Install whatsapp bridge deps in container

Remove git submodules from container
apt -> apt-get
2026-03-29 14:30:09 +11:00 · 2026-03-29 14:29:29 +11:00 · 2026-03-29 13:55:18 +11:00 · 2026-03-29 13:55:18 +11:00 · 2026-03-29 13:55:18 +11:00 · 2026-03-29 13:55:18 +11:00
104 changed files with 3518 additions and 374 deletions
@@ -0,0 +1,13 @@
+# Git
+.git
+.gitignore
+.gitmodules
+
+# Dependencies
+node_modules
+
+# CI/CD
+.github
+
+# Environment files
+.env
@@ -74,6 +74,10 @@ HF_TOKEN=
 # 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=
@@ -0,0 +1,61 @@
+name: Docker Build and Publish
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+
+concurrency:
+  group: docker-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  build-and-push:
+    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'
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+
+      - name: Push image
+        if: github.event_name == 'push' && github.ref == 'refs/heads/main'
+        uses: docker/build-push-action@v6
+        with:
+          context: .
+          file: Dockerfile
+          push: true
+          tags: |
+            nousresearch/hermes-agent:latest
+            nousresearch/hermes-agent:${{ github.sha }}
+          cache-from: type=gha
+          cache-to: type=gha,mode=max
@@ -0,0 +1,20 @@
+FROM debian:13.4
+
+RUN apt-get update
+RUN apt-get install -y nodejs npm python3 python3-pip ripgrep ffmpeg gcc python3-dev libffi-dev
+
+COPY . /opt/hermes
+WORKDIR /opt/hermes
+
+RUN pip install -e ".[all]" --break-system-packages
+RUN npm install
+RUN npx playwright install --with-deps chromium
+WORKDIR /opt/hermes/scripts/whatsapp-bridge
+RUN npm install
+
+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" ]
@@ -0,0 +1,348 @@
+# 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)
@@ -1458,6 +1458,29 @@ 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,
@@ -1515,7 +1538,7 @@ def call_llm(
    temperature: float = None,
    max_tokens: int = None,
    tools: list = None,
-    timeout: float = 30.0,
+    timeout: float = None,
    extra_body: dict = None,
 ) -> Any:
    """Centralized synchronous LLM call.
@@ -1533,7 +1556,7 @@ 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.
+        timeout: Request timeout in seconds (None = read from auxiliary.{task}.timeout config).
        extra_body: Additional request body fields.

    Returns:
@@ -1598,10 +1621,12 @@ 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)
+
    kwargs = _build_call_kwargs(
        resolved_provider, final_model, messages,
        temperature=temperature, max_tokens=max_tokens,
-        tools=tools, timeout=timeout, extra_body=extra_body,
+        tools=tools, timeout=effective_timeout, extra_body=extra_body,
        base_url=resolved_base_url)

    # Handle max_tokens vs max_completion_tokens retry
@@ -1683,7 +1708,7 @@ async def async_call_llm(
    temperature: float = None,
    max_tokens: int = None,
    tools: list = None,
-    timeout: float = 30.0,
+    timeout: float = None,
    extra_body: dict = None,
 ) -> Any:
    """Centralized asynchronous LLM call.
@@ -1744,10 +1769,12 @@ 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=timeout, extra_body=extra_body,
+        tools=tools, timeout=effective_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": (self.last_prompt_tokens / self.context_length * 100) if self.context_length else 0,
+            "usage_percent": min(100, (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": 45.0,
+                # timeout resolved from auxiliary.compression.timeout config by call_llm
            }
            if self.summary_model:
                call_kwargs["model"] = self.summary_model
@@ -284,11 +284,11 @@ class KawaiiSpinner:
        The CLI already drives a TUI widget (_spinner_text) for spinner display,
        so KawaiiSpinner's \\r-based animation is redundant under StdoutProxy.
        """
-        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
+        try:
+            from prompt_toolkit.patch_stdout import StdoutProxy
+            return isinstance(self._out, StdoutProxy)
+        except ImportError:
+            return False

    def _animate(self):
        # When stdout is not a real terminal (e.g. Docker, systemd, pipe),
@@ -15,6 +15,8 @@ import time
 from pathlib import Path
 from typing import Any, Dict, Optional

+from utils import atomic_json_write
+
 import requests

 logger = logging.getLogger(__name__)
@@ -64,12 +66,10 @@ def _load_disk_cache() -> Dict[str, Any]:


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

@@ -19,7 +19,7 @@ _TITLE_PROMPT = (
 )


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

    Uses the auxiliary LLM client (cheapest/fastest available model).
@@ -7,6 +7,7 @@
 # =============================================================================
 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:
@@ -1078,7 +1078,7 @@ class HermesCLI:
        # authoritative.  This avoids conflicts in multi-agent setups where
        # env vars would stomp each other.
        _model_config = CLI_CONFIG.get("model", {})
-        _config_model = _model_config.get("default", "") if isinstance(_model_config, dict) else (_model_config or "")
+        _config_model = (_model_config.get("default") or _model_config.get("model") or "") if isinstance(_model_config, dict) else (_model_config or "")
        _FALLBACK_MODEL = "anthropic/claude-opus-4.6"
        self.model = model or _config_model or _FALLBACK_MODEL
        # Auto-detect model from local server if still on fallback
@@ -4034,6 +4034,17 @@ class HermesCLI:
                    provider_data_collection=self._provider_data_collection,
                    fallback_model=self._fallback_model,
                )
+                # Silence raw spinner; route thinking through TUI widget when no foreground agent is active.
+                bg_agent._print_fn = lambda *_a, **_kw: None
+
+                def _bg_thinking(text: str) -> None:
+                    # Concurrent bg tasks may race on _spinner_text; acceptable for best-effort UI.
+                    if not self._agent_running:
+                        self._spinner_text = text
+                        if self._app:
+                            self._app.invalidate()
+
+                bg_agent.thinking_callback = _bg_thinking

                result = bg_agent.run_conversation(
                    user_message=prompt,
@@ -4096,6 +4107,9 @@ class HermesCLI:
                _cprint(f"  ❌ Background task #{task_num} failed: {e}")
            finally:
                self._background_tasks.pop(task_id, None)
+                # Clear spinner only if no foreground agent owns it
+                if not self._agent_running:
+                    self._spinner_text = ""
                if self._app:
                    self._invalidate(min_interval=0)

@@ -4506,7 +4520,7 @@ class HermesCLI:
        compressor = agent.context_compressor
        last_prompt = compressor.last_prompt_tokens
        ctx_len = compressor.context_length
-        pct = (last_prompt / ctx_len * 100) if ctx_len else 0
+        pct = min(100, (last_prompt / ctx_len * 100)) if ctx_len else 0
        compressions = compressor.compression_count

        msg_count = len(self.conversation_history)
@@ -5534,6 +5548,13 @@ class HermesCLI:
            except Exception as e:
                logging.debug("@ context reference expansion failed: %s", e)

+        # Sanitize surrogate characters that can arrive via clipboard paste from
+        # rich-text editors (Google Docs, Word, etc.).  Lone surrogates are invalid
+        # UTF-8 and crash JSON serialization in the OpenAI SDK.
+        if isinstance(message, str):
+            from run_agent import _sanitize_surrogates
+            message = _sanitize_surrogates(message)
+
        # Add user message to history
        self.conversation_history.append({"role": "user", "content": message})

@@ -5891,10 +5912,22 @@ class HermesCLI:
            else:
                duration_str = f"{seconds}s"
            
+            # Look up session title for resume-by-name hint
+            session_title = None
+            if self._session_db:
+                try:
+                    session_title = self._session_db.get_session_title(self.session_id)
+                except Exception:
+                    pass
+
            print("Resume this session with:")
            print(f"  hermes --resume {self.session_id}")
+            if session_title:
+                print(f"  hermes -c \"{session_title}\"")
            print()
            print(f"Session:        {self.session_id}")
+            if session_title:
+                print(f"Title:          {session_title}")
            print(f"Duration:       {duration_str}")
            print(f"Messages:       {msg_count} ({user_msgs} user, {tool_calls} tool calls)")
        else:
@@ -6070,7 +6103,7 @@ class HermesCLI:
            from honcho_integration.client import HonchoClientConfig
            from agent.display import honcho_session_line, write_tty
            hcfg = HonchoClientConfig.from_global_config()
-            if hcfg.enabled and hcfg.api_key and hcfg.explicitly_configured:
+            if hcfg.enabled and (hcfg.api_key or hcfg.base_url) and hcfg.explicitly_configured:
                sname = hcfg.resolve_session_name(session_id=self.session_id)
                if sname:
                    write_tty(honcho_session_line(hcfg.workspace_id, sname) + "\n")
@@ -6644,6 +6677,7 @@ class HermesCLI:
        # Paste collapsing: detect large pastes and save to temp file
        _paste_counter = [0]
        _prev_text_len = [0]
+        _prev_newline_count = [0]
        _paste_just_collapsed = [False]

        def _on_text_changed(buf):
@@ -6652,18 +6686,27 @@ class HermesCLI:
            When bracketed paste is available, handle_paste collapses
            large pastes directly.  This handler is a fallback for
            terminals without bracketed paste support.
+
+            Two heuristics (either triggers collapse):
+            1. Many characters added at once (chars_added > 1) — works
+               when the terminal delivers the paste in one event-loop tick.
+            2. Newline count jumped by 4+ in a single text-change event —
+               catches terminals that feed characters individually but
+               still batch newlines.  Alt+Enter only adds 1 newline per
+               event so it never triggers this.
            """
            text = buf.text
            chars_added = len(text) - _prev_text_len[0]
            _prev_text_len[0] = len(text)
            if _paste_just_collapsed[0]:
                _paste_just_collapsed[0] = False
+                _prev_newline_count[0] = text.count('\n')
                return
            line_count = text.count('\n')
-            # Heuristic: a real paste adds many characters at once (not just a
-            # single newline from Alt+Enter) AND the result has 5+ lines.
-            # Fallback for terminals without bracketed paste support.
-            if line_count >= 5 and chars_added > 1 and not text.startswith('/'):
+            newlines_added = line_count - _prev_newline_count[0]
+            _prev_newline_count[0] = line_count
+            is_paste = chars_added > 1 or newlines_added >= 4
+            if line_count >= 5 and is_paste and not text.startswith('/'):
                _paste_counter[0] += 1
                # Save to temp file
                paste_dir = _hermes_home / "pastes"
@@ -6671,6 +6714,7 @@ class HermesCLI:
                paste_file = paste_dir / f"paste_{_paste_counter[0]}_{datetime.now().strftime('%H%M%S')}.txt"
                paste_file.write_text(text, encoding="utf-8")
                # Replace buffer with compact reference
+                _paste_just_collapsed[0] = True
                buf.text = f"[Pasted text #{_paste_counter[0]}: {line_count + 1} lines \u2192 {paste_file}]"
                buf.cursor_position = len(buf.text)

@@ -0,0 +1,15 @@
+# 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.
+-->
@@ -0,0 +1,31 @@
+#!/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 directory structure
+mkdir -p "$HERMES_HOME"/{cron,sessions,logs,pairing,hooks,image_cache,audio_cache,memories,skills,whatsapp/session}
+
+# .env
+if [ ! -f "$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 "$@"
@@ -0,0 +1,56 @@
+# Hermes Agent — Docker
+
+Want to run Hermes Agent, but without installing packages on your host? This'll sort you out.
+
+This will let you run the agent in a container, with the most relevant modes outlined below.
+
+The container stores all user data (config, API keys, sessions, skills, memories) in a single directory mounted from the host at `/opt/data`. The image itself is stateless and can be upgraded by pulling a new version without losing any configuration.
+
+## Quick start
+
+If this is your first time running Hermes Agent, create a data directory on the host and start the container interactively to run the setup wizard:
+
+```sh
+mkdir -p ~/.hermes
+docker run -it --rm \
+  -v ~/.hermes:/opt/data \
+  nousresearch/hermes-agent
+```
+
+This drops you into the setup wizard, which will prompt you for your API keys and write them to `~/.hermes/.env`. You only need to do this once. It is highly recommended to set up a chat system for the gateway to work with at this point.
+
+## Running in gateway mode
+
+Once configured, run the container in the background as a persistent gateway (Telegram, Discord, Slack, WhatsApp, etc.):
+
+```sh
+docker run -d \
+  --name hermes \
+  --restart unless-stopped \
+  -v ~/.hermes:/opt/data \
+  nousresearch/hermes-agent gateway run
+```
+
+## Running interactively (CLI chat)
+
+To open an interactive chat session against a running data directory:
+
+```sh
+docker run -it --rm \
+  -v ~/.hermes:/opt/data \
+  nousresearch/hermes-agent
+```
+
+## Upgrading
+
+Pull the latest image and recreate the container. Your data directory is untouched.
+
+```sh
+docker pull nousresearch/hermes-agent:latest
+docker rm -f hermes
+docker run -d \
+  --name hermes \
+  --restart unless-stopped \
+  -v ~/.hermes:/opt/data \
+  nousresearch/hermes-agent
+```
@@ -25,7 +25,7 @@ import time
 from pathlib import Path
 from typing import Optional

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


 # 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_home() / "pairing"
+PAIRING_DIR = get_hermes_dir("platforms/pairing", "pairing")


 def _secure_write(path: Path, data: str) -> None:
@@ -223,6 +223,23 @@ 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."""
@@ -307,6 +324,7 @@ 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:
@@ -315,6 +333,7 @@ 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:
@@ -582,10 +601,14 @@ class APIServerAdapter(BasePlatformAdapter):
        """
        import queue as _q

-        response = web.StreamResponse(
-            status=200,
-            headers={"Content-Type": "text/event-stream", "Cache-Control": "no-cache"},
-        )
+        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)
        await response.prepare(request)

        try:
@@ -1218,10 +1241,11 @@ class APIServerAdapter(BasePlatformAdapter):
            return False

        try:
-            mws = [mw for mw in (cors_middleware, body_limit_middleware) if mw is not None]
+            mws = [mw for mw in (cors_middleware, body_limit_middleware, security_headers_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)
@@ -27,6 +27,7 @@ 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 = (
@@ -44,8 +45,8 @@ GATEWAY_SECRET_CAPTURE_UNSUPPORTED_MESSAGE = (
 # (e.g. Telegram file URLs expire after ~1 hour).
 # ---------------------------------------------------------------------------

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


 def get_image_cache_dir() -> Path:
@@ -147,7 +148,7 @@ 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_home() / "audio_cache"
+AUDIO_CACHE_DIR = get_hermes_dir("cache/audio", "audio_cache")


 def get_audio_cache_dir() -> Path:
@@ -174,29 +175,51 @@ 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") -> str:
+async def cache_audio_from_url(url: str, ext: str = ".ogg", retries: int = 2) -> 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:
-        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)
+        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


 # ---------------------------------------------------------------------------
@@ -206,7 +229,7 @@ async def cache_audio_from_url(url: str, ext: str = ".ogg") -> str:
 # here so the agent can reference them by local file path.
 # ---------------------------------------------------------------------------

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

 SUPPORTED_DOCUMENT_TYPES = {
    ".pdf": "application/pdf",
@@ -333,7 +356,10 @@ class MessageEvent:
            return None
        # Split on space and get first word, strip the /
        parts = self.text.split(maxsplit=1)
-        return parts[0][1:].lower() if parts else None
+        raw = parts[0][1:].lower() if parts else None
+        if raw and "@" in raw:
+            raw = raw.split("@", 1)[0]
+        return raw
    
    def get_command_args(self) -> str:
        """Get the arguments after a command."""
@@ -550,6 +550,22 @@ class DiscordAdapter(BasePlatformAdapter):
                            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
@@ -43,6 +43,20 @@ 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
@@ -50,7 +64,17 @@ 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")
@@ -346,6 +370,11 @@ class EmailAdapter(BasePlatformAdapter):
                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)

@@ -374,6 +403,11 @@ 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"]
@@ -40,7 +40,9 @@ logger = logging.getLogger(__name__)
 MAX_MESSAGE_LENGTH = 4000

 # Store directory for E2EE keys and sync state.
-_STORE_DIR = Path.home() / ".hermes" / "matrix" / "store"
+# 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")

 # Grace period: ignore messages older than this many seconds before startup.
 _STARTUP_GRACE_SECONDS = 5
@@ -345,7 +345,8 @@ 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:
-            config_path = _Path.home() / ".hermes" / "config.yaml"
+            from hermes_constants import get_hermes_home
+            config_path = get_hermes_home() / "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
@@ -1757,7 +1758,8 @@ class TelegramAdapter(BasePlatformAdapter):
        recognized without a gateway restart.
        """
        try:
-            config_path = _Path.home() / ".hermes" / "config.yaml"
+            from hermes_constants import get_hermes_home
+            config_path = get_hermes_home() / "config.yaml"
            if not config_path.exists():
                return

@@ -12,6 +12,7 @@ from __future__ import annotations
 import asyncio
 import ipaddress
 import logging
+import os
 import socket
 from typing import Iterable, Optional

@@ -43,6 +44,14 @@ _DOH_PROVIDERS: list[dict] = [
 _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.

@@ -54,6 +63,9 @@ class TelegramFallbackTransport(httpx.AsyncBaseTransport):

    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
@@ -27,6 +27,7 @@ import hashlib
 import hmac
 import json
 import logging
+import os
 import re
 import subprocess
 import time
@@ -53,6 +54,7 @@ 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:
@@ -68,7 +70,10 @@ 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._routes: Dict[str, dict] = config.extra.get("routes", {})
+        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._runner = None

        # Delivery info keyed by session chat_id — consumed by send()
@@ -96,6 +101,9 @@ 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)
@@ -182,8 +190,46 @@ 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)

@@ -26,6 +26,7 @@ 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__)

@@ -134,7 +135,7 @@ class WhatsAppAdapter(BasePlatformAdapter):
        )
        self._session_path: Path = Path(config.extra.get(
            "session_path",
-            get_hermes_home() / "whatsapp" / "session"
+            get_hermes_dir("platforms/whatsapp/session", "whatsapp/session")
        ))
        self._reply_prefix: Optional[str] = config.extra.get("reply_prefix")
        self._message_queue: asyncio.Queue = asyncio.Queue()
@@ -526,6 +527,7 @@ 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)
@@ -536,6 +538,7 @@ 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)
@@ -547,6 +550,7 @@ 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(
@@ -288,7 +288,7 @@ def _resolve_gateway_model(config: dict | None = None) -> str:
    if isinstance(model_cfg, str):
        model = model_cfg
    elif isinstance(model_cfg, dict):
-        model = model_cfg.get("default", model)
+        model = model_cfg.get("default") or model_cfg.get("model") or model
    return model


@@ -432,7 +432,7 @@ class GatewayRunner:
            from honcho_integration.session import HonchoSessionManager

            hcfg = HonchoClientConfig.from_global_config()
-            if not hcfg.enabled or not hcfg.api_key:
+            if not hcfg.enabled or not (hcfg.api_key or hcfg.base_url):
                return None, hcfg

            client = get_honcho_client(hcfg)
@@ -745,10 +745,22 @@ class GatewayRunner:
                logger.error("No connected messaging platforms remain. Shutting down gateway cleanly.")
            await self.stop()
        elif not self.adapters and self._failed_platforms:
-            logger.warning(
-                "No connected messaging platforms remain, but %d platform(s) queued for reconnection",
-                len(self._failed_platforms),
-            )
+            # All platforms are down and queued for background reconnection.
+            # If the error is retryable, exit with failure so systemd Restart=on-failure
+            # can restart the process. Otherwise stay alive and keep retrying in background.
+            if adapter.fatal_error_retryable:
+                self._exit_reason = adapter.fatal_error_message or "All messaging platforms failed with retryable errors"
+                self._exit_with_failure = True
+                logger.error(
+                    "All messaging platforms failed with retryable errors. "
+                    "Shutting down gateway for service restart (systemd will retry)."
+                )
+                await self.stop()
+            else:
+                logger.warning(
+                    "No connected messaging platforms remain, but %d platform(s) queued for reconnection",
+                    len(self._failed_platforms),
+                )

    def _request_clean_exit(self, reason: str) -> None:
        self._exit_cleanly = True
@@ -2081,7 +2093,7 @@ class GatewayRunner:
                    if isinstance(_model_cfg, str):
                        _hyg_model = _model_cfg
                    elif isinstance(_model_cfg, dict):
-                        _hyg_model = _model_cfg.get("default", _hyg_model)
+                        _hyg_model = _model_cfg.get("default") or _model_cfg.get("model") or _hyg_model
                        # Read explicit context_length override from model config
                        # (same as run_agent.py lines 995-1005)
                        _raw_ctx = _model_cfg.get("context_length")
@@ -4178,7 +4190,7 @@ class GatewayRunner:
            ]
            ctx = agent.context_compressor
            if ctx.last_prompt_tokens:
-                pct = ctx.last_prompt_tokens / ctx.context_length * 100 if ctx.context_length else 0
+                pct = min(100, ctx.last_prompt_tokens / ctx.context_length * 100) if ctx.context_length else 0
                lines.append(f"Context: {ctx.last_prompt_tokens:,} / {ctx.context_length:,} ({pct:.0f}%)")
            if ctx.compression_count:
                lines.append(f"Compressions: {ctx.compression_count}")
@@ -11,5 +11,5 @@ Provides subcommands for:
 - hermes cron          - Manage cron jobs
 """

-__version__ = "0.4.0"
-__release_date__ = "2026.3.23"
+__version__ = "0.5.0"
+__release_date__ = "2026.3.28"
@@ -227,42 +227,49 @@ DEFAULT_CONFIG = {
            "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,
        },
    },
    
@@ -616,6 +623,14 @@ OPTIONAL_ENV_VARS = {
    },

    # ── 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",
@@ -1672,6 +1687,7 @@ 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"),
@@ -1831,7 +1847,7 @@ 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',
-        'PARALLEL_API_KEY', 'FIRECRAWL_API_KEY', 'FIRECRAWL_API_URL', 'TAVILY_API_KEY',
+        'EXA_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',
@@ -56,7 +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)
+        return bool(cfg.enabled and (cfg.api_key or cfg.base_url))
    except Exception:
        return False

@@ -708,8 +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:
-            check_fail("Honcho API key not set", "run: hermes honcho setup")
+        elif not (hcfg.api_key or hcfg.base_url):
+            check_fail("Honcho API key or base URL 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
@@ -125,20 +125,43 @@ _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).
-    Any other HERMES_HOME appends a short hash so multiple installations
-    can each have their own systemd service without conflicting.
+    Profile ``~/.hermes/profiles/coder`` returns ``hermes-gateway-coder``.
+    Any other HERMES_HOME appends a short hash for uniqueness.
    """
-    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:
+    suffix = _profile_suffix()
+    if not suffix:
        return _SERVICE_BASE
-    suffix = hashlib.sha256(str(home).encode()).hexdigest()[:8]
    return f"{_SERVICE_BASE}-{suffix}"


