fix: prevent context pressure warning spam (agent loop + gateway rate-limit)

Two complementary fixes for repeated context pressure warnings spamming
gateway users (Telegram, Discord, etc.):

1. Agent-level loop fix (run_agent.py):
   After compression, only reset _context_pressure_warned if the
   post-compression estimate is actually below the 85% warning level.
   Previously the flag was unconditionally reset, causing the warning
   to re-fire every loop iteration when compression couldn't reduce
   below 85% of the threshold (e.g. very low threshold like 15%,
   or system prompt alone exceeds the warning level).

2. Gateway-level rate-limit (gateway/run.py, salvaged from PR #3786):
   Per-chat_id cooldown of 1 hour on compression warning messages.
   Both warning paths ('still large after compression' and 'compression
   failed') are gated. Defense-in-depth — even if the agent-level fix
   has edge cases, users won't see more than one warning per hour.

Co-authored-by: dlkakbs <dlkakbs@users.noreply.github.com>

.dockerignore

@@ -0,0 +1,13 @@
+# Git
+.git
+.gitignore
+.gitmodules
+
+# Dependencies
+node_modules
+
+# CI/CD
+.github
+
+# Environment files
+.env

.env.example

@@ -45,14 +45,48 @@ MINIMAX_API_KEY=
 MINIMAX_CN_API_KEY=
 # MINIMAX_CN_BASE_URL=https://api.minimaxi.com/v1  # Override default base URL
 
+# =============================================================================
+# LLM PROVIDER (OpenCode Zen)
+# =============================================================================
+# OpenCode Zen provides curated, tested models (GPT, Claude, Gemini, MiniMax, GLM, Kimi)
+# Pay-as-you-go pricing. Get your key at: https://opencode.ai/auth
+OPENCODE_ZEN_API_KEY=
+# OPENCODE_ZEN_BASE_URL=https://opencode.ai/zen/v1  # Override default base URL
+
+# =============================================================================
+# LLM PROVIDER (OpenCode Go)
+# =============================================================================
+# OpenCode Go provides access to open models (GLM-5, Kimi K2.5, MiniMax M2.5)
+# $10/month subscription. Get your key at: https://opencode.ai/auth
+OPENCODE_GO_API_KEY=
+
+# =============================================================================
+# LLM PROVIDER (Hugging Face Inference Providers)
+# =============================================================================
+# Hugging Face routes to 20+ open models via unified OpenAI-compatible endpoint.
+# Free tier included ($0.10/month), no markup on provider rates.
+# Get your token at: https://huggingface.co/settings/tokens
+# Required permission: "Make calls to Inference Providers"
+HF_TOKEN=
+# OPENCODE_GO_BASE_URL=https://opencode.ai/zen/go/v1  # Override default base URL
+
 # =============================================================================
 # TOOL API KEYS
 # =============================================================================
 
+# Exa API Key - AI-native web search and contents
+# Get at: https://exa.ai
+EXA_API_KEY=
+
+# Parallel API Key - AI-native web search and extract
+# Get at: https://parallel.ai
+PARALLEL_API_KEY=
+
 # Firecrawl API Key - Web search, extract, and crawl
 # Get at: https://firecrawl.dev/
 FIRECRAWL_API_KEY=
 
+
 # FAL.ai API Key - Image generation
 # Get at: https://fal.ai/
 FAL_KEY=
@@ -64,7 +98,7 @@ FAL_KEY=
 HONCHO_API_KEY=
 
 # =============================================================================
-# TERMINAL TOOL CONFIGURATION (mini-swe-agent backend)
+# TERMINAL TOOL CONFIGURATION
 # =============================================================================
 # Backend type: "local", "singularity", "docker", "modal", or "ssh"
 # Terminal backend is configured in ~/.hermes/config.yaml (terminal.backend).
@@ -201,6 +235,18 @@ VOICE_TOOLS_OPENAI_KEY=
 # WHATSAPP_ENABLED=false
 # WHATSAPP_ALLOWED_USERS=15551234567
 
+# Email (IMAP/SMTP — send and receive emails as Hermes)
+# For Gmail: enable 2FA → create App Password at https://myaccount.google.com/apppasswords
+# EMAIL_ADDRESS=hermes@gmail.com
+# EMAIL_PASSWORD=xxxx xxxx xxxx xxxx
+# EMAIL_IMAP_HOST=imap.gmail.com
+# EMAIL_IMAP_PORT=993
+# EMAIL_SMTP_HOST=smtp.gmail.com
+# EMAIL_SMTP_PORT=587
+# EMAIL_POLL_INTERVAL=15
+# EMAIL_ALLOWED_USERS=your@email.com
+# EMAIL_HOME_ADDRESS=your@email.com
+
 # Gateway-wide: allow ALL users without an allowlist (default: false = deny)
 # Only set to true if you intentionally want open access.
 # GATEWAY_ALLOW_ALL_USERS=false
@@ -263,3 +309,27 @@ WANDB_API_KEY=
 # GITHUB_APP_ID=
 # GITHUB_APP_PRIVATE_KEY_PATH=
 # GITHUB_APP_INSTALLATION_ID=
+
+# Groq API key (free tier — used for Whisper STT in voice mode)
+# GROQ_API_KEY=
+
+# =============================================================================
+# STT PROVIDER SELECTION
+# =============================================================================
+# Default STT provider is "local" (faster-whisper) — runs on your machine, no API key needed.
+# Install with: pip install faster-whisper
+# Model downloads automatically on first use (~150 MB for "base").
+# To use cloud providers instead, set GROQ_API_KEY or VOICE_TOOLS_OPENAI_KEY above.
+# Provider priority: local > groq > openai
+# Configure in config.yaml: stt.provider: local | groq | openai
+
+# =============================================================================
+# STT ADVANCED OVERRIDES (optional)
+# =============================================================================
+# Override default STT models per provider (normally set via stt.model in config.yaml)
+# STT_GROQ_MODEL=whisper-large-v3-turbo
+# STT_OPENAI_MODEL=whisper-1
+
+# Override STT provider endpoints (for proxies or self-hosted instances)
+# GROQ_BASE_URL=https://api.groq.com/openai/v1
+# STT_OPENAI_BASE_URL=https://api.openai.com/v1

.envrc

@@ -0,0 +1 @@
+use flake

.github/workflows/docker-publish.yml

@@ -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

.github/workflows/docs-site-checks.yml

@@ -0,0 +1,39 @@
+name: Docs Site Checks
+
+on:
+  pull_request:
+    paths:
+      - 'website/**'
+      - '.github/workflows/docs-site-checks.yml'
+  workflow_dispatch:
+
+jobs:
+  docs-site-checks:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: actions/setup-node@v4
+        with:
+          node-version: 20
+          cache: npm
+          cache-dependency-path: website/package-lock.json
+
+      - name: Install website dependencies
+        run: npm ci
+        working-directory: website
+
+      - uses: actions/setup-python@v5
+        with:
+          python-version: '3.11'
+
+      - name: Install ascii-guard
+        run: python -m pip install ascii-guard
+
+      - name: Lint docs diagrams
+        run: npm run lint:diagrams
+        working-directory: website
+
+      - name: Build Docusaurus
+        run: npm run build
+        working-directory: website

.github/workflows/nix.yml

@@ -0,0 +1,40 @@
+name: Nix
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    paths:
+      - 'flake.nix'
+      - 'flake.lock'
+      - 'nix/**'
+      - 'pyproject.toml'
+      - 'uv.lock'
+      - 'hermes_cli/**'
+      - 'run_agent.py'
+      - 'acp_adapter/**'
+
+concurrency:
+  group: nix-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  nix:
+    strategy:
+      matrix:
+        os: [ubuntu-latest, macos-latest]
+    runs-on: ${{ matrix.os }}
+    timeout-minutes: 30
+    steps:
+      - uses: actions/checkout@v4
+      - uses: DeterminateSystems/nix-installer-action@main
+      - uses: DeterminateSystems/magic-nix-cache-action@main
+      - name: Check flake
+        if: runner.os == 'Linux'
+        run: nix flake check --print-build-logs
+      - name: Build package
+        if: runner.os == 'Linux'
+        run: nix build --print-build-logs
+      - name: Evaluate flake (macOS)
+        if: runner.os == 'macOS'
+        run: nix flake show --json > /dev/null

.github/workflows/supply-chain-audit.yml

@@ -0,0 +1,192 @@
+name: Supply Chain Audit
+
+on:
+  pull_request:
+    types: [opened, synchronize, reopened]
+
+permissions:
+  pull-requests: write
+  contents: read
+
+jobs:
+  scan:
+    name: Scan PR for supply chain risks
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Scan diff for suspicious patterns
+        id: scan
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        run: |
+          set -euo pipefail
+
+          BASE="${{ github.event.pull_request.base.sha }}"
+          HEAD="${{ github.event.pull_request.head.sha }}"
+
+          # Get the full diff (added lines only)
+          DIFF=$(git diff "$BASE".."$HEAD" -- . ':!uv.lock' ':!*.lock' ':!package-lock.json' ':!yarn.lock' || true)
+
+          FINDINGS=""
+          CRITICAL=false
+
+          # --- .pth files (auto-execute on Python startup) ---
+          PTH_FILES=$(git diff --name-only "$BASE".."$HEAD" | grep '\.pth$' || true)
+          if [ -n "$PTH_FILES" ]; then
+            CRITICAL=true
+            FINDINGS="${FINDINGS}
+          ### 🚨 CRITICAL: .pth file added or modified
+          Python \`.pth\` files in \`site-packages/\` execute automatically when the interpreter starts — no import required. This is the exact mechanism used in the [litellm supply chain attack](https://github.com/BerriAI/litellm/issues/24512).
+
+          **Files:**
+          \`\`\`
+          ${PTH_FILES}
+          \`\`\`
+          "
+          fi
+
+          # --- base64 + exec/eval combo (the litellm attack pattern) ---
+          B64_EXEC_HITS=$(echo "$DIFF" | grep -n '^\+' | grep -iE 'base64\.(b64decode|decodebytes|urlsafe_b64decode)' | grep -iE 'exec\(|eval\(' | head -10 || true)
+          if [ -n "$B64_EXEC_HITS" ]; then
+            CRITICAL=true
+            FINDINGS="${FINDINGS}
+          ### 🚨 CRITICAL: base64 decode + exec/eval combo
+          This is the exact pattern used in the [litellm supply chain attack](https://github.com/BerriAI/litellm/issues/24512) — base64-decoded strings passed to exec/eval to hide credential-stealing payloads.
+
+          **Matches:**
+          \`\`\`
+          ${B64_EXEC_HITS}
+          \`\`\`
+          "
+          fi
+
+          # --- base64 decode/encode (alone — legitimate uses exist) ---
+          B64_HITS=$(echo "$DIFF" | grep -n '^\+' | grep -iE 'base64\.(b64decode|b64encode|decodebytes|encodebytes|urlsafe_b64decode)|atob\(|btoa\(|Buffer\.from\(.*base64' | head -20 || true)
+          if [ -n "$B64_HITS" ]; then
+            FINDINGS="${FINDINGS}
+          ### ⚠️ WARNING: base64 encoding/decoding detected
+          Base64 has legitimate uses (images, JWT, etc.) but is also commonly used to obfuscate malicious payloads. Verify the usage is appropriate.
+
+          **Matches (first 20):**
+          \`\`\`
+          ${B64_HITS}
+          \`\`\`
+          "
+          fi
+
+          # --- exec/eval with string arguments ---
+          EXEC_HITS=$(echo "$DIFF" | grep -n '^\+' | grep -E '(exec|eval)\s*\(' | grep -v '^\+\s*#' | grep -v 'test_\|mock\|assert\|# ' | head -20 || true)
+          if [ -n "$EXEC_HITS" ]; then
+            FINDINGS="${FINDINGS}
+          ### ⚠️ WARNING: exec() or eval() usage
+          Dynamic code execution can hide malicious behavior, especially when combined with base64 or network fetches.
+
+          **Matches (first 20):**
+          \`\`\`
+          ${EXEC_HITS}
+          \`\`\`
+          "
+          fi
+
+          # --- subprocess with encoded/obfuscated commands ---
+          PROC_HITS=$(echo "$DIFF" | grep -n '^\+' | grep -E 'subprocess\.(Popen|call|run)\s*\(' | grep -iE 'base64|decode|encode|\\x|chr\(' | head -10 || true)
+          if [ -n "$PROC_HITS" ]; then
+            CRITICAL=true
+            FINDINGS="${FINDINGS}
+          ### 🚨 CRITICAL: subprocess with encoded/obfuscated command
+          Subprocess calls with encoded arguments are a strong indicator of payload execution.
+
+          **Matches:**
+          \`\`\`
+          ${PROC_HITS}
+          \`\`\`
+          "
+          fi
+
+          # --- Network calls to non-standard domains ---
+          EXFIL_HITS=$(echo "$DIFF" | grep -n '^\+' | grep -iE 'requests\.(post|put)\(|httpx\.(post|put)\(|urllib\.request\.urlopen' | grep -v '^\+\s*#' | grep -v 'test_\|mock\|assert' | head -10 || true)
+          if [ -n "$EXFIL_HITS" ]; then
+            FINDINGS="${FINDINGS}
+          ### ⚠️ WARNING: Outbound network calls (POST/PUT)
+          Outbound POST/PUT requests in new code could be data exfiltration. Verify the destination URLs are legitimate.
+
+          **Matches (first 10):**
+          \`\`\`
+          ${EXFIL_HITS}
+          \`\`\`
+          "
+          fi
+
+          # --- setup.py / setup.cfg install hooks ---
+          SETUP_HITS=$(git diff --name-only "$BASE".."$HEAD" | grep -E '(setup\.py|setup\.cfg|__init__\.pth|sitecustomize\.py|usercustomize\.py)$' || true)
+          if [ -n "$SETUP_HITS" ]; then
+            FINDINGS="${FINDINGS}
+          ### ⚠️ WARNING: Install hook files modified
+          These files can execute code during package installation or interpreter startup.
+
+          **Files:**
+          \`\`\`
+          ${SETUP_HITS}
+          \`\`\`
+          "
+          fi
+
+          # --- Compile/marshal/pickle (code object injection) ---
+          MARSHAL_HITS=$(echo "$DIFF" | grep -n '^\+' | grep -iE 'marshal\.loads|pickle\.loads|compile\(' | grep -v '^\+\s*#' | grep -v 'test_\|re\.compile\|ast\.compile' | head -10 || true)
+          if [ -n "$MARSHAL_HITS" ]; then
+            FINDINGS="${FINDINGS}
+          ### ⚠️ WARNING: marshal/pickle/compile usage
+          These can deserialize or construct executable code objects.
+
+          **Matches:**
+          \`\`\`
+          ${MARSHAL_HITS}
+          \`\`\`
+          "
+          fi
+
+          # --- Output results ---
+          if [ -n "$FINDINGS" ]; then
+            echo "found=true" >> "$GITHUB_OUTPUT"
+            if [ "$CRITICAL" = true ]; then
+              echo "critical=true" >> "$GITHUB_OUTPUT"
+            else
+              echo "critical=false" >> "$GITHUB_OUTPUT"
+            fi
+            # Write findings to a file (multiline env vars are fragile)
+            echo "$FINDINGS" > /tmp/findings.md
+          else
+            echo "found=false" >> "$GITHUB_OUTPUT"
+            echo "critical=false" >> "$GITHUB_OUTPUT"
+          fi
+
+      - name: Post warning comment
+        if: steps.scan.outputs.found == 'true'
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        run: |
+          SEVERITY="⚠️ Supply Chain Risk Detected"
+          if [ "${{ steps.scan.outputs.critical }}" = "true" ]; then
+            SEVERITY="🚨 CRITICAL Supply Chain Risk Detected"
+          fi
+
+          BODY="## ${SEVERITY}
+
+          This PR contains patterns commonly associated with supply chain attacks. This does **not** mean the PR is malicious — but these patterns require careful human review before merging.
+
+          $(cat /tmp/findings.md)
+
+          ---
+          *Automated scan triggered by [supply-chain-audit](/.github/workflows/supply-chain-audit.yml). If this is a false positive, a maintainer can approve after manual review.*"
+
+          gh pr comment "${{ github.event.pull_request.number }}" --body "$BODY"
+
+      - name: Fail on critical findings
+        if: steps.scan.outputs.critical == 'true'
+        run: |
+          echo "::error::CRITICAL supply chain risk patterns detected in this PR. See the PR comment for details."
+          exit 1

.gitignore

@@ -1,51 +1,60 @@
-/venv/
-/_pycache/
-*.pyc*
-__pycache__/
-.venv/
-.vscode/
-.env
-.env.local
-.env.development.local
-.env.test.local
-.env.production.local
-.env.development
-.env.test
-export*
-__pycache__/model_tools.cpython-310.pyc
-__pycache__/web_tools.cpython-310.pyc
-logs/
-data/
-.pytest_cache/
-tmp/
-temp_vision_images/
-hermes-*/*
-examples/
-tests/quick_test_dataset.jsonl
-tests/sample_dataset.jsonl
-run_datagen_kimik2-thinking.sh
-run_datagen_megascience_glm4-6.sh
-run_datagen_sonnet.sh
-source-data/*
-run_datagen_megascience_glm4-6.sh
-data/*
-node_modules/
-browser-use/
-agent-browser/
-# Private keys
-*.ppk
-*.pem
-privvy*
-images/
-__pycache__/
-hermes_agent.egg-info/
-wandb/
-testlogs
-
-# CLI config (may contain sensitive SSH paths)
-cli-config.yaml
-
-# Skills Hub state (lives in ~/.hermes/skills/.hub/ at runtime, but just in case)
-skills/.hub/
+/venv/
+/_pycache/
+*.pyc*
+__pycache__/
+.venv/
+.vscode/
+.env
+.env.local
+.env.development.local
+.env.test.local
+.env.production.local
+.env.development
+.env.test
+export*
+__pycache__/model_tools.cpython-310.pyc
+__pycache__/web_tools.cpython-310.pyc
+logs/
+data/
+.pytest_cache/
+tmp/
+temp_vision_images/
+hermes-*/*
+examples/
+tests/quick_test_dataset.jsonl
+tests/sample_dataset.jsonl
+run_datagen_kimik2-thinking.sh
+run_datagen_megascience_glm4-6.sh
+run_datagen_sonnet.sh
+source-data/*
+run_datagen_megascience_glm4-6.sh
+data/*
+node_modules/
+browser-use/
+agent-browser/
+# Private keys
+*.ppk
+*.pem
+privvy*
+images/
+__pycache__/
+hermes_agent.egg-info/
+wandb/
+testlogs
+
+# CLI config (may contain sensitive SSH paths)
+cli-config.yaml
+
+# Skills Hub state (lives in ~/.hermes/skills/.hub/ at runtime, but just in case)
+skills/.hub/
 ignored/
 .worktrees/
+environments/benchmarks/evals/
+
+# Release script temp files
+.release_notes.md
+mini-swe-agent/
+
+# Nix
+.direnv/
+result

.gitmodules

@@ -1,6 +1,3 @@
-[submodule "mini-swe-agent"]
-	path = mini-swe-agent
-	url = https://github.com/SWE-agent/mini-swe-agent
 [submodule "tinker-atropos"]
 	path = tinker-atropos
 	url = https://github.com/nousresearch/tinker-atropos

.plans/openai-api-server.md

@@ -0,0 +1,291 @@
+# OpenAI-Compatible API Server for Hermes Agent
+
+## Motivation
+
+Every major chat frontend (Open WebUI 126k★, LobeChat 73k★, LibreChat 34k★,
+AnythingLLM 56k★, NextChat 87k★, ChatBox 39k★, Jan 26k★, HF Chat-UI 8k★,
+big-AGI 7k★) connects to backends via the OpenAI-compatible REST API with
+SSE streaming. By exposing this endpoint, hermes-agent becomes instantly
+usable as a backend for all of them — no custom adapters needed.
+
+## What It Enables
+
+```
+┌──────────────────┐
+│  Open WebUI      │──┐
+│  LobeChat        │  │    POST /v1/chat/completions
+│  LibreChat       │  ├──► Authorization: Bearer <key>     ┌─────────────────┐
+│  AnythingLLM     │  │    {"messages": [...]}             │  hermes-agent   │
+│  NextChat        │  │                                    │  gateway        │
+│  Any OAI client  │──┘    ◄── SSE streaming response      │  (API server)   │
+└──────────────────┘                                        └─────────────────┘
+```
+
+A user would:
+1. Set `API_SERVER_ENABLED=true` in `~/.hermes/.env`
+2. Run `hermes gateway` (API server starts alongside Telegram/Discord/etc.)
+3. Point Open WebUI (or any frontend) at `http://localhost:8642/v1`
+4. Chat with hermes-agent through any OpenAI-compatible UI
+
+## Endpoints
+
+| Method | Path | Purpose |
+|--------|------|---------|
+| POST | `/v1/chat/completions` | Chat with the agent (streaming + non-streaming) |
+| GET | `/v1/models` | List available "models" (returns hermes-agent as a model) |
+| GET | `/health` | Health check |
+
+## Architecture
+
+### Option A: Gateway Platform Adapter (recommended)
+
+Create `gateway/platforms/api_server.py` as a new platform adapter that
+extends `BasePlatformAdapter`. This is the cleanest approach because:
+
+- Reuses all gateway infrastructure (session management, auth, context building)
+- Runs in the same async loop as other adapters
+- Gets message handling, interrupt support, and session persistence for free
+- Follows the established pattern (like Telegram, Discord, etc.)
+- Uses `aiohttp.web` (already a dependency) for the HTTP server
+
+The adapter would start an `aiohttp.web.Application` server in `connect()`
+and route incoming HTTP requests through the standard `handle_message()` pipeline.
+
+### Option B: Standalone Component
+
+A separate HTTP server class in `gateway/api_server.py` that creates its own
+AIAgent instances directly. Simpler but duplicates session/auth logic.
+
+**Recommendation: Option A** — fits the existing architecture, less code to
+maintain, gets all gateway features for free.
+
+## Request/Response Format
+
+### Chat Completions (non-streaming)
+
+```
+POST /v1/chat/completions
+Authorization: Bearer hermes-api-key-here
+Content-Type: application/json
+
+{
+  "model": "hermes-agent",
+  "messages": [
+    {"role": "system", "content": "You are a helpful assistant."},
+    {"role": "user", "content": "What files are in the current directory?"}
+  ],
+  "stream": false,
+  "temperature": 0.7
+}
+```
+
+Response:
+```json
+{
+  "id": "chatcmpl-abc123",
+  "object": "chat.completion",
+  "created": 1710000000,
+  "model": "hermes-agent",
+  "choices": [{
+    "index": 0,
+    "message": {
+      "role": "assistant",
+      "content": "Here are the files in the current directory:\n..."
+    },
+    "finish_reason": "stop"
+  }],
+  "usage": {
+    "prompt_tokens": 50,
+    "completion_tokens": 200,
+    "total_tokens": 250
+  }
+}
+```
+
+### Chat Completions (streaming)
+
+Same request with `"stream": true`. Response is SSE:
+
+```
+data: {"id":"chatcmpl-abc123","object":"chat.completion.chunk","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
+
+data: {"id":"chatcmpl-abc123","object":"chat.completion.chunk","choices":[{"index":0,"delta":{"content":"Here "},"finish_reason":null}]}
+
+data: {"id":"chatcmpl-abc123","object":"chat.completion.chunk","choices":[{"index":0,"delta":{"content":"are "},"finish_reason":null}]}
+
+data: {"id":"chatcmpl-abc123","object":"chat.completion.chunk","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
+
+data: [DONE]
+```
+
+### Models List
+
+```
+GET /v1/models
+Authorization: Bearer hermes-api-key-here
+```
+
+Response:
+```json
+{
+  "object": "list",
+  "data": [{
+    "id": "hermes-agent",
+    "object": "model",
+    "created": 1710000000,
+    "owned_by": "hermes-agent"
+  }]
+}
+```
+
+## Key Design Decisions
+
+### 1. Session Management
+
+The OpenAI API is stateless — each request includes the full conversation.
+But hermes-agent sessions have persistent state (memory, skills, tool context).
+
+**Approach: Hybrid**
+- Default: Stateless. Each request is independent. The `messages` array IS
+  the conversation. No session persistence between requests.
+- Opt-in persistent sessions via `X-Session-ID` header. When provided, the
+  server maintains session state across requests (conversation history,
+  memory context, tool state). This enables richer agent behavior.
+- The session ID also enables interrupt support — a subsequent request with
+  the same session ID while one is running triggers an interrupt.
+
+### 2. Streaming
+
+The agent's `run_conversation()` is synchronous and returns the full response.
+For real SSE streaming, we need to emit chunks as they're generated.
+
+**Phase 1 (MVP):** Run agent in a thread, return the complete response as
+a single SSE chunk + `[DONE]`. This works with all frontends — they just see
+a fast single-chunk response. Not true streaming but functional.
+
+**Phase 2:** Add a response callback to AIAgent that emits text chunks as the
+LLM generates them. The API server captures these via a queue and streams them
+as SSE events. This gives real token-by-token streaming.
+
+**Phase 3:** Stream tool execution progress too — emit tool call/result events
+as the agent works, giving frontends visibility into what the agent is doing.
+
+### 3. Tool Transparency
+
+Two modes:
+- **Opaque (default):** Frontends see only the final response. Tool calls
+  happen server-side and are invisible. Best for general-purpose UIs.
+- **Transparent (opt-in via header):** Tool calls are emitted as OpenAI-format
+  tool_call/tool_result messages in the stream. Useful for agent-aware frontends.
+
+### 4. Authentication
+
+- Bearer token via `Authorization: Bearer <key>` header
+- Token configured via `API_SERVER_KEY` env var
+- Optional: allow unauthenticated local-only access (127.0.0.1 bind)
+- Follows the same pattern as other platform adapters
+
+### 5. Model Mapping
+
+Frontends send `"model": "hermes-agent"` (or whatever). The actual LLM model
+used is configured server-side in config.yaml. The API server maps any
+requested model name to the configured hermes-agent model.
+
+Optionally, allow model passthrough: if the frontend sends
+`"model": "anthropic/claude-sonnet-4"`, the agent uses that model. Controlled
+by a config flag.
+
+## Configuration
+
+```yaml
+# In config.yaml
+api_server:
+  enabled: true
+  port: 8642
+  host: "127.0.0.1"        # localhost only by default
+  key: "your-secret-key"   # or via API_SERVER_KEY env var
+  allow_model_override: false  # let clients choose the model
+  max_concurrent: 5         # max simultaneous requests
+```
+
+Environment variables:
+```bash
+API_SERVER_ENABLED=true
+API_SERVER_PORT=8642
+API_SERVER_HOST=127.0.0.1
+API_SERVER_KEY=your-secret-key
+```
+
+## Implementation Plan
+
+### Phase 1: MVP (non-streaming) — PR
+
+1. `gateway/platforms/api_server.py` — new adapter
+   - aiohttp.web server with endpoints:
+     - `POST /v1/chat/completions` — Chat Completions API (universal compat)
+     - `POST /v1/responses` — Responses API (server-side state, tool preservation)
+     - `GET /v1/models` — list available models
+     - `GET /health` — health check
+   - Bearer token auth middleware
+   - Non-streaming responses (run agent, return full result)
+   - Chat Completions: stateless, messages array is the conversation
+   - Responses API: server-side conversation storage via previous_response_id
+     - Store full internal conversation (including tool calls) keyed by response ID
+     - On subsequent requests, reconstruct full context from stored chain
+   - Frontend system prompt layered on top of hermes-agent's core prompt
+
+2. `gateway/config.py` — add `Platform.API_SERVER` enum + config
+
+3. `gateway/run.py` — register adapter in `_create_adapter()`
+
+4. Tests in `tests/gateway/test_api_server.py`
+
+### Phase 2: SSE Streaming
+
+1. Add response streaming to both endpoints
+   - Chat Completions: `choices[0].delta.content` SSE format
+   - Responses API: semantic events (response.output_text.delta, etc.)
+   - Run agent in thread, collect output via callback queue
+   - Handle client disconnect (cancel agent)
+
+2. Add `stream_callback` parameter to `AIAgent.run_conversation()`
+
+### Phase 3: Enhanced Features
+
+1. Tool call transparency mode (opt-in)
+2. Model passthrough/override
+3. Concurrent request limiting
+4. Usage tracking / rate limiting
+5. CORS headers for browser-based frontends
+6. GET /v1/responses/{id} — retrieve stored response
+7. DELETE /v1/responses/{id} — delete stored response
+
+## Files Changed
+
+| File | Change |
+|------|--------|
+| `gateway/platforms/api_server.py` | NEW — main adapter (~300 lines) |
+| `gateway/config.py` | Add Platform.API_SERVER + config (~20 lines) |
+| `gateway/run.py` | Register adapter in _create_adapter() (~10 lines) |
+| `tests/gateway/test_api_server.py` | NEW — tests (~200 lines) |
+| `cli-config.yaml.example` | Add api_server section |
+| `README.md` | Mention API server in platform list |
+
+## Compatibility Matrix
+
+Once implemented, hermes-agent works as a drop-in backend for:
+
+| Frontend | Stars | How to Connect |
+|----------|-------|---------------|
+| Open WebUI | 126k | Settings → Connections → Add OpenAI API, URL: `http://localhost:8642/v1` |
+| NextChat | 87k | BASE_URL env var |
+| LobeChat | 73k | Custom provider endpoint |
+| AnythingLLM | 56k | LLM Provider → Generic OpenAI |
+| Oobabooga | 42k | Already a backend, not a frontend |
+| ChatBox | 39k | API Host setting |
+| LibreChat | 34k | librechat.yaml custom endpoint |
+| Chatbot UI | 29k | Custom API endpoint |
+| Jan | 26k | Remote model config |
+| AionUI | 18k | Custom API endpoint |
+| HF Chat-UI | 8k | OPENAI_BASE_URL env var |
+| big-AGI | 7k | Custom endpoint |

.plans/streaming-support.md

@@ -0,0 +1,705 @@
+# Streaming LLM Response Support for Hermes Agent
+
+## Overview
+
+Add token-by-token streaming of LLM responses across all platforms. When enabled,
+users see the response typing out live instead of waiting for the full generation.
+Streaming is opt-in via config, defaults to off, and all existing non-streaming
+code paths remain intact as the default.
+
+## Design Principles
+
+1. **Feature-flagged**: `streaming.enabled: true` in config.yaml. Off by default.
+   When off, all existing code paths are unchanged — zero risk to current behavior.
+2. **Callback-based**: A simple `stream_callback(text_delta: str)` function injected
+   into AIAgent. The agent doesn't know or care what the consumer does with tokens.
+3. **Graceful degradation**: If the provider doesn't support streaming, or streaming
+   fails for any reason, silently fall back to the non-streaming path.
+4. **Platform-agnostic core**: The streaming mechanism in AIAgent works the same
+   regardless of whether the consumer is CLI, Telegram, Discord, or the API server.
+
+---
+
+## Architecture
+
+```
+                              stream_callback(delta)
+                                    │
+  ┌─────────────┐    ┌─────────────▼──────────────┐
+  │  LLM API    │    │      queue.Queue()          │
+  │  (stream)   │───►│  thread-safe bridge between │
+  │             │    │  agent thread & consumer    │
+  └─────────────┘    └─────────────┬──────────────┘
+                                   │
+                    ┌──────────────┼──────────────┐
+                    │              │              │
+              ┌─────▼─────┐ ┌─────▼─────┐ ┌─────▼─────┐
+              │    CLI     │ │  Gateway  │ │ API Server│
+              │ print to   │ │ edit msg  │ │ SSE event │
+              │ terminal   │ │ on Tg/Dc  │ │ to client │
+              └───────────┘ └───────────┘ └───────────┘
+```
+
+The agent runs in a thread. The callback puts tokens into a thread-safe queue.
+Each consumer reads the queue in its own context (async task, main thread, etc.).
+
+---
+
+## Configuration
+
+### config.yaml
+
+```yaml
+streaming:
+  enabled: false          # Master switch. Default off.
+  # Per-platform overrides (optional):
+  # cli: true             # Override for CLI only
+  # telegram: true        # Override for Telegram only
+  # discord: false        # Keep Discord non-streaming
+  # api_server: true      # Override for API server
+```
+
+### Environment variables
+
+```
+HERMES_STREAMING_ENABLED=true    # Master switch via env
+```
+
+### How the flag is read
+
+- **CLI**: `load_cli_config()` reads `streaming.enabled`, sets env var. AIAgent
+  checks at init time.
+- **Gateway**: `_run_agent()` reads config, decides whether to pass
+  `stream_callback` to the AIAgent constructor.
+- **API server**: For Chat Completions `stream=true` requests, always uses streaming
+  regardless of config (the client is explicitly requesting it). For non-stream
+  requests, uses config.
+
+### Precedence
+
+1. API server: client's `stream` field overrides everything
+2. Per-platform config override (e.g., `streaming.telegram: true`)
+3. Master `streaming.enabled` flag
+4. Default: off
+
+---
+
+## Implementation Plan
+
+### Phase 1: Core streaming infrastructure in AIAgent
+
+**File: run_agent.py**
+
+#### 1a. Add stream_callback parameter to __init__ (~5 lines)
+
+```python
+def __init__(self, ..., stream_callback: callable = None, ...):
+    self.stream_callback = stream_callback
+```
+
+No other init changes. The callback is optional — when None, everything
+works exactly as before.
+
+#### 1b. Add _run_streaming_chat_completion() method (~65 lines)
+
+New method for Chat Completions API streaming:
+
+```python
+def _run_streaming_chat_completion(self, api_kwargs: dict):
+    """Stream a chat completion, emitting text tokens via stream_callback.
+    
+    Returns a fake response object compatible with the non-streaming code path.
+    Falls back to non-streaming on any error.
+    """
+    stream_kwargs = dict(api_kwargs)
+    stream_kwargs["stream"] = True
+    stream_kwargs["stream_options"] = {"include_usage": True}
+    
+    accumulated_content = []
+    accumulated_tool_calls = {}  # index -> {id, name, arguments}
+    final_usage = None
+    
+    try:
+        stream = self.client.chat.completions.create(**stream_kwargs)
+        
+        for chunk in stream:
+            if not chunk.choices:
+                # Usage-only chunk (final)
+                if chunk.usage:
+                    final_usage = chunk.usage
+                continue
+            
+            delta = chunk.choices[0].delta
+            
+            # Text content — emit via callback
+            if delta.content:
+                accumulated_content.append(delta.content)
+                if self.stream_callback:
+                    try:
+                        self.stream_callback(delta.content)
+                    except Exception:
+                        pass
+            
+            # Tool call deltas — accumulate silently
+            if delta.tool_calls:
+                for tc_delta in delta.tool_calls:
+                    idx = tc_delta.index
+                    if idx not in accumulated_tool_calls:
+                        accumulated_tool_calls[idx] = {
+                            "id": tc_delta.id or "",
+                            "name": "", "arguments": ""
+                        }
+                    if tc_delta.function:
+                        if tc_delta.function.name:
+                            accumulated_tool_calls[idx]["name"] = tc_delta.function.name
+                        if tc_delta.function.arguments:
+                            accumulated_tool_calls[idx]["arguments"] += tc_delta.function.arguments
+        
+        # Build fake response compatible with existing code
+        tool_calls = []
+        for idx in sorted(accumulated_tool_calls):
+            tc = accumulated_tool_calls[idx]
+            if tc["name"]:
+                tool_calls.append(SimpleNamespace(
+                    id=tc["id"], type="function",
+                    function=SimpleNamespace(name=tc["name"], arguments=tc["arguments"]),
+                ))
+        
+        return SimpleNamespace(
+            choices=[SimpleNamespace(
+                message=SimpleNamespace(
+                    content="".join(accumulated_content) or "",
+                    tool_calls=tool_calls or None,
+                    role="assistant",
+                ),
+                finish_reason="tool_calls" if tool_calls else "stop",
+            )],
+            usage=final_usage,
+            model=self.model,
+        )
+    
+    except Exception as e:
+        logger.debug("Streaming failed, falling back to non-streaming: %s", e)
+        return self.client.chat.completions.create(**api_kwargs)
+```
+
+#### 1c. Modify _run_codex_stream() for Responses API (~10 lines)
+
+The method already iterates the stream. Add callback emission:
+
+```python
+def _run_codex_stream(self, api_kwargs: dict):
+    with self.client.responses.stream(**api_kwargs) as stream:
+        for event in stream:
+            # Emit text deltas if streaming callback is set
+            if self.stream_callback and hasattr(event, 'type'):
+                if event.type == 'response.output_text.delta':
+                    try:
+                        self.stream_callback(event.delta)
+                    except Exception:
+                        pass
+        return stream.get_final_response()
+```
+
+#### 1d. Modify _interruptible_api_call() (~5 lines)
+
+Add the streaming branch:
+
+```python
+def _call():
+    try:
+        if self.api_mode == "codex_responses":
+            result["response"] = self._run_codex_stream(api_kwargs)
+        elif self.stream_callback is not None:
+            result["response"] = self._run_streaming_chat_completion(api_kwargs)
+        else:
+            result["response"] = self.client.chat.completions.create(**api_kwargs)
+    except Exception as e:
+        result["error"] = e
+```
+
+#### 1e. Signal end-of-stream to consumers (~5 lines)
+
+After the API call returns, signal the callback that streaming is done
+so consumers can finalize (remove cursor, close SSE, etc.):
+
+```python
+# In run_conversation(), after _interruptible_api_call returns:
+if self.stream_callback:
+    try:
+        self.stream_callback(None)  # None = end of stream signal
+    except Exception:
+        pass
+```
+
+Consumers check: `if delta is None: finalize()`
+
+**Tests for Phase 1:** (~150 lines)
+- Test _run_streaming_chat_completion with mocked stream
+- Test fallback to non-streaming on error
+- Test tool_call accumulation during streaming
+- Test stream_callback receives correct deltas
+- Test None signal at end of stream
+- Test streaming disabled when callback is None
+
+---
+
+### Phase 2: Gateway consumers (Telegram, Discord, etc.)
+
+**File: gateway/run.py**
+
+#### 2a. Read streaming config (~15 lines)
+
+In `_run_agent()`, before creating the AIAgent:
+
+```python
+# Read streaming config
+_streaming_enabled = False
+try:
+    # Check per-platform override first
+    platform_key = source.platform.value if source.platform else ""
+    _stream_cfg = {}  # loaded from config.yaml streaming section
+    if _stream_cfg.get(platform_key) is not None:
+        _streaming_enabled = bool(_stream_cfg[platform_key])
+    else:
+        _streaming_enabled = bool(_stream_cfg.get("enabled", False))
+except Exception:
+    pass
+# Env var override
+if os.getenv("HERMES_STREAMING_ENABLED", "").lower() in ("true", "1", "yes"):
+    _streaming_enabled = True
+```
+
+#### 2b. Set up queue + callback (~15 lines)
+
+```python
+_stream_q = None
+_stream_done = None
+_stream_msg_id = [None]  # mutable ref for the async task
+
+if _streaming_enabled:
+    import queue as _q
+    _stream_q = _q.Queue()
+    _stream_done = threading.Event()
+    
+    def _on_token(delta):
+        if delta is None:
+            _stream_done.set()
+        else:
+            _stream_q.put(delta)
+```
+
+Pass `stream_callback=_on_token` to the AIAgent constructor.
+
+#### 2c. Telegram/Discord stream preview task (~50 lines)
+
+```python
+async def stream_preview():
+    """Progressively edit a message with streaming tokens."""
+    if not _stream_q:
+        return
+    adapter = self.adapters.get(source.platform)
+    if not adapter:
+        return
+    
+    accumulated = []
+    token_count = 0
+    last_edit = 0.0
+    MIN_TOKENS = 20          # Don't show until enough context
+    EDIT_INTERVAL = 1.5      # Respect Telegram rate limits
+    
+    try:
+        while not _stream_done.is_set():
+            try:
+                chunk = _stream_q.get(timeout=0.1)
+                accumulated.append(chunk)
+                token_count += 1
+            except queue.Empty:
+                continue
+            
+            now = time.monotonic()
+            if token_count >= MIN_TOKENS and (now - last_edit) >= EDIT_INTERVAL:
+                preview = "".join(accumulated) + " ▌"
+                if _stream_msg_id[0] is None:
+                    r = await adapter.send(
+                        chat_id=source.chat_id,
+                        content=preview,
+                        metadata=_thread_metadata,
+                    )
+                    if r.success and r.message_id:
+                        _stream_msg_id[0] = r.message_id
+                else:
+                    await adapter.edit_message(
+                        chat_id=source.chat_id,
+                        message_id=_stream_msg_id[0],
+                        content=preview,
+                    )
+                last_edit = now
+        
+        # Drain remaining tokens
+        while not _stream_q.empty():
+            accumulated.append(_stream_q.get_nowait())
+        
+        # Final edit — remove cursor, show complete text
+        if _stream_msg_id[0] and accumulated:
+            await adapter.edit_message(
+                chat_id=source.chat_id,
+                message_id=_stream_msg_id[0],
+                content="".join(accumulated),
+            )
+    
+    except asyncio.CancelledError:
+        # Clean up on cancel
+        if _stream_msg_id[0] and accumulated:
+            try:
+                await adapter.edit_message(
+                    chat_id=source.chat_id,
+                    message_id=_stream_msg_id[0],
+                    content="".join(accumulated),
+                )
+            except Exception:
+                pass
+    except Exception as e:
+        logger.debug("stream_preview error: %s", e)
+```
+
+#### 2d. Skip final send if already streamed (~10 lines)
+
+In `_process_message_background()` (base.py), after getting the response,
+if streaming was active and `_stream_msg_id[0]` is set, the final response
+was already delivered via progressive edits. Skip the normal `self.send()`
+call to avoid duplicating the message.
+
+This is the most delicate integration point — we need to communicate from
+the gateway's `_run_agent` back to the base adapter's response sender that
+the response was already delivered. Options:
+
+- **Option A**: Return a special marker in the result dict:
+  `result["_streamed_msg_id"] = _stream_msg_id[0]`
+  The base adapter checks this and skips `send()`.
+  
+- **Option B**: Edit the already-sent message with the final response
+  (which may differ slightly from accumulated tokens due to think-block
+  stripping, etc.) and don't send a new one.
+
+- **Option C**: The stream preview task handles the FULL final response
+  (including any post-processing), and the handler returns None to skip
+  the normal send path.
+
+Recommended: **Option A** — cleanest separation. The result dict already
+carries metadata; adding one more field is low-risk.
+
+**Platform-specific considerations:**
+
+| Platform | Edit support | Rate limits | Streaming approach |
+|----------|-------------|-------------|-------------------|
+| Telegram | ✅ edit_message_text | ~20 edits/min | Edit every 1.5s |
+| Discord | ✅ message.edit | 5 edits/5s per message | Edit every 1.2s |
+| Slack | ✅ chat.update | Tier 3 (~50/min) | Edit every 1.5s |
+| WhatsApp | ❌ no edit support | N/A | Skip streaming, use normal path |
+| HomeAssistant | ❌ no edit | N/A | Skip streaming |
+| API Server | ✅ SSE native | No limit | Real SSE events |
+
+WhatsApp and HomeAssistant fall back to non-streaming automatically because
+they don't support message editing.
+
+**Tests for Phase 2:** (~100 lines)
+- Test stream_preview sends/edits correctly
+- Test skip-final-send when streaming delivered
+- Test WhatsApp/HA graceful fallback
+- Test streaming disabled per-platform config
+- Test thread_id metadata forwarded in stream messages
+
+---
+
+### Phase 3: CLI streaming
+
+**File: cli.py**
+
+#### 3a. Set up callback in the CLI chat loop (~20 lines)
+
+In `_chat_once()` or wherever the agent is invoked:
+
+```python
+if streaming_enabled:
+    _stream_q = queue.Queue()
+    _stream_done = threading.Event()
+    
+    def _cli_stream_callback(delta):
+        if delta is None:
+            _stream_done.set()
+        else:
+            _stream_q.put(delta)
+    
+    agent.stream_callback = _cli_stream_callback
+```
+
+#### 3b. Token display thread/task (~30 lines)
+
+Start a thread that reads the queue and prints tokens:
+
+```python
+def _stream_display():
+    """Print tokens to terminal as they arrive."""
+    first_token = True
+    while not _stream_done.is_set():
+        try:
+            delta = _stream_q.get(timeout=0.1)
+        except queue.Empty:
+            continue
+        if first_token:
+            # Print response box top border
+            _cprint(f"\n{top}")
+            first_token = False
+        sys.stdout.write(delta)
+        sys.stdout.flush()
+    # Drain remaining
+    while not _stream_q.empty():
+        sys.stdout.write(_stream_q.get_nowait())
+    sys.stdout.flush()
+    # Print bottom border
+    _cprint(f"\n\n{bot}")
+```
+
+**Integration challenge: prompt_toolkit**
+
+The CLI uses prompt_toolkit which controls the terminal. Writing directly
+to stdout while prompt_toolkit is active can cause display corruption.
+The existing KawaiiSpinner already solves this by using prompt_toolkit's
+`patch_stdout` context. The streaming display would need to do the same.
+
+Alternative: use `_cprint()` for each token chunk (routes through
+prompt_toolkit's renderer). But this might be slow for individual tokens.
+
+Recommended approach: accumulate tokens in small batches (e.g., every 50ms)
+and `_cprint()` the batch. This balances display responsiveness with
+prompt_toolkit compatibility.
+
+**Tests for Phase 3:** (~50 lines)
+- Test CLI streaming callback setup
+- Test response box borders with streaming
+- Test fallback when streaming disabled
+
+---
+
+### Phase 4: API Server real streaming
+
+**File: gateway/platforms/api_server.py**
+
+Replace the pseudo-streaming `_write_sse_chat_completion()` with real
+token-by-token SSE when the agent supports it.
+
+#### 4a. Wire streaming callback for stream=true requests (~20 lines)
+
+```python
+if stream:
+    _stream_q = queue.Queue()
+    
+    def _api_stream_callback(delta):
+        _stream_q.put(delta)  # None = done
+    
+    # Pass callback to _run_agent
+    result, usage = await self._run_agent(
+        ..., stream_callback=_api_stream_callback,
+    )
+```
+
+#### 4b. Real SSE writer (~40 lines)
+
+```python
+async def _write_real_sse(self, request, completion_id, model, stream_q):
+    response = web.StreamResponse(
+        headers={"Content-Type": "text/event-stream", "Cache-Control": "no-cache"},
+    )
+    await response.prepare(request)
+    
+    # Role chunk
+    await response.write(...)
+    
+    # Stream content chunks as they arrive
+    while True:
+        try:
+            delta = await asyncio.get_event_loop().run_in_executor(
+                None, lambda: stream_q.get(timeout=0.1)
+            )
+        except queue.Empty:
+            continue
+        
+        if delta is None:  # End of stream
+            break
+        
+        chunk = {"id": completion_id, "object": "chat.completion.chunk", ...
+                 "choices": [{"delta": {"content": delta}, ...}]}
+        await response.write(f"data: {json.dumps(chunk)}\n\n".encode())
+    
+    # Finish + [DONE]
+    await response.write(...)
+    await response.write(b"data: [DONE]\n\n")
+    return response
+```
+
+**Challenge: concurrent execution**
+
+The agent runs in a thread executor. SSE writing happens in the async event
+loop. The queue bridges them. But `_run_agent()` currently awaits the full
+result before returning. For real streaming, we need to start the agent in
+the background and stream tokens while it runs:
+
+```python
+# Start agent in background
+agent_task = asyncio.create_task(self._run_agent_async(...))
+
+# Stream tokens while agent runs
+await self._write_real_sse(request, ..., stream_q)
+
+# Agent is done by now (stream_q received None)
+result, usage = await agent_task
+```
+
+This requires splitting `_run_agent` into an async version that doesn't
+block waiting for the result, or running it in a separate task.
+
+**Responses API SSE format:**
+
+For `/v1/responses` with `stream=true`, the SSE events are different:
+
+```
+event: response.output_text.delta
+data: {"type":"response.output_text.delta","delta":"Hello"}
+
+event: response.completed  
+data: {"type":"response.completed","response":{...}}
+```
+
+This needs a separate SSE writer that emits Responses API format events.
+
+**Tests for Phase 4:** (~80 lines)
+- Test real SSE streaming with mocked agent
+- Test SSE event format (Chat Completions vs Responses)
+- Test client disconnect during streaming
+- Test fallback to pseudo-streaming when callback not available
+
+---
+
+## Integration Issues & Edge Cases
+
+### 1. Tool calls during streaming
+
+When the model returns tool calls instead of text, no text tokens are emitted.
+The stream_callback is simply never called with text. After tools execute, the
+next API call may produce the final text response — streaming picks up again.
+
+The stream preview task needs to handle this: if no tokens arrive during a
+tool-call round, don't send/edit any message. The tool progress messages
+continue working as before.
+
+### 2. Duplicate messages
+
+The biggest risk: the agent sends the final response normally (via the
+existing send path) AND the stream preview already showed it. The user
+sees the response twice.
+
+Prevention: when streaming is active and tokens were delivered, the final
+response send must be suppressed. The `result["_streamed_msg_id"]` marker
+tells the base adapter to skip its normal send.
+
+### 3. Response post-processing
+
+The final response may differ from the accumulated streamed tokens:
+- Think block stripping (`<think>...</think>` removed)
+- Trailing whitespace cleanup
+- Tool result media tag appending
+
+The stream preview shows raw tokens. The final edit should use the
+post-processed version. This means the final edit (removing the cursor)
+should use the post-processed `final_response`, not just the accumulated
+stream text.
+
+### 4. Context compression during streaming
+
+If the agent triggers context compression mid-conversation, the streaming
+tokens from BEFORE compression are from a different context than those
+after. This isn't a problem in practice — compression happens between
+API calls, not during streaming.
+
+### 5. Interrupt during streaming
+
+User sends a new message while streaming → interrupt. The stream is killed
+(HTTP connection closed), accumulated tokens are shown as-is (no cursor),
+and the interrupt message is processed normally. This is already handled by
+`_interruptible_api_call` closing the client.
+
+### 6. Multi-model / fallback
+
+If the primary model fails and the agent falls back to a different model,
+streaming state resets. The fallback call may or may not support streaming.
+The graceful fallback in `_run_streaming_chat_completion` handles this.
+
+### 7. Rate limiting on edits
+
+Telegram: ~20 edits/minute (~1 every 3 seconds to be safe)
+Discord: 5 edits per 5 seconds per message
+Slack: ~50 API calls/minute
+
+The 1.5s edit interval is conservative enough for all platforms. If we get
+429 rate limit errors on edits, just skip that edit cycle and try next time.
+
+---
+
+## Files Changed Summary
+
+| File | Phase | Changes |
+|------|-------|---------|
+| `run_agent.py` | 1 | +stream_callback param, +_run_streaming_chat_completion(), modify _run_codex_stream(), modify _interruptible_api_call() |
+| `gateway/run.py` | 2 | +streaming config reader, +queue/callback setup, +stream_preview task, +skip-final-send logic |
+| `gateway/platforms/base.py` | 2 | +check for _streamed_msg_id in response handler |
+| `cli.py` | 3 | +streaming setup, +token display, +response box integration |
+| `gateway/platforms/api_server.py` | 4 | +real SSE writer, +streaming callback wiring |
+| `hermes_cli/config.py` | 1 | +streaming config defaults |
+| `cli-config.yaml.example` | 1 | +streaming section |
+| `tests/test_streaming.py` | 1-4 | NEW — ~380 lines of tests |
+
+**Total new code**: ~500 lines across all phases
+**Total test code**: ~380 lines
+
+---
+
+## Rollout Plan
+
+1. **Phase 1** (core): Merge to main. Streaming disabled by default.
+   Zero impact on existing behavior. Can be tested with env var.
+
+2. **Phase 2** (gateway): Merge to main. Test on Telegram manually.
+   Enable per-platform: `streaming.telegram: true` in config.
+
+3. **Phase 3** (CLI): Merge to main. Test in terminal.
+   Enable: `streaming.cli: true` or `streaming.enabled: true`.
+
+4. **Phase 4** (API server): Merge to main. Test with Open WebUI.
+   Auto-enabled when client sends `stream: true`.
+
+Each phase is independently mergeable and testable. Streaming stays
+off by default throughout. Once all phases are stable, consider
+changing the default to enabled.
+
+---
+
+## Config Reference (final state)
+
+```yaml
+# config.yaml
+streaming:
+  enabled: false          # Master switch (default: off)
+  cli: true               # Per-platform override
+  telegram: true
+  discord: true
+  slack: true
+  api_server: true        # API server always streams when client requests it
+  edit_interval: 1.5      # Seconds between message edits (default: 1.5)
+  min_tokens: 20          # Tokens before first display (default: 20)
+```
+
+```bash
+# Environment variable override
+HERMES_STREAMING_ENABLED=true
+```

