fix:
            memories_dir.mkdir(parents=True, exist_ok=True)
-            check_ok(f"Created {_DHH}/memories/")
+            check_ok("Created ~/.hermes/memories/")
            fixed_count += 1
    
    # Check SQLite session store
@@ -374,11 +372,11 @@ def run_doctor(args):
            cursor = conn.execute("SELECT COUNT(*) FROM sessions")
            count = cursor.fetchone()[0]
            conn.close()
-            check_ok(f"{_DHH}/state.db exists ({count} sessions)")
+            check_ok(f"~/.hermes/state.db exists ({count} sessions)")
        except Exception as e:
-            check_warn(f"{_DHH}/state.db exists but has issues: {e}")
+            check_warn(f"~/.hermes/state.db exists but has issues: {e}")
    else:
-        check_info(f"{_DHH}/state.db not created yet (will be created on first session)")
+        check_info("~/.hermes/state.db not created yet (will be created on first session)")

    _check_gateway_service_linger(issues)
    
@@ -406,11 +404,8 @@ def run_doctor(args):
    if terminal_env == "docker":
        if shutil.which("docker"):
            # Check if docker daemon is running
-            try:
-                result = subprocess.run(["docker", "info"], capture_output=True, timeout=10)
-            except subprocess.TimeoutExpired:
-                result = None
-            if result is not None and result.returncode == 0:
+            result = subprocess.run(["docker", "info"], capture_output=True)
+            if result.returncode == 0:
                check_ok("docker", "(daemon running)")
            else:
                check_fail("docker daemon not running")
@@ -429,16 +424,12 @@ def run_doctor(args):
        ssh_host = os.getenv("TERMINAL_SSH_HOST")
        if ssh_host:
            # Try to connect
-            try:
-                result = subprocess.run(
-                    ["ssh", "-o", "ConnectTimeout=5", "-o", "BatchMode=yes", ssh_host, "echo ok"],
-                    capture_output=True,
-                    text=True,
-                    timeout=15
-                )
-            except subprocess.TimeoutExpired:
-                result = None
-            if result is not None and result.returncode == 0:
+            result = subprocess.run(
+                ["ssh", "-o", "ConnectTimeout=5", "-o", "BatchMode=yes", ssh_host, "echo ok"],
+                capture_output=True,
+                text=True
+            )
+            if result.returncode == 0:
                check_ok(f"SSH connection to {ssh_host}")
            else:
                check_fail(f"SSH connection to {ssh_host}")
@@ -700,7 +691,7 @@ def run_doctor(args):
    if github_token:
        check_ok("GitHub token configured (authenticated API access)")
    else:
-        check_warn("No GITHUB_TOKEN", f"(60 req/hr rate limit — set in {_DHH}/.env for better rates)")
+        check_warn("No GITHUB_TOKEN", "(60 req/hr rate limit — set in ~/.hermes/.env for better rates)")

    # =========================================================================
    # Honcho memory
@@ -717,8 +708,8 @@ def run_doctor(args):
            check_warn("Honcho config not found", "run: hermes honcho setup")
        elif not hcfg.enabled:
            check_info(f"Honcho disabled (set enabled: true in {_honcho_cfg_path} to activate)")
-        elif not (hcfg.api_key or hcfg.base_url):
-            check_fail("Honcho API key or base URL not set", "run: hermes honcho setup")
+        elif not hcfg.api_key:
+            check_fail("Honcho API key not set", "run: hermes honcho setup")
            issues.append("No Honcho API key — run 'hermes honcho setup'")
        else:
            from honcho_integration.client import get_honcho_client, reset_honcho_client
@@ -737,53 +728,6 @@ def run_doctor(args):
    except Exception as _e:
        check_warn("Honcho check failed", str(_e))

-    # =========================================================================
-    # Profiles
-    # =========================================================================
-    try:
-        from hermes_cli.profiles import list_profiles, _get_wrapper_dir, profile_exists
-        import re as _re
-
-        named_profiles = [p for p in list_profiles() if not p.is_default]
-        if named_profiles:
-            print()
-            print(color("◆ Profiles", Colors.CYAN, Colors.BOLD))
-            check_ok(f"{len(named_profiles)} profile(s) found")
-            wrapper_dir = _get_wrapper_dir()
-            for p in named_profiles:
-                parts = []
-                if p.gateway_running:
-                    parts.append("gateway running")
-                if p.model:
-                    parts.append(p.model[:30])
-                if not (p.path / "config.yaml").exists():
-                    parts.append("⚠ missing config")
-                if not (p.path / ".env").exists():
-                    parts.append("no .env")
-                wrapper = wrapper_dir / p.name
-                if not wrapper.exists():
-                    parts.append("no alias")
-                status = ", ".join(parts) if parts else "configured"
-                check_ok(f"  {p.name}: {status}")
-
-            # Check for orphan wrappers
-            if wrapper_dir.is_dir():
-                for wrapper in wrapper_dir.iterdir():
-                    if not wrapper.is_file():
-                        continue
-                    try:
-                        content = wrapper.read_text()
-                        if "hermes -p" in content:
-                            _m = _re.search(r"hermes -p (\S+)", content)
-                            if _m and not profile_exists(_m.group(1)):
-                                check_warn(f"Orphan alias: {wrapper.name} → profile '{_m.group(1)}' no longer exists")
-                    except Exception:
-                        pass
-    except ImportError:
-        pass
-    except Exception as _e:
-        logger.debug("Profile health check failed: %s", _e)
-
    # =========================================================================
    # Summary
    # =========================================================================
@@ -15,8 +15,6 @@ from pathlib import Path
 PROJECT_ROOT = Path(__file__).parent.parent.resolve()

 from hermes_cli.config import get_env_value, get_hermes_home, save_env_value, is_managed, managed_error
-# display_hermes_home is imported lazily at call sites to avoid ImportError
-# when hermes_constants is cached from a pre-update version during `hermes update`.
 from hermes_cli.setup import (
    print_header, print_info, print_success, print_warning, print_error,
    prompt, prompt_choice, prompt_yes_no,
@@ -127,43 +125,20 @@ _SERVICE_BASE = "hermes-gateway"
 SERVICE_DESCRIPTION = "Hermes Agent Gateway - Messaging Platform Integration"


-def _profile_suffix() -> str:
-    """Derive a service-name suffix from the current HERMES_HOME.
-
-    Returns ``""`` for the default ``~/.hermes``, the profile name for
-    ``~/.hermes/profiles/<name>``, or a short hash for any other custom
-    HERMES_HOME path.
-    """
-    import hashlib
-    import re
-    from pathlib import Path as _Path
-    home = get_hermes_home().resolve()
-    default = (_Path.home() / ".hermes").resolve()
-    if home == default:
-        return ""
-    # Detect ~/.hermes/profiles/<name> pattern → use the profile name
-    profiles_root = (default / "profiles").resolve()
-    try:
-        rel = home.relative_to(profiles_root)
-        parts = rel.parts
-        if len(parts) == 1 and re.match(r"^[a-z0-9][a-z0-9_-]{0,63}$", parts[0]):
-            return parts[0]
-    except ValueError:
-        pass
-    # Fallback: short hash for arbitrary HERMES_HOME paths
-    return hashlib.sha256(str(home).encode()).hexdigest()[:8]
-
-
 def get_service_name() -> str:
    """Derive a systemd service name scoped to this HERMES_HOME.

    Default ``~/.hermes`` returns ``hermes-gateway`` (backward compatible).
-    Profile ``~/.hermes/profiles/coder`` returns ``hermes-gateway-coder``.
-    Any other HERMES_HOME appends a short hash for uniqueness.
+    Any other HERMES_HOME appends a short hash so multiple installations
+    can each have their own systemd service without conflicting.
    """
-    suffix = _profile_suffix()
-    if not suffix:
+    import hashlib
+    from pathlib import Path as _Path  # local import to avoid monkeypatch interference
+    home = get_hermes_home().resolve()
+    default = (_Path.home() / ".hermes").resolve()
+    if home == default:
        return _SERVICE_BASE
+    suffix = hashlib.sha256(str(home).encode()).hexdigest()[:8]
    return f"{_SERVICE_BASE}-{suffix}"


@@ -394,14 +369,7 @@ def print_systemd_linger_guidance() -> None:
        print("  sudo loginctl enable-linger $USER")

 def get_launchd_plist_path() -> Path:
-    """Return the launchd plist path, scoped per profile.
-
-    Default ``~/.hermes`` → ``ai.hermes.gateway.plist`` (backward compatible).
-    Profile ``~/.hermes/profiles/coder`` → ``ai.hermes.gateway-coder.plist``.
-    """
-    suffix = _profile_suffix()
-    name = f"ai.hermes.gateway-{suffix}" if suffix else "ai.hermes.gateway"
-    return Path.home() / "Library" / "LaunchAgents" / f"{name}.plist"
+    return Path.home() / "Library" / "LaunchAgents" / "ai.hermes.gateway.plist"

 def _detect_venv_dir() -> Path | None:
    """Detect the active virtualenv directory.
@@ -452,43 +420,6 @@ def get_hermes_cli_path() -> str:
 # Systemd (Linux)
 # =============================================================================

-def _build_user_local_paths(home: Path, path_entries: list[str]) -> list[str]:
-    """Return user-local bin dirs that exist and aren't already in *path_entries*."""
-    candidates = [
-        str(home / ".local" / "bin"),       # uv, uvx, pip-installed CLIs
-        str(home / ".cargo" / "bin"),        # Rust/cargo tools
-        str(home / "go" / "bin"),            # Go tools
-        str(home / ".npm-global" / "bin"),   # npm global packages
-    ]
-    return [p for p in candidates if p not in path_entries and Path(p).exists()]
-
-
-def _hermes_home_for_target_user(target_home_dir: str) -> str:
-    """Remap the current HERMES_HOME to the equivalent under a target user's home.
-
-    When installing a system service via sudo, get_hermes_home() resolves to
-    root's home.  This translates it to the target user's equivalent path:
-      /root/.hermes                    → /home/alice/.hermes
-      /root/.hermes/profiles/coder     → /home/alice/.hermes/profiles/coder
-      /opt/custom-hermes               → /opt/custom-hermes  (kept as-is)
-    """
-    current_hermes = get_hermes_home().resolve()
-    current_default = (Path.home() / ".hermes").resolve()
-    target_default = Path(target_home_dir) / ".hermes"
-
-    # Default ~/.hermes → remap to target user's default
-    if current_hermes == current_default:
-        return str(target_default)
-
-    # Profile or subdir of ~/.hermes → preserve the relative structure
-    try:
-        relative = current_hermes.relative_to(current_default)
-        return str(target_default / relative)
-    except ValueError:
-        # Completely custom path (not under ~/.hermes) — keep as-is
-        return str(current_hermes)
-
-
 def generate_systemd_unit(system: bool = False, run_as_user: str | None = None) -> str:
    python_path = get_python_path()
    working_dir = str(PROJECT_ROOT)
@@ -503,15 +434,13 @@ def generate_systemd_unit(system: bool = False, run_as_user: str | None = None)
        resolved_node_dir = str(Path(resolved_node).resolve().parent)
        if resolved_node_dir not in path_entries:
            path_entries.append(resolved_node_dir)
+    path_entries.extend(["/usr/local/sbin", "/usr/local/bin", "/usr/sbin", "/usr/bin", "/sbin", "/bin"])
+    sane_path = ":".join(path_entries)

-    common_bin_paths = ["/usr/local/sbin", "/usr/local/bin", "/usr/sbin", "/usr/bin", "/sbin", "/bin"]
+    hermes_home = str(get_hermes_home().resolve())

    if system:
        username, group_name, home_dir = _system_service_identity(run_as_user)
-        hermes_home = _hermes_home_for_target_user(home_dir)
-        path_entries.extend(_build_user_local_paths(Path(home_dir), path_entries))
-        path_entries.extend(common_bin_paths)
-        sane_path = ":".join(path_entries)
        return f"""[Unit]
 Description={SERVICE_DESCRIPTION}
 After=network-online.target
@@ -543,10 +472,6 @@ StandardError=journal
 WantedBy=multi-user.target
 """

-    hermes_home = str(get_hermes_home().resolve())
-    path_entries.extend(_build_user_local_paths(Path.home(), path_entries))
-    path_entries.extend(common_bin_paths)
-    sane_path = ":".join(path_entries)
    return f"""[Unit]
 Description={SERVICE_DESCRIPTION}
 After=network.target
@@ -827,46 +752,18 @@ def systemd_status(deep: bool = False, system: bool = False):
 # Launchd (macOS)
 # =============================================================================

-def get_launchd_label() -> str:
-    """Return the launchd service label, scoped per profile."""
-    suffix = _profile_suffix()
-    return f"ai.hermes.gateway-{suffix}" if suffix else "ai.hermes.gateway"
-
-
 def generate_launchd_plist() -> str:
    python_path = get_python_path()
    working_dir = str(PROJECT_ROOT)
-    hermes_home = str(get_hermes_home().resolve())
    log_dir = get_hermes_home() / "logs"
    log_dir.mkdir(parents=True, exist_ok=True)
-    label = get_launchd_label()
-    # Build a sane PATH for the launchd plist.  launchd provides only a
-    # minimal default (/usr/bin:/bin:/usr/sbin:/sbin) which misses Homebrew,
-    # nvm, cargo, etc.  We prepend venv/bin and node_modules/.bin (matching
-    # the systemd unit), then capture the user's full shell PATH so every
-    # user-installed tool (node, ffmpeg, …) is reachable.
-    detected_venv = _detect_venv_dir()
-    venv_bin = str(detected_venv / "bin") if detected_venv else str(PROJECT_ROOT / "venv" / "bin")
-    venv_dir = str(detected_venv) if detected_venv else str(PROJECT_ROOT / "venv")
-    node_bin = str(PROJECT_ROOT / "node_modules" / ".bin")
-    # Resolve the directory containing the node binary (e.g. Homebrew, nvm)
-    # so it's explicitly in PATH even if the user's shell PATH changes later.
-    priority_dirs = [venv_bin, node_bin]
-    resolved_node = shutil.which("node")
-    if resolved_node:
-        resolved_node_dir = str(Path(resolved_node).resolve().parent)
-        if resolved_node_dir not in priority_dirs:
-            priority_dirs.append(resolved_node_dir)
-    sane_path = ":".join(
-        dict.fromkeys(priority_dirs + [p for p in os.environ.get("PATH", "").split(":") if p])
-    )
-
+    
    return f"""<?xml version="1.0" encoding="UTF-8"?>
 <!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
 <plist version="1.0">
 <dict>
    <key>Label</key>
-    <string>{label}</string>
+    <string>ai.hermes.gateway</string>
    
    <key>ProgramArguments</key>
    <array>
@@ -881,16 +778,6 @@ def generate_launchd_plist() -> str:
    <key>WorkingDirectory</key>
    <string>{working_dir}</string>
    
-    <key>EnvironmentVariables</key>
-    <dict>
-        <key>PATH</key>
-        <string>{sane_path}</string>
-        <key>VIRTUAL_ENV</key>
-        <string>{venv_dir}</string>
-        <key>HERMES_HOME</key>
-        <string>{hermes_home}</string>
-    </dict>
-    
    <key>RunAtLoad</key>
    <true/>
    
@@ -963,8 +850,7 @@ def launchd_install(force: bool = False):
    print()
    print("Next steps:")
    print("  hermes gateway status             # Check status")
-    from hermes_constants import display_hermes_home as _dhh
-    print(f"  tail -f {_dhh()}/logs/gateway.log  # View logs")
+    print("  tail -f ~/.hermes/logs/gateway.log  # View logs")

 def launchd_uninstall():
    plist_path = get_launchd_plist_path()
@@ -977,33 +863,20 @@ def launchd_uninstall():
    print("✓ Service uninstalled")

 def launchd_start():
-    plist_path = get_launchd_plist_path()
-    label = get_launchd_label()
-
-    # Self-heal if the plist is missing entirely (e.g., manual cleanup, failed upgrade)
-    if not plist_path.exists():
-        print("↻ launchd plist missing; regenerating service definition")
-        plist_path.parent.mkdir(parents=True, exist_ok=True)
-        plist_path.write_text(generate_launchd_plist(), encoding="utf-8")
-        subprocess.run(["launchctl", "load", str(plist_path)], check=True)
-        subprocess.run(["launchctl", "start", label], check=True)
-        print("✓ Service started")
-        return
-
    refresh_launchd_plist_if_needed()
+    plist_path = get_launchd_plist_path()
    try:
-        subprocess.run(["launchctl", "start", label], check=True)
+        subprocess.run(["launchctl", "start", "ai.hermes.gateway"], check=True)
    except subprocess.CalledProcessError as e:
-        if e.returncode != 3:
+        if e.returncode != 3 or not plist_path.exists():
            raise
        print("↻ launchd job was unloaded; reloading service definition")
        subprocess.run(["launchctl", "load", str(plist_path)], check=True)
-        subprocess.run(["launchctl", "start", label], check=True)
+        subprocess.run(["launchctl", "start", "ai.hermes.gateway"], check=True)
    print("✓ Service started")

 def launchd_stop():
-    label = get_launchd_label()
-    subprocess.run(["launchctl", "stop", label], check=True)
+    subprocess.run(["launchctl", "stop", "ai.hermes.gateway"], check=True)
    print("✓ Service stopped")

 def _wait_for_gateway_exit(timeout: float = 10.0, force_after: float = 5.0):
@@ -1058,9 +931,8 @@ def launchd_restart():

 def launchd_status(deep: bool = False):
    plist_path = get_launchd_plist_path()
-    label = get_launchd_label()
    result = subprocess.run(
-        ["launchctl", "list", label],
+        ["launchctl", "list", "ai.hermes.gateway"],
        capture_output=True,
        text=True
    )
@@ -1348,59 +1220,6 @@ _PLATFORMS = [
             "help": "The AppSecret from your DingTalk application credentials."},
        ],
    },
-    {
-        "key": "feishu",
-        "label": "Feishu / Lark",
-        "emoji": "🪽",
-        "token_var": "FEISHU_APP_ID",
-        "setup_instructions": [
-            "1. Go to https://open.feishu.cn/ (or https://open.larksuite.com/ for Lark)",
-            "2. Create an app and copy the App ID and App Secret",
-            "3. Enable the Bot capability for the app",
-            "4. Choose WebSocket (recommended) or Webhook connection mode",
-            "5. Add the bot to a group chat or message it directly",
-            "6. Restrict access with FEISHU_ALLOWED_USERS for production use",
-        ],
-        "vars": [
-            {"name": "FEISHU_APP_ID", "prompt": "App ID", "password": False,
-             "help": "The App ID from your Feishu/Lark application."},
-            {"name": "FEISHU_APP_SECRET", "prompt": "App Secret", "password": True,
-             "help": "The App Secret from your Feishu/Lark application."},
-            {"name": "FEISHU_DOMAIN", "prompt": "Domain — feishu or lark (default: feishu)", "password": False,
-             "help": "Use 'feishu' for Feishu China, or 'lark' for Lark international."},
-            {"name": "FEISHU_CONNECTION_MODE", "prompt": "Connection mode — websocket or webhook (default: websocket)", "password": False,
-             "help": "websocket is recommended unless you specifically need webhook mode."},
-            {"name": "FEISHU_ALLOWED_USERS", "prompt": "Allowed user IDs (comma-separated, or empty)", "password": False,
-             "is_allowlist": True,
-             "help": "Restrict which Feishu/Lark users can interact with the bot."},
-            {"name": "FEISHU_HOME_CHANNEL", "prompt": "Home chat ID (optional, for cron/notifications)", "password": False,
-             "help": "Chat ID for scheduled results and notifications."},
-        ],
-    },
-    {
-        "key": "wecom",
-        "label": "WeCom (Enterprise WeChat)",
-        "emoji": "💬",
-        "token_var": "WECOM_BOT_ID",
-        "setup_instructions": [
-            "1. Go to WeCom Admin Console → Applications → Create AI Bot",
-            "2. Copy the Bot ID and Secret from the bot's credentials page",
-            "3. The bot connects via WebSocket — no public endpoint needed",
-            "4. Add the bot to a group chat or message it directly in WeCom",
-            "5. Restrict access with WECOM_ALLOWED_USERS for production use",
-        ],
-        "vars": [
-            {"name": "WECOM_BOT_ID", "prompt": "Bot ID", "password": False,
-             "help": "The Bot ID from your WeCom AI Bot."},
-            {"name": "WECOM_SECRET", "prompt": "Secret", "password": True,
-             "help": "The secret from your WeCom AI Bot."},
-            {"name": "WECOM_ALLOWED_USERS", "prompt": "Allowed user IDs (comma-separated, or empty)", "password": False,
-             "is_allowlist": True,
-             "help": "Restrict which WeCom users can interact with the bot."},
-            {"name": "WECOM_HOME_CHANNEL", "prompt": "Home chat ID (optional, for cron/notifications)", "password": False,
-             "help": "Chat ID for scheduled results and notifications."},
-        ],
-    },
 ]


@@ -1618,7 +1437,7 @@ def _is_service_running() -> bool:
        return False
    elif is_macos() and get_launchd_plist_path().exists():
        result = subprocess.run(
-            ["launchctl", "list", get_launchd_label()],
+            ["launchctl", "list", "ai.hermes.gateway"],
            capture_output=True, text=True
        )
        return result.returncode == 0
@@ -24,7 +24,6 @@ from hermes_cli.config import (
    get_hermes_home,  # noqa: F401 — used by test mocks
 )
 from hermes_cli.colors import Colors, color
-from hermes_constants import display_hermes_home

 logger = logging.getLogger(__name__)

@@ -245,7 +244,7 @@ def cmd_mcp_add(args):
                    api_key = _prompt("API key / Bearer token", password=True)
                    if api_key:
                        save_env_value(env_key, api_key)
-                        _success(f"Saved to {display_hermes_home()}/.env as {env_key}")
+                        _success(f"Saved to ~/.hermes/.env as {env_key}")

                # Set header with env var interpolation
                if api_key or existing_key:
@@ -333,7 +332,7 @@ def cmd_mcp_add(args):
    _save_mcp_server(name, server_config)

    print()
-    _success(f"Saved '{name}' to {display_hermes_home()}/config.yaml ({tool_count}/{total} tools enabled)")
+    _success(f"Saved '{name}' to ~/.hermes/config.yaml ({tool_count}/{total} tools enabled)")
    _info("Start a new session to use these tools.")