@@ -369,7 +392,14 @@ def print_systemd_linger_guidance() -> None:
        print("  sudo loginctl enable-linger $USER")

 def get_launchd_plist_path() -> Path:
-    return Path.home() / "Library" / "LaunchAgents" / "ai.hermes.gateway.plist"
+    """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"

 def _detect_venv_dir() -> Path | None:
    """Detect the active virtualenv directory.
@@ -769,18 +799,46 @@ 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>ai.hermes.gateway</string>
+    <string>{label}</string>
    
    <key>ProgramArguments</key>
    <array>
@@ -795,6 +853,16 @@ 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/>
    
@@ -880,20 +948,33 @@ def launchd_uninstall():
    print("✓ Service uninstalled")

 def launchd_start():
-    refresh_launchd_plist_if_needed()
    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()
    try:
-        subprocess.run(["launchctl", "start", "ai.hermes.gateway"], check=True)
+        subprocess.run(["launchctl", "start", label], check=True)
    except subprocess.CalledProcessError as e:
-        if e.returncode != 3 or not plist_path.exists():
+        if e.returncode != 3:
            raise
        print("↻ launchd job was unloaded; reloading service definition")
        subprocess.run(["launchctl", "load", str(plist_path)], check=True)
-        subprocess.run(["launchctl", "start", "ai.hermes.gateway"], check=True)
+        subprocess.run(["launchctl", "start", label], check=True)
    print("✓ Service started")

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

 def _wait_for_gateway_exit(timeout: float = 10.0, force_after: float = 5.0):
@@ -948,8 +1029,9 @@ def launchd_restart():

 def launchd_status(deep: bool = False):
    plist_path = get_launchd_plist_path()
+    label = get_launchd_label()
    result = subprocess.run(
-        ["launchctl", "list", "ai.hermes.gateway"],
+        ["launchctl", "list", label],
        capture_output=True,
        text=True
    )
@@ -1454,7 +1536,7 @@ def _is_service_running() -> bool:
        return False
    elif is_macos() and get_launchd_plist_path().exists():
        result = subprocess.run(
-            ["launchctl", "list", "ai.hermes.gateway"],
+            ["launchctl", "list", get_launchd_label()],
            capture_output=True, text=True
        )
        return result.returncode == 0
@@ -2339,6 +2339,12 @@ def cmd_cron(args):
    cron_command(args)


+def cmd_webhook(args):
+    """Webhook subscription management."""
+    from hermes_cli.webhook import webhook_command
+    webhook_command(args)
+
+
 def cmd_doctor(args):
    """Check configuration and dependencies."""
    from hermes_cli.doctor import run_doctor
@@ -2470,8 +2476,18 @@ def _update_via_zip(args):
            )
    else:
        # Use sys.executable to explicitly call the venv's pip module,
-        # avoiding PEP 668 'externally-managed-environment' errors on Debian/Ubuntu
+        # avoiding PEP 668 'externally-managed-environment' errors on Debian/Ubuntu.
+        # Some environments lose pip inside the venv; bootstrap it back with
+        # ensurepip before trying the editable install.
        pip_cmd = [sys.executable, "-m", "pip"]
+        try:
+            subprocess.run(pip_cmd + ["--version"], cwd=PROJECT_ROOT, check=True, capture_output=True)
+        except subprocess.CalledProcessError:
+            subprocess.run(
+                [sys.executable, "-m", "ensurepip", "--upgrade", "--default-pip"],
+                cwd=PROJECT_ROOT,
+                check=True,
+            )
        try:
            subprocess.run(pip_cmd + ["install", "-e", ".[all]", "--quiet"], cwd=PROJECT_ROOT, check=True)
        except subprocess.CalledProcessError:
@@ -2857,8 +2873,18 @@ def cmd_update(args):
                )
        else:
            # Use sys.executable to explicitly call the venv's pip module,
-            # avoiding PEP 668 'externally-managed-environment' errors on Debian/Ubuntu
+            # avoiding PEP 668 'externally-managed-environment' errors on Debian/Ubuntu.
+            # Some environments lose pip inside the venv; bootstrap it back with
+            # ensurepip before trying the editable install.
            pip_cmd = [sys.executable, "-m", "pip"]
+            try:
+                subprocess.run(pip_cmd + ["--version"], cwd=PROJECT_ROOT, check=True, capture_output=True)
+            except subprocess.CalledProcessError:
+                subprocess.run(
+                    [sys.executable, "-m", "ensurepip", "--upgrade", "--default-pip"],
+                    cwd=PROJECT_ROOT,
+                    check=True,
+                )
            try:
                subprocess.run(pip_cmd + ["install", "-e", ".[all]", "--quiet"], cwd=PROJECT_ROOT, check=True)
            except subprocess.CalledProcessError:
@@ -2917,10 +2943,15 @@ def cmd_update(args):
                print(f"  ℹ️  {len(missing_config)} new config option(s) available")
            
            print()
-            if sys.stdin.isatty():
-                response = input("Would you like to configure them now? [Y/n]: ").strip().lower()
-            else:
+            if not (sys.stdin.isatty() and sys.stdout.isatty()):
+                print("  ℹ Non-interactive session — skipping config migration prompt.")
+                print("    Run 'hermes config migrate' later to apply any new config/env options.")
                response = "n"
+            else:
+                try:
+                    response = input("Would you like to configure them now? [Y/n]: ").strip().lower()
+                except EOFError:
+                    response = "n"
            
            if response in ('', 'y', 'yes'):
                print()
@@ -2968,10 +2999,11 @@ def cmd_update(args):
            # Check for macOS launchd service
            if is_macos():
                try:
+                    from hermes_cli.gateway import get_launchd_label
                    plist_path = get_launchd_plist_path()
                    if plist_path.exists():
                        check = subprocess.run(
-                            ["launchctl", "list", "ai.hermes.gateway"],
+                            ["launchctl", "list", get_launchd_label()],
                            capture_output=True, text=True, timeout=5,
                        )
                        has_launchd_service = check.returncode == 0
@@ -3027,12 +3059,13 @@ def cmd_update(args):
                    # after a manual SIGTERM, which would race with the
                    # PID file cleanup.
                    print("→ Restarting gateway service...")
+                    _launchd_label = get_launchd_label()
                    stop = subprocess.run(
-                        ["launchctl", "stop", "ai.hermes.gateway"],
+                        ["launchctl", "stop", _launchd_label],
                        capture_output=True, text=True, timeout=10,
                    )
                    start = subprocess.run(
-                        ["launchctl", "start", "ai.hermes.gateway"],
+                        ["launchctl", "start", _launchd_label],
                        capture_output=True, text=True, timeout=10,
                    )
                    if start.returncode == 0:
@@ -3516,7 +3549,38 @@ For more help on a command:
    cron_subparsers.add_parser("tick", help="Run due jobs once and exit")

    cron_parser.set_defaults(func=cmd_cron)
-    
+
+    # =========================================================================
+    # webhook command
+    # =========================================================================
+    webhook_parser = subparsers.add_parser(
+        "webhook",
+        help="Manage dynamic webhook subscriptions",
+        description="Create, list, and remove webhook subscriptions for event-driven agent activation",
+    )
+    webhook_subparsers = webhook_parser.add_subparsers(dest="webhook_action")
+
+    wh_sub = webhook_subparsers.add_parser("subscribe", aliases=["add"], help="Create a webhook subscription")
+    wh_sub.add_argument("name", help="Route name (used in URL: /webhooks/<name>)")
+    wh_sub.add_argument("--prompt", default="", help="Prompt template with {dot.notation} payload refs")
+    wh_sub.add_argument("--events", default="", help="Comma-separated event types to accept")
+    wh_sub.add_argument("--description", default="", help="What this subscription does")
+    wh_sub.add_argument("--skills", default="", help="Comma-separated skill names to load")
+    wh_sub.add_argument("--deliver", default="log", help="Delivery target: log, telegram, discord, slack, etc.")
+    wh_sub.add_argument("--deliver-chat-id", default="", help="Target chat ID for cross-platform delivery")
+    wh_sub.add_argument("--secret", default="", help="HMAC secret (auto-generated if omitted)")
+
+    webhook_subparsers.add_parser("list", aliases=["ls"], help="List all dynamic subscriptions")
+
+    wh_rm = webhook_subparsers.add_parser("remove", aliases=["rm"], help="Remove a subscription")
+    wh_rm.add_argument("name", help="Subscription name to remove")
+
+    wh_test = webhook_subparsers.add_parser("test", help="Send a test POST to a webhook route")
+    wh_test.add_argument("name", help="Subscription name to test")
+    wh_test.add_argument("--payload", default="", help="JSON payload to send (default: test payload)")
+
+    webhook_parser.set_defaults(func=cmd_webhook)
+
    # =========================================================================
    # doctor command
    # =========================================================================
@@ -3649,7 +3713,7 @@ For more help on a command:
    skills_snapshot = skills_subparsers.add_parser("snapshot", help="Export/import skill configurations")
    snapshot_subparsers = skills_snapshot.add_subparsers(dest="snapshot_action")
    snap_export = snapshot_subparsers.add_parser("export", help="Export installed skills to a file")
-    snap_export.add_argument("output", help="Output JSON file path")
+    snap_export.add_argument("output", help="Output JSON file path (use - for stdout)")
    snap_import = snapshot_subparsers.add_parser("import", help="Import and install skills from a file")
    snap_import.add_argument("input", help="Input JSON file path")
    snap_import.add_argument("--force", action="store_true", help="Force install despite caution verdict")
@@ -3926,7 +3990,7 @@ For more help on a command:
    sessions_list.add_argument("--limit", type=int, default=20, help="Max sessions to show")

    sessions_export = sessions_subparsers.add_parser("export", help="Export sessions to a JSONL file")
-    sessions_export.add_argument("output", help="Output JSONL file path")
+    sessions_export.add_argument("output", help="Output JSONL file path (use - for stdout)")
    sessions_export.add_argument("--source", help="Filter by source")
    sessions_export.add_argument("--session-id", help="Export a specific session")

@@ -4007,15 +4071,25 @@ For more help on a command:
                if not data:
                    print(f"Session '{args.session_id}' not found.")
                    return
-                with open(args.output, "w", encoding="utf-8") as f:
-                    f.write(_json.dumps(data, ensure_ascii=False) + "\n")
-                print(f"Exported 1 session to {args.output}")
+                line = _json.dumps(data, ensure_ascii=False) + "\n"
+                if args.output == "-":
+                    import sys
+                    sys.stdout.write(line)
+                else:
+                    with open(args.output, "w", encoding="utf-8") as f:
+                        f.write(line)
+                    print(f"Exported 1 session to {args.output}")
            else:
                sessions = db.export_all(source=args.source)
-                with open(args.output, "w", encoding="utf-8") as f:
+                if args.output == "-":
+                    import sys
                    for s in sessions:
-                        f.write(_json.dumps(s, ensure_ascii=False) + "\n")
-                print(f"Exported {len(sessions)} sessions to {args.output}")
+                        sys.stdout.write(_json.dumps(s, ensure_ascii=False) + "\n")
+                else:
+                    with open(args.output, "w", encoding="utf-8") as f:
+                        for s in sessions:
+                            f.write(_json.dumps(s, ensure_ascii=False) + "\n")
+                    print(f"Exported {len(sessions)} sessions to {args.output}")

        elif action == "delete":
            resolved_session_id = db.resolve_session_id(args.session_id)
@@ -63,6 +63,9 @@ 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()
        is_local = "localhost" in base_url or "127.0.0.1" in base_url
@@ -203,7 +206,7 @@ def _resolve_named_custom_runtime(
        or _detect_api_mode_for_url(base_url)
        or "chat_completions",
        "base_url": base_url,
-        "api_key": api_key,
+        "api_key": api_key or "no-key-required",
        "source": f"custom_provider:{custom_provider.get('name', requested_provider)}",
    }

@@ -585,11 +585,11 @@ def _print_setup_summary(config: dict, hermes_home):
    else:
        tool_status.append(("Mixture of Agents", False, "OPENROUTER_API_KEY"))

-    # Web tools (Parallel, Firecrawl, or Tavily)
-    if get_env_value("PARALLEL_API_KEY") or get_env_value("FIRECRAWL_API_KEY") or get_env_value("FIRECRAWL_API_URL") or get_env_value("TAVILY_API_KEY"):
+    # Web tools (Exa, Parallel, Firecrawl, or Tavily)
+    if get_env_value("EXA_API_KEY") or get_env_value("PARALLEL_API_KEY") or get_env_value("FIRECRAWL_API_KEY") or get_env_value("FIRECRAWL_API_URL") or get_env_value("TAVILY_API_KEY"):
        tool_status.append(("Web Search & Extract", True, None))
    else:
-        tool_status.append(("Web Search & Extract", False, "PARALLEL_API_KEY, FIRECRAWL_API_KEY, or TAVILY_API_KEY"))
+        tool_status.append(("Web Search & Extract", False, "EXA_API_KEY, PARALLEL_API_KEY, FIRECRAWL_API_KEY, or TAVILY_API_KEY"))

    # Browser tools (local Chromium or Browserbase cloud)
    import shutil
@@ -24,6 +24,10 @@ PLATFORMS = {
    "whatsapp": "📱 WhatsApp",
    "signal":   "📡 Signal",
    "email":    "📧 Email",
+    "homeassistant": "🏠 Home Assistant",
+    "mattermost": "💬 Mattermost",
+    "matrix":   "💬 Matrix",
+    "dingtalk": "💬 DingTalk",
 }

 # ─── Config Helpers ───────────────────────────────────────────────────────────
@@ -304,7 +304,8 @@ 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) -> None:
+               console: Optional[Console] = None, skip_confirm: bool = False,
+               invalidate_cache: bool = True) -> None:
    """Fetch, quarantine, scan, confirm, and install a skill."""
    from tools.skills_hub import (
        GitHubAuth, create_source_router, ensure_hub_dirs,
@@ -417,12 +418,16 @@ def do_install(identifier: str, category: str = "", force: bool = False,
    c.print(f"[bold green]Installed:[/] {install_dir.relative_to(SKILLS_DIR)}")
    c.print(f"[dim]Files: {', '.join(bundle.files.keys())}[/]\n")

-    # 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
+    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:
@@ -610,7 +615,8 @@ 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) -> None:
+                 skip_confirm: bool = False,
+                 invalidate_cache: bool = True) -> None:
    """Remove a hub-installed skill with confirmation."""
    from tools.skills_hub import uninstall_skill

@@ -630,11 +636,15 @@ def do_uninstall(name: str, console: Optional[Console] = None,
    success, msg = uninstall_skill(name)
    if success:
        c.print(f"[bold green]{msg}[/]\n")
-        try:
-            from agent.prompt_builder import clear_skills_system_prompt_cache
-            clear_skills_system_prompt_cache(clear_snapshot=True)
-        except Exception:
-            pass
+        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")

@@ -877,10 +887,15 @@ def do_snapshot_export(output_path: str, console: Optional[Console] = None) -> N
        "taps": tap_list,
    }

-    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")
+    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")


 def do_snapshot_import(input_path: str, force: bool = False,
@@ -1071,19 +1086,23 @@ 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|--yes]\n")
+            c.print("[bold red]Usage:[/] /skills install <identifier> [--category <cat>] [--force] [--now]\n")
            return
        identifier = args[0]
        category = ""
-        # --yes / -y bypasses confirmation prompt (needed in TUI mode)
-        # --force handles reinstall override
-        skip_confirm = any(flag in args for flag in ("--yes", "-y"))
+        # Slash commands run inside prompt_toolkit where input() hangs.
+        # Always skip confirmation — the user typing the command is implicit consent.
+        skip_confirm = True
        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, console=c)
+                   skip_confirm=skip_confirm, invalidate_cache=invalidate_cache,
+                   console=c)

    elif action == "inspect":
        if not args:
@@ -1113,10 +1132,13 @@ 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> [--yes]\n")
+            c.print("[bold red]Usage:[/] /skills uninstall <name> [--now]\n")
            return
-        skip_confirm = any(flag in args for flag in ("--yes", "-y"))
-        do_uninstall(args[0], console=c, skip_confirm=skip_confirm)
+        # 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)

    elif action == "publish":
        if not args:
@@ -292,8 +292,9 @@ def show_status(args):
        print("  Manager:      systemd (user)")
        
    elif sys.platform == 'darwin':
+        from hermes_cli.gateway import get_launchd_label
        result = subprocess.run(
-            ["launchctl", "list", "ai.hermes.gateway"],
+            ["launchctl", "list", get_launchd_label()],
            capture_output=True,
            text=True
        )
@@ -138,6 +138,7 @@ PLATFORMS = {
    "matrix":   {"label": "💬 Matrix",     "default_toolset": "hermes-matrix"},
    "dingtalk": {"label": "💬 DingTalk",   "default_toolset": "hermes-dingtalk"},
    "api_server": {"label": "🌐 API Server", "default_toolset": "hermes-api-server"},
+    "mattermost": {"label": "💬 Mattermost", "default_toolset": "hermes-mattermost"},
 }


@@ -189,6 +190,14 @@ 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",
@@ -0,0 +1,256 @@
+"""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
+
+
+_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}"
+
+
+_SETUP_HINT = """
+  Webhook platform is not enabled. To set it up:
+
+  1. Run the gateway setup wizard:
+     hermes gateway setup
+
+  2. Or manually add to ~/.hermes/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 ~/.hermes/.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)")
@@ -17,6 +17,27 @@ def get_hermes_home() -> Path:
    return Path(os.getenv("HERMES_HOME", Path.home() / ".hermes"))


+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
+
+
 VALID_REASONING_EFFORTS = ("xhigh", "high", "medium", "low", "minimal")


@@ -270,7 +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:
+    if hcfg.enabled and (hcfg.api_key or hcfg.base_url):
        print("\n  Connection... ", end="", flush=True)
        try:
            get_honcho_client(hcfg)
@@ -278,7 +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"
+        reason = "disabled" if not hcfg.enabled else "no API key or base URL"
        print(f"\n  Not connected ({reason})\n")


@@ -417,9 +417,18 @@ 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": config.api_key,
+        "api_key": effective_api_key,
        "environment": config.environment,
    }
    if resolved_base_url:
@@ -111,6 +111,7 @@
      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
@@ -551,8 +552,8 @@
      # ── Directories ───────────────────────────────────────────────────
      {
        systemd.tmpfiles.rules = [
-          "d ${cfg.stateDir}                0755 ${cfg.user} ${cfg.group} - -"
-          "d ${cfg.stateDir}/.hermes        0755 ${cfg.user} ${cfg.group} - -"
+          "d ${cfg.stateDir}                0750 ${cfg.user} ${cfg.group} - -"
+          "d ${cfg.stateDir}/.hermes        0750 ${cfg.user} ${cfg.group} - -"
          "d ${cfg.stateDir}/home           0750 ${cfg.user} ${cfg.group} - -"
          "d ${cfg.workingDirectory}         0750 ${cfg.user} ${cfg.group} - -"
        ];
@@ -566,21 +567,23 @@
          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 0644 -D ${configFile} ${cfg.stateDir}/.hermes/config.yaml
+            install -o ${cfg.user} -g ${cfg.group} -m 0640 -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 0644 ${cfg.stateDir}/.hermes/config.yaml
+            chmod 0640 ${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) ''
@@ -612,7 +615,7 @@ HERMES_NIX_ENV_EOF

          # Link documents into workspace
          ${lib.concatStringsSep "\n" (lib.mapAttrsToList (name: _value: ''
-            install -o ${cfg.user} -g ${cfg.group} -m 0644 ${documentDerivation}/${name} ${cfg.workingDirectory}/${name}
+            install -o ${cfg.user} -g ${cfg.group} -m 0640 ${documentDerivation}/${name} ${cfg.workingDirectory}/${name}
          '') cfg.documents)}
        '';
      }
@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"

 [project]
 name = "hermes-agent"
-version = "0.4.0"
+version = "0.5.0"
 description = "The self-improving AI agent — creates skills from experience, improves them during use, and runs anywhere"
 readme = "README.md"
 requires-python = ">=3.11"
@@ -26,6 +26,7 @@ dependencies = [
  # Interactive CLI (prompt_toolkit is used directly by cli.py)
  "prompt_toolkit>=3.0.52,<4",
  # Tools
+  "exa-py>=2.9.0,<3",
  "firecrawl-py>=4.16.0,<5",
  "parallel-web>=0.4.2,<1",
  "fal-client>=0.13.1,<1",
@@ -368,6 +368,48 @@ _BUDGET_WARNING_RE = re.compile(
 )


+# Regex to match lone surrogate code points (U+D800..U+DFFF).
+# These are invalid in UTF-8 and cause UnicodeEncodeError when the OpenAI SDK
+# serialises messages to JSON.  Common source: clipboard paste from Google Docs
+# or other rich-text editors on some platforms.
+_SURROGATE_RE = re.compile(r'[\ud800-\udfff]')
+
+
+def _sanitize_surrogates(text: str) -> str:
+    """Replace lone surrogate code points with U+FFFD (replacement character).
+
+    Surrogates are invalid in UTF-8 and will crash ``json.dumps()`` inside the
+    OpenAI SDK.  This is a fast no-op when the text contains no surrogates.
+    """
+    if _SURROGATE_RE.search(text):
+        return _SURROGATE_RE.sub('\ufffd', text)
+    return text
+
+
+def _sanitize_messages_surrogates(messages: list) -> bool:
+    """Sanitize surrogate characters from all string content in a messages list.
+
+    Walks message dicts in-place.  Returns True if any surrogates were found
+    and replaced, False otherwise.
+    """
+    found = False
+    for msg in messages:
+        if not isinstance(msg, dict):
+            continue
+        content = msg.get("content")
+        if isinstance(content, str) and _SURROGATE_RE.search(content):
+            msg["content"] = _SURROGATE_RE.sub('\ufffd', content)
+            found = True
+        elif isinstance(content, list):
+            for part in content:
+                if isinstance(part, dict):
+                    text = part.get("text")
+                    if isinstance(text, str) and _SURROGATE_RE.search(text):
+                        part["text"] = _SURROGATE_RE.sub('\ufffd', text)
+                        found = True
+    return found
+
+
 def _strip_budget_warnings_from_history(messages: list) -> None:
    """Remove budget pressure warnings from tool-result messages in-place.