AGENTS.md

@@ -5,7 +5,7 @@ Instructions for AI coding assistants and developers working on the hermes-agent
 ## Development Environment
 
 ```bash
-source .venv/bin/activate  # ALWAYS activate before running Python
+source venv/bin/activate  # ALWAYS activate before running Python
 ```
 
 ## Project Structure
@@ -23,6 +23,7 @@ hermes-agent/
 │   ├── prompt_caching.py     # Anthropic prompt caching
 │   ├── auxiliary_client.py   # Auxiliary LLM client (vision, summarization)
 │   ├── model_metadata.py     # Model context lengths, token estimation
+│   ├── models_dev.py         # models.dev registry integration (provider-aware context)
 │   ├── display.py            # KawaiiSpinner, tool preview formatting
 │   ├── skill_commands.py     # Skill slash commands (shared CLI/gateway)
 │   └── trajectory.py         # Trajectory saving helpers
@@ -31,14 +32,21 @@ hermes-agent/
 │   ├── config.py         # DEFAULT_CONFIG, OPTIONAL_ENV_VARS, migration
 │   ├── commands.py       # Slash command definitions + SlashCommandCompleter
 │   ├── callbacks.py      # Terminal callbacks (clarify, sudo, approval)
-│   └── setup.py          # Interactive setup wizard
+│   ├── setup.py          # Interactive setup wizard
+│   ├── skin_engine.py    # Skin/theme engine — CLI visual customization
+│   ├── skills_config.py  # `hermes skills` — enable/disable skills per platform
+│   ├── tools_config.py   # `hermes tools` — enable/disable tools per platform
+│   ├── skills_hub.py     # `/skills` slash command (search, browse, install)
+│   ├── models.py         # Model catalog, provider model lists
+│   ├── model_switch.py   # Shared /model switch pipeline (CLI + gateway)
+│   └── auth.py           # Provider credential resolution
 ├── tools/                # Tool implementations (one file per tool)
 │   ├── registry.py       # Central tool registry (schemas, handlers, dispatch)
 │   ├── approval.py       # Dangerous command detection
 │   ├── terminal_tool.py  # Terminal orchestration
 │   ├── process_registry.py # Background process management
 │   ├── file_tools.py     # File read/write/search/patch
-│   ├── web_tools.py      # Firecrawl search/extract
+│   ├── web_tools.py      # Web search/extract (Parallel + Firecrawl)
 │   ├── browser_tool.py   # Browserbase browser automation
 │   ├── code_execution_tool.py # execute_code sandbox
 │   ├── delegate_tool.py  # Subagent delegation
@@ -48,9 +56,10 @@ hermes-agent/
 │   ├── run.py            # Main loop, slash commands, message dispatch
 │   ├── session.py        # SessionStore — conversation persistence
 │   └── platforms/        # Adapters: telegram, discord, slack, whatsapp, homeassistant, signal
+├── acp_adapter/          # ACP server (VS Code / Zed / JetBrains integration)
 ├── cron/                 # Scheduler (jobs.py, scheduler.py)
 ├── environments/         # RL training environments (Atropos)
-├── tests/                # Pytest suite (~2500+ tests)
+├── tests/                # Pytest suite (~3000 tests)
 └── batch_runner.py       # Parallel batch processing
 ```
 
@@ -121,14 +130,52 @@ Messages follow OpenAI format: `{"role": "system/user/assistant/tool", ...}`. Re
 - **Rich** for banner/panels, **prompt_toolkit** for input with autocomplete
 - **KawaiiSpinner** (`agent/display.py`) — animated faces during API calls, `┊` activity feed for tool results
 - `load_cli_config()` in cli.py merges hardcoded defaults + user config YAML
-- `process_command()` is a method on `HermesCLI` (not in commands.py)
+- **Skin engine** (`hermes_cli/skin_engine.py`) — data-driven CLI theming; initialized from `display.skin` config key at startup; skins customize banner colors, spinner faces/verbs/wings, tool prefix, response box, branding text
+- `process_command()` is a method on `HermesCLI` — dispatches on canonical command name resolved via `resolve_command()` from the central registry
 - Skill slash commands: `agent/skill_commands.py` scans `~/.hermes/skills/`, injects as **user message** (not system prompt) to preserve prompt caching
 
-### Adding CLI Commands
+### Slash Command Registry (`hermes_cli/commands.py`)
 
-1. Add to `COMMANDS` dict in `hermes_cli/commands.py`
-2. Add handler in `HermesCLI.process_command()` in `cli.py`
-3. For persistent settings, use `save_config_value()` in `cli.py`
+All slash commands are defined in a central `COMMAND_REGISTRY` list of `CommandDef` objects. Every downstream consumer derives from this registry automatically:
+
+- **CLI** — `process_command()` resolves aliases via `resolve_command()`, dispatches on canonical name
+- **Gateway** — `GATEWAY_KNOWN_COMMANDS` frozenset for hook emission, `resolve_command()` for dispatch
+- **Gateway help** — `gateway_help_lines()` generates `/help` output
+- **Telegram** — `telegram_bot_commands()` generates the BotCommand menu
+- **Slack** — `slack_subcommand_map()` generates `/hermes` subcommand routing
+- **Autocomplete** — `COMMANDS` flat dict feeds `SlashCommandCompleter`
+- **CLI help** — `COMMANDS_BY_CATEGORY` dict feeds `show_help()`
+
+### Adding a Slash Command
+
+1. Add a `CommandDef` entry to `COMMAND_REGISTRY` in `hermes_cli/commands.py`:
+```python
+CommandDef("mycommand", "Description of what it does", "Session",
+           aliases=("mc",), args_hint="[arg]"),
+```
+2. Add handler in `HermesCLI.process_command()` in `cli.py`:
+```python
+elif canonical == "mycommand":
+    self._handle_mycommand(cmd_original)
+```
+3. If the command is available in the gateway, add a handler in `gateway/run.py`:
+```python
+if canonical == "mycommand":
+    return await self._handle_mycommand(event)
+```
+4. For persistent settings, use `save_config_value()` in `cli.py`
+
+**CommandDef fields:**
+- `name` — canonical name without slash (e.g. `"background"`)
+- `description` — human-readable description
+- `category` — one of `"Session"`, `"Configuration"`, `"Tools & Skills"`, `"Info"`, `"Exit"`
+- `aliases` — tuple of alternative names (e.g. `("bg",)`)
+- `args_hint` — argument placeholder shown in help (e.g. `"<prompt>"`, `"[name]"`)
+- `cli_only` — only available in the interactive CLI
+- `gateway_only` — only available in messaging platforms
+- `gateway_config_gate` — config dotpath (e.g. `"display.tool_progress_command"`); when set on a `cli_only` command, the command becomes available in the gateway if the config value is truthy. `GATEWAY_KNOWN_COMMANDS` always includes config-gated commands so the gateway can dispatch them; help/menus only show them when the gate is open.
+
+**Adding an alias** requires only adding it to the `aliases` tuple on the existing `CommandDef`. No other file changes needed — dispatch, help text, Telegram menu, Slack mapping, and autocomplete all update automatically.
 
 ---
 
@@ -163,6 +210,10 @@ registry.register(
 
 The registry handles schema collection, dispatch, availability checking, and error wrapping. All handlers MUST return a JSON string.
 
+**Path references in tool schemas**: If the schema description mentions file paths (e.g. default output directories), use `display_hermes_home()` to make them profile-aware. The schema is generated at import time, which is after `_apply_profile_override()` sets `HERMES_HOME`.
+
+**State files**: If a tool stores persistent state (caches, logs, checkpoints), use `get_hermes_home()` for the base directory — never `Path.home() / ".hermes"`. This ensures each profile gets its own state.
+
 **Agent-level tools** (todo, memory): intercepted by `run_agent.py` before `handle_function_call()`. See `todo_tool.py` for the pattern.
 
 ---
@@ -195,8 +246,96 @@ The registry handles schema collection, dispatch, availability checking, and err
 
 ---
 
-## Important Policies
+## Skin/Theme System
 
+The skin engine (`hermes_cli/skin_engine.py`) provides data-driven CLI visual customization. Skins are **pure data** — no code changes needed to add a new skin.
+
+### Architecture
+
+```
+hermes_cli/skin_engine.py    # SkinConfig dataclass, built-in skins, YAML loader
+~/.hermes/skins/*.yaml       # User-installed custom skins (drop-in)
+```
+
+- `init_skin_from_config()` — called at CLI startup, reads `display.skin` from config
+- `get_active_skin()` — returns cached `SkinConfig` for the current skin
+- `set_active_skin(name)` — switches skin at runtime (used by `/skin` command)
+- `load_skin(name)` — loads from user skins first, then built-ins, then falls back to default
+- Missing skin values inherit from the `default` skin automatically
+
+### What skins customize
+
+| Element | Skin Key | Used By |
+|---------|----------|---------|
+| Banner panel border | `colors.banner_border` | `banner.py` |
+| Banner panel title | `colors.banner_title` | `banner.py` |
+| Banner section headers | `colors.banner_accent` | `banner.py` |
+| Banner dim text | `colors.banner_dim` | `banner.py` |
+| Banner body text | `colors.banner_text` | `banner.py` |
+| Response box border | `colors.response_border` | `cli.py` |
+| Spinner faces (waiting) | `spinner.waiting_faces` | `display.py` |
+| Spinner faces (thinking) | `spinner.thinking_faces` | `display.py` |
+| Spinner verbs | `spinner.thinking_verbs` | `display.py` |
+| Spinner wings (optional) | `spinner.wings` | `display.py` |
+| Tool output prefix | `tool_prefix` | `display.py` |
+| Per-tool emojis | `tool_emojis` | `display.py` → `get_tool_emoji()` |
+| Agent name | `branding.agent_name` | `banner.py`, `cli.py` |
+| Welcome message | `branding.welcome` | `cli.py` |
+| Response box label | `branding.response_label` | `cli.py` |
+| Prompt symbol | `branding.prompt_symbol` | `cli.py` |
+
+### Built-in skins
+
+- `default` — Classic Hermes gold/kawaii (the current look)
+- `ares` — Crimson/bronze war-god theme with custom spinner wings
+- `mono` — Clean grayscale monochrome
+- `slate` — Cool blue developer-focused theme
+
+### Adding a built-in skin
+
+Add to `_BUILTIN_SKINS` dict in `hermes_cli/skin_engine.py`:
+
+```python
+"mytheme": {
+    "name": "mytheme",
+    "description": "Short description",
+    "colors": { ... },
+    "spinner": { ... },
+    "branding": { ... },
+    "tool_prefix": "┊",
+},
+```
+
+### User skins (YAML)
+
+Users create `~/.hermes/skins/<name>.yaml`:
+
+```yaml
+name: cyberpunk
+description: Neon-soaked terminal theme
+
+colors:
+  banner_border: "#FF00FF"
+  banner_title: "#00FFFF"
+  banner_accent: "#FF1493"
+
+spinner:
+  thinking_verbs: ["jacking in", "decrypting", "uploading"]
+  wings:
+    - ["⟨⚡", "⚡⟩"]
+
+branding:
+  agent_name: "Cyber Agent"
+  response_label: " ⚡ Cyber "
+
+tool_prefix: "▏"
+```
+
+Activate with `/skin cyberpunk` or `display.skin: cyberpunk` in config.yaml.
+
+---
+
+## Important Policies
 ### Prompt Caching Must Not Break
 
 Hermes-Agent ensures caching remains valid throughout a conversation. **Do NOT implement changes that would:**
@@ -210,10 +349,82 @@ Cache-breaking forces dramatically higher costs. The ONLY time we alter context
 - **CLI**: Uses current directory (`.` → `os.getcwd()`)
 - **Messaging**: Uses `MESSAGING_CWD` env var (default: home directory)
 
+### Background Process Notifications (Gateway)
+
+When `terminal(background=true, check_interval=...)` is used, the gateway runs a watcher that
+pushes status updates to the user's chat. Control verbosity with `display.background_process_notifications`
+in config.yaml (or `HERMES_BACKGROUND_NOTIFICATIONS` env var):
+
+- `all` — running-output updates + final message (default)
+- `result` — only the final completion message
+- `error` — only the final message when exit code != 0
+- `off` — no watcher messages at all
+
 ---
 
+## Profiles: Multi-Instance Support
+
+Hermes supports **profiles** — multiple fully isolated instances, each with its own
+`HERMES_HOME` directory (config, API keys, memory, sessions, skills, gateway, etc.).
+
+The core mechanism: `_apply_profile_override()` in `hermes_cli/main.py` sets
+`HERMES_HOME` before any module imports. All 119+ references to `get_hermes_home()`
+automatically scope to the active profile.
+
+### Rules for profile-safe code
+
+1. **Use `get_hermes_home()` for all HERMES_HOME paths.** Import from `hermes_constants`.
+   NEVER hardcode `~/.hermes` or `Path.home() / ".hermes"` in code that reads/writes state.
+   ```python
+   # GOOD
+   from hermes_constants import get_hermes_home
+   config_path = get_hermes_home() / "config.yaml"
+
+   # BAD — breaks profiles
+   config_path = Path.home() / ".hermes" / "config.yaml"
+   ```
+
+2. **Use `display_hermes_home()` for user-facing messages.** Import from `hermes_constants`.
+   This returns `~/.hermes` for default or `~/.hermes/profiles/<name>` for profiles.
+   ```python
+   # GOOD
+   from hermes_constants import display_hermes_home
+   print(f"Config saved to {display_hermes_home()}/config.yaml")
+
+   # BAD — shows wrong path for profiles
+   print("Config saved to ~/.hermes/config.yaml")
+   ```
+
+3. **Module-level constants are fine** — they cache `get_hermes_home()` at import time,
+   which is AFTER `_apply_profile_override()` sets the env var. Just use `get_hermes_home()`,
+   not `Path.home() / ".hermes"`.
+
+4. **Tests that mock `Path.home()` must also set `HERMES_HOME`** — since code now uses
+   `get_hermes_home()` (reads env var), not `Path.home() / ".hermes"`:
+   ```python
+   with patch.object(Path, "home", return_value=tmp_path), \
+        patch.dict(os.environ, {"HERMES_HOME": str(tmp_path / ".hermes")}):
+       ...
+   ```
+
+5. **Gateway platform adapters should use token locks** — if the adapter connects with
+   a unique credential (bot token, API key), call `acquire_scoped_lock()` from
+   `gateway.status` in the `connect()`/`start()` method and `release_scoped_lock()` in
+   `disconnect()`/`stop()`. This prevents two profiles from using the same credential.
+   See `gateway/platforms/telegram.py` for the canonical pattern.
+
+6. **Profile operations are HOME-anchored, not HERMES_HOME-anchored** — `_get_profiles_root()`
+   returns `Path.home() / ".hermes" / "profiles"`, NOT `get_hermes_home() / "profiles"`.
+   This is intentional — it lets `hermes -p coder profile list` see all profiles regardless
+   of which one is active.
+
 ## Known Pitfalls
 
+### DO NOT hardcode `~/.hermes` paths
+Use `get_hermes_home()` from `hermes_constants` for code paths. Use `display_hermes_home()`
+for user-facing print/log messages. Hardcoding `~/.hermes` breaks profiles — each profile
+has its own `HERMES_HOME` directory. This was the source of 5 bugs fixed in PR #3575.
+
 ### DO NOT use `simple_term_menu` for interactive menus
 Rendering bugs in tmux/iTerm2 — ghosting on scroll. Use `curses` (stdlib) instead. See `hermes_cli/tools_config.py` for the pattern.
 
@@ -221,18 +432,34 @@ Rendering bugs in tmux/iTerm2 — ghosting on scroll. Use `curses` (stdlib) inst
 Leaks as literal `?[K` text under `prompt_toolkit`'s `patch_stdout`. Use space-padding: `f"\r{line}{' ' * pad}"`.
 
 ### `_last_resolved_tool_names` is a process-global in `model_tools.py`
-When subagents overwrite this global, `execute_code` calls after delegation may fail with missing tool imports. Known bug.
+`_run_single_child()` in `delegate_tool.py` saves and restores this global around subagent execution. If you add new code that reads this global, be aware it may be temporarily stale during child agent runs.
+
+### DO NOT hardcode cross-tool references in schema descriptions
+Tool schema descriptions must not mention tools from other toolsets by name (e.g., `browser_navigate` saying "prefer web_search"). Those tools may be unavailable (missing API keys, disabled toolset), causing the model to hallucinate calls to non-existent tools. If a cross-reference is needed, add it dynamically in `get_tool_definitions()` in `model_tools.py` — see the `browser_navigate` / `execute_code` post-processing blocks for the pattern.
 
 ### Tests must not write to `~/.hermes/`
 The `_isolate_hermes_home` autouse fixture in `tests/conftest.py` redirects `HERMES_HOME` to a temp dir. Never hardcode `~/.hermes/` paths in tests.
 
+**Profile tests**: When testing profile features, also mock `Path.home()` so that
+`_get_profiles_root()` and `_get_default_hermes_home()` resolve within the temp dir.
+Use the pattern from `tests/hermes_cli/test_profiles.py`:
+```python
+@pytest.fixture
+def profile_env(tmp_path, monkeypatch):
+    home = tmp_path / ".hermes"
+    home.mkdir()
+    monkeypatch.setattr(Path, "home", lambda: tmp_path)
+    monkeypatch.setenv("HERMES_HOME", str(home))
+    return home
+```
+
 ---
 
 ## Testing
 
 ```bash
-source .venv/bin/activate
-python -m pytest tests/ -q          # Full suite (~2500 tests, ~2 min)
+source venv/bin/activate
+python -m pytest tests/ -q          # Full suite (~3000 tests, ~3 min)
 python -m pytest tests/test_model_tools.py -q   # Toolset resolution
 python -m pytest tests/test_cli_init.py -q       # CLI config loading
 python -m pytest tests/gateway/ -q               # Gateway tests

CONTRIBUTING.md

@@ -72,8 +72,9 @@ export VIRTUAL_ENV="$(pwd)/venv"
 
 # Install with all extras (messaging, cron, CLI menus, dev tools)
 uv pip install -e ".[all,dev]"
-uv pip install -e "./mini-swe-agent"
-uv pip install -e "./tinker-atropos"
+
+# Optional: RL training submodule
+# git submodule update --init tinker-atropos && uv pip install -e "./tinker-atropos"
 
 # Optional: browser tools
 npm install
@@ -136,17 +137,18 @@ hermes-agent/
 │   ├── auth.py                   # Provider resolution, OAuth, Nous Portal
 │   ├── models.py                 # OpenRouter model selection lists
 │   ├── banner.py                 # Welcome banner, ASCII art
-│   ├── commands.py               # Slash command definitions + autocomplete
+│   ├── commands.py               # Central slash command registry (CommandDef), autocomplete, gateway helpers
 │   ├── callbacks.py              # Interactive callbacks (clarify, sudo, approval)
 │   ├── doctor.py                 # Diagnostics
-│   └── skills_hub.py             # Skills Hub CLI + /skills slash command
+│   ├── skills_hub.py             # Skills Hub CLI + /skills slash command
+│   └── skin_engine.py            # Skin/theme engine — data-driven CLI visual customization
 │
 ├── tools/                    # Tool implementations (self-registering)
 │   ├── registry.py               # Central tool registry (schemas, handlers, dispatch)
 │   ├── approval.py               # Dangerous command detection + per-session approval
 │   ├── terminal_tool.py          # Terminal orchestration (sudo, env lifecycle, backends)
 │   ├── file_operations.py        # read_file, write_file, search, patch, etc.
-│   ├── web_tools.py              # web_search, web_extract (Firecrawl + Gemini summarization)
+│   ├── web_tools.py              # web_search, web_extract (Parallel/Firecrawl + Gemini summarization)
 │   ├── vision_tools.py           # Image analysis via multimodal models
 │   ├── delegate_tool.py          # Subagent spawning and parallel task execution
 │   ├── code_execution_tool.py    # Sandboxed Python with RPC tool access
@@ -328,10 +330,20 @@ license: MIT
 platforms: [macos, linux]          # Optional — restrict to specific OS platforms
                                    #   Valid: macos, linux, windows
                                    #   Omit to load on all platforms (default)
+required_environment_variables:    # Optional — secure setup-on-load metadata
+  - name: MY_API_KEY
+    prompt: API key
+    help: Where to get it
+    required_for: full functionality
+prerequisites:                     # Optional legacy runtime requirements
+  env_vars: [MY_API_KEY]           #   Backward-compatible alias for required env vars
+  commands: [curl, jq]             #   Advisory only; does not hide the skill
 metadata:
   hermes:
     tags: [Category, Subcategory, Keywords]
     related_skills: [other-skill-name]
+    fallback_for_toolsets: [web]       # Optional — show only when toolset is unavailable
+    requires_toolsets: [terminal]      # Optional — show only when toolset is available
 ---
 
 # Skill Title
@@ -366,6 +378,82 @@ platforms: [windows]          # Windows only
 
 If the field is omitted or empty, the skill loads on all platforms (backward compatible). See `skills/apple/` for examples of macOS-only skills.
 
+### Conditional skill activation
+
+Skills can declare conditions that control when they appear in the system prompt, based on which tools and toolsets are available in the current session. This is primarily used for **fallback skills** — alternatives that should only be shown when a primary tool is unavailable.
+
+Four fields are supported under `metadata.hermes`:
+
+```yaml
+metadata:
+  hermes:
+    fallback_for_toolsets: [web]      # Show ONLY when these toolsets are unavailable
+    requires_toolsets: [terminal]     # Show ONLY when these toolsets are available
+    fallback_for_tools: [web_search]  # Show ONLY when these specific tools are unavailable
+    requires_tools: [terminal]        # Show ONLY when these specific tools are available
+```
+
+**Semantics:**
+- `fallback_for_*`: The skill is a backup. It is **hidden** when the listed tools/toolsets are available, and **shown** when they are unavailable. Use this for free alternatives to premium tools.
+- `requires_*`: The skill needs certain tools to function. It is **hidden** when the listed tools/toolsets are unavailable. Use this for skills that depend on specific capabilities (e.g., a skill that only makes sense with terminal access).
+- If both are specified, both conditions must be satisfied for the skill to appear.
+- If neither is specified, the skill is always shown (backward compatible).
+
+**Examples:**
+
+```yaml
+# DuckDuckGo search — shown when Firecrawl (web toolset) is unavailable
+metadata:
+  hermes:
+    fallback_for_toolsets: [web]
+
+# Smart home skill — only useful when terminal is available
+metadata:
+  hermes:
+    requires_toolsets: [terminal]
+
+# Local browser fallback — shown when Browserbase is unavailable
+metadata:
+  hermes:
+    fallback_for_toolsets: [browser]
+```
+
+The filtering happens at prompt build time in `agent/prompt_builder.py`. The `build_skills_system_prompt()` function receives the set of available tools and toolsets from the agent and uses `_skill_should_show()` to evaluate each skill's conditions.
+
+### Skill setup metadata
+
+Skills can declare secure setup-on-load metadata via the `required_environment_variables` frontmatter field. Missing values do not hide the skill from discovery; they trigger a CLI-only secure prompt when the skill is actually loaded.
+
+```yaml
+required_environment_variables:
+  - name: TENOR_API_KEY
+    prompt: Tenor API key
+    help: Get a key from https://developers.google.com/tenor
+    required_for: full functionality
+```
+
+The user may skip setup and keep loading the skill. Hermes only exposes metadata (`stored_as`, `skipped`, `validated`) to the model — never the secret value.
+
+Legacy `prerequisites.env_vars` remains supported and is normalized into the new representation.
+
+```yaml
+prerequisites:
+  env_vars: [TENOR_API_KEY]       # Legacy alias for required_environment_variables
+  commands: [curl, jq]            # Advisory CLI checks
+```
+
+Gateway and messaging sessions never collect secrets in-band; they instruct the user to run `hermes setup` or update `~/.hermes/.env` locally.
+
+**When to declare required environment variables:**
+- The skill uses an API key or token that should be collected securely at load time
+- The skill can still be useful if the user skips setup, but may degrade gracefully
+
+**When to declare command prerequisites:**
+- The skill relies on a CLI tool that may not be installed (e.g., `himalaya`, `openhue`, `ddgs`)
+- Treat command checks as guidance, not discovery-time hiding
+
+See `skills/gifs/gif-search/` and `skills/email/himalaya/` for examples.
+
 ### Skill guidelines
 
 - **No external dependencies unless absolutely necessary.** Prefer stdlib Python, curl, and existing Hermes tools (`web_extract`, `terminal`, `read_file`).
@@ -375,6 +463,56 @@ If the field is omitted or empty, the skill loads on all platforms (backward com
 
 ---
 
+## Adding a Skin / Theme
+
+Hermes uses a data-driven skin system — no code changes needed to add a new skin.
+
+**Option A: User skin (YAML file)**
+
+Create `~/.hermes/skins/<name>.yaml`:
+
+```yaml
+name: mytheme
+description: Short description of the theme
+
+colors:
+  banner_border: "#HEX"     # Panel border color
+  banner_title: "#HEX"      # Panel title color
+  banner_accent: "#HEX"     # Section header color
+  banner_dim: "#HEX"        # Muted/dim text color
+  banner_text: "#HEX"       # Body text color
+  response_border: "#HEX"   # Response box border
+
+spinner:
+  waiting_faces: ["(⚔)", "(⛨)"]
+  thinking_faces: ["(⚔)", "(⌁)"]
+  thinking_verbs: ["forging", "plotting"]
+  wings:                     # Optional left/right decorations
+    - ["⟪⚔", "⚔⟫"]
+
+branding:
+  agent_name: "My Agent"
+  welcome: "Welcome message"
+  response_label: " ⚔ Agent "
+  prompt_symbol: "⚔ ❯ "
+
+tool_prefix: "╎"             # Tool output line prefix
+```
+
+All fields are optional — missing values inherit from the default skin.
+
+**Option B: Built-in skin**
+
+Add to `_BUILTIN_SKINS` dict in `hermes_cli/skin_engine.py`. Use the same schema as above but as a Python dict. Built-in skins ship with the package and are always available.
+
+**Activating:**
+- CLI: `/skin mytheme` or set `display.skin: mytheme` in config.yaml
+- Config: `display: { skin: mytheme }`
+
+See `hermes_cli/skin_engine.py` for the full schema and existing skins as examples.
+
+---
+
 ## Cross-Platform Compatibility
 
 Hermes runs on Linux, macOS, and Windows. When writing code that touches the OS:

Dockerfile

@@ -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" ]

README.md

@@ -2,7 +2,7 @@
   <img src="assets/banner.png" alt="Hermes Agent" width="100%">
 </p>
 
-# Hermes Agent ⚕
+# Hermes Agent ☤
 
 <p align="center">
   <a href="https://hermes-agent.nousresearch.com/docs/"><img src="https://img.shields.io/badge/Docs-hermes--agent.nousresearch.com-FFD700?style=for-the-badge" alt="Documentation"></a>
@@ -41,7 +41,6 @@ After installation:
 
 ```bash
 source ~/.bashrc    # reload shell (or: source ~/.zshrc)
-hermes setup        # configure your LLM provider
 hermes              # start chatting!
 ```
 
@@ -51,15 +50,36 @@ hermes              # start chatting!
 
 ```bash
 hermes              # Interactive CLI — start a conversation
-hermes model        # Switch provider or model
-hermes setup        # Re-run the setup wizard
+hermes model        # Choose your LLM provider and model
+hermes tools        # Configure which tools are enabled
+hermes config set   # Set individual config values
 hermes gateway      # Start the messaging gateway (Telegram, Discord, etc.)
+hermes setup        # Run the full setup wizard (configures everything at once)
+hermes claw migrate # Migrate from OpenClaw (if coming from OpenClaw)
 hermes update       # Update to the latest version
 hermes doctor       # Diagnose any issues
 ```
 
 📖 **[Full documentation →](https://hermes-agent.nousresearch.com/docs/)**
 
+## CLI vs Messaging Quick Reference
+
+Hermes has two entry points: start the terminal UI with `hermes`, or run the gateway and talk to it from Telegram, Discord, Slack, WhatsApp, Signal, or Email. Once you're in a conversation, many slash commands are shared across both interfaces.
+
+| Action | CLI | Messaging platforms |
+|---------|-----|---------------------|
+| Start chatting | `hermes` | Run `hermes gateway setup` + `hermes gateway start`, then send the bot a message |
+| Start fresh conversation | `/new` or `/reset` | `/new` or `/reset` |
+| Change model | `/model [provider:model]` | `/model [provider:model]` |
+| Set a personality | `/personality [name]` | `/personality [name]` |
+| Retry or undo the last turn | `/retry`, `/undo` | `/retry`, `/undo` |
+| Compress context / check usage | `/compress`, `/usage`, `/insights [--days N]` | `/compress`, `/usage`, `/insights [days]` |
+| Browse skills | `/skills` or `/<skill-name>` | `/skills` or `/<skill-name>` |
+| Interrupt current work | `Ctrl+C` or send a new message | `/stop` or send a new message |
+| Platform-specific status | `/platforms` | `/status`, `/sethome` |
+
+For the full command lists, see the [CLI guide](https://hermes-agent.nousresearch.com/docs/user-guide/cli) and the [Messaging Gateway guide](https://hermes-agent.nousresearch.com/docs/user-guide/messaging).
+
 ---
 
 ## Documentation
@@ -86,6 +106,35 @@ All documentation lives at **[hermes-agent.nousresearch.com/docs](https://hermes
 
 ---
 
+## Migrating from OpenClaw
+
+If you're coming from OpenClaw, Hermes can automatically import your settings, memories, skills, and API keys.
+
+**During first-time setup:** The setup wizard (`hermes setup`) automatically detects `~/.openclaw` and offers to migrate before configuration begins.
+
+**Anytime after install:**
+
+```bash
+hermes claw migrate              # Interactive migration (full preset)
+hermes claw migrate --dry-run    # Preview what would be migrated
+hermes claw migrate --preset user-data   # Migrate without secrets
+hermes claw migrate --overwrite  # Overwrite existing conflicts
+```
+
+What gets imported:
+- **SOUL.md** — persona file
+- **Memories** — MEMORY.md and USER.md entries
+- **Skills** — user-created skills → `~/.hermes/skills/openclaw-imports/`
+- **Command allowlist** — approval patterns
+- **Messaging settings** — platform configs, allowed users, working directory
+- **API keys** — allowlisted secrets (Telegram, OpenRouter, OpenAI, Anthropic, ElevenLabs)
+- **TTS assets** — workspace audio files
+- **Workspace instructions** — AGENTS.md (with `--workspace-target`)
+
+See `hermes claw migrate --help` for all options, or use the `openclaw-migration` skill for an interactive agent-guided migration with dry-run previews.
+
+---
+
 ## Contributing
 
 We welcome contributions! See the [Contributing Guide](https://hermes-agent.nousresearch.com/docs/developer-guide/contributing) for development setup, code style, and PR process.
@@ -93,16 +142,21 @@ We welcome contributions! See the [Contributing Guide](https://hermes-agent.nous
 Quick start for contributors:
 
 ```bash
-git clone --recurse-submodules https://github.com/NousResearch/hermes-agent.git
+git clone https://github.com/NousResearch/hermes-agent.git
 cd hermes-agent
 curl -LsSf https://astral.sh/uv/install.sh | sh
-uv venv .venv --python 3.11
-source .venv/bin/activate
+uv venv venv --python 3.11
+source venv/bin/activate
 uv pip install -e ".[all,dev]"
-uv pip install -e "./mini-swe-agent"
 python -m pytest tests/ -q
 ```
 
+> **RL Training (optional):** To work on the RL/Tinker-Atropos integration:
+> ```bash
+> git submodule update --init tinker-atropos
+> uv pip install -e "./tinker-atropos"
+> ```
+
 ---
 