@@ -511,10 +510,6 @@ def _interpolate_value(value: str) -> str:

 def cmd_mcp_configure(args):
    """Reconfigure which tools are enabled for an existing MCP server."""
-    import sys as _sys
-    if not _sys.stdin.isatty():
-        print("Error: 'hermes mcp configure' requires an interactive terminal.", file=_sys.stderr)
-        _sys.exit(1)
    name = args.name
    servers = _get_mcp_servers()

@@ -612,11 +607,6 @@ def mcp_command(args):
    """Main dispatcher for ``hermes mcp`` subcommands."""
    action = getattr(args, "mcp_action", None)

-    if action == "serve":
-        from mcp_serve import run_mcp_server
-        run_mcp_server(verbose=getattr(args, "verbose", False))
-        return
-
    handlers = {
        "add": cmd_mcp_add,
        "remove": cmd_mcp_remove,
@@ -635,7 +625,6 @@ def mcp_command(args):
        # No subcommand — show list
        cmd_mcp_list()
        print(color("  Commands:", Colors.CYAN))
-        _info("hermes mcp serve                              Run as MCP server")
        _info("hermes mcp add <name> --url <endpoint>        Add an MCP server")
        _info("hermes mcp add <name> --command <cmd>         Add a stdio server")
        _info("hermes mcp remove <name>                      Remove a server")
@@ -27,8 +27,6 @@ GITHUB_MODELS_CATALOG_URL = COPILOT_MODELS_URL
 # (model_id, display description shown in menus)
 OPENROUTER_MODELS: list[tuple[str, str]] = [
    ("anthropic/claude-opus-4.6",       "recommended"),
-    ("anthropic/claude-sonnet-4.6",     ""),
-    ("qwen/qwen3.6-plus-preview:free", "free"),
    ("anthropic/claude-sonnet-4.5",     ""),
    ("anthropic/claude-haiku-4.5",      ""),
    ("openai/gpt-5.4",                  ""),
@@ -37,8 +35,6 @@ OPENROUTER_MODELS: list[tuple[str, str]] = [
    ("openai/gpt-5.3-codex",            ""),
    ("google/gemini-3-pro-preview",     ""),
    ("google/gemini-3-flash-preview",   ""),
-    ("google/gemini-3.1-pro-preview",     ""),
-    ("google/gemini-3.1-flash-lite-preview",   ""),
    ("qwen/qwen3.5-plus-02-15",         ""),
    ("qwen/qwen3.5-35b-a3b",            ""),
    ("stepfun/step-3.5-flash",          ""),
@@ -58,8 +54,6 @@ OPENROUTER_MODELS: list[tuple[str, str]] = [
 _PROVIDER_MODELS: dict[str, list[str]] = {
    "nous": [
        "anthropic/claude-opus-4.6",
-        "anthropic/claude-sonnet-4.6",
-        "qwen/qwen3.6-plus-preview:free",
        "anthropic/claude-sonnet-4.5",
        "anthropic/claude-haiku-4.5",
        "openai/gpt-5.4",
@@ -68,8 +62,6 @@ _PROVIDER_MODELS: dict[str, list[str]] = {
        "openai/gpt-5.3-codex",
        "google/gemini-3-pro-preview",
        "google/gemini-3-flash-preview",
-        "google/gemini-3.1-pro-preview",
-        "google/gemini-3.1-flash-lite-preview",
        "qwen/qwen3.5-plus-02-15",
        "qwen/qwen3.5-35b-a3b",
        "stepfun/step-3.5-flash",
@@ -193,7 +185,7 @@ _PROVIDER_MODELS: dict[str, list[str]] = {
    "opencode-go": [
        "glm-5",
        "kimi-k2.5",
-        "minimax-m2.7",
+        "minimax-m2.5",
    ],
    "ai-gateway": [
        "anthropic/claude-opus-4.6",
@@ -216,31 +208,14 @@ _PROVIDER_MODELS: dict[str, list[str]] = {
        "google/gemini-3-pro-preview",
        "google/gemini-3-flash-preview",
    ],
-    # Alibaba DashScope Coding platform (coding-intl) — default endpoint.
-    # Supports Qwen models + third-party providers (GLM, Kimi, MiniMax).
-    # Users with classic DashScope keys should override DASHSCOPE_BASE_URL
-    # to https://dashscope-intl.aliyuncs.com/compatible-mode/v1 (OpenAI-compat)
-    # or https://dashscope-intl.aliyuncs.com/apps/anthropic (Anthropic-compat).
    "alibaba": [
        "qwen3.5-plus",
+        "qwen3-max",
        "qwen3-coder-plus",
        "qwen3-coder-next",
-        # Third-party models available on coding-intl
-        "glm-5",
-        "glm-4.7",
-        "kimi-k2.5",
-        "MiniMax-M2.5",
-    ],
-    # Curated HF model list — only agentic models that map to OpenRouter defaults.
-    "huggingface": [
-        "Qwen/Qwen3.5-397B-A17B",
-        "Qwen/Qwen3.5-35B-A3B",
-        "deepseek-ai/DeepSeek-V3.2",
-        "moonshotai/Kimi-K2.5",
-        "MiniMaxAI/MiniMax-M2.5",
-        "zai-org/GLM-5",
-        "XiaomiMiMo/MiMo-V2-Flash",
-        "moonshotai/Kimi-K2-Thinking",
+        "qwen-plus-latest",
+        "qwen3.5-flash",
+        "qwen-vl-max",
    ],
 }

@@ -261,7 +236,6 @@ _PROVIDER_LABELS = {
    "ai-gateway": "AI Gateway",
    "kilocode": "Kilo Code",
    "alibaba": "Alibaba Cloud (DashScope)",
-    "huggingface": "Hugging Face",
    "custom": "Custom endpoint",
 }

@@ -297,9 +271,6 @@ _PROVIDER_ALIASES = {
    "aliyun": "alibaba",
    "qwen": "alibaba",
    "alibaba-cloud": "alibaba",
-    "hf": "huggingface",
-    "hugging-face": "huggingface",
-    "huggingface-hub": "huggingface",
 }


@@ -333,7 +304,7 @@ def list_available_providers() -> list[dict[str, str]]:
    # Canonical providers in display order
    _PROVIDER_ORDER = [
        "openrouter", "nous", "openai-codex", "copilot", "copilot-acp",
-        "huggingface", "zai", "kimi-coding", "minimax", "minimax-cn", "kilocode", "anthropic", "alibaba",
+        "zai", "kimi-coding", "minimax", "minimax-cn", "kilocode", "anthropic", "alibaba",
        "opencode-zen", "opencode-go",
        "ai-gateway", "deepseek", "custom",
    ]
@@ -351,7 +322,7 @@ def list_available_providers() -> list[dict[str, str]]:
        try:
            from hermes_cli.auth import get_auth_status, has_usable_secret
            if pid == "custom":
-                custom_base_url = _get_custom_base_url() or ""
+                custom_base_url = _get_custom_base_url() or os.getenv("OPENAI_BASE_URL", "")
                has_creds = bool(custom_base_url.strip())
            elif pid == "openrouter":
                has_creds = has_usable_secret(os.getenv("OPENROUTER_API_KEY", ""))
@@ -68,17 +68,6 @@ def _env_enabled(name: str) -> bool:
    return os.getenv(name, "").strip().lower() in {"1", "true", "yes", "on"}


-def _get_disabled_plugins() -> set:
-    """Read the disabled plugins list from config.yaml."""
-    try:
-        from hermes_cli.config import load_config
-        config = load_config()
-        disabled = config.get("plugins", {}).get("disabled", [])
-        return set(disabled) if isinstance(disabled, list) else set()
-    except Exception:
-        return set()
-
-
 # ---------------------------------------------------------------------------
 # Data classes
 # ---------------------------------------------------------------------------
@@ -152,34 +141,6 @@ class PluginContext:
        self._manager._plugin_tool_names.add(name)
        logger.debug("Plugin %s registered tool: %s", self.manifest.name, name)

-    # -- message injection --------------------------------------------------
-
-    def inject_message(self, content: str, role: str = "user") -> bool:
-        """Inject a message into the active conversation.
-
-        If the agent is idle (waiting for user input), this starts a new turn.
-        If the agent is running, this interrupts and injects the message.
-
-        This enables plugins (e.g. remote control viewers, messaging bridges)
-        to send messages into the conversation from external sources.
-
-        Returns True if the message was queued successfully.
-        """
-        cli = self._manager._cli_ref
-        if cli is None:
-            logger.warning("inject_message: no CLI reference (not available in gateway mode)")
-            return False
-
-        msg = content if role == "user" else f"[{role}] {content}"
-
-        if getattr(cli, "_agent_running", False):
-            # Agent is mid-turn — interrupt with the message
-            cli._interrupt_queue.put(msg)
-        else:
-            # Agent is idle — queue as next input
-            cli._pending_input.put(msg)
-        return True
-
    # -- hook registration --------------------------------------------------

    def register_hook(self, hook_name: str, callback: Callable) -> None:
@@ -212,7 +173,6 @@ class PluginManager:
        self._hooks: Dict[str, List[Callable]] = {}
        self._plugin_tool_names: Set[str] = set()
        self._discovered: bool = False
-        self._cli_ref = None  # Set by CLI after plugin discovery

    # -----------------------------------------------------------------------
    # Public
@@ -239,15 +199,8 @@ class PluginManager:
        # 3. Pip / entry-point plugins
        manifests.extend(self._scan_entry_points())

-        # Load each manifest (skip user-disabled plugins)
-        disabled = _get_disabled_plugins()
+        # Load each manifest
        for manifest in manifests:
-            if manifest.name in disabled:
-                loaded = LoadedPlugin(manifest=manifest, enabled=False)
-                loaded.error = "disabled via config"
-                self._plugins[manifest.name] = loaded
-                logger.debug("Skipping disabled plugin '%s'", manifest.name)
-                continue
            self._load_plugin(manifest)

        if manifests:
@@ -432,23 +385,16 @@ class PluginManager:
    # Hook invocation
    # -----------------------------------------------------------------------

-    def invoke_hook(self, hook_name: str, **kwargs: Any) -> List[Any]:
+    def invoke_hook(self, hook_name: str, **kwargs: Any) -> None:
        """Call all registered callbacks for *hook_name*.

        Each callback is wrapped in its own try/except so a misbehaving
        plugin cannot break the core agent loop.
-
-        Returns a list of non-``None`` return values from callbacks.
-        This allows hooks like ``pre_llm_call`` to contribute context
-        that the agent core can collect and inject.
        """
        callbacks = self._hooks.get(hook_name, [])
-        results: List[Any] = []
        for cb in callbacks:
            try:
-                ret = cb(**kwargs)
-                if ret is not None:
-                    results.append(ret)
+                cb(**kwargs)
            except Exception as exc:
                logger.warning(
                    "Hook '%s' callback %s raised: %s",
@@ -456,7 +402,6 @@ class PluginManager:
                    getattr(cb, "__name__", repr(cb)),
                    exc,
                )
-        return results

    # -----------------------------------------------------------------------
    # Introspection
@@ -501,12 +446,9 @@ def discover_plugins() -> None:
    get_plugin_manager().discover_and_load()


-def invoke_hook(hook_name: str, **kwargs: Any) -> List[Any]:
-    """Invoke a lifecycle hook on all loaded plugins.
-
-    Returns a list of non-``None`` return values from plugin callbacks.
-    """
-    return get_plugin_manager().invoke_hook(hook_name, **kwargs)
+def invoke_hook(hook_name: str, **kwargs: Any) -> None:
+    """Invoke a lifecycle hook on all loaded plugins."""
+    get_plugin_manager().invoke_hook(hook_name, **kwargs)


 def get_plugin_tool_names() -> Set[str]:
@@ -265,11 +265,10 @@ def cmd_install(identifier: str, force: bool = False) -> None:
                )
                sys.exit(1)
            if mv_int > _SUPPORTED_MANIFEST_VERSION:
-                from hermes_cli.config import recommended_update_command
                console.print(
                    f"[red]Error:[/red] Plugin '{plugin_name}' requires manifest_version "
                    f"{mv}, but this installer only supports up to {_SUPPORTED_MANIFEST_VERSION}.\n"
-                    f"Run [bold]{recommended_update_command()}[/bold] to get a newer installer."
+                    f"Run [bold]hermes update[/bold] to get a newer installer."
                )
                sys.exit(1)

@@ -375,73 +374,6 @@ def cmd_remove(name: str) -> None:
    _display_removed(name, plugins_dir)


-def _get_disabled_set() -> set:
-    """Read the disabled plugins set from config.yaml."""
-    try:
-        from hermes_cli.config import load_config
-        config = load_config()
-        disabled = config.get("plugins", {}).get("disabled", [])
-        return set(disabled) if isinstance(disabled, list) else set()
-    except Exception:
-        return set()
-
-
-def _save_disabled_set(disabled: set) -> None:
-    """Write the disabled plugins list to config.yaml."""
-    from hermes_cli.config import load_config, save_config
-    config = load_config()
-    if "plugins" not in config:
-        config["plugins"] = {}
-    config["plugins"]["disabled"] = sorted(disabled)
-    save_config(config)
-
-
-def cmd_enable(name: str) -> None:
-    """Enable a previously disabled plugin."""
-    from rich.console import Console
-
-    console = Console()
-    plugins_dir = _plugins_dir()
-
-    # Verify the plugin exists
-    target = plugins_dir / name
-    if not target.is_dir():
-        console.print(f"[red]Plugin '{name}' is not installed.[/red]")
-        sys.exit(1)
-
-    disabled = _get_disabled_set()
-    if name not in disabled:
-        console.print(f"[dim]Plugin '{name}' is already enabled.[/dim]")
-        return
-
-    disabled.discard(name)
-    _save_disabled_set(disabled)
-    console.print(f"[green]✓[/green] Plugin [bold]{name}[/bold] enabled. Takes effect on next session.")
-
-
-def cmd_disable(name: str) -> None:
-    """Disable a plugin without removing it."""
-    from rich.console import Console
-
-    console = Console()
-    plugins_dir = _plugins_dir()
-
-    # Verify the plugin exists
-    target = plugins_dir / name
-    if not target.is_dir():
-        console.print(f"[red]Plugin '{name}' is not installed.[/red]")
-        sys.exit(1)
-
-    disabled = _get_disabled_set()
-    if name in disabled:
-        console.print(f"[dim]Plugin '{name}' is already disabled.[/dim]")
-        return
-
-    disabled.add(name)
-    _save_disabled_set(disabled)
-    console.print(f"[yellow]⊘[/yellow] Plugin [bold]{name}[/bold] disabled. Takes effect on next session.")
-
-
 def cmd_list() -> None:
    """List installed plugins."""
    from rich.console import Console
@@ -461,11 +393,8 @@ def cmd_list() -> None:
        console.print("[dim]Install with:[/dim] hermes plugins install owner/repo")
        return

-    disabled = _get_disabled_set()
-
    table = Table(title="Installed Plugins", show_lines=False)
    table.add_column("Name", style="bold")
-    table.add_column("Status")
    table.add_column("Version", style="dim")
    table.add_column("Description")
    table.add_column("Source", style="dim")
@@ -491,86 +420,11 @@ def cmd_list() -> None:
        if (d / ".git").exists():
            source = "git"

-        is_disabled = name in disabled or d.name in disabled
-        status = "[red]disabled[/red]" if is_disabled else "[green]enabled[/green]"
-        table.add_row(name, status, str(version), description, source)
+        table.add_row(name, str(version), description, source)

    console.print()
    console.print(table)
    console.print()
-    console.print("[dim]Interactive toggle:[/dim] hermes plugins")
-    console.print("[dim]Enable/disable:[/dim] hermes plugins enable/disable <name>")
-
-
-def cmd_toggle() -> None:
-    """Interactive curses checklist to enable/disable installed plugins."""
-    from rich.console import Console
-
-    try:
-        import yaml
-    except ImportError:
-        yaml = None
-
-    console = Console()
-    plugins_dir = _plugins_dir()
-
-    dirs = sorted(d for d in plugins_dir.iterdir() if d.is_dir())
-    if not dirs:
-        console.print("[dim]No plugins installed.[/dim]")
-        console.print("[dim]Install with:[/dim] hermes plugins install owner/repo")
-        return
-
-    disabled = _get_disabled_set()
-
-    # Build items list: "name — description" for display
-    names = []
-    labels = []
-    selected = set()
-
-    for i, d in enumerate(dirs):
-        manifest_file = d / "plugin.yaml"
-        name = d.name
-        description = ""
-
-        if manifest_file.exists() and yaml:
-            try:
-                with open(manifest_file) as f:
-                    manifest = yaml.safe_load(f) or {}
-                name = manifest.get("name", d.name)
-                description = manifest.get("description", "")
-            except Exception:
-                pass
-
-        names.append(name)
-        label = f"{name} — {description}" if description else name
-        labels.append(label)
-
-        if name not in disabled and d.name not in disabled:
-            selected.add(i)
-
-    from hermes_cli.curses_ui import curses_checklist
-
-    result = curses_checklist(
-        title="Plugins — toggle enabled/disabled",
-        items=labels,
-        selected=selected,
-    )
-
-    # Compute new disabled set from deselected items
-    new_disabled = set()
-    for i, name in enumerate(names):
-        if i not in result:
-            new_disabled.add(name)
-
-    if new_disabled != disabled:
-        _save_disabled_set(new_disabled)
-        enabled_count = len(names) - len(new_disabled)
-        console.print(
-            f"\n[green]✓[/green] {enabled_count} enabled, {len(new_disabled)} disabled. "
-            f"Takes effect on next session."
-        )
-    else:
-        console.print("\n[dim]No changes.[/dim]")


 def plugins_command(args) -> None:
@@ -583,14 +437,8 @@ def plugins_command(args) -> None:
        cmd_update(args.name)
    elif action in ("remove", "rm", "uninstall"):
        cmd_remove(args.name)
-    elif action == "enable":
-        cmd_enable(args.name)
-    elif action == "disable":
-        cmd_disable(args.name)
-    elif action in ("list", "ls"):
+    elif action in ("list", "ls") or action is None:
        cmd_list()
-    elif action is None:
-        cmd_toggle()
    else:
        from rich.console import Console

@@ -6,10 +6,8 @@ import os
 from typing import Any, Dict, Optional

 from hermes_cli import auth as auth_mod
-from agent.credential_pool import CredentialPool, PooledCredential, get_custom_provider_pool_key, load_pool
 from hermes_cli.auth import (
    AuthError,
-    DEFAULT_CODEX_BASE_URL,
    PROVIDER_REGISTRY,
    format_auth_error,
    resolve_provider,
@@ -65,11 +63,8 @@ def _get_model_config() -> Dict[str, Any]:
    model_cfg = config.get("model")
    if isinstance(model_cfg, dict):
        cfg = dict(model_cfg)
-        # Accept "model" as alias for "default" (users intuitively write model.model)
-        if not cfg.get("default") and cfg.get("model"):
-            cfg["default"] = cfg["model"]
-        default = (cfg.get("default") or "").strip()
-        base_url = (cfg.get("base_url") or "").strip()
+        default = cfg.get("default", "").strip()
+        base_url = cfg.get("base_url", "").strip()
        is_local = "localhost" in base_url or "127.0.0.1" in base_url
        is_fallback = not default or default == "anthropic/claude-opus-4.6"
        if is_local and is_fallback and base_url:
@@ -111,50 +106,6 @@ def _parse_api_mode(raw: Any) -> Optional[str]:
    return None


-def _resolve_runtime_from_pool_entry(
-    *,
-    provider: str,
-    entry: PooledCredential,
-    requested_provider: str,
-    model_cfg: Optional[Dict[str, Any]] = None,
-    pool: Optional[CredentialPool] = None,
-) -> Dict[str, Any]:
-    model_cfg = model_cfg or _get_model_config()
-    base_url = (getattr(entry, "runtime_base_url", None) or getattr(entry, "base_url", None) or "").rstrip("/")
-    api_key = getattr(entry, "runtime_api_key", None) or getattr(entry, "access_token", "")
-    api_mode = "chat_completions"
-    if provider == "openai-codex":
-        api_mode = "codex_responses"
-        base_url = base_url or DEFAULT_CODEX_BASE_URL
-    elif provider == "anthropic":
-        api_mode = "anthropic_messages"
-        cfg_provider = str(model_cfg.get("provider") or "").strip().lower()
-        cfg_base_url = ""
-        if cfg_provider == "anthropic":
-            cfg_base_url = str(model_cfg.get("base_url") or "").strip().rstrip("/")
-        base_url = cfg_base_url or base_url or "https://api.anthropic.com"
-    elif provider == "nous":
-        api_mode = "chat_completions"
-    elif provider == "copilot":
-        api_mode = _copilot_runtime_api_mode(model_cfg, getattr(entry, "runtime_api_key", ""))
-    else:
-        configured_mode = _parse_api_mode(model_cfg.get("api_mode"))
-        if configured_mode:
-            api_mode = configured_mode
-        elif base_url.rstrip("/").endswith("/anthropic"):
-            api_mode = "anthropic_messages"
-
-    return {
-        "provider": provider,
-        "api_mode": api_mode,
-        "base_url": base_url,
-        "api_key": api_key,
-        "source": getattr(entry, "source", "pool"),
-        "credential_pool": pool,
-        "requested_provider": requested_provider,
-    }
-
-
 def resolve_requested_provider(requested: Optional[str] = None) -> str:
    """Resolve provider request from explicit arg, config, then env."""
    if requested and requested.strip():
@@ -174,37 +125,6 @@ def resolve_requested_provider(requested: Optional[str] = None) -> str:
    return "auto"


-def _try_resolve_from_custom_pool(
-    base_url: str,
-    provider_label: str,
-    api_mode_override: Optional[str] = None,
-) -> Optional[Dict[str, Any]]:
-    """Check if a credential pool exists for a custom endpoint and return a runtime dict if so."""
-    pool_key = get_custom_provider_pool_key(base_url)
-    if not pool_key:
-        return None
-    try:
-        pool = load_pool(pool_key)
-        if not pool.has_credentials():
-            return None
-        entry = pool.select()
-        if entry is None:
-            return None
-        pool_api_key = getattr(entry, "runtime_api_key", None) or getattr(entry, "access_token", "")
-        if not pool_api_key:
-            return None
-        return {
-            "provider": provider_label,
-            "api_mode": api_mode_override or _detect_api_mode_for_url(base_url) or "chat_completions",
-            "base_url": base_url,
-            "api_key": pool_api_key,
-            "source": f"pool:{pool_key}",
-            "credential_pool": pool,
-        }
-    except Exception:
-        return None
-
-
 def _get_named_custom_provider(requested_provider: str) -> Optional[Dict[str, Any]]:
    requested_norm = _normalize_custom_provider_name(requested_provider or "")
    if not requested_norm or requested_norm == "custom":
@@ -269,11 +189,6 @@ def _resolve_named_custom_runtime(
    if not base_url:
        return None

-    # Check if a credential pool exists for this custom endpoint
-    pool_result = _try_resolve_from_custom_pool(base_url, "custom", custom_provider.get("api_mode"))
-    if pool_result:
-        return pool_result
-
    api_key_candidates = [
        (explicit_api_key or "").strip(),
        str(custom_provider.get("api_key", "") or "").strip(),
@@ -288,7 +203,7 @@ def _resolve_named_custom_runtime(
        or _detect_api_mode_for_url(base_url)
        or "chat_completions",
        "base_url": base_url,
-        "api_key": api_key or "no-key-required",
+        "api_key": api_key,
        "source": f"custom_provider:{custom_provider.get('name', requested_provider)}",
    }

@@ -311,22 +226,28 @@ def _resolve_openrouter_runtime(
    requested_norm = (requested_provider or "").strip().lower()
    cfg_provider = cfg_provider.strip().lower()

+    env_openai_base_url = os.getenv("OPENAI_BASE_URL", "").strip()
    env_openrouter_base_url = os.getenv("OPENROUTER_BASE_URL", "").strip()

-    # Use config base_url when available and the provider context matches.
-    # OPENAI_BASE_URL env var is no longer consulted — config.yaml is
-    # the single source of truth for endpoint URLs.
    use_config_base_url = False
    if cfg_base_url.strip() and not explicit_base_url:
        if requested_norm == "auto":
-            if not cfg_provider or cfg_provider == "auto":
+            if (not cfg_provider or cfg_provider == "auto") and not env_openai_base_url:
                use_config_base_url = True
        elif requested_norm == "custom" and cfg_provider == "custom":
+            # provider: custom — use base_url from config (Fixes #1760).
            use_config_base_url = True

+    # When the user explicitly requested the openrouter provider, skip
+    # OPENAI_BASE_URL — it typically points to a custom / non-OpenRouter
+    # endpoint and would prevent switching back to OpenRouter (#874).
+    skip_openai_base = requested_norm == "openrouter"
+
+    # For custom, prefer config base_url over env so config.yaml is honored (#1760).
    base_url = (
        (explicit_base_url or "").strip()
        or (cfg_base_url.strip() if use_config_base_url else "")
+        or ("" if skip_openai_base else env_openai_base_url)
        or env_openrouter_base_url
        or OPENROUTER_BASE_URL
    ).rstrip("/")
@@ -363,15 +284,6 @@ def _resolve_openrouter_runtime(
    # Also provide a placeholder API key for local servers that don't require
    # authentication — the OpenAI SDK requires a non-empty api_key string.
    effective_provider = "custom" if requested_norm == "custom" else "openrouter"
-
-    # For custom endpoints, check if a credential pool exists
-    if effective_provider == "custom" and base_url:
-        pool_result = _try_resolve_from_custom_pool(
-            base_url, effective_provider, _parse_api_mode(model_cfg.get("api_mode")),
-        )
-        if pool_result:
-            return pool_result
-
    if effective_provider == "custom" and not api_key and not _is_openrouter_url:
        api_key = "no-key-required"

@@ -386,134 +298,6 @@ def _resolve_openrouter_runtime(
    }


-def _resolve_explicit_runtime(
-    *,
-    provider: str,
-    requested_provider: str,
-    model_cfg: Dict[str, Any],
-    explicit_api_key: Optional[str] = None,
-    explicit_base_url: Optional[str] = None,
-) -> Optional[Dict[str, Any]]:
-    explicit_api_key = str(explicit_api_key or "").strip()
-    explicit_base_url = str(explicit_base_url or "").strip().rstrip("/")
-    if not explicit_api_key and not explicit_base_url:
-        return None
-
-    if provider == "anthropic":
-        cfg_provider = str(model_cfg.get("provider") or "").strip().lower()
-        cfg_base_url = ""
-        if cfg_provider == "anthropic":
-            cfg_base_url = str(model_cfg.get("base_url") or "").strip().rstrip("/")
-        base_url = explicit_base_url or cfg_base_url or "https://api.anthropic.com"
-        api_key = explicit_api_key
-        if not api_key:
-            from agent.anthropic_adapter import resolve_anthropic_token
-
-            api_key = resolve_anthropic_token()
-            if not api_key:
-                raise AuthError(
-                    "No Anthropic credentials found. Set ANTHROPIC_TOKEN or ANTHROPIC_API_KEY, "
-                    "run 'claude setup-token', or authenticate with 'claude /login'."
-                )
-        return {
-            "provider": "anthropic",
-            "api_mode": "anthropic_messages",
-            "base_url": base_url,
-            "api_key": api_key,
-            "source": "explicit",
-            "requested_provider": requested_provider,
-        }
-
-    if provider == "openai-codex":
-        base_url = explicit_base_url or DEFAULT_CODEX_BASE_URL
-        api_key = explicit_api_key
-        last_refresh = None
-        if not api_key:
-            creds = resolve_codex_runtime_credentials()
-            api_key = creds.get("api_key", "")
-            last_refresh = creds.get("last_refresh")
-            if not explicit_base_url:
-                base_url = creds.get("base_url", "").rstrip("/") or base_url
-        return {
-            "provider": "openai-codex",
-            "api_mode": "codex_responses",
-            "base_url": base_url,
-            "api_key": api_key,
-            "source": "explicit",
-            "last_refresh": last_refresh,
-            "requested_provider": requested_provider,
-        }
-
-    if provider == "nous":
-        state = auth_mod.get_provider_auth_state("nous") or {}
-        base_url = (
-            explicit_base_url
-            or str(state.get("inference_base_url") or auth_mod.DEFAULT_NOUS_INFERENCE_URL).strip().rstrip("/")
-        )
-        api_key = explicit_api_key or str(state.get("agent_key") or state.get("access_token") or "").strip()
-        expires_at = state.get("agent_key_expires_at") or state.get("expires_at")
-        if not api_key:
-            creds = resolve_nous_runtime_credentials(
-                min_key_ttl_seconds=max(60, int(os.getenv("HERMES_NOUS_MIN_KEY_TTL_SECONDS", "1800"))),
-                timeout_seconds=float(os.getenv("HERMES_NOUS_TIMEOUT_SECONDS", "15")),
-            )
-            api_key = creds.get("api_key", "")
-            expires_at = creds.get("expires_at")
-            if not explicit_base_url:
-                base_url = creds.get("base_url", "").rstrip("/") or base_url
-        return {
-            "provider": "nous",
-            "api_mode": "chat_completions",
-            "base_url": base_url,
-            "api_key": api_key,
-            "source": "explicit",
-            "expires_at": expires_at,
-            "requested_provider": requested_provider,
-        }
-
-    pconfig = PROVIDER_REGISTRY.get(provider)
-    if pconfig and pconfig.auth_type == "api_key":
-        env_url = ""
-        if pconfig.base_url_env_var:
-            env_url = os.getenv(pconfig.base_url_env_var, "").strip().rstrip("/")
-
-        base_url = explicit_base_url
-        if not base_url:
-            if provider == "kimi-coding":
-                creds = resolve_api_key_provider_credentials(provider)
-                base_url = creds.get("base_url", "").rstrip("/")
-            else:
-                base_url = env_url or pconfig.inference_base_url
-
-        api_key = explicit_api_key
-        if not api_key:
-            creds = resolve_api_key_provider_credentials(provider)
-            api_key = creds.get("api_key", "")
-            if not base_url:
-                base_url = creds.get("base_url", "").rstrip("/")
-
-        api_mode = "chat_completions"
-        if provider == "copilot":
-            api_mode = _copilot_runtime_api_mode(model_cfg, api_key)
-        else:
-            configured_mode = _parse_api_mode(model_cfg.get("api_mode"))
-            if configured_mode:
-                api_mode = configured_mode
-            elif base_url.rstrip("/").endswith("/anthropic"):
-                api_mode = "anthropic_messages"
-
-        return {
-            "provider": provider,
-            "api_mode": api_mode,
-            "base_url": base_url.rstrip("/"),
-            "api_key": api_key,
-            "source": "explicit",
-            "requested_provider": requested_provider,
-        }
-
-    return None
-
-
 def resolve_runtime_provider(
    *,
    requested: Optional[str] = None,
@@ -537,57 +321,6 @@ def resolve_runtime_provider(
        explicit_api_key=explicit_api_key,
        explicit_base_url=explicit_base_url,
    )
-    model_cfg = _get_model_config()
-    explicit_runtime = _resolve_explicit_runtime(
-        provider=provider,
-        requested_provider=requested_provider,
-        model_cfg=model_cfg,
-        explicit_api_key=explicit_api_key,
-        explicit_base_url=explicit_base_url,
-    )
-    if explicit_runtime:
-        return explicit_runtime
-
-    should_use_pool = provider != "openrouter"
-    if provider == "openrouter":
-        cfg_provider = str(model_cfg.get("provider") or "").strip().lower()
-        cfg_base_url = str(model_cfg.get("base_url") or "").strip()
-        env_openai_base_url = os.getenv("OPENAI_BASE_URL", "").strip()
-        env_openrouter_base_url = os.getenv("OPENROUTER_BASE_URL", "").strip()
-        has_custom_endpoint = bool(
-            explicit_base_url
-            or env_openai_base_url
-            or env_openrouter_base_url
-        )
-        if cfg_base_url and cfg_provider in {"auto", "custom"}:
-            has_custom_endpoint = True
-        has_runtime_override = bool(explicit_api_key or explicit_base_url)
-        should_use_pool = (
-            requested_provider in {"openrouter", "auto"}
-            and not has_custom_endpoint
-            and not has_runtime_override
-        )
-
-    try:
-        pool = load_pool(provider) if should_use_pool else None
-    except Exception:
-        pool = None
-    if pool and pool.has_credentials():
-        entry = pool.select()
-        pool_api_key = ""
-        if entry is not None:
-            pool_api_key = (
-                getattr(entry, "runtime_api_key", None)
-                or getattr(entry, "access_token", "")
-            )
-        if entry is not None and pool_api_key:
-            return _resolve_runtime_from_pool_entry(
-                provider=provider,
-                entry=entry,
-                requested_provider=requested_provider,
-                model_cfg=model_cfg,
-                pool=pool,
-            )