@@ -1042,8 +1084,8 @@ class AIAgent:
                    else:
                        if not hcfg.enabled:
                            logger.debug("Honcho disabled in global config")
-                        elif not hcfg.api_key:
-                            logger.debug("Honcho enabled but no API key configured")
+                        elif not (hcfg.api_key or hcfg.base_url):
+                            logger.debug("Honcho enabled but no API key or base URL configured")
                        else:
                            logger.debug("Honcho enabled but missing API key or disabled in config")
            except Exception as e:
@@ -2250,8 +2292,14 @@ class AIAgent:
    # ── Honcho integration helpers ──

    def _honcho_should_activate(self, hcfg) -> bool:
-        """Return True when remote Honcho should be active."""
-        if not hcfg or not hcfg.enabled or not hcfg.api_key:
+        """Return True when Honcho should be active.
+
+        Self-hosted Honcho may be configured with a base_url and no API key,
+        so activation should accept either credential style.
+        """
+        if not hcfg or not hcfg.enabled:
+            return False
+        if not (hcfg.api_key or hcfg.base_url):
            return False
        return True

@@ -3883,6 +3931,12 @@ class AIAgent:
            content_parts: list = []
            tool_calls_acc: dict = {}
            tool_gen_notified: set = set()
+            # Ollama-compatible endpoints reuse index 0 for every tool call
+            # in a parallel batch, distinguishing them only by id.  Track
+            # the last seen id per raw index so we can detect a new tool
+            # call starting at the same index and redirect it to a fresh slot.
+            _last_id_at_idx: dict = {}      # raw_index -> last seen non-empty id
+            _active_slot_by_idx: dict = {}  # raw_index -> current slot in tool_calls_acc
            finish_reason = None
            model_name = None
            role = "assistant"
@@ -3945,7 +3999,24 @@ class AIAgent:
                # Accumulate tool call deltas — notify display on first name
                if delta and delta.tool_calls:
                    for tc_delta in delta.tool_calls:
-                        idx = tc_delta.index if tc_delta.index is not None else 0
+                        raw_idx = tc_delta.index if tc_delta.index is not None else 0
+                        delta_id = tc_delta.id or ""
+
+                        # Ollama fix: detect a new tool call reusing the same
+                        # raw index (different id) and redirect to a fresh slot.
+                        if raw_idx not in _active_slot_by_idx:
+                            _active_slot_by_idx[raw_idx] = raw_idx
+                        if (
+                            delta_id
+                            and raw_idx in _last_id_at_idx
+                            and delta_id != _last_id_at_idx[raw_idx]
+                        ):
+                            new_slot = max(tool_calls_acc, default=-1) + 1
+                            _active_slot_by_idx[raw_idx] = new_slot
+                        if delta_id:
+                            _last_id_at_idx[raw_idx] = delta_id
+                        idx = _active_slot_by_idx[raw_idx]
+
                        if idx not in tool_calls_acc:
                            tool_calls_acc[idx] = {
                                "id": tc_delta.id or "",
@@ -5936,6 +6007,14 @@ class AIAgent:
        # Installed once, transparent when streams are healthy, prevents crash on write.
        _install_safe_stdio()

+        # Sanitize surrogate characters from user input.  Clipboard paste from
+        # rich-text editors (Google Docs, Word, etc.) can inject lone surrogates
+        # that are invalid UTF-8 and crash JSON serialization in the OpenAI SDK.
+        if isinstance(user_message, str):
+            user_message = _sanitize_surrogates(user_message)
+        if isinstance(persist_user_message, str):
+            persist_user_message = _sanitize_surrogates(persist_user_message)
+
        # Store stream callback for _interruptible_api_call to pick up
        self._stream_callback = stream_callback
        self._persist_user_message_idx = None
@@ -5952,6 +6031,7 @@ class AIAgent:
        self._codex_incomplete_retries = 0
        self._last_content_with_tools = None
        self._mute_post_response = False
+        self._surrogate_sanitized = False
        # NOTE: _turns_since_memory and _iters_since_skill are NOT reset here.
        # They are initialized in __init__ and must persist across run_conversation
        # calls so that nudge logic accumulates correctly in CLI mode.
@@ -6787,6 +6867,24 @@ class AIAgent:
                    if self.thinking_callback:
                        self.thinking_callback("")

+                    # -----------------------------------------------------------
+                    # Surrogate character recovery.  UnicodeEncodeError happens
+                    # when the messages contain lone surrogates (U+D800..U+DFFF)
+                    # that are invalid UTF-8.  Common source: clipboard paste
+                    # from Google Docs or similar rich-text editors.  We sanitize
+                    # the entire messages list in-place and retry once.
+                    # -----------------------------------------------------------
+                    if isinstance(api_error, UnicodeEncodeError) and not getattr(self, '_surrogate_sanitized', False):
+                        self._surrogate_sanitized = True
+                        if _sanitize_messages_surrogates(messages):
+                            self._vprint(
+                                f"{self.log_prefix}⚠️  Stripped invalid surrogate characters from messages. Retrying...",
+                                force=True,
+                            )
+                            continue
+                        # Surrogates weren't in messages — might be in system
+                        # prompt or prefill.  Fall through to normal error path.
+
                    status_code = getattr(api_error, "status_code", None)
                    if (
                        self.api_mode == "codex_responses"
@@ -7055,8 +7153,13 @@ class AIAgent:
                    # 529 (Anthropic overloaded) is also transient.
                    # Also catch local validation errors (ValueError, TypeError) — these
                    # are programming bugs, not transient failures.
+                    # Exclude UnicodeEncodeError — it's a ValueError subclass but is
+                    # handled separately by the surrogate sanitization path above.
                    _RETRYABLE_STATUS_CODES = {413, 429, 529}
-                    is_local_validation_error = isinstance(api_error, (ValueError, TypeError))
+                    is_local_validation_error = (
+                        isinstance(api_error, (ValueError, TypeError))
+                        and not isinstance(api_error, UnicodeEncodeError)
+                    )
                    # Detect generic 400s from Anthropic OAuth (transient server-side failures).
                    # Real invalid_request_error responses include a descriptive message;
                    # transient ones contain only "Error" or are empty. (ref: issue #1608)
@@ -0,0 +1,180 @@
+---
+name: webhook-subscriptions
+description: Create and manage webhook subscriptions for event-driven agent activation. Use when the user wants external services to trigger agent runs automatically.
+version: 1.0.0
+metadata:
+  hermes:
+    tags: [webhook, events, automation, integrations]
+---
+
+# Webhook Subscriptions
+
+Create dynamic webhook subscriptions so external services (GitHub, GitLab, Stripe, CI/CD, IoT sensors, monitoring tools) can trigger Hermes agent runs by POSTing events to a URL.
+
+## Setup (Required First)
+
+The webhook platform must be enabled before subscriptions can be created. Check with:
+```bash
+hermes webhook list
+```
+
+If it says "Webhook platform is not enabled", set it up:
+
+### Option 1: Setup wizard
+```bash
+hermes gateway setup
+```
+Follow the prompts to enable webhooks, set the port, and set a global HMAC secret.
+
+### Option 2: Manual config
+Add to `~/.hermes/config.yaml`:
+```yaml
+platforms:
+  webhook:
+    enabled: true
+    extra:
+      host: "0.0.0.0"
+      port: 8644
+      secret: "generate-a-strong-secret-here"
+```
+
+### Option 3: Environment variables
+Add to `~/.hermes/.env`:
+```bash
+WEBHOOK_ENABLED=true
+WEBHOOK_PORT=8644
+WEBHOOK_SECRET=generate-a-strong-secret-here
+```
+
+After configuration, start (or restart) the gateway:
+```bash
+hermes gateway run
+# Or if using systemd:
+systemctl --user restart hermes-gateway
+```
+
+Verify it's running:
+```bash
+curl http://localhost:8644/health
+```
+
+## Commands
+
+All management is via the `hermes webhook` CLI command:
+
+### Create a subscription
+```bash
+hermes webhook subscribe <name> \
+  --prompt "Prompt template with {payload.fields}" \
+  --events "event1,event2" \
+  --description "What this does" \
+  --skills "skill1,skill2" \
+  --deliver telegram \
+  --deliver-chat-id "12345" \
+  --secret "optional-custom-secret"
+```
+
+Returns the webhook URL and HMAC secret. The user configures their service to POST to that URL.
+
+### List subscriptions
+```bash
+hermes webhook list
+```
+
+### Remove a subscription
+```bash
+hermes webhook remove <name>
+```
+
+### Test a subscription
+```bash
+hermes webhook test <name>
+hermes webhook test <name> --payload '{"key": "value"}'
+```
+
+## Prompt Templates
+
+Prompts support `{dot.notation}` for accessing nested payload fields:
+
+- `{issue.title}` — GitHub issue title
+- `{pull_request.user.login}` — PR author
+- `{data.object.amount}` — Stripe payment amount
+- `{sensor.temperature}` — IoT sensor reading
+
+If no prompt is specified, the full JSON payload is dumped into the agent prompt.
+
+## Common Patterns
+
+### GitHub: new issues
+```bash
+hermes webhook subscribe github-issues \
+  --events "issues" \
+  --prompt "New GitHub issue #{issue.number}: {issue.title}\n\nAction: {action}\nAuthor: {issue.user.login}\nBody:\n{issue.body}\n\nPlease triage this issue." \
+  --deliver telegram \
+  --deliver-chat-id "-100123456789"
+```
+
+Then in GitHub repo Settings → Webhooks → Add webhook:
+- Payload URL: the returned webhook_url
+- Content type: application/json
+- Secret: the returned secret
+- Events: "Issues"
+
+### GitHub: PR reviews
+```bash
+hermes webhook subscribe github-prs \
+  --events "pull_request" \
+  --prompt "PR #{pull_request.number} {action}: {pull_request.title}\nBy: {pull_request.user.login}\nBranch: {pull_request.head.ref}\n\n{pull_request.body}" \
+  --skills "github-code-review" \
+  --deliver github_comment
+```
+
+### Stripe: payment events
+```bash
+hermes webhook subscribe stripe-payments \
+  --events "payment_intent.succeeded,payment_intent.payment_failed" \
+  --prompt "Payment {data.object.status}: {data.object.amount} cents from {data.object.receipt_email}" \
+  --deliver telegram \
+  --deliver-chat-id "-100123456789"
+```
+
+### CI/CD: build notifications
+```bash
+hermes webhook subscribe ci-builds \
+  --events "pipeline" \
+  --prompt "Build {object_attributes.status} on {project.name} branch {object_attributes.ref}\nCommit: {commit.message}" \
+  --deliver discord \
+  --deliver-chat-id "1234567890"
+```
+
+### Generic monitoring alert
+```bash
+hermes webhook subscribe alerts \
+  --prompt "Alert: {alert.name}\nSeverity: {alert.severity}\nMessage: {alert.message}\n\nPlease investigate and suggest remediation." \
+  --deliver origin
+```
+
+## Security
+
+- Each subscription gets an auto-generated HMAC-SHA256 secret (or provide your own with `--secret`)
+- The webhook adapter validates signatures on every incoming POST
+- Static routes from config.yaml cannot be overwritten by dynamic subscriptions
+- Subscriptions persist to `~/.hermes/webhook_subscriptions.json`
+
+## How It Works
+
+1. `hermes webhook subscribe` writes to `~/.hermes/webhook_subscriptions.json`
+2. The webhook adapter hot-reloads this file on each incoming request (mtime-gated, negligible overhead)
+3. When a POST arrives matching a route, the adapter formats the prompt and triggers an agent run
+4. The agent's response is delivered to the configured target (Telegram, Discord, GitHub comment, etc.)
+
+## Troubleshooting
+
+If webhooks aren't working:
+
+1. **Is the gateway running?** Check with `systemctl --user status hermes-gateway` or `ps aux | grep gateway`
+2. **Is the webhook server listening?** `curl http://localhost:8644/health` should return `{"status": "ok"}`
+3. **Check gateway logs:** `grep webhook ~/.hermes/logs/gateway.log | tail -20`
+4. **Signature mismatch?** Verify the secret in your service matches the one from `hermes webhook list`. GitHub sends `X-Hub-Signature-256`, GitLab sends `X-Gitlab-Token`.
+5. **Firewall/NAT?** The webhook URL must be reachable from the service. For local development, use a tunnel (ngrok, cloudflared).
+6. **Wrong event type?** Check `--events` filter matches what the service sends. Use `hermes webhook test <name>` to verify the route works.
@@ -219,6 +219,9 @@ if command -v gh &>/dev/null && gh auth status &>/dev/null; then
  echo "AUTH_METHOD=gh"
 elif [ -n "$GITHUB_TOKEN" ]; then
  echo "AUTH_METHOD=curl"
+elif [ -f ~/.hermes/.env ] && grep -q "^GITHUB_TOKEN=" ~/.hermes/.env; then
+  export GITHUB_TOKEN=$(grep "^GITHUB_TOKEN=" ~/.hermes/.env | head -1 | cut -d= -f2 | tr -d '\n\r')
+  echo "AUTH_METHOD=curl"
 elif grep -q "github.com" ~/.git-credentials 2>/dev/null; then
  export GITHUB_TOKEN=$(grep "github.com" ~/.git-credentials | head -1 | sed 's|https://[^:]*:\([^@]*\)@.*|\1|')
  echo "AUTH_METHOD=curl"
@@ -23,6 +23,11 @@ if command -v gh &>/dev/null && gh auth status &>/dev/null 2>&1; then
    GH_USER=$(gh api user --jq '.login' 2>/dev/null)
 elif [ -n "$GITHUB_TOKEN" ]; then
    GH_AUTH_METHOD="curl"
+elif [ -f "$HOME/.hermes/.env" ] && grep -q "^GITHUB_TOKEN=" "$HOME/.hermes/.env" 2>/dev/null; then
+    GITHUB_TOKEN=$(grep "^GITHUB_TOKEN=" "$HOME/.hermes/.env" | head -1 | cut -d= -f2 | tr -d '\n\r')
+    if [ -n "$GITHUB_TOKEN" ]; then
+        GH_AUTH_METHOD="curl"
+    fi
 elif [ -f "$HOME/.git-credentials" ] && grep -q "github.com" "$HOME/.git-credentials" 2>/dev/null; then
    GITHUB_TOKEN=$(grep "github.com" "$HOME/.git-credentials" | head -1 | sed 's|https://[^:]*:\([^@]*\)@.*|\1|')
    if [ -n "$GITHUB_TOKEN" ]; then
@@ -27,7 +27,11 @@ if command -v gh &>/dev/null && gh auth status &>/dev/null; then
 else
  AUTH="git"
  if [ -z "$GITHUB_TOKEN" ]; then
-    GITHUB_TOKEN=$(grep "github.com" ~/.git-credentials 2>/dev/null | head -1 | sed 's|https://[^:]*:\([^@]*\)@.*|\1|')
+    if [ -f ~/.hermes/.env ] && grep -q "^GITHUB_TOKEN=" ~/.hermes/.env; then
+      GITHUB_TOKEN=$(grep "^GITHUB_TOKEN=" ~/.hermes/.env | head -1 | cut -d= -f2 | tr -d '\n\r')
+    elif grep -q "github.com" ~/.git-credentials 2>/dev/null; then
+      GITHUB_TOKEN=$(grep "github.com" ~/.git-credentials 2>/dev/null | head -1 | sed 's|https://[^:]*:\([^@]*\)@.*|\1|')
+    fi
  fi
 fi

@@ -27,7 +27,11 @@ if command -v gh &>/dev/null && gh auth status &>/dev/null; then
 else
  AUTH="git"
  if [ -z "$GITHUB_TOKEN" ]; then
-    GITHUB_TOKEN=$(grep "github.com" ~/.git-credentials 2>/dev/null | head -1 | sed 's|https://[^:]*:\([^@]*\)@.*|\1|')
+    if [ -f ~/.hermes/.env ] && grep -q "^GITHUB_TOKEN=" ~/.hermes/.env; then
+      GITHUB_TOKEN=$(grep "^GITHUB_TOKEN=" ~/.hermes/.env | head -1 | cut -d= -f2 | tr -d '\n\r')
+    elif grep -q "github.com" ~/.git-credentials 2>/dev/null; then
+      GITHUB_TOKEN=$(grep "github.com" ~/.git-credentials 2>/dev/null | head -1 | sed 's|https://[^:]*:\([^@]*\)@.*|\1|')
+    fi
  fi
 fi

@@ -29,7 +29,11 @@ else
  AUTH="git"
  # Ensure we have a token for API calls
  if [ -z "$GITHUB_TOKEN" ]; then
-    GITHUB_TOKEN=$(grep "github.com" ~/.git-credentials 2>/dev/null | head -1 | sed 's|https://[^:]*:\([^@]*\)@.*|\1|')
+    if [ -f ~/.hermes/.env ] && grep -q "^GITHUB_TOKEN=" ~/.hermes/.env; then
+      GITHUB_TOKEN=$(grep "^GITHUB_TOKEN=" ~/.hermes/.env | head -1 | cut -d= -f2 | tr -d '\n\r')
+    elif grep -q "github.com" ~/.git-credentials 2>/dev/null; then
+      GITHUB_TOKEN=$(grep "github.com" ~/.git-credentials 2>/dev/null | head -1 | sed 's|https://[^:]*:\([^@]*\)@.*|\1|')
+    fi
  fi
 fi
 echo "Using: $AUTH"
@@ -26,7 +26,11 @@ if command -v gh &>/dev/null && gh auth status &>/dev/null; then
 else
  AUTH="git"
  if [ -z "$GITHUB_TOKEN" ]; then
-    GITHUB_TOKEN=$(grep "github.com" ~/.git-credentials 2>/dev/null | head -1 | sed 's|https://[^:]*:\([^@]*\)@.*|\1|')
+    if [ -f ~/.hermes/.env ] && grep -q "^GITHUB_TOKEN=" ~/.hermes/.env; then
+      GITHUB_TOKEN=$(grep "^GITHUB_TOKEN=" ~/.hermes/.env | head -1 | cut -d= -f2 | tr -d '\n\r')
+    elif grep -q "github.com" ~/.git-credentials 2>/dev/null; then
+      GITHUB_TOKEN=$(grep "github.com" ~/.git-credentials 2>/dev/null | head -1 | sed 's|https://[^:]*:\([^@]*\)@.*|\1|')
+    fi
  fi
 fi

@@ -28,6 +28,7 @@ from gateway.platforms.api_server import (
    _CORS_HEADERS,
    check_api_server_requirements,
    cors_middleware,
+    security_headers_middleware,
 )


@@ -214,9 +215,11 @@ def _make_adapter(api_key: str = "", cors_origins=None) -> APIServerAdapter:

 def _create_app(adapter: APIServerAdapter) -> web.Application:
    """Create the aiohttp app from the adapter (without starting the full server)."""
-    app = web.Application(middlewares=[cors_middleware])
+    mws = [mw for mw in (cors_middleware, security_headers_middleware) if mw is not None]
+    app = web.Application(middlewares=mws)
    app["api_server_adapter"] = adapter
    app.router.add_get("/health", adapter._handle_health)
+    app.router.add_get("/v1/health", adapter._handle_health)
    app.router.add_get("/v1/models", adapter._handle_models)
    app.router.add_post("/v1/chat/completions", adapter._handle_chat_completions)
    app.router.add_post("/v1/responses", adapter._handle_responses)
@@ -241,6 +244,16 @@ def auth_adapter():


 class TestHealthEndpoint:
+    @pytest.mark.asyncio
+    async def test_security_headers_present(self, adapter):
+        """Responses should include basic security headers."""
+        app = _create_app(adapter)
+        async with TestClient(TestServer(app)) as cli:
+            resp = await cli.get("/health")
+            assert resp.status == 200
+            assert resp.headers.get("X-Content-Type-Options") == "nosniff"
+            assert resp.headers.get("Referrer-Policy") == "no-referrer"
+
    @pytest.mark.asyncio
    async def test_health_returns_ok(self, adapter):
        app = _create_app(adapter)
@@ -251,6 +264,17 @@ class TestHealthEndpoint:
            assert data["status"] == "ok"
            assert data["platform"] == "hermes-agent"

+    @pytest.mark.asyncio
+    async def test_v1_health_alias_returns_ok(self, adapter):
+        """GET /v1/health should return the same response as /health."""
+        app = _create_app(adapter)
+        async with TestClient(TestServer(app)) as cli:
+            resp = await cli.get("/v1/health")
+            assert resp.status == 200
+            data = await resp.json()
+            assert data["status"] == "ok"
+            assert data["platform"] == "hermes-agent"
+

 # ---------------------------------------------------------------------------
 # /v1/models endpoint
@@ -1344,6 +1368,21 @@ class TestCORS:
            assert "Authorization" in resp.headers.get("Access-Control-Allow-Headers", "")


+    @pytest.mark.asyncio
+    async def test_cors_preflight_sets_max_age(self):
+        adapter = _make_adapter(cors_origins=["http://localhost:3000"])
+        app = _create_app(adapter)
+        async with TestClient(TestServer(app)) as cli:
+            resp = await cli.options(
+                "/v1/chat/completions",
+                headers={
+                    "Origin": "http://localhost:3000",
+                    "Access-Control-Request-Method": "POST",
+                    "Access-Control-Request-Headers": "Authorization, Content-Type",
+                },
+            )
+            assert resp.status == 200
+            assert resp.headers.get("Access-Control-Max-Age") == "600"
 # ---------------------------------------------------------------------------
 # Conversation parameter
 # ---------------------------------------------------------------------------
@@ -10,6 +10,7 @@ Covers:
 """

 import asyncio
+import os
 import sys
 from pathlib import Path
 from types import SimpleNamespace
@@ -227,7 +228,8 @@ def test_persist_dm_topic_thread_id_writes_config(tmp_path):

    adapter = _make_adapter()

-    with patch.object(Path, "home", return_value=tmp_path):
+    with patch.object(Path, "home", return_value=tmp_path), \
+         patch.dict(os.environ, {"HERMES_HOME": str(tmp_path / ".hermes")}):
        adapter._persist_dm_topic_thread_id(111, "General", 999)

    with open(config_file) as f:
@@ -366,7 +368,8 @@ def test_get_dm_topic_info_hot_reloads_from_config(tmp_path):
    with open(config_file, "w") as f:
        yaml.dump(config_data, f)

-    with patch.object(Path, "home", return_value=tmp_path):
+    with patch.object(Path, "home", return_value=tmp_path), \
+         patch.dict(os.environ, {"HERMES_HOME": str(tmp_path / ".hermes")}):
        result = adapter._get_dm_topic_info("111", "555")

    assert result is not None
@@ -171,6 +171,170 @@ class TestCacheImageFromUrl:
        mock_sleep.assert_not_called()