 ## Community

RELEASE_v0.2.0.md

@@ -0,0 +1,383 @@
+# Hermes Agent v0.2.0 (v2026.3.12)
+
+**Release Date:** March 12, 2026
+
+> First tagged release since v0.1.0 (the initial pre-public foundation). In just over two weeks, Hermes Agent went from a small internal project to a full-featured AI agent platform — thanks to an explosion of community contributions. This release covers **216 merged pull requests** from **63 contributors**, resolving **119 issues**.
+
+---
+
+## ✨ Highlights
+
+- **Multi-Platform Messaging Gateway** — Telegram, Discord, Slack, WhatsApp, Signal, Email (IMAP/SMTP), and Home Assistant platforms with unified session management, media attachments, and per-platform tool configuration.
+
+- **MCP (Model Context Protocol) Client** — Native MCP support with stdio and HTTP transports, reconnection, resource/prompt discovery, and sampling (server-initiated LLM requests). ([#291](https://github.com/NousResearch/hermes-agent/pull/291) — @0xbyt4, [#301](https://github.com/NousResearch/hermes-agent/pull/301), [#753](https://github.com/NousResearch/hermes-agent/pull/753))
+
+- **Skills Ecosystem** — 70+ bundled and optional skills across 15+ categories with a Skills Hub for community discovery, per-platform enable/disable, conditional activation based on tool availability, and prerequisite validation. ([#743](https://github.com/NousResearch/hermes-agent/pull/743) — @teyrebaz33, [#785](https://github.com/NousResearch/hermes-agent/pull/785) — @teyrebaz33)
+
+- **Centralized Provider Router** — Unified `call_llm()`/`async_call_llm()` API replaces scattered provider logic across vision, summarization, compression, and trajectory saving. All auxiliary consumers route through a single code path with automatic credential resolution. ([#1003](https://github.com/NousResearch/hermes-agent/pull/1003))
+
+- **ACP Server** — VS Code, Zed, and JetBrains editor integration via the Agent Communication Protocol standard. ([#949](https://github.com/NousResearch/hermes-agent/pull/949))
+
+- **CLI Skin/Theme Engine** — Data-driven visual customization: banners, spinners, colors, branding. 7 built-in skins + custom YAML skins.
+
+- **Git Worktree Isolation** — `hermes -w` launches isolated agent sessions in git worktrees for safe parallel work on the same repo. ([#654](https://github.com/NousResearch/hermes-agent/pull/654))
+
+- **Filesystem Checkpoints & Rollback** — Automatic snapshots before destructive operations with `/rollback` to restore. ([#824](https://github.com/NousResearch/hermes-agent/pull/824))
+
+- **3,289 Tests** — From near-zero test coverage to a comprehensive test suite covering agent, gateway, tools, cron, and CLI.
+
+---
+
+## 🏗️ Core Agent & Architecture
+
+### Provider & Model Support
+- Centralized provider router with `resolve_provider_client()` + `call_llm()` API ([#1003](https://github.com/NousResearch/hermes-agent/pull/1003))
+- Nous Portal as first-class provider in setup ([#644](https://github.com/NousResearch/hermes-agent/issues/644))
+- OpenAI Codex (Responses API) with ChatGPT subscription support ([#43](https://github.com/NousResearch/hermes-agent/pull/43)) — @grp06
+- Codex OAuth vision support + multimodal content adapter
+- Validate `/model` against live API instead of hardcoded lists
+- Self-hosted Firecrawl support ([#460](https://github.com/NousResearch/hermes-agent/pull/460)) — @caentzminger
+- Kimi Code API support ([#635](https://github.com/NousResearch/hermes-agent/pull/635)) — @christomitov
+- MiniMax model ID update ([#473](https://github.com/NousResearch/hermes-agent/pull/473)) — @tars90percent
+- OpenRouter provider routing configuration (provider_preferences)
+- Nous credential refresh on 401 errors ([#571](https://github.com/NousResearch/hermes-agent/pull/571), [#269](https://github.com/NousResearch/hermes-agent/pull/269)) — @rewbs
+- z.ai/GLM, Kimi/Moonshot, MiniMax, Azure OpenAI as first-class providers
+- Unified `/model` and `/provider` into single view
+
+### Agent Loop & Conversation
+- Simple fallback model for provider resilience ([#740](https://github.com/NousResearch/hermes-agent/pull/740))
+- Shared iteration budget across parent + subagent delegation
+- Iteration budget pressure via tool result injection
+- Configurable subagent provider/model with full credential resolution
+- Handle 413 payload-too-large via compression instead of aborting ([#153](https://github.com/NousResearch/hermes-agent/pull/153)) — @tekelala
+- Retry with rebuilt payload after compression ([#616](https://github.com/NousResearch/hermes-agent/pull/616)) — @tripledoublev
+- Auto-compress pathologically large gateway sessions ([#628](https://github.com/NousResearch/hermes-agent/issues/628))
+- Tool call repair middleware — auto-lowercase and invalid tool handler
+- Reasoning effort configuration and `/reasoning` command ([#921](https://github.com/NousResearch/hermes-agent/pull/921))
+- Detect and block file re-read/search loops after context compression ([#705](https://github.com/NousResearch/hermes-agent/pull/705)) — @0xbyt4
+
+### Session & Memory
+- Session naming with unique titles, auto-lineage, rich listing, and resume by name ([#720](https://github.com/NousResearch/hermes-agent/pull/720))
+- Interactive session browser with search filtering ([#733](https://github.com/NousResearch/hermes-agent/pull/733))
+- Display previous messages when resuming a session ([#734](https://github.com/NousResearch/hermes-agent/pull/734))
+- Honcho AI-native cross-session user modeling ([#38](https://github.com/NousResearch/hermes-agent/pull/38)) — @erosika
+- Proactive async memory flush on session expiry
+- Smart context length probing with persistent caching + banner display
+- `/resume` command for switching to named sessions in gateway
+- Session reset policy for messaging platforms
+
+---
+
+## 📱 Messaging Platforms (Gateway)
+
+### Telegram
+- Native file attachments: send_document + send_video
+- Document file processing for PDF, text, and Office files — @tekelala
+- Forum topic session isolation ([#766](https://github.com/NousResearch/hermes-agent/pull/766)) — @spanishflu-est1918
+- Browser screenshot sharing via MEDIA: protocol ([#657](https://github.com/NousResearch/hermes-agent/pull/657))
+- Location support for find-nearby skill
+- TTS voice message accumulation fix ([#176](https://github.com/NousResearch/hermes-agent/pull/176)) — @Bartok9
+- Improved error handling and logging ([#763](https://github.com/NousResearch/hermes-agent/pull/763)) — @aydnOktay
+- Italic regex newline fix + 43 format tests ([#204](https://github.com/NousResearch/hermes-agent/pull/204)) — @0xbyt4
+
+### Discord
+- Channel topic included in session context ([#248](https://github.com/NousResearch/hermes-agent/pull/248)) — @Bartok9
+- DISCORD_ALLOW_BOTS config for bot message filtering ([#758](https://github.com/NousResearch/hermes-agent/pull/758))
+- Document and video support ([#784](https://github.com/NousResearch/hermes-agent/pull/784))
+- Improved error handling and logging ([#761](https://github.com/NousResearch/hermes-agent/pull/761)) — @aydnOktay
+
+### Slack
+- App_mention 404 fix + document/video support ([#784](https://github.com/NousResearch/hermes-agent/pull/784))
+- Structured logging replacing print statements — @aydnOktay
+
+### WhatsApp
+- Native media sending — images, videos, documents ([#292](https://github.com/NousResearch/hermes-agent/pull/292)) — @satelerd
+- Multi-user session isolation ([#75](https://github.com/NousResearch/hermes-agent/pull/75)) — @satelerd
+- Cross-platform port cleanup replacing Linux-only fuser ([#433](https://github.com/NousResearch/hermes-agent/pull/433)) — @Farukest
+- DM interrupt key mismatch fix ([#350](https://github.com/NousResearch/hermes-agent/pull/350)) — @Farukest
+
+### Signal
+- Full Signal messenger gateway via signal-cli-rest-api ([#405](https://github.com/NousResearch/hermes-agent/issues/405))
+- Media URL support in message events ([#871](https://github.com/NousResearch/hermes-agent/pull/871))
+
+### Email (IMAP/SMTP)
+- New email gateway platform — @0xbyt4
+
+### Home Assistant
+- REST tools + WebSocket gateway integration ([#184](https://github.com/NousResearch/hermes-agent/pull/184)) — @0xbyt4
+- Service discovery and enhanced setup
+- Toolset mapping fix ([#538](https://github.com/NousResearch/hermes-agent/pull/538)) — @Himess
+
+### Gateway Core
+- Expose subagent tool calls and thinking to users ([#186](https://github.com/NousResearch/hermes-agent/pull/186)) — @cutepawss
+- Configurable background process watcher notifications ([#840](https://github.com/NousResearch/hermes-agent/pull/840))
+- `edit_message()` for Telegram/Discord/Slack with fallback
+- `/compress`, `/usage`, `/update` slash commands
+- Eliminated 3x SQLite message duplication in gateway sessions ([#873](https://github.com/NousResearch/hermes-agent/pull/873))
+- Stabilize system prompt across gateway turns for cache hits ([#754](https://github.com/NousResearch/hermes-agent/pull/754))
+- MCP server shutdown on gateway exit ([#796](https://github.com/NousResearch/hermes-agent/pull/796)) — @0xbyt4
+- Pass session_db to AIAgent, fixing session_search error ([#108](https://github.com/NousResearch/hermes-agent/pull/108)) — @Bartok9
+- Persist transcript changes in /retry, /undo; fix /reset attribute ([#217](https://github.com/NousResearch/hermes-agent/pull/217)) — @Farukest
+- UTF-8 encoding fix preventing Windows crashes ([#369](https://github.com/NousResearch/hermes-agent/pull/369)) — @ch3ronsa
+
+---
+
+## 🖥️ CLI & User Experience
+
+### Interactive CLI
+- Data-driven skin/theme engine — 7 built-in skins (default, ares, mono, slate, poseidon, sisyphus, charizard) + custom YAML skins
+- `/personality` command with custom personality + disable support ([#773](https://github.com/NousResearch/hermes-agent/pull/773)) — @teyrebaz33
+- User-defined quick commands that bypass the agent loop ([#746](https://github.com/NousResearch/hermes-agent/pull/746)) — @teyrebaz33
+- `/reasoning` command for effort level and display toggle ([#921](https://github.com/NousResearch/hermes-agent/pull/921))
+- `/verbose` slash command to toggle debug at runtime ([#94](https://github.com/NousResearch/hermes-agent/pull/94)) — @cesareth
+- `/insights` command — usage analytics, cost estimation & activity patterns ([#552](https://github.com/NousResearch/hermes-agent/pull/552))
+- `/background` command for managing background processes
+- `/help` formatting with command categories
+- Bell-on-complete — terminal bell when agent finishes ([#738](https://github.com/NousResearch/hermes-agent/pull/738))
+- Up/down arrow history navigation
+- Clipboard image paste (Alt+V / Ctrl+V)
+- Loading indicators for slow slash commands ([#882](https://github.com/NousResearch/hermes-agent/pull/882))
+- Spinner flickering fix under patch_stdout ([#91](https://github.com/NousResearch/hermes-agent/pull/91)) — @0xbyt4
+- `--quiet/-Q` flag for programmatic single-query mode
+- `--fuck-it-ship-it` flag to bypass all approval prompts ([#724](https://github.com/NousResearch/hermes-agent/pull/724)) — @dmahan93
+- Tools summary flag ([#767](https://github.com/NousResearch/hermes-agent/pull/767)) — @luisv-1
+- Terminal blinking fix on SSH ([#284](https://github.com/NousResearch/hermes-agent/pull/284)) — @ygd58
+- Multi-line paste detection fix ([#84](https://github.com/NousResearch/hermes-agent/pull/84)) — @0xbyt4
+
+### Setup & Configuration
+- Modular setup wizard with section subcommands and tool-first UX
+- Container resource configuration prompts
+- Backend validation for required binaries
+- Config migration system (currently v7)
+- API keys properly routed to .env instead of config.yaml ([#469](https://github.com/NousResearch/hermes-agent/pull/469)) — @ygd58
+- Atomic write for .env to prevent API key loss on crash ([#954](https://github.com/NousResearch/hermes-agent/pull/954))
+- `hermes tools` — per-platform tool enable/disable with curses UI
+- `hermes doctor` for health checks across all configured providers
+- `hermes update` with auto-restart for gateway service
+- Show update-available notice in CLI banner
+- Multiple named custom providers
+- Shell config detection improvement for PATH setup ([#317](https://github.com/NousResearch/hermes-agent/pull/317)) — @mehmetkr-31
+- Consistent HERMES_HOME and .env path resolution ([#51](https://github.com/NousResearch/hermes-agent/pull/51), [#48](https://github.com/NousResearch/hermes-agent/pull/48)) — @deankerr
+- Docker backend fix on macOS + subagent auth for Nous Portal ([#46](https://github.com/NousResearch/hermes-agent/pull/46)) — @rsavitt
+
+---
+
+## 🔧 Tool System
+
+### MCP (Model Context Protocol)
+- Native MCP client with stdio + HTTP transports ([#291](https://github.com/NousResearch/hermes-agent/pull/291) — @0xbyt4, [#301](https://github.com/NousResearch/hermes-agent/pull/301))
+- Sampling support — server-initiated LLM requests ([#753](https://github.com/NousResearch/hermes-agent/pull/753))
+- Resource and prompt discovery
+- Automatic reconnection and security hardening
+- Banner integration, `/reload-mcp` command
+- `hermes tools` UI integration
+
+### Browser
+- Local browser backend — zero-cost headless Chromium (no Browserbase needed)
+- Console/errors tool, annotated screenshots, auto-recording, dogfood QA skill ([#745](https://github.com/NousResearch/hermes-agent/pull/745))
+- Screenshot sharing via MEDIA: on all messaging platforms ([#657](https://github.com/NousResearch/hermes-agent/pull/657))
+
+### Terminal & Execution
+- `execute_code` sandbox with json_parse, shell_quote, retry helpers
+- Docker: custom volume mounts ([#158](https://github.com/NousResearch/hermes-agent/pull/158)) — @Indelwin
+- Daytona cloud sandbox backend ([#451](https://github.com/NousResearch/hermes-agent/pull/451)) — @rovle
+- SSH backend fix ([#59](https://github.com/NousResearch/hermes-agent/pull/59)) — @deankerr
+- Shell noise filtering and login shell execution for environment consistency
+- Head+tail truncation for execute_code stdout overflow
+- Configurable background process notification modes
+
+### File Operations
+- Filesystem checkpoints and `/rollback` command ([#824](https://github.com/NousResearch/hermes-agent/pull/824))
+- Structured tool result hints (next-action guidance) for patch and search_files ([#722](https://github.com/NousResearch/hermes-agent/issues/722))
+- Docker volumes passed to sandbox container config ([#687](https://github.com/NousResearch/hermes-agent/pull/687)) — @manuelschipper
+
+---
+
+## 🧩 Skills Ecosystem
+
+### Skills System
+- Per-platform skill enable/disable ([#743](https://github.com/NousResearch/hermes-agent/pull/743)) — @teyrebaz33
+- Conditional skill activation based on tool availability ([#785](https://github.com/NousResearch/hermes-agent/pull/785)) — @teyrebaz33
+- Skill prerequisites — hide skills with unmet dependencies ([#659](https://github.com/NousResearch/hermes-agent/pull/659)) — @kshitijk4poor
+- Optional skills — shipped but not activated by default
+- `hermes skills browse` — paginated hub browsing
+- Skills sub-category organization
+- Platform-conditional skill loading
+- Atomic skill file writes ([#551](https://github.com/NousResearch/hermes-agent/pull/551)) — @aydnOktay
+- Skills sync data loss prevention ([#563](https://github.com/NousResearch/hermes-agent/pull/563)) — @0xbyt4
+- Dynamic skill slash commands for CLI and gateway
+
+### New Skills (selected)
+- **ASCII Art** — pyfiglet (571 fonts), cowsay, image-to-ascii ([#209](https://github.com/NousResearch/hermes-agent/pull/209)) — @0xbyt4
+- **ASCII Video** — Full production pipeline ([#854](https://github.com/NousResearch/hermes-agent/pull/854)) — @SHL0MS
+- **DuckDuckGo Search** — Firecrawl fallback ([#267](https://github.com/NousResearch/hermes-agent/pull/267)) — @gamedevCloudy; DDGS API expansion ([#598](https://github.com/NousResearch/hermes-agent/pull/598)) — @areu01or00
+- **Solana Blockchain** — Wallet balances, USD pricing, token names ([#212](https://github.com/NousResearch/hermes-agent/pull/212)) — @gizdusum
+- **AgentMail** — Agent-owned email inboxes ([#330](https://github.com/NousResearch/hermes-agent/pull/330)) — @teyrebaz33
+- **Polymarket** — Prediction market data (read-only) ([#629](https://github.com/NousResearch/hermes-agent/pull/629))
+- **OpenClaw Migration** — Official migration tool ([#570](https://github.com/NousResearch/hermes-agent/pull/570)) — @unmodeled-tyler
+- **Domain Intelligence** — Passive recon: subdomains, SSL, WHOIS, DNS ([#136](https://github.com/NousResearch/hermes-agent/pull/136)) — @FurkanL0
+- **Superpowers** — Software development skills ([#137](https://github.com/NousResearch/hermes-agent/pull/137)) — @kaos35
+- **Hermes-Atropos** — RL environment development skill ([#815](https://github.com/NousResearch/hermes-agent/pull/815))
+- Plus: arXiv search, OCR/documents, Excalidraw diagrams, YouTube transcripts, GIF search, Pokémon player, Minecraft modpack server, OpenHue (Philips Hue), Google Workspace, Notion, PowerPoint, Obsidian, find-nearby, and 40+ MLOps skills
+
+---
+
+## 🔒 Security & Reliability
+
+### Security Hardening
+- Path traversal fix in skill_view — prevented reading arbitrary files ([#220](https://github.com/NousResearch/hermes-agent/issues/220)) — @Farukest
+- Shell injection prevention in sudo password piping ([#65](https://github.com/NousResearch/hermes-agent/pull/65)) — @leonsgithub
+- Dangerous command detection: multiline bypass fix ([#233](https://github.com/NousResearch/hermes-agent/pull/233)) — @Farukest; tee/process substitution patterns ([#280](https://github.com/NousResearch/hermes-agent/pull/280)) — @dogiladeveloper
+- Symlink boundary check fix in skills_guard ([#386](https://github.com/NousResearch/hermes-agent/pull/386)) — @Farukest
+- Symlink bypass fix in write deny list on macOS ([#61](https://github.com/NousResearch/hermes-agent/pull/61)) — @0xbyt4
+- Multi-word prompt injection bypass prevention ([#192](https://github.com/NousResearch/hermes-agent/pull/192)) — @0xbyt4
+- Cron prompt injection scanner bypass fix ([#63](https://github.com/NousResearch/hermes-agent/pull/63)) — @0xbyt4
+- Enforce 0600/0700 file permissions on sensitive files ([#757](https://github.com/NousResearch/hermes-agent/pull/757))
+- .env file permissions restricted to owner-only ([#529](https://github.com/NousResearch/hermes-agent/pull/529)) — @Himess
+- `--force` flag properly blocked from overriding dangerous verdicts ([#388](https://github.com/NousResearch/hermes-agent/pull/388)) — @Farukest
+- FTS5 query sanitization + DB connection leak fix ([#565](https://github.com/NousResearch/hermes-agent/pull/565)) — @0xbyt4
+- Expand secret redaction patterns + config toggle to disable
+- In-memory permanent allowlist to prevent data leak ([#600](https://github.com/NousResearch/hermes-agent/pull/600)) — @alireza78a
+
+### Atomic Writes (data loss prevention)
+- sessions.json ([#611](https://github.com/NousResearch/hermes-agent/pull/611)) — @alireza78a
+- Cron jobs ([#146](https://github.com/NousResearch/hermes-agent/pull/146)) — @alireza78a
+- .env config ([#954](https://github.com/NousResearch/hermes-agent/pull/954))
+- Process checkpoints ([#298](https://github.com/NousResearch/hermes-agent/pull/298)) — @aydnOktay
+- Batch runner ([#297](https://github.com/NousResearch/hermes-agent/pull/297)) — @aydnOktay
+- Skill files ([#551](https://github.com/NousResearch/hermes-agent/pull/551)) — @aydnOktay
+
+### Reliability
+- Guard all print() against OSError for systemd/headless environments ([#963](https://github.com/NousResearch/hermes-agent/pull/963))
+- Reset all retry counters at start of run_conversation ([#607](https://github.com/NousResearch/hermes-agent/pull/607)) — @0xbyt4
+- Return deny on approval callback timeout instead of None ([#603](https://github.com/NousResearch/hermes-agent/pull/603)) — @0xbyt4
+- Fix None message content crashes across codebase ([#277](https://github.com/NousResearch/hermes-agent/pull/277))
+- Fix context overrun crash with local LLM backends ([#403](https://github.com/NousResearch/hermes-agent/pull/403)) — @ch3ronsa
+- Prevent `_flush_sentinel` from leaking to external APIs ([#227](https://github.com/NousResearch/hermes-agent/pull/227)) — @Farukest
+- Prevent conversation_history mutation in callers ([#229](https://github.com/NousResearch/hermes-agent/pull/229)) — @Farukest
+- Fix systemd restart loop ([#614](https://github.com/NousResearch/hermes-agent/pull/614)) — @voidborne-d
+- Close file handles and sockets to prevent fd leaks ([#568](https://github.com/NousResearch/hermes-agent/pull/568) — @alireza78a, [#296](https://github.com/NousResearch/hermes-agent/pull/296) — @alireza78a, [#709](https://github.com/NousResearch/hermes-agent/pull/709) — @memosr)
+- Prevent data loss in clipboard PNG conversion ([#602](https://github.com/NousResearch/hermes-agent/pull/602)) — @0xbyt4
+- Eliminate shell noise from terminal output ([#293](https://github.com/NousResearch/hermes-agent/pull/293)) — @0xbyt4
+- Timezone-aware now() for prompt, cron, and execute_code ([#309](https://github.com/NousResearch/hermes-agent/pull/309)) — @areu01or00
+
+### Windows Compatibility
+- Guard POSIX-only process functions ([#219](https://github.com/NousResearch/hermes-agent/pull/219)) — @Farukest
+- Windows native support via Git Bash + ZIP-based update fallback
+- pywinpty for PTY support ([#457](https://github.com/NousResearch/hermes-agent/pull/457)) — @shitcoinsherpa
+- Explicit UTF-8 encoding on all config/data file I/O ([#458](https://github.com/NousResearch/hermes-agent/pull/458)) — @shitcoinsherpa
+- Windows-compatible path handling ([#354](https://github.com/NousResearch/hermes-agent/pull/354), [#390](https://github.com/NousResearch/hermes-agent/pull/390)) — @Farukest
+- Regex-based search output parsing for drive-letter paths ([#533](https://github.com/NousResearch/hermes-agent/pull/533)) — @Himess
+- Auth store file lock for Windows ([#455](https://github.com/NousResearch/hermes-agent/pull/455)) — @shitcoinsherpa
+
+---
+
+## 🐛 Notable Bug Fixes
+
+- Fix DeepSeek V3 tool call parser silently dropping multi-line JSON arguments ([#444](https://github.com/NousResearch/hermes-agent/pull/444)) — @PercyDikec
+- Fix gateway transcript losing 1 message per turn due to offset mismatch ([#395](https://github.com/NousResearch/hermes-agent/pull/395)) — @PercyDikec
+- Fix /retry command silently discarding the agent's final response ([#441](https://github.com/NousResearch/hermes-agent/pull/441)) — @PercyDikec
+- Fix max-iterations retry returning empty string after think-block stripping ([#438](https://github.com/NousResearch/hermes-agent/pull/438)) — @PercyDikec
+- Fix max-iterations retry using hardcoded max_tokens ([#436](https://github.com/NousResearch/hermes-agent/pull/436)) — @Farukest
+- Fix Codex status dict key mismatch ([#448](https://github.com/NousResearch/hermes-agent/pull/448)) and visibility filter ([#446](https://github.com/NousResearch/hermes-agent/pull/446)) — @PercyDikec
+- Strip \<think\> blocks from final user-facing responses ([#174](https://github.com/NousResearch/hermes-agent/pull/174)) — @Bartok9
+- Fix \<think\> block regex stripping visible content when model discusses tags literally ([#786](https://github.com/NousResearch/hermes-agent/issues/786))
+- Fix Mistral 422 errors from leftover finish_reason in assistant messages ([#253](https://github.com/NousResearch/hermes-agent/pull/253)) — @Sertug17
+- Fix OPENROUTER_API_KEY resolution order across all code paths ([#295](https://github.com/NousResearch/hermes-agent/pull/295)) — @0xbyt4
+- Fix OPENAI_BASE_URL API key priority ([#420](https://github.com/NousResearch/hermes-agent/pull/420)) — @manuelschipper
+- Fix Anthropic "prompt is too long" 400 error not detected as context length error ([#813](https://github.com/NousResearch/hermes-agent/issues/813))
+- Fix SQLite session transcript accumulating duplicate messages — 3-4x token inflation ([#860](https://github.com/NousResearch/hermes-agent/issues/860))
+- Fix setup wizard skipping API key prompts on first install ([#748](https://github.com/NousResearch/hermes-agent/pull/748))
+- Fix setup wizard showing OpenRouter model list for Nous Portal ([#575](https://github.com/NousResearch/hermes-agent/pull/575)) — @PercyDikec
+- Fix provider selection not persisting when switching via hermes model ([#881](https://github.com/NousResearch/hermes-agent/pull/881))
+- Fix Docker backend failing when docker not in PATH on macOS ([#889](https://github.com/NousResearch/hermes-agent/pull/889))
+- Fix ClawHub Skills Hub adapter for API endpoint changes ([#286](https://github.com/NousResearch/hermes-agent/pull/286)) — @BP602
+- Fix Honcho auto-enable when API key is present ([#243](https://github.com/NousResearch/hermes-agent/pull/243)) — @Bartok9
+- Fix duplicate 'skills' subparser crash on Python 3.11+ ([#898](https://github.com/NousResearch/hermes-agent/issues/898))
+- Fix memory tool entry parsing when content contains section sign ([#162](https://github.com/NousResearch/hermes-agent/pull/162)) — @aydnOktay
+- Fix piped install silently aborting when interactive prompts fail ([#72](https://github.com/NousResearch/hermes-agent/pull/72)) — @cutepawss
+- Fix false positives in recursive delete detection ([#68](https://github.com/NousResearch/hermes-agent/pull/68)) — @cutepawss
+- Fix Ruff lint warnings across codebase ([#608](https://github.com/NousResearch/hermes-agent/pull/608)) — @JackTheGit
+- Fix Anthropic native base URL fail-fast ([#173](https://github.com/NousResearch/hermes-agent/pull/173)) — @adavyas
+- Fix install.sh creating ~/.hermes before moving Node.js directory ([#53](https://github.com/NousResearch/hermes-agent/pull/53)) — @JoshuaMart
+- Fix SystemExit traceback during atexit cleanup on Ctrl+C ([#55](https://github.com/NousResearch/hermes-agent/pull/55)) — @bierlingm
+- Restore missing MIT license file ([#620](https://github.com/NousResearch/hermes-agent/pull/620)) — @stablegenius49
+
+---
+
+## 🧪 Testing
+
+- **3,289 tests** across agent, gateway, tools, cron, and CLI
+- Parallelized test suite with pytest-xdist ([#802](https://github.com/NousResearch/hermes-agent/pull/802)) — @OutThisLife
+- Unit tests batch 1: 8 core modules ([#60](https://github.com/NousResearch/hermes-agent/pull/60)) — @0xbyt4
+- Unit tests batch 2: 8 more modules ([#62](https://github.com/NousResearch/hermes-agent/pull/62)) — @0xbyt4
+- Unit tests batch 3: 8 untested modules ([#191](https://github.com/NousResearch/hermes-agent/pull/191)) — @0xbyt4
+- Unit tests batch 4: 5 security/logic-critical modules ([#193](https://github.com/NousResearch/hermes-agent/pull/193)) — @0xbyt4
+- AIAgent (run_agent.py) unit tests ([#67](https://github.com/NousResearch/hermes-agent/pull/67)) — @0xbyt4
+- Trajectory compressor tests ([#203](https://github.com/NousResearch/hermes-agent/pull/203)) — @0xbyt4
+- Clarify tool tests ([#121](https://github.com/NousResearch/hermes-agent/pull/121)) — @Bartok9
+- Telegram format tests — 43 tests for italic/bold/code rendering ([#204](https://github.com/NousResearch/hermes-agent/pull/204)) — @0xbyt4
+- Vision tools type hints + 42 tests ([#792](https://github.com/NousResearch/hermes-agent/pull/792))
+- Compressor tool-call boundary regression tests ([#648](https://github.com/NousResearch/hermes-agent/pull/648)) — @intertwine
+- Test structure reorganization ([#34](https://github.com/NousResearch/hermes-agent/pull/34)) — @0xbyt4
+- Shell noise elimination + fix 36 test failures ([#293](https://github.com/NousResearch/hermes-agent/pull/293)) — @0xbyt4
+
+---
+
+## 🔬 RL & Evaluation Environments
+
+- WebResearchEnv — Multi-step web research RL environment ([#434](https://github.com/NousResearch/hermes-agent/pull/434)) — @jackx707
+- Modal sandbox concurrency limits to avoid deadlocks ([#621](https://github.com/NousResearch/hermes-agent/pull/621)) — @voteblake
+- Hermes-atropos-environments bundled skill ([#815](https://github.com/NousResearch/hermes-agent/pull/815))
+- Local vLLM instance support for evaluation — @dmahan93
+- YC-Bench long-horizon agent benchmark environment
+- OpenThoughts-TBLite evaluation environment and scripts
+
+---
+
+## 📚 Documentation
+
+- Full documentation website (Docusaurus) with 37+ pages
+- Comprehensive platform setup guides for Telegram, Discord, Slack, WhatsApp, Signal, Email
+- AGENTS.md — development guide for AI coding assistants
+- CONTRIBUTING.md ([#117](https://github.com/NousResearch/hermes-agent/pull/117)) — @Bartok9
+- Slash commands reference ([#142](https://github.com/NousResearch/hermes-agent/pull/142)) — @Bartok9
+- Comprehensive AGENTS.md accuracy audit ([#732](https://github.com/NousResearch/hermes-agent/pull/732))
+- Skin/theme system documentation
+- MCP documentation and examples
+- Docs accuracy audit — 35+ corrections
+- Documentation typo fixes ([#825](https://github.com/NousResearch/hermes-agent/pull/825), [#439](https://github.com/NousResearch/hermes-agent/pull/439)) — @JackTheGit
+- CLI config precedence and terminology standardization ([#166](https://github.com/NousResearch/hermes-agent/pull/166), [#167](https://github.com/NousResearch/hermes-agent/pull/167), [#168](https://github.com/NousResearch/hermes-agent/pull/168)) — @Jr-kenny
+- Telegram token regex documentation ([#713](https://github.com/NousResearch/hermes-agent/pull/713)) — @VolodymyrBg
+
+---
+
+## 👥 Contributors
+
+Thank you to the 63 contributors who made this release possible! In just over two weeks, the Hermes Agent community came together to ship an extraordinary amount of work.
+
+### Core
+- **@teknium1** — 43 PRs: Project lead, core architecture, provider router, sessions, skills, CLI, documentation
+
+### Top Community Contributors
+- **@0xbyt4** — 40 PRs: MCP client, Home Assistant, security fixes (symlink, prompt injection, cron), extensive test coverage (6 batches), ascii-art skill, shell noise elimination, skills sync, Telegram formatting, and dozens more
+- **@Farukest** — 16 PRs: Security hardening (path traversal, dangerous command detection, symlink boundary), Windows compatibility (POSIX guards, path handling), WhatsApp fixes, max-iterations retry, gateway fixes
+- **@aydnOktay** — 11 PRs: Atomic writes (process checkpoints, batch runner, skill files), error handling improvements across Telegram, Discord, code execution, transcription, TTS, and skills
+- **@Bartok9** — 9 PRs: CONTRIBUTING.md, slash commands reference, Discord channel topics, think-block stripping, TTS fix, Honcho fix, session count fix, clarify tests
+- **@PercyDikec** — 7 PRs: DeepSeek V3 parser fix, /retry response discard, gateway transcript offset, Codex status/visibility, max-iterations retry, setup wizard fix
+- **@teyrebaz33** — 5 PRs: Skills enable/disable system, quick commands, personality customization, conditional skill activation
+- **@alireza78a** — 5 PRs: Atomic writes (cron, sessions), fd leak prevention, security allowlist, code execution socket cleanup
+- **@shitcoinsherpa** — 3 PRs: Windows support (pywinpty, UTF-8 encoding, auth store lock)
+- **@Himess** — 3 PRs: Cron/HomeAssistant/Daytona fix, Windows drive-letter parsing, .env permissions
+- **@satelerd** — 2 PRs: WhatsApp native media, multi-user session isolation
+- **@rovle** — 1 PR: Daytona cloud sandbox backend (4 commits)
+- **@erosika** — 1 PR: Honcho AI-native memory integration
+- **@dmahan93** — 1 PR: --fuck-it-ship-it flag + RL environment work
+- **@SHL0MS** — 1 PR: ASCII video skill
+
+### All Contributors
+@0xbyt4, @BP602, @Bartok9, @Farukest, @FurkanL0, @Himess, @Indelwin, @JackTheGit, @JoshuaMart, @Jr-kenny, @OutThisLife, @PercyDikec, @SHL0MS, @Sertug17, @VencentSoliman, @VolodymyrBg, @adavyas, @alireza78a, @areu01or00, @aydnOktay, @batuhankocyigit, @bierlingm, @caentzminger, @cesareth, @ch3ronsa, @christomitov, @cutepawss, @deankerr, @dmahan93, @dogiladeveloper, @dragonkhoi, @erosika, @gamedevCloudy, @gizdusum, @grp06, @intertwine, @jackx707, @jdblackstar, @johnh4098, @kaos35, @kshitijk4poor, @leonsgithub, @luisv-1, @manuelschipper, @mehmetkr-31, @memosr, @PeterFile, @rewbs, @rovle, @rsavitt, @satelerd, @spanishflu-est1918, @stablegenius49, @tars90percent, @tekelala, @teknium1, @teyrebaz33, @tripledoublev, @unmodeled-tyler, @voidborne-d, @voteblake, @ygd58
+
+---
+
+**Full Changelog**: [v0.1.0...v2026.3.12](https://github.com/NousResearch/hermes-agent/compare/v0.1.0...v2026.3.12)