    if provider == "nous":
        creds = resolve_nous_runtime_credentials(
@@ -641,6 +374,7 @@ def resolve_runtime_provider(
        # Allow base URL override from config.yaml model.base_url, but only
        # when the configured provider is anthropic — otherwise a non-Anthropic
        # base_url (e.g. Codex endpoint) would leak into Anthropic requests.
+        model_cfg = _get_model_config()
        cfg_provider = str(model_cfg.get("provider") or "").strip().lower()
        cfg_base_url = ""
        if cfg_provider == "anthropic":
@@ -659,6 +393,7 @@ def resolve_runtime_provider(
    pconfig = PROVIDER_REGISTRY.get(provider)
    if pconfig and pconfig.auth_type == "api_key":
        creds = resolve_api_key_provider_credentials(provider)
+        model_cfg = _get_model_config()
        base_url = creds.get("base_url", "").rstrip("/")
        api_mode = "chat_completions"
        if provider == "copilot":
@@ -672,6 +407,12 @@ def resolve_runtime_provider(
            # (e.g. https://api.minimax.io/anthropic, https://dashscope.../anthropic)
            elif base_url.rstrip("/").endswith("/anthropic"):
                api_mode = "anthropic_messages"
+            # MiniMax providers always use Anthropic Messages API.
+            # Auto-correct stale /v1 URLs (from old .env or config) to /anthropic.
+            elif provider in ("minimax", "minimax-cn"):
+                api_mode = "anthropic_messages"
+                if base_url.rstrip("/").endswith("/v1"):
+                    base_url = base_url.rstrip("/")[:-3] + "/anthropic"
        return {
            "provider": provider,
            "api_mode": api_mode,
@@ -24,12 +24,6 @@ PLATFORMS = {
    "whatsapp": "📱 WhatsApp",
    "signal":   "📡 Signal",
    "email":    "📧 Email",
-    "homeassistant": "🏠 Home Assistant",
-    "mattermost": "💬 Mattermost",
-    "matrix":   "💬 Matrix",
-    "dingtalk": "💬 DingTalk",
-    "feishu": "🪽 Feishu",
-    "wecom": "💬 WeCom",
 }

 # ─── Config Helpers ───────────────────────────────────────────────────────────
@@ -21,7 +21,6 @@ from rich.table import Table

 # Lazy imports to avoid circular dependencies and slow startup.
 # tools.skills_hub and tools.skills_guard are imported inside functions.
-from hermes_constants import display_hermes_home

 _console = Console()

@@ -305,8 +304,7 @@ def do_browse(page: int = 1, page_size: int = 20, source: str = "all",


 def do_install(identifier: str, category: str = "", force: bool = False,
-               console: Optional[Console] = None, skip_confirm: bool = False,
-               invalidate_cache: bool = True) -> None:
+               console: Optional[Console] = None, skip_confirm: bool = False) -> None:
    """Fetch, quarantine, scan, confirm, and install a skill."""
    from tools.skills_hub import (
        GitHubAuth, create_source_router, ensure_hub_dirs,
@@ -354,14 +352,7 @@ def do_install(identifier: str, category: str = "", force: bool = False,
    extra_metadata.update(getattr(bundle, "metadata", {}) or {})

    # Quarantine the bundle
-    try:
-        q_path = quarantine_bundle(bundle)
-    except ValueError as exc:
-        c.print(f"[bold red]Installation blocked:[/] {exc}\n")
-        from tools.skills_hub import append_audit_log
-        append_audit_log("BLOCKED", bundle.name, bundle.source,
-                         bundle.trust_level, "invalid_path", str(exc))
-        return
+    q_path = quarantine_bundle(bundle)
    c.print(f"[dim]Quarantined to {q_path.relative_to(q_path.parent.parent.parent)}[/]")

    # Scan
@@ -396,7 +387,7 @@ def do_install(identifier: str, category: str = "", force: bool = False,
                "[bold bright_cyan]This is an official optional skill maintained by Nous Research.[/]\n\n"
                "It ships with hermes-agent but is not activated by default.\n"
                "Installing will copy it to your skills directory where the agent can use it.\n\n"
-                f"Files will be at: [cyan]{display_hermes_home()}/skills/{category + '/' if category else ''}{bundle.name}/[/]",
+                f"Files will be at: [cyan]~/.hermes/skills/{category + '/' if category else ''}{bundle.name}/[/]",
                title="Official Skill",
                border_style="bright_cyan",
            ))
@@ -406,7 +397,7 @@ def do_install(identifier: str, category: str = "", force: bool = False,
                "External skills can contain instructions that influence agent behavior,\n"
                "shell commands, and scripts. Even after automated scanning, you should\n"
                "review the installed files before use.\n\n"
-                f"Files will be at: [cyan]{display_hermes_home()}/skills/{category + '/' if category else ''}{bundle.name}/[/]",
+                f"Files will be at: [cyan]~/.hermes/skills/{category + '/' if category else ''}{bundle.name}/[/]",
                title="Disclaimer",
                border_style="yellow",
            ))
@@ -421,30 +412,11 @@ def do_install(identifier: str, category: str = "", force: bool = False,
            return

    # Install
-    try:
-        install_dir = install_from_quarantine(q_path, bundle.name, category, bundle, result)
-    except ValueError as exc:
-        c.print(f"[bold red]Installation blocked:[/] {exc}\n")
-        shutil.rmtree(q_path, ignore_errors=True)
-        from tools.skills_hub import append_audit_log
-        append_audit_log("BLOCKED", bundle.name, bundle.source,
-                         bundle.trust_level, "invalid_path", str(exc))
-        return
+    install_dir = install_from_quarantine(q_path, bundle.name, category, bundle, result)
    from tools.skills_hub import SKILLS_DIR
    c.print(f"[bold green]Installed:[/] {install_dir.relative_to(SKILLS_DIR)}")
    c.print(f"[dim]Files: {', '.join(bundle.files.keys())}[/]\n")

-    if invalidate_cache:
-        # Invalidate the skills prompt cache so the new skill appears immediately
-        try:
-            from agent.prompt_builder import clear_skills_system_prompt_cache
-            clear_skills_system_prompt_cache(clear_snapshot=True)
-        except Exception:
-            pass
-    else:
-        c.print("[dim]Skill will be available in your next session.[/]")
-        c.print("[dim]Use /reset to start a new session now, or --now to activate immediately (invalidates prompt cache).[/]\n")
-

 def do_inspect(identifier: str, console: Optional[Console] = None) -> None:
    """Preview a skill's SKILL.md content without installing."""
@@ -631,8 +603,7 @@ def do_audit(name: Optional[str] = None, console: Optional[Console] = None) -> N


 def do_uninstall(name: str, console: Optional[Console] = None,
-                 skip_confirm: bool = False,
-                 invalidate_cache: bool = True) -> None:
+                 skip_confirm: bool = False) -> None:
    """Remove a hub-installed skill with confirmation."""
    from tools.skills_hub import uninstall_skill

@@ -652,15 +623,6 @@ def do_uninstall(name: str, console: Optional[Console] = None,
    success, msg = uninstall_skill(name)
    if success:
        c.print(f"[bold green]{msg}[/]\n")
-        if invalidate_cache:
-            try:
-                from agent.prompt_builder import clear_skills_system_prompt_cache
-                clear_skills_system_prompt_cache(clear_snapshot=True)
-            except Exception:
-                pass
-        else:
-            c.print("[dim]Change will take effect in your next session.[/]")
-            c.print("[dim]Use /reset to start a new session now, or --now to apply immediately (invalidates prompt cache).[/]\n")
    else:
        c.print(f"[bold red]Error:[/] {msg}\n")

@@ -760,7 +722,7 @@ def do_publish(skill_path: str, target: str = "github", repo: str = "",
        auth = GitHubAuth()
        if not auth.is_authenticated():
            c.print("[bold red]Error:[/] GitHub authentication required.\n"
-                    f"Set GITHUB_TOKEN in {display_hermes_home()}/.env or run 'gh auth login'.\n")
+                    "Set GITHUB_TOKEN in ~/.hermes/.env or run 'gh auth login'.\n")
            return

        c.print(f"[bold]Publishing '{name}' to {repo}...[/]")
@@ -903,15 +865,10 @@ def do_snapshot_export(output_path: str, console: Optional[Console] = None) -> N
        "taps": tap_list,
    }

-    payload = json.dumps(snapshot, indent=2, ensure_ascii=False) + "\n"
-    if output_path == "-":
-        import sys
-        sys.stdout.write(payload)
-    else:
-        out = Path(output_path)
-        out.write_text(payload)
-        c.print(f"[bold green]Snapshot exported:[/] {out}")
-        c.print(f"[dim]{len(installed)} skill(s), {len(tap_list)} tap(s)[/]\n")
+    out = Path(output_path)
+    out.write_text(json.dumps(snapshot, indent=2, ensure_ascii=False) + "\n")
+    c.print(f"[bold green]Snapshot exported:[/] {out}")
+    c.print(f"[dim]{len(installed)} skill(s), {len(tap_list)} tap(s)[/]\n")


 def do_snapshot_import(input_path: str, force: bool = False,
@@ -1102,23 +1059,19 @@ def handle_skills_slash(cmd: str, console: Optional[Console] = None) -> None:

    elif action == "install":
        if not args:
-            c.print("[bold red]Usage:[/] /skills install <identifier> [--category <cat>] [--force] [--now]\n")
+            c.print("[bold red]Usage:[/] /skills install <identifier> [--category <cat>] [--force|--yes]\n")
            return
        identifier = args[0]
        category = ""
-        # Slash commands run inside prompt_toolkit where input() hangs.
-        # Always skip confirmation — the user typing the command is implicit consent.
-        skip_confirm = True
+        # --yes / -y bypasses confirmation prompt (needed in TUI mode)
+        # --force handles reinstall override
+        skip_confirm = any(flag in args for flag in ("--yes", "-y"))
        force = "--force" in args
-        # --now invalidates prompt cache immediately (costs more money).
-        # Default: defer to next session to preserve cache.
-        invalidate_cache = "--now" in args
        for i, a in enumerate(args):
            if a == "--category" and i + 1 < len(args):
                category = args[i + 1]
        do_install(identifier, category=category, force=force,
-                   skip_confirm=skip_confirm, invalidate_cache=invalidate_cache,
-                   console=c)
+                   skip_confirm=skip_confirm, console=c)

    elif action == "inspect":
        if not args:
@@ -1148,13 +1101,10 @@ def handle_skills_slash(cmd: str, console: Optional[Console] = None) -> None:

    elif action == "uninstall":
        if not args:
-            c.print("[bold red]Usage:[/] /skills uninstall <name> [--now]\n")
+            c.print("[bold red]Usage:[/] /skills uninstall <name> [--yes]\n")
            return
-        # Slash commands run inside prompt_toolkit where input() hangs.
-        skip_confirm = True
-        invalidate_cache = "--now" in args
-        do_uninstall(args[0], console=c, skip_confirm=skip_confirm,
-                     invalidate_cache=invalidate_cache)
+        skip_confirm = any(flag in args for flag in ("--yes", "-y"))
+        do_uninstall(args[0], console=c, skip_confirm=skip_confirm)

    elif action == "publish":
        if not args:
@@ -254,9 +254,6 @@ def show_status(args):
        "Slack": ("SLACK_BOT_TOKEN", None),
        "Email": ("EMAIL_ADDRESS", "EMAIL_HOME_ADDRESS"),
        "SMS": ("TWILIO_ACCOUNT_SID", "SMS_HOME_CHANNEL"),
-        "DingTalk": ("DINGTALK_CLIENT_ID", None),
-        "Feishu": ("FEISHU_APP_ID", "FEISHU_HOME_CHANNEL"),
-        "WeCom": ("WECOM_BOT_ID", "WECOM_HOME_CHANNEL"),
    }
    
    for name, (token_var, home_var) in platforms.items():
@@ -285,31 +282,22 @@ def show_status(args):
            _gw_svc = get_service_name()
        except Exception:
            _gw_svc = "hermes-gateway"
-        try:
-            result = subprocess.run(
-                ["systemctl", "--user", "is-active", _gw_svc],
-                capture_output=True,
-                text=True,
-                timeout=5
-            )
-            is_active = result.stdout.strip() == "active"
-        except subprocess.TimeoutExpired:
-            is_active = False
+        result = subprocess.run(
+            ["systemctl", "--user", "is-active", _gw_svc],
+            capture_output=True,
+            text=True
+        )
+        is_active = result.stdout.strip() == "active"
        print(f"  Status:       {check_mark(is_active)} {'running' if is_active else 'stopped'}")
        print("  Manager:      systemd (user)")
        
    elif sys.platform == 'darwin':
-        from hermes_cli.gateway import get_launchd_label
-        try:
-            result = subprocess.run(
-                ["launchctl", "list", get_launchd_label()],
-                capture_output=True,
-                text=True,
-                timeout=5
-            )
-            is_loaded = result.returncode == 0
-        except subprocess.TimeoutExpired:
-            is_loaded = False
+        result = subprocess.run(
+            ["launchctl", "list", "ai.hermes.gateway"],
+            capture_output=True,
+            text=True
+        )
+        is_loaded = result.returncode == 0
        print(f"  Status:       {check_mark(is_loaded)} {'loaded' if is_loaded else 'not loaded'}")
        print("  Manager:      launchd")
    else:
@@ -9,8 +9,6 @@ Saves per-platform tool configuration to ~/.hermes/config.yaml under
 the `platform_toolsets` key.
 """

-import json as _json
-import logging
 import sys
 from pathlib import Path
 from typing import Dict, List, Optional, Set
@@ -21,8 +19,6 @@ from hermes_cli.config import (
 )
 from hermes_cli.colors import Colors, color

-logger = logging.getLogger(__name__)
-
 PROJECT_ROOT = Path(__file__).parent.parent.resolve()


@@ -112,8 +108,7 @@ def _get_effective_configurable_toolsets():
    """
    result = list(CONFIGURABLE_TOOLSETS)
    try:
-        from hermes_cli.plugins import discover_plugins, get_plugin_toolsets
-        discover_plugins()  # idempotent — ensures plugins are loaded
+        from hermes_cli.plugins import get_plugin_toolsets
        result.extend(get_plugin_toolsets())
    except Exception:
        pass
@@ -123,8 +118,7 @@ def _get_effective_configurable_toolsets():
 def _get_plugin_toolset_keys() -> set:
    """Return the set of toolset keys provided by plugins."""
    try:
-        from hermes_cli.plugins import discover_plugins, get_plugin_toolsets
-        discover_plugins()  # idempotent — ensures plugins are loaded
+        from hermes_cli.plugins import get_plugin_toolsets
        return {ts_key for ts_key, _, _ in get_plugin_toolsets()}
    except Exception:
        return set()
@@ -139,12 +133,8 @@ PLATFORMS = {
    "signal":   {"label": "📡 Signal",     "default_toolset": "hermes-signal"},
    "homeassistant": {"label": "🏠 Home Assistant", "default_toolset": "hermes-homeassistant"},
    "email":    {"label": "📧 Email",      "default_toolset": "hermes-email"},
-    "matrix":   {"label": "💬 Matrix",     "default_toolset": "hermes-matrix"},
- "dingtalk": {"label": "💬 DingTalk", "default_toolset": "hermes-dingtalk"},
-    "feishu": {"label": "🪽 Feishu", "default_toolset": "hermes-feishu"},
-    "wecom": {"label": "💬 WeCom", "default_toolset": "hermes-wecom"},
+    "dingtalk": {"label": "💬 DingTalk",   "default_toolset": "hermes-dingtalk"},
    "api_server": {"label": "🌐 API Server", "default_toolset": "hermes-api-server"},
-    "mattermost": {"label": "💬 Mattermost", "default_toolset": "hermes-mattermost"},
 }


@@ -196,14 +186,6 @@ TOOL_CATEGORIES = {
                    {"key": "FIRECRAWL_API_KEY", "prompt": "Firecrawl API key", "url": "https://firecrawl.dev"},
                ],
            },
-            {
-                "name": "Exa",
-                "tag": "AI-native search and contents",
-                "web_backend": "exa",
-                "env_vars": [
-                    {"key": "EXA_API_KEY", "prompt": "Exa API key", "url": "https://exa.ai"},
-                ],
-            },
            {
                "name": "Parallel",
                "tag": "AI-native search and extract",
@@ -273,16 +255,6 @@ TOOL_CATEGORIES = {
                "browser_provider": "browser-use",
                "post_setup": "browserbase",
            },
-            {
-                "name": "Camofox",
-                "tag": "Local anti-detection browser (Firefox/Camoufox)",
-                "env_vars": [
-                    {"key": "CAMOFOX_URL", "prompt": "Camofox server URL", "default": "http://localhost:9377",
-                     "url": "https://github.com/jo-inc/camofox-browser"},
-                ],
-                "browser_provider": "camofox",
-                "post_setup": "camofox",
-            },
        ],
    },
    "homeassistant": {
@@ -342,33 +314,10 @@ def _run_post_setup(post_setup_key: str):
            if result.returncode == 0:
                _print_success("    Node.js dependencies installed")
            else:
-                from hermes_constants import display_hermes_home
-                _print_warning(f"    npm install failed - run manually: cd {display_hermes_home()}/hermes-agent && npm install")
+                _print_warning("    npm install failed - run manually: cd ~/.hermes/hermes-agent && npm install")
        elif not node_modules.exists():
            _print_warning("    Node.js not found - browser tools require: npm install (in hermes-agent directory)")

-    elif post_setup_key == "camofox":
-        camofox_dir = PROJECT_ROOT / "node_modules" / "@askjo" / "camoufox-browser"
-        if not camofox_dir.exists() and shutil.which("npm"):
-            _print_info("    Installing Camofox browser server...")
-            import subprocess
-            result = subprocess.run(
-                ["npm", "install", "--silent"],
-                capture_output=True, text=True, cwd=str(PROJECT_ROOT)
-            )
-            if result.returncode == 0:
-                _print_success("    Camofox installed")
-            else:
-                _print_warning("    npm install failed - run manually: npm install")
-        if camofox_dir.exists():
-            _print_info("    Start the Camofox server:")
-            _print_info("      npx @askjo/camoufox-browser")
-            _print_info("    First run downloads the Camoufox engine (~300MB)")
-            _print_info("    Or use Docker: docker run -p 9377:9377 -e CAMOFOX_PORT=9377 jo-inc/camofox-browser")
-        elif not shutil.which("npm"):
-            _print_warning("    Node.js not found. Install Camofox via Docker:")
-            _print_info("      docker run -p 9377:9377 -e CAMOFOX_PORT=9377 jo-inc/camofox-browser")
-
    elif post_setup_key == "rl_training":
        try:
            __import__("tinker_atropos")
@@ -597,9 +546,7 @@ def _toolset_has_keys(ts_key: str) -> bool:
    if cat:
        for provider in cat.get("providers", []):
            env_vars = provider.get("env_vars", [])
-            if not env_vars:
-                return True  # No-key provider (e.g. Local Browser, Edge TTS)
-            if all(get_env_value(e["key"]) for e in env_vars):
+            if env_vars and all(get_env_value(e["key"]) for e in env_vars):
                return True
        return False

@@ -693,61 +640,9 @@ def _prompt_choice(question: str, choices: list, default: int = 0) -> int:
            return default


-# ─── Token Estimation ────────────────────────────────────────────────────────
-
-# Module-level cache so discovery + tokenization runs at most once per process.
-_tool_token_cache: Optional[Dict[str, int]] = None
-
-
-def _estimate_tool_tokens() -> Dict[str, int]:
-    """Return estimated token counts per individual tool name.
-
-    Uses tiktoken (cl100k_base) to count tokens in the JSON-serialised
-    OpenAI-format tool schema.  Triggers tool discovery on first call,
-    then caches the result for the rest of the process.
-
-    Returns an empty dict when tiktoken or the registry is unavailable.
-    """
-    global _tool_token_cache
-    if _tool_token_cache is not None:
-        return _tool_token_cache
-
-    try:
-        import tiktoken
-        enc = tiktoken.get_encoding("cl100k_base")
-    except Exception:
-        logger.debug("tiktoken unavailable; skipping tool token estimation")
-        _tool_token_cache = {}
-        return _tool_token_cache
-
-    try:
-        # Trigger full tool discovery (imports all tool modules).
-        import model_tools  # noqa: F401
-        from tools.registry import registry
-    except Exception:
-        logger.debug("Tool registry unavailable; skipping token estimation")
-        _tool_token_cache = {}
-        return _tool_token_cache
-
-    counts: Dict[str, int] = {}
-    for name in registry.get_all_tool_names():
-        schema = registry.get_schema(name)
-        if schema:
-            # Mirror what gets sent to the API:
-            # {"type": "function", "function": <schema>}
-            text = _json.dumps({"type": "function", "function": schema})
-            counts[name] = len(enc.encode(text))
-    _tool_token_cache = counts
-    return _tool_token_cache
-
-
 def _prompt_toolset_checklist(platform_label: str, enabled: Set[str]) -> Set[str]:
    """Multi-select checklist of toolsets. Returns set of selected toolset keys."""
    from hermes_cli.curses_ui import curses_checklist
-    from toolsets import resolve_toolset
-
-    # Pre-compute per-tool token counts (cached after first call).
-    tool_tokens = _estimate_tool_tokens()

    effective = _get_effective_configurable_toolsets()

@@ -763,27 +658,11 @@ def _prompt_toolset_checklist(platform_label: str, enabled: Set[str]) -> Set[str
        if ts_key in enabled
    }

-    # Build a live status function that shows deduplicated total token cost.
-    status_fn = None
-    if tool_tokens:
-        ts_keys = [ts_key for ts_key, _, _ in effective]
-
-        def status_fn(chosen: set) -> str:
-            # Collect unique tool names across all selected toolsets
-            all_tools: set = set()
-            for idx in chosen:
-                all_tools.update(resolve_toolset(ts_keys[idx]))
-            total = sum(tool_tokens.get(name, 0) for name in all_tools)
-            if total >= 1000:
-                return f"Est. tool context: ~{total / 1000:.1f}k tokens"
-            return f"Est. tool context: ~{total} tokens"
-
    chosen = curses_checklist(
        f"Tools for {platform_label}",
        labels,
        pre_selected,
        cancel_returns=pre_selected,
-        status_fn=status_fn,
    )
    return {effective[i][0] for i in chosen}

@@ -983,13 +862,8 @@ def _configure_simple_requirements(ts_key: str):
            key_label = "    OPENAI_API_KEY" if "api.openai.com" in base_url.lower() else "    API key"
            api_key = _prompt(key_label, password=True)
            if api_key and api_key.strip():
+                save_env_value("OPENAI_BASE_URL", base_url)
                save_env_value("OPENAI_API_KEY", api_key.strip())
-                # Save vision base URL to config (not .env — only secrets go there)
-                from hermes_cli.config import load_config, save_config
-                _cfg = load_config()
-                _aux = _cfg.setdefault("auxiliary", {}).setdefault("vision", {})
-                _aux["base_url"] = base_url
-                save_config(_cfg)
                if "api.openai.com" in base_url.lower():
                    save_env_value("AUXILIARY_VISION_MODEL", "gpt-4o-mini")
                _print_success("    Saved")
@@ -1378,8 +1252,7 @@ def tools_command(args=None, first_install: bool = False, config: dict = None):
        platform_choices[idx] = f"Configure {pinfo['label']}  ({new_count}/{total} enabled)"

    print()
-    from hermes_constants import display_hermes_home
-    print(color(f"  Tool configuration saved to {display_hermes_home()}/config.yaml", Colors.DIM))
+    print(color("  Tool configuration saved to ~/.hermes/config.yaml", Colors.DIM))
    print(color("  Changes take effect on next 'hermes' or gateway restart.", Colors.DIM))
    print()