+# ---------------------------------------------------------------------------
+# cache_audio_from_url (base.py)
+# ---------------------------------------------------------------------------
+
+class TestCacheAudioFromUrl:
+    """Tests for gateway.platforms.base.cache_audio_from_url"""
+
+    def test_success_on_first_attempt(self, tmp_path, monkeypatch):
+        """A clean 200 response caches the audio and returns a path."""
+        monkeypatch.setattr("gateway.platforms.base.AUDIO_CACHE_DIR", tmp_path / "audio")
+
+        fake_response = MagicMock()
+        fake_response.content = b"\x00\x01 fake audio"
+        fake_response.raise_for_status = MagicMock()
+
+        mock_client = AsyncMock()
+        mock_client.get = AsyncMock(return_value=fake_response)
+        mock_client.__aenter__ = AsyncMock(return_value=mock_client)
+        mock_client.__aexit__ = AsyncMock(return_value=False)
+
+        async def run():
+            with patch("httpx.AsyncClient", return_value=mock_client):
+                from gateway.platforms.base import cache_audio_from_url
+                return await cache_audio_from_url(
+                    "http://example.com/voice.ogg", ext=".ogg"
+                )
+
+        path = asyncio.run(run())
+        assert path.endswith(".ogg")
+        mock_client.get.assert_called_once()
+
+    def test_retries_on_timeout_then_succeeds(self, tmp_path, monkeypatch):
+        """A timeout on the first attempt is retried; second attempt succeeds."""
+        monkeypatch.setattr("gateway.platforms.base.AUDIO_CACHE_DIR", tmp_path / "audio")
+
+        fake_response = MagicMock()
+        fake_response.content = b"audio data"
+        fake_response.raise_for_status = MagicMock()
+
+        mock_client = AsyncMock()
+        mock_client.get = AsyncMock(
+            side_effect=[_make_timeout_error(), fake_response]
+        )
+        mock_client.__aenter__ = AsyncMock(return_value=mock_client)
+        mock_client.__aexit__ = AsyncMock(return_value=False)
+
+        mock_sleep = AsyncMock()
+
+        async def run():
+            with patch("httpx.AsyncClient", return_value=mock_client), \
+                 patch("asyncio.sleep", mock_sleep):
+                from gateway.platforms.base import cache_audio_from_url
+                return await cache_audio_from_url(
+                    "http://example.com/voice.ogg", ext=".ogg", retries=2
+                )
+
+        path = asyncio.run(run())
+        assert path.endswith(".ogg")
+        assert mock_client.get.call_count == 2
+        mock_sleep.assert_called_once()
+
+    def test_retries_on_429_then_succeeds(self, tmp_path, monkeypatch):
+        """A 429 response on the first attempt is retried; second attempt succeeds."""
+        monkeypatch.setattr("gateway.platforms.base.AUDIO_CACHE_DIR", tmp_path / "audio")
+
+        ok_response = MagicMock()
+        ok_response.content = b"audio data"
+        ok_response.raise_for_status = MagicMock()
+
+        mock_client = AsyncMock()
+        mock_client.get = AsyncMock(
+            side_effect=[_make_http_status_error(429), ok_response]
+        )
+        mock_client.__aenter__ = AsyncMock(return_value=mock_client)
+        mock_client.__aexit__ = AsyncMock(return_value=False)
+
+        async def run():
+            with patch("httpx.AsyncClient", return_value=mock_client), \
+                 patch("asyncio.sleep", new_callable=AsyncMock):
+                from gateway.platforms.base import cache_audio_from_url
+                return await cache_audio_from_url(
+                    "http://example.com/voice.ogg", ext=".ogg", retries=2
+                )
+
+        path = asyncio.run(run())
+        assert path.endswith(".ogg")
+        assert mock_client.get.call_count == 2
+
+    def test_retries_on_500_then_succeeds(self, tmp_path, monkeypatch):
+        """A 500 response on the first attempt is retried; second attempt succeeds."""
+        monkeypatch.setattr("gateway.platforms.base.AUDIO_CACHE_DIR", tmp_path / "audio")
+
+        ok_response = MagicMock()
+        ok_response.content = b"audio data"
+        ok_response.raise_for_status = MagicMock()
+
+        mock_client = AsyncMock()
+        mock_client.get = AsyncMock(
+            side_effect=[_make_http_status_error(500), ok_response]
+        )
+        mock_client.__aenter__ = AsyncMock(return_value=mock_client)
+        mock_client.__aexit__ = AsyncMock(return_value=False)
+
+        async def run():
+            with patch("httpx.AsyncClient", return_value=mock_client), \
+                 patch("asyncio.sleep", new_callable=AsyncMock):
+                from gateway.platforms.base import cache_audio_from_url
+                return await cache_audio_from_url(
+                    "http://example.com/voice.ogg", ext=".ogg", retries=2
+                )
+
+        path = asyncio.run(run())
+        assert path.endswith(".ogg")
+        assert mock_client.get.call_count == 2
+
+    def test_raises_after_max_retries_exhausted(self, tmp_path, monkeypatch):
+        """Timeout on every attempt raises after all retries are consumed."""
+        monkeypatch.setattr("gateway.platforms.base.AUDIO_CACHE_DIR", tmp_path / "audio")
+
+        mock_client = AsyncMock()
+        mock_client.get = AsyncMock(side_effect=_make_timeout_error())
+        mock_client.__aenter__ = AsyncMock(return_value=mock_client)
+        mock_client.__aexit__ = AsyncMock(return_value=False)
+
+        async def run():
+            with patch("httpx.AsyncClient", return_value=mock_client), \
+                 patch("asyncio.sleep", new_callable=AsyncMock):
+                from gateway.platforms.base import cache_audio_from_url
+                await cache_audio_from_url(
+                    "http://example.com/voice.ogg", ext=".ogg", retries=2
+                )
+
+        with pytest.raises(httpx.TimeoutException):
+            asyncio.run(run())
+
+        # 3 total calls: initial + 2 retries
+        assert mock_client.get.call_count == 3
+
+    def test_non_retryable_4xx_raises_immediately(self, tmp_path, monkeypatch):
+        """A 404 (non-retryable) is raised immediately without any retry."""
+        monkeypatch.setattr("gateway.platforms.base.AUDIO_CACHE_DIR", tmp_path / "audio")
+
+        mock_sleep = AsyncMock()
+        mock_client = AsyncMock()
+        mock_client.get = AsyncMock(side_effect=_make_http_status_error(404))
+        mock_client.__aenter__ = AsyncMock(return_value=mock_client)
+        mock_client.__aexit__ = AsyncMock(return_value=False)
+
+        async def run():
+            with patch("httpx.AsyncClient", return_value=mock_client), \
+                 patch("asyncio.sleep", mock_sleep):
+                from gateway.platforms.base import cache_audio_from_url
+                await cache_audio_from_url(
+                    "http://example.com/voice.ogg", ext=".ogg", retries=2
+                )
+
+        with pytest.raises(httpx.HTTPStatusError):
+            asyncio.run(run())
+
+        # Only 1 attempt, no sleep
+        assert mock_client.get.call_count == 1
+        mock_sleep.assert_not_called()
+
+
 # ---------------------------------------------------------------------------
 # Slack mock setup (mirrors existing test_slack.py approach)
 # ---------------------------------------------------------------------------
@@ -62,6 +62,18 @@ class TestMessageEventGetCommand:
        event = MessageEvent(text="/")
        assert event.get_command() == ""

+    def test_command_with_at_botname(self):
+        event = MessageEvent(text="/new@TigerNanoBot")
+        assert event.get_command() == "new"
+
+    def test_command_with_at_botname_and_args(self):
+        event = MessageEvent(text="/compress@TigerNanoBot")
+        assert event.get_command() == "compress"
+
+    def test_command_mixed_case_with_at_botname(self):
+        event = MessageEvent(text="/RESET@TigerNanoBot")
+        assert event.get_command() == "reset"
+

 class TestMessageEventGetCommandArgs:
    def test_command_with_args(self):
@@ -344,6 +344,7 @@ class TestRuntimeDisconnectQueuing:
    async def test_retryable_runtime_error_queued_for_reconnect(self):
        """Retryable runtime errors should add the platform to _failed_platforms."""
        runner = _make_runner()
+        runner.stop = AsyncMock()

        adapter = StubAdapter(succeed=True)
        adapter._set_fatal_error("network_error", "DNS failure", retryable=True)
@@ -371,8 +372,12 @@ class TestRuntimeDisconnectQueuing:
        assert Platform.TELEGRAM not in runner._failed_platforms

    @pytest.mark.asyncio
-    async def test_retryable_error_prevents_shutdown_when_queued(self):
-        """Gateway should not shut down if failed platforms are queued for reconnection."""
+    async def test_retryable_error_exits_for_service_restart_when_all_down(self):
+        """Gateway should exit with failure when all platforms fail with retryable errors.
+
+        This lets systemd Restart=on-failure restart the process, which is more
+        reliable than in-process background reconnection after exhausted retries.
+        """
        runner = _make_runner()
        runner.stop = AsyncMock()

@@ -382,7 +387,28 @@ class TestRuntimeDisconnectQueuing:

        await runner._handle_adapter_fatal_error(adapter)

-        # stop() should NOT have been called since we have platforms queued
+        # stop() SHOULD be called — gateway exits for systemd restart
+        runner.stop.assert_called_once()
+        assert runner._exit_with_failure is True
+        assert Platform.TELEGRAM in runner._failed_platforms
+
+    @pytest.mark.asyncio
+    async def test_retryable_error_no_exit_when_other_adapters_still_connected(self):
+        """Gateway should NOT exit if some adapters are still connected."""
+        runner = _make_runner()
+        runner.stop = AsyncMock()
+
+        failing_adapter = StubAdapter(succeed=True)
+        failing_adapter._set_fatal_error("network_error", "DNS failure", retryable=True)
+        runner.adapters[Platform.TELEGRAM] = failing_adapter
+
+        # Another adapter is still connected
+        healthy_adapter = StubAdapter(succeed=True)
+        runner.adapters[Platform.DISCORD] = healthy_adapter
+
+        await runner._handle_adapter_fatal_error(failing_adapter)
+
+        # stop() should NOT have been called — Discord is still up
        runner.stop.assert_not_called()
        assert Platform.TELEGRAM in runner._failed_platforms

@@ -89,7 +89,8 @@ async def test_runner_queues_retryable_runtime_fatal_for_reconnection(monkeypatc

    await runner._handle_adapter_fatal_error(adapter)

-    # Should NOT shut down — platform is queued for reconnection
-    runner.stop.assert_not_awaited()
+    # Should shut down with failure — systemd Restart=on-failure will restart
+    runner.stop.assert_awaited_once()
+    assert runner._exit_with_failure is True
    assert Platform.WHATSAPP in runner._failed_platforms
    assert runner._failed_platforms[Platform.WHATSAPP]["attempts"] == 0
@@ -315,6 +315,24 @@ class TestFallbackTransportInit:
        transport = tnet.TelegramFallbackTransport(["149.154.167.220", "not-an-ip"])
        assert transport._fallback_ips == ["149.154.167.220"]

+    def test_uses_proxy_env_for_primary_and_fallback_transports(self, monkeypatch):
+        seen_kwargs = []
+
+        def factory(**kwargs):
+            seen_kwargs.append(kwargs.copy())
+            return FakeTransport([], {})
+
+        for key in ("HTTPS_PROXY", "HTTP_PROXY", "ALL_PROXY", "https_proxy", "http_proxy", "all_proxy"):
+            monkeypatch.delenv(key, raising=False)
+        monkeypatch.setenv("HTTPS_PROXY", "http://proxy.example:8080")
+        monkeypatch.setattr(tnet.httpx, "AsyncHTTPTransport", factory)
+
+        transport = tnet.TelegramFallbackTransport(["149.154.167.220"])
+
+        assert transport._fallback_ips == ["149.154.167.220"]
+        assert len(seen_kwargs) == 2
+        assert all(kwargs["proxy"] == "http://proxy.example:8080" for kwargs in seen_kwargs)
+

 class TestFallbackTransportClose:
    @pytest.mark.asyncio
@@ -0,0 +1,87 @@
+"""Tests for webhook adapter dynamic route loading."""
+
+import json
+import os
+import pytest
+from pathlib import Path
+
+from gateway.config import PlatformConfig
+from gateway.platforms.webhook import WebhookAdapter, _DYNAMIC_ROUTES_FILENAME
+
+
+def _make_adapter(routes=None, extra=None):
+    _extra = extra or {}
+    if routes:
+        _extra["routes"] = routes
+    _extra.setdefault("secret", "test-global-secret")
+    config = PlatformConfig(enabled=True, extra=_extra)
+    return WebhookAdapter(config)
+
+
+@pytest.fixture(autouse=True)
+def _isolate(tmp_path, monkeypatch):
+    monkeypatch.setenv("HERMES_HOME", str(tmp_path))
+
+
+class TestDynamicRouteLoading:
+    def test_no_dynamic_file(self):
+        adapter = _make_adapter(routes={"static": {"secret": "s"}})
+        adapter._reload_dynamic_routes()
+        assert "static" in adapter._routes
+        assert len(adapter._dynamic_routes) == 0
+
+    def test_loads_dynamic_routes(self, tmp_path):
+        subs = {"my-hook": {"secret": "dynamic-secret", "prompt": "test", "events": []}}
+        (tmp_path / _DYNAMIC_ROUTES_FILENAME).write_text(json.dumps(subs))
+
+        adapter = _make_adapter(routes={"static": {"secret": "s"}})
+        adapter._reload_dynamic_routes()
+        assert "my-hook" in adapter._routes
+        assert "static" in adapter._routes
+
+    def test_static_takes_precedence(self, tmp_path):
+        (tmp_path / _DYNAMIC_ROUTES_FILENAME).write_text(
+            json.dumps({"conflict": {"secret": "dynamic", "prompt": "dyn"}})
+        )
+        adapter = _make_adapter(routes={"conflict": {"secret": "static", "prompt": "stat"}})
+        adapter._reload_dynamic_routes()
+        assert adapter._routes["conflict"]["secret"] == "static"
+
+    def test_mtime_gated(self, tmp_path):
+        import time
+        path = tmp_path / _DYNAMIC_ROUTES_FILENAME
+        path.write_text(json.dumps({"v1": {"secret": "s"}}))
+
+        adapter = _make_adapter()
+        adapter._reload_dynamic_routes()
+        assert "v1" in adapter._dynamic_routes
+
+        # Same mtime — no reload
+        adapter._dynamic_routes["injected"] = True
+        adapter._reload_dynamic_routes()
+        assert "injected" in adapter._dynamic_routes
+
+        # New write — reloads
+        time.sleep(0.05)
+        path.write_text(json.dumps({"v2": {"secret": "s"}}))
+        adapter._reload_dynamic_routes()
+        assert "v2" in adapter._dynamic_routes
+        assert "v1" not in adapter._dynamic_routes
+
+    def test_file_removal_clears(self, tmp_path):
+        path = tmp_path / _DYNAMIC_ROUTES_FILENAME
+        path.write_text(json.dumps({"temp": {"secret": "s"}}))
+        adapter = _make_adapter()
+        adapter._reload_dynamic_routes()
+        assert "temp" in adapter._dynamic_routes
+
+        path.unlink()
+        adapter._reload_dynamic_routes()
+        assert len(adapter._dynamic_routes) == 0
+
+    def test_corrupted_file(self, tmp_path):
+        (tmp_path / _DYNAMIC_ROUTES_FILENAME).write_text("not json")
+        adapter = _make_adapter(routes={"static": {"secret": "s"}})
+        adapter._reload_dynamic_routes()
+        assert "static" in adapter._routes
+        assert len(adapter._dynamic_routes) == 0
@@ -105,3 +105,24 @@ class TestCmdUpdateBranchFallback:
        commands = [" ".join(str(a) for a in c.args[0]) for c in mock_run.call_args_list]
        pull_cmds = [c for c in commands if "pull" in c]
        assert len(pull_cmds) == 0
+
+    def test_update_non_interactive_skips_migration_prompt(self, mock_args, capsys):
+        """When stdin/stdout aren't TTYs, config migration prompt is skipped."""
+        with patch("shutil.which", return_value=None), patch(
+            "subprocess.run"
+        ) as mock_run, patch("builtins.input") as mock_input, patch(
+            "hermes_cli.config.get_missing_env_vars", return_value=["MISSING_KEY"]
+        ), patch("hermes_cli.config.get_missing_config_fields", return_value=[]), patch(
+            "hermes_cli.config.check_config_version", return_value=(1, 2)
+        ), patch("hermes_cli.main.sys") as mock_sys:
+            mock_sys.stdin.isatty.return_value = False
+            mock_sys.stdout.isatty.return_value = False
+            mock_run.side_effect = _make_run_side_effect(
+                branch="main", verify_ok=True, commit_count="1"
+            )
+
+            cmd_update(mock_args)
+
+            mock_input.assert_not_called()
+            captured = capsys.readouterr()
+            assert "Non-interactive session" in captured.out
@@ -153,12 +153,13 @@ class TestLaunchdServiceRecovery:
    def test_launchd_start_reloads_unloaded_job_and_retries(self, tmp_path, monkeypatch):
        plist_path = tmp_path / "ai.hermes.gateway.plist"
        plist_path.write_text(gateway_cli.generate_launchd_plist(), encoding="utf-8")
+        label = gateway_cli.get_launchd_label()

        calls = []

        def fake_run(cmd, check=False, **kwargs):
            calls.append(cmd)
-            if cmd == ["launchctl", "start", "ai.hermes.gateway"] and calls.count(cmd) == 1:
+            if cmd == ["launchctl", "start", label] and calls.count(cmd) == 1:
                raise gateway_cli.subprocess.CalledProcessError(3, cmd, stderr="Could not find service")
            return SimpleNamespace(returncode=0, stdout="", stderr="")

@@ -168,9 +169,9 @@ class TestLaunchdServiceRecovery:
        gateway_cli.launchd_start()

        assert calls == [
-            ["launchctl", "start", "ai.hermes.gateway"],
+            ["launchctl", "start", label],
            ["launchctl", "load", str(plist_path)],
-            ["launchctl", "start", "ai.hermes.gateway"],
+            ["launchctl", "start", label],
        ]

    def test_launchd_status_reports_local_stale_plist_when_unloaded(self, tmp_path, monkeypatch, capsys):
@@ -1,10 +1,13 @@
 """
-Tests for skip_confirm behavior in /skills install and /skills uninstall.
+Tests for skip_confirm and invalidate_cache behavior in /skills install
+and /skills uninstall slash commands.

-Verifies that --yes / -y bypasses the interactive confirmation prompt
-that hangs inside prompt_toolkit's TUI.
+Slash commands always skip confirmation (input() hangs in TUI).
+Cache invalidation is deferred by default; --now opts into immediate
+invalidation (at the cost of breaking prompt cache mid-session).

 Based on PR #1595 by 333Alden333 (salvaged).
+Updated for PR #3586 (cache-aware install/uninstall).
 """

 from unittest.mock import patch, MagicMock
@@ -32,23 +35,43 @@ class TestHandleSkillsSlashInstallFlags:
            _, kwargs = mock_install.call_args
            assert kwargs.get("skip_confirm") is True

-    def test_force_flag_sets_force_not_skip(self):
+    def test_force_flag_sets_force(self):
        from hermes_cli.skills_hub import handle_skills_slash
        with patch("hermes_cli.skills_hub.do_install") as mock_install:
            handle_skills_slash("/skills install test/skill --force")
            mock_install.assert_called_once()
            _, kwargs = mock_install.call_args
            assert kwargs.get("force") is True
-            assert kwargs.get("skip_confirm") is False
+            # Slash commands always skip confirmation (input() hangs in TUI)
+            assert kwargs.get("skip_confirm") is True

-    def test_no_flags(self):
+    def test_no_flags_still_skips_confirm(self):
+        """Slash commands always skip confirmation — input() hangs in TUI."""
        from hermes_cli.skills_hub import handle_skills_slash
        with patch("hermes_cli.skills_hub.do_install") as mock_install:
            handle_skills_slash("/skills install test/skill")
            mock_install.assert_called_once()
            _, kwargs = mock_install.call_args
            assert kwargs.get("force") is False
-            assert kwargs.get("skip_confirm") is False
+            assert kwargs.get("skip_confirm") is True
+
+    def test_default_defers_cache_invalidation(self):
+        """Without --now, cache invalidation is deferred to next session."""
+        from hermes_cli.skills_hub import handle_skills_slash
+        with patch("hermes_cli.skills_hub.do_install") as mock_install:
+            handle_skills_slash("/skills install test/skill")
+            mock_install.assert_called_once()
+            _, kwargs = mock_install.call_args
+            assert kwargs.get("invalidate_cache") is False
+
+    def test_now_flag_invalidates_cache(self):
+        """--now opts into immediate cache invalidation."""
+        from hermes_cli.skills_hub import handle_skills_slash
+        with patch("hermes_cli.skills_hub.do_install") as mock_install:
+            handle_skills_slash("/skills install test/skill --now")
+            mock_install.assert_called_once()
+            _, kwargs = mock_install.call_args
+            assert kwargs.get("invalidate_cache") is True


 class TestHandleSkillsSlashUninstallFlags:
@@ -70,13 +93,32 @@ class TestHandleSkillsSlashUninstallFlags:
            _, kwargs = mock_uninstall.call_args
            assert kwargs.get("skip_confirm") is True

-    def test_no_flags(self):
+    def test_no_flags_still_skips_confirm(self):
+        """Slash commands always skip confirmation — input() hangs in TUI."""
        from hermes_cli.skills_hub import handle_skills_slash
        with patch("hermes_cli.skills_hub.do_uninstall") as mock_uninstall:
            handle_skills_slash("/skills uninstall test-skill")
            mock_uninstall.assert_called_once()
            _, kwargs = mock_uninstall.call_args
-            assert kwargs.get("skip_confirm", False) is False
+            assert kwargs.get("skip_confirm") is True
+
+    def test_default_defers_cache_invalidation(self):
+        """Without --now, cache invalidation is deferred to next session."""
+        from hermes_cli.skills_hub import handle_skills_slash
+        with patch("hermes_cli.skills_hub.do_uninstall") as mock_uninstall:
+            handle_skills_slash("/skills uninstall test-skill")
+            mock_uninstall.assert_called_once()
+            _, kwargs = mock_uninstall.call_args
+            assert kwargs.get("invalidate_cache") is False
+
+    def test_now_flag_invalidates_cache(self):
+        """--now opts into immediate cache invalidation."""
+        from hermes_cli.skills_hub import handle_skills_slash
+        with patch("hermes_cli.skills_hub.do_uninstall") as mock_uninstall:
+            handle_skills_slash("/skills uninstall test-skill --now")
+            mock_uninstall.assert_called_once()
+            _, kwargs = mock_uninstall.call_args
+            assert kwargs.get("invalidate_cache") is True


 class TestDoInstallSkipConfirm:
@@ -237,3 +237,53 @@ def test_save_platform_tools_still_preserves_mcp_with_platform_default_present()