RELEASE_v0.3.0.md

@@ -0,0 +1,377 @@
+# Hermes Agent v0.3.0 (v2026.3.17)
+
+**Release Date:** March 17, 2026
+
+> The streaming, plugins, and provider release — unified real-time token delivery, first-class plugin architecture, rebuilt provider system with Vercel AI Gateway, native Anthropic provider, smart approvals, live Chrome CDP browser connect, ACP IDE integration, Honcho memory, voice mode, persistent shell, and 50+ bug fixes across every platform.
+
+---
+
+## ✨ Highlights
+
+- **Unified Streaming Infrastructure** — Real-time token-by-token delivery in CLI and all gateway platforms. Responses stream as they're generated instead of arriving as a block. ([#1538](https://github.com/NousResearch/hermes-agent/pull/1538))
+
+- **First-Class Plugin Architecture** — Drop Python files into `~/.hermes/plugins/` to extend Hermes with custom tools, commands, and hooks. No forking required. ([#1544](https://github.com/NousResearch/hermes-agent/pull/1544), [#1555](https://github.com/NousResearch/hermes-agent/pull/1555))
+
+- **Native Anthropic Provider** — Direct Anthropic API calls with Claude Code credential auto-discovery, OAuth PKCE flows, and native prompt caching. No OpenRouter middleman needed. ([#1097](https://github.com/NousResearch/hermes-agent/pull/1097))
+
+- **Smart Approvals + /stop Command** — Codex-inspired approval system that learns which commands are safe and remembers your preferences. `/stop` kills the current agent run immediately. ([#1543](https://github.com/NousResearch/hermes-agent/pull/1543))
+
+- **Honcho Memory Integration** — Async memory writes, configurable recall modes, session title integration, and multi-user isolation in gateway mode. By @erosika. ([#736](https://github.com/NousResearch/hermes-agent/pull/736))
+
+- **Voice Mode** — Push-to-talk in CLI, voice notes in Telegram/Discord, Discord voice channel support, and local Whisper transcription via faster-whisper. ([#1299](https://github.com/NousResearch/hermes-agent/pull/1299), [#1185](https://github.com/NousResearch/hermes-agent/pull/1185), [#1429](https://github.com/NousResearch/hermes-agent/pull/1429))
+
+- **Concurrent Tool Execution** — Multiple independent tool calls now run in parallel via ThreadPoolExecutor, significantly reducing latency for multi-tool turns. ([#1152](https://github.com/NousResearch/hermes-agent/pull/1152))
+
+- **PII Redaction** — When `privacy.redact_pii` is enabled, personally identifiable information is automatically scrubbed before sending context to LLM providers. ([#1542](https://github.com/NousResearch/hermes-agent/pull/1542))
+
+- **`/browser connect` via CDP** — Attach browser tools to a live Chrome instance through Chrome DevTools Protocol. Debug, inspect, and interact with pages you already have open. ([#1549](https://github.com/NousResearch/hermes-agent/pull/1549))
+
+- **Vercel AI Gateway Provider** — Route Hermes through Vercel's AI Gateway for access to their model catalog and infrastructure. ([#1628](https://github.com/NousResearch/hermes-agent/pull/1628))
+
+- **Centralized Provider Router** — Rebuilt provider system with `call_llm` API, unified `/model` command, auto-detect provider on model switch, and direct endpoint overrides for auxiliary/delegation clients. ([#1003](https://github.com/NousResearch/hermes-agent/pull/1003), [#1506](https://github.com/NousResearch/hermes-agent/pull/1506), [#1375](https://github.com/NousResearch/hermes-agent/pull/1375))
+
+- **ACP Server (IDE Integration)** — VS Code, Zed, and JetBrains can now connect to Hermes as an agent backend, with full slash command support. ([#1254](https://github.com/NousResearch/hermes-agent/pull/1254), [#1532](https://github.com/NousResearch/hermes-agent/pull/1532))
+
+- **Persistent Shell Mode** — Local and SSH terminal backends can maintain shell state across tool calls — cd, env vars, and aliases persist. By @alt-glitch. ([#1067](https://github.com/NousResearch/hermes-agent/pull/1067), [#1483](https://github.com/NousResearch/hermes-agent/pull/1483))
+
+- **Agentic On-Policy Distillation (OPD)** — New RL training environment for distilling agent policies, expanding the Atropos training ecosystem. ([#1149](https://github.com/NousResearch/hermes-agent/pull/1149))
+
+---
+
+## 🏗️ Core Agent & Architecture
+
+### Provider & Model Support
+- **Centralized provider router** with `call_llm` API and unified `/model` command — switch models and providers seamlessly ([#1003](https://github.com/NousResearch/hermes-agent/pull/1003))
+- **Vercel AI Gateway** provider support ([#1628](https://github.com/NousResearch/hermes-agent/pull/1628))
+- **Auto-detect provider** when switching models via `/model` ([#1506](https://github.com/NousResearch/hermes-agent/pull/1506))
+- **Direct endpoint overrides** for auxiliary and delegation clients — point vision/subagent calls at specific endpoints ([#1375](https://github.com/NousResearch/hermes-agent/pull/1375))
+- **Native Anthropic auxiliary vision** — use Claude's native vision API instead of routing through OpenAI-compatible endpoints ([#1377](https://github.com/NousResearch/hermes-agent/pull/1377))
+- Anthropic OAuth flow improvements — auto-run `claude setup-token`, reauthentication, PKCE state persistence, identity fingerprinting ([#1132](https://github.com/NousResearch/hermes-agent/pull/1132), [#1360](https://github.com/NousResearch/hermes-agent/pull/1360), [#1396](https://github.com/NousResearch/hermes-agent/pull/1396), [#1597](https://github.com/NousResearch/hermes-agent/pull/1597))
+- Fix adaptive thinking without `budget_tokens` for Claude 4.6 models — by @ASRagab ([#1128](https://github.com/NousResearch/hermes-agent/pull/1128))
+- Fix Anthropic cache markers through adapter — by @brandtcormorant ([#1216](https://github.com/NousResearch/hermes-agent/pull/1216))
+- Retry Anthropic 429/529 errors and surface details to users — by @0xbyt4 ([#1585](https://github.com/NousResearch/hermes-agent/pull/1585))
+- Fix Anthropic adapter max_tokens, fallback crash, proxy base_url — by @0xbyt4 ([#1121](https://github.com/NousResearch/hermes-agent/pull/1121))
+- Fix DeepSeek V3 parser dropping multiple parallel tool calls — by @mr-emmett-one ([#1365](https://github.com/NousResearch/hermes-agent/pull/1365), [#1300](https://github.com/NousResearch/hermes-agent/pull/1300))
+- Accept unlisted models with warning instead of rejecting ([#1047](https://github.com/NousResearch/hermes-agent/pull/1047), [#1102](https://github.com/NousResearch/hermes-agent/pull/1102))
+- Skip reasoning params for unsupported OpenRouter models ([#1485](https://github.com/NousResearch/hermes-agent/pull/1485))
+- MiniMax Anthropic API compatibility fix ([#1623](https://github.com/NousResearch/hermes-agent/pull/1623))
+- Custom endpoint `/models` verification and `/v1` base URL suggestion ([#1480](https://github.com/NousResearch/hermes-agent/pull/1480))
+- Resolve delegation providers from `custom_providers` config ([#1328](https://github.com/NousResearch/hermes-agent/pull/1328))
+- Kimi model additions and User-Agent fix ([#1039](https://github.com/NousResearch/hermes-agent/pull/1039))
+- Strip `call_id`/`response_item_id` for Mistral compatibility ([#1058](https://github.com/NousResearch/hermes-agent/pull/1058))
+
+### Agent Loop & Conversation
+- **Anthropic Context Editing API** support ([#1147](https://github.com/NousResearch/hermes-agent/pull/1147))
+- Improved context compaction handoff summaries — compressor now preserves more actionable state ([#1273](https://github.com/NousResearch/hermes-agent/pull/1273))
+- Sync session_id after mid-run context compression ([#1160](https://github.com/NousResearch/hermes-agent/pull/1160))
+- Session hygiene threshold tuned to 50% for more proactive compression ([#1096](https://github.com/NousResearch/hermes-agent/pull/1096), [#1161](https://github.com/NousResearch/hermes-agent/pull/1161))
+- Include session ID in system prompt via `--pass-session-id` flag ([#1040](https://github.com/NousResearch/hermes-agent/pull/1040))
+- Prevent closed OpenAI client reuse across retries ([#1391](https://github.com/NousResearch/hermes-agent/pull/1391))
+- Sanitize chat payloads and provider precedence ([#1253](https://github.com/NousResearch/hermes-agent/pull/1253))
+- Handle dict tool call arguments from Codex and local backends ([#1393](https://github.com/NousResearch/hermes-agent/pull/1393), [#1440](https://github.com/NousResearch/hermes-agent/pull/1440))
+
+### Memory & Sessions
+- **Improve memory prioritization** — user preferences and corrections weighted above procedural knowledge ([#1548](https://github.com/NousResearch/hermes-agent/pull/1548))
+- Tighter memory and session recall guidance in system prompts ([#1329](https://github.com/NousResearch/hermes-agent/pull/1329))
+- Persist CLI token counts to session DB for `/insights` ([#1498](https://github.com/NousResearch/hermes-agent/pull/1498))
+- Keep Honcho recall out of the cached system prefix ([#1201](https://github.com/NousResearch/hermes-agent/pull/1201))
+- Correct `seed_ai_identity` to use `session.add_messages()` ([#1475](https://github.com/NousResearch/hermes-agent/pull/1475))
+- Isolate Honcho session routing for multi-user gateway ([#1500](https://github.com/NousResearch/hermes-agent/pull/1500))
+
+---
+
+## 📱 Messaging Platforms (Gateway)
+
+### Gateway Core
+- **System gateway service mode** — run as a system-level systemd service, not just user-level ([#1371](https://github.com/NousResearch/hermes-agent/pull/1371))
+- **Gateway install scope prompts** — choose user vs system scope during setup ([#1374](https://github.com/NousResearch/hermes-agent/pull/1374))
+- **Reasoning hot reload** — change reasoning settings without restarting the gateway ([#1275](https://github.com/NousResearch/hermes-agent/pull/1275))
+- Default group sessions to per-user isolation — no more shared state across users in group chats ([#1495](https://github.com/NousResearch/hermes-agent/pull/1495), [#1417](https://github.com/NousResearch/hermes-agent/pull/1417))
+- Harden gateway restart recovery ([#1310](https://github.com/NousResearch/hermes-agent/pull/1310))
+- Cancel active runs during shutdown ([#1427](https://github.com/NousResearch/hermes-agent/pull/1427))
+- SSL certificate auto-detection for NixOS and non-standard systems ([#1494](https://github.com/NousResearch/hermes-agent/pull/1494))
+- Auto-detect D-Bus session bus for `systemctl --user` on headless servers ([#1601](https://github.com/NousResearch/hermes-agent/pull/1601))
+- Auto-enable systemd linger during gateway install on headless servers ([#1334](https://github.com/NousResearch/hermes-agent/pull/1334))
+- Fall back to module entrypoint when `hermes` is not on PATH ([#1355](https://github.com/NousResearch/hermes-agent/pull/1355))
+- Fix dual gateways on macOS launchd after `hermes update` ([#1567](https://github.com/NousResearch/hermes-agent/pull/1567))
+- Remove recursive ExecStop from systemd units ([#1530](https://github.com/NousResearch/hermes-agent/pull/1530))
+- Prevent logging handler accumulation in gateway mode ([#1251](https://github.com/NousResearch/hermes-agent/pull/1251))
+- Restart on retryable startup failures — by @jplew ([#1517](https://github.com/NousResearch/hermes-agent/pull/1517))
+- Backfill model on gateway sessions after agent runs ([#1306](https://github.com/NousResearch/hermes-agent/pull/1306))
+- PID-based gateway kill and deferred config write ([#1499](https://github.com/NousResearch/hermes-agent/pull/1499))
+
+### Telegram
+- Buffer media groups to prevent self-interruption from photo bursts ([#1341](https://github.com/NousResearch/hermes-agent/pull/1341), [#1422](https://github.com/NousResearch/hermes-agent/pull/1422))
+- Retry on transient TLS failures during connect and send ([#1535](https://github.com/NousResearch/hermes-agent/pull/1535))
+- Harden polling conflict handling ([#1339](https://github.com/NousResearch/hermes-agent/pull/1339))
+- Escape chunk indicators and inline code in MarkdownV2 ([#1478](https://github.com/NousResearch/hermes-agent/pull/1478), [#1626](https://github.com/NousResearch/hermes-agent/pull/1626))
+- Check updater/app state before disconnect ([#1389](https://github.com/NousResearch/hermes-agent/pull/1389))
+
+### Discord
+- `/thread` command with `auto_thread` config and media metadata fixes ([#1178](https://github.com/NousResearch/hermes-agent/pull/1178))
+- Auto-thread on @mention, skip mention text in bot threads ([#1438](https://github.com/NousResearch/hermes-agent/pull/1438))
+- Retry without reply reference for system messages ([#1385](https://github.com/NousResearch/hermes-agent/pull/1385))
+- Preserve native document and video attachment support ([#1392](https://github.com/NousResearch/hermes-agent/pull/1392))
+- Defer discord adapter annotations to avoid optional import crashes ([#1314](https://github.com/NousResearch/hermes-agent/pull/1314))
+
+### Slack
+- Thread handling overhaul — progress messages, responses, and session isolation all respect threads ([#1103](https://github.com/NousResearch/hermes-agent/pull/1103))
+- Formatting, reactions, user resolution, and command improvements ([#1106](https://github.com/NousResearch/hermes-agent/pull/1106))
+- Fix MAX_MESSAGE_LENGTH 3900 → 39000 ([#1117](https://github.com/NousResearch/hermes-agent/pull/1117))
+- File upload fallback preserves thread context — by @0xbyt4 ([#1122](https://github.com/NousResearch/hermes-agent/pull/1122))
+- Improve setup guidance ([#1387](https://github.com/NousResearch/hermes-agent/pull/1387))
+
+### Email
+- Fix IMAP UID tracking and SMTP TLS verification ([#1305](https://github.com/NousResearch/hermes-agent/pull/1305))
+- Add `skip_attachments` option via config.yaml ([#1536](https://github.com/NousResearch/hermes-agent/pull/1536))
+
+### Home Assistant
+- Event filtering closed by default ([#1169](https://github.com/NousResearch/hermes-agent/pull/1169))
+
+---
+
+## 🖥️ CLI & User Experience
+
+### Interactive CLI
+- **Persistent CLI status bar** — always-visible model, provider, and token counts ([#1522](https://github.com/NousResearch/hermes-agent/pull/1522))
+- **File path autocomplete** in the input prompt ([#1545](https://github.com/NousResearch/hermes-agent/pull/1545))
+- **`/plan` command** — generate implementation plans from specs ([#1372](https://github.com/NousResearch/hermes-agent/pull/1372), [#1381](https://github.com/NousResearch/hermes-agent/pull/1381))
+- **Major `/rollback` improvements** — richer checkpoint history, clearer UX ([#1505](https://github.com/NousResearch/hermes-agent/pull/1505))
+- **Preload CLI skills on launch** — skills are ready before the first prompt ([#1359](https://github.com/NousResearch/hermes-agent/pull/1359))
+- **Centralized slash command registry** — all commands defined once, consumed everywhere ([#1603](https://github.com/NousResearch/hermes-agent/pull/1603))
+- `/bg` alias for `/background` ([#1590](https://github.com/NousResearch/hermes-agent/pull/1590))
+- Prefix matching for slash commands — `/mod` resolves to `/model` ([#1320](https://github.com/NousResearch/hermes-agent/pull/1320))
+- `/new`, `/reset`, `/clear` now start genuinely fresh sessions ([#1237](https://github.com/NousResearch/hermes-agent/pull/1237))
+- Accept session ID prefixes for session actions ([#1425](https://github.com/NousResearch/hermes-agent/pull/1425))
+- TUI prompt and accent output now respect active skin ([#1282](https://github.com/NousResearch/hermes-agent/pull/1282))
+- Centralize tool emoji metadata in registry + skin integration ([#1484](https://github.com/NousResearch/hermes-agent/pull/1484))
+- "View full command" option added to dangerous command approval — by @teknium1 based on design by community ([#887](https://github.com/NousResearch/hermes-agent/pull/887))
+- Non-blocking startup update check and banner deduplication ([#1386](https://github.com/NousResearch/hermes-agent/pull/1386))
+- `/reasoning` command output ordering and inline think extraction fixes ([#1031](https://github.com/NousResearch/hermes-agent/pull/1031))
+- Verbose mode shows full untruncated output ([#1472](https://github.com/NousResearch/hermes-agent/pull/1472))
+- Fix `/status` to report live state and tokens ([#1476](https://github.com/NousResearch/hermes-agent/pull/1476))
+- Seed a default global SOUL.md ([#1311](https://github.com/NousResearch/hermes-agent/pull/1311))
+
+### Setup & Configuration
+- **OpenClaw migration** during first-time setup — by @kshitijk4poor ([#981](https://github.com/NousResearch/hermes-agent/pull/981))
+- `hermes claw migrate` command + migration docs ([#1059](https://github.com/NousResearch/hermes-agent/pull/1059))
+- Smart vision setup that respects the user's chosen provider ([#1323](https://github.com/NousResearch/hermes-agent/pull/1323))
+- Handle headless setup flows end-to-end ([#1274](https://github.com/NousResearch/hermes-agent/pull/1274))
+- Prefer curses over `simple_term_menu` in setup.py ([#1487](https://github.com/NousResearch/hermes-agent/pull/1487))
+- Show effective model and provider in `/status` ([#1284](https://github.com/NousResearch/hermes-agent/pull/1284))
+- Config set examples use placeholder syntax ([#1322](https://github.com/NousResearch/hermes-agent/pull/1322))
+- Reload .env over stale shell overrides ([#1434](https://github.com/NousResearch/hermes-agent/pull/1434))
+- Fix is_coding_plan NameError crash — by @0xbyt4 ([#1123](https://github.com/NousResearch/hermes-agent/pull/1123))
+- Add missing packages to setuptools config — by @alt-glitch ([#912](https://github.com/NousResearch/hermes-agent/pull/912))
+- Installer: clarify why sudo is needed at every prompt ([#1602](https://github.com/NousResearch/hermes-agent/pull/1602))
+
+---
+
+## 🔧 Tool System
+
+### Terminal & Execution
+- **Persistent shell mode** for local and SSH backends — maintain shell state across tool calls — by @alt-glitch ([#1067](https://github.com/NousResearch/hermes-agent/pull/1067), [#1483](https://github.com/NousResearch/hermes-agent/pull/1483))
+- **Tirith pre-exec command scanning** — security layer that analyzes commands before execution ([#1256](https://github.com/NousResearch/hermes-agent/pull/1256))
+- Strip Hermes provider env vars from all subprocess environments ([#1157](https://github.com/NousResearch/hermes-agent/pull/1157), [#1172](https://github.com/NousResearch/hermes-agent/pull/1172), [#1399](https://github.com/NousResearch/hermes-agent/pull/1399), [#1419](https://github.com/NousResearch/hermes-agent/pull/1419)) — initial fix by @eren-karakus0
+- SSH preflight check ([#1486](https://github.com/NousResearch/hermes-agent/pull/1486))
+- Docker backend: make cwd workspace mount explicit opt-in ([#1534](https://github.com/NousResearch/hermes-agent/pull/1534))
+- Add project root to PYTHONPATH in execute_code sandbox ([#1383](https://github.com/NousResearch/hermes-agent/pull/1383))
+- Eliminate execute_code progress spam on gateway platforms ([#1098](https://github.com/NousResearch/hermes-agent/pull/1098))
+- Clearer docker backend preflight errors ([#1276](https://github.com/NousResearch/hermes-agent/pull/1276))
+
+### Browser
+- **`/browser connect`** — attach browser tools to a live Chrome instance via CDP ([#1549](https://github.com/NousResearch/hermes-agent/pull/1549))
+- Improve browser cleanup, local browser PATH setup, and screenshot recovery ([#1333](https://github.com/NousResearch/hermes-agent/pull/1333))
+
+### MCP
+- **Selective tool loading** with utility policies — filter which MCP tools are available ([#1302](https://github.com/NousResearch/hermes-agent/pull/1302))
+- Auto-reload MCP tools when `mcp_servers` config changes without restart ([#1474](https://github.com/NousResearch/hermes-agent/pull/1474))
+- Resolve npx stdio connection failures ([#1291](https://github.com/NousResearch/hermes-agent/pull/1291))
+- Preserve MCP toolsets when saving platform tool config ([#1421](https://github.com/NousResearch/hermes-agent/pull/1421))
+
+### Vision
+- Unify vision backend gating ([#1367](https://github.com/NousResearch/hermes-agent/pull/1367))
+- Surface actual error reason instead of generic message ([#1338](https://github.com/NousResearch/hermes-agent/pull/1338))
+- Make Claude image handling work end-to-end ([#1408](https://github.com/NousResearch/hermes-agent/pull/1408))
+
+### Cron
+- **Compress cron management into one tool** — single `cronjob` tool replaces multiple commands ([#1343](https://github.com/NousResearch/hermes-agent/pull/1343))
+- Suppress duplicate cron sends to auto-delivery targets ([#1357](https://github.com/NousResearch/hermes-agent/pull/1357))
+- Persist cron sessions to SQLite ([#1255](https://github.com/NousResearch/hermes-agent/pull/1255))
+- Per-job runtime overrides (provider, model, base_url) ([#1398](https://github.com/NousResearch/hermes-agent/pull/1398))
+- Atomic write in `save_job_output` to prevent data loss on crash ([#1173](https://github.com/NousResearch/hermes-agent/pull/1173))
+- Preserve thread context for `deliver=origin` ([#1437](https://github.com/NousResearch/hermes-agent/pull/1437))
+
+### Patch Tool
+- Avoid corrupting pipe chars in V4A patch apply ([#1286](https://github.com/NousResearch/hermes-agent/pull/1286))
+- Permissive `block_anchor` thresholds and unicode normalization ([#1539](https://github.com/NousResearch/hermes-agent/pull/1539))
+
+### Delegation
+- Add observability metadata to subagent results (model, tokens, duration, tool trace) ([#1175](https://github.com/NousResearch/hermes-agent/pull/1175))
+
+---
+
+## 🧩 Skills Ecosystem
+
+### Skills System
+- **Integrate skills.sh** as a hub source alongside ClawHub ([#1303](https://github.com/NousResearch/hermes-agent/pull/1303))
+- Secure skill env setup on load ([#1153](https://github.com/NousResearch/hermes-agent/pull/1153))
+- Honor policy table for dangerous verdicts ([#1330](https://github.com/NousResearch/hermes-agent/pull/1330))
+- Harden ClawHub skill search exact matches ([#1400](https://github.com/NousResearch/hermes-agent/pull/1400))
+- Fix ClawHub skill install — use `/download` ZIP endpoint ([#1060](https://github.com/NousResearch/hermes-agent/pull/1060))
+- Avoid mislabeling local skills as builtin — by @arceus77-7 ([#862](https://github.com/NousResearch/hermes-agent/pull/862))
+
+### New Skills
+- **Linear** project management ([#1230](https://github.com/NousResearch/hermes-agent/pull/1230))
+- **X/Twitter** via x-cli ([#1285](https://github.com/NousResearch/hermes-agent/pull/1285))
+- **Telephony** — Twilio, SMS, and AI calls ([#1289](https://github.com/NousResearch/hermes-agent/pull/1289))
+- **1Password** — by @arceus77-7 ([#883](https://github.com/NousResearch/hermes-agent/pull/883), [#1179](https://github.com/NousResearch/hermes-agent/pull/1179))
+- **NeuroSkill BCI** integration ([#1135](https://github.com/NousResearch/hermes-agent/pull/1135))
+- **Blender MCP** for 3D modeling ([#1531](https://github.com/NousResearch/hermes-agent/pull/1531))
+- **OSS Security Forensics** ([#1482](https://github.com/NousResearch/hermes-agent/pull/1482))
+- **Parallel CLI** research skill ([#1301](https://github.com/NousResearch/hermes-agent/pull/1301))
+- **OpenCode** CLI skill ([#1174](https://github.com/NousResearch/hermes-agent/pull/1174))
+- **ASCII Video** skill refactored — by @SHL0MS ([#1213](https://github.com/NousResearch/hermes-agent/pull/1213), [#1598](https://github.com/NousResearch/hermes-agent/pull/1598))
+
+---
+
+## 🎙️ Voice Mode
+
+- Voice mode foundation — push-to-talk CLI, Telegram/Discord voice notes ([#1299](https://github.com/NousResearch/hermes-agent/pull/1299))
+- Free local Whisper transcription via faster-whisper ([#1185](https://github.com/NousResearch/hermes-agent/pull/1185))
+- Discord voice channel reliability fixes ([#1429](https://github.com/NousResearch/hermes-agent/pull/1429))
+- Restore local STT fallback for gateway voice notes ([#1490](https://github.com/NousResearch/hermes-agent/pull/1490))
+- Honor `stt.enabled: false` across gateway transcription ([#1394](https://github.com/NousResearch/hermes-agent/pull/1394))
+- Fix bogus incapability message on Telegram voice notes (Issue [#1033](https://github.com/NousResearch/hermes-agent/issues/1033))
+
+---
+
+## 🔌 ACP (IDE Integration)
+
+- Restore ACP server implementation ([#1254](https://github.com/NousResearch/hermes-agent/pull/1254))
+- Support slash commands in ACP adapter ([#1532](https://github.com/NousResearch/hermes-agent/pull/1532))
+
+---
+
+## 🧪 RL Training
+
+- **Agentic On-Policy Distillation (OPD)** environment — new RL training environment for agent policy distillation ([#1149](https://github.com/NousResearch/hermes-agent/pull/1149))
+- Make tinker-atropos RL training fully optional ([#1062](https://github.com/NousResearch/hermes-agent/pull/1062))
+
+---
+
+## 🔒 Security & Reliability
+
+### Security Hardening
+- **Tirith pre-exec command scanning** — static analysis of terminal commands before execution ([#1256](https://github.com/NousResearch/hermes-agent/pull/1256))
+- **PII redaction** when `privacy.redact_pii` is enabled ([#1542](https://github.com/NousResearch/hermes-agent/pull/1542))
+- Strip Hermes provider/gateway/tool env vars from all subprocess environments ([#1157](https://github.com/NousResearch/hermes-agent/pull/1157), [#1172](https://github.com/NousResearch/hermes-agent/pull/1172), [#1399](https://github.com/NousResearch/hermes-agent/pull/1399), [#1419](https://github.com/NousResearch/hermes-agent/pull/1419))
+- Docker cwd workspace mount now explicit opt-in — never auto-mount host directories ([#1534](https://github.com/NousResearch/hermes-agent/pull/1534))
+- Escape parens and braces in fork bomb regex pattern ([#1397](https://github.com/NousResearch/hermes-agent/pull/1397))
+- Harden `.worktreeinclude` path containment ([#1388](https://github.com/NousResearch/hermes-agent/pull/1388))
+- Use description as `pattern_key` to prevent approval collisions ([#1395](https://github.com/NousResearch/hermes-agent/pull/1395))
+
+### Reliability
+- Guard init-time stdio writes ([#1271](https://github.com/NousResearch/hermes-agent/pull/1271))
+- Session log writes reuse shared atomic JSON helper ([#1280](https://github.com/NousResearch/hermes-agent/pull/1280))
+- Atomic temp cleanup protected on interrupts ([#1401](https://github.com/NousResearch/hermes-agent/pull/1401))
+
+---
+
+## 🐛 Notable Bug Fixes
+
+- **`/status` always showing 0 tokens** — now reports live state (Issue [#1465](https://github.com/NousResearch/hermes-agent/issues/1465), [#1476](https://github.com/NousResearch/hermes-agent/pull/1476))
+- **Custom model endpoints not working** — restored config-saved endpoint resolution (Issue [#1460](https://github.com/NousResearch/hermes-agent/issues/1460), [#1373](https://github.com/NousResearch/hermes-agent/pull/1373))
+- **MCP tools not visible until restart** — auto-reload on config change (Issue [#1036](https://github.com/NousResearch/hermes-agent/issues/1036), [#1474](https://github.com/NousResearch/hermes-agent/pull/1474))
+- **`hermes tools` removing MCP tools** — preserve MCP toolsets when saving (Issue [#1247](https://github.com/NousResearch/hermes-agent/issues/1247), [#1421](https://github.com/NousResearch/hermes-agent/pull/1421))
+- **Terminal subprocesses inheriting `OPENAI_BASE_URL`** breaking external tools (Issue [#1002](https://github.com/NousResearch/hermes-agent/issues/1002), [#1399](https://github.com/NousResearch/hermes-agent/pull/1399))
+- **Background process lost on gateway restart** — improved recovery (Issue [#1144](https://github.com/NousResearch/hermes-agent/issues/1144))
+- **Cron jobs not persisting state** — now stored in SQLite (Issue [#1416](https://github.com/NousResearch/hermes-agent/issues/1416), [#1255](https://github.com/NousResearch/hermes-agent/pull/1255))
+- **Cronjob `deliver: origin` not preserving thread context** (Issue [#1219](https://github.com/NousResearch/hermes-agent/issues/1219), [#1437](https://github.com/NousResearch/hermes-agent/pull/1437))
+- **Gateway systemd service failing to auto-restart** when browser processes orphaned (Issue [#1617](https://github.com/NousResearch/hermes-agent/issues/1617))
+- **`/background` completion report cut off in Telegram** (Issue [#1443](https://github.com/NousResearch/hermes-agent/issues/1443))
+- **Model switching not taking effect** (Issue [#1244](https://github.com/NousResearch/hermes-agent/issues/1244), [#1183](https://github.com/NousResearch/hermes-agent/pull/1183))
+- **`hermes doctor` reporting cronjob as unavailable** (Issue [#878](https://github.com/NousResearch/hermes-agent/issues/878), [#1180](https://github.com/NousResearch/hermes-agent/pull/1180))
+- **WhatsApp bridge messages not received** from mobile (Issue [#1142](https://github.com/NousResearch/hermes-agent/issues/1142))
+- **Setup wizard hanging on headless SSH** (Issue [#905](https://github.com/NousResearch/hermes-agent/issues/905), [#1274](https://github.com/NousResearch/hermes-agent/pull/1274))
+- **Log handler accumulation** degrading gateway performance (Issue [#990](https://github.com/NousResearch/hermes-agent/issues/990), [#1251](https://github.com/NousResearch/hermes-agent/pull/1251))
+- **Gateway NULL model in DB** (Issue [#987](https://github.com/NousResearch/hermes-agent/issues/987), [#1306](https://github.com/NousResearch/hermes-agent/pull/1306))
+- **Strict endpoints rejecting replayed tool_calls** (Issue [#893](https://github.com/NousResearch/hermes-agent/issues/893))
+- **Remaining hardcoded `~/.hermes` paths** — all now respect `HERMES_HOME` (Issue [#892](https://github.com/NousResearch/hermes-agent/issues/892), [#1233](https://github.com/NousResearch/hermes-agent/pull/1233))
+- **Delegate tool not working with custom inference providers** (Issue [#1011](https://github.com/NousResearch/hermes-agent/issues/1011), [#1328](https://github.com/NousResearch/hermes-agent/pull/1328))
+- **Skills Guard blocking official skills** (Issue [#1006](https://github.com/NousResearch/hermes-agent/issues/1006), [#1330](https://github.com/NousResearch/hermes-agent/pull/1330))
+- **Setup writing provider before model selection** (Issue [#1182](https://github.com/NousResearch/hermes-agent/issues/1182))
+- **`GatewayConfig.get()` AttributeError** crashing all message handling (Issue [#1158](https://github.com/NousResearch/hermes-agent/issues/1158), [#1287](https://github.com/NousResearch/hermes-agent/pull/1287))
+- **`/update` hard-failing with "command not found"** (Issue [#1049](https://github.com/NousResearch/hermes-agent/issues/1049))
+- **Image analysis failing silently** (Issue [#1034](https://github.com/NousResearch/hermes-agent/issues/1034), [#1338](https://github.com/NousResearch/hermes-agent/pull/1338))
+- **API `BadRequestError` from `'dict'` object has no attribute `'strip'`** (Issue [#1071](https://github.com/NousResearch/hermes-agent/issues/1071))
+- **Slash commands requiring exact full name** — now uses prefix matching (Issue [#928](https://github.com/NousResearch/hermes-agent/issues/928), [#1320](https://github.com/NousResearch/hermes-agent/pull/1320))
+- **Gateway stops responding when terminal is closed on headless** (Issue [#1005](https://github.com/NousResearch/hermes-agent/issues/1005))
+
+---
+
+## 🧪 Testing
+
+- Cover empty cached Anthropic tool-call turns ([#1222](https://github.com/NousResearch/hermes-agent/pull/1222))
+- Fix stale CI assumptions in parser and quick-command coverage ([#1236](https://github.com/NousResearch/hermes-agent/pull/1236))
+- Fix gateway async tests without implicit event loop ([#1278](https://github.com/NousResearch/hermes-agent/pull/1278))
+- Make gateway async tests xdist-safe ([#1281](https://github.com/NousResearch/hermes-agent/pull/1281))
+- Cross-timezone naive timestamp regression for cron ([#1319](https://github.com/NousResearch/hermes-agent/pull/1319))
+- Isolate codex provider tests from local env ([#1335](https://github.com/NousResearch/hermes-agent/pull/1335))
+- Lock retry replacement semantics ([#1379](https://github.com/NousResearch/hermes-agent/pull/1379))
+- Improve error logging in session search tool — by @aydnOktay ([#1533](https://github.com/NousResearch/hermes-agent/pull/1533))
+
+---
+
+## 📚 Documentation
+
+- Comprehensive SOUL.md guide ([#1315](https://github.com/NousResearch/hermes-agent/pull/1315))
+- Voice mode documentation ([#1316](https://github.com/NousResearch/hermes-agent/pull/1316), [#1362](https://github.com/NousResearch/hermes-agent/pull/1362))
+- Provider contribution guide ([#1361](https://github.com/NousResearch/hermes-agent/pull/1361))
+- ACP and internal systems implementation guides ([#1259](https://github.com/NousResearch/hermes-agent/pull/1259))
+- Expand Docusaurus coverage across CLI, tools, skills, and skins ([#1232](https://github.com/NousResearch/hermes-agent/pull/1232))
+- Terminal backend and Windows troubleshooting ([#1297](https://github.com/NousResearch/hermes-agent/pull/1297))
+- Skills hub reference section ([#1317](https://github.com/NousResearch/hermes-agent/pull/1317))
+- Checkpoint, /rollback, and git worktrees guide ([#1493](https://github.com/NousResearch/hermes-agent/pull/1493), [#1524](https://github.com/NousResearch/hermes-agent/pull/1524))
+- CLI status bar and /usage reference ([#1523](https://github.com/NousResearch/hermes-agent/pull/1523))
+- Fallback providers + /background command docs ([#1430](https://github.com/NousResearch/hermes-agent/pull/1430))
+- Gateway service scopes docs ([#1378](https://github.com/NousResearch/hermes-agent/pull/1378))
+- Slack thread reply behavior docs ([#1407](https://github.com/NousResearch/hermes-agent/pull/1407))
+- Redesigned landing page with Nous blue palette — by @austinpickett ([#974](https://github.com/NousResearch/hermes-agent/pull/974))
+- Fix several documentation typos — by @JackTheGit ([#953](https://github.com/NousResearch/hermes-agent/pull/953))
+- Stabilize website diagrams ([#1405](https://github.com/NousResearch/hermes-agent/pull/1405))
+- CLI vs messaging quick reference in README ([#1491](https://github.com/NousResearch/hermes-agent/pull/1491))
+- Add search to Docusaurus ([#1053](https://github.com/NousResearch/hermes-agent/pull/1053))
+- Home Assistant integration docs ([#1170](https://github.com/NousResearch/hermes-agent/pull/1170))
+
+---
+
+## 👥 Contributors
+
+### Core
+- **@teknium1** — 220+ PRs spanning every area of the codebase
+
+### Top Community Contributors
+
+- **@0xbyt4** (4 PRs) — Anthropic adapter fixes (max_tokens, fallback crash, 429/529 retry), Slack file upload thread context, setup NameError fix
+- **@erosika** (1 PR) — Honcho memory integration: async writes, memory modes, session title integration
+- **@SHL0MS** (2 PRs) — ASCII video skill design patterns and refactoring
+- **@alt-glitch** (2 PRs) — Persistent shell mode for local/SSH backends, setuptools packaging fix
+- **@arceus77-7** (2 PRs) — 1Password skill, fix skills list mislabeling
+- **@kshitijk4poor** (1 PR) — OpenClaw migration during setup wizard
+- **@ASRagab** (1 PR) — Fix adaptive thinking for Claude 4.6 models
+- **@eren-karakus0** (1 PR) — Strip Hermes provider env vars from subprocess environment
+- **@mr-emmett-one** (1 PR) — Fix DeepSeek V3 parser multi-tool call support
+- **@jplew** (1 PR) — Gateway restart on retryable startup failures
+- **@brandtcormorant** (1 PR) — Fix Anthropic cache control for empty text blocks
+- **@aydnOktay** (1 PR) — Improve error logging in session search tool
+- **@austinpickett** (1 PR) — Landing page redesign with Nous blue palette
+- **@JackTheGit** (1 PR) — Documentation typo fixes
+
+### All Contributors
+
+@0xbyt4, @alt-glitch, @arceus77-7, @ASRagab, @austinpickett, @aydnOktay, @brandtcormorant, @eren-karakus0, @erosika, @JackTheGit, @jplew, @kshitijk4poor, @mr-emmett-one, @SHL0MS, @teknium1
+
+---
+
+**Full Changelog**: [v2026.3.12...v2026.3.17](https://github.com/NousResearch/hermes-agent/compare/v2026.3.12...v2026.3.17)