@@ -1,260 +0,0 @@
-"""hermes webhook — manage dynamic webhook subscriptions from the CLI.
-
-Usage:
-    hermes webhook subscribe <name> [options]
-    hermes webhook list
-    hermes webhook remove <name>
-    hermes webhook test <name> [--payload '{"key": "value"}']
-
-Subscriptions persist to ~/.hermes/webhook_subscriptions.json and are
-hot-reloaded by the webhook adapter without a gateway restart.
-"""
-
-import json
-import os
-import re
-import secrets
-import time
-from pathlib import Path
-from typing import Dict, Optional
-
-from hermes_constants import display_hermes_home
-
-
-_SUBSCRIPTIONS_FILENAME = "webhook_subscriptions.json"
-
-
-def _hermes_home() -> Path:
-    return Path(
-        os.getenv("HERMES_HOME", str(Path.home() / ".hermes"))
-    ).expanduser()
-
-
-def _subscriptions_path() -> Path:
-    return _hermes_home() / _SUBSCRIPTIONS_FILENAME
-
-
-def _load_subscriptions() -> Dict[str, dict]:
-    path = _subscriptions_path()
-    if not path.exists():
-        return {}
-    try:
-        data = json.loads(path.read_text(encoding="utf-8"))
-        return data if isinstance(data, dict) else {}
-    except Exception:
-        return {}
-
-
-def _save_subscriptions(subs: Dict[str, dict]) -> None:
-    path = _subscriptions_path()
-    path.parent.mkdir(parents=True, exist_ok=True)
-    tmp_path = path.with_suffix(".tmp")
-    tmp_path.write_text(
-        json.dumps(subs, indent=2, ensure_ascii=False),
-        encoding="utf-8",
-    )
-    os.replace(str(tmp_path), str(path))
-
-
-def _get_webhook_config() -> dict:
-    """Load webhook platform config. Returns {} if not configured."""
-    try:
-        from hermes_cli.config import load_config
-        cfg = load_config()
-        return cfg.get("platforms", {}).get("webhook", {})
-    except Exception:
-        return {}
-
-
-def _is_webhook_enabled() -> bool:
-    return bool(_get_webhook_config().get("enabled"))
-
-
-def _get_webhook_base_url() -> str:
-    wh = _get_webhook_config().get("extra", {})
-    host = wh.get("host", "0.0.0.0")
-    port = wh.get("port", 8644)
-    display_host = "localhost" if host == "0.0.0.0" else host
-    return f"http://{display_host}:{port}"
-
-
-def _setup_hint() -> str:
-    _dhh = display_hermes_home()
-    return f"""
-  Webhook platform is not enabled. To set it up:
-
-  1. Run the gateway setup wizard:
-     hermes gateway setup
-
-  2. Or manually add to {_dhh}/config.yaml:
-     platforms:
-       webhook:
-         enabled: true
-         extra:
-           host: "0.0.0.0"
-           port: 8644
-           secret: "your-global-hmac-secret"
-
-  3. Or set environment variables in {_dhh}/.env:
-     WEBHOOK_ENABLED=true
-     WEBHOOK_PORT=8644
-     WEBHOOK_SECRET=your-global-secret
-
-  Then start the gateway: hermes gateway run
-"""
-
-
-def _require_webhook_enabled() -> bool:
-    """Check webhook is enabled. Print setup guide and return False if not."""
-    if _is_webhook_enabled():
-        return True
-    print(_setup_hint())
-    return False
-
-
-def webhook_command(args):
-    """Entry point for 'hermes webhook' subcommand."""
-    sub = getattr(args, "webhook_action", None)
-
-    if not sub:
-        print("Usage: hermes webhook {subscribe|list|remove|test}")
-        print("Run 'hermes webhook --help' for details.")
-        return
-
-    if not _require_webhook_enabled():
-        return
-
-    if sub in ("subscribe", "add"):
-        _cmd_subscribe(args)
-    elif sub in ("list", "ls"):
-        _cmd_list(args)
-    elif sub in ("remove", "rm"):
-        _cmd_remove(args)
-    elif sub == "test":
-        _cmd_test(args)
-
-
-def _cmd_subscribe(args):
-    name = args.name.strip().lower().replace(" ", "-")
-    if not re.match(r'^[a-z0-9][a-z0-9_-]*$', name):
-        print(f"Error: Invalid name '{name}'. Use lowercase alphanumeric with hyphens/underscores.")
-        return
-
-    subs = _load_subscriptions()
-    is_update = name in subs
-
-    secret = args.secret or secrets.token_urlsafe(32)
-    events = [e.strip() for e in args.events.split(",")] if args.events else []
-
-    route = {
-        "description": args.description or f"Agent-created subscription: {name}",
-        "events": events,
-        "secret": secret,
-        "prompt": args.prompt or "",
-        "skills": [s.strip() for s in args.skills.split(",")] if args.skills else [],
-        "deliver": args.deliver or "log",
-        "created_at": time.strftime("%Y-%m-%dT%H:%M:%SZ", time.gmtime()),
-    }
-
-    if args.deliver_chat_id:
-        route["deliver_extra"] = {"chat_id": args.deliver_chat_id}
-
-    subs[name] = route
-    _save_subscriptions(subs)
-
-    base_url = _get_webhook_base_url()
-    status = "Updated" if is_update else "Created"
-
-    print(f"\n  {status} webhook subscription: {name}")
-    print(f"  URL:    {base_url}/webhooks/{name}")
-    print(f"  Secret: {secret}")
-    if events:
-        print(f"  Events: {', '.join(events)}")
-    else:
-        print("  Events: (all)")
-    print(f"  Deliver: {route['deliver']}")
-    if route.get("prompt"):
-        prompt_preview = route["prompt"][:80] + ("..." if len(route["prompt"]) > 80 else "")
-        print(f"  Prompt: {prompt_preview}")
-    print(f"\n  Configure your service to POST to the URL above.")
-    print(f"  Use the secret for HMAC-SHA256 signature validation.")
-    print(f"  The gateway must be running to receive events (hermes gateway run).\n")
-
-
-def _cmd_list(args):
-    subs = _load_subscriptions()
-    if not subs:
-        print("  No dynamic webhook subscriptions.")
-        print("  Create one with: hermes webhook subscribe <name>")
-        return
-
-    base_url = _get_webhook_base_url()
-    print(f"\n  {len(subs)} webhook subscription(s):\n")
-    for name, route in subs.items():
-        events = ", ".join(route.get("events", [])) or "(all)"
-        deliver = route.get("deliver", "log")
-        desc = route.get("description", "")
-        print(f"  ◆ {name}")
-        if desc:
-            print(f"    {desc}")
-        print(f"    URL:     {base_url}/webhooks/{name}")
-        print(f"    Events:  {events}")
-        print(f"    Deliver: {deliver}")
-        print()
-
-
-def _cmd_remove(args):
-    name = args.name.strip().lower()
-    subs = _load_subscriptions()
-
-    if name not in subs:
-        print(f"  No subscription named '{name}'.")
-        print("  Note: Static routes from config.yaml cannot be removed here.")
-        return
-
-    del subs[name]
-    _save_subscriptions(subs)
-    print(f"  Removed webhook subscription: {name}")
-
-
-def _cmd_test(args):
-    """Send a test POST to a webhook route."""
-    name = args.name.strip().lower()
-    subs = _load_subscriptions()
-
-    if name not in subs:
-        print(f"  No subscription named '{name}'.")
-        return
-
-    route = subs[name]
-    secret = route.get("secret", "")
-    base_url = _get_webhook_base_url()
-    url = f"{base_url}/webhooks/{name}"
-
-    payload = args.payload or '{"test": true, "event_type": "test", "message": "Hello from hermes webhook test"}'
-
-    import hmac
-    import hashlib
-    sig = "sha256=" + hmac.new(
-        secret.encode(), payload.encode(), hashlib.sha256
-    ).hexdigest()
-
-    print(f"  Sending test POST to {url}")
-    try:
-        import urllib.request
-        req = urllib.request.Request(
-            url,
-            data=payload.encode(),
-            headers={
-                "Content-Type": "application/json",
-                "X-Hub-Signature-256": sig,
-                "X-GitHub-Event": "test",
-            },
-            method="POST",
-        )
-        with urllib.request.urlopen(req, timeout=10) as resp:
-            body = resp.read().decode()
-            print(f"  Response ({resp.status}): {body}")
-    except Exception as e:
-        print(f"  Error: {e}")
-        print("  Is the gateway running? (hermes gateway run)")
@@ -17,61 +17,6 @@ def get_hermes_home() -> Path:
    return Path(os.getenv("HERMES_HOME", Path.home() / ".hermes"))


-def get_optional_skills_dir(default: Path | None = None) -> Path:
-    """Return the optional-skills directory, honoring package-manager wrappers.
-
-    Packaged installs may ship ``optional-skills`` outside the Python package
-    tree and expose it via ``HERMES_OPTIONAL_SKILLS``.
-    """
-    override = os.getenv("HERMES_OPTIONAL_SKILLS", "").strip()
-    if override:
-        return Path(override)
-    if default is not None:
-        return default
-    return get_hermes_home() / "optional-skills"
-
-
-def get_hermes_dir(new_subpath: str, old_name: str) -> Path:
-    """Resolve a Hermes subdirectory with backward compatibility.
-
-    New installs get the consolidated layout (e.g. ``cache/images``).
-    Existing installs that already have the old path (e.g. ``image_cache``)
-    keep using it — no migration required.
-
-    Args:
-        new_subpath: Preferred path relative to HERMES_HOME (e.g. ``"cache/images"``).
-        old_name: Legacy path relative to HERMES_HOME (e.g. ``"image_cache"``).
-
-    Returns:
-        Absolute ``Path`` — old location if it exists on disk, otherwise the new one.
-    """
-    home = get_hermes_home()
-    old_path = home / old_name
-    if old_path.exists():
-        return old_path
-    return home / new_subpath
-
-
-def display_hermes_home() -> str:
-    """Return a user-friendly display string for the current HERMES_HOME.
-
-    Uses ``~/`` shorthand for readability::
-
-        default:  ``~/.hermes``
-        profile:  ``~/.hermes/profiles/coder``
-        custom:   ``/opt/hermes-custom``
-
-    Use this in **user-facing** print/log messages instead of hardcoding
-    ``~/.hermes``.  For code that needs a real ``Path``, use
-    :func:`get_hermes_home` instead.
-    """
-    home = get_hermes_home()
-    try:
-        return "~/" + str(home.relative_to(Path.home()))
-    except ValueError:
-        return str(home)
-
-
 VALID_REASONING_EFFORTS = ("xhigh", "high", "medium", "low", "minimal")


@@ -15,20 +15,15 @@ Key design decisions:
 """

 import json
-import logging
 import os
-import random
 import re
 import sqlite3
 import threading
 import time
 from pathlib import Path
 from hermes_constants import get_hermes_home
-from typing import Any, Callable, Dict, List, Optional, TypeVar
+from typing import Dict, Any, List, Optional

-logger = logging.getLogger(__name__)
-
-T = TypeVar("T")

 DEFAULT_DB_PATH = get_hermes_home() / "state.db"

@@ -121,38 +116,18 @@ class SessionDB:
    single writer via WAL mode). Each method opens its own cursor.
    """

-    # ── Write-contention tuning ──
-    # With multiple hermes processes (gateway + CLI sessions + worktree agents)
-    # all sharing one state.db, WAL write-lock contention causes visible TUI
-    # freezes.  SQLite's built-in busy handler uses a deterministic sleep
-    # schedule that causes convoy effects under high concurrency.
-    #
-    # Instead, we keep the SQLite timeout short (1s) and handle retries at the
-    # application level with random jitter, which naturally staggers competing
-    # writers and avoids the convoy.
-    _WRITE_MAX_RETRIES = 15
-    _WRITE_RETRY_MIN_S = 0.020   # 20ms
-    _WRITE_RETRY_MAX_S = 0.150   # 150ms
-    # Attempt a PASSIVE WAL checkpoint every N successful writes.
-    _CHECKPOINT_EVERY_N_WRITES = 50
-
    def __init__(self, db_path: Path = None):
        self.db_path = db_path or DEFAULT_DB_PATH
        self.db_path.parent.mkdir(parents=True, exist_ok=True)

        self._lock = threading.Lock()
-        self._write_count = 0
        self._conn = sqlite3.connect(
            str(self.db_path),
            check_same_thread=False,
-            # Short timeout — application-level retry with random jitter
-            # handles contention instead of sitting in SQLite's internal
-            # busy handler for up to 30s.
-            timeout=1.0,
-            # Autocommit mode: Python's default isolation_level="" auto-starts
-            # transactions on DML, which conflicts with our explicit
-            # BEGIN IMMEDIATE.  None = we manage transactions ourselves.
-            isolation_level=None,
+            # 30s gives the WAL writer (CLI or gateway) time to finish a batch
+            # flush before the concurrent reader/writer gives up.  10s was too
+            # short when the CLI is doing frequent memory flushes.
+            timeout=30.0,
        )
        self._conn.row_factory = sqlite3.Row
        self._conn.execute("PRAGMA journal_mode=WAL")
@@ -160,96 +135,6 @@ class SessionDB:

        self._init_schema()

-    # ── Core write helper ──
-
-    def _execute_write(self, fn: Callable[[sqlite3.Connection], T]) -> T:
-        """Execute a write transaction with BEGIN IMMEDIATE and jitter retry.
-
-        *fn* receives the connection and should perform INSERT/UPDATE/DELETE
-        statements.  The caller must NOT call ``commit()`` — that's handled
-        here after *fn* returns.
-
-        BEGIN IMMEDIATE acquires the WAL write lock at transaction start
-        (not at commit time), so lock contention surfaces immediately.
-        On ``database is locked``, we release the Python lock, sleep a
-        random 20-150ms, and retry — breaking the convoy pattern that
-        SQLite's built-in deterministic backoff creates.
-
-        Returns whatever *fn* returns.
-        """
-        last_err: Optional[Exception] = None
-        for attempt in range(self._WRITE_MAX_RETRIES):
-            try:
-                with self._lock:
-                    self._conn.execute("BEGIN IMMEDIATE")
-                    try:
-                        result = fn(self._conn)
-                        self._conn.commit()
-                    except BaseException:
-                        try:
-                            self._conn.rollback()
-                        except Exception:
-                            pass
-                        raise
-                # Success — periodic best-effort checkpoint.
-                self._write_count += 1
-                if self._write_count % self._CHECKPOINT_EVERY_N_WRITES == 0:
-                    self._try_wal_checkpoint()
-                return result
-            except sqlite3.OperationalError as exc:
-                err_msg = str(exc).lower()
-                if "locked" in err_msg or "busy" in err_msg:
-                    last_err = exc
-                    if attempt < self._WRITE_MAX_RETRIES - 1:
-                        jitter = random.uniform(
-                            self._WRITE_RETRY_MIN_S,
-                            self._WRITE_RETRY_MAX_S,
-                        )
-                        time.sleep(jitter)
-                        continue
-                # Non-lock error or retries exhausted — propagate.
-                raise
-        # Retries exhausted (shouldn't normally reach here).
-        raise last_err or sqlite3.OperationalError(
-            "database is locked after max retries"
-        )
-
-    def _try_wal_checkpoint(self) -> None:
-        """Best-effort PASSIVE WAL checkpoint.  Never blocks, never raises.
-
-        Flushes committed WAL frames back into the main DB file for any
-        frames that no other connection currently needs.  Keeps the WAL
-        from growing unbounded when many processes hold persistent
-        connections.
-        """
-        try:
-            with self._lock:
-                result = self._conn.execute(
-                    "PRAGMA wal_checkpoint(PASSIVE)"
-                ).fetchone()
-                if result and result[1] > 0:
-                    logger.debug(
-                        "WAL checkpoint: %d/%d pages checkpointed",
-                        result[2], result[1],
-                    )
-        except Exception:
-            pass  # Best effort — never fatal.
-
-    def close(self):
-        """Close the database connection.
-
-        Attempts a PASSIVE WAL checkpoint first so that exiting processes
-        help keep the WAL file from growing unbounded.
-        """
-        with self._lock:
-            if self._conn:
-                try:
-                    self._conn.execute("PRAGMA wal_checkpoint(PASSIVE)")
-                except Exception:
-                    pass
-                self._conn.close()
-                self._conn = None
-
    def _init_schema(self):
        """Create tables and FTS if they don't exist, run migrations."""
        cursor = self._conn.cursor()
@@ -371,8 +256,8 @@ class SessionDB:
        parent_session_id: str = None,
    ) -> str:
        """Create a new session record. Returns the session_id."""
-        def _do(conn):
-            conn.execute(
+        with self._lock:
+            self._conn.execute(
                """INSERT OR IGNORE INTO sessions (id, source, user_id, model, model_config,
                   system_prompt, parent_session_id, started_at)
                   VALUES (?, ?, ?, ?, ?, ?, ?, ?)""",
@@ -387,35 +272,26 @@ class SessionDB:
                    time.time(),
                ),
            )
-        self._execute_write(_do)
+            self._conn.commit()
        return session_id

    def end_session(self, session_id: str, end_reason: str) -> None:
        """Mark a session as ended."""
-        def _do(conn):
-            conn.execute(
+        with self._lock:
+            self._conn.execute(
                "UPDATE sessions SET ended_at = ?, end_reason = ? WHERE id = ?",
                (time.time(), end_reason, session_id),
            )
-        self._execute_write(_do)
-
-    def reopen_session(self, session_id: str) -> None:
-        """Clear ended_at/end_reason so a session can be resumed."""
-        def _do(conn):
-            conn.execute(
-                "UPDATE sessions SET ended_at = NULL, end_reason = NULL WHERE id = ?",
-                (session_id,),
-            )
-        self._execute_write(_do)
+            self._conn.commit()

    def update_system_prompt(self, session_id: str, system_prompt: str) -> None:
        """Store the full assembled system prompt snapshot."""
-        def _do(conn):
-            conn.execute(
+        with self._lock:
+            self._conn.execute(
                "UPDATE sessions SET system_prompt = ? WHERE id = ?",
                (system_prompt, session_id),
            )
-        self._execute_write(_do)
+            self._conn.commit()

    def update_token_counts(
        self,
@@ -434,39 +310,11 @@ class SessionDB:
        billing_provider: Optional[str] = None,
        billing_base_url: Optional[str] = None,
        billing_mode: Optional[str] = None,
-        absolute: bool = False,
    ) -> None:
-        """Update token counters and backfill model if not already set.
-
-        When *absolute* is False (default), values are **incremented** — use
-        this for per-API-call deltas (CLI path).
-
-        When *absolute* is True, values are **set directly** — use this when
-        the caller already holds cumulative totals (gateway path, where the
-        cached agent accumulates across messages).
-        """
-        if absolute:
-            sql = """UPDATE sessions SET
-                   input_tokens = ?,
-                   output_tokens = ?,
-                   cache_read_tokens = ?,
-                   cache_write_tokens = ?,
-                   reasoning_tokens = ?,
-                   estimated_cost_usd = COALESCE(?, 0),
-                   actual_cost_usd = CASE
-                       WHEN ? IS NULL THEN actual_cost_usd
-                       ELSE ?
-                   END,
-                   cost_status = COALESCE(?, cost_status),
-                   cost_source = COALESCE(?, cost_source),
-                   pricing_version = COALESCE(?, pricing_version),
-                   billing_provider = COALESCE(billing_provider, ?),
-                   billing_base_url = COALESCE(billing_base_url, ?),
-                   billing_mode = COALESCE(billing_mode, ?),
-                   model = COALESCE(model, ?)
-                   WHERE id = ?"""
-        else:
-            sql = """UPDATE sessions SET
+        """Increment token counters and backfill model if not already set."""
+        with self._lock:
+            self._conn.execute(
+                """UPDATE sessions SET
                   input_tokens = input_tokens + ?,
                   output_tokens = output_tokens + ?,
                   cache_read_tokens = cache_read_tokens + ?,
@@ -484,94 +332,6 @@ class SessionDB:
                   billing_base_url = COALESCE(billing_base_url, ?),
                   billing_mode = COALESCE(billing_mode, ?),
                   model = COALESCE(model, ?)
-                   WHERE id = ?"""
-        params = (
-            input_tokens,
-            output_tokens,
-            cache_read_tokens,
-            cache_write_tokens,
-            reasoning_tokens,
-            estimated_cost_usd,
-            actual_cost_usd,
-            actual_cost_usd,
-            cost_status,
-            cost_source,
-            pricing_version,
-            billing_provider,
-            billing_base_url,
-            billing_mode,
-            model,
-            session_id,
-        )
-        def _do(conn):
-            conn.execute(sql, params)
-        self._execute_write(_do)
-
-    def ensure_session(
-        self,
-        session_id: str,
-        source: str = "unknown",
-        model: str = None,
-    ) -> None:
-        """Ensure a session row exists, creating it with minimal metadata if absent.
-
-        Used by _flush_messages_to_session_db to recover from a failed
-        create_session() call (e.g. transient SQLite lock at agent startup).
-        INSERT OR IGNORE is safe to call even when the row already exists.
-        """
-        def _do(conn):
-            conn.execute(
-                """INSERT OR IGNORE INTO sessions
-                   (id, source, model, started_at)
-                   VALUES (?, ?, ?, ?)""",
-                (session_id, source, model, time.time()),
-            )
-        self._execute_write(_do)
-
-    def set_token_counts(
-        self,
-        session_id: str,
-        input_tokens: int = 0,
-        output_tokens: int = 0,
-        model: str = None,
-        cache_read_tokens: int = 0,
-        cache_write_tokens: int = 0,
-        reasoning_tokens: int = 0,
-        estimated_cost_usd: Optional[float] = None,
-        actual_cost_usd: Optional[float] = None,
-        cost_status: Optional[str] = None,
-        cost_source: Optional[str] = None,
-        pricing_version: Optional[str] = None,
-        billing_provider: Optional[str] = None,
-        billing_base_url: Optional[str] = None,
-        billing_mode: Optional[str] = None,
-    ) -> None:
-        """Set token counters to absolute values (not increment).
-
-        Use this when the caller provides cumulative totals from a completed
-        conversation run (e.g. the gateway, where the cached agent's
-        session_prompt_tokens already reflects the running total).
-        """
-        def _do(conn):
-            conn.execute(
-                """UPDATE sessions SET
-                   input_tokens = ?,
-                   output_tokens = ?,
-                   cache_read_tokens = ?,
-                   cache_write_tokens = ?,
-                   reasoning_tokens = ?,
-                   estimated_cost_usd = ?,
-                   actual_cost_usd = CASE
-                       WHEN ? IS NULL THEN actual_cost_usd
-                       ELSE ?
-                   END,
-                   cost_status = COALESCE(?, cost_status),
-                   cost_source = COALESCE(?, cost_source),
-                   pricing_version = COALESCE(?, pricing_version),
-                   billing_provider = COALESCE(billing_provider, ?),
-                   billing_base_url = COALESCE(billing_base_url, ?),
-                   billing_mode = COALESCE(billing_mode, ?),
-                   model = COALESCE(model, ?)
                   WHERE id = ?""",
                (
                    input_tokens,
@@ -592,7 +352,28 @@ class SessionDB:
                    session_id,
                ),
            )
-        self._execute_write(_do)
+            self._conn.commit()
+
+    def ensure_session(
+        self,
+        session_id: str,
+        source: str = "unknown",
+        model: str = None,
+    ) -> None:
+        """Ensure a session row exists, creating it with minimal metadata if absent.
+
+        Used by _flush_messages_to_session_db to recover from a failed
+        create_session() call (e.g. transient SQLite lock at agent startup).
+        INSERT OR IGNORE is safe to call even when the row already exists.
+        """
+        with self._lock:
+            self._conn.execute(
+                """INSERT OR IGNORE INTO sessions
+                   (id, source, model, started_at)
+                   VALUES (?, ?, ?, ?)""",
+                (session_id, source, model, time.time()),
+            )
+            self._conn.commit()

    def get_session(self, session_id: str) -> Optional[Dict[str, Any]]:
        """Get a session by ID."""
@@ -686,10 +467,10 @@ class SessionDB:
        Empty/whitespace-only strings are normalized to None (clearing the title).
        """
        title = self.sanitize_title(title)
-        def _do(conn):
+        with self._lock:
            if title:
                # Check uniqueness (allow the same session to keep its own title)
-                cursor = conn.execute(
+                cursor = self._conn.execute(
                    "SELECT id FROM sessions WHERE title = ? AND id != ?",
                    (title, session_id),
                )
@@ -698,12 +479,12 @@ class SessionDB:
                    raise ValueError(
                        f"Title '{title}' is already in use by session {conflict['id']}"
                    )
-            cursor = conn.execute(
+            cursor = self._conn.execute(
                "UPDATE sessions SET title = ? WHERE id = ?",
                (title, session_id),
            )
-            return cursor.rowcount
-        rowcount = self._execute_write(_do)
+            self._conn.commit()
+            rowcount = cursor.rowcount
        return rowcount > 0

    def get_session_title(self, session_id: str) -> Optional[str]:
@@ -875,24 +656,17 @@ class SessionDB:
        Also increments the session's message_count (and tool_call_count
        if role is 'tool' or tool_calls is present).
        """
-        # Serialize structured fields to JSON before entering the write txn
-        reasoning_details_json = (
-            json.dumps(reasoning_details)
-            if reasoning_details else None
-        )
-        codex_items_json = (
-            json.dumps(codex_reasoning_items)
-            if codex_reasoning_items else None
-        )
-        tool_calls_json = json.dumps(tool_calls) if tool_calls else None
-
-        # Pre-compute tool call count
-        num_tool_calls = 0
-        if tool_calls is not None:
-            num_tool_calls = len(tool_calls) if isinstance(tool_calls, list) else 1
-
-        def _do(conn):
-            cursor = conn.execute(
+        with self._lock:
+            # Serialize structured fields to JSON for storage
+            reasoning_details_json = (
+                json.dumps(reasoning_details)
+                if reasoning_details else None
+            )
+            codex_items_json = (
+                json.dumps(codex_reasoning_items)
+                if codex_reasoning_items else None
+            )
+            cursor = self._conn.execute(
                """INSERT INTO messages (session_id, role, content, tool_call_id,
                   tool_calls, tool_name, timestamp, token_count, finish_reason,
                   reasoning, reasoning_details, codex_reasoning_items)
@@ -902,7 +676,7 @@ class SessionDB:
                    role,
                    content,
                    tool_call_id,
-                    tool_calls_json,
+                    json.dumps(tool_calls) if tool_calls else None,
                    tool_name,
                    time.time(),
                    token_count,
@@ -915,20 +689,25 @@ class SessionDB:
            msg_id = cursor.lastrowid