    # Deselected configurable toolset removed
    assert "terminal" not in saved
+
+
+# ── Platform / toolset consistency ────────────────────────────────────────────
+
+
+class TestPlatformToolsetConsistency:
+    """Every platform in tools_config.PLATFORMS must have a matching toolset."""
+
+    def test_all_platforms_have_toolset_definitions(self):
+        """Each platform's default_toolset must exist in TOOLSETS."""
+        from hermes_cli.tools_config import PLATFORMS
+        from toolsets import TOOLSETS
+
+        for platform, meta in PLATFORMS.items():
+            ts_name = meta["default_toolset"]
+            assert ts_name in TOOLSETS, (
+                f"Platform {platform!r} references toolset {ts_name!r} "
+                f"which is not defined in toolsets.py"
+            )
+
+    def test_gateway_toolset_includes_all_messaging_platforms(self):
+        """hermes-gateway includes list should cover all messaging platforms."""
+        from hermes_cli.tools_config import PLATFORMS
+        from toolsets import TOOLSETS
+
+        gateway_includes = set(TOOLSETS["hermes-gateway"]["includes"])
+        # Exclude non-messaging platforms from the check
+        non_messaging = {"cli", "api_server"}
+        for platform, meta in PLATFORMS.items():
+            if platform in non_messaging:
+                continue
+            ts_name = meta["default_toolset"]
+            assert ts_name in gateway_includes, (
+                f"Platform {platform!r} toolset {ts_name!r} missing from "
+                f"hermes-gateway includes"
+            )
+
+    def test_skills_config_covers_tools_config_platforms(self):
+        """skills_config.PLATFORMS should have entries for all gateway platforms."""
+        from hermes_cli.tools_config import PLATFORMS as TOOLS_PLATFORMS
+        from hermes_cli.skills_config import PLATFORMS as SKILLS_PLATFORMS
+
+        non_messaging = {"api_server"}
+        for platform in TOOLS_PLATFORMS:
+            if platform in non_messaging:
+                continue
+            assert platform in SKILLS_PLATFORMS, (
+                f"Platform {platform!r} in tools_config but missing from "
+                f"skills_config PLATFORMS"
+            )
@@ -101,6 +101,69 @@ class TestLaunchdPlistReplace:
        assert replace_idx == run_idx + 1


+class TestLaunchdPlistPath:
+    def test_plist_contains_environment_variables(self):
+        plist = gateway_cli.generate_launchd_plist()
+        assert "<key>EnvironmentVariables</key>" in plist
+        assert "<key>PATH</key>" in plist
+        assert "<key>VIRTUAL_ENV</key>" in plist
+        assert "<key>HERMES_HOME</key>" in plist
+
+    def test_plist_path_includes_venv_bin(self):
+        plist = gateway_cli.generate_launchd_plist()
+        detected = gateway_cli._detect_venv_dir()
+        venv_bin = str(detected / "bin") if detected else str(gateway_cli.PROJECT_ROOT / "venv" / "bin")
+        assert venv_bin in plist
+
+    def test_plist_path_starts_with_venv_bin(self):
+        plist = gateway_cli.generate_launchd_plist()
+        lines = plist.splitlines()
+        for i, line in enumerate(lines):
+            if "<key>PATH</key>" in line.strip():
+                path_value = lines[i + 1].strip()
+                path_value = path_value.replace("<string>", "").replace("</string>", "")
+                detected = gateway_cli._detect_venv_dir()
+                venv_bin = str(detected / "bin") if detected else str(gateway_cli.PROJECT_ROOT / "venv" / "bin")
+                assert path_value.startswith(venv_bin + ":")
+                break
+        else:
+            raise AssertionError("PATH key not found in plist")
+
+    def test_plist_path_includes_node_modules_bin(self):
+        plist = gateway_cli.generate_launchd_plist()
+        node_bin = str(gateway_cli.PROJECT_ROOT / "node_modules" / ".bin")
+        lines = plist.splitlines()
+        for i, line in enumerate(lines):
+            if "<key>PATH</key>" in line.strip():
+                path_value = lines[i + 1].strip()
+                path_value = path_value.replace("<string>", "").replace("</string>", "")
+                assert node_bin in path_value.split(":")
+                break
+        else:
+            raise AssertionError("PATH key not found in plist")
+
+    def test_plist_path_includes_current_env_path(self, monkeypatch):
+        monkeypatch.setenv("PATH", "/custom/bin:/usr/bin:/bin")
+        plist = gateway_cli.generate_launchd_plist()
+        assert "/custom/bin" in plist
+
+    def test_plist_path_deduplicates_venv_bin_when_already_in_path(self, monkeypatch):
+        detected = gateway_cli._detect_venv_dir()
+        venv_bin = str(detected / "bin") if detected else str(gateway_cli.PROJECT_ROOT / "venv" / "bin")
+        monkeypatch.setenv("PATH", f"{venv_bin}:/usr/bin:/bin")
+        plist = gateway_cli.generate_launchd_plist()
+        lines = plist.splitlines()
+        for i, line in enumerate(lines):
+            if "<key>PATH</key>" in line.strip():
+                path_value = lines[i + 1].strip()
+                path_value = path_value.replace("<string>", "").replace("</string>", "")
+                parts = path_value.split(":")
+                assert parts.count(venv_bin) == 1
+                break
+        else:
+            raise AssertionError("PATH key not found in plist")
+
+
 # ---------------------------------------------------------------------------
 # cmd_update — macOS launchd detection
 # ---------------------------------------------------------------------------
@@ -177,6 +240,33 @@ class TestLaunchdPlistRefresh:
        assert any("unload" in s for s in cmd_strs)
        assert any("start" in s for s in cmd_strs)

+    def test_launchd_start_recreates_missing_plist_and_loads_service(self, tmp_path, monkeypatch):
+        """launchd_start self-heals when the plist file is missing entirely."""
+        plist_path = tmp_path / "ai.hermes.gateway.plist"
+        assert not plist_path.exists()
+
+        monkeypatch.setattr(gateway_cli, "get_launchd_plist_path", lambda: plist_path)
+
+        calls = []
+        def fake_run(cmd, check=False, **kwargs):
+            calls.append(cmd)
+            return SimpleNamespace(returncode=0, stdout="", stderr="")
+
+        monkeypatch.setattr(gateway_cli.subprocess, "run", fake_run)
+
+        gateway_cli.launchd_start()
+
+        # Should have created the plist
+        assert plist_path.exists()
+        assert "--replace" in plist_path.read_text()
+
+        cmd_strs = [" ".join(c) for c in calls]
+        # Should load the new plist, then start
+        assert any("load" in s for s in cmd_strs)
+        assert any("start" in s for s in cmd_strs)
+        # Should NOT call unload (nothing to unload)
+        assert not any("unload" in s for s in cmd_strs)
+

 class TestCmdUpdateLaunchdRestart:
    """cmd_update correctly detects and handles launchd on macOS."""
@@ -0,0 +1,189 @@
+"""Tests for hermes_cli/webhook.py — webhook subscription CLI."""
+
+import json
+import os
+import pytest
+from argparse import Namespace
+from pathlib import Path
+
+from hermes_cli.webhook import (
+    webhook_command,
+    _load_subscriptions,
+    _save_subscriptions,
+    _subscriptions_path,
+    _is_webhook_enabled,
+)
+
+
+@pytest.fixture(autouse=True)
+def _isolate(tmp_path, monkeypatch):
+    monkeypatch.setenv("HERMES_HOME", str(tmp_path))
+    # Default: webhooks enabled (most tests need this)
+    monkeypatch.setattr(
+        "hermes_cli.webhook._is_webhook_enabled", lambda: True
+    )
+
+
+def _make_args(**kwargs):
+    defaults = {
+        "webhook_action": None,
+        "name": "",
+        "prompt": "",
+        "events": "",
+        "description": "",
+        "skills": "",
+        "deliver": "log",
+        "deliver_chat_id": "",
+        "secret": "",
+        "payload": "",
+    }
+    defaults.update(kwargs)
+    return Namespace(**defaults)
+
+
+class TestSubscribe:
+    def test_basic_create(self, capsys):
+        webhook_command(_make_args(webhook_action="subscribe", name="test-hook"))
+        out = capsys.readouterr().out
+        assert "Created" in out
+        assert "/webhooks/test-hook" in out
+        subs = _load_subscriptions()
+        assert "test-hook" in subs
+
+    def test_with_options(self, capsys):
+        webhook_command(_make_args(
+            webhook_action="subscribe",
+            name="gh-issues",
+            events="issues,pull_request",
+            prompt="Issue: {issue.title}",
+            deliver="telegram",
+            deliver_chat_id="12345",
+            description="Watch GitHub",
+        ))
+        subs = _load_subscriptions()
+        route = subs["gh-issues"]
+        assert route["events"] == ["issues", "pull_request"]
+        assert route["prompt"] == "Issue: {issue.title}"
+        assert route["deliver"] == "telegram"
+        assert route["deliver_extra"] == {"chat_id": "12345"}
+
+    def test_custom_secret(self):
+        webhook_command(_make_args(
+            webhook_action="subscribe", name="s", secret="my-secret"
+        ))
+        assert _load_subscriptions()["s"]["secret"] == "my-secret"
+
+    def test_auto_secret(self):
+        webhook_command(_make_args(webhook_action="subscribe", name="s"))
+        secret = _load_subscriptions()["s"]["secret"]
+        assert len(secret) > 20
+
+    def test_update(self, capsys):
+        webhook_command(_make_args(webhook_action="subscribe", name="x", prompt="v1"))
+        webhook_command(_make_args(webhook_action="subscribe", name="x", prompt="v2"))
+        out = capsys.readouterr().out
+        assert "Updated" in out
+        assert _load_subscriptions()["x"]["prompt"] == "v2"
+
+    def test_invalid_name(self, capsys):
+        webhook_command(_make_args(webhook_action="subscribe", name="bad name!"))
+        out = capsys.readouterr().out
+        assert "Error" in out or "Invalid" in out
+        assert _load_subscriptions() == {}
+
+
+class TestList:
+    def test_empty(self, capsys):
+        webhook_command(_make_args(webhook_action="list"))
+        out = capsys.readouterr().out
+        assert "No dynamic" in out
+
+    def test_with_entries(self, capsys):
+        webhook_command(_make_args(webhook_action="subscribe", name="a"))
+        webhook_command(_make_args(webhook_action="subscribe", name="b"))
+        capsys.readouterr()  # clear
+        webhook_command(_make_args(webhook_action="list"))
+        out = capsys.readouterr().out
+        assert "2 webhook" in out
+        assert "a" in out
+        assert "b" in out
+
+
+class TestRemove:
+    def test_remove_existing(self, capsys):
+        webhook_command(_make_args(webhook_action="subscribe", name="temp"))
+        webhook_command(_make_args(webhook_action="remove", name="temp"))
+        out = capsys.readouterr().out
+        assert "Removed" in out
+        assert _load_subscriptions() == {}
+
+    def test_remove_nonexistent(self, capsys):
+        webhook_command(_make_args(webhook_action="remove", name="nope"))
+        out = capsys.readouterr().out
+        assert "No subscription" in out
+
+    def test_selective_remove(self):
+        webhook_command(_make_args(webhook_action="subscribe", name="keep"))
+        webhook_command(_make_args(webhook_action="subscribe", name="drop"))
+        webhook_command(_make_args(webhook_action="remove", name="drop"))
+        subs = _load_subscriptions()
+        assert "keep" in subs
+        assert "drop" not in subs
+
+
+class TestPersistence:
+    def test_file_written(self):
+        webhook_command(_make_args(webhook_action="subscribe", name="persist"))
+        path = _subscriptions_path()
+        assert path.exists()
+        data = json.loads(path.read_text())
+        assert "persist" in data
+
+    def test_corrupted_file(self):
+        path = _subscriptions_path()
+        path.parent.mkdir(parents=True, exist_ok=True)
+        path.write_text("broken{{{")
+        assert _load_subscriptions() == {}
+
+
+class TestWebhookEnabledGate:
+    def test_blocks_when_disabled(self, capsys, monkeypatch):
+        monkeypatch.setattr("hermes_cli.webhook._is_webhook_enabled", lambda: False)
+        webhook_command(_make_args(webhook_action="subscribe", name="blocked"))
+        out = capsys.readouterr().out
+        assert "not enabled" in out.lower()
+        assert "hermes gateway setup" in out
+        assert _load_subscriptions() == {}
+
+    def test_blocks_list_when_disabled(self, capsys, monkeypatch):
+        monkeypatch.setattr("hermes_cli.webhook._is_webhook_enabled", lambda: False)
+        webhook_command(_make_args(webhook_action="list"))
+        out = capsys.readouterr().out
+        assert "not enabled" in out.lower()
+
+    def test_allows_when_enabled(self, capsys):
+        # _is_webhook_enabled already patched to True by autouse fixture
+        webhook_command(_make_args(webhook_action="subscribe", name="allowed"))
+        out = capsys.readouterr().out
+        assert "Created" in out
+        assert "allowed" in _load_subscriptions()
+
+    def test_real_check_disabled(self, monkeypatch):
+        monkeypatch.setattr(
+            "hermes_cli.webhook._get_webhook_config",
+            lambda: {},
+        )
+        monkeypatch.setattr(
+            "hermes_cli.webhook._is_webhook_enabled",
+            lambda: bool({}.get("enabled")),
+        )
+        import hermes_cli.webhook as wh_mod
+        assert wh_mod._is_webhook_enabled() is False
+
+    def test_real_check_enabled(self, monkeypatch):
+        monkeypatch.setattr(
+            "hermes_cli.webhook._is_webhook_enabled",
+            lambda: True,
+        )
+        import hermes_cli.webhook as wh_mod
+        assert wh_mod._is_webhook_enabled() is True
@@ -0,0 +1,154 @@
+"""Tests for percentage clamping at 100% across display paths.
+
+PR #3480 capped context pressure percentage at 100% in agent/display.py
+but missed the same unclamped pattern in 4 other files. When token counts
+overshoot the context length (possible during streaming or before
+compression fires), users see >100% in /stats, gateway status, and
+memory tool output.
+"""
+
+import pytest
+
+
+class TestContextCompressorUsagePercent:
+    """agent/context_compressor.py — get_status() usage_percent"""
+
+    def test_usage_percent_capped_at_100(self):
+        """Tokens exceeding context_length should still show max 100%."""
+        from agent.context_compressor import ContextCompressor
+
+        comp = ContextCompressor.__new__(ContextCompressor)
+        comp.last_prompt_tokens = 210_000  # exceeds context_length
+        comp.context_length = 200_000
+        comp.threshold_tokens = 160_000
+        comp.compression_count = 0
+
+        status = comp.get_status()
+        assert status["usage_percent"] <= 100
+
+    def test_usage_percent_normal(self):
+        """Normal usage should show correct percentage."""
+        from agent.context_compressor import ContextCompressor
+
+        comp = ContextCompressor.__new__(ContextCompressor)
+        comp.last_prompt_tokens = 100_000
+        comp.context_length = 200_000
+        comp.threshold_tokens = 160_000
+        comp.compression_count = 0
+
+        status = comp.get_status()
+        assert status["usage_percent"] == 50.0
+
+    def test_usage_percent_zero_context_length(self):
+        """Zero context_length should return 0, not crash."""
+        from agent.context_compressor import ContextCompressor
+
+        comp = ContextCompressor.__new__(ContextCompressor)
+        comp.last_prompt_tokens = 1000
+        comp.context_length = 0
+        comp.threshold_tokens = 0
+        comp.compression_count = 0
+
+        status = comp.get_status()
+        assert status["usage_percent"] == 0
+
+
+class TestMemoryToolPercentClamp:
+    """tools/memory_tool.py — _success_response and _render_block pct"""
+
+    def test_over_limit_clamped_at_100(self):
+        """Percentage should be capped at 100 even if current > limit."""
+        # Simulate the calculation directly
+        current = 5500
+        limit = 5000
+        pct = min(100, int((current / limit) * 100)) if limit > 0 else 0
+        assert pct == 100
+
+    def test_normal_percentage(self):
+        current = 2500
+        limit = 5000
+        pct = min(100, int((current / limit) * 100)) if limit > 0 else 0
+        assert pct == 50
+
+    def test_zero_limit_returns_zero(self):
+        current = 100
+        limit = 0
+        pct = min(100, int((current / limit) * 100)) if limit > 0 else 0
+        assert pct == 0
+
+
+class TestCLIStatsPercentClamp:
+    """cli.py — /stats command percentage"""
+
+    def test_over_context_clamped_at_100(self):
+        """Tokens exceeding context_length should show max 100%."""
+        last_prompt = 210_000
+        ctx_len = 200_000
+        pct = min(100, (last_prompt / ctx_len * 100)) if ctx_len else 0
+        assert pct == 100
+
+    def test_normal_context(self):
+        last_prompt = 100_000
+        ctx_len = 200_000
+        pct = min(100, (last_prompt / ctx_len * 100)) if ctx_len else 0
+        assert pct == 50.0
+
+    def test_zero_context_length(self):
+        last_prompt = 1000
+        ctx_len = 0
+        pct = min(100, (last_prompt / ctx_len * 100)) if ctx_len else 0
+        assert pct == 0
+
+
+class TestGatewayStatsPercentClamp:
+    """gateway/run.py — _format_usage_stats percentage"""
+
+    def test_over_context_clamped_at_100(self):
+        last_prompt_tokens = 210_000
+        context_length = 200_000
+        pct = min(100, last_prompt_tokens / context_length * 100) if context_length else 0
+        assert pct == 100
+
+    def test_normal_context(self):
+        last_prompt_tokens = 150_000
+        context_length = 200_000
+        pct = min(100, last_prompt_tokens / context_length * 100) if context_length else 0
+        assert pct == 75.0
+
+
+class TestSourceLinesAreClamped:
+    """Verify the actual source files have min(100, ...) applied."""
+
+    @staticmethod
+    def _read_file(rel_path: str) -> str:
+        import os
+        base = os.path.dirname(os.path.dirname(__file__))
+        with open(os.path.join(base, rel_path)) as f:
+            return f.read()
+
+    def test_context_compressor_clamped(self):
+        src = self._read_file("agent/context_compressor.py")
+        assert "min(100," in src, (
+            "context_compressor.py usage_percent is not clamped with min(100, ...)"
+        )
+
+    def test_gateway_run_clamped(self):
+        src = self._read_file("gateway/run.py")
+        # Check that the stats handler has min(100, ...)
+        assert "min(100, ctx.last_prompt_tokens" in src, (
+            "gateway/run.py stats pct is not clamped with min(100, ...)"
+        )
+
+    def test_cli_clamped(self):
+        src = self._read_file("cli.py")
+        assert "min(100, (last_prompt" in src, (
+            "cli.py /stats pct is not clamped with min(100, ...)"
+        )
+
+    def test_memory_tool_clamped(self):
+        src = self._read_file("tools/memory_tool.py")
+        # Both _success_response and _render_block should have min(100, ...)
+        count = src.count("min(100, int((current / limit)")
+        assert count >= 2, (
+            f"memory_tool.py has only {count} clamped pct lines, expected >= 2"
+        )
@@ -2793,6 +2793,50 @@ class TestStreamingApiCall:
        assert tc[0].function.name == "search"
        assert tc[1].function.name == "read"

+    def test_ollama_reused_index_separate_tool_calls(self, agent):
+        """Ollama sends every tool call at index 0 with different ids.
+
+        Without the fix, names and arguments get concatenated into one slot.
+        """
+        chunks = [
+            _make_chunk(tool_calls=[_make_tc_delta(0, "call_a", "search", '{"q":"hello"}')]),
+            # Second tool call at the SAME index 0, but different id
+            _make_chunk(tool_calls=[_make_tc_delta(0, "call_b", "read_file", '{"path":"x.py"}')]),
+            _make_chunk(finish_reason="tool_calls"),
+        ]
+        agent.client.chat.completions.create.return_value = iter(chunks)
+
+        resp = agent._interruptible_streaming_api_call({"messages": []})
+
+        tc = resp.choices[0].message.tool_calls
+        assert len(tc) == 2, f"Expected 2 tool calls, got {len(tc)}: {[t.function.name for t in tc]}"
+        assert tc[0].function.name == "search"
+        assert tc[0].function.arguments == '{"q":"hello"}'
+        assert tc[0].id == "call_a"
+        assert tc[1].function.name == "read_file"
+        assert tc[1].function.arguments == '{"path":"x.py"}'
+        assert tc[1].id == "call_b"
+
+    def test_ollama_reused_index_streamed_args(self, agent):
+        """Ollama with streamed arguments across multiple chunks at same index."""
+        chunks = [
+            _make_chunk(tool_calls=[_make_tc_delta(0, "call_a", "search", '{"q":')]),
+            _make_chunk(tool_calls=[_make_tc_delta(0, None, None, '"hello"}')]),
+            # New tool call, same index 0
+            _make_chunk(tool_calls=[_make_tc_delta(0, "call_b", "read", '{}')]),
+            _make_chunk(finish_reason="tool_calls"),
+        ]
+        agent.client.chat.completions.create.return_value = iter(chunks)
+
+        resp = agent._interruptible_streaming_api_call({"messages": []})
+
+        tc = resp.choices[0].message.tool_calls
+        assert len(tc) == 2
+        assert tc[0].function.name == "search"
+        assert tc[0].function.arguments == '{"q":"hello"}'
+        assert tc[1].function.name == "read"
+        assert tc[1].function.arguments == '{}'
+
    def test_content_and_tool_calls_together(self, agent):
        chunks = [
            _make_chunk(content="I'll search"),
@@ -362,9 +362,11 @@ class TestStreamingCallbacks:

        # Text before tool call IS fired (we don't know yet it will have tools)
        assert "thinking..." in deltas
-        # Text after tool call is NOT fired
-        assert " more text" not in deltas
-        # But content is still accumulated in the response
+        # Text after tool call IS still routed to stream_delta_callback so that
+        # reasoning tag extraction can fire (PR #3566).  Display-level suppression
+        # of non-reasoning text happens in the CLI's _stream_delta, not here.
+        assert " more text" in deltas
+        # Content is still accumulated in the response
        assert response.choices[0].message.content == "thinking... more text"