RELEASE_v0.4.0.md

@@ -0,0 +1,400 @@
+# Hermes Agent v0.4.0 (v2026.3.23)
+
+**Release Date:** March 23, 2026
+
+> The platform expansion release — OpenAI-compatible API server, 6 new messaging adapters, 4 new inference providers, MCP server management with OAuth 2.1, @ context references, gateway prompt caching, streaming enabled by default, and a sweeping reliability pass with 200+ bug fixes.
+
+---
+
+## ✨ Highlights
+
+- **OpenAI-compatible API server** — Expose Hermes as an `/v1/chat/completions` endpoint with a new `/api/jobs` REST API for cron job management, hardened with input limits, field whitelists, SQLite-backed response persistence, and CORS origin protection ([#1756](https://github.com/NousResearch/hermes-agent/pull/1756), [#2450](https://github.com/NousResearch/hermes-agent/pull/2450), [#2456](https://github.com/NousResearch/hermes-agent/pull/2456), [#2451](https://github.com/NousResearch/hermes-agent/pull/2451), [#2472](https://github.com/NousResearch/hermes-agent/pull/2472))
+
+- **6 new messaging platform adapters** — Signal, DingTalk, SMS (Twilio), Mattermost, Matrix, and Webhook adapters join Telegram, Discord, and WhatsApp. Gateway auto-reconnects failed platforms with exponential backoff ([#2206](https://github.com/NousResearch/hermes-agent/pull/2206), [#1685](https://github.com/NousResearch/hermes-agent/pull/1685), [#1688](https://github.com/NousResearch/hermes-agent/pull/1688), [#1683](https://github.com/NousResearch/hermes-agent/pull/1683), [#2166](https://github.com/NousResearch/hermes-agent/pull/2166), [#2584](https://github.com/NousResearch/hermes-agent/pull/2584))
+
+- **@ context references** — Claude Code-style `@file` and `@url` context injection with tab completions in the CLI ([#2343](https://github.com/NousResearch/hermes-agent/pull/2343), [#2482](https://github.com/NousResearch/hermes-agent/pull/2482))
+
+- **4 new inference providers** — GitHub Copilot (OAuth + token validation), Alibaba Cloud / DashScope, Kilo Code, and OpenCode Zen/Go ([#1924](https://github.com/NousResearch/hermes-agent/pull/1924), [#1879](https://github.com/NousResearch/hermes-agent/pull/1879) by @mchzimm, [#1673](https://github.com/NousResearch/hermes-agent/pull/1673), [#1666](https://github.com/NousResearch/hermes-agent/pull/1666), [#1650](https://github.com/NousResearch/hermes-agent/pull/1650))
+
+- **MCP server management CLI** — `hermes mcp` commands for installing, configuring, and authenticating MCP servers with full OAuth 2.1 PKCE flow ([#2465](https://github.com/NousResearch/hermes-agent/pull/2465))
+
+- **Gateway prompt caching** — Cache AIAgent instances per session, preserving Anthropic prompt cache across turns for dramatic cost reduction on long conversations ([#2282](https://github.com/NousResearch/hermes-agent/pull/2282), [#2284](https://github.com/NousResearch/hermes-agent/pull/2284), [#2361](https://github.com/NousResearch/hermes-agent/pull/2361))
+
+- **Context compression overhaul** — Structured summaries with iterative updates, token-budget tail protection, configurable summary endpoint, and fallback model support ([#2323](https://github.com/NousResearch/hermes-agent/pull/2323), [#1727](https://github.com/NousResearch/hermes-agent/pull/1727), [#2224](https://github.com/NousResearch/hermes-agent/pull/2224))
+
+- **Streaming enabled by default** — CLI streaming on by default with proper spinner/tool progress display during streaming mode, plus extensive linebreak and concatenation fixes ([#2340](https://github.com/NousResearch/hermes-agent/pull/2340), [#2161](https://github.com/NousResearch/hermes-agent/pull/2161), [#2258](https://github.com/NousResearch/hermes-agent/pull/2258))
+
+---
+
+## 🖥️ CLI & User Experience
+
+### New Commands & Interactions
+- **@ context completions** — Tab-completable `@file`/`@url` references that inject file content or web pages into the conversation ([#2482](https://github.com/NousResearch/hermes-agent/pull/2482), [#2343](https://github.com/NousResearch/hermes-agent/pull/2343))
+- **`/statusbar`** — Toggle a persistent config bar showing model + provider info in the prompt ([#2240](https://github.com/NousResearch/hermes-agent/pull/2240), [#1917](https://github.com/NousResearch/hermes-agent/pull/1917))
+- **`/queue`** — Queue prompts for the agent without interrupting the current run ([#2191](https://github.com/NousResearch/hermes-agent/pull/2191), [#2469](https://github.com/NousResearch/hermes-agent/pull/2469))
+- **`/permission`** — Switch approval mode dynamically during a session ([#2207](https://github.com/NousResearch/hermes-agent/pull/2207))
+- **`/browser`** — Interactive browser sessions from the CLI ([#2273](https://github.com/NousResearch/hermes-agent/pull/2273), [#1814](https://github.com/NousResearch/hermes-agent/pull/1814))
+- **`/cost`** — Live pricing and usage tracking in gateway mode ([#2180](https://github.com/NousResearch/hermes-agent/pull/2180))
+- **`/approve` and `/deny`** — Replaced bare text approval in gateway with explicit commands ([#2002](https://github.com/NousResearch/hermes-agent/pull/2002))
+
+### Streaming & Display
+- Streaming enabled by default in CLI ([#2340](https://github.com/NousResearch/hermes-agent/pull/2340))
+- Show spinners and tool progress during streaming mode ([#2161](https://github.com/NousResearch/hermes-agent/pull/2161))
+- Show reasoning/thinking blocks when `show_reasoning` enabled ([#2118](https://github.com/NousResearch/hermes-agent/pull/2118))
+- Context pressure warnings for CLI and gateway ([#2159](https://github.com/NousResearch/hermes-agent/pull/2159))
+- Fix: streaming chunks concatenated without whitespace ([#2258](https://github.com/NousResearch/hermes-agent/pull/2258))
+- Fix: iteration boundary linebreak prevents stream concatenation ([#2413](https://github.com/NousResearch/hermes-agent/pull/2413))
+- Fix: defer streaming linebreak to prevent blank line stacking ([#2473](https://github.com/NousResearch/hermes-agent/pull/2473))
+- Fix: suppress spinner animation in non-TTY environments ([#2216](https://github.com/NousResearch/hermes-agent/pull/2216))
+- Fix: display provider and endpoint in API error messages ([#2266](https://github.com/NousResearch/hermes-agent/pull/2266))
+- Fix: resolve garbled ANSI escape codes in status printouts ([#2448](https://github.com/NousResearch/hermes-agent/pull/2448))
+- Fix: update gold ANSI color to true-color format ([#2246](https://github.com/NousResearch/hermes-agent/pull/2246))
+- Fix: normalize toolset labels and use skin colors in banner ([#1912](https://github.com/NousResearch/hermes-agent/pull/1912))
+
+### CLI Polish
+- Fix: prevent 'Press ENTER to continue...' on exit ([#2555](https://github.com/NousResearch/hermes-agent/pull/2555))
+- Fix: flush stdout during agent loop to prevent macOS display freeze ([#1654](https://github.com/NousResearch/hermes-agent/pull/1654))
+- Fix: show human-readable error when `hermes setup` hits permissions error ([#2196](https://github.com/NousResearch/hermes-agent/pull/2196))
+- Fix: `/stop` command crash + UnboundLocalError in streaming media delivery ([#2463](https://github.com/NousResearch/hermes-agent/pull/2463))
+- Fix: allow custom/local endpoints without API key ([#2556](https://github.com/NousResearch/hermes-agent/pull/2556))
+- Fix: Kitty keyboard protocol Shift+Enter for Ghostty/WezTerm (attempted + reverted due to prompt_toolkit crash) ([#2345](https://github.com/NousResearch/hermes-agent/pull/2345), [#2349](https://github.com/NousResearch/hermes-agent/pull/2349))
+
+### Configuration
+- **`${ENV_VAR}` substitution** in config.yaml ([#2684](https://github.com/NousResearch/hermes-agent/pull/2684))
+- **Real-time config reload** — config.yaml changes apply without restart ([#2210](https://github.com/NousResearch/hermes-agent/pull/2210))
+- **`custom_models.yaml`** for user-managed model additions ([#2214](https://github.com/NousResearch/hermes-agent/pull/2214))
+- **Priority-based context file selection** + CLAUDE.md support ([#2301](https://github.com/NousResearch/hermes-agent/pull/2301))
+- **Merge nested YAML sections** instead of replacing on config update ([#2213](https://github.com/NousResearch/hermes-agent/pull/2213))
+- Fix: config.yaml provider key overrides env var silently ([#2272](https://github.com/NousResearch/hermes-agent/pull/2272))
+- Fix: log warning instead of silently swallowing config.yaml errors ([#2683](https://github.com/NousResearch/hermes-agent/pull/2683))
+- Fix: disabled toolsets re-enable themselves after `hermes tools` ([#2268](https://github.com/NousResearch/hermes-agent/pull/2268))
+- Fix: platform default toolsets silently override tool deselection ([#2624](https://github.com/NousResearch/hermes-agent/pull/2624))
+- Fix: honor bare YAML `approvals.mode: off` ([#2620](https://github.com/NousResearch/hermes-agent/pull/2620))
+- Fix: `hermes update` use `.[all]` extras with fallback ([#1728](https://github.com/NousResearch/hermes-agent/pull/1728))
+- Fix: `hermes update` prompt before resetting working tree on stash conflicts ([#2390](https://github.com/NousResearch/hermes-agent/pull/2390))
+- Fix: use git pull --rebase in update/install to avoid divergent branch error ([#2274](https://github.com/NousResearch/hermes-agent/pull/2274))
+- Fix: add zprofile fallback and create zshrc on fresh macOS installs ([#2320](https://github.com/NousResearch/hermes-agent/pull/2320))
+- Fix: remove `ANTHROPIC_BASE_URL` env var to avoid collisions ([#1675](https://github.com/NousResearch/hermes-agent/pull/1675))
+- Fix: don't ask IMAP password if already in keyring or env ([#2212](https://github.com/NousResearch/hermes-agent/pull/2212))
+- Fix: OpenCode Zen/Go show OpenRouter models instead of their own ([#2277](https://github.com/NousResearch/hermes-agent/pull/2277))
+
+---
+
+## 🏗️ Core Agent & Architecture
+
+### New Providers
+- **GitHub Copilot** — Full OAuth auth, API routing, token validation, and 400k context. ([#1924](https://github.com/NousResearch/hermes-agent/pull/1924), [#1896](https://github.com/NousResearch/hermes-agent/pull/1896), [#1879](https://github.com/NousResearch/hermes-agent/pull/1879) by @mchzimm, [#2507](https://github.com/NousResearch/hermes-agent/pull/2507))
+- **Alibaba Cloud / DashScope** — Full integration with DashScope v1 runtime, model dot preservation, and 401 auth fixes ([#1673](https://github.com/NousResearch/hermes-agent/pull/1673), [#2332](https://github.com/NousResearch/hermes-agent/pull/2332), [#2459](https://github.com/NousResearch/hermes-agent/pull/2459))
+- **Kilo Code** — First-class inference provider ([#1666](https://github.com/NousResearch/hermes-agent/pull/1666))
+- **OpenCode Zen and OpenCode Go** — New provider backends ([#1650](https://github.com/NousResearch/hermes-agent/pull/1650), [#2393](https://github.com/NousResearch/hermes-agent/pull/2393) by @0xbyt4)
+- **NeuTTS** — Local TTS provider backend with built-in setup flow, replacing the old optional skill ([#1657](https://github.com/NousResearch/hermes-agent/pull/1657), [#1664](https://github.com/NousResearch/hermes-agent/pull/1664))
+
+### Provider Improvements
+- **Eager fallback** to backup model on rate-limit errors ([#1730](https://github.com/NousResearch/hermes-agent/pull/1730))
+- **Endpoint metadata** for custom model context and pricing; query local servers for actual context window size ([#1906](https://github.com/NousResearch/hermes-agent/pull/1906), [#2091](https://github.com/NousResearch/hermes-agent/pull/2091) by @dusterbloom)
+- **Context length detection overhaul** — models.dev integration, provider-aware resolution, fuzzy matching for custom endpoints, `/v1/props` for llama.cpp ([#2158](https://github.com/NousResearch/hermes-agent/pull/2158), [#2051](https://github.com/NousResearch/hermes-agent/pull/2051), [#2403](https://github.com/NousResearch/hermes-agent/pull/2403))
+- **Model catalog updates** — gpt-5.4-mini, gpt-5.4-nano, healer-alpha, haiku-4.5, minimax-m2.7, claude 4.6 at 1M context ([#1913](https://github.com/NousResearch/hermes-agent/pull/1913), [#1915](https://github.com/NousResearch/hermes-agent/pull/1915), [#1900](https://github.com/NousResearch/hermes-agent/pull/1900), [#2155](https://github.com/NousResearch/hermes-agent/pull/2155), [#2474](https://github.com/NousResearch/hermes-agent/pull/2474))
+- **Custom endpoint improvements** — `model.base_url` in config.yaml, `api_mode` override for responses API, allow endpoints without API key, fail fast on missing keys ([#2330](https://github.com/NousResearch/hermes-agent/pull/2330), [#1651](https://github.com/NousResearch/hermes-agent/pull/1651), [#2556](https://github.com/NousResearch/hermes-agent/pull/2556), [#2445](https://github.com/NousResearch/hermes-agent/pull/2445), [#1994](https://github.com/NousResearch/hermes-agent/pull/1994), [#1998](https://github.com/NousResearch/hermes-agent/pull/1998))
+- Inject model and provider into system prompt ([#1929](https://github.com/NousResearch/hermes-agent/pull/1929))
+- Tie `api_mode` to provider config instead of env var ([#1656](https://github.com/NousResearch/hermes-agent/pull/1656))
+- Fix: prevent Anthropic token leaking to third-party `anthropic_messages` providers ([#2389](https://github.com/NousResearch/hermes-agent/pull/2389))
+- Fix: prevent Anthropic fallback from inheriting non-Anthropic `base_url` ([#2388](https://github.com/NousResearch/hermes-agent/pull/2388))
+- Fix: `auxiliary_is_nous` flag never resets — leaked Nous tags to other providers ([#1713](https://github.com/NousResearch/hermes-agent/pull/1713))
+- Fix: Anthropic `tool_choice 'none'` still allowed tool calls ([#1714](https://github.com/NousResearch/hermes-agent/pull/1714))
+- Fix: Mistral parser nested JSON fallback extraction ([#2335](https://github.com/NousResearch/hermes-agent/pull/2335))
+- Fix: MiniMax 401 auth resolved by defaulting to `anthropic_messages` ([#2103](https://github.com/NousResearch/hermes-agent/pull/2103))
+- Fix: case-insensitive model family matching ([#2350](https://github.com/NousResearch/hermes-agent/pull/2350))
+- Fix: ignore placeholder provider keys in activation checks ([#2358](https://github.com/NousResearch/hermes-agent/pull/2358))
+- Fix: Preserve Ollama model:tag colons in context length detection ([#2149](https://github.com/NousResearch/hermes-agent/pull/2149))
+- Fix: recognize Claude Code OAuth credentials in startup gate ([#1663](https://github.com/NousResearch/hermes-agent/pull/1663))
+- Fix: detect Claude Code version dynamically for OAuth user-agent ([#1670](https://github.com/NousResearch/hermes-agent/pull/1670))
+- Fix: OAuth flag stale after refresh/fallback ([#1890](https://github.com/NousResearch/hermes-agent/pull/1890))
+- Fix: auxiliary client skips expired Codex JWT ([#2397](https://github.com/NousResearch/hermes-agent/pull/2397))
+
+### Agent Loop
+- **Gateway prompt caching** — Cache AIAgent per session, keep assistant turns, fix session restore ([#2282](https://github.com/NousResearch/hermes-agent/pull/2282), [#2284](https://github.com/NousResearch/hermes-agent/pull/2284), [#2361](https://github.com/NousResearch/hermes-agent/pull/2361))
+- **Context compression overhaul** — Structured summaries, iterative updates, token-budget tail protection, configurable `summary_base_url` ([#2323](https://github.com/NousResearch/hermes-agent/pull/2323), [#1727](https://github.com/NousResearch/hermes-agent/pull/1727), [#2224](https://github.com/NousResearch/hermes-agent/pull/2224))
+- **Pre-call sanitization and post-call tool guardrails** ([#1732](https://github.com/NousResearch/hermes-agent/pull/1732))
+- **Auto-recover** from provider-rejected `tool_choice` by retrying without ([#2174](https://github.com/NousResearch/hermes-agent/pull/2174))
+- **Background memory/skill review** replaces inline nudges ([#2235](https://github.com/NousResearch/hermes-agent/pull/2235))
+- **SOUL.md as primary agent identity** instead of hardcoded default ([#1922](https://github.com/NousResearch/hermes-agent/pull/1922))
+- Fix: prevent silent tool result loss during context compression ([#1993](https://github.com/NousResearch/hermes-agent/pull/1993))
+- Fix: handle empty/null function arguments in tool call recovery ([#2163](https://github.com/NousResearch/hermes-agent/pull/2163))
+- Fix: handle API refusal responses gracefully instead of crashing ([#2156](https://github.com/NousResearch/hermes-agent/pull/2156))
+- Fix: prevent stuck agent loop on malformed tool calls ([#2114](https://github.com/NousResearch/hermes-agent/pull/2114))
+- Fix: return JSON parse error to model instead of dispatching with empty args ([#2342](https://github.com/NousResearch/hermes-agent/pull/2342))
+- Fix: consecutive assistant message merge drops content on mixed types ([#1703](https://github.com/NousResearch/hermes-agent/pull/1703))
+- Fix: message role alternation violations in JSON recovery and error handler ([#1722](https://github.com/NousResearch/hermes-agent/pull/1722))
+- Fix: `compression_attempts` resets each iteration — allowed unlimited compressions ([#1723](https://github.com/NousResearch/hermes-agent/pull/1723))
+- Fix: `length_continue_retries` never resets — later truncations got fewer retries ([#1717](https://github.com/NousResearch/hermes-agent/pull/1717))
+- Fix: compressor summary role violated consecutive-role constraint ([#1720](https://github.com/NousResearch/hermes-agent/pull/1720), [#1743](https://github.com/NousResearch/hermes-agent/pull/1743))
+- Fix: remove hardcoded `gemini-3-flash-preview` as default summary model ([#2464](https://github.com/NousResearch/hermes-agent/pull/2464))
+- Fix: correctly handle empty tool results ([#2201](https://github.com/NousResearch/hermes-agent/pull/2201))
+- Fix: crash on None entry in `tool_calls` list ([#2209](https://github.com/NousResearch/hermes-agent/pull/2209) by @0xbyt4, [#2316](https://github.com/NousResearch/hermes-agent/pull/2316))
+- Fix: per-thread persistent event loops in worker threads ([#2214](https://github.com/NousResearch/hermes-agent/pull/2214) by @jquesnelle)
+- Fix: prevent 'event loop already running' when async tools run in parallel ([#2207](https://github.com/NousResearch/hermes-agent/pull/2207))
+- Fix: strip ANSI at the source — clean terminal output before it reaches the model ([#2115](https://github.com/NousResearch/hermes-agent/pull/2115))
+- Fix: skip top-level `cache_control` on role:tool for OpenRouter ([#2391](https://github.com/NousResearch/hermes-agent/pull/2391))
+- Fix: delegate tool — save parent tool names before child construction mutates global ([#2083](https://github.com/NousResearch/hermes-agent/pull/2083) by @ygd58, [#1894](https://github.com/NousResearch/hermes-agent/pull/1894))
+- Fix: only strip last assistant message if empty string ([#2326](https://github.com/NousResearch/hermes-agent/pull/2326))
+
+### Session & Memory
+- **Session search** and management slash commands ([#2198](https://github.com/NousResearch/hermes-agent/pull/2198))
+- **Auto session titles** and `.hermes.md` project config ([#1712](https://github.com/NousResearch/hermes-agent/pull/1712))
+- Fix: concurrent memory writes silently drop entries — added file locking ([#1726](https://github.com/NousResearch/hermes-agent/pull/1726))
+- Fix: search all sources by default in `session_search` ([#1892](https://github.com/NousResearch/hermes-agent/pull/1892))
+- Fix: handle hyphenated FTS5 queries and preserve quoted literals ([#1776](https://github.com/NousResearch/hermes-agent/pull/1776))
+- Fix: skip corrupt lines in `load_transcript` instead of crashing ([#1744](https://github.com/NousResearch/hermes-agent/pull/1744))
+- Fix: normalize session keys to prevent case-sensitive duplicates ([#2157](https://github.com/NousResearch/hermes-agent/pull/2157))
+- Fix: prevent `session_search` crash when no sessions exist ([#2194](https://github.com/NousResearch/hermes-agent/pull/2194))
+- Fix: reset token counters on new session for accurate usage display ([#2101](https://github.com/NousResearch/hermes-agent/pull/2101) by @InB4DevOps)
+- Fix: prevent stale memory overwrites by flush agent ([#2687](https://github.com/NousResearch/hermes-agent/pull/2687))
+- Fix: remove synthetic error message injection, fix session resume after repeated failures ([#2303](https://github.com/NousResearch/hermes-agent/pull/2303))
+- Fix: quiet mode with `--resume` now passes conversation_history ([#2357](https://github.com/NousResearch/hermes-agent/pull/2357))
+- Fix: unify resume logic in batch mode ([#2331](https://github.com/NousResearch/hermes-agent/pull/2331))
+
+### Honcho Memory
+- Honcho config fixes and @ context reference integration ([#2343](https://github.com/NousResearch/hermes-agent/pull/2343))
+- Self-hosted / Docker configuration documentation ([#2475](https://github.com/NousResearch/hermes-agent/pull/2475))
+
+---
+
+## 📱 Messaging Platforms (Gateway)
+
+### New Platform Adapters
+- **Signal Messenger** — Full adapter with attachment handling, group message filtering, and Note to Self echo-back protection ([#2206](https://github.com/NousResearch/hermes-agent/pull/2206), [#2400](https://github.com/NousResearch/hermes-agent/pull/2400), [#2297](https://github.com/NousResearch/hermes-agent/pull/2297), [#2156](https://github.com/NousResearch/hermes-agent/pull/2156))
+- **DingTalk** — Adapter with gateway wiring and setup docs ([#1685](https://github.com/NousResearch/hermes-agent/pull/1685), [#1690](https://github.com/NousResearch/hermes-agent/pull/1690), [#1692](https://github.com/NousResearch/hermes-agent/pull/1692))
+- **SMS (Twilio)** ([#1688](https://github.com/NousResearch/hermes-agent/pull/1688))
+- **Mattermost** — With @-mention-only channel filter ([#1683](https://github.com/NousResearch/hermes-agent/pull/1683), [#2443](https://github.com/NousResearch/hermes-agent/pull/2443))
+- **Matrix** — With vision support and image caching ([#1683](https://github.com/NousResearch/hermes-agent/pull/1683), [#2520](https://github.com/NousResearch/hermes-agent/pull/2520))
+- **Webhook** — Platform adapter for external event triggers ([#2166](https://github.com/NousResearch/hermes-agent/pull/2166))
+- **OpenAI-compatible API server** — `/v1/chat/completions` endpoint with `/api/jobs` cron management ([#1756](https://github.com/NousResearch/hermes-agent/pull/1756), [#2450](https://github.com/NousResearch/hermes-agent/pull/2450), [#2456](https://github.com/NousResearch/hermes-agent/pull/2456))
+
+### Telegram Improvements
+- MarkdownV2 support — strikethrough, spoiler, blockquotes, escape parentheses/braces/backslashes/backticks ([#2199](https://github.com/NousResearch/hermes-agent/pull/2199), [#2200](https://github.com/NousResearch/hermes-agent/pull/2200) by @llbn, [#2386](https://github.com/NousResearch/hermes-agent/pull/2386))
+- Auto-detect HTML tags and use `parse_mode=HTML` ([#1709](https://github.com/NousResearch/hermes-agent/pull/1709))
+- Telegram group vision support + thread-based sessions ([#2153](https://github.com/NousResearch/hermes-agent/pull/2153))
+- Auto-reconnect polling after network interruption ([#2517](https://github.com/NousResearch/hermes-agent/pull/2517))
+- Aggregate split text messages before dispatching ([#1674](https://github.com/NousResearch/hermes-agent/pull/1674))
+- Fix: streaming config bridge, not-modified, flood control ([#1782](https://github.com/NousResearch/hermes-agent/pull/1782), [#1783](https://github.com/NousResearch/hermes-agent/pull/1783))
+- Fix: edited_message event crashes ([#2074](https://github.com/NousResearch/hermes-agent/pull/2074))
+- Fix: retry 409 polling conflicts before giving up ([#2312](https://github.com/NousResearch/hermes-agent/pull/2312))
+- Fix: topic delivery via `platform:chat_id:thread_id` format ([#2455](https://github.com/NousResearch/hermes-agent/pull/2455))
+
+### Discord Improvements
+- Document caching and text-file injection ([#2503](https://github.com/NousResearch/hermes-agent/pull/2503))
+- Persistent typing indicator for DMs ([#2468](https://github.com/NousResearch/hermes-agent/pull/2468))
+- Discord DM vision — inline images + attachment analysis ([#2186](https://github.com/NousResearch/hermes-agent/pull/2186))
+- Persist thread participation across gateway restarts ([#1661](https://github.com/NousResearch/hermes-agent/pull/1661))
+- Fix: gateway crash on non-ASCII guild names ([#2302](https://github.com/NousResearch/hermes-agent/pull/2302))
+- Fix: thread permission errors ([#2073](https://github.com/NousResearch/hermes-agent/pull/2073))
+- Fix: slash event routing in threads ([#2460](https://github.com/NousResearch/hermes-agent/pull/2460))
+- Fix: remove bugged followup messages + `/ask` command ([#1836](https://github.com/NousResearch/hermes-agent/pull/1836))
+- Fix: graceful WebSocket reconnection ([#2127](https://github.com/NousResearch/hermes-agent/pull/2127))
+- Fix: voice channel TTS when streaming enabled ([#2322](https://github.com/NousResearch/hermes-agent/pull/2322))
+
+### WhatsApp & Other Adapters
+- WhatsApp: outbound `send_message` routing ([#1769](https://github.com/NousResearch/hermes-agent/pull/1769) by @sai-samarth), LID format self-chat ([#1667](https://github.com/NousResearch/hermes-agent/pull/1667)), `reply_prefix` config fix ([#1923](https://github.com/NousResearch/hermes-agent/pull/1923)), restart on bridge child exit ([#2334](https://github.com/NousResearch/hermes-agent/pull/2334)), image/bridge improvements ([#2181](https://github.com/NousResearch/hermes-agent/pull/2181))
+- Matrix: correct `reply_to_message_id` parameter ([#1895](https://github.com/NousResearch/hermes-agent/pull/1895)), bare media types fix ([#1736](https://github.com/NousResearch/hermes-agent/pull/1736))
+- Mattermost: MIME types for media attachments ([#2329](https://github.com/NousResearch/hermes-agent/pull/2329))
+
+### Gateway Core
+- **Auto-reconnect** failed platforms with exponential backoff ([#2584](https://github.com/NousResearch/hermes-agent/pull/2584))
+- **Notify users when session auto-resets** ([#2519](https://github.com/NousResearch/hermes-agent/pull/2519))
+- **Reply-to message context** for out-of-session replies ([#1662](https://github.com/NousResearch/hermes-agent/pull/1662))
+- **Ignore unauthorized DMs** config option ([#1919](https://github.com/NousResearch/hermes-agent/pull/1919))
+- Fix: `/reset` in thread-mode resets global session instead of thread ([#2254](https://github.com/NousResearch/hermes-agent/pull/2254))
+- Fix: deliver MEDIA: files after streaming responses ([#2382](https://github.com/NousResearch/hermes-agent/pull/2382))
+- Fix: cap interrupt recursion depth to prevent resource exhaustion ([#1659](https://github.com/NousResearch/hermes-agent/pull/1659))
+- Fix: detect stopped processes and release stale locks on `--replace` ([#2406](https://github.com/NousResearch/hermes-agent/pull/2406), [#1908](https://github.com/NousResearch/hermes-agent/pull/1908))
+- Fix: PID-based wait with force-kill for gateway restart ([#1902](https://github.com/NousResearch/hermes-agent/pull/1902))
+- Fix: prevent `--replace` mode from killing the caller process ([#2185](https://github.com/NousResearch/hermes-agent/pull/2185))
+- Fix: `/model` shows active fallback model instead of config default ([#1660](https://github.com/NousResearch/hermes-agent/pull/1660))
+- Fix: `/title` command fails when session doesn't exist in SQLite yet ([#2379](https://github.com/NousResearch/hermes-agent/pull/2379) by @ten-jampa)
+- Fix: process `/queue`'d messages after agent completion ([#2469](https://github.com/NousResearch/hermes-agent/pull/2469))
+- Fix: strip orphaned `tool_results` + let `/reset` bypass running agent ([#2180](https://github.com/NousResearch/hermes-agent/pull/2180))
+- Fix: prevent agents from starting gateway outside systemd management ([#2617](https://github.com/NousResearch/hermes-agent/pull/2617))
+- Fix: prevent systemd restart storm on gateway connection failure ([#2327](https://github.com/NousResearch/hermes-agent/pull/2327))
+- Fix: include resolved node path in systemd unit ([#1767](https://github.com/NousResearch/hermes-agent/pull/1767) by @sai-samarth)
+- Fix: send error details to user in gateway outer exception handler ([#1966](https://github.com/NousResearch/hermes-agent/pull/1966))
+- Fix: improve error handling for 429 usage limits and 500 context overflow ([#1839](https://github.com/NousResearch/hermes-agent/pull/1839))
+- Fix: add all missing platform allowlist env vars to startup warning check ([#2628](https://github.com/NousResearch/hermes-agent/pull/2628))
+- Fix: media delivery fails for file paths containing spaces ([#2621](https://github.com/NousResearch/hermes-agent/pull/2621))
+- Fix: duplicate session-key collision in multi-platform gateway ([#2171](https://github.com/NousResearch/hermes-agent/pull/2171))
+- Fix: Matrix and Mattermost never report as connected ([#1711](https://github.com/NousResearch/hermes-agent/pull/1711))
+- Fix: PII redaction config never read — missing yaml import ([#1701](https://github.com/NousResearch/hermes-agent/pull/1701))
+- Fix: NameError on skill slash commands ([#1697](https://github.com/NousResearch/hermes-agent/pull/1697))
+- Fix: persist watcher metadata in checkpoint for crash recovery ([#1706](https://github.com/NousResearch/hermes-agent/pull/1706))
+- Fix: pass `message_thread_id` in send_image_file, send_document, send_video ([#2339](https://github.com/NousResearch/hermes-agent/pull/2339))
+- Fix: media-group aggregation on rapid successive photo messages ([#2160](https://github.com/NousResearch/hermes-agent/pull/2160))
+
+---
+
+## 🔧 Tool System
+
+### MCP Enhancements
+- **MCP server management CLI** + OAuth 2.1 PKCE auth ([#2465](https://github.com/NousResearch/hermes-agent/pull/2465))
+- **Expose MCP servers as standalone toolsets** ([#1907](https://github.com/NousResearch/hermes-agent/pull/1907))
+- **Interactive MCP tool configuration** in `hermes tools` ([#1694](https://github.com/NousResearch/hermes-agent/pull/1694))
+- Fix: MCP-OAuth port mismatch, path traversal, and shared handler state ([#2552](https://github.com/NousResearch/hermes-agent/pull/2552))
+- Fix: preserve MCP tool registrations across session resets ([#2124](https://github.com/NousResearch/hermes-agent/pull/2124))
+- Fix: concurrent file access crash + duplicate MCP registration ([#2154](https://github.com/NousResearch/hermes-agent/pull/2154))
+- Fix: normalise MCP schemas + expand session list columns ([#2102](https://github.com/NousResearch/hermes-agent/pull/2102))
+- Fix: `tool_choice` `mcp_` prefix handling ([#1775](https://github.com/NousResearch/hermes-agent/pull/1775))
+
+### Web Tool Backends
+- **Tavily** as web search/extract/crawl backend ([#1731](https://github.com/NousResearch/hermes-agent/pull/1731))
+- **Parallel** as alternative web search/extract backend ([#1696](https://github.com/NousResearch/hermes-agent/pull/1696))
+- **Configurable web backend** — Firecrawl/BeautifulSoup/Playwright selection ([#2256](https://github.com/NousResearch/hermes-agent/pull/2256))
+- Fix: whitespace-only env vars bypass web backend detection ([#2341](https://github.com/NousResearch/hermes-agent/pull/2341))
+
+### New Tools
+- **IMAP email** reading and sending ([#2173](https://github.com/NousResearch/hermes-agent/pull/2173))
+- **STT (speech-to-text)** tool using Whisper API ([#2072](https://github.com/NousResearch/hermes-agent/pull/2072))
+- **Route-aware pricing estimates** ([#1695](https://github.com/NousResearch/hermes-agent/pull/1695))
+
+### Tool Improvements
+- TTS: `base_url` support for OpenAI TTS provider ([#2064](https://github.com/NousResearch/hermes-agent/pull/2064) by @hanai)
+- Vision: configurable timeout, tilde expansion in file paths, DM vision with multi-image and base64 fallback ([#2480](https://github.com/NousResearch/hermes-agent/pull/2480), [#2585](https://github.com/NousResearch/hermes-agent/pull/2585), [#2211](https://github.com/NousResearch/hermes-agent/pull/2211))
+- Browser: race condition fix in session creation ([#1721](https://github.com/NousResearch/hermes-agent/pull/1721)), TypeError on unexpected LLM params ([#1735](https://github.com/NousResearch/hermes-agent/pull/1735))
+- File tools: strip ANSI escape codes from write_file and patch content ([#2532](https://github.com/NousResearch/hermes-agent/pull/2532)), include pagination args in repeated search key ([#1824](https://github.com/NousResearch/hermes-agent/pull/1824) by @cutepawss), improve fuzzy matching accuracy + position calculation refactor ([#2096](https://github.com/NousResearch/hermes-agent/pull/2096), [#1681](https://github.com/NousResearch/hermes-agent/pull/1681))
+- Code execution: resource leak and double socket close fix ([#2381](https://github.com/NousResearch/hermes-agent/pull/2381))
+- Delegate: thread safety for concurrent subagent delegation ([#1672](https://github.com/NousResearch/hermes-agent/pull/1672)), preserve parent agent's tool list after delegation ([#1778](https://github.com/NousResearch/hermes-agent/pull/1778))
+- Fix: make concurrent tool batching path-aware for file mutations ([#1914](https://github.com/NousResearch/hermes-agent/pull/1914))
+- Fix: chunk long messages in `send_message_tool` before platform dispatch ([#1646](https://github.com/NousResearch/hermes-agent/pull/1646))
+- Fix: add missing 'messaging' toolset ([#1718](https://github.com/NousResearch/hermes-agent/pull/1718))
+- Fix: prevent unavailable tool names from leaking into model schemas ([#2072](https://github.com/NousResearch/hermes-agent/pull/2072))
+- Fix: pass visited set by reference to prevent diamond dependency duplication ([#2311](https://github.com/NousResearch/hermes-agent/pull/2311))
+- Fix: Daytona sandbox lookup migrated from `find_one` to `get/list` ([#2063](https://github.com/NousResearch/hermes-agent/pull/2063) by @rovle)
+
+---
+
+## 🧩 Skills Ecosystem
+
+### Skills System Improvements
+- **Agent-created skills** — Caution-level findings allowed, dangerous skills ask instead of block ([#1840](https://github.com/NousResearch/hermes-agent/pull/1840), [#2446](https://github.com/NousResearch/hermes-agent/pull/2446))
+- **`--yes` flag** to bypass confirmation in `/skills install` and uninstall ([#1647](https://github.com/NousResearch/hermes-agent/pull/1647))
+- **Disabled skills respected** across banner, system prompt, and slash commands ([#1897](https://github.com/NousResearch/hermes-agent/pull/1897))
+- Fix: skills custom_tools import crash + sandbox file_tools integration ([#2239](https://github.com/NousResearch/hermes-agent/pull/2239))
+- Fix: agent-created skills with pip requirements crash on install ([#2145](https://github.com/NousResearch/hermes-agent/pull/2145))
+- Fix: race condition in `Skills.__init__` when `hub.yaml` missing ([#2242](https://github.com/NousResearch/hermes-agent/pull/2242))
+- Fix: validate skill metadata before install and block duplicates ([#2241](https://github.com/NousResearch/hermes-agent/pull/2241))
+- Fix: skills hub inspect/resolve — 4 bugs in inspect, redirects, discovery, tap list ([#2447](https://github.com/NousResearch/hermes-agent/pull/2447))
+- Fix: agent-created skills keep working after session reset ([#2121](https://github.com/NousResearch/hermes-agent/pull/2121))
+
+### New Skills
+- **OCR-and-documents** — PDF/DOCX/XLS/PPTX/image OCR with optional GPU ([#2236](https://github.com/NousResearch/hermes-agent/pull/2236), [#2461](https://github.com/NousResearch/hermes-agent/pull/2461))
+- **Huggingface-hub** bundled skill ([#1921](https://github.com/NousResearch/hermes-agent/pull/1921))
+- **Sherlock OSINT** username search ([#1671](https://github.com/NousResearch/hermes-agent/pull/1671))
+- **Meme-generation** — Image generator with Pillow ([#2344](https://github.com/NousResearch/hermes-agent/pull/2344))
+- **Bioinformatics** gateway skill — index to 400+ bio skills ([#2387](https://github.com/NousResearch/hermes-agent/pull/2387))
+- **Inference.sh** skill (terminal-based) ([#1686](https://github.com/NousResearch/hermes-agent/pull/1686))
+- **Base blockchain** optional skill ([#1643](https://github.com/NousResearch/hermes-agent/pull/1643))
+- **3D-model-viewer** optional skill ([#2226](https://github.com/NousResearch/hermes-agent/pull/2226))
+- **FastMCP** optional skill ([#2113](https://github.com/NousResearch/hermes-agent/pull/2113))
+- **Hermes-agent-setup** skill ([#1905](https://github.com/NousResearch/hermes-agent/pull/1905))
+
+---
+
+## 🔌 Plugin System Enhancements
+
+- **TUI extension hooks** — Build custom CLIs on top of Hermes ([#2333](https://github.com/NousResearch/hermes-agent/pull/2333))
+- **`hermes plugins install/remove/list`** commands ([#2337](https://github.com/NousResearch/hermes-agent/pull/2337))
+- **Slash command registration** for plugins ([#2359](https://github.com/NousResearch/hermes-agent/pull/2359))
+- **`session:end` lifecycle event** hook ([#1725](https://github.com/NousResearch/hermes-agent/pull/1725))
+- Fix: require opt-in for project plugin discovery ([#2215](https://github.com/NousResearch/hermes-agent/pull/2215))
+
+---
+
+## 🔒 Security & Reliability
+
+### Security
+- **SSRF protection** for vision_tools and web_tools ([#2679](https://github.com/NousResearch/hermes-agent/pull/2679))
+- **Shell injection prevention** in `_expand_path` via `~user` path suffix ([#2685](https://github.com/NousResearch/hermes-agent/pull/2685))
+- **Block untrusted browser-origin** API server access ([#2451](https://github.com/NousResearch/hermes-agent/pull/2451))
+- **Block sandbox backend creds** from subprocess env ([#1658](https://github.com/NousResearch/hermes-agent/pull/1658))
+- **Block @ references** from reading secrets outside workspace ([#2601](https://github.com/NousResearch/hermes-agent/pull/2601) by @Gutslabs)
+- **Malicious code pattern pre-exec scanner** for terminal_tool ([#2245](https://github.com/NousResearch/hermes-agent/pull/2245))
+- **Harden terminal safety** and sandbox file writes ([#1653](https://github.com/NousResearch/hermes-agent/pull/1653))
+- **PKCE verifier leak** fix + OAuth refresh Content-Type ([#1775](https://github.com/NousResearch/hermes-agent/pull/1775))
+- **Eliminate SQL string formatting** in `execute()` calls ([#2061](https://github.com/NousResearch/hermes-agent/pull/2061) by @dusterbloom)
+- **Harden jobs API** — input limits, field whitelist, startup check ([#2456](https://github.com/NousResearch/hermes-agent/pull/2456))
+
+### Reliability
+- Thread locks on 4 SessionDB methods ([#1704](https://github.com/NousResearch/hermes-agent/pull/1704))
+- File locking for concurrent memory writes ([#1726](https://github.com/NousResearch/hermes-agent/pull/1726))
+- Handle OpenRouter errors gracefully ([#2112](https://github.com/NousResearch/hermes-agent/pull/2112))
+- Guard print() calls against OSError ([#1668](https://github.com/NousResearch/hermes-agent/pull/1668))
+- Safely handle non-string inputs in redacting formatter ([#2392](https://github.com/NousResearch/hermes-agent/pull/2392), [#1700](https://github.com/NousResearch/hermes-agent/pull/1700))
+- ACP: preserve session provider on model switch, persist sessions to disk ([#2380](https://github.com/NousResearch/hermes-agent/pull/2380), [#2071](https://github.com/NousResearch/hermes-agent/pull/2071))
+- API server: persist ResponseStore to SQLite across restarts ([#2472](https://github.com/NousResearch/hermes-agent/pull/2472))
+- Fix: `fetch_nous_models` always TypeError from positional args ([#1699](https://github.com/NousResearch/hermes-agent/pull/1699))
+- Fix: resolve merge conflict markers in cli.py breaking startup ([#2347](https://github.com/NousResearch/hermes-agent/pull/2347))
+- Fix: `minisweagent_path.py` missing from wheel ([#2098](https://github.com/NousResearch/hermes-agent/pull/2098) by @JiwaniZakir)
+
+### Cron System
+- **`[SILENT]` response** — cron agents can suppress delivery ([#1833](https://github.com/NousResearch/hermes-agent/pull/1833))
+- **Scale missed-job grace window** with schedule frequency ([#2449](https://github.com/NousResearch/hermes-agent/pull/2449))
+- **Recover recent one-shot jobs** ([#1918](https://github.com/NousResearch/hermes-agent/pull/1918))
+- Fix: normalize `repeat<=0` to None — jobs deleted after first run when LLM passes -1 ([#2612](https://github.com/NousResearch/hermes-agent/pull/2612) by @Mibayy)
+- Fix: Matrix added to scheduler delivery platform_map ([#2167](https://github.com/NousResearch/hermes-agent/pull/2167) by @buntingszn)
+- Fix: naive ISO timestamps without timezone — jobs fire at wrong time ([#1729](https://github.com/NousResearch/hermes-agent/pull/1729))
+- Fix: `get_due_jobs` reads `jobs.json` twice — race condition ([#1716](https://github.com/NousResearch/hermes-agent/pull/1716))
+- Fix: silent jobs return empty response for delivery skip ([#2442](https://github.com/NousResearch/hermes-agent/pull/2442))
+- Fix: stop injecting cron outputs into gateway session history ([#2313](https://github.com/NousResearch/hermes-agent/pull/2313))
+- Fix: close abandoned coroutine when `asyncio.run()` raises RuntimeError ([#2317](https://github.com/NousResearch/hermes-agent/pull/2317))
+
+---
+
+## 🧪 Testing
+
+- Resolve all consistently failing tests ([#2488](https://github.com/NousResearch/hermes-agent/pull/2488))
+- Replace `FakePath` with `monkeypatch` for Python 3.12 compat ([#2444](https://github.com/NousResearch/hermes-agent/pull/2444))
+- Align Hermes setup and full-suite expectations ([#1710](https://github.com/NousResearch/hermes-agent/pull/1710))
+
+---
+
+## 📚 Documentation
+
+- Comprehensive docs update for recent features ([#1693](https://github.com/NousResearch/hermes-agent/pull/1693), [#2183](https://github.com/NousResearch/hermes-agent/pull/2183))
+- Alibaba Cloud and DingTalk setup guides ([#1687](https://github.com/NousResearch/hermes-agent/pull/1687), [#1692](https://github.com/NousResearch/hermes-agent/pull/1692))
+- Detailed skills documentation ([#2244](https://github.com/NousResearch/hermes-agent/pull/2244))
+- Honcho self-hosted / Docker configuration ([#2475](https://github.com/NousResearch/hermes-agent/pull/2475))
+- Context length detection FAQ and quickstart references ([#2179](https://github.com/NousResearch/hermes-agent/pull/2179))
+- Fix docs inconsistencies across reference and user guides ([#1995](https://github.com/NousResearch/hermes-agent/pull/1995))
+- Fix MCP install commands — use uv, not bare pip ([#1909](https://github.com/NousResearch/hermes-agent/pull/1909))
+- Replace ASCII diagrams with Mermaid/lists ([#2402](https://github.com/NousResearch/hermes-agent/pull/2402))
+- Gemini OAuth provider implementation plan ([#2467](https://github.com/NousResearch/hermes-agent/pull/2467))
+- Discord Server Members Intent marked as required ([#2330](https://github.com/NousResearch/hermes-agent/pull/2330))
+- Fix MDX build error in api-server.md ([#1787](https://github.com/NousResearch/hermes-agent/pull/1787))
+- Align venv path to match installer ([#2114](https://github.com/NousResearch/hermes-agent/pull/2114))
+- New skills added to hub index ([#2281](https://github.com/NousResearch/hermes-agent/pull/2281))
+
+---
+
+## 👥 Contributors
+
+### Core
+- **@teknium1** (Teknium) — 280 PRs
+
+### Community Contributors
+- **@mchzimm** (to_the_max) — GitHub Copilot provider integration ([#1879](https://github.com/NousResearch/hermes-agent/pull/1879))
+- **@jquesnelle** (Jeffrey Quesnelle) — Per-thread persistent event loops fix ([#2214](https://github.com/NousResearch/hermes-agent/pull/2214))
+- **@llbn** (lbn) — Telegram MarkdownV2 strikethrough, spoiler, blockquotes, and escape fixes ([#2199](https://github.com/NousResearch/hermes-agent/pull/2199), [#2200](https://github.com/NousResearch/hermes-agent/pull/2200))
+- **@dusterbloom** — SQL injection prevention + local server context window querying ([#2061](https://github.com/NousResearch/hermes-agent/pull/2061), [#2091](https://github.com/NousResearch/hermes-agent/pull/2091))
+- **@0xbyt4** — Anthropic tool_calls None guard + OpenCode-Go provider config fix ([#2209](https://github.com/NousResearch/hermes-agent/pull/2209), [#2393](https://github.com/NousResearch/hermes-agent/pull/2393))
+- **@sai-samarth** (Saisamarth) — WhatsApp send_message routing + systemd node path ([#1769](https://github.com/NousResearch/hermes-agent/pull/1769), [#1767](https://github.com/NousResearch/hermes-agent/pull/1767))
+- **@Gutslabs** (Guts) — Block @ references from reading secrets ([#2601](https://github.com/NousResearch/hermes-agent/pull/2601))
+- **@Mibayy** (Mibay) — Cron job repeat normalization ([#2612](https://github.com/NousResearch/hermes-agent/pull/2612))
+- **@ten-jampa** (Tenzin Jampa) — Gateway /title command fix ([#2379](https://github.com/NousResearch/hermes-agent/pull/2379))
+- **@cutepawss** (lila) — File tools search pagination fix ([#1824](https://github.com/NousResearch/hermes-agent/pull/1824))
+- **@hanai** (Hanai) — OpenAI TTS base_url support ([#2064](https://github.com/NousResearch/hermes-agent/pull/2064))
+- **@rovle** (Lovre Pešut) — Daytona sandbox API migration ([#2063](https://github.com/NousResearch/hermes-agent/pull/2063))
+- **@buntingszn** (bunting szn) — Matrix cron delivery support ([#2167](https://github.com/NousResearch/hermes-agent/pull/2167))
+- **@InB4DevOps** — Token counter reset on new session ([#2101](https://github.com/NousResearch/hermes-agent/pull/2101))
+- **@JiwaniZakir** (Zakir Jiwani) — Missing file in wheel fix ([#2098](https://github.com/NousResearch/hermes-agent/pull/2098))
+- **@ygd58** (buray) — Delegate tool parent tool names fix ([#2083](https://github.com/NousResearch/hermes-agent/pull/2083))
+
+---
+
+**Full Changelog**: [v2026.3.17...v2026.3.23](https://github.com/NousResearch/hermes-agent/compare/v2026.3.17...v2026.3.23)

RELEASE_v0.5.0.md

@@ -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)

RELEASE_v0.6.0.md

@@ -0,0 +1,249 @@
+# Hermes Agent v0.6.0 (v2026.3.30)
+
+**Release Date:** March 30, 2026
+
+> The multi-instance release — Profiles for running isolated agent instances, MCP server mode, Docker container, fallback provider chains, two new messaging platforms (Feishu/Lark and WeCom), Telegram webhook mode, Slack multi-workspace OAuth, 95 PRs and 16 resolved issues in 2 days.
+
+---
+
+## ✨ Highlights
+
+- **Profiles — Multi-Instance Hermes** — Run multiple isolated Hermes instances from the same installation. Each profile gets its own config, memory, sessions, skills, and gateway service. Create with `hermes profile create`, switch with `hermes -p <name>`, export/import for sharing. Full token-lock isolation prevents two profiles from using the same bot credential. ([#3681](https://github.com/NousResearch/hermes-agent/pull/3681))
+
+- **MCP Server Mode** — Expose Hermes conversations and sessions to any MCP-compatible client (Claude Desktop, Cursor, VS Code, etc.) via `hermes mcp serve`. Browse conversations, read messages, search across sessions, and manage attachments — all through the Model Context Protocol. Supports both stdio and Streamable HTTP transports. ([#3795](https://github.com/NousResearch/hermes-agent/pull/3795))
+
+- **Docker Container** — Official Dockerfile for running Hermes Agent in a container. Supports both CLI and gateway modes with volume-mounted config. ([#3668](https://github.com/NousResearch/hermes-agent/pull/3668), closes [#850](https://github.com/NousResearch/hermes-agent/issues/850))
+
+- **Ordered Fallback Provider Chain** — Configure multiple inference providers with automatic failover. When your primary provider returns errors or is unreachable, Hermes automatically tries the next provider in the chain. Configure via `fallback_providers` in config.yaml. ([#3813](https://github.com/NousResearch/hermes-agent/pull/3813), closes [#1734](https://github.com/NousResearch/hermes-agent/issues/1734))
+
+- **Feishu/Lark Platform Support** — Full gateway adapter for Feishu (飞书) and Lark with event subscriptions, message cards, group chat, image/file attachments, and interactive card callbacks. ([#3799](https://github.com/NousResearch/hermes-agent/pull/3799), [#3817](https://github.com/NousResearch/hermes-agent/pull/3817), closes [#1788](https://github.com/NousResearch/hermes-agent/issues/1788))
+
+- **WeCom (Enterprise WeChat) Platform Support** — New gateway adapter for WeCom (企业微信) with text/image/voice messages, group chats, and callback verification. ([#3847](https://github.com/NousResearch/hermes-agent/pull/3847))
+
+- **Slack Multi-Workspace OAuth** — Connect a single Hermes gateway to multiple Slack workspaces via OAuth token file. Each workspace gets its own bot token, resolved dynamically per incoming event. ([#3903](https://github.com/NousResearch/hermes-agent/pull/3903))
+
+- **Telegram Webhook Mode & Group Controls** — Run the Telegram adapter in webhook mode as an alternative to polling — faster response times and better for production deployments behind a reverse proxy. New group mention gating controls when the bot responds: always, only when @mentioned, or via regex triggers. ([#3880](https://github.com/NousResearch/hermes-agent/pull/3880), [#3870](https://github.com/NousResearch/hermes-agent/pull/3870))
+
+- **Exa Search Backend** — Add Exa as an alternative web search and content extraction backend alongside Firecrawl and DuckDuckGo. Set `EXA_API_KEY` and configure as preferred backend. ([#3648](https://github.com/NousResearch/hermes-agent/pull/3648))
+
+- **Skills & Credentials on Remote Backends** — Mount skill directories and credential files into Modal and Docker containers, so remote terminal sessions have access to the same skills and secrets as local execution. ([#3890](https://github.com/NousResearch/hermes-agent/pull/3890), [#3671](https://github.com/NousResearch/hermes-agent/pull/3671), closes [#3665](https://github.com/NousResearch/hermes-agent/issues/3665), [#3433](https://github.com/NousResearch/hermes-agent/issues/3433))
+
+---
+
+## 🏗️ Core Agent & Architecture
+
+### Provider & Model Support
+- **Ordered fallback provider chain** — automatic failover across multiple configured providers ([#3813](https://github.com/NousResearch/hermes-agent/pull/3813))
+- **Fix api_mode on provider switch** — switching providers via `hermes model` now correctly clears stale `api_mode` instead of hardcoding `chat_completions`, fixing 404s for providers with Anthropic-compatible endpoints ([#3726](https://github.com/NousResearch/hermes-agent/pull/3726), [#3857](https://github.com/NousResearch/hermes-agent/pull/3857), closes [#3685](https://github.com/NousResearch/hermes-agent/issues/3685))
+- **Stop silent OpenRouter fallback** — when no provider is configured, Hermes now raises a clear error instead of silently routing to OpenRouter ([#3807](https://github.com/NousResearch/hermes-agent/pull/3807), [#3862](https://github.com/NousResearch/hermes-agent/pull/3862))
+- **Gemini 3.1 preview models** — added to OpenRouter and Nous Portal catalogs ([#3803](https://github.com/NousResearch/hermes-agent/pull/3803), closes [#3753](https://github.com/NousResearch/hermes-agent/issues/3753))
+- **Gemini direct API context length** — full context length resolution for direct Google AI endpoints ([#3876](https://github.com/NousResearch/hermes-agent/pull/3876))
+- **gpt-5.4-mini** added to Codex fallback catalog ([#3855](https://github.com/NousResearch/hermes-agent/pull/3855))
+- **Curated model lists preferred** over live API probe when the probe returns fewer models ([#3856](https://github.com/NousResearch/hermes-agent/pull/3856), [#3867](https://github.com/NousResearch/hermes-agent/pull/3867))
+- **User-friendly 429 rate limit messages** with Retry-After countdown ([#3809](https://github.com/NousResearch/hermes-agent/pull/3809))
+- **Auxiliary client placeholder key** for local servers without auth requirements ([#3842](https://github.com/NousResearch/hermes-agent/pull/3842))
+- **INFO-level logging** for auxiliary provider resolution ([#3866](https://github.com/NousResearch/hermes-agent/pull/3866))
+
+### Agent Loop & Conversation
+- **Subagent status reporting** — reports `completed` status when summary exists instead of generic failure ([#3829](https://github.com/NousResearch/hermes-agent/pull/3829))
+- **Session log file updated during compression** — prevents stale file references after context compression ([#3835](https://github.com/NousResearch/hermes-agent/pull/3835))
+- **Omit empty tools param** — sends no `tools` parameter when empty instead of `None`, fixing compatibility with strict providers ([#3820](https://github.com/NousResearch/hermes-agent/pull/3820))
+
+### Profiles & Multi-Instance
+- **Profiles system** — `hermes profile create/list/switch/delete/export/import/rename`. Each profile gets isolated HERMES_HOME, gateway service, CLI wrapper. Token locks prevent credential collisions. Tab completion for profile names. ([#3681](https://github.com/NousResearch/hermes-agent/pull/3681))
+- **Profile-aware display paths** — all user-facing `~/.hermes` paths replaced with `display_hermes_home()` to show the correct profile directory ([#3623](https://github.com/NousResearch/hermes-agent/pull/3623))
+- **Lazy display_hermes_home imports** — prevents `ImportError` during `hermes update` when modules cache stale bytecode ([#3776](https://github.com/NousResearch/hermes-agent/pull/3776))
+- **HERMES_HOME for protected paths** — `.env` write-deny path now respects HERMES_HOME instead of hardcoded `~/.hermes` ([#3840](https://github.com/NousResearch/hermes-agent/pull/3840))
+
+---
+
+## 📱 Messaging Platforms (Gateway)
+
+### New Platforms
+- **Feishu/Lark** — Full adapter with event subscriptions, message cards, group chat, image/file attachments, interactive card callbacks ([#3799](https://github.com/NousResearch/hermes-agent/pull/3799), [#3817](https://github.com/NousResearch/hermes-agent/pull/3817))
+- **WeCom (Enterprise WeChat)** — Text/image/voice messages, group chats, callback verification ([#3847](https://github.com/NousResearch/hermes-agent/pull/3847))
+
+### Telegram
+- **Webhook mode** — run as webhook endpoint instead of polling for production deployments ([#3880](https://github.com/NousResearch/hermes-agent/pull/3880))
+- **Group mention gating & regex triggers** — configurable bot response behavior in groups: always, @mention-only, or regex-matched ([#3870](https://github.com/NousResearch/hermes-agent/pull/3870))
+- **Gracefully handle deleted reply targets** — no more crashes when the message being replied to was deleted ([#3858](https://github.com/NousResearch/hermes-agent/pull/3858), closes [#3229](https://github.com/NousResearch/hermes-agent/issues/3229))
+
+### Discord
+- **Message processing reactions** — adds a reaction emoji while processing and removes it when done, giving visual feedback in channels ([#3871](https://github.com/NousResearch/hermes-agent/pull/3871))
+- **DISCORD_IGNORE_NO_MENTION** — skip messages that @mention other users/bots but not Hermes ([#3640](https://github.com/NousResearch/hermes-agent/pull/3640))
+- **Clean up deferred "thinking..."** — properly removes the "thinking..." indicator after slash commands complete ([#3674](https://github.com/NousResearch/hermes-agent/pull/3674), closes [#3595](https://github.com/NousResearch/hermes-agent/issues/3595))
+
+### Slack
+- **Multi-workspace OAuth** — connect to multiple Slack workspaces from a single gateway via OAuth token file ([#3903](https://github.com/NousResearch/hermes-agent/pull/3903))
+
+### WhatsApp
+- **Persistent aiohttp session** — reuse HTTP sessions across requests instead of creating new ones per message ([#3818](https://github.com/NousResearch/hermes-agent/pull/3818))
+- **LID↔phone alias resolution** — correctly match Linked ID and phone number formats in allowlists ([#3830](https://github.com/NousResearch/hermes-agent/pull/3830))
+- **Skip reply prefix in bot mode** — cleaner message formatting when running as a WhatsApp bot ([#3931](https://github.com/NousResearch/hermes-agent/pull/3931))
+
+### Matrix
+- **Native voice messages via MSC3245** — send voice messages as proper Matrix voice events instead of file attachments ([#3877](https://github.com/NousResearch/hermes-agent/pull/3877))
+
+### Mattermost
+- **Configurable mention behavior** — respond to messages without requiring @mention ([#3664](https://github.com/NousResearch/hermes-agent/pull/3664))
+
+### Signal
+- **URL-encode phone numbers** and correct attachment RPC parameter — fixes delivery failures with certain phone number formats ([#3670](https://github.com/NousResearch/hermes-agent/pull/3670)) — @kshitijk4poor
+
+### Email
+- **Close SMTP/IMAP connections on failure** — prevents connection leaks during error scenarios ([#3804](https://github.com/NousResearch/hermes-agent/pull/3804))
+
+### Gateway Core
+- **Atomic config writes** — use atomic file writes for config.yaml to prevent data loss during crashes ([#3800](https://github.com/NousResearch/hermes-agent/pull/3800))
+- **Home channel env overrides** — apply environment variable overrides for home channels consistently ([#3796](https://github.com/NousResearch/hermes-agent/pull/3796), [#3808](https://github.com/NousResearch/hermes-agent/pull/3808))
+- **Replace print() with logger** — BasePlatformAdapter now uses proper logging instead of print statements ([#3669](https://github.com/NousResearch/hermes-agent/pull/3669))
+- **Cron delivery labels** — resolve human-friendly delivery labels via channel directory ([#3860](https://github.com/NousResearch/hermes-agent/pull/3860), closes [#1945](https://github.com/NousResearch/hermes-agent/issues/1945))
+- **Cron [SILENT] tightening** — prevent agents from prefixing reports with [SILENT] to suppress delivery ([#3901](https://github.com/NousResearch/hermes-agent/pull/3901))
+- **Background task media delivery** and vision download timeout fixes ([#3919](https://github.com/NousResearch/hermes-agent/pull/3919))
+- **Boot-md hook** — example built-in hook to run a BOOT.md file on gateway startup ([#3733](https://github.com/NousResearch/hermes-agent/pull/3733))
+
+---
+
+## 🖥️ CLI & User Experience
+
+### Interactive CLI
+- **Configurable tool preview length** — show full file paths by default instead of truncating at 40 chars ([#3841](https://github.com/NousResearch/hermes-agent/pull/3841))
+- **Tool token context display** — `hermes tools` checklist now shows estimated token cost per toolset ([#3805](https://github.com/NousResearch/hermes-agent/pull/3805))
+- **/bg spinner TUI fix** — route background task spinner through the TUI widget to prevent status bar collision ([#3643](https://github.com/NousResearch/hermes-agent/pull/3643))
+- **Prevent status bar wrapping** into duplicate rows ([#3883](https://github.com/NousResearch/hermes-agent/pull/3883)) — @kshitijk4poor
+- **Handle closed stdout ValueError** in safe print paths — fixes crashes when stdout is closed during gateway thread shutdown ([#3843](https://github.com/NousResearch/hermes-agent/pull/3843), closes [#3534](https://github.com/NousResearch/hermes-agent/issues/3534))
+- **Remove input() from /tools disable** — eliminates freeze in terminal when disabling tools ([#3918](https://github.com/NousResearch/hermes-agent/pull/3918))
+- **TTY guard for interactive CLI commands** — prevent CPU spin when launched without a terminal ([#3933](https://github.com/NousResearch/hermes-agent/pull/3933))
+- **Argparse entrypoint** — use argparse in the top-level launcher for cleaner error handling ([#3874](https://github.com/NousResearch/hermes-agent/pull/3874))
+- **Lazy-initialized tools show yellow** in banner instead of red, reducing false alarm about "missing" tools ([#3822](https://github.com/NousResearch/hermes-agent/pull/3822))
+- **Honcho tools shown in banner** when configured ([#3810](https://github.com/NousResearch/hermes-agent/pull/3810))
+
+### Setup & Configuration
+- **Auto-install matrix-nio** during `hermes setup` when Matrix is selected ([#3802](https://github.com/NousResearch/hermes-agent/pull/3802), [#3873](https://github.com/NousResearch/hermes-agent/pull/3873))
+- **Session export stdout support** — export sessions to stdout with `-` for piping ([#3641](https://github.com/NousResearch/hermes-agent/pull/3641), closes [#3609](https://github.com/NousResearch/hermes-agent/issues/3609))
+- **Configurable approval timeouts** — set how long dangerous command approval prompts wait before auto-denying ([#3886](https://github.com/NousResearch/hermes-agent/pull/3886), closes [#3765](https://github.com/NousResearch/hermes-agent/issues/3765))
+- **Clear __pycache__ during update** — prevents stale bytecode ImportError after `hermes update` ([#3819](https://github.com/NousResearch/hermes-agent/pull/3819))
+
+---
+
+## 🔧 Tool System
+
+### MCP
+- **MCP Server Mode** — `hermes mcp serve` exposes conversations, sessions, and attachments to MCP clients via stdio or Streamable HTTP ([#3795](https://github.com/NousResearch/hermes-agent/pull/3795))
+- **Dynamic tool discovery** — respond to `notifications/tools/list_changed` events to pick up new tools from MCP servers without reconnecting ([#3812](https://github.com/NousResearch/hermes-agent/pull/3812))
+- **Non-deprecated HTTP transport** — switched from `sse_client` to `streamable_http_client` ([#3646](https://github.com/NousResearch/hermes-agent/pull/3646))
+
+### Web Tools
+- **Exa search backend** — alternative to Firecrawl and DuckDuckGo for web search and extraction ([#3648](https://github.com/NousResearch/hermes-agent/pull/3648))
+
+### Browser
+- **Guard against None LLM responses** in browser snapshot and vision tools ([#3642](https://github.com/NousResearch/hermes-agent/pull/3642))
+
+### Terminal & Remote Backends
+- **Mount skill directories** into Modal and Docker containers ([#3890](https://github.com/NousResearch/hermes-agent/pull/3890))
+- **Mount credential files** into remote backends with mtime+size caching ([#3671](https://github.com/NousResearch/hermes-agent/pull/3671))
+- **Preserve partial output** when commands time out instead of losing everything ([#3868](https://github.com/NousResearch/hermes-agent/pull/3868))
+- **Stop marking persisted env vars as missing** on remote backends ([#3650](https://github.com/NousResearch/hermes-agent/pull/3650))
+
+### Audio
+- **.aac format support** in transcription tool ([#3865](https://github.com/NousResearch/hermes-agent/pull/3865), closes [#1963](https://github.com/NousResearch/hermes-agent/issues/1963))
+- **Audio download retry** — retry logic for `cache_audio_from_url` matching the existing image download pattern ([#3401](https://github.com/NousResearch/hermes-agent/pull/3401)) — @binhnt92
+
+### Vision
+- **Reject non-image files** and enforce website-only policy for vision analysis ([#3845](https://github.com/NousResearch/hermes-agent/pull/3845))
+
+### Tool Schema
+- **Ensure name field** always present in tool definitions, fixing `KeyError: 'name'` crashes ([#3811](https://github.com/NousResearch/hermes-agent/pull/3811), closes [#3729](https://github.com/NousResearch/hermes-agent/issues/3729))
+
+### ACP (Editor Integration)
+- **Complete session management surface** for VS Code/Zed/JetBrains clients — proper task lifecycle, cancel support, session persistence ([#3675](https://github.com/NousResearch/hermes-agent/pull/3675))
+
+---
+
+## 🧩 Skills & Plugins
+
+### Skills System
+- **External skill directories** — configure additional skill directories via `skills.external_dirs` in config.yaml ([#3678](https://github.com/NousResearch/hermes-agent/pull/3678))
+- **Category path traversal blocked** — prevents `../` attacks in skill category names ([#3844](https://github.com/NousResearch/hermes-agent/pull/3844))
+- **parallel-cli moved to optional-skills** — reduces default skill footprint ([#3673](https://github.com/NousResearch/hermes-agent/pull/3673)) — @kshitijk4poor
+
+### New Skills
+- **memento-flashcards** — spaced repetition flashcard system ([#3827](https://github.com/NousResearch/hermes-agent/pull/3827))
+- **songwriting-and-ai-music** — songwriting craft and AI music generation prompts ([#3834](https://github.com/NousResearch/hermes-agent/pull/3834))
+- **SiYuan Note** — integration with SiYuan note-taking app ([#3742](https://github.com/NousResearch/hermes-agent/pull/3742))
+- **Scrapling** — web scraping skill using Scrapling library ([#3742](https://github.com/NousResearch/hermes-agent/pull/3742))
+- **one-three-one-rule** — communication framework skill ([#3797](https://github.com/NousResearch/hermes-agent/pull/3797))
+
+### Plugin System
+- **Plugin enable/disable commands** — `hermes plugins enable/disable <name>` for managing plugin state without removing them ([#3747](https://github.com/NousResearch/hermes-agent/pull/3747))
+- **Plugin message injection** — plugins can now inject messages into the conversation stream on behalf of the user via `ctx.inject_message()` ([#3778](https://github.com/NousResearch/hermes-agent/pull/3778)) — @winglian
+- **Honcho self-hosted support** — allow local Honcho instances without requiring an API key ([#3644](https://github.com/NousResearch/hermes-agent/pull/3644))
+
+---
+
+## 🔒 Security & Reliability
+
+### Security Hardening
+- **Hardened dangerous command detection** — expanded pattern matching for risky shell commands and added file tool path guards for sensitive locations (`/etc/`, `/boot/`, docker.sock) ([#3872](https://github.com/NousResearch/hermes-agent/pull/3872))
+- **Sensitive path write checks** in approval system — catch writes to system config files through file tools, not just terminal ([#3859](https://github.com/NousResearch/hermes-agent/pull/3859))
+- **Secret redaction expansion** — now covers ElevenLabs, Tavily, and Exa API keys ([#3920](https://github.com/NousResearch/hermes-agent/pull/3920))
+- **Vision file rejection** — reject non-image files passed to vision analysis to prevent information disclosure ([#3845](https://github.com/NousResearch/hermes-agent/pull/3845))
+- **Category path traversal blocking** — prevent directory traversal in skill category names ([#3844](https://github.com/NousResearch/hermes-agent/pull/3844))
+
+### Reliability
+- **Atomic config.yaml writes** — prevent data loss during gateway crashes ([#3800](https://github.com/NousResearch/hermes-agent/pull/3800))
+- **Clear __pycache__ on update** — prevent stale bytecode from causing ImportError after updates ([#3819](https://github.com/NousResearch/hermes-agent/pull/3819))
+- **Lazy imports for update safety** — prevent ImportError chains during `hermes update` when modules reference new functions ([#3776](https://github.com/NousResearch/hermes-agent/pull/3776))
+- **Restore terminalbench2 from patch corruption** — recovered file damaged by patch tool's secret redaction ([#3801](https://github.com/NousResearch/hermes-agent/pull/3801))
+- **Terminal timeout preserves partial output** — no more lost command output on timeout ([#3868](https://github.com/NousResearch/hermes-agent/pull/3868))
+
+---
+
+## 🐛 Notable Bug Fixes
+
+- **OpenClaw migration model config overwrite** — migration no longer overwrites model config dict with a string ([#3924](https://github.com/NousResearch/hermes-agent/pull/3924)) — @0xbyt4
+- **OpenClaw migration expanded** — covers full data footprint including sessions, cron, memory ([#3869](https://github.com/NousResearch/hermes-agent/pull/3869))
+- **Telegram deleted reply targets** — gracefully handle replies to deleted messages instead of crashing ([#3858](https://github.com/NousResearch/hermes-agent/pull/3858))
+- **Discord "thinking..." persistence** — properly cleans up deferred response indicators ([#3674](https://github.com/NousResearch/hermes-agent/pull/3674))
+- **WhatsApp LID↔phone aliases** — fixes allowlist matching failures with Linked ID format ([#3830](https://github.com/NousResearch/hermes-agent/pull/3830))
+- **Signal URL-encoded phone numbers** — fixes delivery failures with certain formats ([#3670](https://github.com/NousResearch/hermes-agent/pull/3670))
+- **Email connection leaks** — properly close SMTP/IMAP connections on error ([#3804](https://github.com/NousResearch/hermes-agent/pull/3804))
+- **_safe_print ValueError** — no more gateway thread crashes on closed stdout ([#3843](https://github.com/NousResearch/hermes-agent/pull/3843))
+- **Tool schema KeyError 'name'** — ensure name field always present in tool definitions ([#3811](https://github.com/NousResearch/hermes-agent/pull/3811))
+- **api_mode stale on provider switch** — correctly clear when switching providers via `hermes model` ([#3857](https://github.com/NousResearch/hermes-agent/pull/3857))
+
+---
+
+## 🧪 Testing
+
+- Resolved 10+ CI failures across hooks, tiktoken, plugins, and skill tests ([#3848](https://github.com/NousResearch/hermes-agent/pull/3848), [#3721](https://github.com/NousResearch/hermes-agent/pull/3721), [#3936](https://github.com/NousResearch/hermes-agent/pull/3936))
+
+---
+
+## 📚 Documentation
+
+- **Comprehensive OpenClaw migration guide** — step-by-step guide for migrating from OpenClaw/Claw3D to Hermes Agent ([#3864](https://github.com/NousResearch/hermes-agent/pull/3864), [#3900](https://github.com/NousResearch/hermes-agent/pull/3900))
+- **Credential file passthrough docs** — document how to forward credential files and env vars to remote backends ([#3677](https://github.com/NousResearch/hermes-agent/pull/3677))
+- **DuckDuckGo requirements clarified** — note runtime dependency on duckduckgo-search package ([#3680](https://github.com/NousResearch/hermes-agent/pull/3680))
+- **Skills catalog updated** — added red-teaming category and optional skills listing ([#3745](https://github.com/NousResearch/hermes-agent/pull/3745))
+- **Feishu docs MDX fix** — escape angle-bracket URLs that break Docusaurus build ([#3902](https://github.com/NousResearch/hermes-agent/pull/3902))
+
+---
+
+## 👥 Contributors
+
+### Core
+- **@teknium1** — 90 PRs across all subsystems
+
+### Community Contributors
+- **@kshitijk4poor** — 3 PRs: Signal phone number fix ([#3670](https://github.com/NousResearch/hermes-agent/pull/3670)), parallel-cli to optional-skills ([#3673](https://github.com/NousResearch/hermes-agent/pull/3673)), status bar wrapping fix ([#3883](https://github.com/NousResearch/hermes-agent/pull/3883))
+- **@winglian** — 1 PR: Plugin message injection interface ([#3778](https://github.com/NousResearch/hermes-agent/pull/3778))
+- **@binhnt92** — 1 PR: Audio download retry logic ([#3401](https://github.com/NousResearch/hermes-agent/pull/3401))
+- **@0xbyt4** — 1 PR: OpenClaw migration model config fix ([#3924](https://github.com/NousResearch/hermes-agent/pull/3924))
+
+### Issues Resolved from Community
+@Material-Scientist ([#850](https://github.com/NousResearch/hermes-agent/issues/850)), @hanxu98121 ([#1734](https://github.com/NousResearch/hermes-agent/issues/1734)), @penwyp ([#1788](https://github.com/NousResearch/hermes-agent/issues/1788)), @dan-and ([#1945](https://github.com/NousResearch/hermes-agent/issues/1945)), @AdrianScott ([#1963](https://github.com/NousResearch/hermes-agent/issues/1963)), @clawdbot47 ([#3229](https://github.com/NousResearch/hermes-agent/issues/3229)), @alanfwilliams ([#3404](https://github.com/NousResearch/hermes-agent/issues/3404)), @kentimsit ([#3433](https://github.com/NousResearch/hermes-agent/issues/3433)), @hayka-pacha ([#3534](https://github.com/NousResearch/hermes-agent/issues/3534)), @primmer ([#3595](https://github.com/NousResearch/hermes-agent/issues/3595)), @dagelf ([#3609](https://github.com/NousResearch/hermes-agent/issues/3609)), @HenkDz ([#3685](https://github.com/NousResearch/hermes-agent/issues/3685)), @tmdgusya ([#3729](https://github.com/NousResearch/hermes-agent/issues/3729)), @TypQxQ ([#3753](https://github.com/NousResearch/hermes-agent/issues/3753)), @acsezen ([#3765](https://github.com/NousResearch/hermes-agent/issues/3765))
+
+---
+
+**Full Changelog**: [v2026.3.28...v2026.3.30](https://github.com/NousResearch/hermes-agent/compare/v2026.3.28...v2026.3.30)