            # Update counters
+            # Count actual tool calls from the tool_calls list (not from tool responses).
+            # A single assistant message can contain multiple parallel tool calls.
+            num_tool_calls = 0
+            if tool_calls is not None:
+                num_tool_calls = len(tool_calls) if isinstance(tool_calls, list) else 1
            if num_tool_calls > 0:
-                conn.execute(
+                self._conn.execute(
                    """UPDATE sessions SET message_count = message_count + 1,
                       tool_call_count = tool_call_count + ? WHERE id = ?""",
                    (num_tool_calls, session_id),
                )
            else:
-                conn.execute(
+                self._conn.execute(
                    "UPDATE sessions SET message_count = message_count + 1 WHERE id = ?",
                    (session_id,),
                )
-            return msg_id

-        return self._execute_write(_do)
+            self._conn.commit()
+        return msg_id

    def get_messages(self, session_id: str) -> List[Dict[str, Any]]:
        """Load all messages for a session, ordered by timestamp."""
@@ -1222,53 +1001,54 @@ class SessionDB:

    def clear_messages(self, session_id: str) -> None:
        """Delete all messages for a session and reset its counters."""
-        def _do(conn):
-            conn.execute(
+        with self._lock:
+            self._conn.execute(
                "DELETE FROM messages WHERE session_id = ?", (session_id,)
            )
-            conn.execute(
+            self._conn.execute(
                "UPDATE sessions SET message_count = 0, tool_call_count = 0 WHERE id = ?",
                (session_id,),
            )
-        self._execute_write(_do)
+            self._conn.commit()

    def delete_session(self, session_id: str) -> bool:
        """Delete a session and all its messages. Returns True if found."""
-        def _do(conn):
-            cursor = conn.execute(
+        with self._lock:
+            cursor = self._conn.execute(
                "SELECT COUNT(*) FROM sessions WHERE id = ?", (session_id,)
            )
            if cursor.fetchone()[0] == 0:
                return False
-            conn.execute("DELETE FROM messages WHERE session_id = ?", (session_id,))
-            conn.execute("DELETE FROM sessions WHERE id = ?", (session_id,))
+            self._conn.execute("DELETE FROM messages WHERE session_id = ?", (session_id,))
+            self._conn.execute("DELETE FROM sessions WHERE id = ?", (session_id,))
+            self._conn.commit()
            return True
-        return self._execute_write(_do)

    def prune_sessions(self, older_than_days: int = 90, source: str = None) -> int:
        """
        Delete sessions older than N days. Returns count of deleted sessions.
        Only prunes ended sessions (not active ones).
        """
-        cutoff = time.time() - (older_than_days * 86400)
+        import time as _time
+        cutoff = _time.time() - (older_than_days * 86400)

-        def _do(conn):
+        with self._lock:
            if source:
-                cursor = conn.execute(
+                cursor = self._conn.execute(
                    """SELECT id FROM sessions
                       WHERE started_at < ? AND ended_at IS NOT NULL AND source = ?""",
                    (cutoff, source),
                )
            else:
-                cursor = conn.execute(
+                cursor = self._conn.execute(
                    "SELECT id FROM sessions WHERE started_at < ? AND ended_at IS NOT NULL",
                    (cutoff,),
                )
            session_ids = [row["id"] for row in cursor.fetchall()]

            for sid in session_ids:
-                conn.execute("DELETE FROM messages WHERE session_id = ?", (sid,))
-                conn.execute("DELETE FROM sessions WHERE id = ?", (sid,))
-            return len(session_ids)
+                self._conn.execute("DELETE FROM messages WHERE session_id = ?", (sid,))
+                self._conn.execute("DELETE FROM sessions WHERE id = ?", (sid,))

-        return self._execute_write(_do)
+            self._conn.commit()
+        return len(session_ids)
@@ -10,27 +10,16 @@ import os
 import sys
 from pathlib import Path

-from hermes_constants import get_hermes_home
 from honcho_integration.client import resolve_config_path, GLOBAL_CONFIG_PATH

 HOST = "hermes"


 def _config_path() -> Path:
-    """Return the active Honcho config path for reading (instance-local or global)."""
+    """Return the active Honcho config path (instance-local or global)."""
    return resolve_config_path()


-def _local_config_path() -> Path:
-    """Return the instance-local Honcho config path for writing.
-
-    Always returns $HERMES_HOME/honcho.json so each profile/instance gets
-    its own config file.  The global ~/.honcho/config.json is only used as
-    a read fallback (via resolve_config_path) for cross-app interop.
-    """
-    return get_hermes_home() / "honcho.json"
-
-
 def _read_config() -> dict:
    path = _config_path()
    if path.exists():
@@ -42,7 +31,7 @@ def _read_config() -> dict:


 def _write_config(cfg: dict, path: Path | None = None) -> None:
-    path = path or _local_config_path()
+    path = path or _config_path()
    path.parent.mkdir(parents=True, exist_ok=True)
    path.write_text(
        json.dumps(cfg, indent=2, ensure_ascii=False) + "\n",
@@ -106,13 +95,13 @@ def cmd_setup(args) -> None:
    """Interactive Honcho setup wizard."""
    cfg = _read_config()

-    write_path = _local_config_path()
-    read_path = _config_path()
+    active_path = _config_path()
    print("\nHoncho memory setup\n" + "─" * 40)
    print("  Honcho gives Hermes persistent cross-session memory.")
-    print(f"  Config: {write_path}")
-    if read_path != write_path and read_path.exists():
-        print(f"  (seeding from existing config at {read_path})")
+    if active_path != GLOBAL_CONFIG_PATH:
+        print(f"  Instance config: {active_path}")
+    else:
+        print("  Config is shared with other hosts at ~/.honcho/config.json")
    print()

    if not _ensure_sdk_installed():
@@ -200,7 +189,7 @@ def cmd_setup(args) -> None:
    hermes_host.setdefault("saveMessages", True)

    _write_config(cfg)
-    print(f"\n  Config written to {write_path}")
+    print(f"\n  Config written to {active_path}")

    # Test connection
    print("  Testing connection... ", end="", flush=True)
@@ -248,7 +237,6 @@ def cmd_status(args) -> None:
    cfg = _read_config()

    active_path = _config_path()
-    write_path = _local_config_path()

    if not cfg:
        print(f"  No Honcho config found at {active_path}")
@@ -271,8 +259,6 @@ def cmd_status(args) -> None:
    print(f"  Workspace:      {hcfg.workspace_id}")
    print(f"  Host:           {hcfg.host}")
    print(f"  Config path:    {active_path}")
-    if write_path != active_path:
-        print(f"  Write path:     {write_path}  (instance-local)")
    print(f"  AI peer:        {hcfg.ai_peer}")
    print(f"  User peer:      {hcfg.peer_name or 'not set'}")
    print(f"  Session key:    {hcfg.resolve_session_name()}")
@@ -284,7 +270,7 @@ def cmd_status(args) -> None:
            print(f"    {peer}: {mode}")
    print(f"  Write freq:     {hcfg.write_frequency}")

-    if hcfg.enabled and (hcfg.api_key or hcfg.base_url):
+    if hcfg.enabled and hcfg.api_key:
        print("\n  Connection... ", end="", flush=True)
        try:
            get_honcho_client(hcfg)
@@ -292,7 +278,7 @@ def cmd_status(args) -> None:
        except Exception as e:
            print(f"FAILED ({e})\n")
    else:
-        reason = "disabled" if not hcfg.enabled else "no API key or base URL"
+        reason = "disabled" if not hcfg.enabled else "no API key"
        print(f"\n  Not connected ({reason})\n")


@@ -417,18 +417,9 @@ def get_honcho_client(config: HonchoClientConfig | None = None) -> Honcho:
    else:
        logger.info("Initializing Honcho client (host: %s, workspace: %s)", config.host, config.workspace_id)

-    # Local Honcho instances don't require an API key, but the SDK
-    # expects a non-empty string.  Use a placeholder for local URLs.
-    _is_local = resolved_base_url and (
-        "localhost" in resolved_base_url
-        or "127.0.0.1" in resolved_base_url
-        or "::1" in resolved_base_url
-    )
-    effective_api_key = config.api_key or ("local" if _is_local else None)
-
    kwargs: dict = {
        "workspace_id": config.workspace_id,
-        "api_key": effective_api_key,
+        "api_key": config.api_key,
        "environment": config.environment,
    }
    if resolved_base_url:
@@ -1,868 +0,0 @@
-"""
-Hermes MCP Server — expose messaging conversations as MCP tools.
-
-Starts a stdio MCP server that lets any MCP client (Claude Code, Cursor, Codex,
-etc.) list conversations, read message history, send messages, poll for live
-events, and manage approval requests across all connected platforms.
-
-Matches OpenClaw's 9-tool MCP channel bridge surface:
-  conversations_list, conversation_get, messages_read, attachments_fetch,
-  events_poll, events_wait, messages_send, permissions_list_open,
-  permissions_respond
-
-Plus: channels_list (Hermes-specific extra)
-
-Usage:
-    hermes mcp serve
-    hermes mcp serve --verbose
-
-MCP client config (e.g. claude_desktop_config.json):
-    {
-        "mcpServers": {
-            "hermes": {
-                "command": "hermes",
-                "args": ["mcp", "serve"]
-            }
-        }
-    }
-"""
-
-from __future__ import annotations
-
-import json
-import logging
-import os
-import re
-import sys
-import threading
-import time
-from dataclasses import dataclass, field
-from datetime import datetime
-from pathlib import Path
-from typing import Any, Dict, List, Optional
-
-logger = logging.getLogger("hermes.mcp_serve")
-
-# ---------------------------------------------------------------------------
-# Lazy MCP SDK import
-# ---------------------------------------------------------------------------
-
-_MCP_SERVER_AVAILABLE = False
-try:
-    from mcp.server.fastmcp import FastMCP
-
-    _MCP_SERVER_AVAILABLE = True
-except ImportError:
-    FastMCP = None  # type: ignore[assignment,misc]
-
-
-# ---------------------------------------------------------------------------
-# Helpers
-# ---------------------------------------------------------------------------
-
-def _get_sessions_dir() -> Path:
-    """Return the sessions directory using HERMES_HOME."""
-    try:
-        from hermes_constants import get_hermes_home
-        return get_hermes_home() / "sessions"
-    except ImportError:
-        return Path(os.environ.get("HERMES_HOME", Path.home() / ".hermes")) / "sessions"
-
-
-def _get_session_db():
-    """Get a SessionDB instance for reading message transcripts."""
-    try:
-        from hermes_state import SessionDB
-        return SessionDB()
-    except Exception as e:
-        logger.debug("SessionDB unavailable: %s", e)
-        return None
-
-
-def _load_sessions_index() -> dict:
-    """Load the gateway sessions.json index directly.
-
-    Returns a dict of session_key -> entry_dict with platform routing info.
-    This avoids importing the full SessionStore which needs GatewayConfig.
-    """
-    sessions_file = _get_sessions_dir() / "sessions.json"
-    if not sessions_file.exists():
-        return {}
-    try:
-        with open(sessions_file, "r", encoding="utf-8") as f:
-            return json.load(f)
-    except Exception as e:
-        logger.debug("Failed to load sessions.json: %s", e)
-        return {}
-
-
-def _load_channel_directory() -> dict:
-    """Load the cached channel directory for available targets."""
-    try:
-        from hermes_constants import get_hermes_home
-        directory_file = get_hermes_home() / "channel_directory.json"
-    except ImportError:
-        directory_file = Path(
-            os.environ.get("HERMES_HOME", Path.home() / ".hermes")
-        ) / "channel_directory.json"
-
-    if not directory_file.exists():
-        return {}
-    try:
-        with open(directory_file, "r", encoding="utf-8") as f:
-            return json.load(f)
-    except Exception as e:
-        logger.debug("Failed to load channel_directory.json: %s", e)
-        return {}
-
-
-def _extract_message_content(msg: dict) -> str:
-    """Extract text content from a message, handling multi-part content."""
-    content = msg.get("content", "")
-    if isinstance(content, list):
-        text_parts = [
-            p.get("text", "") for p in content
-            if isinstance(p, dict) and p.get("type") == "text"
-        ]
-        return "\n".join(text_parts)
-    return str(content) if content else ""
-
-
-def _extract_attachments(msg: dict) -> List[dict]:
-    """Extract non-text attachments from a message.
-
-    Finds: multi-part image/file content blocks, MEDIA: tags in text,
-    image URLs, and file references.
-    """
-    attachments = []
-    content = msg.get("content", "")
-
-    # Multi-part content blocks (image_url, file, etc.)
-    if isinstance(content, list):
-        for part in content:
-            if not isinstance(part, dict):
-                continue
-            ptype = part.get("type", "")
-            if ptype == "image_url":
-                url = part.get("image_url", {}).get("url", "") if isinstance(part.get("image_url"), dict) else ""
-                if url:
-                    attachments.append({"type": "image", "url": url})
-            elif ptype == "image":
-                url = part.get("url", part.get("source", {}).get("url", ""))
-                if url:
-                    attachments.append({"type": "image", "url": url})
-            elif ptype not in ("text",):
-                # Unknown non-text content type
-                attachments.append({"type": ptype, "data": part})
-
-    # MEDIA: tags in text content
-    text = _extract_message_content(msg)
-    if text:
-        media_pattern = re.compile(r'MEDIA:\s*(\S+)')
-        for match in media_pattern.finditer(text):
-            path = match.group(1)
-            attachments.append({"type": "media", "path": path})
-
-    return attachments
-
-
-# ---------------------------------------------------------------------------
-# Event Bridge — polls SessionDB for new messages, maintains event queue
-# ---------------------------------------------------------------------------
-
-QUEUE_LIMIT = 1000
-POLL_INTERVAL = 0.2  # seconds between DB polls (200ms)
-
-
-@dataclass
-class QueueEvent:
-    """An event in the bridge's in-memory queue."""
-    cursor: int
-    type: str  # "message", "approval_requested", "approval_resolved"
-    session_key: str = ""
-    data: dict = field(default_factory=dict)
-
-
-class EventBridge:
-    """Background poller that watches SessionDB for new messages and
-    maintains an in-memory event queue with waiter support.
-
-    This is the Hermes equivalent of OpenClaw's WebSocket gateway bridge.
-    Instead of WebSocket events, we poll the SQLite database for changes.
-    """
-
-    def __init__(self):
-        self._queue: List[QueueEvent] = []
-        self._cursor = 0
-        self._lock = threading.Lock()
-        self._new_event = threading.Event()
-        self._running = False
-        self._thread: Optional[threading.Thread] = None
-        self._last_poll_timestamps: Dict[str, float] = {}  # session_key -> unix timestamp
-        # In-memory approval tracking (populated from events)
-        self._pending_approvals: Dict[str, dict] = {}
-        # mtime cache — skip expensive work when files haven't changed
-        self._sessions_json_mtime: float = 0.0
-        self._state_db_mtime: float = 0.0
-        self._cached_sessions_index: dict = {}
-
-    def start(self):
-        """Start the background polling thread."""
-        if self._running:
-            return
-        self._running = True
-        self._thread = threading.Thread(target=self._poll_loop, daemon=True)
-        self._thread.start()
-        logger.debug("EventBridge started")
-
-    def stop(self):
-        """Stop the background polling thread."""
-        self._running = False
-        self._new_event.set()  # Wake any waiters
-        if self._thread:
-            self._thread.join(timeout=5)
-        logger.debug("EventBridge stopped")
-
-    def poll_events(
-        self,
-        after_cursor: int = 0,
-        session_key: Optional[str] = None,
-        limit: int = 20,
-    ) -> dict:
-        """Return events since after_cursor, optionally filtered by session_key."""
-        with self._lock:
-            events = [
-                e for e in self._queue
-                if e.cursor > after_cursor
-                and (not session_key or e.session_key == session_key)
-            ][:limit]
-
-        next_cursor = events[-1].cursor if events else after_cursor
-        return {
-            "events": [
-                {"cursor": e.cursor, "type": e.type,
-                 "session_key": e.session_key, **e.data}
-                for e in events
-            ],
-            "next_cursor": next_cursor,
-        }
-
-    def wait_for_event(
-        self,
-        after_cursor: int = 0,
-        session_key: Optional[str] = None,
-        timeout_ms: int = 30000,
-    ) -> Optional[dict]:
-        """Block until a matching event arrives or timeout expires."""
-        deadline = time.monotonic() + (timeout_ms / 1000.0)
-
-        while time.monotonic() < deadline:
-            with self._lock:
-                for e in self._queue:
-                    if e.cursor > after_cursor and (
-                        not session_key or e.session_key == session_key
-                    ):
-                        return {
-                            "cursor": e.cursor, "type": e.type,
-                            "session_key": e.session_key, **e.data,
-                        }
-
-            remaining = deadline - time.monotonic()
-            if remaining <= 0:
-                break
-            self._new_event.clear()
-            self._new_event.wait(timeout=min(remaining, POLL_INTERVAL))
-
-        return None
-
-    def list_pending_approvals(self) -> List[dict]:
-        """List approval requests observed during this bridge session."""
-        with self._lock:
-            return sorted(
-                self._pending_approvals.values(),
-                key=lambda a: a.get("created_at", ""),
-            )
-
-    def respond_to_approval(self, approval_id: str, decision: str) -> dict:
-        """Resolve a pending approval (best-effort without gateway IPC)."""
-        with self._lock:
-            approval = self._pending_approvals.pop(approval_id, None)
-
-        if not approval:
-            return {"error": f"Approval not found: {approval_id}"}
-
-        self._enqueue(QueueEvent(
-            cursor=0,  # Will be set by _enqueue
-            type="approval_resolved",
-            session_key=approval.get("session_key", ""),
-            data={"approval_id": approval_id, "decision": decision},
-        ))
-
-        return {"resolved": True, "approval_id": approval_id, "decision": decision}
-
-    def _enqueue(self, event: QueueEvent) -> None:
-        """Add an event to the queue and wake any waiters."""
-        with self._lock:
-            self._cursor += 1
-            event.cursor = self._cursor
-            self._queue.append(event)
-            # Trim queue to limit
-            while len(self._queue) > QUEUE_LIMIT:
-                self._queue.pop(0)
-        self._new_event.set()
-
-    def _poll_loop(self):
-        """Background loop: poll SessionDB for new messages."""
-        db = _get_session_db()
-        if not db:
-            logger.warning("EventBridge: SessionDB unavailable, event polling disabled")
-            return
-
-        while self._running:
-            try:
-                self._poll_once(db)
-            except Exception as e:
-                logger.debug("EventBridge poll error: %s", e)
-            time.sleep(POLL_INTERVAL)
-
-    def _poll_once(self, db):
-        """Check for new messages across all sessions.
-
-        Uses mtime checks on sessions.json and state.db to skip work
-        when nothing has changed — makes 200ms polling essentially free.
-        """
-        # Check if sessions.json has changed (mtime check is ~1μs)
-        sessions_file = _get_sessions_dir() / "sessions.json"
-        try:
-            sj_mtime = sessions_file.stat().st_mtime if sessions_file.exists() else 0.0
-        except OSError:
-            sj_mtime = 0.0
-
-        if sj_mtime != self._sessions_json_mtime:
-            self._sessions_json_mtime = sj_mtime
-            self._cached_sessions_index = _load_sessions_index()
-
-        # Check if state.db has changed
-        try:
-            from hermes_constants import get_hermes_home
-            db_file = get_hermes_home() / "state.db"
-        except ImportError:
-            db_file = Path(os.environ.get("HERMES_HOME", Path.home() / ".hermes")) / "state.db"
-
-        try:
-            db_mtime = db_file.stat().st_mtime if db_file.exists() else 0.0
-        except OSError:
-            db_mtime = 0.0
-
-        if db_mtime == self._state_db_mtime and sj_mtime == self._sessions_json_mtime:
-            return  # Nothing changed since last poll — skip entirely
-
-        self._state_db_mtime = db_mtime
-        entries = self._cached_sessions_index
-
-        for session_key, entry in entries.items():
-            session_id = entry.get("session_id", "")
-            if not session_id:
-                continue
-
-            last_seen = self._last_poll_timestamps.get(session_key, 0.0)
-
-            try:
-                messages = db.get_messages(session_id)
-            except Exception:
-                continue
-
-            if not messages:
-                continue
-
-            # Normalize timestamps to float for comparison
-            def _ts_float(ts) -> float:
-                if isinstance(ts, (int, float)):
-                    return float(ts)
-                if isinstance(ts, str) and ts:
-                    try:
-                        return float(ts)
-                    except ValueError:
-                        # ISO string — parse to epoch
-                        try:
-                            from datetime import datetime
-                            return datetime.fromisoformat(ts).timestamp()
-                        except Exception:
-                            return 0.0
-                return 0.0
-
-            # Find messages newer than our last seen timestamp
-            new_messages = []
-            for msg in messages:
-                ts = _ts_float(msg.get("timestamp", 0))
-                role = msg.get("role", "")
-                if role not in ("user", "assistant"):
-                    continue
-                if ts > last_seen:
-                    new_messages.append(msg)
-
-            for msg in new_messages:
-                content = _extract_message_content(msg)
-                if not content:
-                    continue
-                self._enqueue(QueueEvent(
-                    cursor=0,
-                    type="message",
-                    session_key=session_key,
-                    data={
-                        "role": msg.get("role", ""),
-                        "content": content[:500],
-                        "timestamp": str(msg.get("timestamp", "")),
-                        "message_id": str(msg.get("id", "")),
-                    },
-                ))
-
-            # Update last seen to the most recent message timestamp
-            all_ts = [_ts_float(m.get("timestamp", 0)) for m in messages]
-            if all_ts:
-                latest = max(all_ts)
-                if latest > last_seen:
-                    self._last_poll_timestamps[session_key] = latest
-
-
-# ---------------------------------------------------------------------------
-# MCP Server
-# ---------------------------------------------------------------------------
-
-def create_mcp_server(event_bridge: Optional[EventBridge] = None) -> "FastMCP":
-    """Create and return the Hermes MCP server with all tools registered."""
-    if not _MCP_SERVER_AVAILABLE:
-        raise ImportError(
-            "MCP server requires the 'mcp' package. "
-            "Install with: pip install 'hermes-agent[mcp]'"
-        )
-
-    mcp = FastMCP(
-        "hermes",
-        instructions=(
-            "Hermes Agent messaging bridge. Use these tools to interact with "
-            "conversations across Telegram, Discord, Slack, WhatsApp, Signal, "
-            "Matrix, and other connected platforms."
-        ),
-    )
-
-    bridge = event_bridge or EventBridge()
-
-    # -- conversations_list ------------------------------------------------
-
-    @mcp.tool()
-    def conversations_list(
-        platform: Optional[str] = None,
-        limit: int = 50,
-        search: Optional[str] = None,
-    ) -> str:
-        """List active messaging conversations across connected platforms.
-
-        Returns conversations with their session keys (needed for messages_read),
-        platform, chat type, display name, and last activity time.
-
-        Args:
-            platform: Filter by platform name (telegram, discord, slack, etc.)
-            limit: Maximum number of conversations to return (default 50)
-            search: Optional text to filter conversations by name
-        """
-        entries = _load_sessions_index()
-        conversations = []
-
-        for key, entry in entries.items():
-            origin = entry.get("origin", {})
-            entry_platform = entry.get("platform") or origin.get("platform", "")
-
-            if platform and entry_platform.lower() != platform.lower():
-                continue
-
-            display_name = entry.get("display_name", "")
-            chat_name = origin.get("chat_name", "")
-            if search:
-                search_lower = search.lower()
-                if (search_lower not in display_name.lower()
-                        and search_lower not in chat_name.lower()
-                        and search_lower not in key.lower()):
-                    continue
-
-            conversations.append({
-                "session_key": key,
-                "session_id": entry.get("session_id", ""),
-                "platform": entry_platform,
-                "chat_type": entry.get("chat_type", origin.get("chat_type", "")),
-                "display_name": display_name,
-                "chat_name": chat_name,
-                "user_name": origin.get("user_name", ""),
-                "updated_at": entry.get("updated_at", ""),
-            })
-
-        conversations.sort(key=lambda c: c.get("updated_at", ""), reverse=True)
-        conversations = conversations[:limit]
-
-        return json.dumps({
-            "count": len(conversations),
-            "conversations": conversations,
-        }, indent=2)
-
-    # -- conversation_get --------------------------------------------------
-
-    @mcp.tool()
-    def conversation_get(session_key: str) -> str:
-        """Get detailed info about one conversation by its session key.
-
-        Args:
-            session_key: The session key from conversations_list
-        """
-        entries = _load_sessions_index()
-        entry = entries.get(session_key)
-
-        if not entry:
-            return json.dumps({"error": f"Conversation not found: {session_key}"})
-
-        origin = entry.get("origin", {})
-        return json.dumps({
-            "session_key": session_key,
-            "session_id": entry.get("session_id", ""),
-            "platform": entry.get("platform") or origin.get("platform", ""),
-            "chat_type": entry.get("chat_type", origin.get("chat_type", "")),
-            "display_name": entry.get("display_name", ""),
-            "user_name": origin.get("user_name", ""),
-            "chat_name": origin.get("chat_name", ""),
-            "chat_id": origin.get("chat_id", ""),
-            "thread_id": origin.get("thread_id"),
-            "updated_at": entry.get("updated_at", ""),
-            "created_at": entry.get("created_at", ""),
-            "input_tokens": entry.get("input_tokens", 0),
-            "output_tokens": entry.get("output_tokens", 0),
-            "total_tokens": entry.get("total_tokens", 0),
-        }, indent=2)
-
-    # -- messages_read -----------------------------------------------------
-
-    @mcp.tool()
-    def messages_read(
-        session_key: str,
-        limit: int = 50,
-    ) -> str:
-        """Read recent messages from a conversation.
-
-        Returns the message history in chronological order with role, content,
-        and timestamp for each message.
-
-        Args:
-            session_key: The session key from conversations_list
-            limit: Maximum number of messages to return (default 50, most recent)
-        """
-        entries = _load_sessions_index()
-        entry = entries.get(session_key)
-        if not entry:
-            return json.dumps({"error": f"Conversation not found: {session_key}"})
-
-        session_id = entry.get("session_id", "")
-        if not session_id:
-            return json.dumps({"error": "No session ID for this conversation"})
-
-        db = _get_session_db()
-        if not db:
-            return json.dumps({"error": "Session database unavailable"})
-
-        try:
-            all_messages = db.get_messages(session_id)
-        except Exception as e:
-            return json.dumps({"error": f"Failed to read messages: {e}"})
-
-        filtered = []
-        for msg in all_messages:
-            role = msg.get("role", "")
-            if role in ("user", "assistant"):
-                content = _extract_message_content(msg)
-                if content:
-                    filtered.append({
-                        "id": str(msg.get("id", "")),
-                        "role": role,
-                        "content": content[:2000],
-                        "timestamp": msg.get("timestamp", ""),
-                    })
-
-        messages = filtered[-limit:]
-
-        return json.dumps({
-            "session_key": session_key,
-            "count": len(messages),
-            "total_in_session": len(filtered),
-            "messages": messages,
-        }, indent=2)
-
-    # -- attachments_fetch -------------------------------------------------
-
-    @mcp.tool()
-    def attachments_fetch(
-        session_key: str,
-        message_id: str,
-    ) -> str:
-        """List non-text attachments for a message in a conversation.
-
-        Extracts images, media files, and other non-text content blocks
-        from the specified message.
-
-        Args:
-            session_key: The session key from conversations_list
-            message_id: The message ID from messages_read
-        """
-        entries = _load_sessions_index()
-        entry = entries.get(session_key)
-        if not entry:
-            return json.dumps({"error": f"Conversation not found: {session_key}"})
-
-        session_id = entry.get("session_id", "")
-        if not session_id:
-            return json.dumps({"error": "No session ID for this conversation"})
-
-        db = _get_session_db()
-        if not db:
-            return json.dumps({"error": "Session database unavailable"})
-
-        try:
-            all_messages = db.get_messages(session_id)
-        except Exception as e:
-            return json.dumps({"error": f"Failed to read messages: {e}"})
-
-        # Find the target message
-        target_msg = None
-        for msg in all_messages:
-            if str(msg.get("id", "")) == message_id:
-                target_msg = msg
-                break
-
-        if not target_msg:
-            return json.dumps({"error": f"Message not found: {message_id}"})
-
-        attachments = _extract_attachments(target_msg)
-
-        return json.dumps({
-            "message_id": message_id,
-            "count": len(attachments),
-            "attachments": attachments,
-        }, indent=2)
-
-    # -- events_poll -------------------------------------------------------
-
-    @mcp.tool()
-    def events_poll(
-        after_cursor: int = 0,
-        session_key: Optional[str] = None,
-        limit: int = 20,
-    ) -> str:
-        """Poll for new conversation events since a cursor position.
-
-        Returns events that have occurred since the given cursor. Use the
-        returned next_cursor value for subsequent polls.
-
-        Event types: message, approval_requested, approval_resolved
-
-        Args:
-            after_cursor: Return events after this cursor (0 for all)
-            session_key: Optional filter to one conversation
-            limit: Maximum events to return (default 20)
-        """
-        result = bridge.poll_events(
-            after_cursor=after_cursor,
-            session_key=session_key,
-            limit=limit,
-        )
-        return json.dumps(result, indent=2)
-
-    # -- events_wait -------------------------------------------------------
-
-    @mcp.tool()
-    def events_wait(
-        after_cursor: int = 0,
-        session_key: Optional[str] = None,
-        timeout_ms: int = 30000,
-    ) -> str:
-        """Wait for the next conversation event (long-poll).
-
-        Blocks until a matching event arrives or the timeout expires.
-        Use this for near-real-time event delivery without polling.
-
-        Args:
-            after_cursor: Wait for events after this cursor
-            session_key: Optional filter to one conversation
-            timeout_ms: Maximum wait time in milliseconds (default 30000)
-        """
-        event = bridge.wait_for_event(
-            after_cursor=after_cursor,
-            session_key=session_key,
-            timeout_ms=min(timeout_ms, 300000),  # Cap at 5 minutes
-        )
-        if event:
-            return json.dumps({"event": event}, indent=2)
-        return json.dumps({"event": None, "reason": "timeout"}, indent=2)
-
-    # -- messages_send -----------------------------------------------------
-
-    @mcp.tool()
-    def messages_send(
-        target: str,
-        message: str,
-    ) -> str:
-        """Send a message to a platform conversation.
-
-        The target format is "platform:chat_id" — same format used by the
-        channels_list tool. You can also use human-friendly channel names
-        that will be resolved automatically.
-
-        Examples:
-            target="telegram:6308981865"
-            target="discord:#general"
-            target="slack:#engineering"
-
-        Args:
-            target: Platform target in "platform:identifier" format
-            message: The message text to send
-        """
-        if not target or not message:
-            return json.dumps({"error": "Both target and message are required"})
-
-        try:
-            from tools.send_message_tool import send_message_tool
-            result_str = send_message_tool(
-                {"action": "send", "target": target, "message": message}
-            )
-            return result_str
-        except ImportError:
-            return json.dumps({"error": "Send message tool not available"})
-        except Exception as e:
-            return json.dumps({"error": f"Send failed: {e}"})
-
-    # -- channels_list -----------------------------------------------------
-
-    @mcp.tool()
-    def channels_list(platform: Optional[str] = None) -> str:
-        """List available messaging channels and targets across platforms.
-
-        Returns channels that you can send messages to. The target strings
-        returned here can be used directly with the messages_send tool.
-
-        Args:
-            platform: Filter by platform name (telegram, discord, slack, etc.)
-        """
-        directory = _load_channel_directory()
-        if not directory:
-            entries = _load_sessions_index()
-            targets = []
-            seen = set()
-            for key, entry in entries.items():
-                origin = entry.get("origin", {})
-                p = entry.get("platform") or origin.get("platform", "")
-                chat_id = origin.get("chat_id", "")
-                if not p or not chat_id:
-                    continue
-                if platform and p.lower() != platform.lower():
-                    continue
-                target_str = f"{p}:{chat_id}"
-                if target_str in seen:
-                    continue
-                seen.add(target_str)
-                targets.append({
-                    "target": target_str,
-                    "platform": p,
-                    "name": entry.get("display_name") or origin.get("chat_name", ""),
-                    "chat_type": entry.get("chat_type", origin.get("chat_type", "")),
-                })
-            return json.dumps({"count": len(targets), "channels": targets}, indent=2)
-
-        channels = []
-        for plat, entries_list in directory.items():
-            if platform and plat.lower() != platform.lower():
-                continue
-            if isinstance(entries_list, list):
-                for ch in entries_list:
-                    if isinstance(ch, dict):
-                        chat_id = ch.get("id", ch.get("chat_id", ""))
-                        channels.append({
-                            "target": f"{plat}:{chat_id}" if chat_id else plat,
-                            "platform": plat,
-                            "name": ch.get("name", ch.get("display_name", "")),
-                            "chat_type": ch.get("type", ""),
-                        })
-
-        return json.dumps({"count": len(channels), "channels": channels}, indent=2)
-
-    # -- permissions_list_open ---------------------------------------------
-
-    @mcp.tool()
-    def permissions_list_open() -> str:
-        """List pending approval requests observed during this bridge session.
-
-        Returns exec and plugin approval requests that the bridge has seen
-        since it started. Approvals are live-session only — older approvals
-        from before the bridge connected are not included.
-        """
-        approvals = bridge.list_pending_approvals()
-        return json.dumps({
-            "count": len(approvals),
-            "approvals": approvals,
-        }, indent=2)
-
-    # -- permissions_respond -----------------------------------------------
-
-    @mcp.tool()
-    def permissions_respond(
-        id: str,
-        decision: str,
-    ) -> str:
-        """Respond to a pending approval request.
-
-        Args:
-            id: The approval ID from permissions_list_open
-            decision: One of "allow-once", "allow-always", or "deny"
-        """
-        if decision not in ("allow-once", "allow-always", "deny"):
-            return json.dumps({
-                "error": f"Invalid decision: {decision}. "
-                         f"Must be allow-once, allow-always, or deny"
-            })
-
-        result = bridge.respond_to_approval(id, decision)
-        return json.dumps(result, indent=2)
-
-    return mcp
-
-
-# ---------------------------------------------------------------------------
-# Entry point
-# ---------------------------------------------------------------------------
-
-def run_mcp_server(verbose: bool = False) -> None:
-    """Start the Hermes MCP server on stdio."""
-    if not _MCP_SERVER_AVAILABLE:
-        print(
-            "Error: MCP server requires the 'mcp' package.\n"
-            "Install with: pip install 'hermes-agent[mcp]'",
-            file=sys.stderr,
-        )
-        sys.exit(1)
-
-    if verbose:
-        logging.basicConfig(level=logging.DEBUG, stream=sys.stderr)
-    else:
-        logging.basicConfig(level=logging.WARNING, stream=sys.stderr)
-
-    bridge = EventBridge()
-    bridge.start()
-
-    server = create_mcp_server(event_bridge=bridge)
-
-    import asyncio
-
-    async def _run():
-        try:
-            await server.run_stdio_async()
-        finally:
-            bridge.stop()
-
-    try:
-        asyncio.run(_run())
-    except KeyboardInterrupt:
-        bridge.stop()
@@ -252,7 +252,7 @@ def get_tool_definitions(
    # Determine which tool names the caller wants
    tools_to_include: set = set()