@@ -0,0 +1,154 @@
+"""Tests for surrogate character sanitization in user input.
+
+Surrogates (U+D800..U+DFFF) are invalid in UTF-8 and crash json.dumps()
+inside the OpenAI SDK. They can appear via clipboard paste from rich-text
+editors like Google Docs.
+"""
+import json
+import pytest
+from unittest.mock import MagicMock, patch
+
+from run_agent import (
+    _sanitize_surrogates,
+    _sanitize_messages_surrogates,
+    _SURROGATE_RE,
+)
+
+
+class TestSanitizeSurrogates:
+    """Test the _sanitize_surrogates() helper."""
+
+    def test_normal_text_unchanged(self):
+        text = "Hello, this is normal text with unicode: café ñ 日本語 🎉"
+        assert _sanitize_surrogates(text) == text
+
+    def test_empty_string(self):
+        assert _sanitize_surrogates("") == ""
+
+    def test_single_surrogate_replaced(self):
+        result = _sanitize_surrogates("Hello \udce2 world")
+        assert result == "Hello \ufffd world"
+
+    def test_multiple_surrogates_replaced(self):
+        result = _sanitize_surrogates("a\ud800b\udc00c\udfff")
+        assert result == "a\ufffdb\ufffdc\ufffd"
+
+    def test_all_surrogate_range(self):
+        """Verify the regex catches the full surrogate range."""
+        for cp in [0xD800, 0xD900, 0xDA00, 0xDB00, 0xDC00, 0xDD00, 0xDE00, 0xDF00, 0xDFFF]:
+            text = f"test{chr(cp)}end"
+            result = _sanitize_surrogates(text)
+            assert '\ufffd' in result, f"Surrogate U+{cp:04X} not caught"
+
+    def test_result_is_json_serializable(self):
+        """Sanitized text must survive json.dumps + utf-8 encoding."""
+        dirty = "data \udce2\udcb0 from clipboard"
+        clean = _sanitize_surrogates(dirty)
+        serialized = json.dumps({"content": clean}, ensure_ascii=False)
+        # Must not raise UnicodeEncodeError
+        serialized.encode("utf-8")
+
+    def test_original_surrogates_fail_encoding(self):
+        """Confirm the original bug: surrogates crash utf-8 encoding."""
+        dirty = "data \udce2 from clipboard"
+        serialized = json.dumps({"content": dirty}, ensure_ascii=False)
+        with pytest.raises(UnicodeEncodeError):
+            serialized.encode("utf-8")
+
+
+class TestSanitizeMessagesSurrogates:
+    """Test the _sanitize_messages_surrogates() helper for message lists."""
+
+    def test_clean_messages_returns_false(self):
+        msgs = [
+            {"role": "user", "content": "all clean"},
+            {"role": "assistant", "content": "me too"},
+        ]
+        assert _sanitize_messages_surrogates(msgs) is False
+
+    def test_dirty_string_content_sanitized(self):
+        msgs = [
+            {"role": "user", "content": "text with \udce2 surrogate"},
+        ]
+        assert _sanitize_messages_surrogates(msgs) is True
+        assert "\ufffd" in msgs[0]["content"]
+        assert "\udce2" not in msgs[0]["content"]
+
+    def test_dirty_multimodal_content_sanitized(self):
+        msgs = [
+            {"role": "user", "content": [
+                {"type": "text", "text": "multimodal \udce2 content"},
+                {"type": "image_url", "image_url": {"url": "http://example.com"}},
+            ]},
+        ]
+        assert _sanitize_messages_surrogates(msgs) is True
+        assert "\ufffd" in msgs[0]["content"][0]["text"]
+        assert "\udce2" not in msgs[0]["content"][0]["text"]
+
+    def test_mixed_clean_and_dirty(self):
+        msgs = [
+            {"role": "user", "content": "clean text"},
+            {"role": "user", "content": "dirty \udce2 text"},
+            {"role": "assistant", "content": "clean response"},
+        ]
+        assert _sanitize_messages_surrogates(msgs) is True
+        assert msgs[0]["content"] == "clean text"
+        assert "\ufffd" in msgs[1]["content"]
+        assert msgs[2]["content"] == "clean response"
+
+    def test_non_dict_items_skipped(self):
+        msgs = ["not a dict", {"role": "user", "content": "ok"}]
+        assert _sanitize_messages_surrogates(msgs) is False
+
+    def test_tool_messages_sanitized(self):
+        """Tool results could also contain surrogates from file reads etc."""
+        msgs = [
+            {"role": "tool", "content": "result with \udce2 data", "tool_call_id": "x"},
+        ]
+        assert _sanitize_messages_surrogates(msgs) is True
+        assert "\ufffd" in msgs[0]["content"]
+
+
+class TestRunConversationSurrogateSanitization:
+    """Integration: verify run_conversation sanitizes user_message."""
+
+    @patch("run_agent.AIAgent._build_system_prompt")
+    @patch("run_agent.AIAgent._interruptible_streaming_api_call")
+    @patch("run_agent.AIAgent._interruptible_api_call")
+    def test_user_message_surrogates_sanitized(self, mock_api, mock_stream, mock_sys):
+        """Surrogates in user_message are stripped before API call."""
+        from run_agent import AIAgent
+
+        mock_sys.return_value = "system prompt"
+
+        # Mock streaming to return a simple response
+        mock_choice = MagicMock()
+        mock_choice.message.content = "response"
+        mock_choice.message.tool_calls = None
+        mock_choice.message.refusal = None
+        mock_choice.finish_reason = "stop"
+        mock_choice.message.reasoning_content = None
+
+        mock_response = MagicMock()
+        mock_response.choices = [mock_choice]
+        mock_response.usage = MagicMock(prompt_tokens=10, completion_tokens=5, total_tokens=15)
+        mock_response.model = "test-model"
+        mock_response.id = "test-id"
+
+        mock_stream.return_value = mock_response
+        mock_api.return_value = mock_response
+
+        agent = AIAgent(model="test/model", quiet_mode=True, skip_memory=True, skip_context_files=True)
+        agent.client = MagicMock()
+
+        # Pass a message with surrogates
+        result = agent.run_conversation(
+            user_message="test \udce2 message",
+            conversation_history=[],
+        )
+
+        # The message stored in history should have surrogates replaced
+        for msg in result.get("messages", []):
+            if msg.get("role") == "user":
+                assert "\udce2" not in msg["content"], "Surrogate leaked into stored message"
+                assert "\ufffd" in msg["content"], "Replacement char not in stored message"
@@ -512,6 +512,30 @@ class TestGatewayProtection:
        dangerous, key, desc = detect_dangerous_command(cmd)
        assert dangerous is False

+    def test_pkill_hermes_detected(self):
+        """pkill targeting hermes/gateway processes must be caught."""
+        cmd = 'pkill -f "cli.py --gateway"'
+        dangerous, key, desc = detect_dangerous_command(cmd)
+        assert dangerous is True
+        assert "self-termination" in desc
+
+    def test_killall_hermes_detected(self):
+        cmd = "killall hermes"
+        dangerous, key, desc = detect_dangerous_command(cmd)
+        assert dangerous is True
+        assert "self-termination" in desc
+
+    def test_pkill_gateway_detected(self):
+        cmd = "pkill -f gateway"
+        dangerous, key, desc = detect_dangerous_command(cmd)
+        assert dangerous is True
+
+    def test_pkill_unrelated_not_flagged(self):
+        """pkill targeting unrelated processes should not be flagged."""
+        cmd = "pkill -f nginx"
+        dangerous, key, desc = detect_dangerous_command(cmd)
+        assert dangerous is False
+

 class TestNormalizationBypass:
    """Obfuscation techniques must not bypass dangerous command detection."""
@@ -0,0 +1,109 @@
+"""Tests for None guard on browser_tool LLM response content.
+
+browser_tool.py has two call sites that access response.choices[0].message.content
+without checking for None — _extract_relevant_content (line 996) and
+browser_vision (line 1626). When reasoning-only models (DeepSeek-R1, QwQ)
+return content=None, these produce null snapshots or null analysis.
+
+These tests verify both sites are guarded.
+"""
+
+import types
+from unittest.mock import MagicMock, patch
+
+import pytest
+
+
+# ── helpers ────────────────────────────────────────────────────────────────
+
+def _make_response(content):
+    """Build a minimal OpenAI-compatible ChatCompletion response stub."""
+    message = types.SimpleNamespace(content=content)
+    choice = types.SimpleNamespace(message=message)
+    return types.SimpleNamespace(choices=[choice])
+
+
+# ── _extract_relevant_content (line 996) ──────────────────────────────────
+
+class TestExtractRelevantContentNoneGuard:
+    """tools/browser_tool.py — _extract_relevant_content()"""
+
+    def test_none_content_falls_back_to_truncated(self):
+        """When LLM returns None content, should fall back to truncated snapshot."""
+        with patch("tools.browser_tool.call_llm", return_value=_make_response(None)), \
+             patch("tools.browser_tool._get_extraction_model", return_value="test-model"):
+            from tools.browser_tool import _extract_relevant_content
+            result = _extract_relevant_content("This is a long snapshot text", "find the button")
+
+        assert result is not None
+        assert isinstance(result, str)
+        assert len(result) > 0
+
+    def test_normal_content_returned(self):
+        """Normal string content should pass through."""
+        with patch("tools.browser_tool.call_llm", return_value=_make_response("Extracted content here")), \
+             patch("tools.browser_tool._get_extraction_model", return_value="test-model"):
+            from tools.browser_tool import _extract_relevant_content
+            result = _extract_relevant_content("snapshot text", "task")
+
+        assert result == "Extracted content here"
+
+    def test_empty_string_content_falls_back(self):
+        """Empty string content should also fall back to truncated."""
+        with patch("tools.browser_tool.call_llm", return_value=_make_response("   ")), \
+             patch("tools.browser_tool._get_extraction_model", return_value="test-model"):
+            from tools.browser_tool import _extract_relevant_content
+            result = _extract_relevant_content("This is a long snapshot text", "task")
+
+        assert result is not None
+        assert len(result) > 0
+
+
+# ── browser_vision (line 1626) ────────────────────────────────────────────
+
+class TestBrowserVisionNoneGuard:
+    """tools/browser_tool.py — browser_vision() analysis extraction"""
+
+    def test_none_content_produces_fallback_message(self):
+        """When LLM returns None content, analysis should have a fallback message."""
+        response = _make_response(None)
+        analysis = (response.choices[0].message.content or "").strip()
+        fallback = analysis or "Vision analysis returned no content."
+
+        assert fallback == "Vision analysis returned no content."
+
+    def test_normal_content_passes_through(self):
+        """Normal analysis content should pass through unchanged."""
+        response = _make_response("  The page shows a login form.  ")
+        analysis = (response.choices[0].message.content or "").strip()
+        fallback = analysis or "Vision analysis returned no content."
+
+        assert fallback == "The page shows a login form."
+
+
+# ── source line verification ──────────────────────────────────────────────
+
+class TestBrowserSourceLinesAreGuarded:
+    """Verify the actual source file has the fix applied."""
+
+    @staticmethod
+    def _read_file() -> str:
+        import os
+        base = os.path.dirname(os.path.dirname(os.path.dirname(__file__)))
+        with open(os.path.join(base, "tools", "browser_tool.py")) as f:
+            return f.read()
+
+    def test_extract_relevant_content_guarded(self):
+        src = self._read_file()
+        # The old unguarded pattern should NOT exist
+        assert "return response.choices[0].message.content\n" not in src, (
+            "browser_tool.py _extract_relevant_content still has unguarded "
+            ".content return — apply None guard"
+        )
+
+    def test_browser_vision_guarded(self):
+        src = self._read_file()
+        assert "analysis = response.choices[0].message.content\n" not in src, (
+            "browser_tool.py browser_vision still has unguarded "
+            ".content assignment — apply None guard"
+        )
@@ -63,6 +63,18 @@ class TestLocalOneShotRegression:
        assert r["output"].strip() == ""
        env.cleanup()

+    def test_oneshot_heredoc_does_not_leak_fence_wrapper(self):
+        """Heredoc closing line must not be merged with the fence wrapper tail."""
+        env = LocalEnvironment(persistent=False)
+        cmd = "cat <<'H_EOF'\nheredoc body line\nH_EOF"
+        r = env.execute(cmd)
+        env.cleanup()
+        assert r["returncode"] == 0
+        assert "heredoc body line" in r["output"]
+        assert "__hermes_rc" not in r["output"]
+        assert "printf '" not in r["output"]
+        assert "exit $" not in r["output"]
+

 class TestLocalPersistent:
    @pytest.fixture
@@ -63,6 +63,35 @@ class TestSkillViewRegistersPassthrough:
        assert result["success"] is True
        assert is_env_passthrough("TENOR_API_KEY")

+    def test_remote_backend_persisted_env_vars_registered(self, tmp_path, monkeypatch):
+        """Remote-backed skills still register locally available env vars."""
+        monkeypatch.setenv("TERMINAL_ENV", "docker")
+        _create_skill(
+            tmp_path,
+            "test-skill",
+            frontmatter_extra=(
+                "required_environment_variables:\n"
+                "  - name: TENOR_API_KEY\n"
+                "    prompt: Enter your Tenor API key\n"
+            ),
+        )
+        monkeypatch.setattr("tools.skills_tool.SKILLS_DIR", tmp_path)
+
+        from hermes_cli.config import save_env_value
+
+        save_env_value("TENOR_API_KEY", "persisted-value-123")
+        monkeypatch.delenv("TENOR_API_KEY", raising=False)
+
+        with patch("tools.skills_tool._secret_capture_callback", None):
+            from tools.skills_tool import skill_view
+
+            result = json.loads(skill_view(name="test-skill"))
+
+        assert result["success"] is True
+        assert result["setup_needed"] is False
+        assert result["missing_required_environment_variables"] == []
+        assert is_env_passthrough("TENOR_API_KEY")
+
    def test_missing_env_vars_not_registered(self, tmp_path, monkeypatch):
        """When a skill declares required_environment_variables but the var is NOT set,
        it should NOT be registered in the passthrough."""
@@ -813,6 +813,29 @@ class TestSkillViewPrerequisites:
        assert result["setup_needed"] is False
        assert result["missing_required_environment_variables"] == []

+    def test_remote_backend_treats_persisted_env_as_available(
+        self, tmp_path, monkeypatch
+    ):
+        monkeypatch.setenv("TERMINAL_ENV", "docker")
+
+        with patch("tools.skills_tool.SKILLS_DIR", tmp_path):
+            _make_skill(
+                tmp_path,
+                "remote-ready",
+                frontmatter_extra="prerequisites:\n  env_vars: [PERSISTED_REMOTE_KEY]\n",
+            )
+            from hermes_cli.config import save_env_value
+
+            save_env_value("PERSISTED_REMOTE_KEY", "persisted-value")
+            monkeypatch.delenv("PERSISTED_REMOTE_KEY", raising=False)
+            raw = skill_view("remote-ready")
+
+        result = json.loads(raw)
+        assert result["success"] is True
+        assert result["setup_needed"] is False
+        assert result["missing_required_environment_variables"] == []
+        assert result["readiness_status"] == "available"
+
    def test_no_setup_metadata_when_no_required_envs(self, tmp_path):
        with patch("tools.skills_tool.SKILLS_DIR", tmp_path):
            _make_skill(tmp_path, "plain-skill")
@@ -878,17 +901,11 @@ class TestSkillViewPrerequisites:
        assert result["setup_needed"] is True

    @pytest.mark.parametrize(
-        "backend,expected_note",
-        [
-            ("ssh", "remote environment"),
-            ("daytona", "remote environment"),
-            ("docker", "docker-backed skills"),
-            ("singularity", "singularity-backed skills"),
-            ("modal", "modal-backed skills"),
-        ],
+        "backend",
+        ["ssh", "daytona", "docker", "singularity", "modal"],
    )
-    def test_remote_backend_keeps_setup_needed_after_local_secret_capture(
-        self, tmp_path, monkeypatch, backend, expected_note
+    def test_remote_backend_becomes_available_after_local_secret_capture(
+        self, tmp_path, monkeypatch, backend
    ):
        monkeypatch.setenv("TERMINAL_ENV", backend)
        monkeypatch.delenv("TENOR_API_KEY", raising=False)
@@ -926,10 +943,10 @@ class TestSkillViewPrerequisites:
        result = json.loads(raw)
        assert result["success"] is True
        assert len(calls) == 1
-        assert result["setup_needed"] is True
-        assert result["readiness_status"] == "setup_needed"
-        assert result["missing_required_environment_variables"] == ["TENOR_API_KEY"]
-        assert expected_note in result["setup_note"].lower()
+        assert result["setup_needed"] is False
+        assert result["readiness_status"] == "available"
+        assert result["missing_required_environment_variables"] == []
+        assert "setup_note" not in result

    def test_skill_view_surfaces_skill_read_errors(self, tmp_path, monkeypatch):
        with patch("tools.skills_tool.SKILLS_DIR", tmp_path):
@@ -53,6 +53,8 @@ DANGEROUS_PATTERNS = [
    # Gateway protection: never start gateway outside systemd management
    (r'gateway\s+run\b.*(&\s*$|&\s*;|\bdisown\b|\bsetsid\b)', "start gateway outside systemd (use 'systemctl --user restart hermes-gateway')"),
    (r'\bnohup\b.*gateway\s+run\b', "start gateway outside systemd (use 'systemctl --user restart hermes-gateway')"),
+    # Self-termination protection: prevent agent from killing its own process
+    (r'\b(pkill|killall)\b.*\b(hermes|gateway|cli\.py)\b', "kill hermes/gateway process (self-termination)"),
 ]


@@ -993,7 +993,7 @@ def _extract_relevant_content(
        if model:
            call_kwargs["model"] = model
        response = call_llm(**call_kwargs)
-        return response.choices[0].message.content
+        return (response.choices[0].message.content or "").strip() or _truncate_snapshot(snapshot_text)
    except Exception:
        return _truncate_snapshot(snapshot_text)

@@ -1523,8 +1523,8 @@ def browser_vision(question: str, annotate: bool = False, task_id: Optional[str]
    effective_task_id = task_id or "default"
    
    # Save screenshot to persistent location so it can be shared with users
-    hermes_home = Path(os.environ.get("HERMES_HOME", Path.home() / ".hermes"))
-    screenshots_dir = hermes_home / "browser_screenshots"
+    from hermes_constants import get_hermes_dir
+    screenshots_dir = get_hermes_dir("cache/screenshots", "browser_screenshots")
    screenshot_path = screenshots_dir / f"browser_screenshot_{uuid_mod.uuid4().hex}.png"
    
    try:
@@ -1623,10 +1623,10 @@ def browser_vision(question: str, annotate: bool = False, task_id: Optional[str]
            call_kwargs["model"] = vision_model
        response = call_llm(**call_kwargs)
        
-        analysis = response.choices[0].message.content
+        analysis = (response.choices[0].message.content or "").strip()
        response_data = {
            "success": True,
-            "analysis": analysis,
+            "analysis": analysis or "Vision analysis returned no content.",
            "screenshot_path": str(screenshot_path),
        }
        # Include annotation data if annotated screenshot was taken
@@ -391,12 +391,17 @@ class LocalEnvironment(PersistentShellMixin, BaseEnvironment):
            effective_stdin = stdin_data

        user_shell = _find_bash()
+        # Newline-separated wrapper (not `cmd; __hermes_rc=...` on one line).
+        # A trailing `; __hermes_rc` glued to `<<EOF` / a closing `EOF` line breaks
+        # heredoc parsing: the delimiter must be alone on its line, otherwise the
+        # rest of this script becomes heredoc body and leaks into stdout (e.g. gh
+        # issue/PR flows that use here-documents for bodies).
        fenced_cmd = (
-            f"printf '{_OUTPUT_FENCE}';"
-            f" {exec_command};"
-            f" __hermes_rc=$?;"
-            f" printf '{_OUTPUT_FENCE}';"
-            f" exit $__hermes_rc"
+            f"printf '{_OUTPUT_FENCE}'\n"
+            f"{exec_command}\n"
+            f"__hermes_rc=$?\n"
+            f"printf '{_OUTPUT_FENCE}'\n"
+            f"exit $__hermes_rc\n"
        )
        run_env = _make_run_env(self.env)

@@ -171,8 +171,9 @@ def read_file_tool(path: str, offset: int = 1, limit: int = 500, task_id: str =
        # Security: block direct reads of internal Hermes cache/index files
        # to prevent prompt injection via catalog or hub metadata files.
        import pathlib as _pathlib
+        from hermes_constants import get_hermes_home as _get_hh
        _resolved = _pathlib.Path(path).expanduser().resolve()
-        _hermes_home = _pathlib.Path("~/.hermes").expanduser().resolve()
+        _hermes_home = _get_hh().resolve()
        _blocked_dirs = [
            _hermes_home / "skills" / ".hub" / "index-cache",
            _hermes_home / "skills" / ".hub",
@@ -98,6 +98,13 @@ try:
        _MCP_HTTP_AVAILABLE = True
    except ImportError:
        _MCP_HTTP_AVAILABLE = False
+    # Prefer the non-deprecated API (mcp >= 1.24.0); fall back to the
+    # deprecated wrapper for older SDK versions.
+    try:
+        from mcp.client.streamable_http import streamable_http_client
+        _MCP_NEW_HTTP = True
+    except ImportError:
+        _MCP_NEW_HTTP = False
    # Sampling types -- separated so older SDK versions don't break MCP support
    try:
        from mcp.types import (
@@ -762,21 +769,50 @@ class MCPServerTask:
                logger.warning("MCP OAuth setup failed for '%s': %s", self.name, exc)

        sampling_kwargs = self._sampling.session_kwargs() if self._sampling else {}
-        _http_kwargs: dict = {
-            "headers": headers,
-            "timeout": float(connect_timeout),
-        }
-        if _oauth_auth is not None:
-            _http_kwargs["auth"] = _oauth_auth
-        async with streamablehttp_client(url, **_http_kwargs) as (
-            read_stream, write_stream, _get_session_id,
-        ):
-            async with ClientSession(read_stream, write_stream, **sampling_kwargs) as session:
-                await session.initialize()
-                self.session = session
-                await self._discover_tools()
-                self._ready.set()
-                await self._shutdown_event.wait()
+
+        if _MCP_NEW_HTTP:
+            # New API (mcp >= 1.24.0): build an explicit httpx.AsyncClient
+            # matching the SDK's own create_mcp_http_client defaults.
+            import httpx
+
+            client_kwargs: dict = {
+                "follow_redirects": True,
+                "timeout": httpx.Timeout(float(connect_timeout), read=300.0),
+            }
+            if headers:
+                client_kwargs["headers"] = headers
+            if _oauth_auth is not None:
+                client_kwargs["auth"] = _oauth_auth
+
+            # Caller owns the client lifecycle — the SDK skips cleanup when
+            # http_client is provided, so we wrap in async-with.
+            async with httpx.AsyncClient(**client_kwargs) as http_client:
+                async with streamable_http_client(url, http_client=http_client) as (
+                    read_stream, write_stream, _get_session_id,
+                ):
+                    async with ClientSession(read_stream, write_stream, **sampling_kwargs) as session:
+                        await session.initialize()
+                        self.session = session
+                        await self._discover_tools()
+                        self._ready.set()
+                        await self._shutdown_event.wait()
+        else:
+            # Deprecated API (mcp < 1.24.0): manages httpx client internally.
+            _http_kwargs: dict = {
+                "headers": headers,
+                "timeout": float(connect_timeout),
+            }
+            if _oauth_auth is not None:
+                _http_kwargs["auth"] = _oauth_auth
+            async with streamablehttp_client(url, **_http_kwargs) as (
+                read_stream, write_stream, _get_session_id,
+            ):
+                async with ClientSession(read_stream, write_stream, **sampling_kwargs) as session:
+                    await session.initialize()
+                    self.session = session
+                    await self._discover_tools()
+                    self._ready.set()
+                    await self._shutdown_event.wait()

    async def _discover_tools(self):
        """Discover tools from the connected session."""
@@ -339,7 +339,7 @@ class MemoryStore:
        entries = self._entries_for(target)
        current = self._char_count(target)
        limit = self._char_limit(target)
-        pct = int((current / limit) * 100) if limit > 0 else 0
+        pct = min(100, int((current / limit) * 100)) if limit > 0 else 0

        resp = {
            "success": True,
@@ -360,7 +360,7 @@ class MemoryStore:
        limit = self._char_limit(target)
        content = ENTRY_DELIMITER.join(entries)
        current = len(content)
-        pct = int((current / limit) * 100) if limit > 0 else 0
+        pct = min(100, int((current / limit) * 100)) if limit > 0 else 0

        if target == "user":
            header = f"USER PROFILE (who the user is) [{pct}% — {current:,}/{limit:,} chars]"
@@ -251,6 +251,7 @@ class GitHubSource(SkillSource):
        {"repo": "openai/skills", "path": "skills/"},
        {"repo": "anthropics/skills", "path": "skills/"},
        {"repo": "VoltAgent/awesome-agent-skills", "path": "skills/"},
+        {"repo": "garrytan/gstack", "path": ""},
    ]

    def __init__(self, auth: GitHubAuth, extra_taps: Optional[List[Dict]] = None):
@@ -395,7 +396,8 @@ class GitHubSource(SkillSource):
            if dir_name.startswith(".") or dir_name.startswith("_"):
                continue