acp_adapter/__init__.py

@@ -0,0 +1 @@
+"""ACP (Agent Communication Protocol) adapter for hermes-agent."""

acp_adapter/__main__.py

@@ -0,0 +1,5 @@
+"""Allow running the ACP adapter as ``python -m acp_adapter``."""
+
+from .entry import main
+
+main()

acp_adapter/auth.py

@@ -0,0 +1,24 @@
+"""ACP auth helpers — detect the currently configured Hermes provider."""
+
+from __future__ import annotations
+
+from typing import Optional
+
+
+def detect_provider() -> Optional[str]:
+    """Resolve the active Hermes runtime provider, or None if unavailable."""
+    try:
+        from hermes_cli.runtime_provider import resolve_runtime_provider
+        runtime = resolve_runtime_provider()
+        api_key = runtime.get("api_key")
+        provider = runtime.get("provider")
+        if isinstance(api_key, str) and api_key.strip() and isinstance(provider, str) and provider.strip():
+            return provider.strip().lower()
+    except Exception:
+        return None
+    return None
+
+
+def has_provider() -> bool:
+    """Return True if Hermes can resolve any runtime provider credentials."""
+    return detect_provider() is not None

acp_adapter/entry.py

@@ -0,0 +1,86 @@
+"""CLI entry point for the hermes-agent ACP adapter.
+
+Loads environment variables from ``~/.hermes/.env``, configures logging
+to write to stderr (so stdout is reserved for ACP JSON-RPC transport),
+and starts the ACP agent server.
+
+Usage::
+
+    python -m acp_adapter.entry
+    # or
+    hermes acp
+    # or
+    hermes-acp
+"""
+
+import asyncio
+import logging
+import os
+import sys
+from pathlib import Path
+from hermes_constants import get_hermes_home
+
+
+def _setup_logging() -> None:
+    """Route all logging to stderr so stdout stays clean for ACP stdio."""
+    handler = logging.StreamHandler(sys.stderr)
+    handler.setFormatter(
+        logging.Formatter(
+            "%(asctime)s [%(levelname)s] %(name)s: %(message)s",
+            datefmt="%Y-%m-%d %H:%M:%S",
+        )
+    )
+    root = logging.getLogger()
+    root.handlers.clear()
+    root.addHandler(handler)
+    root.setLevel(logging.INFO)
+
+    # Quiet down noisy libraries
+    logging.getLogger("httpx").setLevel(logging.WARNING)
+    logging.getLogger("httpcore").setLevel(logging.WARNING)
+    logging.getLogger("openai").setLevel(logging.WARNING)
+
+
+def _load_env() -> None:
+    """Load .env from HERMES_HOME (default ``~/.hermes``)."""
+    from hermes_cli.env_loader import load_hermes_dotenv
+
+    hermes_home = get_hermes_home()
+    loaded = load_hermes_dotenv(hermes_home=hermes_home)
+    if loaded:
+        for env_file in loaded:
+            logging.getLogger(__name__).info("Loaded env from %s", env_file)
+    else:
+        logging.getLogger(__name__).info(
+            "No .env found at %s, using system env", hermes_home / ".env"
+        )
+
+
+def main() -> None:
+    """Entry point: load env, configure logging, run the ACP agent."""
+    _setup_logging()
+    _load_env()
+
+    logger = logging.getLogger(__name__)
+    logger.info("Starting hermes-agent ACP adapter")
+
+    # Ensure the project root is on sys.path so ``from run_agent import AIAgent`` works
+    project_root = str(Path(__file__).resolve().parent.parent)
+    if project_root not in sys.path:
+        sys.path.insert(0, project_root)
+
+    import acp
+    from .server import HermesACPAgent
+
+    agent = HermesACPAgent()
+    try:
+        asyncio.run(acp.run_agent(agent, use_unstable_protocol=True))
+    except KeyboardInterrupt:
+        logger.info("Shutting down (KeyboardInterrupt)")
+    except Exception:
+        logger.exception("ACP agent crashed")
+        sys.exit(1)
+
+
+if __name__ == "__main__":
+    main()

acp_adapter/events.py

@@ -0,0 +1,171 @@
+"""Callback factories for bridging AIAgent events to ACP notifications.
+
+Each factory returns a callable with the signature that AIAgent expects
+for its callbacks. Internally, the callbacks push ACP session updates
+to the client via ``conn.session_update()`` using
+``asyncio.run_coroutine_threadsafe()`` (since AIAgent runs in a worker
+thread while the event loop lives on the main thread).
+"""
+
+import asyncio
+import json
+import logging
+from collections import deque
+from typing import Any, Callable, Deque, Dict
+
+import acp
+
+from .tools import (
+    build_tool_complete,
+    build_tool_start,
+    make_tool_call_id,
+)
+
+logger = logging.getLogger(__name__)
+
+
+def _send_update(
+    conn: acp.Client,
+    session_id: str,
+    loop: asyncio.AbstractEventLoop,
+    update: Any,
+) -> None:
+    """Fire-and-forget an ACP session update from a worker thread."""
+    try:
+        future = asyncio.run_coroutine_threadsafe(
+            conn.session_update(session_id, update), loop
+        )
+        future.result(timeout=5)
+    except Exception:
+        logger.debug("Failed to send ACP update", exc_info=True)
+
+
+# ------------------------------------------------------------------
+# Tool progress callback
+# ------------------------------------------------------------------
+
+def make_tool_progress_cb(
+    conn: acp.Client,
+    session_id: str,
+    loop: asyncio.AbstractEventLoop,
+    tool_call_ids: Dict[str, Deque[str]],
+) -> Callable:
+    """Create a ``tool_progress_callback`` for AIAgent.
+
+    Signature expected by AIAgent::
+
+        tool_progress_callback(name: str, preview: str, args: dict)
+
+    Emits ``ToolCallStart`` for each tool invocation and tracks IDs in a FIFO
+    queue per tool name so duplicate/parallel same-name calls still complete
+    against the correct ACP tool call.
+    """
+
+    def _tool_progress(name: str, preview: str, args: Any = None) -> None:
+        if isinstance(args, str):
+            try:
+                args = json.loads(args)
+            except (json.JSONDecodeError, TypeError):
+                args = {"raw": args}
+        if not isinstance(args, dict):
+            args = {}
+
+        tc_id = make_tool_call_id()
+        queue = tool_call_ids.get(name)
+        if queue is None:
+            queue = deque()
+            tool_call_ids[name] = queue
+        elif isinstance(queue, str):
+            queue = deque([queue])
+            tool_call_ids[name] = queue
+        queue.append(tc_id)
+
+        update = build_tool_start(tc_id, name, args)
+        _send_update(conn, session_id, loop, update)
+
+    return _tool_progress
+
+
+# ------------------------------------------------------------------
+# Thinking callback
+# ------------------------------------------------------------------
+
+def make_thinking_cb(
+    conn: acp.Client,
+    session_id: str,
+    loop: asyncio.AbstractEventLoop,
+) -> Callable:
+    """Create a ``thinking_callback`` for AIAgent."""
+
+    def _thinking(text: str) -> None:
+        if not text:
+            return
+        update = acp.update_agent_thought_text(text)
+        _send_update(conn, session_id, loop, update)
+
+    return _thinking
+
+
+# ------------------------------------------------------------------
+# Step callback
+# ------------------------------------------------------------------
+
+def make_step_cb(
+    conn: acp.Client,
+    session_id: str,
+    loop: asyncio.AbstractEventLoop,
+    tool_call_ids: Dict[str, Deque[str]],
+) -> Callable:
+    """Create a ``step_callback`` for AIAgent.
+
+    Signature expected by AIAgent::
+
+        step_callback(api_call_count: int, prev_tools: list)
+    """
+
+    def _step(api_call_count: int, prev_tools: Any = None) -> None:
+        if prev_tools and isinstance(prev_tools, list):
+            for tool_info in prev_tools:
+                tool_name = None
+                result = None
+
+                if isinstance(tool_info, dict):
+                    tool_name = tool_info.get("name") or tool_info.get("function_name")
+                    result = tool_info.get("result") or tool_info.get("output")
+                elif isinstance(tool_info, str):
+                    tool_name = tool_info
+
+                queue = tool_call_ids.get(tool_name or "")
+                if isinstance(queue, str):
+                    queue = deque([queue])
+                    tool_call_ids[tool_name] = queue
+                if tool_name and queue:
+                    tc_id = queue.popleft()
+                    update = build_tool_complete(
+                        tc_id, tool_name, result=str(result) if result is not None else None
+                    )
+                    _send_update(conn, session_id, loop, update)
+                    if not queue:
+                        tool_call_ids.pop(tool_name, None)
+
+    return _step
+
+
+# ------------------------------------------------------------------
+# Agent message callback
+# ------------------------------------------------------------------
+
+def make_message_cb(
+    conn: acp.Client,
+    session_id: str,
+    loop: asyncio.AbstractEventLoop,
+) -> Callable:
+    """Create a callback that streams agent response text to the editor."""
+
+    def _message(text: str) -> None:
+        if not text:
+            return
+        update = acp.update_agent_message_text(text)
+        _send_update(conn, session_id, loop, update)
+
+    return _message

acp_adapter/permissions.py

@@ -0,0 +1,77 @@
+"""ACP permission bridging — maps ACP approval requests to hermes approval callbacks."""
+
+from __future__ import annotations
+
+import asyncio
+import logging
+from concurrent.futures import TimeoutError as FutureTimeout
+from typing import Callable
+
+from acp.schema import (
+    AllowedOutcome,
+    PermissionOption,
+)
+
+logger = logging.getLogger(__name__)
+
+# Maps ACP PermissionOptionKind -> hermes approval result strings
+_KIND_TO_HERMES = {
+    "allow_once": "once",
+    "allow_always": "always",
+    "reject_once": "deny",
+    "reject_always": "deny",
+}
+
+
+def make_approval_callback(
+    request_permission_fn: Callable,
+    loop: asyncio.AbstractEventLoop,
+    session_id: str,
+    timeout: float = 60.0,
+) -> Callable[[str, str], str]:
+    """
+    Return a hermes-compatible ``approval_callback(command, description) -> str``
+    that bridges to the ACP client's ``request_permission`` call.
+
+    Args:
+        request_permission_fn: The ACP connection's ``request_permission`` coroutine.
+        loop: The event loop on which the ACP connection lives.
+        session_id: Current ACP session id.
+        timeout: Seconds to wait for a response before auto-denying.
+    """
+
+    def _callback(command: str, description: str) -> str:
+        options = [
+            PermissionOption(option_id="allow_once", kind="allow_once", name="Allow once"),
+            PermissionOption(option_id="allow_always", kind="allow_always", name="Allow always"),
+            PermissionOption(option_id="deny", kind="reject_once", name="Deny"),
+        ]
+        import acp as _acp
+
+        tool_call = _acp.start_tool_call("perm-check", command, kind="execute")
+
+        coro = request_permission_fn(
+            session_id=session_id,
+            tool_call=tool_call,
+            options=options,
+        )
+
+        try:
+            future = asyncio.run_coroutine_threadsafe(coro, loop)
+            response = future.result(timeout=timeout)
+        except (FutureTimeout, Exception) as exc:
+            logger.warning("Permission request timed out or failed: %s", exc)
+            return "deny"
+
+        outcome = response.outcome
+        if isinstance(outcome, AllowedOutcome):
+            option_id = outcome.option_id
+            # Look up the kind from our options list
+            for opt in options:
+                if opt.option_id == option_id:
+                    return _KIND_TO_HERMES.get(opt.kind, "deny")
+            return "once"  # fallback for unknown option_id
+        else:
+            return "deny"
+
+    return _callback

acp_adapter/server.py

@@ -0,0 +1,535 @@
+"""ACP agent server — exposes Hermes Agent via the Agent Client Protocol."""
+
+from __future__ import annotations
+
+import asyncio
+import logging
+from collections import defaultdict, deque
+from concurrent.futures import ThreadPoolExecutor
+from typing import Any, Deque, Optional
+
+import acp
+from acp.schema import (
+    AgentCapabilities,
+    AuthenticateResponse,
+    AuthMethod,
+    ClientCapabilities,
+    EmbeddedResourceContentBlock,
+    ForkSessionResponse,
+    ImageContentBlock,
+    AudioContentBlock,
+    Implementation,
+    InitializeResponse,
+    ListSessionsResponse,
+    LoadSessionResponse,
+    NewSessionResponse,
+    PromptResponse,
+    ResumeSessionResponse,
+    SetSessionConfigOptionResponse,
+    SetSessionModelResponse,
+    SetSessionModeResponse,
+    ResourceContentBlock,
+    SessionCapabilities,
+    SessionForkCapabilities,
+    SessionListCapabilities,
+    SessionInfo,
+    TextContentBlock,
+    Usage,
+)
+
+from acp_adapter.auth import detect_provider, has_provider
+from acp_adapter.events import (
+    make_message_cb,
+    make_step_cb,
+    make_thinking_cb,
+    make_tool_progress_cb,
+)
+from acp_adapter.permissions import make_approval_callback
+from acp_adapter.session import SessionManager, SessionState
+
+logger = logging.getLogger(__name__)
+
+try:
+    from hermes_cli import __version__ as HERMES_VERSION
+except Exception:
+    HERMES_VERSION = "0.0.0"
+
+# Thread pool for running AIAgent (synchronous) in parallel.
+_executor = ThreadPoolExecutor(max_workers=4, thread_name_prefix="acp-agent")
+
+
+def _extract_text(
+    prompt: list[
+        TextContentBlock
+        | ImageContentBlock
+        | AudioContentBlock
+        | ResourceContentBlock
+        | EmbeddedResourceContentBlock
+    ],
+) -> str:
+    """Extract plain text from ACP content blocks."""
+    parts: list[str] = []
+    for block in prompt:
+        if isinstance(block, TextContentBlock):
+            parts.append(block.text)
+        elif hasattr(block, "text"):
+            parts.append(str(block.text))
+        # Non-text blocks are ignored for now.
+    return "\n".join(parts)
+
+
+class HermesACPAgent(acp.Agent):
+    """ACP Agent implementation wrapping Hermes AIAgent."""
+
+    def __init__(self, session_manager: SessionManager | None = None):
+        super().__init__()
+        self.session_manager = session_manager or SessionManager()
+        self._conn: Optional[acp.Client] = None
+
+    # ---- Connection lifecycle -----------------------------------------------
+
+    def on_connect(self, conn: acp.Client) -> None:
+        """Store the client connection for sending session updates."""
+        self._conn = conn
+        logger.info("ACP client connected")
+
+    # ---- ACP lifecycle ------------------------------------------------------
+
+    async def initialize(
+        self,
+        protocol_version: int | None = None,
+        client_capabilities: ClientCapabilities | None = None,
+        client_info: Implementation | None = None,
+        **kwargs: Any,
+    ) -> InitializeResponse:
+        resolved_protocol_version = (
+            protocol_version if isinstance(protocol_version, int) else acp.PROTOCOL_VERSION
+        )
+        provider = detect_provider()
+        auth_methods = None
+        if provider:
+            auth_methods = [
+                AuthMethod(
+                    id=provider,
+                    name=f"{provider} runtime credentials",
+                    description=f"Authenticate Hermes using the currently configured {provider} runtime credentials.",
+                )
+            ]
+
+        client_name = client_info.name if client_info else "unknown"
+        logger.info(
+            "Initialize from %s (protocol v%s)",
+            client_name,
+            resolved_protocol_version,
+        )
+
+        return InitializeResponse(
+            protocol_version=acp.PROTOCOL_VERSION,
+            agent_info=Implementation(name="hermes-agent", version=HERMES_VERSION),
+            agent_capabilities=AgentCapabilities(
+                session_capabilities=SessionCapabilities(
+                    fork=SessionForkCapabilities(),
+                    list=SessionListCapabilities(),
+                ),
+            ),
+            auth_methods=auth_methods,
+        )
+
+    async def authenticate(self, method_id: str, **kwargs: Any) -> AuthenticateResponse | None:
+        if has_provider():
+            return AuthenticateResponse()
+        return None
+
+    # ---- Session management -------------------------------------------------
+
+    async def new_session(
+        self,
+        cwd: str,
+        mcp_servers: list | None = None,
+        **kwargs: Any,
+    ) -> NewSessionResponse:
+        state = self.session_manager.create_session(cwd=cwd)
+        logger.info("New session %s (cwd=%s)", state.session_id, cwd)
+        return NewSessionResponse(session_id=state.session_id)
+
+    async def load_session(
+        self,
+        cwd: str,
+        session_id: str,
+        mcp_servers: list | None = None,
+        **kwargs: Any,
+    ) -> LoadSessionResponse | None:
+        state = self.session_manager.update_cwd(session_id, cwd)
+        if state is None:
+            logger.warning("load_session: session %s not found", session_id)
+            return None
+        logger.info("Loaded session %s", session_id)
+        return LoadSessionResponse()
+
+    async def resume_session(
+        self,
+        cwd: str,
+        session_id: str,
+        mcp_servers: list | None = None,
+        **kwargs: Any,
+    ) -> ResumeSessionResponse:
+        state = self.session_manager.update_cwd(session_id, cwd)
+        if state is None:
+            logger.warning("resume_session: session %s not found, creating new", session_id)
+            state = self.session_manager.create_session(cwd=cwd)
+        logger.info("Resumed session %s", state.session_id)
+        return ResumeSessionResponse()
+
+    async def cancel(self, session_id: str, **kwargs: Any) -> None:
+        state = self.session_manager.get_session(session_id)
+        if state and state.cancel_event:
+            state.cancel_event.set()
+            try:
+                if getattr(state, "agent", None) and hasattr(state.agent, "interrupt"):
+                    state.agent.interrupt()
+            except Exception:
+                logger.debug("Failed to interrupt ACP session %s", session_id, exc_info=True)
+            logger.info("Cancelled session %s", session_id)
+
+    async def fork_session(
+        self,
+        cwd: str,
+        session_id: str,
+        mcp_servers: list | None = None,
+        **kwargs: Any,
+    ) -> ForkSessionResponse:
+        state = self.session_manager.fork_session(session_id, cwd=cwd)
+        new_id = state.session_id if state else ""
+        logger.info("Forked session %s -> %s", session_id, new_id)
+        return ForkSessionResponse(session_id=new_id)
+
+    async def list_sessions(
+        self,
+        cursor: str | None = None,
+        cwd: str | None = None,
+        **kwargs: Any,
+    ) -> ListSessionsResponse:
+        infos = self.session_manager.list_sessions()
+        sessions = [
+            SessionInfo(session_id=s["session_id"], cwd=s["cwd"])
+            for s in infos
+        ]
+        return ListSessionsResponse(sessions=sessions)
+
+    # ---- Prompt (core) ------------------------------------------------------
+
+    async def prompt(
+        self,
+        prompt: list[
+            TextContentBlock
+            | ImageContentBlock
+            | AudioContentBlock
+            | ResourceContentBlock
+            | EmbeddedResourceContentBlock
+        ],
+        session_id: str,
+        **kwargs: Any,
+    ) -> PromptResponse:
+        """Run Hermes on the user's prompt and stream events back to the editor."""
+        state = self.session_manager.get_session(session_id)
+        if state is None:
+            logger.error("prompt: session %s not found", session_id)
+            return PromptResponse(stop_reason="refusal")
+
+        user_text = _extract_text(prompt).strip()
+        if not user_text:
+            return PromptResponse(stop_reason="end_turn")
+
+        # Intercept slash commands — handle locally without calling the LLM
+        if user_text.startswith("/"):
+            response_text = self._handle_slash_command(user_text, state)
+            if response_text is not None:
+                if self._conn:
+                    update = acp.update_agent_message_text(response_text)
+                    await self._conn.session_update(session_id, update)
+                return PromptResponse(stop_reason="end_turn")
+
+        logger.info("Prompt on session %s: %s", session_id, user_text[:100])
+
+        conn = self._conn
+        loop = asyncio.get_running_loop()
+
+        if state.cancel_event:
+            state.cancel_event.clear()
+
+        tool_call_ids: dict[str, Deque[str]] = defaultdict(deque)
+        previous_approval_cb = None
+
+        if conn:
+            tool_progress_cb = make_tool_progress_cb(conn, session_id, loop, tool_call_ids)
+            thinking_cb = make_thinking_cb(conn, session_id, loop)
+            step_cb = make_step_cb(conn, session_id, loop, tool_call_ids)
+            message_cb = make_message_cb(conn, session_id, loop)
+            approval_cb = make_approval_callback(conn.request_permission, loop, session_id)
+        else:
+            tool_progress_cb = None
+            thinking_cb = None
+            step_cb = None
+            message_cb = None
+            approval_cb = None
+
+        agent = state.agent
+        agent.tool_progress_callback = tool_progress_cb
+        agent.thinking_callback = thinking_cb
+        agent.step_callback = step_cb
+        agent.message_callback = message_cb
+
+        if approval_cb:
+            try:
+                from tools import terminal_tool as _terminal_tool
+                previous_approval_cb = getattr(_terminal_tool, "_approval_callback", None)
+                _terminal_tool.set_approval_callback(approval_cb)
+            except Exception:
+                logger.debug("Could not set ACP approval callback", exc_info=True)
+
+        def _run_agent() -> dict:
+            try:
+                result = agent.run_conversation(
+                    user_message=user_text,
+                    conversation_history=state.history,
+                    task_id=session_id,
+                )
+                return result
+            except Exception as e:
+                logger.exception("Agent error in session %s", session_id)
+                return {"final_response": f"Error: {e}", "messages": state.history}
+            finally:
+                if approval_cb:
+                    try:
+                        from tools import terminal_tool as _terminal_tool
+                        _terminal_tool.set_approval_callback(previous_approval_cb)
+                    except Exception:
+                        logger.debug("Could not restore approval callback", exc_info=True)
+
+        try:
+            result = await loop.run_in_executor(_executor, _run_agent)
+        except Exception:
+            logger.exception("Executor error for session %s", session_id)
+            return PromptResponse(stop_reason="end_turn")
+
+        if result.get("messages"):
+            state.history = result["messages"]
+            # Persist updated history so sessions survive process restarts.
+            self.session_manager.save_session(session_id)
+
+        final_response = result.get("final_response", "")
+        if final_response and conn:
+            update = acp.update_agent_message_text(final_response)
+            await conn.session_update(session_id, update)
+
+        usage = None
+        usage_data = result.get("usage")
+        if usage_data and isinstance(usage_data, dict):
+            usage = Usage(
+                input_tokens=usage_data.get("prompt_tokens", 0),
+                output_tokens=usage_data.get("completion_tokens", 0),
+                total_tokens=usage_data.get("total_tokens", 0),
+                thought_tokens=usage_data.get("reasoning_tokens"),
+                cached_read_tokens=usage_data.get("cached_tokens"),
+            )
+
+        stop_reason = "cancelled" if state.cancel_event and state.cancel_event.is_set() else "end_turn"
+        return PromptResponse(stop_reason=stop_reason, usage=usage)
+
+    # ---- Slash commands (headless) -------------------------------------------
+
+    _SLASH_COMMANDS = {
+        "help": "Show available commands",
+        "model": "Show or change current model",
+        "tools": "List available tools",
+        "context": "Show conversation context info",
+        "reset": "Clear conversation history",
+        "compact": "Compress conversation context",
+        "version": "Show Hermes version",
+    }
+
+    def _handle_slash_command(self, text: str, state: SessionState) -> str | None:
+        """Dispatch a slash command and return the response text.
+
+        Returns ``None`` for unrecognized commands so they fall through
+        to the LLM (the user may have typed ``/something`` as prose).
+        """
+        parts = text.split(maxsplit=1)
+        cmd = parts[0].lstrip("/").lower()
+        args = parts[1].strip() if len(parts) > 1 else ""
+
+        handler = {
+            "help": self._cmd_help,
+            "model": self._cmd_model,
+            "tools": self._cmd_tools,
+            "context": self._cmd_context,
+            "reset": self._cmd_reset,
+            "compact": self._cmd_compact,
+            "version": self._cmd_version,
+        }.get(cmd)
+
+        if handler is None:
+            return None  # not a known command — let the LLM handle it
+
+        try:
+            return handler(args, state)
+        except Exception as e:
+            logger.error("Slash command /%s error: %s", cmd, e, exc_info=True)
+            return f"Error executing /{cmd}: {e}"
+
+    def _cmd_help(self, args: str, state: SessionState) -> str:
+        lines = ["Available commands:", ""]
+        for cmd, desc in self._SLASH_COMMANDS.items():
+            lines.append(f"  /{cmd:10s}  {desc}")
+        lines.append("")
+        lines.append("Unrecognized /commands are sent to the model as normal messages.")
+        return "\n".join(lines)
+
+    def _cmd_model(self, args: str, state: SessionState) -> str:
+        if not args:
+            model = state.model or getattr(state.agent, "model", "unknown")
+            provider = getattr(state.agent, "provider", None) or "auto"
+            return f"Current model: {model}\nProvider: {provider}"
+
+        new_model = args.strip()
+        target_provider = None
+        current_provider = getattr(state.agent, "provider", None) or "openrouter"
+
+        # Auto-detect provider for the requested model
+        try:
+            from hermes_cli.models import parse_model_input, detect_provider_for_model
+            target_provider, new_model = parse_model_input(new_model, current_provider)
+            if target_provider == current_provider:
+                detected = detect_provider_for_model(new_model, current_provider)
+                if detected:
+                    target_provider, new_model = detected
+        except Exception:
+            logger.debug("Provider detection failed, using model as-is", exc_info=True)
+
+        state.model = new_model
+        state.agent = self.session_manager._make_agent(
+            session_id=state.session_id,
+            cwd=state.cwd,
+            model=new_model,
+            requested_provider=target_provider or current_provider,
+        )
+        self.session_manager.save_session(state.session_id)
+        provider_label = getattr(state.agent, "provider", None) or target_provider or current_provider
+        logger.info("Session %s: model switched to %s", state.session_id, new_model)
+        return f"Model switched to: {new_model}\nProvider: {provider_label}"
+
+    def _cmd_tools(self, args: str, state: SessionState) -> str:
+        try:
+            from model_tools import get_tool_definitions
+            toolsets = getattr(state.agent, "enabled_toolsets", None) or ["hermes-acp"]
+            tools = get_tool_definitions(enabled_toolsets=toolsets, quiet_mode=True)
+            if not tools:
+                return "No tools available."
+            lines = [f"Available tools ({len(tools)}):"]
+            for t in tools:
+                name = t.get("function", {}).get("name", "?")
+                desc = t.get("function", {}).get("description", "")
+                # Truncate long descriptions
+                if len(desc) > 80:
+                    desc = desc[:77] + "..."
+                lines.append(f"  {name}: {desc}")
+            return "\n".join(lines)
+        except Exception as e:
+            return f"Could not list tools: {e}"
+
+    def _cmd_context(self, args: str, state: SessionState) -> str:
+        n_messages = len(state.history)
+        if n_messages == 0:
+            return "Conversation is empty (no messages yet)."
+        # Count by role
+        roles: dict[str, int] = {}
+        for msg in state.history:
+            role = msg.get("role", "unknown")
+            roles[role] = roles.get(role, 0) + 1
+        lines = [
+            f"Conversation: {n_messages} messages",
+            f"  user: {roles.get('user', 0)}, assistant: {roles.get('assistant', 0)}, "
+            f"tool: {roles.get('tool', 0)}, system: {roles.get('system', 0)}",
+        ]
+        model = state.model or getattr(state.agent, "model", "")
+        if model:
+            lines.append(f"Model: {model}")
+        return "\n".join(lines)
+
+    def _cmd_reset(self, args: str, state: SessionState) -> str:
+        state.history.clear()
+        self.session_manager.save_session(state.session_id)
+        return "Conversation history cleared."
+
+    def _cmd_compact(self, args: str, state: SessionState) -> str:
+        if not state.history:
+            return "Nothing to compress — conversation is empty."
+        try:
+            agent = state.agent
+            if hasattr(agent, "compress_context"):
+                agent.compress_context(state.history)
+                self.session_manager.save_session(state.session_id)
+                return f"Context compressed. Messages: {len(state.history)}"
+            return "Context compression not available for this agent."
+        except Exception as e:
+            return f"Compression failed: {e}"
+
+    def _cmd_version(self, args: str, state: SessionState) -> str:
+        return f"Hermes Agent v{HERMES_VERSION}"
+
+    # ---- Model switching (ACP protocol method) -------------------------------
+
+    async def set_session_model(
+        self, model_id: str, session_id: str, **kwargs: Any
+    ) -> SetSessionModelResponse | None:
+        """Switch the model for a session (called by ACP protocol)."""
+        state = self.session_manager.get_session(session_id)
+        if state:
+            state.model = model_id
+            current_provider = getattr(state.agent, "provider", None)
+            current_base_url = getattr(state.agent, "base_url", None)
+            current_api_mode = getattr(state.agent, "api_mode", None)
+            state.agent = self.session_manager._make_agent(
+                session_id=session_id,
+                cwd=state.cwd,
+                model=model_id,
+                requested_provider=current_provider,
+                base_url=current_base_url,
+                api_mode=current_api_mode,
+            )
+            self.session_manager.save_session(session_id)
+            logger.info("Session %s: model switched to %s", session_id, model_id)
+            return SetSessionModelResponse()
+        logger.warning("Session %s: model switch requested for missing session", session_id)
+        return None
+
+    async def set_session_mode(
+        self, mode_id: str, session_id: str, **kwargs: Any
+    ) -> SetSessionModeResponse | None:
+        """Persist the editor-requested mode so ACP clients do not fail on mode switches."""
+        state = self.session_manager.get_session(session_id)
+        if state is None:
+            logger.warning("Session %s: mode switch requested for missing session", session_id)
+            return None
+        setattr(state, "mode", mode_id)
+        self.session_manager.save_session(session_id)
+        logger.info("Session %s: mode switched to %s", session_id, mode_id)
+        return SetSessionModeResponse()
+
+    async def set_config_option(
+        self, config_id: str, session_id: str, value: str, **kwargs: Any
+    ) -> SetSessionConfigOptionResponse | None:
+        """Accept ACP config option updates even when Hermes has no typed ACP config surface yet."""
+        state = self.session_manager.get_session(session_id)
+        if state is None:
+            logger.warning("Session %s: config update requested for missing session", session_id)
+            return None
+
+        options = getattr(state, "config_options", None)
+        if not isinstance(options, dict):
+            options = {}
+        options[str(config_id)] = value
+        setattr(state, "config_options", options)
+        self.session_manager.save_session(session_id)
+        logger.info("Session %s: config option %s updated", session_id, config_id)
+        return SetSessionConfigOptionResponse(config_options=[])