-    if enabled_toolsets is not None:
+    if enabled_toolsets:
        for toolset_name in enabled_toolsets:
            if validate_toolset(toolset_name):
                resolved = resolve_toolset(toolset_name)
@@ -10,12 +10,6 @@
 # container recreation. Environment variables are written to $HERMES_HOME/.env
 # and read by hermes at startup — no container recreation needed for env changes.
 #
-# Tool resolution: the hermes wrapper uses --suffix PATH for nix store tools,
-# so apt/uv-installed versions take priority. The container entrypoint provisions
-# extensible tools on first boot: nodejs/npm via apt, uv via curl, and a Python
-# 3.11 venv (bootstrapped entirely by uv) at ~/.venv with pip seeded. Agents get
-# writable tool prefixes for npm i -g, pip install, uv tool install, etc.
-#
 # Usage:
 #   services.hermes-agent = {
 #     enable = true;
@@ -111,52 +105,22 @@
      fi
      mkdir -p "$TARGET_HOME"
      chown "$HERMES_UID:$HERMES_GID" "$TARGET_HOME"
-      chmod 0750 "$TARGET_HOME"

      # Ensure HERMES_HOME is owned by the target user
      if [ -n "''${HERMES_HOME:-}" ] && [ -d "$HERMES_HOME" ]; then
        chown -R "$HERMES_UID:$HERMES_GID" "$HERMES_HOME"
      fi

-      # ── Provision apt packages (first boot only, cached in writable layer) ──
-      # sudo: agent self-modification
-      # nodejs/npm: writable node so npm i -g works (nix store copies are read-only)
-      # curl: needed for uv installer
-      if [ ! -f /var/lib/hermes-tools-provisioned ] && command -v apt-get >/dev/null 2>&1; then
-        echo "First boot: provisioning agent tools..."
-        apt-get update -qq
-        apt-get install -y -qq sudo nodejs npm curl
-        touch /var/lib/hermes-tools-provisioned
+      # Install sudo on Debian/Ubuntu if missing (first boot only, cached in writable layer)
+      if command -v apt-get >/dev/null 2>&1 && ! command -v sudo >/dev/null 2>&1; then
+        apt-get update -qq >/dev/null 2>&1 && apt-get install -y -qq sudo >/dev/null 2>&1 || true
      fi
-
      if command -v sudo >/dev/null 2>&1 && [ ! -f /etc/sudoers.d/hermes ]; then
        mkdir -p /etc/sudoers.d
        echo "$TARGET_USER ALL=(ALL) NOPASSWD:ALL" > /etc/sudoers.d/hermes
        chmod 0440 /etc/sudoers.d/hermes
      fi

-      # uv (Python manager) — not in Ubuntu repos, retry-safe outside the sentinel
-      if ! command -v uv >/dev/null 2>&1 && [ ! -x "$TARGET_HOME/.local/bin/uv" ] && command -v curl >/dev/null 2>&1; then
-        su -s /bin/sh "$TARGET_USER" -c 'curl -LsSf https://astral.sh/uv/install.sh | sh' || true
-      fi
-
-      # Python 3.11 venv — gives the agent a writable Python with pip.
-      # Uses uv to install Python 3.11 (Ubuntu 24.04 ships 3.12).
-      # --seed includes pip/setuptools so bare `pip install` works.
-      _UV_BIN="$TARGET_HOME/.local/bin/uv"
-      if [ ! -d "$TARGET_HOME/.venv" ] && [ -x "$_UV_BIN" ]; then
-        su -s /bin/sh "$TARGET_USER" -c "
-          export PATH=\"\$HOME/.local/bin:\$PATH\"
-          uv python install 3.11
-          uv venv --python 3.11 --seed \"\$HOME/.venv\"
-        " || true
-      fi
-
-      # Put the agent venv first on PATH so python/pip resolve to writable copies
-      if [ -d "$TARGET_HOME/.venv/bin" ]; then
-        export PATH="$TARGET_HOME/.venv/bin:$PATH"
-      fi
-
      if command -v setpriv >/dev/null 2>&1; then
        exec setpriv --reuid="$HERMES_UID" --regid="$HERMES_GID" --init-groups "$@"
      elif command -v su >/dev/null 2>&1; then
@@ -552,8 +516,8 @@
      # ── Directories ───────────────────────────────────────────────────
      {
        systemd.tmpfiles.rules = [
-          "d ${cfg.stateDir}                0750 ${cfg.user} ${cfg.group} - -"
-          "d ${cfg.stateDir}/.hermes        0750 ${cfg.user} ${cfg.group} - -"
+          "d ${cfg.stateDir}                0755 ${cfg.user} ${cfg.group} - -"
+          "d ${cfg.stateDir}/.hermes        0755 ${cfg.user} ${cfg.group} - -"
          "d ${cfg.stateDir}/home           0750 ${cfg.user} ${cfg.group} - -"
          "d ${cfg.workingDirectory}         0750 ${cfg.user} ${cfg.group} - -"
        ];
@@ -567,23 +531,21 @@
          mkdir -p ${cfg.stateDir}/home
          mkdir -p ${cfg.workingDirectory}
          chown ${cfg.user}:${cfg.group} ${cfg.stateDir} ${cfg.stateDir}/.hermes ${cfg.stateDir}/home ${cfg.workingDirectory}
-          chmod 0750 ${cfg.stateDir} ${cfg.stateDir}/.hermes ${cfg.stateDir}/home ${cfg.workingDirectory}

          # Merge Nix settings into existing config.yaml.
          # Preserves user-added keys (skills, streaming, etc.); Nix keys win.
          # If configFile is user-provided (not generated), overwrite instead of merge.
          ${if cfg.configFile != null then ''
-            install -o ${cfg.user} -g ${cfg.group} -m 0640 -D ${configFile} ${cfg.stateDir}/.hermes/config.yaml
+            install -o ${cfg.user} -g ${cfg.group} -m 0644 -D ${configFile} ${cfg.stateDir}/.hermes/config.yaml
          '' else ''
            ${configMergeScript} ${generatedConfigFile} ${cfg.stateDir}/.hermes/config.yaml
            chown ${cfg.user}:${cfg.group} ${cfg.stateDir}/.hermes/config.yaml
-            chmod 0640 ${cfg.stateDir}/.hermes/config.yaml
+            chmod 0644 ${cfg.stateDir}/.hermes/config.yaml
          ''}

          # Managed mode marker (so interactive shells also detect NixOS management)
          touch ${cfg.stateDir}/.hermes/.managed
          chown ${cfg.user}:${cfg.group} ${cfg.stateDir}/.hermes/.managed
-          chmod 0644 ${cfg.stateDir}/.hermes/.managed

          # Seed auth file if provided
          ${lib.optionalString (cfg.authFile != null) ''
@@ -615,7 +577,7 @@ HERMES_NIX_ENV_EOF

          # Link documents into workspace
          ${lib.concatStringsSep "\n" (lib.mapAttrsToList (name: _value: ''
-            install -o ${cfg.user} -g ${cfg.group} -m 0640 ${documentDerivation}/${name} ${cfg.workingDirectory}/${name}
+            install -o ${cfg.user} -g ${cfg.group} -m 0644 ${documentDerivation}/${name} ${cfg.workingDirectory}/${name}
          '') cfg.documents)}
        '';
      }
@@ -35,7 +35,7 @@

          ${pkgs.lib.concatMapStringsSep "\n" (name: ''
            makeWrapper ${hermesVenv}/bin/${name} $out/bin/${name} \
-              --suffix PATH : "${runtimePath}" \
+              --prefix PATH : "${runtimePath}" \
              --set HERMES_BUNDLED_SKILLS $out/share/hermes-agent/skills
          '') [ "hermes" "hermes-agent" "hermes-acp" ]}

@@ -1 +0,0 @@
-Communication and decision-making frameworks — structured response formats for proposals, trade-off analysis, and stakeholder-ready recommendations.
@@ -1,103 +0,0 @@
---
-name: one-three-one-rule
-description: >
-  Structured decision-making framework for technical proposals and trade-off analysis.
-  When the user faces a choice between multiple approaches (architecture decisions,
-  tool selection, refactoring strategies, migration paths), this skill produces a
-  1-3-1 format: one clear problem statement, three distinct options with pros/cons,
-  and one concrete recommendation with definition of done and implementation plan.
-  Use when the user asks for a "1-3-1", says "give me options", or needs help
-  choosing between competing approaches.
-version: 1.0.0
-author: Willard Moore
-license: MIT
-category: communication
-metadata:
-  hermes:
-    tags: [communication, decision-making, proposals, trade-offs]
---
-
-# 1-3-1 Communication Rule
-
-Structured decision-making format for when a task has multiple viable approaches and the user needs a clear recommendation. Produces a concise problem framing, three options with trade-offs, and an actionable plan for the recommended path.
-
-## When to Use
-
- The user explicitly asks for a "1-3-1" response.
- The user says "give me options" or "what are my choices" for a technical decision.
- A task has multiple viable approaches with meaningful trade-offs (architecture, tooling, migration strategy).
- The user needs a proposal they can forward to a team or stakeholder.
-
-Do NOT use for simple questions with one obvious answer, debugging sessions, or tasks where the user has already decided on an approach.
-
-## Procedure
-
-1. **Problem** (one sentence)
-   - State the core decision or desired outcome in a single concise sentence.
-   - Focus on the *what*, not the *how* — no implementation details, tool names, or specific technologies.
-   - Keep it tight. If you need "and", you're describing two problems.
-
-2. **Options** (exactly three)
-   - Present three distinct, viable approaches labeled A, B, C.
-   - Each option gets a brief description, pros, and cons.
-   - Options should represent genuinely different strategies, not minor variations of the same approach.
-
-3. **Recommendation** (one option)
-   - State which option you recommend and why, based on the user's context and priorities.
-   - Be direct — this is your professional judgment, not a hedge.
-
-4. **Definition of Done**
-   - List the specific success criteria for the recommended option.
-   - These are concrete, verifiable outcomes — not vague aspirations.
-   - If the user picks a different option, revise this section to match.
-
-5. **Implementation Plan**
-   - Concrete steps to execute the recommended option.
-   - Include specific commands, tools, or actions where applicable.
-   - If the user picks a different option, revise this section to match.
-
-## Verification
-
- Response has exactly one Problem sentence.
- Response has exactly three Options (A, B, C) with pros and cons for each.
- Response has a single Recommendation that picks one option with reasoning.
- Definition of Done and Implementation Plan align with the recommended option.
- If the user selects a different option, Recommendation, DoD, and Implementation Plan update accordingly.
-
-## Example
-
-User: "Give me a 1-3-1 for adding retry logic to our API client."
-
-Agent:
-
-**Problem:** API calls to external services fail intermittently under load and need graceful retry handling.
-
-**Options:**
-
- **Option A: Exponential backoff with jitter in a shared utility.**
-  Pros: Simple, well-understood pattern; single implementation shared across all callers.
-  Cons: No circuit-breaking; callers still block during retries.
-
- **Option B: Retry library (tenacity) as a decorator on each endpoint call.**
-  Pros: Configurable per-endpoint; built-in support for circuit breakers and rate limits.
-  Cons: Adds a dependency; decorator pattern can obscure control flow.
-
- **Option C: Queue-based async retry with dead letter handling.**
-  Pros: Non-blocking; failed calls are tracked and replayable; scales well.
-  Cons: Significant complexity increase; requires a queue backend; overkill for low-volume services.
-
-**Recommendation:** Option A. The call volume doesn't justify queue infrastructure, and a shared utility with exponential backoff + jitter covers the failure mode cleanly without new dependencies.
-
-**Definition of Done:**
- `api_retry()` utility handles transient HTTP errors (429, 502, 503, 504).
- Retries up to 3 times with exponential backoff and jitter.
- All external API calls route through the retry utility.
- Logs each retry attempt with endpoint and attempt number.
- Tests cover retry exhaustion, immediate success, and transient-then-success scenarios.
-
-**Implementation Plan:**
-1. Create `utils/api_retry.py` with configurable max retries, base delay, and retryable status codes.
-2. Add jitter using `random.uniform(0, base_delay)` to prevent thundering herd.
-3. Wrap existing API calls in `api_client.py` with the retry utility.
-4. Add unit tests mocking HTTP responses for each retry scenario.
-5. Verify under load with a simple stress test against a flaky endpoint mock.
@@ -304,29 +304,6 @@ def ensure_parent(path: Path) -> None:
    path.parent.mkdir(parents=True, exist_ok=True)


-def resolve_secret_input(value: Any, env: Optional[Dict[str, str]] = None) -> Optional[str]:
-    """Resolve an OpenClaw SecretInput value to a plain string.
-
-    SecretInput can be:
-    - A plain string: "sk-..."
-    - An env template: "${OPENROUTER_API_KEY}"
-    - A SecretRef object: {"source": "env", "id": "OPENROUTER_API_KEY"}
-    """
-    if isinstance(value, str):
-        # Check for env template: "${VAR_NAME}"
-        m = re.match(r"^\$\{(\w+)\}$", value.strip())
-        if m and env:
-            return env.get(m.group(1), "").strip() or None
-        return value.strip() or None
-    if isinstance(value, dict):
-        source = value.get("source", "")
-        ref_id = value.get("id", "")
-        if source == "env" and ref_id and env:
-            return env.get(ref_id, "").strip() or None
-        # File/exec sources can't be resolved here — return None
-    return None
-
-
 def load_yaml_file(path: Path) -> Dict[str, Any]:
    if yaml is None or not path.exists():
        return {}
@@ -913,20 +890,14 @@ class Migrator:
            self.record("command-allowlist", source, destination, "migrated", "Would merge patterns", added_patterns=added)

    def load_openclaw_config(self) -> Dict[str, Any]:
-        # Check current name and legacy config filenames
-        for name in ("openclaw.json", "clawdbot.json", "moldbot.json"):
-            config_path = self.source_root / name
-            if config_path.exists():
-                try:
-                    data = json.loads(config_path.read_text(encoding="utf-8"))
-                    return data if isinstance(data, dict) else {}
-                except json.JSONDecodeError:
-                    continue
-        return {}
-
-    def load_openclaw_env(self) -> Dict[str, str]:
-        """Load the OpenClaw .env file for secrets that live there instead of config."""
-        return parse_env_file(self.source_root / ".env")
+        config_path = self.source_root / "openclaw.json"
+        if not config_path.exists():
+            return {}
+        try:
+            data = json.loads(config_path.read_text(encoding="utf-8"))
+            return data if isinstance(data, dict) else {}
+        except json.JSONDecodeError:
+            return {}

    def merge_env_values(self, additions: Dict[str, str], kind: str, source: Path) -> None:
        destination = self.target_root / ".env"
@@ -1053,10 +1024,6 @@ class Migrator:
                supported_targets=sorted(SUPPORTED_SECRET_TARGETS),
            )

-    def _resolve_channel_secret(self, value: Any) -> Optional[str]:
-        """Resolve a channel config value that may be a SecretRef."""
-        return resolve_secret_input(value, self.load_openclaw_env())
-
    def migrate_discord_settings(self, config: Optional[Dict[str, Any]] = None) -> None:
        config = config or self.load_openclaw_config()
        additions: Dict[str, str] = {}
@@ -1151,17 +1118,15 @@ class Migrator:
        secret_additions: Dict[str, str] = {}

        # Extract provider API keys from models.providers
-        # Note: apiKey values can be strings, env templates, or SecretRef objects
-        openclaw_env = self.load_openclaw_env()
        providers = config.get("models", {}).get("providers", {})
        if isinstance(providers, dict):
            for provider_name, provider_cfg in providers.items():
                if not isinstance(provider_cfg, dict):
                    continue
-                raw_key = provider_cfg.get("apiKey")
-                api_key = resolve_secret_input(raw_key, openclaw_env)
-                if not api_key:
+                api_key = provider_cfg.get("apiKey")
+                if not isinstance(api_key, str) or not api_key.strip():
                    continue
+                api_key = api_key.strip()

                base_url = provider_cfg.get("baseUrl", "")
                api_type = provider_cfg.get("api", "")
@@ -1205,50 +1170,6 @@ class Migrator:
                if isinstance(oai_key, str) and oai_key.strip():
                    secret_additions["VOICE_TOOLS_OPENAI_KEY"] = oai_key.strip()