-            skill_identifier = f"{repo}/{path.rstrip('/')}/{dir_name}"
+            prefix = path.rstrip("/")
+            skill_identifier = f"{repo}/{prefix}/{dir_name}" if prefix else f"{repo}/{dir_name}"
            meta = self.inspect(skill_identifier)
            if meta:
                skills.append(meta)
@@ -355,13 +355,8 @@ def _remaining_required_environment_names(
    capture_result: Dict[str, Any],
    *,
    env_snapshot: Dict[str, str] | None = None,
-    backend: str | None = None,
 ) -> List[str]:
-    if backend is None:
-        backend = _get_terminal_backend_name()
    missing_names = set(capture_result["missing_names"])
-    if backend in _REMOTE_ENV_BACKENDS:
-        return [entry["name"] for entry in required_env_vars]

    if env_snapshot is None:
        env_snapshot = load_env()
@@ -1076,8 +1071,7 @@ def skill_view(name: str, file_path: str = None, task_id: str = None) -> str:
        missing_required_env_vars = [
            e
            for e in required_env_vars
-            if backend in _REMOTE_ENV_BACKENDS
-            or not _is_env_var_persisted(e["name"], env_snapshot)
+            if not _is_env_var_persisted(e["name"], env_snapshot)
        ]
        capture_result = _capture_required_environment_variables(
            skill_name,
@@ -1089,7 +1083,6 @@ def skill_view(name: str, file_path: str = None, task_id: str = None) -> str:
            required_env_vars,
            capture_result,
            env_snapshot=env_snapshot,
-            backend=backend,
        )
        setup_needed = bool(remaining_missing_required_envs)

@@ -74,7 +74,11 @@ DEFAULT_ELEVENLABS_MODEL_ID = "eleven_multilingual_v2"
 DEFAULT_ELEVENLABS_STREAMING_MODEL_ID = "eleven_flash_v2_5"
 DEFAULT_OPENAI_MODEL = "gpt-4o-mini-tts"
 DEFAULT_OPENAI_VOICE = "alloy"
-DEFAULT_OUTPUT_DIR = str(get_hermes_home() / "audio_cache")
+def _get_default_output_dir() -> str:
+    from hermes_constants import get_hermes_dir
+    return str(get_hermes_dir("cache/audio", "audio_cache"))
+
+DEFAULT_OUTPUT_DIR = _get_default_output_dir()
 MAX_TEXT_LENGTH = 4000


@@ -828,7 +832,7 @@ TTS_SCHEMA = {
            },
            "output_path": {
                "type": "string",
-                "description": "Optional custom file path to save the audio. Defaults to ~/.hermes/audio_cache/<timestamp>.mp3"
+                "description": "Optional custom file path to save the audio. Defaults to ~/.hermes/cache/audio/<timestamp>.mp3"
            }
        },
        "required": ["text"]
@@ -74,14 +74,16 @@ def _get_backend() -> str:
    keys manually without running setup.
    """
    configured = (_load_web_config().get("backend") or "").lower().strip()
-    if configured in ("parallel", "firecrawl", "tavily"):
+    if configured in ("parallel", "firecrawl", "tavily", "exa"):
        return configured

    # Fallback for manual / legacy config — use whichever key is present.
    has_firecrawl = _has_env("FIRECRAWL_API_KEY") or _has_env("FIRECRAWL_API_URL")
    has_parallel = _has_env("PARALLEL_API_KEY")
    has_tavily = _has_env("TAVILY_API_KEY")
-
+    has_exa = _has_env("EXA_API_KEY")
+    if has_exa and not has_firecrawl and not has_parallel and not has_tavily:
+        return "exa"
    if has_tavily and not has_firecrawl and not has_parallel:
        return "tavily"
    if has_parallel and not has_firecrawl:
@@ -605,6 +607,91 @@ def clean_base64_images(text: str) -> str:
    return cleaned_text


+# ─── Exa Client ──────────────────────────────────────────────────────────────
+
+_exa_client = None
+
+def _get_exa_client():
+    """Get or create the Exa client (lazy initialization).
+
+    Requires EXA_API_KEY environment variable.
+    """
+    from exa_py import Exa
+    global _exa_client
+    if _exa_client is None:
+        api_key = os.getenv("EXA_API_KEY")
+        if not api_key:
+            raise ValueError(
+                "EXA_API_KEY environment variable not set. "
+                "Get your API key at https://exa.ai"
+            )
+        _exa_client = Exa(api_key=api_key)
+        _exa_client.headers["x-exa-integration"] = "hermes-agent"
+    return _exa_client
+
+
+# ─── Exa Search & Extract Helpers ─────────────────────────────────────────────
+
+def _exa_search(query: str, limit: int = 10) -> dict:
+    """Search using the Exa SDK and return results as a dict."""
+    from tools.interrupt import is_interrupted
+    if is_interrupted():
+        return {"error": "Interrupted", "success": False}
+
+    logger.info("Exa search: '%s' (limit=%d)", query, limit)
+    response = _get_exa_client().search(
+        query,
+        num_results=limit,
+        contents={
+            "highlights": True,
+        },
+    )
+
+    web_results = []
+    for i, result in enumerate(response.results or []):
+        highlights = result.highlights or []
+        web_results.append({
+            "url": result.url or "",
+            "title": result.title or "",
+            "description": " ".join(highlights) if highlights else "",
+            "position": i + 1,
+        })
+
+    return {"success": True, "data": {"web": web_results}}
+
+
+def _exa_extract(urls: List[str]) -> List[Dict[str, Any]]:
+    """Extract content from URLs using the Exa SDK.
+
+    Returns a list of result dicts matching the structure expected by the
+    LLM post-processing pipeline (url, title, content, metadata).
+    """
+    from tools.interrupt import is_interrupted
+    if is_interrupted():
+        return [{"url": u, "error": "Interrupted", "title": ""} for u in urls]
+
+    logger.info("Exa extract: %d URL(s)", len(urls))
+    response = _get_exa_client().get_contents(
+        urls,
+        text=True,
+    )
+
+    results = []
+    for result in response.results or []:
+        content = result.text or ""
+        url = result.url or ""
+        title = result.title or ""
+        results.append({
+            "url": url,
+            "title": title,
+            "content": content,
+            "raw_content": content,
+            "metadata": {"sourceURL": url, "title": title},
+        })
+
+    return results
+
+
 # ─── Parallel Search & Extract Helpers ────────────────────────────────────────

 def _parallel_search(query: str, limit: int = 5) -> dict:
@@ -742,6 +829,15 @@ def web_search_tool(query: str, limit: int = 5) -> str:
            _debug.save()
            return result_json

+        if backend == "exa":
+            response_data = _exa_search(query, limit)
+            debug_call_data["results_count"] = len(response_data.get("data", {}).get("web", []))
+            result_json = json.dumps(response_data, indent=2, ensure_ascii=False)
+            debug_call_data["final_response_size"] = len(result_json)
+            _debug.log_call("web_search_tool", debug_call_data)
+            _debug.save()
+            return result_json
+
        if backend == "tavily":
            logger.info("Tavily search: '%s' (limit: %d)", query, limit)
            raw = _tavily_request("search", {
@@ -897,6 +993,8 @@ async def web_extract_tool(

            if backend == "parallel":
                results = await _parallel_extract(safe_urls)
+            elif backend == "exa":
+                results = _exa_extract(safe_urls)
            elif backend == "tavily":
                logger.info("Tavily extract: %d URL(s)", len(safe_urls))
                raw = _tavily_request("extract", {
@@ -1567,9 +1665,10 @@ def check_firecrawl_api_key() -> bool:


 def check_web_api_key() -> bool:
-    """Check if any web backend API key is available (Parallel, Firecrawl, or Tavily)."""
+    """Check if any web backend API key is available (Exa, Parallel, Firecrawl, or Tavily)."""
    return bool(
-        os.getenv("PARALLEL_API_KEY")
+        os.getenv("EXA_API_KEY")
+        or os.getenv("PARALLEL_API_KEY")
        or os.getenv("FIRECRAWL_API_KEY")
        or os.getenv("FIRECRAWL_API_URL")
        or os.getenv("TAVILY_API_KEY")
@@ -1608,7 +1707,9 @@ if __name__ == "__main__":
    if web_available:
        backend = _get_backend()
        print(f"✅ Web backend: {backend}")
-        if backend == "parallel":
+        if backend == "exa":
+            print("   Using Exa API (https://exa.ai)")
+        elif backend == "parallel":
            print("   Using Parallel API (https://parallel.ai)")
        elif backend == "tavily":
            print("   Using Tavily API (https://tavily.com)")
@@ -1616,7 +1717,7 @@ if __name__ == "__main__":
            print("   Using Firecrawl API (https://firecrawl.dev)")
    else:
        print("❌ No web search backend configured")
-        print("Set PARALLEL_API_KEY, TAVILY_API_KEY, or FIRECRAWL_API_KEY")
+        print("Set EXA_API_KEY, PARALLEL_API_KEY, TAVILY_API_KEY, or FIRECRAWL_API_KEY")

    if not nous_available:
        print("❌ No auxiliary model available for LLM content processing")
@@ -1726,7 +1827,7 @@ registry.register(
    schema=WEB_SEARCH_SCHEMA,
    handler=lambda args, **kw: web_search_tool(args.get("query", ""), limit=5),
    check_fn=check_web_api_key,
-    requires_env=["PARALLEL_API_KEY", "FIRECRAWL_API_KEY", "TAVILY_API_KEY"],
+    requires_env=["EXA_API_KEY", "PARALLEL_API_KEY", "FIRECRAWL_API_KEY", "TAVILY_API_KEY"],
    emoji="🔍",
 )
 registry.register(
@@ -1736,7 +1837,7 @@ registry.register(
    handler=lambda args, **kw: web_extract_tool(
        args.get("urls", [])[:5] if isinstance(args.get("urls"), list) else [], "markdown"),
    check_fn=check_web_api_key,
-    requires_env=["PARALLEL_API_KEY", "FIRECRAWL_API_KEY", "TAVILY_API_KEY"],
+    requires_env=["EXA_API_KEY", "PARALLEL_API_KEY", "FIRECRAWL_API_KEY", "TAVILY_API_KEY"],
    is_async=True,
    emoji="📄",
 )
@@ -333,6 +333,24 @@ TOOLSETS = {
        "includes": []
    },

+    "hermes-mattermost": {
+        "description": "Mattermost bot toolset - self-hosted team messaging (full access)",
+        "tools": _HERMES_CORE_TOOLS,
+        "includes": []
+    },
+
+    "hermes-matrix": {
+        "description": "Matrix bot toolset - decentralized encrypted messaging (full access)",
+        "tools": _HERMES_CORE_TOOLS,
+        "includes": []
+    },
+
+    "hermes-dingtalk": {
+        "description": "DingTalk bot toolset - enterprise messaging platform (full access)",
+        "tools": _HERMES_CORE_TOOLS,
+        "includes": []
+    },
+
    "hermes-sms": {
        "description": "SMS bot toolset - interact with Hermes via SMS (Twilio)",
        "tools": _HERMES_CORE_TOOLS,
@@ -342,7 +360,7 @@ TOOLSETS = {
    "hermes-gateway": {
        "description": "Gateway toolset - union of all messaging platform tools",
        "tools": [],
-        "includes": ["hermes-telegram", "hermes-discord", "hermes-whatsapp", "hermes-slack", "hermes-signal", "hermes-homeassistant", "hermes-email", "hermes-sms"]
+        "includes": ["hermes-telegram", "hermes-discord", "hermes-whatsapp", "hermes-slack", "hermes-signal", "hermes-homeassistant", "hermes-email", "hermes-sms", "hermes-mattermost", "hermes-matrix", "hermes-dingtalk"]
    }
 }

@@ -376,15 +376,6 @@ wheels = [
    { url = "https://files.pythonhosted.org/packages/41/0a/0896b829a39b5669a2d811e1a79598de661693685cd62b31f11d0c18e65b/av-17.0.0-cp314-cp314t-win_arm64.whl", hash = "sha256:dba98603fc4665b4f750de86fbaf6c0cfaece970671a9b529e0e3d1711e8367e", size = 22071058, upload-time = "2026-03-14T14:38:43.663Z" },
 ]

-[[package]]
-name = "bashlex"
-version = "0.18"
-source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/76/60/aae0bb54f9af5e0128ba90eb83d8d0d506ee8f0475c4fdda3deeda20b1d2/bashlex-0.18.tar.gz", hash = "sha256:5bb03a01c6d5676338c36fd1028009c8ad07e7d61d8a1ce3f513b7fff52796ee", size = 68742, upload-time = "2023-01-18T15:21:26.402Z" }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/f4/be/6985abb1011fda8a523cfe21ed9629e397d6e06fb5bae99750402b25c95b/bashlex-0.18-py2.py3-none-any.whl", hash = "sha256:91d73a23a3e51711919c1c899083890cdecffc91d8c088942725ac13e9dcfffa", size = 69539, upload-time = "2023-01-18T15:21:24.167Z" },
-]
-
 [[package]]
 name = "blinker"
 version = "1.9.0"
@@ -394,34 +385,6 @@ wheels = [
    { url = "https://files.pythonhosted.org/packages/10/cb/f2ad4230dc2eb1a74edf38f1a38b9b52277f75bef262d8908e60d957e13c/blinker-1.9.0-py3-none-any.whl", hash = "sha256:ba0efaa9080b619ff2f3459d1d500c57bddea4a6b424b60a91141db6fd2f08bc", size = 8458, upload-time = "2024-11-08T17:25:46.184Z" },
 ]

-[[package]]
-name = "boto3"
-version = "1.42.57"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "botocore" },
-    { name = "jmespath" },
-    { name = "s3transfer" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/b6/86/46898eaae75ab2185bcf2af406fb4cd1646a0bc277d5dab8ca36c30b7e5e/boto3-1.42.57.tar.gz", hash = "sha256:b598f1705f231f118a81abbfde0c5b52879b1b1997a1aba513f04d61e7b12cbd", size = 112799, upload-time = "2026-02-25T20:31:59.362Z" }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/9e/21/854be1e1829a33450079c1a05f89ef03a2a44bdad590de3e10dc09d73cbd/boto3-1.42.57-py3-none-any.whl", hash = "sha256:74f47051e3b741a0c1e64d57b891076c2c68f8d7b98aee36b044fab1849b4823", size = 140554, upload-time = "2026-02-25T20:31:53.215Z" },
-]
-
-[[package]]
-name = "botocore"
-version = "1.42.57"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "jmespath" },
-    { name = "python-dateutil" },
-    { name = "urllib3" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/cd/9c/f9e289f44985fe5b2e3ffc127a55cf7e87ef88499f5a8001db86d74ecfb1/botocore-1.42.57.tar.gz", hash = "sha256:51f94c602b687a70aa11d8bbea2b741b87b0aef7bddb43e5386247bf4311c479", size = 14940952, upload-time = "2026-02-25T20:31:42.049Z" }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/cc/bd/89d0fdb65488d6ee40194268b07316433b41f3aa3f242676ed804c3200f5/botocore-1.42.57-py3-none-any.whl", hash = "sha256:0d26c09955e52ac5090d9cf9e218542df81670077049a606be7c3bd235208e67", size = 14614741, upload-time = "2026-02-25T20:31:39.081Z" },
-]
-
 [[package]]
 name = "cachetools"
 version = "5.5.2"
@@ -1637,7 +1600,7 @@ wheels = [

 [[package]]
 name = "hermes-agent"
-version = "0.4.0"
+version = "0.5.0"
 source = { editable = "." }
 dependencies = [
    { name = "anthropic" },
@@ -1674,6 +1637,7 @@ all = [
    { name = "elevenlabs" },
    { name = "honcho-ai" },
    { name = "mcp" },
+    { name = "modal" },
    { name = "numpy" },
    { name = "ptyprocess", marker = "sys_platform != 'win32'" },
    { name = "pytest" },
@@ -1685,7 +1649,6 @@ all = [
    { name = "slack-bolt" },
    { name = "slack-sdk" },
    { name = "sounddevice" },
-    { name = "swe-rex", extra = ["modal"] },
 ]
 cli = [
    { name = "simple-term-menu" },
@@ -1725,7 +1688,7 @@ messaging = [
    { name = "slack-sdk" },
 ]
 modal = [
-    { name = "swe-rex", extra = ["modal"] },
+    { name = "modal" },
 ]
 pty = [
    { name = "ptyprocess", marker = "sys_platform != 'win32'" },
@@ -1758,7 +1721,7 @@ yc-bench = [

 [package.metadata]
 requires-dist = [
-    { name = "agent-client-protocol", marker = "extra == 'acp'", specifier = ">=0.8.1,<1.0" },
+    { name = "agent-client-protocol", marker = "extra == 'acp'", specifier = ">=0.8.1,<0.9" },
    { name = "aiohttp", marker = "extra == 'homeassistant'", specifier = ">=3.9.0,<4" },
    { name = "aiohttp", marker = "extra == 'messaging'", specifier = ">=3.13.3,<4" },
    { name = "aiohttp", marker = "extra == 'sms'", specifier = ">=3.9.0,<4" },
@@ -1797,6 +1760,7 @@ requires-dist = [
    { name = "matrix-nio", extras = ["e2e"], marker = "extra == 'matrix'", specifier = ">=0.24.0,<1" },
    { name = "mcp", marker = "extra == 'dev'", specifier = ">=1.2.0,<2" },
    { name = "mcp", marker = "extra == 'mcp'", specifier = ">=1.2.0,<2" },
+    { name = "modal", marker = "extra == 'modal'", specifier = ">=1.0.0,<2" },
    { name = "numpy", marker = "extra == 'voice'", specifier = ">=1.24.0,<3" },
    { name = "openai", specifier = ">=2.21.0,<3" },
    { name = "parallel-web", specifier = ">=0.4.2,<1" },
@@ -1819,7 +1783,6 @@ requires-dist = [
    { name = "slack-sdk", marker = "extra == 'messaging'", specifier = ">=3.27.0,<4" },
    { name = "slack-sdk", marker = "extra == 'slack'", specifier = ">=3.27.0,<4" },
    { name = "sounddevice", marker = "extra == 'voice'", specifier = ">=0.4.6,<1" },
-    { name = "swe-rex", extras = ["modal"], marker = "extra == 'modal'", specifier = ">=1.4.0,<2" },
    { name = "tenacity", specifier = ">=9.1.4,<10" },
    { name = "tinker", marker = "extra == 'rl'", git = "https://github.com/thinking-machines-lab/tinker.git" },
    { name = "uvicorn", extras = ["standard"], marker = "extra == 'rl'", specifier = ">=0.24.0,<1" },
@@ -2150,15 +2113,6 @@ wheels = [
    { url = "https://files.pythonhosted.org/packages/67/8a/a342b2f0251f3dac4ca17618265d93bf244a2a4d089126e81e4c1056ac50/jiter-0.13.0-graalpy312-graalpy250_312_native-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7bb00b6d26db67a05fe3e12c76edc75f32077fb51deed13822dc648fa373bc19", size = 343768, upload-time = "2026-02-02T12:37:55.055Z" },
 ]

-[[package]]
-name = "jmespath"
-version = "1.1.0"
-source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/d3/59/322338183ecda247fb5d1763a6cbe46eff7222eaeebafd9fa65d4bf5cb11/jmespath-1.1.0.tar.gz", hash = "sha256:472c87d80f36026ae83c6ddd0f1d05d4e510134ed462851fd5f754c8c3cbb88d", size = 27377, upload-time = "2026-01-22T16:35:26.279Z" }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/14/2f/967ba146e6d58cf6a652da73885f52fc68001525b4197effc174321d70b4/jmespath-1.1.0-py3-none-any.whl", hash = "sha256:a5663118de4908c91729bea0acadca56526eb2698e83de10cd116ae0f4e97c64", size = 20419, upload-time = "2026-01-22T16:35:24.919Z" },
-]
-
 [[package]]
 name = "joblib"
 version = "1.5.3"
@@ -3256,18 +3210,6 @@ wheels = [
    { url = "https://files.pythonhosted.org/packages/1a/41/19c65578ef9a54b3083253c68a607f099642747168fe00f3a2bceb7c3a34/peewee-3.19.0-py3-none-any.whl", hash = "sha256:de220b94766e6008c466e00ce4ba5299b9a832117d9eb36d45d0062f3cfd7417", size = 411885, upload-time = "2026-01-07T17:24:58.33Z" },
 ]

-[[package]]
-name = "pexpect"
-version = "4.9.0"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "ptyprocess" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/42/92/cc564bf6381ff43ce1f4d06852fc19a2f11d180f23dc32d9588bee2f149d/pexpect-4.9.0.tar.gz", hash = "sha256:ee7d41123f3c9911050ea2c2dac107568dc43b2d3b0c7557a33212c398ead30f", size = 166450, upload-time = "2023-11-25T09:07:26.339Z" }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/9e/c3/059298687310d527a58bb01f3b1965787ee3b40dce76752eda8b44e9a2c5/pexpect-4.9.0-py2.py3-none-any.whl", hash = "sha256:7236d1e080e4936be2dc3e326cec0af72acf9212a7e1d060210e70a47e253523", size = 63772, upload-time = "2023-11-25T06:56:14.81Z" },
-]
-
 [[package]]
 name = "pillow"
 version = "12.1.1"
@@ -4301,18 +4243,6 @@ wheels = [
    { url = "https://files.pythonhosted.org/packages/d1/b7/b95708304cd49b7b6f82fdd039f1748b66ec2b21d6a45180910802f1abf1/rpds_py-0.30.0-pp311-pypy311_pp73-musllinux_1_2_x86_64.whl", hash = "sha256:ac37f9f516c51e5753f27dfdef11a88330f04de2d564be3991384b2f3535d02e", size = 562191, upload-time = "2025-11-30T20:24:36.853Z" },
 ]