acp_adapter/session.py

@@ -0,0 +1,461 @@
+"""ACP session manager — maps ACP sessions to Hermes AIAgent instances.
+
+Sessions are persisted to the shared SessionDB (``~/.hermes/state.db``) so they
+survive process restarts and appear in ``session_search``.  When the editor
+reconnects after idle/restart, the ``load_session`` / ``resume_session`` calls
+find the persisted session in the database and restore the full conversation
+history.
+"""
+from __future__ import annotations
+
+from hermes_constants import get_hermes_home
+
+import copy
+import json
+import logging
+import uuid
+from dataclasses import dataclass, field
+from threading import Lock
+from typing import Any, Dict, List, Optional
+
+logger = logging.getLogger(__name__)
+
+
+def _register_task_cwd(task_id: str, cwd: str) -> None:
+    """Bind a task/session id to the editor's working directory for tools."""
+    if not task_id:
+        return
+    try:
+        from tools.terminal_tool import register_task_env_overrides
+        register_task_env_overrides(task_id, {"cwd": cwd})
+    except Exception:
+        logger.debug("Failed to register ACP task cwd override", exc_info=True)
+
+
+def _clear_task_cwd(task_id: str) -> None:
+    """Remove task-specific cwd overrides for an ACP session."""
+    if not task_id:
+        return
+    try:
+        from tools.terminal_tool import clear_task_env_overrides
+        clear_task_env_overrides(task_id)
+    except Exception:
+        logger.debug("Failed to clear ACP task cwd override", exc_info=True)
+
+
+@dataclass
+class SessionState:
+    """Tracks per-session state for an ACP-managed Hermes agent."""
+
+    session_id: str
+    agent: Any  # AIAgent instance
+    cwd: str = "."
+    model: str = ""
+    history: List[Dict[str, Any]] = field(default_factory=list)
+    cancel_event: Any = None  # threading.Event
+
+
+class SessionManager:
+    """Thread-safe manager for ACP sessions backed by Hermes AIAgent instances.
+
+    Sessions are held in-memory for fast access **and** persisted to the
+    shared SessionDB so they survive process restarts and are searchable
+    via ``session_search``.
+    """
+
+    def __init__(self, agent_factory=None, db=None):
+        """
+        Args:
+            agent_factory: Optional callable that creates an AIAgent-like object.
+                           Used by tests. When omitted, a real AIAgent is created
+                           using the current Hermes runtime provider configuration.
+            db:            Optional SessionDB instance. When omitted, the default
+                           SessionDB (``~/.hermes/state.db``) is lazily created.
+        """
+        self._sessions: Dict[str, SessionState] = {}
+        self._lock = Lock()
+        self._agent_factory = agent_factory
+        self._db_instance = db  # None → lazy-init on first use
+
+    # ---- public API ---------------------------------------------------------
+
+    def create_session(self, cwd: str = ".") -> SessionState:
+        """Create a new session with a unique ID and a fresh AIAgent."""
+        import threading
+
+        session_id = str(uuid.uuid4())
+        agent = self._make_agent(session_id=session_id, cwd=cwd)
+        state = SessionState(
+            session_id=session_id,
+            agent=agent,
+            cwd=cwd,
+            model=getattr(agent, "model", "") or "",
+            cancel_event=threading.Event(),
+        )
+        with self._lock:
+            self._sessions[session_id] = state
+        _register_task_cwd(session_id, cwd)
+        self._persist(state)
+        logger.info("Created ACP session %s (cwd=%s)", session_id, cwd)
+        return state
+
+    def get_session(self, session_id: str) -> Optional[SessionState]:
+        """Return the session for *session_id*, or ``None``.
+
+        If the session is not in memory but exists in the database (e.g. after
+        a process restart), it is transparently restored.
+        """
+        with self._lock:
+            state = self._sessions.get(session_id)
+        if state is not None:
+            return state
+        # Attempt to restore from database.
+        return self._restore(session_id)
+
+    def remove_session(self, session_id: str) -> bool:
+        """Remove a session from memory and database. Returns True if it existed."""
+        with self._lock:
+            existed = self._sessions.pop(session_id, None) is not None
+        db_existed = self._delete_persisted(session_id)
+        if existed or db_existed:
+            _clear_task_cwd(session_id)
+        return existed or db_existed
+
+    def fork_session(self, session_id: str, cwd: str = ".") -> Optional[SessionState]:
+        """Deep-copy a session's history into a new session."""
+        import threading
+
+        original = self.get_session(session_id)  # checks DB too
+        if original is None:
+            return None
+
+        new_id = str(uuid.uuid4())
+        agent = self._make_agent(
+            session_id=new_id,
+            cwd=cwd,
+            model=original.model or None,
+        )
+        state = SessionState(
+            session_id=new_id,
+            agent=agent,
+            cwd=cwd,
+            model=getattr(agent, "model", original.model) or original.model,
+            history=copy.deepcopy(original.history),
+            cancel_event=threading.Event(),
+        )
+        with self._lock:
+            self._sessions[new_id] = state
+        _register_task_cwd(new_id, cwd)
+        self._persist(state)
+        logger.info("Forked ACP session %s -> %s", session_id, new_id)
+        return state
+
+    def list_sessions(self) -> List[Dict[str, Any]]:
+        """Return lightweight info dicts for all sessions (memory + database)."""
+        # Collect in-memory sessions first.
+        with self._lock:
+            seen_ids = set(self._sessions.keys())
+            results = [
+                {
+                    "session_id": s.session_id,
+                    "cwd": s.cwd,
+                    "model": s.model,
+                    "history_len": len(s.history),
+                }
+                for s in self._sessions.values()
+            ]
+
+        # Merge any persisted sessions not currently in memory.
+        db = self._get_db()
+        if db is not None:
+            try:
+                rows = db.search_sessions(source="acp", limit=1000)
+                for row in rows:
+                    sid = row["id"]
+                    if sid in seen_ids:
+                        continue
+                    # Extract cwd from model_config JSON.
+                    cwd = "."
+                    mc = row.get("model_config")
+                    if mc:
+                        try:
+                            cwd = json.loads(mc).get("cwd", ".")
+                        except (json.JSONDecodeError, TypeError):
+                            pass
+                    results.append({
+                        "session_id": sid,
+                        "cwd": cwd,
+                        "model": row.get("model") or "",
+                        "history_len": row.get("message_count") or 0,
+                    })
+            except Exception:
+                logger.debug("Failed to list ACP sessions from DB", exc_info=True)
+
+        return results
+
+    def update_cwd(self, session_id: str, cwd: str) -> Optional[SessionState]:
+        """Update the working directory for a session and its tool overrides."""
+        state = self.get_session(session_id)  # checks DB too
+        if state is None:
+            return None
+        state.cwd = cwd
+        _register_task_cwd(session_id, cwd)
+        self._persist(state)
+        return state
+
+    def cleanup(self) -> None:
+        """Remove all sessions (memory and database) and clear task-specific cwd overrides."""
+        with self._lock:
+            session_ids = list(self._sessions.keys())
+            self._sessions.clear()
+        for session_id in session_ids:
+            _clear_task_cwd(session_id)
+            self._delete_persisted(session_id)
+        # Also remove any DB-only ACP sessions not currently in memory.
+        db = self._get_db()
+        if db is not None:
+            try:
+                rows = db.search_sessions(source="acp", limit=10000)
+                for row in rows:
+                    sid = row["id"]
+                    _clear_task_cwd(sid)
+                    db.delete_session(sid)
+            except Exception:
+                logger.debug("Failed to cleanup ACP sessions from DB", exc_info=True)
+
+    def save_session(self, session_id: str) -> None:
+        """Persist the current state of a session to the database.
+
+        Called by the server after prompt completion, slash commands that
+        mutate history, and model switches.
+        """
+        with self._lock:
+            state = self._sessions.get(session_id)
+        if state is not None:
+            self._persist(state)
+
+    # ---- persistence via SessionDB ------------------------------------------
+
+    def _get_db(self):
+        """Lazily initialise and return the SessionDB instance.
+
+        Returns ``None`` if the DB is unavailable (e.g. import error in a
+        minimal test environment).
+
+        Note: we resolve ``HERMES_HOME`` dynamically rather than relying on
+        the module-level ``DEFAULT_DB_PATH`` constant, because that constant
+        is evaluated at import time and won't reflect env-var changes made
+        later (e.g. by the test fixture ``_isolate_hermes_home``).
+        """
+        if self._db_instance is not None:
+            return self._db_instance
+        try:
+            import os
+            from pathlib import Path
+            from hermes_state import SessionDB
+            hermes_home = get_hermes_home()
+            self._db_instance = SessionDB(db_path=hermes_home / "state.db")
+            return self._db_instance
+        except Exception:
+            logger.debug("SessionDB unavailable for ACP persistence", exc_info=True)
+            return None
+
+    def _persist(self, state: SessionState) -> None:
+        """Write session state to the database.
+
+        Creates the session record if it doesn't exist, then replaces all
+        stored messages with the current in-memory history.
+        """
+        db = self._get_db()
+        if db is None:
+            return
+
+        # Ensure model is a plain string (not a MagicMock or other proxy).
+        model_str = str(state.model) if state.model else None
+        session_meta = {"cwd": state.cwd}
+        provider = getattr(state.agent, "provider", None)
+        base_url = getattr(state.agent, "base_url", None)
+        api_mode = getattr(state.agent, "api_mode", None)
+        if isinstance(provider, str) and provider.strip():
+            session_meta["provider"] = provider.strip()
+        if isinstance(base_url, str) and base_url.strip():
+            session_meta["base_url"] = base_url.strip()
+        if isinstance(api_mode, str) and api_mode.strip():
+            session_meta["api_mode"] = api_mode.strip()
+        cwd_json = json.dumps(session_meta)
+
+        try:
+            # Ensure the session record exists.
+            existing = db.get_session(state.session_id)
+            if existing is None:
+                db.create_session(
+                    session_id=state.session_id,
+                    source="acp",
+                    model=model_str,
+                    model_config={"cwd": state.cwd},
+                )
+            else:
+                # Update model_config (contains cwd) if changed.
+                try:
+                    with db._lock:
+                        db._conn.execute(
+                            "UPDATE sessions SET model_config = ?, model = COALESCE(?, model) WHERE id = ?",
+                            (cwd_json, model_str, state.session_id),
+                        )
+                        db._conn.commit()
+                except Exception:
+                    logger.debug("Failed to update ACP session metadata", exc_info=True)
+
+            # Replace stored messages with current history.
+            db.clear_messages(state.session_id)
+            for msg in state.history:
+                db.append_message(
+                    session_id=state.session_id,
+                    role=msg.get("role", "user"),
+                    content=msg.get("content"),
+                    tool_name=msg.get("tool_name") or msg.get("name"),
+                    tool_calls=msg.get("tool_calls"),
+                    tool_call_id=msg.get("tool_call_id"),
+                )
+        except Exception:
+            logger.warning("Failed to persist ACP session %s", state.session_id, exc_info=True)
+
+    def _restore(self, session_id: str) -> Optional[SessionState]:
+        """Load a session from the database into memory, recreating the AIAgent."""
+        import threading
+
+        db = self._get_db()
+        if db is None:
+            return None
+
+        try:
+            row = db.get_session(session_id)
+        except Exception:
+            logger.debug("Failed to query DB for ACP session %s", session_id, exc_info=True)
+            return None
+
+        if row is None:
+            return None
+
+        # Only restore ACP sessions.
+        if row.get("source") != "acp":
+            return None
+
+        # Extract cwd from model_config.
+        cwd = "."
+        requested_provider = row.get("billing_provider")
+        restored_base_url = row.get("billing_base_url")
+        restored_api_mode = None
+        mc = row.get("model_config")
+        if mc:
+            try:
+                meta = json.loads(mc)
+                if isinstance(meta, dict):
+                    cwd = meta.get("cwd", ".")
+                    requested_provider = meta.get("provider") or requested_provider
+                    restored_base_url = meta.get("base_url") or restored_base_url
+                    restored_api_mode = meta.get("api_mode") or restored_api_mode
+            except (json.JSONDecodeError, TypeError):
+                pass
+
+        model = row.get("model") or None
+
+        # Load conversation history.
+        try:
+            history = db.get_messages_as_conversation(session_id)
+        except Exception:
+            logger.warning("Failed to load messages for ACP session %s", session_id, exc_info=True)
+            history = []
+
+        try:
+            agent = self._make_agent(
+                session_id=session_id,
+                cwd=cwd,
+                model=model,
+                requested_provider=requested_provider,
+                base_url=restored_base_url,
+                api_mode=restored_api_mode,
+            )
+        except Exception:
+            logger.warning("Failed to recreate agent for ACP session %s", session_id, exc_info=True)
+            return None
+
+        state = SessionState(
+            session_id=session_id,
+            agent=agent,
+            cwd=cwd,
+            model=model or getattr(agent, "model", "") or "",
+            history=history,
+            cancel_event=threading.Event(),
+        )
+        with self._lock:
+            self._sessions[session_id] = state
+        _register_task_cwd(session_id, cwd)
+        logger.info("Restored ACP session %s from DB (%d messages)", session_id, len(history))
+        return state
+
+    def _delete_persisted(self, session_id: str) -> bool:
+        """Delete a session from the database. Returns True if it existed."""
+        db = self._get_db()
+        if db is None:
+            return False
+        try:
+            return db.delete_session(session_id)
+        except Exception:
+            logger.debug("Failed to delete ACP session %s from DB", session_id, exc_info=True)
+            return False
+
+    # ---- internal -----------------------------------------------------------
+
+    def _make_agent(
+        self,
+        *,
+        session_id: str,
+        cwd: str,
+        model: str | None = None,
+        requested_provider: str | None = None,
+        base_url: str | None = None,
+        api_mode: str | None = None,
+    ):
+        if self._agent_factory is not None:
+            return self._agent_factory()
+
+        from run_agent import AIAgent
+        from hermes_cli.config import load_config
+        from hermes_cli.runtime_provider import resolve_runtime_provider
+
+        config = load_config()
+        model_cfg = config.get("model")
+        default_model = "anthropic/claude-opus-4.6"
+        config_provider = None
+        if isinstance(model_cfg, dict):
+            default_model = str(model_cfg.get("default") or default_model)
+            config_provider = model_cfg.get("provider")
+        elif isinstance(model_cfg, str) and model_cfg.strip():
+            default_model = model_cfg.strip()
+
+        kwargs = {
+            "platform": "acp",
+            "enabled_toolsets": ["hermes-acp"],
+            "quiet_mode": True,
+            "session_id": session_id,
+            "model": model or default_model,
+        }
+
+        try:
+            runtime = resolve_runtime_provider(requested=requested_provider or config_provider)
+            kwargs.update(
+                {
+                    "provider": runtime.get("provider"),
+                    "api_mode": api_mode or runtime.get("api_mode"),
+                    "base_url": base_url or runtime.get("base_url"),
+                    "api_key": runtime.get("api_key"),
+                    "command": runtime.get("command"),
+                    "args": list(runtime.get("args") or []),
+                }
+            )
+        except Exception:
+            logger.debug("ACP session falling back to default provider resolution", exc_info=True)
+
+        _register_task_cwd(session_id, cwd)
+        return AIAgent(**kwargs)

acp_adapter/tools.py

@@ -0,0 +1,215 @@
+"""ACP tool-call helpers for mapping hermes tools to ACP ToolKind and building content."""
+
+from __future__ import annotations
+
+import uuid
+from typing import Any, Dict, List, Optional
+
+import acp
+from acp.schema import (
+    ToolCallLocation,
+    ToolCallStart,
+    ToolCallProgress,
+    ToolKind,
+)
+
+# ---------------------------------------------------------------------------
+# Map hermes tool names -> ACP ToolKind
+# ---------------------------------------------------------------------------
+
+TOOL_KIND_MAP: Dict[str, ToolKind] = {
+    # File operations
+    "read_file": "read",
+    "write_file": "edit",
+    "patch": "edit",
+    "search_files": "search",
+    # Terminal / execution
+    "terminal": "execute",
+    "process": "execute",
+    "execute_code": "execute",
+    # Web / fetch
+    "web_search": "fetch",
+    "web_extract": "fetch",
+    # Browser
+    "browser_navigate": "fetch",
+    "browser_click": "execute",
+    "browser_type": "execute",
+    "browser_snapshot": "read",
+    "browser_vision": "read",
+    "browser_scroll": "execute",
+    "browser_press": "execute",
+    "browser_back": "execute",
+    "browser_close": "execute",
+    "browser_get_images": "read",
+    # Agent internals
+    "delegate_task": "execute",
+    "vision_analyze": "read",
+    "image_generate": "execute",
+    "text_to_speech": "execute",
+    # Thinking / meta
+    "_thinking": "think",
+}
+
+
+def get_tool_kind(tool_name: str) -> ToolKind:
+    """Return the ACP ToolKind for a hermes tool, defaulting to 'other'."""
+    return TOOL_KIND_MAP.get(tool_name, "other")
+
+
+def make_tool_call_id() -> str:
+    """Generate a unique tool call ID."""
+    return f"tc-{uuid.uuid4().hex[:12]}"
+
+
+def build_tool_title(tool_name: str, args: Dict[str, Any]) -> str:
+    """Build a human-readable title for a tool call."""
+    if tool_name == "terminal":
+        cmd = args.get("command", "")
+        if len(cmd) > 80:
+            cmd = cmd[:77] + "..."
+        return f"terminal: {cmd}"
+    if tool_name == "read_file":
+        return f"read: {args.get('path', '?')}"
+    if tool_name == "write_file":
+        return f"write: {args.get('path', '?')}"
+    if tool_name == "patch":
+        mode = args.get("mode", "replace")
+        path = args.get("path", "?")
+        return f"patch ({mode}): {path}"
+    if tool_name == "search_files":
+        return f"search: {args.get('pattern', '?')}"
+    if tool_name == "web_search":
+        return f"web search: {args.get('query', '?')}"
+    if tool_name == "web_extract":
+        urls = args.get("urls", [])
+        if urls:
+            return f"extract: {urls[0]}" + (f" (+{len(urls)-1})" if len(urls) > 1 else "")
+        return "web extract"
+    if tool_name == "delegate_task":
+        goal = args.get("goal", "")
+        if goal and len(goal) > 60:
+            goal = goal[:57] + "..."
+        return f"delegate: {goal}" if goal else "delegate task"
+    if tool_name == "execute_code":
+        return "execute code"
+    if tool_name == "vision_analyze":
+        return f"analyze image: {args.get('question', '?')[:50]}"
+    return tool_name
+
+
+# ---------------------------------------------------------------------------
+# Build ACP content objects for tool-call events
+# ---------------------------------------------------------------------------
+
+
+def build_tool_start(
+    tool_call_id: str,
+    tool_name: str,
+    arguments: Dict[str, Any],
+) -> ToolCallStart:
+    """Create a ToolCallStart event for the given hermes tool invocation."""
+    kind = get_tool_kind(tool_name)
+    title = build_tool_title(tool_name, arguments)
+    locations = extract_locations(arguments)
+
+    if tool_name == "patch":
+        mode = arguments.get("mode", "replace")
+        if mode == "replace":
+            path = arguments.get("path", "")
+            old = arguments.get("old_string", "")
+            new = arguments.get("new_string", "")
+            content = [acp.tool_diff_content(path=path, new_text=new, old_text=old)]
+        else:
+            # Patch mode — show the patch content as text
+            patch_text = arguments.get("patch", "")
+            content = [acp.tool_content(acp.text_block(patch_text))]
+        return acp.start_tool_call(
+            tool_call_id, title, kind=kind, content=content, locations=locations,
+            raw_input=arguments,
+        )
+
+    if tool_name == "write_file":
+        path = arguments.get("path", "")
+        file_content = arguments.get("content", "")
+        content = [acp.tool_diff_content(path=path, new_text=file_content)]
+        return acp.start_tool_call(
+            tool_call_id, title, kind=kind, content=content, locations=locations,
+            raw_input=arguments,
+        )
+
+    if tool_name == "terminal":
+        command = arguments.get("command", "")
+        content = [acp.tool_content(acp.text_block(f"$ {command}"))]
+        return acp.start_tool_call(
+            tool_call_id, title, kind=kind, content=content, locations=locations,
+            raw_input=arguments,
+        )
+
+    if tool_name == "read_file":
+        path = arguments.get("path", "")
+        content = [acp.tool_content(acp.text_block(f"Reading {path}"))]
+        return acp.start_tool_call(
+            tool_call_id, title, kind=kind, content=content, locations=locations,
+            raw_input=arguments,
+        )
+
+    if tool_name == "search_files":
+        pattern = arguments.get("pattern", "")
+        target = arguments.get("target", "content")
+        content = [acp.tool_content(acp.text_block(f"Searching for '{pattern}' ({target})"))]
+        return acp.start_tool_call(
+            tool_call_id, title, kind=kind, content=content, locations=locations,
+            raw_input=arguments,
+        )
+
+    # Generic fallback
+    import json
+    try:
+        args_text = json.dumps(arguments, indent=2, default=str)
+    except (TypeError, ValueError):
+        args_text = str(arguments)
+    content = [acp.tool_content(acp.text_block(args_text))]
+    return acp.start_tool_call(
+        tool_call_id, title, kind=kind, content=content, locations=locations,
+        raw_input=arguments,
+    )
+
+
+def build_tool_complete(
+    tool_call_id: str,
+    tool_name: str,
+    result: Optional[str] = None,
+) -> ToolCallProgress:
+    """Create a ToolCallUpdate (progress) event for a completed tool call."""
+    kind = get_tool_kind(tool_name)
+
+    # Truncate very large results for the UI
+    display_result = result or ""
+    if len(display_result) > 5000:
+        display_result = display_result[:4900] + f"\n... ({len(result)} chars total, truncated)"
+
+    content = [acp.tool_content(acp.text_block(display_result))]
+    return acp.update_tool_call(
+        tool_call_id,
+        kind=kind,
+        status="completed",
+        content=content,
+        raw_output=result,
+    )
+
+
+# ---------------------------------------------------------------------------
+# Location extraction
+# ---------------------------------------------------------------------------
+
+
+def extract_locations(
+    arguments: Dict[str, Any],
+) -> List[ToolCallLocation]:
+    """Extract file-system locations from tool arguments."""
+    locations: List[ToolCallLocation] = []
+    path = arguments.get("path")
+    if path:
+        line = arguments.get("offset") or arguments.get("line")
+        locations.append(ToolCallLocation(path=path, line=line))
+    return locations

acp_registry/agent.json

@@ -0,0 +1,12 @@
+{
+  "schema_version": 1,
+  "name": "hermes-agent",
+  "display_name": "Hermes Agent",
+  "description": "AI agent by Nous Research with 90+ tools, persistent memory, and multi-platform support",
+  "icon": "icon.svg",
+  "distribution": {
+    "type": "command",
+    "command": "hermes",
+    "args": ["acp"]
+  }
+}

acp_registry/icon.svg

@@ -0,0 +1,25 @@
+<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 64 64" width="64" height="64">
+  <defs>
+    <linearGradient id="gold" x1="0%" y1="0%" x2="0%" y2="100%">
+      <stop offset="0%" style="stop-color:#F5C542;stop-opacity:1" />
+      <stop offset="100%" style="stop-color:#D4961C;stop-opacity:1" />
+    </linearGradient>
+  </defs>
+  <!-- Staff -->
+  <rect x="30" y="10" width="4" height="46" rx="2" fill="url(#gold)" />
+  <!-- Wings (left) -->
+  <path d="M30 18 C24 14, 14 14, 10 18 C14 16, 22 16, 28 20" fill="#F5C542" opacity="0.9" />
+  <path d="M30 22 C26 19, 18 19, 14 22 C18 20, 24 20, 28 24" fill="#D4961C" opacity="0.8" />
+  <!-- Wings (right) -->
+  <path d="M34 18 C40 14, 50 14, 54 18 C50 16, 42 16, 36 20" fill="#F5C542" opacity="0.9" />
+  <path d="M34 22 C38 19, 46 19, 50 22 C46 20, 40 20, 36 24" fill="#D4961C" opacity="0.8" />
+  <!-- Left serpent -->
+  <path d="M32 48 C22 44, 20 38, 26 34 C20 36, 18 42, 24 46 C18 40, 22 30, 30 28 C24 32, 22 38, 28 42"
+        fill="none" stroke="#F5C542" stroke-width="2.5" stroke-linecap="round" />
+  <!-- Right serpent -->
+  <path d="M32 48 C42 44, 44 38, 38 34 C44 36, 46 42, 40 46 C46 40, 42 30, 34 28 C40 32, 42 38, 36 42"
+        fill="none" stroke="#D4961C" stroke-width="2.5" stroke-linecap="round" />
+  <!-- Orb at top -->
+  <circle cx="32" cy="10" r="4" fill="#F5C542" />
+  <circle cx="32" cy="10" r="2" fill="#FFF8E1" opacity="0.7" />
+</svg>

agent/context_compressor.py

@@ -1,15 +1,22 @@
 """Automatic context window compression for long conversations.
 
 Self-contained class with its own OpenAI client for summarization.
-Uses Gemini Flash (cheap/fast) to summarize middle turns while
+Uses auxiliary model (cheap/fast) to summarize middle turns while
 protecting head and tail context.
+
+Improvements over v1:
+  - Structured summary template (Goal, Progress, Decisions, Files, Next Steps)
+  - Iterative summary updates (preserves info across multiple compactions)
+  - Token-budget tail protection instead of fixed message count
+  - Tool output pruning before LLM summarization (cheap pre-pass)
+  - Scaled summary budget (proportional to compressed content)
+  - Richer tool call/result detail in summarizer input
 """
 
 import logging
-import os
 from typing import Any, Dict, List, Optional
 
-from agent.auxiliary_client import get_text_auxiliary_client
+from agent.auxiliary_client import call_llm
 from agent.model_metadata import (
     get_model_context_length,
     estimate_messages_tokens_rough,
@@ -17,44 +24,100 @@ from agent.model_metadata import (
 
 logger = logging.getLogger(__name__)
 
+SUMMARY_PREFIX = (
+    "[CONTEXT COMPACTION] Earlier turns in this conversation were compacted "
+    "to save context space. The summary below describes work that was "
+    "already completed, and the current session state may still reflect "
+    "that work (for example, files may already be changed). Use the summary "
+    "and the current state to continue from where things left off, and "
+    "avoid repeating work:"
+)
+LEGACY_SUMMARY_PREFIX = "[CONTEXT SUMMARY]:"
+
+# Minimum tokens for the summary output
+_MIN_SUMMARY_TOKENS = 2000
+# Proportion of compressed content to allocate for summary
+_SUMMARY_RATIO = 0.20
+# Absolute ceiling for summary tokens (even on very large context windows)
+_SUMMARY_TOKENS_CEILING = 12_000
+
+# Placeholder used when pruning old tool results
+_PRUNED_TOOL_PLACEHOLDER = "[Old tool output cleared to save context space]"
+
+# Chars per token rough estimate
+_CHARS_PER_TOKEN = 4
+
 
 class ContextCompressor:
     """Compresses conversation context when approaching the model's context limit.
 
-    Algorithm: protect first N + last N turns, summarize everything in between.
-    Token tracking uses actual counts from API responses for accuracy.
+    Algorithm:
+      1. Prune old tool results (cheap, no LLM call)
+      2. Protect head messages (system prompt + first exchange)
+      3. Protect tail messages by token budget (most recent ~20K tokens)
+      4. Summarize middle turns with structured LLM prompt
+      5. On subsequent compactions, iteratively update the previous summary
     """
 
     def __init__(
         self,
         model: str,
-        threshold_percent: float = 0.85,
+        threshold_percent: float = 0.50,
         protect_first_n: int = 3,
-        protect_last_n: int = 4,
-        summary_target_tokens: int = 2500,
+        protect_last_n: int = 20,
+        summary_target_ratio: float = 0.20,
         quiet_mode: bool = False,
         summary_model_override: str = None,
         base_url: str = "",
+        api_key: str = "",
+        config_context_length: int | None = None,
+        provider: str = "",
     ):
         self.model = model
         self.base_url = base_url
+        self.api_key = api_key
+        self.provider = provider
         self.threshold_percent = threshold_percent
         self.protect_first_n = protect_first_n
         self.protect_last_n = protect_last_n
-        self.summary_target_tokens = summary_target_tokens
+        self.summary_target_ratio = max(0.10, min(summary_target_ratio, 0.80))
         self.quiet_mode = quiet_mode
 
-        self.context_length = get_model_context_length(model, base_url=base_url)
+        self.context_length = get_model_context_length(
+            model, base_url=base_url, api_key=api_key,
+            config_context_length=config_context_length,
+            provider=provider,
+        )
         self.threshold_tokens = int(self.context_length * threshold_percent)
         self.compression_count = 0
+
+        # Derive token budgets: ratio is relative to the threshold, not total context
+        target_tokens = int(self.threshold_tokens * self.summary_target_ratio)
+        self.tail_token_budget = target_tokens
+        self.max_summary_tokens = min(
+            int(self.context_length * 0.05), _SUMMARY_TOKENS_CEILING,
+        )
+
+        if not quiet_mode:
+            logger.info(
+                "Context compressor initialized: model=%s context_length=%d "
+                "threshold=%d (%.0f%%) target_ratio=%.0f%% tail_budget=%d "
+                "provider=%s base_url=%s",
+                model, self.context_length, self.threshold_tokens,
+                threshold_percent * 100, self.summary_target_ratio * 100,
+                self.tail_token_budget,
+                provider or "none", base_url or "none",
+            )
         self._context_probed = False  # True after a step-down from context error
 
         self.last_prompt_tokens = 0
         self.last_completion_tokens = 0
         self.last_total_tokens = 0
 
-        self.client, default_model = get_text_auxiliary_client("compression")
-        self.summary_model = summary_model_override or default_model
+        self.summary_model = summary_model_override or ""
+
+        # Stores the previous compaction summary for iterative updates
+        self._previous_summary: Optional[str] = None
 
     def update_from_response(self, usage: Dict[str, Any]):
         """Update tracked token usage from API response."""
@@ -78,126 +141,242 @@ 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,
         }
 
-    def _generate_summary(self, turns_to_summarize: List[Dict[str, Any]]) -> Optional[str]:
-        """Generate a concise summary of conversation turns.
+    # ------------------------------------------------------------------
+    # Tool output pruning (cheap pre-pass, no LLM call)
+    # ------------------------------------------------------------------
 
-        Tries the auxiliary model first, then falls back to the user's main
-        model.  Returns None if all attempts fail — the caller should drop
+    def _prune_old_tool_results(
+        self, messages: List[Dict[str, Any]], protect_tail_count: int,
+    ) -> tuple[List[Dict[str, Any]], int]:
+        """Replace old tool result contents with a short placeholder.
+
+        Walks backward from the end, protecting the most recent
+        ``protect_tail_count`` messages. Older tool results get their
+        content replaced with a placeholder string.
+
+        Returns (pruned_messages, pruned_count).
+        """
+        if not messages:
+            return messages, 0
+
+        result = [m.copy() for m in messages]
+        pruned = 0
+        prune_boundary = len(result) - protect_tail_count
+
+        for i in range(prune_boundary):
+            msg = result[i]
+            if msg.get("role") != "tool":
+                continue
+            content = msg.get("content", "")
+            if not content or content == _PRUNED_TOOL_PLACEHOLDER:
+                continue
+            # Only prune if the content is substantial (>200 chars)
+            if len(content) > 200:
+                result[i] = {**msg, "content": _PRUNED_TOOL_PLACEHOLDER}
+                pruned += 1
+
+        return result, pruned
+
+    # ------------------------------------------------------------------
+    # Summarization
+    # ------------------------------------------------------------------
+
+    def _compute_summary_budget(self, turns_to_summarize: List[Dict[str, Any]]) -> int:
+        """Scale summary token budget with the amount of content being compressed.
+
+        The maximum scales with the model's context window (5% of context,
+        capped at ``_SUMMARY_TOKENS_CEILING``) so large-context models get
+        richer summaries instead of being hard-capped at 8K tokens.
+        """
+        content_tokens = estimate_messages_tokens_rough(turns_to_summarize)
+        budget = int(content_tokens * _SUMMARY_RATIO)
+        return max(_MIN_SUMMARY_TOKENS, min(budget, self.max_summary_tokens))
+
+    def _serialize_for_summary(self, turns: List[Dict[str, Any]]) -> str:
+        """Serialize conversation turns into labeled text for the summarizer.
+
+        Includes tool call arguments and result content (up to 3000 chars
+        per message) so the summarizer can preserve specific details like
+        file paths, commands, and outputs.
+        """
+        parts = []
+        for msg in turns:
+            role = msg.get("role", "unknown")
+            content = msg.get("content") or ""
+
+            # Tool results: keep more content than before (3000 chars)
+            if role == "tool":
+                tool_id = msg.get("tool_call_id", "")
+                if len(content) > 3000:
+                    content = content[:2000] + "\n...[truncated]...\n" + content[-800:]
+                parts.append(f"[TOOL RESULT {tool_id}]: {content}")
+                continue
+
+            # Assistant messages: include tool call names AND arguments
+            if role == "assistant":
+                if len(content) > 3000:
+                    content = content[:2000] + "\n...[truncated]...\n" + content[-800:]
+                tool_calls = msg.get("tool_calls", [])
+                if tool_calls:
+                    tc_parts = []
+                    for tc in tool_calls:
+                        if isinstance(tc, dict):
+                            fn = tc.get("function", {})
+                            name = fn.get("name", "?")
+                            args = fn.get("arguments", "")
+                            # Truncate long arguments but keep enough for context
+                            if len(args) > 500:
+                                args = args[:400] + "..."
+                            tc_parts.append(f"  {name}({args})")
+                        else:
+                            fn = getattr(tc, "function", None)
+                            name = getattr(fn, "name", "?") if fn else "?"
+                            tc_parts.append(f"  {name}(...)")
+                    content += "\n[Tool calls:\n" + "\n".join(tc_parts) + "\n]"
+                parts.append(f"[ASSISTANT]: {content}")
+                continue
+
+            # User and other roles
+            if len(content) > 3000:
+                content = content[:2000] + "\n...[truncated]...\n" + content[-800:]
+            parts.append(f"[{role.upper()}]: {content}")
+
+        return "\n\n".join(parts)
+
+    def _generate_summary(self, turns_to_summarize: List[Dict[str, Any]]) -> Optional[str]:
+        """Generate a structured summary of conversation turns.
+
+        Uses a structured template (Goal, Progress, Decisions, Files, Next Steps)
+        inspired by Pi-mono and OpenCode. When a previous summary exists,
+        generates an iterative update instead of summarizing from scratch.
+
+        Returns None if all attempts fail — the caller should drop
         the middle turns without a summary rather than inject a useless
         placeholder.
         """
-        parts = []
-        for msg in turns_to_summarize:
-            role = msg.get("role", "unknown")
-            content = msg.get("content") or ""
-            if len(content) > 2000:
-                content = content[:1000] + "\n...[truncated]...\n" + content[-500:]
-            tool_calls = msg.get("tool_calls", [])
-            if tool_calls:
-                tool_names = [tc.get("function", {}).get("name", "?") for tc in tool_calls if isinstance(tc, dict)]
-                content += f"\n[Tool calls: {', '.join(tool_names)}]"
-            parts.append(f"[{role.upper()}]: {content}")
+        summary_budget = self._compute_summary_budget(turns_to_summarize)
+        content_to_summarize = self._serialize_for_summary(turns_to_summarize)
 
-        content_to_summarize = "\n\n".join(parts)
-        prompt = f"""Summarize these conversation turns concisely. This summary will replace these turns in the conversation history.
+        if self._previous_summary:
+            # Iterative update: preserve existing info, add new progress
+            prompt = f"""You are updating a context compaction summary. A previous compaction produced the summary below. New conversation turns have occurred since then and need to be incorporated.
 
-Write from a neutral perspective describing:
-1. What actions were taken (tool calls, searches, file operations)
-2. Key information or results obtained
-3. Important decisions or findings
-4. Relevant data, file names, or outputs
+PREVIOUS SUMMARY:
+{self._previous_summary}
 
-Keep factual and informative. Target ~{self.summary_target_tokens} tokens.
+NEW TURNS TO INCORPORATE:
+{content_to_summarize}
+
+Update the summary using this exact structure. PRESERVE all existing information that is still relevant. ADD new progress. Move items from "In Progress" to "Done" when completed. Remove information only if it is clearly obsolete.
+
+## Goal
+[What the user is trying to accomplish — preserve from previous summary, update if goal evolved]
+
+## Constraints & Preferences
+[User preferences, coding style, constraints, important decisions — accumulate across compactions]
+
+## Progress
+### Done
+[Completed work — include specific file paths, commands run, results obtained]
+### In Progress
+[Work currently underway]
+### Blocked
+[Any blockers or issues encountered]
+
+## Key Decisions
+[Important technical decisions and why they were made]
+
+## Relevant Files
+[Files read, modified, or created — with brief note on each. Accumulate across compactions.]
+
+## Next Steps
+[What needs to happen next to continue the work]
+
+## Critical Context
+[Any specific values, error messages, configuration details, or data that would be lost without explicit preservation]
+
+Target ~{summary_budget} tokens. Be specific — include file paths, command outputs, error messages, and concrete values rather than vague descriptions.
+
+Write only the summary body. Do not include any preamble or prefix."""
+        else:
+            # First compaction: summarize from scratch
+            prompt = f"""Create a structured handoff summary for a later assistant that will continue this conversation after earlier turns are compacted.
 
----
 TURNS TO SUMMARIZE:
 {content_to_summarize}
----
 
-Write only the summary, starting with "[CONTEXT SUMMARY]:" prefix."""
+Use this exact structure:
 
-        # 1. Try the auxiliary model (cheap/fast)
-        if self.client:
-            try:
-                return self._call_summary_model(self.client, self.summary_model, prompt)
-            except Exception as e:
-                logging.warning(f"Failed to generate context summary with auxiliary model: {e}")
+## Goal
+[What the user is trying to accomplish]
 
-        # 2. Fallback: try the user's main model endpoint
-        fallback_client, fallback_model = self._get_fallback_client()
-        if fallback_client is not None:
-            try:
-                logger.info("Retrying context summary with main model (%s)", fallback_model)
-                summary = self._call_summary_model(fallback_client, fallback_model, prompt)
-                self.client = fallback_client
-                self.summary_model = fallback_model
-                return summary
-            except Exception as fallback_err:
-                logging.warning(f"Main model summary also failed: {fallback_err}")
+## Constraints & Preferences
+[User preferences, coding style, constraints, important decisions]
 
-        # 3. All models failed — return None so the caller drops turns without a summary
-        logging.warning("Context compression: no model available for summary. Middle turns will be dropped without summary.")
-        return None
+## Progress
+### Done
+[Completed work — include specific file paths, commands run, results obtained]
+### In Progress
+[Work currently underway]
+### Blocked
+[Any blockers or issues encountered]
+
+## Key Decisions
+[Important technical decisions and why they were made]
+
+## Relevant Files
+[Files read, modified, or created — with brief note on each]
+
+## Next Steps
+[What needs to happen next to continue the work]
+
+## Critical Context
+[Any specific values, error messages, configuration details, or data that would be lost without explicit preservation]
+
+Target ~{summary_budget} tokens. Be specific — include file paths, command outputs, error messages, and concrete values rather than vague descriptions. The goal is to prevent the next assistant from repeating work or losing important details.
+
+Write only the summary body. Do not include any preamble or prefix."""
 
-    def _call_summary_model(self, client, model: str, prompt: str) -> str:
-        """Make the actual LLM call to generate a summary. Raises on failure."""
-        kwargs = {
-            "model": model,
-            "messages": [{"role": "user", "content": prompt}],
-            "temperature": 0.3,
-            "timeout": 30.0,
-        }
-        # Most providers (OpenRouter, local models) use max_tokens.
-        # Direct OpenAI with newer models (gpt-4o, o-series, gpt-5+)
-        # requires max_completion_tokens instead.
         try:
-            kwargs["max_tokens"] = self.summary_target_tokens * 2
-            response = client.chat.completions.create(**kwargs)
-        except Exception as first_err:
-            if "max_tokens" in str(first_err) or "unsupported_parameter" in str(first_err):
-                kwargs.pop("max_tokens", None)
-                kwargs["max_completion_tokens"] = self.summary_target_tokens * 2
-                response = client.chat.completions.create(**kwargs)
-            else:
-                raise
+            call_kwargs = {
+                "task": "compression",
+                "messages": [{"role": "user", "content": prompt}],
+                "temperature": 0.3,
+                "max_tokens": summary_budget * 2,
+                # timeout resolved from auxiliary.compression.timeout config by call_llm
+            }
+            if self.summary_model:
+                call_kwargs["model"] = self.summary_model
+            response = call_llm(**call_kwargs)
+            content = response.choices[0].message.content
+            # Handle cases where content is not a string (e.g., dict from llama.cpp)
+            if not isinstance(content, str):
+                content = str(content) if content else ""
+            summary = content.strip()
+            # Store for iterative updates on next compaction
+            self._previous_summary = summary
+            return self._with_summary_prefix(summary)
+        except RuntimeError:
+            logging.warning("Context compression: no provider available for "
+                            "summary. Middle turns will be dropped without summary.")
+            return None
+        except Exception as e:
+            logging.warning("Failed to generate context summary: %s", e)
+            return None
 
-        summary = response.choices[0].message.content.strip()
-        if not summary.startswith("[CONTEXT SUMMARY]:"):
-            summary = "[CONTEXT SUMMARY]: " + summary
-        return summary
-
-    def _get_fallback_client(self):
-        """Try to build a fallback client from the main model's endpoint config.
-
-        When the primary auxiliary client fails (e.g. stale OpenRouter key), this
-        creates a client using the user's active custom endpoint (OPENAI_BASE_URL)
-        so compression can still produce a real summary instead of a static string.
-
-        Returns (client, model) or (None, None).
-        """
-        custom_base = os.getenv("OPENAI_BASE_URL")
-        custom_key = os.getenv("OPENAI_API_KEY")
-        if not custom_base or not custom_key:
-            return None, None
-
-        # Don't fallback to the same provider that just failed
-        from hermes_constants import OPENROUTER_BASE_URL
-        if custom_base.rstrip("/") == OPENROUTER_BASE_URL.rstrip("/"):
-            return None, None
-
-        model = os.getenv("LLM_MODEL") or os.getenv("OPENAI_MODEL") or self.model
-        try:
-            from openai import OpenAI as _OpenAI
-            client = _OpenAI(api_key=custom_key, base_url=custom_base)
-            logger.debug("Built fallback auxiliary client: %s via %s", model, custom_base)
-            return client, model
-        except Exception as exc:
-            logger.debug("Could not build fallback auxiliary client: %s", exc)
-            return None, None
+    @staticmethod
+    def _with_summary_prefix(summary: str) -> str:
+        """Normalize summary text to the current compaction handoff format."""
+        text = (summary or "").strip()
+        for prefix in (LEGACY_SUMMARY_PREFIX, SUMMARY_PREFIX):
+            if text.startswith(prefix):
+                text = text[len(prefix):].lstrip()
+                break
+        return f"{SUMMARY_PREFIX}\n{text}" if text else SUMMARY_PREFIX
 
     # ------------------------------------------------------------------
     # Tool-call / tool-result pair integrity helpers
@@ -284,73 +463,200 @@ Write only the summary, starting with "[CONTEXT SUMMARY]:" prefix."""
         """Pull a compress-end boundary backward to avoid splitting a
         tool_call / result group.
 