-        # Also check the OpenClaw .env file — many users store keys there
-        # instead of inline in openclaw.json
-        openclaw_env = self.load_openclaw_env()
-        env_key_mapping = {
-            "OPENROUTER_API_KEY": "OPENROUTER_API_KEY",
-            "OPENAI_API_KEY": "OPENAI_API_KEY",
-            "ANTHROPIC_API_KEY": "ANTHROPIC_API_KEY",
-            "ELEVENLABS_API_KEY": "ELEVENLABS_API_KEY",
-            "TELEGRAM_BOT_TOKEN": "TELEGRAM_BOT_TOKEN",
-            "DEEPSEEK_API_KEY": "DEEPSEEK_API_KEY",
-            "GEMINI_API_KEY": "GEMINI_API_KEY",
-            "ZAI_API_KEY": "ZAI_API_KEY",
-            "MINIMAX_API_KEY": "MINIMAX_API_KEY",
-        }
-        for oc_key, hermes_key in env_key_mapping.items():
-            val = openclaw_env.get(oc_key, "").strip()
-            if val and hermes_key not in secret_additions:
-                secret_additions[hermes_key] = val
-
-        # Check per-agent auth-profiles.json for additional credentials
-        auth_profiles_path = self.source_root / "agents" / "main" / "agent" / "auth-profiles.json"
-        if auth_profiles_path.exists():
-            try:
-                profiles = json.loads(auth_profiles_path.read_text(encoding="utf-8"))
-                if isinstance(profiles, dict):
-                    # auth-profiles.json wraps profiles in a "profiles" key
-                    profile_entries = profiles.get("profiles", profiles) if isinstance(profiles.get("profiles"), dict) else profiles
-                    for profile_name, profile_data in profile_entries.items():
-                        if not isinstance(profile_data, dict):
-                            continue
-                        # Canonical field is "key", "apiKey" is accepted as alias
-                        api_key = profile_data.get("key", "") or profile_data.get("apiKey", "")
-                        if not isinstance(api_key, str) or not api_key.strip():
-                            continue
-                        name_lower = profile_name.lower()
-                        if "openrouter" in name_lower and "OPENROUTER_API_KEY" not in secret_additions:
-                            secret_additions["OPENROUTER_API_KEY"] = api_key.strip()
-                        elif "openai" in name_lower and "OPENAI_API_KEY" not in secret_additions:
-                            secret_additions["OPENAI_API_KEY"] = api_key.strip()
-                        elif "anthropic" in name_lower and "ANTHROPIC_API_KEY" not in secret_additions:
-                            secret_additions["ANTHROPIC_API_KEY"] = api_key.strip()
-            except (json.JSONDecodeError, OSError):
-                pass
-
        if secret_additions:
            self.merge_env_values(secret_additions, "provider-keys", self.source_root / "openclaw.json")
        else:
@@ -1297,11 +1218,7 @@ class Migrator:

        if self.execute:
            backup_path = self.maybe_backup(destination)
-            existing_model = hermes_config.get("model")
-            if isinstance(existing_model, dict):
-                existing_model["default"] = model_str
-            else:
-                hermes_config["model"] = {"default": model_str}
+            hermes_config["model"] = model_str
            dump_yaml_file(destination, hermes_config)
            self.record("model-config", source_path, destination, "migrated", backup=str(backup_path) if backup_path else "", model=model_str)
        else:
@@ -1327,44 +1244,22 @@ class Migrator:
        if isinstance(provider, str) and provider in ("elevenlabs", "openai", "edge"):
            tts_data["provider"] = provider

-        # TTS provider settings live under messages.tts.providers.{provider}
-        # in OpenClaw (not messages.tts.elevenlabs directly)
-        providers = tts.get("providers") or {}
-
-        # Also check the top-level "talk" config which has provider settings too
-        talk_cfg = (config or self.load_openclaw_config()).get("talk") or {}
-        talk_providers = talk_cfg.get("providers") or {}
-
-        # Merge: messages.tts.providers takes priority, then talk.providers,
-        # then legacy flat keys (messages.tts.elevenlabs, etc.)
-        elevenlabs = (
-            (providers.get("elevenlabs") or {})
-            if isinstance(providers.get("elevenlabs"), dict) else
-            (talk_providers.get("elevenlabs") or {})
-            if isinstance(talk_providers.get("elevenlabs"), dict) else
-            (tts.get("elevenlabs") or {})
-        )
+        elevenlabs = tts.get("elevenlabs", {})
        if isinstance(elevenlabs, dict):
            el_settings: Dict[str, str] = {}
-            voice_id = elevenlabs.get("voiceId") or talk_cfg.get("voiceId")
+            voice_id = elevenlabs.get("voiceId")
            if isinstance(voice_id, str) and voice_id.strip():
                el_settings["voice_id"] = voice_id.strip()
-            model_id = elevenlabs.get("modelId") or talk_cfg.get("modelId")
+            model_id = elevenlabs.get("modelId")
            if isinstance(model_id, str) and model_id.strip():
                el_settings["model_id"] = model_id.strip()
            if el_settings:
                tts_data["elevenlabs"] = el_settings

-        openai_tts = (
-            (providers.get("openai") or {})
-            if isinstance(providers.get("openai"), dict) else
-            (talk_providers.get("openai") or {})
-            if isinstance(talk_providers.get("openai"), dict) else
-            (tts.get("openai") or {})
-        )
+        openai_tts = tts.get("openai", {})
        if isinstance(openai_tts, dict):
            oai_settings: Dict[str, str] = {}
-            oai_model = openai_tts.get("model") or openai_tts.get("modelId")
+            oai_model = openai_tts.get("model")
            if isinstance(oai_model, str) and oai_model.strip():
                oai_settings["model"] = oai_model.strip()
            oai_voice = openai_tts.get("voice")
@@ -1373,11 +1268,7 @@ class Migrator:
            if oai_settings:
                tts_data["openai"] = oai_settings

-        edge_tts = (
-            (providers.get("edge") or {})
-            if isinstance(providers.get("edge"), dict) else
-            (tts.get("edge") or {})
-        )
+        edge_tts = tts.get("edge", {})
        if isinstance(edge_tts, dict):
            edge_voice = edge_tts.get("voice")
            if isinstance(edge_voice, str) and edge_voice.strip():
@@ -1407,29 +1298,15 @@ class Migrator:
            self.record("tts-config", source_path, destination, "migrated", "Would set TTS config", settings=list(tts_data.keys()))

    def migrate_shared_skills(self) -> None:
-        # Check all OpenClaw skill sources: managed, personal, project-level
-        skill_sources = [
-            (self.source_root / "skills", "shared-skills", "managed skills"),
-            (Path.home() / ".agents" / "skills", "personal-skills", "personal cross-project skills"),
-            (self.source_root / "workspace" / ".agents" / "skills", "project-skills", "project-level shared skills"),
-            (self.source_root / "workspace.default" / ".agents" / "skills", "project-skills", "project-level shared skills"),
-        ]
-        found_any = False
-        for source_root, kind_label, desc in skill_sources:
-            if source_root.exists():
-                found_any = True
-                self._import_skill_directory(source_root, kind_label, desc)
-        if not found_any:
-            destination_root = self.target_root / "skills" / SKILL_CATEGORY_DIRNAME
-            self.record("shared-skills", None, destination_root, "skipped", "No shared OpenClaw skills directories found")
-
-    def _import_skill_directory(self, source_root: Path, kind_label: str, desc: str) -> None:
-        """Import skills from a single source directory into openclaw-imports."""
+        source_root = self.source_root / "skills"
        destination_root = self.target_root / "skills" / SKILL_CATEGORY_DIRNAME
+        if not source_root.exists():
+            self.record("shared-skills", None, destination_root, "skipped", "No shared OpenClaw skills directory found")
+            return

        skill_dirs = [p for p in sorted(source_root.iterdir()) if p.is_dir() and (p / "SKILL.md").exists()]
        if not skill_dirs:
-            self.record(kind_label, source_root, destination_root, "skipped", f"No skills with SKILL.md found in {desc}")
+            self.record("shared-skills", source_root, destination_root, "skipped", "No shared skills with SKILL.md found")
            return

        for skill_dir in skill_dirs:
@@ -1437,7 +1314,7 @@ class Migrator:
            final_destination = destination
            if destination.exists():
                if self.skill_conflict_mode == "skip":
-                    self.record(kind_label, skill_dir, destination, "conflict", "Destination skill already exists")
+                    self.record("shared-skill", skill_dir, destination, "conflict", "Destination skill already exists")
                    continue
                if self.skill_conflict_mode == "rename":
                    final_destination = self.resolve_skill_destination(destination)
@@ -1452,19 +1329,19 @@ class Migrator:
                details: Dict[str, Any] = {"backup": str(backup_path) if backup_path else ""}
                if final_destination != destination:
                    details["renamed_from"] = str(destination)
-                self.record(kind_label, skill_dir, final_destination, "migrated", **details)
+                self.record("shared-skill", skill_dir, final_destination, "migrated", **details)
            else:
                if final_destination != destination:
                    self.record(
-                        kind_label,
+                        "shared-skill",
                        skill_dir,
                        final_destination,
                        "migrated",
-                        f"Would copy {desc} directory under a renamed folder",
+                        "Would copy shared skill directory under a renamed folder",
                        renamed_from=str(destination),
                    )
                else:
-                    self.record(kind_label, skill_dir, final_destination, "migrated", f"Would copy {desc} directory")
+                    self.record("shared-skill", skill_dir, final_destination, "migrated", "Would copy shared skill directory")

        desc_path = destination_root / "DESCRIPTION.md"
        if self.execute:
@@ -1641,7 +1518,6 @@ class Migrator:
            self.source_candidate("workspace/IDENTITY.md", "workspace.default/IDENTITY.md"),
            self.source_candidate("workspace/TOOLS.md", "workspace.default/TOOLS.md"),
            self.source_candidate("workspace/HEARTBEAT.md", "workspace.default/HEARTBEAT.md"),
-            self.source_candidate("workspace/BOOTSTRAP.md", "workspace.default/BOOTSTRAP.md"),
        ]
        for candidate in candidates:
            if candidate:
@@ -1913,9 +1789,8 @@ class Migrator:
        human_delay = defaults.get("humanDelay") or {}
        if human_delay:
            hd = hermes_cfg.get("human_delay") or {}
-            hd_mode = human_delay.get("mode") or ("natural" if human_delay.get("enabled") else None)
-            if hd_mode and hd_mode != "off":
-                hd["mode"] = hd_mode
+            if human_delay.get("enabled"):
+                hd["mode"] = "natural"
            if human_delay.get("minMs"):
                hd["min_ms"] = human_delay["minMs"]
            if human_delay.get("maxMs"):
@@ -1929,11 +1804,11 @@ class Migrator:
            changes = True

        # Map terminal/exec settings
-        exec_cfg = (config.get("tools") or {}).get("exec") or {}
+        exec_cfg = defaults.get("exec") or (config.get("tools") or {}).get("exec") or {}
        if exec_cfg:
            terminal_cfg = hermes_cfg.get("terminal") or {}
-            if exec_cfg.get("timeoutSec") or exec_cfg.get("timeout"):
-                terminal_cfg["timeout"] = exec_cfg.get("timeoutSec") or exec_cfg.get("timeout")
+            if exec_cfg.get("timeout"):
+                terminal_cfg["timeout"] = exec_cfg["timeout"]
                changes = True
            hermes_cfg["terminal"] = terminal_cfg

@@ -2008,34 +1883,24 @@ class Migrator:
        sr = hermes_cfg.get("session_reset") or {}
        changes = False

-        # OpenClaw uses session.reset (structured) and session.resetTriggers (string array)
-        reset = session.get("reset") or {}
-        reset_triggers = session.get("resetTriggers") or session.get("reset_triggers") or []
+        reset_triggers = session.get("resetTriggers") or session.get("reset_triggers") or {}
+        if reset_triggers:
+            daily = reset_triggers.get("daily") or {}
+            idle = reset_triggers.get("idle") or {}

-        if reset:
-            # Structured reset config: has mode, atHour, idleMinutes
-            mode = reset.get("mode", "")
-            if mode == "daily":
+            if daily.get("enabled") and idle.get("enabled"):
+                sr["mode"] = "both"
+            elif daily.get("enabled"):
                sr["mode"] = "daily"
-            elif mode == "idle":
+            elif idle.get("enabled"):
                sr["mode"] = "idle"
            else:
-                sr["mode"] = mode or "none"
-            if reset.get("atHour") is not None:
-                sr["at_hour"] = reset["atHour"]
-            if reset.get("idleMinutes"):
-                sr["idle_minutes"] = reset["idleMinutes"]
-            changes = True
-        elif isinstance(reset_triggers, list) and reset_triggers:
-            # Simple string triggers: ["daily", "idle"]
-            has_daily = "daily" in reset_triggers
-            has_idle = "idle" in reset_triggers
-            if has_daily and has_idle:
-                sr["mode"] = "both"
-            elif has_daily:
-                sr["mode"] = "daily"
-            elif has_idle:
-                sr["mode"] = "idle"
+                sr["mode"] = "none"
+
+            if daily.get("hour") is not None:
+                sr["at_hour"] = daily["hour"]
+            if idle.get("minutes") or idle.get("timeoutMinutes"):
+                sr["idle_minutes"] = idle.get("minutes") or idle.get("timeoutMinutes")
            changes = True

        if changes:
@@ -2227,12 +2092,11 @@ class Migrator:
        browser_hermes = hermes_cfg.get("browser") or {}
        changed = False

-        # Map fields that have Hermes equivalents
-        if browser.get("cdpUrl"):
-            browser_hermes["cdp_url"] = browser["cdpUrl"]
+        if browser.get("inactivityTimeoutMs"):
+            browser_hermes["inactivity_timeout"] = browser["inactivityTimeoutMs"] // 1000
            changed = True
-        if browser.get("headless") is not None:
-            browser_hermes["headless"] = browser["headless"]
+        if browser.get("commandTimeoutMs"):
+            browser_hermes["command_timeout"] = browser["commandTimeoutMs"] // 1000
            changed = True

        if changed:
@@ -2243,9 +2107,9 @@ class Migrator:
            self.record("browser-config", "openclaw.json browser.*", "config.yaml browser",
                        "migrated")

-        # Archive remaining browser settings
+        # Archive advanced browser settings
        advanced = {k: v for k, v in browser.items()
-                   if k not in ("cdpUrl", "headless") and v}
+                   if k not in ("inactivityTimeoutMs", "commandTimeoutMs") and v}
        if advanced and self.archive_dir:
            if self.execute:
                self.archive_dir.mkdir(parents=True, exist_ok=True)
@@ -2266,22 +2130,18 @@ class Migrator:
        hermes_cfg = load_yaml_file(hermes_cfg_path)
        changed = False

-        # Map exec timeout -> terminal timeout (field is timeoutSec in OpenClaw)
+        # Map exec timeout -> terminal timeout
        exec_cfg = tools.get("exec") or {}
-        timeout_val = exec_cfg.get("timeoutSec") or exec_cfg.get("timeout")
-        if timeout_val:
+        if exec_cfg.get("timeout"):
            terminal_cfg = hermes_cfg.get("terminal") or {}
-            terminal_cfg["timeout"] = timeout_val
+            terminal_cfg["timeout"] = exec_cfg["timeout"]
            hermes_cfg["terminal"] = terminal_cfg
            changed = True

-        # Map web search API key (path: tools.web.search.brave.apiKey in OpenClaw)
-        web_cfg = tools.get("web") or tools.get("webSearch") or {}
-        search_cfg = web_cfg.get("search") or web_cfg if not web_cfg.get("search") else web_cfg["search"]
-        brave_cfg = search_cfg.get("brave") or {}
-        brave_key = brave_cfg.get("apiKey") or search_cfg.get("braveApiKey") or web_cfg.get("braveApiKey")
-        if brave_key and isinstance(brave_key, str) and self.migrate_secrets:
-            self._set_env_var("BRAVE_API_KEY", brave_key, "tools.web.search.brave.apiKey")
+        # Map web search API key
+        web_cfg = tools.get("webSearch") or tools.get("web") or {}
+        if web_cfg.get("braveApiKey") and self.migrate_secrets:
+            self._set_env_var("BRAVE_API_KEY", web_cfg["braveApiKey"], "tools.webSearch.braveApiKey")

        if changed and self.execute:
            self.maybe_backup(hermes_cfg_path)
@@ -2309,9 +2169,8 @@ class Migrator:
        hermes_cfg_path = self.target_root / "config.yaml"
        hermes_cfg = load_yaml_file(hermes_cfg_path)

-        # Map approval mode (nested under approvals.exec.mode in OpenClaw)
-        exec_approvals = approvals.get("exec") or {}
-        mode = (exec_approvals.get("mode") if isinstance(exec_approvals, dict) else None) or approvals.get("mode") or approvals.get("defaultMode")
+        # Map approval mode
+        mode = approvals.get("mode") or approvals.get("defaultMode")
        if mode:
            mode_map = {"auto": "off", "always": "manual", "smart": "smart", "manual": "manual"}
            hermes_mode = mode_map.get(mode, "manual")
@@ -2455,24 +2314,9 @@ class Migrator:
            notes.append("")