-[[package]]
-name = "s3transfer"
-version = "0.16.0"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "botocore" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/05/04/74127fc843314818edfa81b5540e26dd537353b123a4edc563109d8f17dd/s3transfer-0.16.0.tar.gz", hash = "sha256:8e990f13268025792229cd52fa10cb7163744bf56e719e0b9cb925ab79abf920", size = 153827, upload-time = "2025-12-01T02:30:59.114Z" }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/fc/51/727abb13f44c1fcf6d145979e1535a35794db0f6e450a0cb46aa24732fe2/s3transfer-0.16.0-py3-none-any.whl", hash = "sha256:18e25d66fed509e3868dc1572b3f427ff947dd2c56f844a5bf09481ad3f3b2fe", size = 86830, upload-time = "2025-12-01T02:30:57.729Z" },
-]
-
 [[package]]
 name = "safetensors"
 version = "0.7.0"
@@ -4547,31 +4477,6 @@ wheels = [
    { url = "https://files.pythonhosted.org/packages/dc/e6/412c1e1f200ca8c32ecf10201839183e261ad61ced3ede34a66f6d4be3cf/streamlit-1.55.0-py3-none-any.whl", hash = "sha256:1e4a16449c6131696180f4ddb40ea8c51834e89c2a43e1b0362bc9b1cfd9b415", size = 9075714, upload-time = "2026-03-03T22:25:59.126Z" },
 ]

-[[package]]
-name = "swe-rex"
-version = "1.4.0"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "bashlex" },
-    { name = "fastapi" },
-    { name = "pexpect" },
-    { name = "pydantic" },
-    { name = "python-multipart" },
-    { name = "requests" },
-    { name = "rich" },
-    { name = "uvicorn" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/94/86/a069f93ec866151a4d476d546e60220e66b3788878b6e248b2df3ab2c5f1/swe_rex-1.4.0.tar.gz", hash = "sha256:14f8a24c49a63f9e251340b1109ac75a4aacbaece410f8599209de9bfca843c0", size = 41755, upload-time = "2025-08-14T01:19:20.22Z" }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/98/0d/d06ab2aa78138055c297490762cd7b4d8ac58a544783f874c869cdb7b534/swe_rex-1.4.0-py3-none-any.whl", hash = "sha256:61261ad03eb23b717b5901cd5d229f24f6e1be2e120aad5c2e5ea3384a1d15ad", size = 47756, upload-time = "2025-08-14T01:19:18.93Z" },
-]
-
-[package.optional-dependencies]
-modal = [
-    { name = "boto3" },
-    { name = "modal" },
-]
-
 [[package]]
 name = "sympy"
 version = "1.14.0"
@@ -168,11 +168,15 @@ journalctl -u hermes-gateway -f

 ```bash
 # macOS — manage the service
-launchctl start ai.hermes.gateway
-launchctl stop ai.hermes.gateway
+hermes gateway start
+hermes gateway stop
 tail -f ~/.hermes/logs/gateway.log
 ```

+:::tip macOS PATH
+The launchd plist captures your shell PATH at install time so gateway subprocesses can find tools like Node.js and ffmpeg. If you install new tools later, re-run `hermes gateway install` to update the plist.
+:::
+
 ### Verify It's Running

 ```bash
@@ -39,6 +39,7 @@ hermes [global-options] <command> [subcommand/options]
 | `hermes login` / `logout` | Authenticate with OAuth-backed providers. |
 | `hermes status` | Show agent, auth, and platform status. |
 | `hermes cron` | Inspect and tick the cron scheduler. |
+| `hermes webhook` | Manage dynamic webhook subscriptions for event-driven activation. |
 | `hermes doctor` | Diagnose config and dependency issues. |
 | `hermes config` | Show, edit, migrate, and query configuration files. |
 | `hermes pairing` | Approve or revoke messaging pairing codes. |
@@ -66,7 +67,7 @@ Common options:
 | `-q`, `--query "..."` | One-shot, non-interactive prompt. |
 | `-m`, `--model <model>` | Override the model for this run. |
 | `-t`, `--toolsets <csv>` | Enable a comma-separated set of toolsets. |
-| `--provider <provider>` | Force a provider: `auto`, `openrouter`, `nous`, `openai-codex`, `copilot`, `copilot-acp`, `anthropic`, `huggingface`, `zai`, `kimi-coding`, `minimax`, `minimax-cn`, `kilocode`. |
+| `--provider <provider>` | Force a provider: `auto`, `openrouter`, `nous`, `openai-codex`, `copilot`, `copilot-acp`, `anthropic`, `huggingface`, `alibaba`, `zai`, `kimi-coding`, `minimax`, `minimax-cn`, `kilocode`. |
 | `-s`, `--skills <name>` | Preload one or more skills for the session (can be repeated or comma-separated). |
 | `-v`, `--verbose` | Verbose output. |
 | `-Q`, `--quiet` | Programmatic mode: suppress banner/spinner/tool previews. |
@@ -214,6 +215,39 @@ hermes cron <list|create|edit|pause|resume|run|remove|status|tick>
 | `status` | Check whether the cron scheduler is running. |
 | `tick` | Run due jobs once and exit. |

+## `hermes webhook`
+
+```bash
+hermes webhook <subscribe|list|remove|test>
+```
+
+Manage dynamic webhook subscriptions for event-driven agent activation. Requires the webhook platform to be enabled in config — if not configured, prints setup instructions.
+
+| Subcommand | Description |
+|------------|-------------|
+| `subscribe` / `add` | Create a webhook route. Returns the URL and HMAC secret to configure on your service. |
+| `list` / `ls` | Show all agent-created subscriptions. |
+| `remove` / `rm` | Delete a dynamic subscription. Static routes from config.yaml are not affected. |
+| `test` | Send a test POST to verify a subscription is working. |
+
+### `hermes webhook subscribe`
+
+```bash
+hermes webhook subscribe <name> [options]
+```
+
+| Option | Description |
+|--------|-------------|
+| `--prompt` | Prompt template with `{dot.notation}` payload references. |
+| `--events` | Comma-separated event types to accept (e.g. `issues,pull_request`). Empty = all. |
+| `--description` | Human-readable description. |
+| `--skills` | Comma-separated skill names to load for the agent run. |
+| `--deliver` | Delivery target: `log` (default), `telegram`, `discord`, `slack`, `github_comment`. |
+| `--deliver-chat-id` | Target chat/channel ID for cross-platform delivery. |
+| `--secret` | Custom HMAC secret. Auto-generated if omitted. |
+
+Subscriptions persist to `~/.hermes/webhook_subscriptions.json` and are hot-reloaded by the webhook adapter without a gateway restart.
+
 ## `hermes doctor`

 ```bash
@@ -42,7 +42,7 @@ All variables go in `~/.hermes/.env`. You can also set them with `hermes config
 | `ANTHROPIC_API_KEY` | Anthropic Console API key ([console.anthropic.com](https://console.anthropic.com/)) |
 | `ANTHROPIC_TOKEN` | Manual or legacy Anthropic OAuth/setup-token override |
 | `DASHSCOPE_API_KEY` | Alibaba Cloud DashScope API key for Qwen models ([modelstudio.console.alibabacloud.com](https://modelstudio.console.alibabacloud.com/)) |
-| `DASHSCOPE_BASE_URL` | Custom DashScope base URL (default: international endpoint) |
+| `DASHSCOPE_BASE_URL` | Custom DashScope base URL (default: `https://coding-intl.dashscope.aliyuncs.com/v1`) |
 | `DEEPSEEK_API_KEY` | DeepSeek API key for direct DeepSeek access ([platform.deepseek.com](https://platform.deepseek.com/api_keys)) |
 | `DEEPSEEK_BASE_URL` | Custom DeepSeek API base URL |
 | `OPENCODE_ZEN_API_KEY` | OpenCode Zen API key — pay-as-you-go access to curated models ([opencode.ai](https://opencode.ai/auth)) |
@@ -357,6 +357,23 @@ lsof -i :8080
 hermes config show
 ```

+#### macOS: Node.js / ffmpeg / other tools not found by gateway
+
+**Cause:** launchd services inherit a minimal PATH (`/usr/bin:/bin:/usr/sbin:/sbin`) that doesn't include Homebrew, nvm, cargo, or other user-installed tool directories. This commonly breaks the WhatsApp bridge (`node not found`) or voice transcription (`ffmpeg not found`).
+
+**Solution:** The gateway captures your shell PATH when you run `hermes gateway install`. If you installed tools after setting up the gateway, re-run the install to capture the updated PATH:
+
+```bash
+hermes gateway install    # Re-snapshots your current PATH
+hermes gateway start      # Detects the updated plist and reloads
+```
+
+You can verify the plist has the correct PATH:
+```bash
+/usr/libexec/PlistBuddy -c "Print :EnvironmentVariables:PATH" \
+  ~/Library/LaunchAgents/ai.hermes.gateway.plist
+```
+
 ---

 ### Performance Issues
@@ -48,6 +48,14 @@ Creative content generation — ASCII art, hand-drawn style diagrams, and visual
 | `ascii-video` | "Production pipeline for ASCII art video — any format. Converts video/audio/images/generative input into colored ASCII character video output (MP4, GIF, image sequence). Covers: video-to-ASCII conversion, audio-reactive music visualizers, generative ASCII art animations, hybrid… | `creative/ascii-video` |
 | `excalidraw` | Create hand-drawn style diagrams using Excalidraw JSON format. Generate .excalidraw files for architecture diagrams, flowcharts, sequence diagrams, concept maps, and more. Files can be opened at excalidraw.com or uploaded for shareable links. | `creative/excalidraw` |

+## devops
+
+DevOps and infrastructure automation skills.
+
+| Skill | Description | Path |
+|-------|-------------|------|
+| `webhook-subscriptions` | Create and manage webhook subscriptions for event-driven agent activation. External services (GitHub, Stripe, CI/CD, IoT) POST events to trigger agent runs. Requires webhook platform to be enabled. | `devops/webhook-subscriptions` |
+
 ## dogfood

 | Skill | Description | Path |
@@ -19,10 +19,14 @@ Toolsets are named bundles of tools that you can enable with `hermes chat --tool
 | `file` | core | `patch`, `read_file`, `search_files`, `write_file` |
 | `hermes-acp` | platform | `browser_back`, `browser_click`, `browser_close`, `browser_console`, `browser_get_images`, `browser_navigate`, `browser_press`, `browser_scroll`, `browser_snapshot`, `browser_type`, `browser_vision`, `delegate_task`, `execute_code`, `memory`, `patch`, `process`, `read_file`, `search_files`, `session_search`, `skill_manage`, `skill_view`, `skills_list`, `terminal`, `todo`, `vision_analyze`, `web_extract`, `web_search`, `write_file` |
 | `hermes-cli` | platform | `browser_back`, `browser_click`, `browser_close`, `browser_console`, `browser_get_images`, `browser_navigate`, `browser_press`, `browser_scroll`, `browser_snapshot`, `browser_type`, `browser_vision`, `clarify`, `cronjob`, `delegate_task`, `execute_code`, `ha_call_service`, `ha_get_state`, `ha_list_entities`, `ha_list_services`, `honcho_conclude`, `honcho_context`, `honcho_profile`, `honcho_search`, `image_generate`, `memory`, `mixture_of_agents`, `patch`, `process`, `read_file`, `search_files`, `send_message`, `session_search`, `skill_manage`, `skill_view`, `skills_list`, `terminal`, `text_to_speech`, `todo`, `vision_analyze`, `web_extract`, `web_search`, `write_file` |
+| `hermes-api-server` | platform | _(same as hermes-cli)_ |
+| `hermes-dingtalk` | platform | _(same as hermes-cli)_ |
 | `hermes-discord` | platform | _(same as hermes-cli)_ |
 | `hermes-email` | platform | _(same as hermes-cli)_ |
 | `hermes-gateway` | composite | Union of all messaging platform toolsets |
 | `hermes-homeassistant` | platform | _(same as hermes-cli)_ |
+| `hermes-matrix` | platform | _(same as hermes-cli)_ |
+| `hermes-mattermost` | platform | _(same as hermes-cli)_ |
 | `hermes-signal` | platform | _(same as hermes-cli)_ |
 | `hermes-slack` | platform | _(same as hermes-cli)_ |
 | `hermes-sms` | platform | _(same as hermes-cli)_ |
@@ -95,6 +95,10 @@ You need at least one way to connect to an LLM. Use `hermes model` to switch pro
 | **Hugging Face** | `HF_TOKEN` in `~/.hermes/.env` (provider: `huggingface`, aliases: `hf`) |
 | **Custom Endpoint** | `hermes model` (saved in `config.yaml`) or `OPENAI_BASE_URL` + `OPENAI_API_KEY` in `~/.hermes/.env` |

+:::tip Model key alias
+In the `model:` config section, you can use either `default:` or `model:` as the key name for your model ID. Both `model: { default: my-model }` and `model: { model: my-model }` work identically.
+:::
+
 :::info Codex Note
 The OpenAI Codex provider authenticates via device code (open a URL, enter a code). Hermes stores the resulting credentials in its own auth store under `~/.hermes/auth.json` and can import existing Codex CLI credentials from `~/.codex/auth.json` when present. No Codex CLI installation is required.
 :::
@@ -212,7 +216,7 @@ hermes chat --provider minimax-cn --model MiniMax-M2.7
 # Requires: MINIMAX_CN_API_KEY in ~/.hermes/.env

 # Alibaba Cloud / DashScope (Qwen models)
-hermes chat --provider alibaba --model qwen-plus
+hermes chat --provider alibaba --model qwen3.5-plus
 # Requires: DASHSCOPE_API_KEY in ~/.hermes/.env
 ```

@@ -1022,6 +1026,7 @@ auxiliary:
    model: ""                  # e.g. "google/gemini-2.5-flash"
    base_url: ""
    api_key: ""
+    timeout: 30                # seconds

  # Dangerous command approval classifier
  approval:
@@ -1029,8 +1034,17 @@ auxiliary:
    model: ""
    base_url: ""
    api_key: ""
+    timeout: 30                # seconds
+
+  # Context compression timeout (separate from compression.* config)
+  compression:
+    timeout: 120               # seconds — compression summarizes long conversations, needs more time
 ```

+:::tip
+Each auxiliary task has a configurable `timeout` (in seconds). Defaults: vision 30s, web_extract 30s, approval 30s, compression 120s. Increase these if you use slow local models for auxiliary tasks.
+:::
+
 :::info
 Context compression has its own top-level `compression:` block with `summary_provider`, `summary_model`, and `summary_base_url` — see [Context Compression](#context-compression) above. The fallback model uses a `fallback_model:` block — see [Fallback Model](#fallback-model) above. All three follow the same provider/model/base_url pattern.
 :::
@@ -1162,6 +1176,24 @@ You can also change the reasoning effort at runtime with the `/reasoning` comman
 /reasoning hide      # Hide model thinking
 ```

+## Tool-Use Enforcement
+
+Some models (especially GPT-family) occasionally describe intended actions as text instead of making tool calls. Tool-use enforcement injects guidance that steers the model back to actually calling tools.
+
+```yaml
+agent:
+  tool_use_enforcement: "auto"   # "auto" | true | false | ["model-substring", ...]
+```
+
+| Value | Behavior |
+|-------|----------|
+| `"auto"` (default) | Enabled for GPT models (`gpt-`, `openai/gpt-`) and disabled for all others. |
+| `true` | Always enabled for all models. |
+| `false` | Always disabled. |
+| `["gpt-", "o1-", "custom-model"]` | Enabled only for models whose name contains one of the listed substrings. |
+
+When enabled, the system prompt includes guidance reminding the model to make actual tool calls rather than describing what it would do. This is transparent to the user and has no effect on models that already use tools reliably.
+
 ## TTS Configuration

 ```yaml
@@ -154,7 +154,7 @@ Lists `hermes-agent` as an available model. Required by most frontends for model

 ### GET /health

-Health check. Returns `{"status": "ok"}`.
+Health check. Returns `{"status": "ok"}`. Also available at **GET /v1/health** for OpenAI-compatible clients that expect the `/v1/` prefix.

 ## System Prompt Handling

@@ -199,6 +199,12 @@ The default bind address (`127.0.0.1`) is for local-only use. Browser access is
 # config.yaml support coming in a future release.
 ```

+## Security Headers
+
+All responses include security headers:
+- `X-Content-Type-Options: nosniff` — prevents MIME type sniffing
+- `Referrer-Policy: no-referrer` — prevents referrer leakage
+
 ## CORS

 The API server does **not** enable browser CORS by default.
@@ -209,6 +215,11 @@ For direct browser access, set an explicit allowlist:
 API_SERVER_CORS_ORIGINS=http://localhost:3000,http://127.0.0.1:3000
 ```

+When CORS is enabled:
+- **Preflight responses** include `Access-Control-Max-Age: 600` (10 minute cache)
+- **SSE streaming responses** include CORS headers so browser EventSource clients work correctly
+- **`Idempotency-Key`** is an allowed request header — clients can send it for deduplication (responses are cached by key for 5 minutes)
+
 Most documented frontends such as Open WebUI connect server-to-server and do not need CORS at all.

 ## Compatible Frontends
@@ -44,6 +44,7 @@ Both `provider` and `model` are **required**. If either is missing, the fallback
 | MiniMax | `minimax` | `MINIMAX_API_KEY` |
 | MiniMax (China) | `minimax-cn` | `MINIMAX_CN_API_KEY` |
 | Kilo Code | `kilocode` | `KILOCODE_API_KEY` |
+| Alibaba / DashScope | `alibaba` | `DASHSCOPE_API_KEY` |
 | Hugging Face | `huggingface` | `HF_TOKEN` |
 | Custom endpoint | `custom` | `base_url` + `api_key_env` (see below) |

@@ -209,10 +209,10 @@ def register(ctx):
 |------|-----------|-------------------|
 | `pre_tool_call` | Before any tool executes | `tool_name`, `args`, `task_id` |
 | `post_tool_call` | After any tool returns | `tool_name`, `args`, `result`, `task_id` |
-| `pre_llm_call` | Before LLM API request | *(planned — not yet wired)* |
-| `post_llm_call` | After LLM API response | *(planned — not yet wired)* |
-| `on_session_start` | Session begins | *(planned — not yet wired)* |
-| `on_session_end` | Session ends | *(planned — not yet wired)* |
+| `pre_llm_call` | Before LLM API request | `session_id`, `user_message`, `conversation_history`, `is_first_turn`, `model`, `platform` |
+| `post_llm_call` | After LLM API response | `session_id`, `user_message`, `assistant_response`, `conversation_history`, `model`, `platform` |
+| `on_session_start` | Session begins | `session_id`, `model`, `platform` |
+| `on_session_end` | Session ends | `session_id`, `completed`, `interrupted`, `model`, `platform` |

 Callbacks receive keyword arguments matching the columns above:

@@ -277,9 +277,12 @@ hermes skills install well-known:https://mintlify.com/docs/.well-known/skills/mi

 Hermes can install directly from GitHub repositories and GitHub-based taps. This is useful when you already know the repo/path or want to add your own custom source repo.

- OpenAI skills: [openai/skills](https://github.com/openai/skills)
- Anthropic skills: [anthropics/skills](https://github.com/anthropics/skills)
- Example community tap source: [VoltAgent/awesome-agent-skills](https://github.com/VoltAgent/awesome-agent-skills)
+Default taps (browsable without any setup):
+- [openai/skills](https://github.com/openai/skills)
+- [anthropics/skills](https://github.com/anthropics/skills)
+- [VoltAgent/awesome-agent-skills](https://github.com/VoltAgent/awesome-agent-skills)
+- [garrytan/gstack](https://github.com/garrytan/gstack)
+
 - Example:

 ```bash
@@ -104,6 +104,7 @@ The adapter polls the IMAP inbox for UNSEEN messages at a configurable interval
  - Documents (PDF, ZIP, etc.) → available for file access
 - **HTML-only emails** have tags stripped for plain text extraction
 - **Self-messages** are filtered out to prevent reply loops
+- **Automated/noreply senders** are silently ignored — `noreply@`, `mailer-daemon@`, `bounce@`, `no-reply@`, and emails with `Auto-Submitted`, `Precedence: bulk`, or `List-Unsubscribe` headers

 ### Sending Replies

@@ -289,12 +289,27 @@ If you run multiple Hermes installations on the same machine (with different `HE
 ### macOS (launchd)

 ```bash
-hermes gateway install
-launchctl start ai.hermes.gateway
-launchctl stop ai.hermes.gateway
-tail -f ~/.hermes/logs/gateway.log
+hermes gateway install               # Install as launchd agent
+hermes gateway start                 # Start the service
+hermes gateway stop                  # Stop the service
+hermes gateway status                # Check status
+tail -f ~/.hermes/logs/gateway.log   # View logs
 ```

+The generated plist lives at `~/Library/LaunchAgents/ai.hermes.gateway.plist`. It includes three environment variables:
+
+- **PATH** — your full shell PATH at install time, with the venv `bin/` and `node_modules/.bin` prepended. This ensures user-installed tools (Node.js, ffmpeg, etc.) are available to gateway subprocesses like the WhatsApp bridge.
+- **VIRTUAL_ENV** — points to the Python virtualenv so tools can resolve packages correctly.
+- **HERMES_HOME** — scopes the gateway to your Hermes installation.
+
+:::tip PATH changes after install
+launchd plists are static — if you install new tools (e.g. a new Node.js version via nvm, or ffmpeg via Homebrew) after setting up the gateway, run `hermes gateway install` again to capture the updated PATH. The gateway will detect the stale plist and reload automatically.
+:::
+
+:::info Multiple installations
+Like the Linux systemd service, each `HERMES_HOME` directory gets its own launchd label. The default `~/.hermes` uses `ai.hermes.gateway`; other installations use `ai.hermes.gateway-<suffix>`.
+:::
+
 ## Platform-Specific Toolsets

 Each platform has its own toolset:
@@ -36,22 +36,6 @@ brew install signal-cli
 # Extract and add to PATH
 ```

-### Alternative: Docker (signal-cli-rest-api)
-
-If you prefer Docker, use the [signal-cli-rest-api](https://github.com/bbernhard/signal-cli-rest-api) container:
-
-```bash
-docker run -d --name signal-cli \
-  -p 8080:8080 \
-  -v $HOME/.local/share/signal-cli:/home/.local/share/signal-cli \
-  -e MODE=json-rpc \
-  bbernhard/signal-cli-rest-api
-```
-
-:::tip
-Use `MODE=json-rpc` for best performance. The `normal` mode spawns a JVM per request and is much slower.
-:::
-
 ---

 ## Step 1: Link Your Signal Account
--- a/Show More
+++ b/Show More