        notes.extend([
-            "## IMPORTANT: Archive the OpenClaw Directory",
-            "",
-            "After migration, your OpenClaw directory still exists on disk with workspace",
-            "state files (todo.json, sessions, logs). If the Hermes agent discovers these",
-            "directories, it may read/write to them instead of the Hermes state, causing",
-            "confusion (e.g., cron jobs reading a different todo list than interactive sessions).",
-            "",
-            "**Strongly recommended:** Run `hermes claw cleanup` to rename the OpenClaw",
-            "directory to `.openclaw.pre-migration`. This prevents the agent from finding it.",
-            "The directory is renamed, not deleted — you can undo this at any time.",
-            "",
-            "If you skip this step and notice the agent getting confused about workspaces",
-            "or todo lists, run `hermes claw cleanup` to fix it.",
-            "",
            "## Hermes-Specific Setup",
            "",
            "After migration, you may want to:",
-            "- Run `hermes claw cleanup` to archive the OpenClaw directory (prevents state confusion)",
            "- Run `hermes setup` to configure any remaining settings",
            "- Run `hermes mcp list` to verify MCP servers were imported correctly",
            "- Run `hermes cron` to recreate scheduled tasks (see archive/cron-config.json)",
@@ -1,97 +0,0 @@
---
-name: canvas
-description: Canvas LMS integration — fetch enrolled courses and assignments using API token authentication.
-version: 1.0.0
-author: community
-license: MIT
-prerequisites:
-  env_vars: [CANVAS_API_TOKEN, CANVAS_BASE_URL]
-metadata:
-  hermes:
-    tags: [Canvas, LMS, Education, Courses, Assignments]
---
-
-# Canvas LMS — Course & Assignment Access
-
-Read-only access to Canvas LMS for listing courses and assignments.
-
-## Scripts
-
- `scripts/canvas_api.py` — Python CLI for Canvas API calls
-
-## Setup
-
-1. Log in to your Canvas instance in a browser
-2. Go to **Account → Settings** (click your profile icon, then Settings)
-3. Scroll to **Approved Integrations** and click **+ New Access Token**
-4. Name the token (e.g., "Hermes Agent"), set an optional expiry, and click **Generate Token**
-5. Copy the token and add to `~/.hermes/.env`:
-
-```
-CANVAS_API_TOKEN=your_token_here
-CANVAS_BASE_URL=https://yourschool.instructure.com
-```
-
-The base URL is whatever appears in your browser when you're logged into Canvas (no trailing slash).
-
-## Usage
-
-```bash
-CANVAS="python $HERMES_HOME/skills/productivity/canvas/scripts/canvas_api.py"
-
-# List all active courses
-$CANVAS list_courses --enrollment-state active
-
-# List all courses (any state)
-$CANVAS list_courses
-
-# List assignments for a specific course
-$CANVAS list_assignments 12345
-
-# List assignments ordered by due date
-$CANVAS list_assignments 12345 --order-by due_at
-```
-
-## Output Format
-
-**list_courses** returns:
-```json
-[{"id": 12345, "name": "Intro to CS", "course_code": "CS101", "workflow_state": "available", "start_at": "...", "end_at": "..."}]
-```
-
-**list_assignments** returns:
-```json
-[{"id": 67890, "name": "Homework 1", "due_at": "2025-02-15T23:59:00Z", "points_possible": 100, "submission_types": ["online_upload"], "html_url": "...", "description": "...", "course_id": 12345}]
-```
-
-Note: Assignment descriptions are truncated to 500 characters. The `html_url` field links to the full assignment page in Canvas.
-
-## API Reference (curl)
-
-```bash
-# List courses
-curl -s -H "Authorization: Bearer $CANVAS_API_TOKEN" \
-  "$CANVAS_BASE_URL/api/v1/courses?enrollment_state=active&per_page=10"
-
-# List assignments for a course
-curl -s -H "Authorization: Bearer $CANVAS_API_TOKEN" \
-  "$CANVAS_BASE_URL/api/v1/courses/COURSE_ID/assignments?per_page=10&order_by=due_at"
-```
-
-Canvas uses `Link` headers for pagination. The Python script handles pagination automatically.
-
-## Rules
-
- This skill is **read-only** — it only fetches data, never modifies courses or assignments
- On first use, verify auth by running `$CANVAS list_courses` — if it fails with 401, guide the user through setup
- Canvas rate-limits to ~700 requests per 10 minutes; check `X-Rate-Limit-Remaining` header if hitting limits
-
-## Troubleshooting
-
-| Problem | Fix |
-|---------|-----|
-| 401 Unauthorized | Token invalid or expired — regenerate in Canvas Settings |
-| 403 Forbidden | Token lacks permission for this course |
-| Empty course list | Try `--enrollment-state active` or omit the flag to see all states |
-| Wrong institution | Verify `CANVAS_BASE_URL` matches the URL in your browser |
-| Timeout errors | Check network connectivity to your Canvas instance |
@@ -1,157 +0,0 @@
-#!/usr/bin/env python3
-"""Canvas LMS API CLI for Hermes Agent.
-
-A thin CLI wrapper around the Canvas REST API.
-Authenticates using a personal access token from environment variables.
-
-Usage:
-  python canvas_api.py list_courses [--per-page N] [--enrollment-state STATE]
-  python canvas_api.py list_assignments COURSE_ID [--per-page N] [--order-by FIELD]
-"""
-
-import argparse
-import json
-import os
-import sys
-
-import requests
-
-CANVAS_API_TOKEN = os.environ.get("CANVAS_API_TOKEN", "")
-CANVAS_BASE_URL = os.environ.get("CANVAS_BASE_URL", "").rstrip("/")
-
-
-def _check_config():
-    """Validate required environment variables are set."""
-    missing = []
-    if not CANVAS_API_TOKEN:
-        missing.append("CANVAS_API_TOKEN")
-    if not CANVAS_BASE_URL:
-        missing.append("CANVAS_BASE_URL")
-    if missing:
-        print(
-            f"Missing required environment variables: {', '.join(missing)}\n"
-            "Set them in ~/.hermes/.env or export them in your shell.\n"
-            "See the canvas skill SKILL.md for setup instructions.",
-            file=sys.stderr,
-        )
-        sys.exit(1)
-
-
-def _headers():
-    return {"Authorization": f"Bearer {CANVAS_API_TOKEN}"}
-
-
-def _paginated_get(url, params=None, max_items=200):
-    """Fetch all pages up to max_items, following Canvas Link headers."""
-    results = []
-    while url and len(results) < max_items:
-        resp = requests.get(url, headers=_headers(), params=params, timeout=30)
-        resp.raise_for_status()
-        results.extend(resp.json())
-        params = None  # params are included in the Link URL for subsequent pages
-        url = None
-        link = resp.headers.get("Link", "")
-        for part in link.split(","):
-            if 'rel="next"' in part:
-                url = part.split(";")[0].strip().strip("<>")
-    return results[:max_items]
-
-
-# =========================================================================
-# Commands
-# =========================================================================
-
-
-def list_courses(args):
-    """List enrolled courses."""
-    _check_config()
-    url = f"{CANVAS_BASE_URL}/api/v1/courses"
-    params = {"per_page": args.per_page}
-    if args.enrollment_state:
-        params["enrollment_state"] = args.enrollment_state
-    try:
-        courses = _paginated_get(url, params)
-    except requests.HTTPError as e:
-        print(f"API error: {e.response.status_code} {e.response.text}", file=sys.stderr)
-        sys.exit(1)
-    output = [
-        {
-            "id": c["id"],
-            "name": c.get("name", ""),
-            "course_code": c.get("course_code", ""),
-            "enrollment_term_id": c.get("enrollment_term_id"),
-            "start_at": c.get("start_at"),
-            "end_at": c.get("end_at"),
-            "workflow_state": c.get("workflow_state", ""),
-        }
-        for c in courses
-    ]
-    print(json.dumps(output, indent=2))
-
-
-def list_assignments(args):
-    """List assignments for a course."""
-    _check_config()
-    url = f"{CANVAS_BASE_URL}/api/v1/courses/{args.course_id}/assignments"
-    params = {"per_page": args.per_page}
-    if args.order_by:
-        params["order_by"] = args.order_by
-    try:
-        assignments = _paginated_get(url, params)
-    except requests.HTTPError as e:
-        print(f"API error: {e.response.status_code} {e.response.text}", file=sys.stderr)
-        sys.exit(1)
-    output = [
-        {
-            "id": a["id"],
-            "name": a.get("name", ""),
-            "description": (a.get("description") or "")[:500],
-            "due_at": a.get("due_at"),
-            "points_possible": a.get("points_possible"),
-            "submission_types": a.get("submission_types", []),
-            "html_url": a.get("html_url", ""),
-            "course_id": a.get("course_id"),
-        }
-        for a in assignments
-    ]
-    print(json.dumps(output, indent=2))
-
-
-# =========================================================================
-# CLI parser
-# =========================================================================
-
-
-def main():
-    parser = argparse.ArgumentParser(
-        description="Canvas LMS API CLI for Hermes Agent"
-    )
-    sub = parser.add_subparsers(dest="command", required=True)
-
-    # --- list_courses ---
-    p = sub.add_parser("list_courses", help="List enrolled courses")
-    p.add_argument("--per-page", type=int, default=50, help="Results per page (default 50)")
-    p.add_argument(
-        "--enrollment-state",
-        default="",
-        help="Filter by enrollment state (active, invited_or_pending, completed)",
-    )
-    p.set_defaults(func=list_courses)
-
-    # --- list_assignments ---
-    p = sub.add_parser("list_assignments", help="List assignments for a course")
-    p.add_argument("course_id", help="Canvas course ID")
-    p.add_argument("--per-page", type=int, default=50, help="Results per page (default 50)")
-    p.add_argument(
-        "--order-by",
-        default="",
-        help="Order by field (due_at, name, position)",
-    )
-    p.set_defaults(func=list_assignments)
-
-    args = parser.parse_args()
-    args.func(args)
-
-
-if __name__ == "__main__":
-    main()
@@ -1,324 +0,0 @@
---
-name: memento-flashcards
-description: >-
-  Spaced-repetition flashcard system. Create cards from facts or text,
-  chat with flashcards using free-text answers graded by the agent,
-  generate quizzes from YouTube transcripts, review due cards with
-  adaptive scheduling, and export/import decks as CSV.
-version: 1.0.0
-author: Memento AI
-license: MIT
-platforms: [macos, linux]
-metadata:
-  hermes:
-    tags: [Education, Flashcards, Spaced Repetition, Learning, Quiz, YouTube]
-    requires_toolsets: [terminal]
-    category: productivity
---
-
-# Memento Flashcards — Spaced-Repetition Flashcard Skill
-
-## Overview
-
-Memento gives you a local, file-based flashcard system with spaced-repetition scheduling.
-Users can chat with their flashcards by answering in free text and having the agent grade the response before scheduling the next review.
-Use it whenever the user wants to:
-
- **Remember a fact** — turn any statement into a Q/A flashcard
- **Study with spaced repetition** — review due cards with adaptive intervals and agent-graded free-text answers
- **Quiz from a YouTube video** — fetch a transcript and generate a 5-question quiz
- **Manage decks** — organise cards into collections, export/import CSV
-
-All card data lives in a single JSON file. No external API keys are required — you (the agent) generate flashcard content and quiz questions directly.
-
-User-facing response style for Memento Flashcards:
- Use plain text only. Do not use Markdown formatting in replies to the user.
- Keep review and quiz feedback brief and neutral. Avoid extra praise, pep, or long explanations.
-
-## When to Use
-
-Use this skill when the user wants to:
- Save facts as flashcards for later review
- Review due cards with spaced repetition
- Generate a quiz from a YouTube video transcript
- Import, export, inspect, or delete flashcard data
-
-Do not use this skill for general Q&A, coding help, or non-memory tasks.
-
-## Quick Reference
-
-| User intent | Action |
-|---|---|
-| "Remember that X" / "save this as a flashcard" | Generate a Q/A card, call `memento_cards.py add` |
-| Sends a fact without mentioning flashcards | Ask "Want me to save this as a Memento flashcard?" — only create if confirmed |
-| "Create a flashcard" | Ask for Q, A, collection; call `memento_cards.py add` |
-| "Review my cards" | Call `memento_cards.py due`, present cards one-by-one |
-| "Quiz me on [YouTube URL]" | Call `youtube_quiz.py fetch VIDEO_ID`, generate 5 questions, call `memento_cards.py add-quiz` |
-| "Export my cards" | Call `memento_cards.py export --output PATH` |
-| "Import cards from CSV" | Call `memento_cards.py import --file PATH --collection NAME` |
-| "Show my stats" | Call `memento_cards.py stats` |
-| "Delete a card" | Call `memento_cards.py delete --id ID` |
-| "Delete a collection" | Call `memento_cards.py delete-collection --collection NAME` |
-
-## Card Storage
-
-Cards are stored in a JSON file at:
-
-```
-~/.hermes/skills/productivity/memento-flashcards/data/cards.json
-```
-
-**Never edit this file directly.** Always use `memento_cards.py` subcommands. The script handles atomic writes (write to temp file, then rename) to prevent corruption.
-
-The file is created automatically on first use.
-
-## Procedure
-
-### Creating Cards from Facts
-
-### Activation Rules
-
-Not every factual statement should become a flashcard. Use this three-tier check:
-
-1. **Explicit intent** — the user mentions "memento", "flashcard", "remember this", "save this card", "add a card", or similar phrasing that clearly requests a flashcard → **create the card directly**, no confirmation needed.
-2. **Implicit intent** — the user sends a factual statement without mentioning flashcards (e.g. "The speed of light is 299,792 km/s") → **ask first**: "Want me to save this as a Memento flashcard?" Only create the card if the user confirms.
-3. **No intent** — the message is a coding task, a question, instructions, normal conversation, or anything that is clearly not a fact to memorize → **do NOT activate this skill at all**. Let other skills or default behavior handle it.
-
-When activation is confirmed (tier 1 directly, tier 2 after confirmation), generate a flashcard:
-
-**Step 1:** Turn the statement into a Q/A pair. Use this format internally:
-
-```
-Turn the factual statement into a front-back pair.
-Return exactly two lines:
-Q: <question text>
-A: <answer text>
-
-Statement: "{statement}"
-```
-
-Rules:
- The question should test recall of the key fact
- The answer should be concise and direct
-
-**Step 2:** Call the script to store the card:
-
-```bash
-python3 ~/.hermes/skills/productivity/memento-flashcards/scripts/memento_cards.py add \
-  --question "What year did World War 2 end?" \
-  --answer "1945" \
-  --collection "History"
-```
-
-If the user doesn't specify a collection, use `"General"` as the default.
-
-The script outputs JSON confirming the created card.
-
-### Manual Card Creation
-
-When the user explicitly asks to create a flashcard, ask them for:
-1. The question (front of card)
-2. The answer (back of card)
-3. The collection name (optional — default to `"General"`)
-
-Then call `memento_cards.py add` as above.
-
-### Reviewing Due Cards
-
-When the user wants to review, fetch all due cards:
-
-```bash
-python3 ~/.hermes/skills/productivity/memento-flashcards/scripts/memento_cards.py due
-```
-
-This returns a JSON array of cards where `next_review_at <= now`. If a collection filter is needed:
-
-```bash
-python3 ~/.hermes/skills/productivity/memento-flashcards/scripts/memento_cards.py due --collection "History"
-```
-
-**Review flow (free-text grading):**
-
-Here is an example of the EXACT interaction pattern you must follow. The user answers, you grade them, tell them the correct answer, then rate the card.
-
-**Example interaction:**
-
-> **Agent:** What year did the Berlin Wall fall?
->
-> **User:** 1991
->
-> **Agent:** Not quite. The Berlin Wall fell in 1989. Next review is tomorrow.
-> *(agent calls: memento_cards.py rate --id ABC --rating hard --user-answer "1991")*
->
-> Next question: Who was the first person to walk on the moon?
-
-**The rules:**
-
-1. Show only the question. Wait for the user to answer.
-2. After receiving their answer, compare it to the expected answer and grade it:
-   - **correct** → user got the key fact right (even if worded differently)
-   - **partial** → right track but missing the core detail
-   - **incorrect** → wrong or off-topic
-3. **You MUST tell the user the correct answer and how they did.** Keep it short and plain-text. Use this format:
-   - correct: "Correct. Answer: {answer}. Next review in 7 days."
-   - partial: "Close. Answer: {answer}. {what they missed}. Next review in 3 days."
-   - incorrect: "Not quite. Answer: {answer}. Next review tomorrow."
-4. Then call the rate command: correct→easy, partial→good, incorrect→hard.
-5. Then show the next question.
-
-```bash
-python3 ~/.hermes/skills/productivity/memento-flashcards/scripts/memento_cards.py rate \
-  --id CARD_ID --rating easy --user-answer "what the user said"
-```
-
-**Never skip step 3.** The user must always see the correct answer and feedback before you move on.
-
-If no cards are due, tell the user: "No cards due for review right now. Check back later!"
-
-**Retire override:** At any point the user can say "retire this card" to permanently remove it from reviews. Use `--rating retire` for this.
-
-### Spaced Repetition Algorithm
-
-The rating determines the next review interval:
-
-| Rating | Interval | ease_streak | Status change |
-|---|---|---|---|
-| **hard** | +1 day | reset to 0 | stays learning |
-| **good** | +3 days | reset to 0 | stays learning |
-| **easy** | +7 days | +1 | if ease_streak >= 3 → retired |
-| **retire** | permanent | reset to 0 | → retired |
-
- **learning**: card is actively in rotation
- **retired**: card won't appear in reviews (user has mastered it or manually retired it)
- Three consecutive "easy" ratings automatically retire a card
-
-### YouTube Quiz Generation
-
-When the user sends a YouTube URL and wants a quiz:
-
-**Step 1:** Extract the video ID from the URL (e.g. `dQw4w9WgXcQ` from `https://www.youtube.com/watch?v=dQw4w9WgXcQ`).
-
-**Step 2:** Fetch the transcript:
-
-```bash
-python3 ~/.hermes/skills/productivity/memento-flashcards/scripts/youtube_quiz.py fetch VIDEO_ID
-```
-
-This returns `{"title": "...", "transcript": "..."}` or an error.
-
-If the script reports `missing_dependency`, tell the user to install it:
-```bash
-pip install youtube-transcript-api
-```
-
-**Step 3:** Generate 5 quiz questions from the transcript. Use these rules:
-
-```
-You are creating a 5-question quiz for a podcast episode.
-Return ONLY a JSON array with exactly 5 objects.
-Each object must contain keys 'question' and 'answer'.
-
-Selection criteria:
- Prioritize important, surprising, or foundational facts.
- Skip filler, obvious details, and facts that require heavy context.
- Never return true/false questions.
- Never ask only for a date.
-
-Question rules:
- Each question must test exactly one discrete fact.
- Use clear, unambiguous wording.
- Prefer What, Who, How many, Which.
- Avoid open-ended Describe or Explain prompts.
-
-Answer rules:
- Each answer must be under 240 characters.
- Lead with the answer itself, not preamble.
- Add only minimal clarifying detail if needed.
-```
-
-Use the first 15,000 characters of the transcript as context. Generate the questions yourself (you are the LLM).
-
-**Step 4:** Validate the output is valid JSON with exactly 5 items, each having non-empty `question` and `answer` strings. If validation fails, retry once.
-
-**Step 5:** Store quiz cards:
-
-```bash
-python3 ~/.hermes/skills/productivity/memento-flashcards/scripts/memento_cards.py add-quiz \
-  --video-id "VIDEO_ID" \
-  --questions '[{"question":"...","answer":"..."},...]' \
-  --collection "Quiz - Episode Title"
-```
-
-The script deduplicates by `video_id` — if cards for that video already exist, it skips creation and reports the existing cards.
-
-**Step 6:** Present questions one-by-one using the same free-text grading flow:
-1. Show "Question 1/5: ..." and wait for the user's answer. Never include the answer or any hint about revealing it.
-2. Wait for the user to answer in their own words
-3. Grade their answer using the grading prompt (see "Reviewing Due Cards" section)
-4. **IMPORTANT: You MUST reply to the user with feedback before doing anything else.** Show the grade, the correct answer, and when the card is next due. Do NOT silently skip to the next question. Keep it short and plain-text. Example: "Not quite. Answer: {answer}. Next review tomorrow."
-5. **After showing feedback**, call the rate command and then show the next question in the same message:
-```bash
-python3 ~/.hermes/skills/productivity/memento-flashcards/scripts/memento_cards.py rate \
-  --id CARD_ID --rating easy --user-answer "what the user said"
-```
-6. Repeat. Every answer MUST receive visible feedback before the next question.
-
-### Export/Import CSV
-
-**Export:**
-```bash
-python3 ~/.hermes/skills/productivity/memento-flashcards/scripts/memento_cards.py export \
-  --output ~/flashcards.csv
-```
-
-Produces a 3-column CSV: `question,answer,collection` (no header row).
-
-**Import:**
-```bash
-python3 ~/.hermes/skills/productivity/memento-flashcards/scripts/memento_cards.py import \
-  --file ~/flashcards.csv \
-  --collection "Imported"
-```
-
-Reads a CSV with columns: question, answer, and optionally collection (column 3). If the collection column is missing, uses the `--collection` argument.
-
-### Statistics
-
-```bash
-python3 ~/.hermes/skills/productivity/memento-flashcards/scripts/memento_cards.py stats
-```
-
-Returns JSON with:
- `total`: total card count
- `learning`: cards in active rotation
- `retired`: mastered cards
- `due_now`: cards due for review right now
- `collections`: breakdown by collection name
-
-## Pitfalls
-
- **Never edit `cards.json` directly** — always use the script subcommands to avoid corruption
- **Transcript failures** — some YouTube videos have no English transcript or have transcripts disabled; inform the user and suggest another video
- **Optional dependency** — `youtube_quiz.py` needs `youtube-transcript-api`; if missing, tell the user to run `pip install youtube-transcript-api`
- **Large imports** — CSV imports with thousands of rows work fine but the JSON output may be verbose; summarize the result for the user
- **Video ID extraction** — support both `youtube.com/watch?v=ID` and `youtu.be/ID` URL formats
-
-## Verification
-
-Verify the helper scripts directly:
-
-```bash
-python3 ~/.hermes/skills/productivity/memento-flashcards/scripts/memento_cards.py stats
-python3 ~/.hermes/skills/productivity/memento-flashcards/scripts/memento_cards.py add --question "Capital of France?" --answer "Paris" --collection "General"
-python3 ~/.hermes/skills/productivity/memento-flashcards/scripts/memento_cards.py due
-```
-
-If you are testing from the repo checkout, run:
-
-```bash
-pytest tests/skills/test_memento_cards.py tests/skills/test_youtube_quiz.py -q
-```
-
-Agent-level verification:
- Start a review and confirm feedback is plain text, brief, and always includes the correct answer before the next card
- Run a YouTube quiz flow and confirm each answer receives visible feedback before the next question
@@ -1,353 +0,0 @@
-#!/usr/bin/env python3
-"""Memento card storage, spaced-repetition engine, and CSV I/O.
-
-Stdlib-only. All output is JSON for agent parsing.
-Data file: $HERMES_HOME/skills/productivity/memento-flashcards/data/cards.json
-"""
-
-import argparse
-import csv
-import json
-import os
-import sys
-import tempfile
-import uuid
-from datetime import datetime, timedelta, timezone
-from pathlib import Path
-
-_HERMES_HOME = Path(os.environ.get("HERMES_HOME", Path.home() / ".hermes"))
-DATA_DIR = _HERMES_HOME / "skills" / "productivity" / "memento-flashcards" / "data"
-CARDS_FILE = DATA_DIR / "cards.json"
-
-RETIRED_SENTINEL = "9999-12-31T23:59:59+00:00"
-
-
-def _now() -> datetime:
-    return datetime.now(timezone.utc)
-
-
-def _iso(dt: datetime) -> str:
-    return dt.isoformat()
-
-
-def _parse_iso(s: str) -> datetime:
-    return datetime.fromisoformat(s)
-
-
-def _empty_store() -> dict:
-    return {"cards": [], "version": 1}
-
-
-def _load() -> dict:
-    if not CARDS_FILE.exists():
-        return _empty_store()
-    try:
-        with open(CARDS_FILE, "r", encoding="utf-8") as f:
-            data = json.load(f)
-        if not isinstance(data, dict) or "cards" not in data:
-            return _empty_store()
-        return data
-    except (json.JSONDecodeError, OSError):
-        return _empty_store()
-
-
-def _save(data: dict) -> None:
-    DATA_DIR.mkdir(parents=True, exist_ok=True)
-    fd, tmp = tempfile.mkstemp(dir=DATA_DIR, suffix=".tmp")
-    try:
-        with os.fdopen(fd, "w", encoding="utf-8") as f:
-            json.dump(data, f, indent=2, ensure_ascii=False)
-            f.write("\n")
-        os.replace(tmp, CARDS_FILE)
-    except BaseException:
-        try:
-            os.unlink(tmp)
-        except OSError:
-            pass
-        raise
-
-
-def _out(obj: object) -> None:
-    json.dump(obj, sys.stdout, indent=2, ensure_ascii=False)
-    sys.stdout.write("\n")
-
-
-# ── Subcommands ──────────────────────────────────────────────────────────────
-
-def cmd_add(args: argparse.Namespace) -> None:
-    data = _load()
-    now = _now()
-    card = {
-        "id": str(uuid.uuid4()),
-        "question": args.question,
-        "answer": args.answer,
-        "collection": args.collection or "General",
-        "status": "learning",
-        "ease_streak": 0,
-        "next_review_at": _iso(now),
-        "created_at": _iso(now),
-        "video_id": None,
-        "last_user_answer": None,
-    }
-    data["cards"].append(card)
-    _save(data)
-    _out({"ok": True, "card": card})
-
-
-def cmd_add_quiz(args: argparse.Namespace) -> None:
-    data = _load()
-    now = _now()
-
-    try:
-        questions = json.loads(args.questions)
-    except json.JSONDecodeError as exc:
-        _out({"ok": False, "error": f"Invalid JSON for --questions: {exc}"})
-        sys.exit(1)
-
-    # Dedup: skip if cards with this video_id already exist
-    existing_ids = {c["video_id"] for c in data["cards"] if c.get("video_id")}
-    if args.video_id in existing_ids:
-        existing = [c for c in data["cards"] if c.get("video_id") == args.video_id]
-        _out({"ok": True, "skipped": True, "reason": "duplicate_video_id", "existing_count": len(existing), "cards": existing})
-        return
-
-    created = []
-    for qa in questions:
-        card = {
-            "id": str(uuid.uuid4()),
-            "question": qa["question"],
-            "answer": qa["answer"],
-            "collection": args.collection or "Quiz",
-            "status": "learning",
-            "ease_streak": 0,
-            "next_review_at": _iso(now),
-            "created_at": _iso(now),
-            "video_id": args.video_id,
-            "last_user_answer": None,
-        }
-        data["cards"].append(card)
-        created.append(card)
-
-    _save(data)
-    _out({"ok": True, "created_count": len(created), "cards": created})
-
-
-def cmd_due(args: argparse.Namespace) -> None:
-    data = _load()
-    now = _now()
-    due = []
-    for card in data["cards"]:
-        if card["status"] == "retired":
-            continue
-        review_at = _parse_iso(card["next_review_at"])
-        if review_at <= now:
-            if args.collection and card["collection"] != args.collection:
-                continue
-            due.append(card)
-    _out({"ok": True, "count": len(due), "cards": due})
-
-
-def cmd_rate(args: argparse.Namespace) -> None:
-    data = _load()
-    now = _now()
-    card = None
-    for c in data["cards"]:
-        if c["id"] == args.id:
-            card = c
-            break
-    if not card:
-        _out({"ok": False, "error": f"Card not found: {args.id}"})
-        sys.exit(1)
-
-    rating = args.rating
-    user_answer = getattr(args, "user_answer", None)
-    if user_answer is not None:
-        card["last_user_answer"] = user_answer
-
-    if rating == "retire":
-        card["status"] = "retired"
-        card["next_review_at"] = RETIRED_SENTINEL
-        card["ease_streak"] = 0
-    elif rating == "hard":
-        card["next_review_at"] = _iso(now + timedelta(days=1))
-        card["ease_streak"] = 0
-    elif rating == "good":
-        card["next_review_at"] = _iso(now + timedelta(days=3))
-        card["ease_streak"] = 0
-    elif rating == "easy":
-        card["next_review_at"] = _iso(now + timedelta(days=7))
-        card["ease_streak"] = card.get("ease_streak", 0) + 1
-        if card["ease_streak"] >= 3:
-            card["status"] = "retired"
-
-    _save(data)
-    _out({"ok": True, "card": card})
-
-
-def cmd_list(args: argparse.Namespace) -> None:
-    data = _load()
-    cards = data["cards"]
-    if args.collection:
-        cards = [c for c in cards if c["collection"] == args.collection]
-    if args.status:
-        cards = [c for c in cards if c["status"] == args.status]
-    _out({"ok": True, "count": len(cards), "cards": cards})
-
-
-def cmd_stats(args: argparse.Namespace) -> None:
-    data = _load()
-    now = _now()
-    total = len(data["cards"])
-    learning = sum(1 for c in data["cards"] if c["status"] == "learning")
-    retired = sum(1 for c in data["cards"] if c["status"] == "retired")
-    due_now = 0
-    for c in data["cards"]:
-        if c["status"] != "retired" and _parse_iso(c["next_review_at"]) <= now:
-            due_now += 1
-
-    collections: dict[str, int] = {}
-    for c in data["cards"]:
-        name = c["collection"]
-        collections[name] = collections.get(name, 0) + 1
-
-    _out({
-        "ok": True,
-        "total": total,
-        "learning": learning,
-        "retired": retired,
-        "due_now": due_now,
-        "collections": collections,
-    })
-
-
-def cmd_export(args: argparse.Namespace) -> None:
-    data = _load()
-    output_path = Path(args.output).expanduser()
-    with open(output_path, "w", newline="", encoding="utf-8") as f:
-        writer = csv.writer(f, lineterminator="\n")
-        for card in data["cards"]:
-            writer.writerow([card["question"], card["answer"], card["collection"]])
-    _out({"ok": True, "exported": len(data["cards"]), "path": str(output_path)})
-
-
-def cmd_import(args: argparse.Namespace) -> None:
-    data = _load()
-    now = _now()
-    file_path = Path(args.file).expanduser()
-
-    if not file_path.exists():
-        _out({"ok": False, "error": f"File not found: {file_path}"})
-        sys.exit(1)
-
-    created = 0
-    with open(file_path, "r", encoding="utf-8") as f:
-        reader = csv.reader(f)
-        for row in reader:
-            if len(row) < 2:
-                continue
-            question = row[0].strip()
-            answer = row[1].strip()
-            collection = row[2].strip() if len(row) >= 3 and row[2].strip() else (args.collection or "Imported")
-            if not question or not answer:
-                continue
-            card = {
-                "id": str(uuid.uuid4()),
-                "question": question,
-                "answer": answer,
-                "collection": collection,
-                "status": "learning",
-                "ease_streak": 0,
-                "next_review_at": _iso(now),
-                "created_at": _iso(now),
-                "video_id": None,
-                "last_user_answer": None,
-            }
-            data["cards"].append(card)
-            created += 1
-
-    _save(data)
-    _out({"ok": True, "imported": created})
-
-
-def cmd_delete(args: argparse.Namespace) -> None:
-    data = _load()
-    original = len(data["cards"])
-    data["cards"] = [c for c in data["cards"] if c["id"] != args.id]
-    removed = original - len(data["cards"])
-    if removed == 0:
-        _out({"ok": False, "error": f"Card not found: {args.id}"})
-        sys.exit(1)
-    _save(data)
-    _out({"ok": True, "deleted": args.id})
-
-
-def cmd_delete_collection(args: argparse.Namespace) -> None:
-    data = _load()
-    original = len(data["cards"])
-    data["cards"] = [c for c in data["cards"] if c["collection"] != args.collection]
-    removed = original - len(data["cards"])
-    _save(data)
-    _out({"ok": True, "deleted_count": removed, "collection": args.collection})
-
-
-# ── CLI ──────────────────────────────────────────────────────────────────────
-
-def main() -> None:
-    parser = argparse.ArgumentParser(description="Memento flashcard manager")
-    sub = parser.add_subparsers(dest="command", required=True)
-
-    p_add = sub.add_parser("add", help="Create one card")
-    p_add.add_argument("--question", required=True)
-    p_add.add_argument("--answer", required=True)
-    p_add.add_argument("--collection", default="General")
-
-    p_quiz = sub.add_parser("add-quiz", help="Batch-add quiz cards")
-    p_quiz.add_argument("--video-id", required=True)
-    p_quiz.add_argument("--questions", required=True, help="JSON array of {question, answer}")
-    p_quiz.add_argument("--collection", default="Quiz")
-
-    p_due = sub.add_parser("due", help="List due cards")
-    p_due.add_argument("--collection", default=None)
-
-    p_rate = sub.add_parser("rate", help="Rate a card")
-    p_rate.add_argument("--id", required=True)
-    p_rate.add_argument("--rating", required=True, choices=["easy", "good", "hard", "retire"])
-    p_rate.add_argument("--user-answer", default=None)
-
-    p_list = sub.add_parser("list", help="List cards")
-    p_list.add_argument("--collection", default=None)
-    p_list.add_argument("--status", default=None, choices=["learning", "retired"])
-
-    sub.add_parser("stats", help="Show statistics")
-
-    p_export = sub.add_parser("export", help="Export cards to CSV")
-    p_export.add_argument("--output", required=True)
-
-    p_import = sub.add_parser("import", help="Import cards from CSV")
-    p_import.add_argument("--file", required=True)
-    p_import.add_argument("--collection", default="Imported")
-
-    p_del = sub.add_parser("delete", help="Delete one card")
-    p_del.add_argument("--id", required=True)
-
-    p_delcol = sub.add_parser("delete-collection", help="Delete all cards in a collection")
-    p_delcol.add_argument("--collection", required=True)
-
-    args = parser.parse_args()
-    cmd_map = {
-        "add": cmd_add,
-        "add-quiz": cmd_add_quiz,
-        "due": cmd_due,
-        "rate": cmd_rate,
-        "list": cmd_list,
-        "stats": cmd_stats,
-        "export": cmd_export,
-        "import": cmd_import,
-        "delete": cmd_delete,
-        "delete-collection": cmd_delete_collection,
-    }
-    cmd_map[args.command](args)
-
-
-if __name__ == "__main__":
-    main()
--- a/Show More
+++ b/Show More
				`@@ -1 +0,0 @@`
				`"""Built-in gateway hooks that are always registered."""`
				`@@ -1 +0,0 @@`
				`Communication and decision-making frameworks — structured response formats for proposals, trade-off analysis, and stakeholder-ready recommendations.`