-        If the message just before ``idx`` is an assistant message with
-        tool_calls, those tool results will start at ``idx`` and would be
-        separated from their parent.  Move backwards to include the whole
-        group in the summarised region.
+        If the boundary falls in the middle of a tool-result group (i.e.
+        there are consecutive tool messages before ``idx``), walk backward
+        past all of them to find the parent assistant message.  If found,
+        move the boundary before the assistant so the entire
+        assistant + tool_results group is included in the summarised region
+        rather than being split (which causes silent data loss when
+        ``_sanitize_tool_pairs`` removes the orphaned tail results).
         """
         if idx <= 0 or idx >= len(messages):
             return idx
-        prev = messages[idx - 1]
-        if prev.get("role") == "assistant" and prev.get("tool_calls"):
-            # The results for this assistant turn sit at idx..idx+k.
-            # Include the assistant message in the summarised region too.
-            idx -= 1
+        # Walk backward past consecutive tool results
+        check = idx - 1
+        while check >= 0 and messages[check].get("role") == "tool":
+            check -= 1
+        # If we landed on the parent assistant with tool_calls, pull the
+        # boundary before it so the whole group gets summarised together.
+        if check >= 0 and messages[check].get("role") == "assistant" and messages[check].get("tool_calls"):
+            idx = check
         return idx
 
+    # ------------------------------------------------------------------
+    # Tail protection by token budget
+    # ------------------------------------------------------------------
+
+    def _find_tail_cut_by_tokens(
+        self, messages: List[Dict[str, Any]], head_end: int,
+        token_budget: int | None = None,
+    ) -> int:
+        """Walk backward from the end of messages, accumulating tokens until
+        the budget is reached. Returns the index where the tail starts.
+
+        ``token_budget`` defaults to ``self.tail_token_budget`` which is
+        derived from ``summary_target_ratio * context_length``, so it
+        scales automatically with the model's context window.
+
+        Never cuts inside a tool_call/result group. Falls back to the old
+        ``protect_last_n`` if the budget would protect fewer messages.
+        """
+        if token_budget is None:
+            token_budget = self.tail_token_budget
+        n = len(messages)
+        min_tail = self.protect_last_n
+        accumulated = 0
+        cut_idx = n  # start from beyond the end
+
+        for i in range(n - 1, head_end - 1, -1):
+            msg = messages[i]
+            content = msg.get("content") or ""
+            msg_tokens = len(content) // _CHARS_PER_TOKEN + 10  # +10 for role/metadata
+            # Include tool call arguments in estimate
+            for tc in msg.get("tool_calls") or []:
+                if isinstance(tc, dict):
+                    args = tc.get("function", {}).get("arguments", "")
+                    msg_tokens += len(args) // _CHARS_PER_TOKEN
+            if accumulated + msg_tokens > token_budget and (n - i) >= min_tail:
+                break
+            accumulated += msg_tokens
+            cut_idx = i
+
+        # Ensure we protect at least protect_last_n messages
+        fallback_cut = n - min_tail
+        if cut_idx > fallback_cut:
+            cut_idx = fallback_cut
+
+        # If the token budget would protect everything (small conversations),
+        # fall back to the fixed protect_last_n approach so compression can
+        # still remove middle turns.
+        if cut_idx <= head_end:
+            cut_idx = fallback_cut
+
+        # Align to avoid splitting tool groups
+        cut_idx = self._align_boundary_backward(messages, cut_idx)
+
+        return max(cut_idx, head_end + 1)
+
+    # ------------------------------------------------------------------
+    # Main compression entry point
+    # ------------------------------------------------------------------
+
     def compress(self, messages: List[Dict[str, Any]], current_tokens: int = None) -> List[Dict[str, Any]]:
         """Compress conversation messages by summarizing middle turns.
 
-        Keeps first N + last N turns, summarizes everything in between.
+        Algorithm:
+          1. Prune old tool results (cheap pre-pass, no LLM call)
+          2. Protect head messages (system prompt + first exchange)
+          3. Find tail boundary by token budget (~20K tokens of recent context)
+          4. Summarize middle turns with structured LLM prompt
+          5. On re-compression, iteratively update the previous summary
+
         After compression, orphaned tool_call / tool_result pairs are cleaned
         up so the API never receives mismatched IDs.
         """
         n_messages = len(messages)
         if n_messages <= self.protect_first_n + self.protect_last_n + 1:
             if not self.quiet_mode:
-                print(f"⚠️  Cannot compress: only {n_messages} messages (need > {self.protect_first_n + self.protect_last_n + 1})")
+                logger.warning(
+                    "Cannot compress: only %d messages (need > %d)",
+                    n_messages,
+                    self.protect_first_n + self.protect_last_n + 1,
+                )
             return messages
 
+        display_tokens = current_tokens if current_tokens else self.last_prompt_tokens or estimate_messages_tokens_rough(messages)
+
+        # Phase 1: Prune old tool results (cheap, no LLM call)
+        messages, pruned_count = self._prune_old_tool_results(
+            messages, protect_tail_count=self.protect_last_n * 3,
+        )
+        if pruned_count and not self.quiet_mode:
+            logger.info("Pre-compression: pruned %d old tool result(s)", pruned_count)
+
+        # Phase 2: Determine boundaries
         compress_start = self.protect_first_n
-        compress_end = n_messages - self.protect_last_n
-        if compress_start >= compress_end:
-            return messages
-
-        # Adjust boundaries to avoid splitting tool_call/result groups.
         compress_start = self._align_boundary_forward(messages, compress_start)
-        compress_end = self._align_boundary_backward(messages, compress_end)
+
+        # Use token-budget tail protection instead of fixed message count
+        compress_end = self._find_tail_cut_by_tokens(messages, compress_start)
+
         if compress_start >= compress_end:
             return messages
 
         turns_to_summarize = messages[compress_start:compress_end]
-        display_tokens = current_tokens if current_tokens else self.last_prompt_tokens or estimate_messages_tokens_rough(messages)
 
         if not self.quiet_mode:
-            print(f"\n📦 Context compression triggered ({display_tokens:,} tokens ≥ {self.threshold_tokens:,} threshold)")
-            print(f"   📊 Model context limit: {self.context_length:,} tokens ({self.threshold_percent*100:.0f}% = {self.threshold_tokens:,})")
-
-        if not self.quiet_mode:
-            print(f"   🗜️  Summarizing turns {compress_start+1}-{compress_end} ({len(turns_to_summarize)} turns)")
+            logger.info(
+                "Context compression triggered (%d tokens >= %d threshold)",
+                display_tokens,
+                self.threshold_tokens,
+            )
+            logger.info(
+                "Model context limit: %d tokens (%.0f%% = %d)",
+                self.context_length,
+                self.threshold_percent * 100,
+                self.threshold_tokens,
+            )
+            tail_msgs = n_messages - compress_end
+            logger.info(
+                "Summarizing turns %d-%d (%d turns), protecting %d head + %d tail messages",
+                compress_start + 1,
+                compress_end,
+                len(turns_to_summarize),
+                compress_start,
+                tail_msgs,
+            )
 
+        # Phase 3: Generate structured summary
         summary = self._generate_summary(turns_to_summarize)
 
+        # Phase 4: Assemble compressed message list
         compressed = []
         for i in range(compress_start):
             msg = messages[i].copy()
             if i == 0 and msg.get("role") == "system" and self.compression_count == 0:
-                msg["content"] = (msg.get("content") or "") + "\n\n[Note: Some earlier conversation turns may be summarized to preserve context space.]"
+                msg["content"] = (
+                    (msg.get("content") or "")
+                    + "\n\n[Note: Some earlier conversation turns have been compacted into a handoff summary to preserve context space. The current session state may still reflect earlier work, so build on that summary and state rather than re-doing work.]"
+                )
             compressed.append(msg)
 
+        _merge_summary_into_tail = False
         if summary:
             last_head_role = messages[compress_start - 1].get("role", "user") if compress_start > 0 else "user"
-            summary_role = "user" if last_head_role in ("assistant", "tool") else "assistant"
-            compressed.append({"role": summary_role, "content": summary})
+            first_tail_role = messages[compress_end].get("role", "user") if compress_end < n_messages else "user"
+            # Pick a role that avoids consecutive same-role with both neighbors.
+            # Priority: avoid colliding with head (already committed), then tail.
+            if last_head_role in ("assistant", "tool"):
+                summary_role = "user"
+            else:
+                summary_role = "assistant"
+            # If the chosen role collides with the tail AND flipping wouldn't
+            # collide with the head, flip it.
+            if summary_role == first_tail_role:
+                flipped = "assistant" if summary_role == "user" else "user"
+                if flipped != last_head_role:
+                    summary_role = flipped
+                else:
+                    # Both roles would create consecutive same-role messages
+                    # (e.g. head=assistant, tail=user — neither role works).
+                    # Merge the summary into the first tail message instead
+                    # of inserting a standalone message that breaks alternation.
+                    _merge_summary_into_tail = True
+            if not _merge_summary_into_tail:
+                compressed.append({"role": summary_role, "content": summary})
         else:
             if not self.quiet_mode:
-                print("   ⚠️  No summary model available — middle turns dropped without summary")
+                logger.warning("No summary model available — middle turns dropped without summary")
 
         for i in range(compress_end, n_messages):
-            compressed.append(messages[i].copy())
+            msg = messages[i].copy()
+            if _merge_summary_into_tail and i == compress_end:
+                original = msg.get("content") or ""
+                msg["content"] = summary + "\n\n" + original
+                _merge_summary_into_tail = False
+            compressed.append(msg)
 
         self.compression_count += 1
 
@@ -359,7 +665,12 @@ Write only the summary, starting with "[CONTEXT SUMMARY]:" prefix."""
         if not self.quiet_mode:
             new_estimate = estimate_messages_tokens_rough(compressed)
             saved_estimate = display_tokens - new_estimate
-            print(f"   ✅ Compressed: {n_messages} → {len(compressed)} messages (~{saved_estimate:,} tokens saved)")
-            print(f"   💡 Compression #{self.compression_count} complete")
+            logger.info(
+                "Compressed: %d -> %d messages (~%d tokens saved)",
+                n_messages,
+                len(compressed),
+                saved_estimate,
+            )
+            logger.info("Compression #%d complete", self.compression_count)
 
         return compressed

agent/context_references.py

@@ -0,0 +1,492 @@
+from __future__ import annotations
+
+import asyncio
+import inspect
+import json
+import mimetypes
+import os
+import re
+import subprocess
+from dataclasses import dataclass, field
+from pathlib import Path
+from typing import Awaitable, Callable
+
+from agent.model_metadata import estimate_tokens_rough
+
+REFERENCE_PATTERN = re.compile(
+    r"(?<![\w/])@(?:(?P<simple>diff|staged)\b|(?P<kind>file|folder|git|url):(?P<value>\S+))"
+)
+TRAILING_PUNCTUATION = ",.;!?"
+_SENSITIVE_HOME_DIRS = (".ssh", ".aws", ".gnupg", ".kube")
+_SENSITIVE_HERMES_DIRS = (Path("skills") / ".hub",)
+_SENSITIVE_HOME_FILES = (
+    Path(".ssh") / "authorized_keys",
+    Path(".ssh") / "id_rsa",
+    Path(".ssh") / "id_ed25519",
+    Path(".ssh") / "config",
+    Path(".bashrc"),
+    Path(".zshrc"),
+    Path(".profile"),
+    Path(".bash_profile"),
+    Path(".zprofile"),
+    Path(".netrc"),
+    Path(".pgpass"),
+    Path(".npmrc"),
+    Path(".pypirc"),
+)
+
+
+@dataclass(frozen=True)
+class ContextReference:
+    raw: str
+    kind: str
+    target: str
+    start: int
+    end: int
+    line_start: int | None = None
+    line_end: int | None = None
+
+
+@dataclass
+class ContextReferenceResult:
+    message: str
+    original_message: str
+    references: list[ContextReference] = field(default_factory=list)
+    warnings: list[str] = field(default_factory=list)
+    injected_tokens: int = 0
+    expanded: bool = False
+    blocked: bool = False
+
+
+def parse_context_references(message: str) -> list[ContextReference]:
+    refs: list[ContextReference] = []
+    if not message:
+        return refs
+
+    for match in REFERENCE_PATTERN.finditer(message):
+        simple = match.group("simple")
+        if simple:
+            refs.append(
+                ContextReference(
+                    raw=match.group(0),
+                    kind=simple,
+                    target="",
+                    start=match.start(),
+                    end=match.end(),
+                )
+            )
+            continue
+
+        kind = match.group("kind")
+        value = _strip_trailing_punctuation(match.group("value") or "")
+        line_start = None
+        line_end = None
+        target = value
+
+        if kind == "file":
+            range_match = re.match(r"^(?P<path>.+?):(?P<start>\d+)(?:-(?P<end>\d+))?$", value)
+            if range_match:
+                target = range_match.group("path")
+                line_start = int(range_match.group("start"))
+                line_end = int(range_match.group("end") or range_match.group("start"))
+
+        refs.append(
+            ContextReference(
+                raw=match.group(0),
+                kind=kind,
+                target=target,
+                start=match.start(),
+                end=match.end(),
+                line_start=line_start,
+                line_end=line_end,
+            )
+        )
+
+    return refs
+
+
+def preprocess_context_references(
+    message: str,
+    *,
+    cwd: str | Path,
+    context_length: int,
+    url_fetcher: Callable[[str], str | Awaitable[str]] | None = None,
+    allowed_root: str | Path | None = None,
+) -> ContextReferenceResult:
+    coro = preprocess_context_references_async(
+        message,
+        cwd=cwd,
+        context_length=context_length,
+        url_fetcher=url_fetcher,
+        allowed_root=allowed_root,
+    )
+    # Safe for both CLI (no loop) and gateway (loop already running).
+    try:
+        loop = asyncio.get_running_loop()
+    except RuntimeError:
+        loop = None
+    if loop and loop.is_running():
+        import concurrent.futures
+        with concurrent.futures.ThreadPoolExecutor(max_workers=1) as pool:
+            return pool.submit(asyncio.run, coro).result()
+    return asyncio.run(coro)
+
+
+async def preprocess_context_references_async(
+    message: str,
+    *,
+    cwd: str | Path,
+    context_length: int,
+    url_fetcher: Callable[[str], str | Awaitable[str]] | None = None,
+    allowed_root: str | Path | None = None,
+) -> ContextReferenceResult:
+    refs = parse_context_references(message)
+    if not refs:
+        return ContextReferenceResult(message=message, original_message=message)
+
+    cwd_path = Path(cwd).expanduser().resolve()
+    # Default to the current working directory so @ references cannot escape
+    # the active workspace unless a caller explicitly widens the root.
+    allowed_root_path = (
+        Path(allowed_root).expanduser().resolve() if allowed_root is not None else cwd_path
+    )
+    warnings: list[str] = []
+    blocks: list[str] = []
+    injected_tokens = 0
+
+    for ref in refs:
+        warning, block = await _expand_reference(
+            ref,
+            cwd_path,
+            url_fetcher=url_fetcher,
+            allowed_root=allowed_root_path,
+        )
+        if warning:
+            warnings.append(warning)
+        if block:
+            blocks.append(block)
+            injected_tokens += estimate_tokens_rough(block)
+
+    hard_limit = max(1, int(context_length * 0.50))
+    soft_limit = max(1, int(context_length * 0.25))
+    if injected_tokens > hard_limit:
+        warnings.append(
+            f"@ context injection refused: {injected_tokens} tokens exceeds the 50% hard limit ({hard_limit})."
+        )
+        return ContextReferenceResult(
+            message=message,
+            original_message=message,
+            references=refs,
+            warnings=warnings,
+            injected_tokens=injected_tokens,
+            expanded=False,
+            blocked=True,
+        )
+
+    if injected_tokens > soft_limit:
+        warnings.append(
+            f"@ context injection warning: {injected_tokens} tokens exceeds the 25% soft limit ({soft_limit})."
+        )
+
+    stripped = _remove_reference_tokens(message, refs)
+    final = stripped
+    if warnings:
+        final = f"{final}\n\n--- Context Warnings ---\n" + "\n".join(f"- {warning}" for warning in warnings)
+    if blocks:
+        final = f"{final}\n\n--- Attached Context ---\n\n" + "\n\n".join(blocks)
+
+    return ContextReferenceResult(
+        message=final.strip(),
+        original_message=message,
+        references=refs,
+        warnings=warnings,
+        injected_tokens=injected_tokens,
+        expanded=bool(blocks or warnings),
+        blocked=False,
+    )
+
+
+async def _expand_reference(
+    ref: ContextReference,
+    cwd: Path,
+    *,
+    url_fetcher: Callable[[str], str | Awaitable[str]] | None = None,
+    allowed_root: Path | None = None,
+) -> tuple[str | None, str | None]:
+    try:
+        if ref.kind == "file":
+            return _expand_file_reference(ref, cwd, allowed_root=allowed_root)
+        if ref.kind == "folder":
+            return _expand_folder_reference(ref, cwd, allowed_root=allowed_root)
+        if ref.kind == "diff":
+            return _expand_git_reference(ref, cwd, ["diff"], "git diff")
+        if ref.kind == "staged":
+            return _expand_git_reference(ref, cwd, ["diff", "--staged"], "git diff --staged")
+        if ref.kind == "git":
+            count = max(1, min(int(ref.target or "1"), 10))
+            return _expand_git_reference(ref, cwd, ["log", f"-{count}", "-p"], f"git log -{count} -p")
+        if ref.kind == "url":
+            content = await _fetch_url_content(ref.target, url_fetcher=url_fetcher)
+            if not content:
+                return f"{ref.raw}: no content extracted", None
+            return None, f"🌐 {ref.raw} ({estimate_tokens_rough(content)} tokens)\n{content}"
+    except Exception as exc:
+        return f"{ref.raw}: {exc}", None
+
+    return f"{ref.raw}: unsupported reference type", None
+
+
+def _expand_file_reference(
+    ref: ContextReference,
+    cwd: Path,
+    *,
+    allowed_root: Path | None = None,
+) -> tuple[str | None, str | None]:
+    path = _resolve_path(cwd, ref.target, allowed_root=allowed_root)
+    _ensure_reference_path_allowed(path)
+    if not path.exists():
+        return f"{ref.raw}: file not found", None
+    if not path.is_file():
+        return f"{ref.raw}: path is not a file", None
+    if _is_binary_file(path):
+        return f"{ref.raw}: binary files are not supported", None
+
+    text = path.read_text(encoding="utf-8")
+    if ref.line_start is not None:
+        lines = text.splitlines()
+        start_idx = max(ref.line_start - 1, 0)
+        end_idx = min(ref.line_end or ref.line_start, len(lines))
+        text = "\n".join(lines[start_idx:end_idx])
+
+    lang = _code_fence_language(path)
+    label = ref.raw
+    return None, f"📄 {label} ({estimate_tokens_rough(text)} tokens)\n```{lang}\n{text}\n```"
+
+
+def _expand_folder_reference(
+    ref: ContextReference,
+    cwd: Path,
+    *,
+    allowed_root: Path | None = None,
+) -> tuple[str | None, str | None]:
+    path = _resolve_path(cwd, ref.target, allowed_root=allowed_root)
+    _ensure_reference_path_allowed(path)
+    if not path.exists():
+        return f"{ref.raw}: folder not found", None
+    if not path.is_dir():
+        return f"{ref.raw}: path is not a folder", None
+
+    listing = _build_folder_listing(path, cwd)
+    return None, f"📁 {ref.raw} ({estimate_tokens_rough(listing)} tokens)\n{listing}"
+
+
+def _expand_git_reference(
+    ref: ContextReference,
+    cwd: Path,
+    args: list[str],
+    label: str,
+) -> tuple[str | None, str | None]:
+    try:
+        result = subprocess.run(
+            ["git", *args],
+            cwd=cwd,
+            capture_output=True,
+            text=True,
+            timeout=30,
+        )
+    except subprocess.TimeoutExpired:
+        return f"{ref.raw}: git command timed out (30s)", None
+    if result.returncode != 0:
+        stderr = (result.stderr or "").strip() or "git command failed"
+        return f"{ref.raw}: {stderr}", None
+    content = result.stdout.strip()
+    if not content:
+        content = "(no output)"
+    return None, f"🧾 {label} ({estimate_tokens_rough(content)} tokens)\n```diff\n{content}\n```"
+
+
+async def _fetch_url_content(
+    url: str,
+    *,
+    url_fetcher: Callable[[str], str | Awaitable[str]] | None = None,
+) -> str:
+    fetcher = url_fetcher or _default_url_fetcher
+    content = fetcher(url)
+    if inspect.isawaitable(content):
+        content = await content
+    return str(content or "").strip()
+
+
+async def _default_url_fetcher(url: str) -> str:
+    from tools.web_tools import web_extract_tool
+
+    raw = await web_extract_tool([url], format="markdown", use_llm_processing=True)
+    payload = json.loads(raw)
+    docs = payload.get("data", {}).get("documents", [])
+    if not docs:
+        return ""
+    doc = docs[0]
+    return str(doc.get("content") or doc.get("raw_content") or "").strip()
+
+
+def _resolve_path(cwd: Path, target: str, *, allowed_root: Path | None = None) -> Path:
+    path = Path(os.path.expanduser(target))
+    if not path.is_absolute():
+        path = cwd / path
+    resolved = path.resolve()
+    if allowed_root is not None:
+        try:
+            resolved.relative_to(allowed_root)
+        except ValueError as exc:
+            raise ValueError("path is outside the allowed workspace") from exc
+    return resolved
+
+
+def _ensure_reference_path_allowed(path: Path) -> None:
+    home = Path(os.path.expanduser("~")).resolve()
+    hermes_home = Path(
+        os.getenv("HERMES_HOME", str(home / ".hermes"))
+    ).expanduser().resolve()
+
+    blocked_exact = {home / rel for rel in _SENSITIVE_HOME_FILES}
+    blocked_exact.add(hermes_home / ".env")
+    blocked_dirs = [home / rel for rel in _SENSITIVE_HOME_DIRS]
+    blocked_dirs.extend(hermes_home / rel for rel in _SENSITIVE_HERMES_DIRS)
+
+    if path in blocked_exact:
+        raise ValueError("path is a sensitive credential file and cannot be attached")
+
+    for blocked_dir in blocked_dirs:
+        try:
+            path.relative_to(blocked_dir)
+        except ValueError:
+            continue
+        raise ValueError("path is a sensitive credential or internal Hermes path and cannot be attached")
+
+
+def _strip_trailing_punctuation(value: str) -> str:
+    stripped = value.rstrip(TRAILING_PUNCTUATION)
+    while stripped.endswith((")", "]", "}")):
+        closer = stripped[-1]
+        opener = {")": "(", "]": "[", "}": "{"}[closer]
+        if stripped.count(closer) > stripped.count(opener):
+            stripped = stripped[:-1]
+            continue
+        break
+    return stripped
+
+
+def _remove_reference_tokens(message: str, refs: list[ContextReference]) -> str:
+    pieces: list[str] = []
+    cursor = 0
+    for ref in refs:
+        pieces.append(message[cursor:ref.start])
+        cursor = ref.end
+    pieces.append(message[cursor:])
+    text = "".join(pieces)
+    text = re.sub(r"\s{2,}", " ", text)
+    text = re.sub(r"\s+([,.;:!?])", r"\1", text)
+    return text.strip()
+
+
+def _is_binary_file(path: Path) -> bool:
+    mime, _ = mimetypes.guess_type(path.name)
+    if mime and not mime.startswith("text/") and not any(
+        path.name.endswith(ext) for ext in (".py", ".md", ".txt", ".json", ".yaml", ".yml", ".toml", ".js", ".ts")
+    ):
+        return True
+    chunk = path.read_bytes()[:4096]
+    return b"\x00" in chunk
+
+
+def _build_folder_listing(path: Path, cwd: Path, limit: int = 200) -> str:
+    lines = [f"{path.relative_to(cwd)}/"]
+    entries = _iter_visible_entries(path, cwd, limit=limit)
+    for entry in entries:
+        rel = entry.relative_to(cwd)
+        indent = "  " * max(len(rel.parts) - len(path.relative_to(cwd).parts) - 1, 0)
+        if entry.is_dir():
+            lines.append(f"{indent}- {entry.name}/")
+        else:
+            meta = _file_metadata(entry)
+            lines.append(f"{indent}- {entry.name} ({meta})")
+    if len(entries) >= limit:
+        lines.append("- ...")
+    return "\n".join(lines)
+
+
+def _iter_visible_entries(path: Path, cwd: Path, limit: int) -> list[Path]:
+    rg_entries = _rg_files(path, cwd, limit=limit)
+    if rg_entries is not None:
+        output: list[Path] = []
+        seen_dirs: set[Path] = set()
+        for rel in rg_entries:
+            full = cwd / rel
+            for parent in full.parents:
+                if parent == cwd or parent in seen_dirs or path not in {parent, *parent.parents}:
+                    continue
+                seen_dirs.add(parent)
+                output.append(parent)
+            output.append(full)
+        return sorted({p for p in output if p.exists()}, key=lambda p: (not p.is_dir(), str(p)))
+
+    output = []
+    for root, dirs, files in os.walk(path):
+        dirs[:] = sorted(d for d in dirs if not d.startswith(".") and d != "__pycache__")
+        files = sorted(f for f in files if not f.startswith("."))
+        root_path = Path(root)
+        for d in dirs:
+            output.append(root_path / d)
+            if len(output) >= limit:
+                return output
+        for f in files:
+            output.append(root_path / f)
+            if len(output) >= limit:
+                return output
+    return output
+
+
+def _rg_files(path: Path, cwd: Path, limit: int) -> list[Path] | None:
+    try:
+        result = subprocess.run(
+            ["rg", "--files", str(path.relative_to(cwd))],
+            cwd=cwd,
+            capture_output=True,
+            text=True,
+            timeout=10,
+        )
+    except FileNotFoundError:
+        return None
+    except subprocess.TimeoutExpired:
+        return None
+    if result.returncode != 0:
+        return None
+    files = [Path(line.strip()) for line in result.stdout.splitlines() if line.strip()]
+    return files[:limit]
+
+
+def _file_metadata(path: Path) -> str:
+    if _is_binary_file(path):
+        return f"{path.stat().st_size} bytes"
+    try:
+        line_count = path.read_text(encoding="utf-8").count("\n") + 1
+    except Exception:
+        return f"{path.stat().st_size} bytes"
+    return f"{line_count} lines"
+
+
+def _code_fence_language(path: Path) -> str:
+    mapping = {
+        ".py": "python",
+        ".js": "javascript",
+        ".ts": "typescript",
+        ".tsx": "tsx",
+        ".jsx": "jsx",
+        ".json": "json",
+        ".md": "markdown",
+        ".sh": "bash",
+        ".yml": "yaml",
+        ".yaml": "yaml",
+        ".toml": "toml",
+    }
+    return mapping.get(path.suffix.lower(), "")

agent/copilot_acp_client.py

@@ -0,0 +1,447 @@
+"""OpenAI-compatible shim that forwards Hermes requests to `copilot --acp`.
+
+This adapter lets Hermes treat the GitHub Copilot ACP server as a chat-style
+backend. Each request starts a short-lived ACP session, sends the formatted
+conversation as a single prompt, collects text chunks, and converts the result
+back into the minimal shape Hermes expects from an OpenAI client.
+"""
+
+from __future__ import annotations
+
+import json
+import os
+import queue
+import shlex
+import subprocess
+import threading
+import time
+from collections import deque
+from pathlib import Path
+from types import SimpleNamespace
+from typing import Any
+
+ACP_MARKER_BASE_URL = "acp://copilot"
+_DEFAULT_TIMEOUT_SECONDS = 900.0
+
+
+def _resolve_command() -> str:
+    return (
+        os.getenv("HERMES_COPILOT_ACP_COMMAND", "").strip()
+        or os.getenv("COPILOT_CLI_PATH", "").strip()
+        or "copilot"
+    )
+
+
+def _resolve_args() -> list[str]:
+    raw = os.getenv("HERMES_COPILOT_ACP_ARGS", "").strip()
+    if not raw:
+        return ["--acp", "--stdio"]
+    return shlex.split(raw)
+
+
+def _jsonrpc_error(message_id: Any, code: int, message: str) -> dict[str, Any]:
+    return {
+        "jsonrpc": "2.0",
+        "id": message_id,
+        "error": {
+            "code": code,
+            "message": message,
+        },
+    }
+
+
+def _format_messages_as_prompt(messages: list[dict[str, Any]], model: str | None = None) -> str:
+    sections: list[str] = [
+        "You are being used as the active ACP agent backend for Hermes.",
+        "Use your own ACP capabilities and respond directly in natural language.",
+        "Do not emit OpenAI tool-call JSON.",
+    ]
+    if model:
+        sections.append(f"Hermes requested model hint: {model}")
+
+    transcript: list[str] = []
+    for message in messages:
+        if not isinstance(message, dict):
+            continue
+        role = str(message.get("role") or "unknown").strip().lower()
+        if role == "tool":
+            role = "tool"
+        elif role not in {"system", "user", "assistant"}:
+            role = "context"
+
+        content = message.get("content")
+        rendered = _render_message_content(content)
+        if not rendered:
+            continue
+
+        label = {
+            "system": "System",
+            "user": "User",
+            "assistant": "Assistant",
+            "tool": "Tool",
+            "context": "Context",
+        }.get(role, role.title())
+        transcript.append(f"{label}:\n{rendered}")
+
+    if transcript:
+        sections.append("Conversation transcript:\n\n" + "\n\n".join(transcript))
+
+    sections.append("Continue the conversation from the latest user request.")
+    return "\n\n".join(section.strip() for section in sections if section and section.strip())
+
+
+def _render_message_content(content: Any) -> str:
+    if content is None:
+        return ""
+    if isinstance(content, str):
+        return content.strip()
+    if isinstance(content, dict):
+        if "text" in content:
+            return str(content.get("text") or "").strip()
+        if "content" in content and isinstance(content.get("content"), str):
+            return str(content.get("content") or "").strip()
+        return json.dumps(content, ensure_ascii=True)
+    if isinstance(content, list):
+        parts: list[str] = []
+        for item in content:
+            if isinstance(item, str):
+                parts.append(item)
+            elif isinstance(item, dict):
+                text = item.get("text")
+                if isinstance(text, str) and text.strip():
+                    parts.append(text.strip())
+        return "\n".join(parts).strip()
+    return str(content).strip()
+
+
+def _ensure_path_within_cwd(path_text: str, cwd: str) -> Path:
+    candidate = Path(path_text)
+    if not candidate.is_absolute():
+        raise PermissionError("ACP file-system paths must be absolute.")
+    resolved = candidate.resolve()
+    root = Path(cwd).resolve()
+    try:
+        resolved.relative_to(root)
+    except ValueError as exc:
+        raise PermissionError(f"Path '{resolved}' is outside the session cwd '{root}'.") from exc
+    return resolved
+
+
+class _ACPChatCompletions:
+    def __init__(self, client: "CopilotACPClient"):
+        self._client = client
+
+    def create(self, **kwargs: Any) -> Any:
+        return self._client._create_chat_completion(**kwargs)
+
+
+class _ACPChatNamespace:
+    def __init__(self, client: "CopilotACPClient"):
+        self.completions = _ACPChatCompletions(client)
+
+
+class CopilotACPClient:
+    """Minimal OpenAI-client-compatible facade for Copilot ACP."""
+
+    def __init__(
+        self,
+        *,
+        api_key: str | None = None,
+        base_url: str | None = None,
+        default_headers: dict[str, str] | None = None,
+        acp_command: str | None = None,
+        acp_args: list[str] | None = None,
+        acp_cwd: str | None = None,
+        command: str | None = None,
+        args: list[str] | None = None,
+        **_: Any,
+    ):
+        self.api_key = api_key or "copilot-acp"
+        self.base_url = base_url or ACP_MARKER_BASE_URL
+        self._default_headers = dict(default_headers or {})
+        self._acp_command = acp_command or command or _resolve_command()
+        self._acp_args = list(acp_args or args or _resolve_args())
+        self._acp_cwd = str(Path(acp_cwd or os.getcwd()).resolve())
+        self.chat = _ACPChatNamespace(self)
+        self.is_closed = False
+        self._active_process: subprocess.Popen[str] | None = None
+        self._active_process_lock = threading.Lock()
+
+    def close(self) -> None:
+        proc: subprocess.Popen[str] | None
+        with self._active_process_lock:
+            proc = self._active_process
+            self._active_process = None
+        self.is_closed = True
+        if proc is None:
+            return
+        try:
+            proc.terminate()
+            proc.wait(timeout=2)
+        except Exception:
+            try:
+                proc.kill()
+            except Exception:
+                pass
+
+    def _create_chat_completion(
+        self,
+        *,
+        model: str | None = None,
+        messages: list[dict[str, Any]] | None = None,
+        timeout: float | None = None,
+        **_: Any,
+    ) -> Any:
+        prompt_text = _format_messages_as_prompt(messages or [], model=model)
+        response_text, reasoning_text = self._run_prompt(
+            prompt_text,
+            timeout_seconds=float(timeout or _DEFAULT_TIMEOUT_SECONDS),
+        )
+
+        usage = SimpleNamespace(
+            prompt_tokens=0,
+            completion_tokens=0,
+            total_tokens=0,
+            prompt_tokens_details=SimpleNamespace(cached_tokens=0),
+        )
+        assistant_message = SimpleNamespace(
+            content=response_text,
+            tool_calls=[],
+            reasoning=reasoning_text or None,
+            reasoning_content=reasoning_text or None,
+            reasoning_details=None,
+        )
+        choice = SimpleNamespace(message=assistant_message, finish_reason="stop")
+        return SimpleNamespace(
+            choices=[choice],
+            usage=usage,
+            model=model or "copilot-acp",
+        )
+
+    def _run_prompt(self, prompt_text: str, *, timeout_seconds: float) -> tuple[str, str]:
+        try:
+            proc = subprocess.Popen(
+                [self._acp_command] + self._acp_args,
+                stdin=subprocess.PIPE,
+                stdout=subprocess.PIPE,
+                stderr=subprocess.PIPE,
+                text=True,
+                bufsize=1,
+                cwd=self._acp_cwd,
+            )
+        except FileNotFoundError as exc:
+            raise RuntimeError(
+                f"Could not start Copilot ACP command '{self._acp_command}'. "
+                "Install GitHub Copilot CLI or set HERMES_COPILOT_ACP_COMMAND/COPILOT_CLI_PATH."
+            ) from exc
+
+        if proc.stdin is None or proc.stdout is None:
+            proc.kill()
+            raise RuntimeError("Copilot ACP process did not expose stdin/stdout pipes.")
+
+        self.is_closed = False
+        with self._active_process_lock:
+            self._active_process = proc
+
+        inbox: queue.Queue[dict[str, Any]] = queue.Queue()
+        stderr_tail: deque[str] = deque(maxlen=40)
+
+        def _stdout_reader() -> None:
+            for line in proc.stdout:
+                try:
+                    inbox.put(json.loads(line))
+                except Exception:
+                    inbox.put({"raw": line.rstrip("\n")})
+
+        def _stderr_reader() -> None:
+            if proc.stderr is None:
+                return
+            for line in proc.stderr:
+                stderr_tail.append(line.rstrip("\n"))
+
+        out_thread = threading.Thread(target=_stdout_reader, daemon=True)
+        err_thread = threading.Thread(target=_stderr_reader, daemon=True)
+        out_thread.start()
+        err_thread.start()
+
+        next_id = 0
+
+        def _request(method: str, params: dict[str, Any], *, text_parts: list[str] | None = None, reasoning_parts: list[str] | None = None) -> Any:
+            nonlocal next_id
+            next_id += 1
+            request_id = next_id
+            payload = {
+                "jsonrpc": "2.0",
+                "id": request_id,
+                "method": method,
+                "params": params,
+            }
+            proc.stdin.write(json.dumps(payload) + "\n")
+            proc.stdin.flush()
+
+            deadline = time.time() + timeout_seconds
+            while time.time() < deadline:
+                if proc.poll() is not None:
+                    break
+                try:
+                    msg = inbox.get(timeout=0.1)
+                except queue.Empty:
+                    continue
+
+                if self._handle_server_message(
+                    msg,
+                    process=proc,
+                    cwd=self._acp_cwd,
+                    text_parts=text_parts,
+                    reasoning_parts=reasoning_parts,
+                ):
+                    continue
+
+                if msg.get("id") != request_id:
+                    continue
+                if "error" in msg:
+                    err = msg.get("error") or {}
+                    raise RuntimeError(
+                        f"Copilot ACP {method} failed: {err.get('message') or err}"
+                    )
+                return msg.get("result")
+
+            stderr_text = "\n".join(stderr_tail).strip()
+            if proc.poll() is not None and stderr_text:
+                raise RuntimeError(f"Copilot ACP process exited early: {stderr_text}")
+            raise TimeoutError(f"Timed out waiting for Copilot ACP response to {method}.")
+
+        try:
+            _request(
+                "initialize",
+                {
+                    "protocolVersion": 1,
+                    "clientCapabilities": {
+                        "fs": {
+                            "readTextFile": True,
+                            "writeTextFile": True,
+                        }
+                    },
+                    "clientInfo": {
+                        "name": "hermes-agent",
+                        "title": "Hermes Agent",
+                        "version": "0.0.0",
+                    },
+                },
+            )
+            session = _request(
+                "session/new",
+                {
+                    "cwd": self._acp_cwd,
+                    "mcpServers": [],
+                },
+            ) or {}
+            session_id = str(session.get("sessionId") or "").strip()
+            if not session_id:
+                raise RuntimeError("Copilot ACP did not return a sessionId.")
+
+            text_parts: list[str] = []
+            reasoning_parts: list[str] = []
+            _request(
+                "session/prompt",
+                {
+                    "sessionId": session_id,
+                    "prompt": [
+                        {
+                            "type": "text",
+                            "text": prompt_text,
+                        }
+                    ],
+                },
+                text_parts=text_parts,
+                reasoning_parts=reasoning_parts,
+            )
+            return "".join(text_parts), "".join(reasoning_parts)
+        finally:
+            self.close()
+
+    def _handle_server_message(
+        self,
+        msg: dict[str, Any],
+        *,
+        process: subprocess.Popen[str],
+        cwd: str,
+        text_parts: list[str] | None,
+        reasoning_parts: list[str] | None,
+    ) -> bool:
+        method = msg.get("method")
+        if not isinstance(method, str):
+            return False
+
+        if method == "session/update":
+            params = msg.get("params") or {}
+            update = params.get("update") or {}
+            kind = str(update.get("sessionUpdate") or "").strip()
+            content = update.get("content") or {}
+            chunk_text = ""
+            if isinstance(content, dict):
+                chunk_text = str(content.get("text") or "")
+            if kind == "agent_message_chunk" and chunk_text and text_parts is not None:
+                text_parts.append(chunk_text)
+            elif kind == "agent_thought_chunk" and chunk_text and reasoning_parts is not None:
+                reasoning_parts.append(chunk_text)
+            return True
+
+        if process.stdin is None:
+            return True
+
+        message_id = msg.get("id")
+        params = msg.get("params") or {}
+
+        if method == "session/request_permission":
+            response = {
+                "jsonrpc": "2.0",
+                "id": message_id,
+                "result": {
+                    "outcome": {
+                        "outcome": "allow_once",
+                    }
+                },
+            }
+        elif method == "fs/read_text_file":
+            try:
+                path = _ensure_path_within_cwd(str(params.get("path") or ""), cwd)
+                content = path.read_text() if path.exists() else ""
+                line = params.get("line")
+                limit = params.get("limit")
+                if isinstance(line, int) and line > 1:
+                    lines = content.splitlines(keepends=True)
+                    start = line - 1
+                    end = start + limit if isinstance(limit, int) and limit > 0 else None
+                    content = "".join(lines[start:end])
+                response = {
+                    "jsonrpc": "2.0",
+                    "id": message_id,
+                    "result": {
+                        "content": content,
+                    },
+                }
+            except Exception as exc:
+                response = _jsonrpc_error(message_id, -32602, str(exc))
+        elif method == "fs/write_text_file":
+            try:
+                path = _ensure_path_within_cwd(str(params.get("path") or ""), cwd)
+                path.parent.mkdir(parents=True, exist_ok=True)
+                path.write_text(str(params.get("content") or ""))
+                response = {
+                    "jsonrpc": "2.0",
+                    "id": message_id,
+                    "result": None,
+                }
+            except Exception as exc:
+                response = _jsonrpc_error(message_id, -32602, str(exc))
+        else:
+            response = _jsonrpc_error(
+                message_id,
+                -32601,
+                f"ACP client method '{method}' is not supported by Hermes yet.",
+            )
+
+        process.stdin.write(json.dumps(response) + "\n")
+        process.stdin.flush()
+        return True

agent/display.py

@@ -5,8 +5,8 @@ Used by AIAgent._execute_tool_calls for CLI feedback.
 """
 
 import json
+import logging
 import os
-import random
 import sys
 import threading
 import time
@@ -15,13 +15,112 @@ import time
 _RED = "\033[31m"
 _RESET = "\033[0m"
 
+logger = logging.getLogger(__name__)
+
+# =========================================================================
+# Configurable tool preview length (0 = no limit)
+# Set once at startup by CLI or gateway from display.tool_preview_length config.
+# =========================================================================
+_tool_preview_max_len: int = 0  # 0 = unlimited
+
+
+def set_tool_preview_max_len(n: int) -> None:
+    """Set the global max length for tool call previews. 0 = no limit."""
+    global _tool_preview_max_len
+    _tool_preview_max_len = max(int(n), 0) if n else 0
+
+
+def get_tool_preview_max_len() -> int:
+    """Return the configured max preview length (0 = unlimited)."""
+    return _tool_preview_max_len
+
+
+# =========================================================================
+# Skin-aware helpers (lazy import to avoid circular deps)
+# =========================================================================
+
+def _get_skin():
+    """Get the active skin config, or None if not available."""
+    try:
+        from hermes_cli.skin_engine import get_active_skin
+        return get_active_skin()
+    except Exception:
+        return None
+
+
+def get_skin_faces(key: str, default: list) -> list:
+    """Get spinner face list from active skin, falling back to default."""
+    skin = _get_skin()
+    if skin:
+        faces = skin.get_spinner_list(key)
+        if faces:
+            return faces
+    return default
+
+
+def get_skin_verbs() -> list:
+    """Get thinking verbs from active skin."""
+    skin = _get_skin()
+    if skin:
+        verbs = skin.get_spinner_list("thinking_verbs")
+        if verbs:
+            return verbs
+    return KawaiiSpinner.THINKING_VERBS
+
+
+def get_skin_tool_prefix() -> str:
+    """Get tool output prefix character from active skin."""
+    skin = _get_skin()
+    if skin:
+        return skin.tool_prefix
+    return "┊"
+
+
+def get_tool_emoji(tool_name: str, default: str = "⚡") -> str:
+    """Get the display emoji for a tool.
+
+    Resolution order:
+    1. Active skin's ``tool_emojis`` overrides (if a skin is loaded)
+    2. Tool registry's per-tool ``emoji`` field
+    3. *default* fallback
+    """
+    # 1. Skin override
+    skin = _get_skin()
+    if skin and skin.tool_emojis:
+        override = skin.tool_emojis.get(tool_name)
+        if override:
+            return override
+    # 2. Registry default
+    try:
+        from tools.registry import registry
+        emoji = registry.get_emoji(tool_name, default="")
+        if emoji:
+            return emoji
+    except Exception:
+        pass
+    # 3. Hardcoded fallback
+    return default
+
 
 # =========================================================================
 # Tool preview (one-line summary of a tool call's primary argument)
 # =========================================================================
 
-def build_tool_preview(tool_name: str, args: dict, max_len: int = 40) -> str:
-    """Build a short preview of a tool call's primary argument for display."""
+def _oneline(text: str) -> str:
+    """Collapse whitespace (including newlines) to single spaces."""
+    return " ".join(text.split())
+
+
+def build_tool_preview(tool_name: str, args: dict, max_len: int | None = None) -> str | None:
+    """Build a short preview of a tool call's primary argument for display.
+
+    *max_len* controls truncation.  ``None`` (default) defers to the global
+    ``_tool_preview_max_len`` set via config; ``0`` means unlimited.
+    """
+    if max_len is None:
+        max_len = _tool_preview_max_len
+    if not args:
+        return None
     primary_args = {
         "terminal": "command", "web_search": "query", "web_extract": "urls",
         "read_file": "path", "write_file": "path", "patch": "path",
@@ -30,7 +129,7 @@ def build_tool_preview(tool_name: str, args: dict, max_len: int = 40) -> str:
         "image_generate": "prompt", "text_to_speech": "text",
         "vision_analyze": "question", "mixture_of_agents": "user_prompt",
         "skill_view": "name", "skills_list": "category",
-        "schedule_cronjob": "name",
+        "cronjob": "action",
         "execute_code": "code", "delegate_task": "goal",
         "clarify": "question", "skill_manage": "name",
     }
@@ -44,7 +143,7 @@ def build_tool_preview(tool_name: str, args: dict, max_len: int = 40) -> str:
         if sid:
             parts.append(sid[:16])
         if data:
-            parts.append(f'"{data[:20]}"')
+            parts.append(f'"{_oneline(data[:20])}"')
         if timeout_val and action == "wait":
             parts.append(f"{timeout_val}s")
         return " ".join(parts) if parts else None
@@ -60,24 +159,24 @@ def build_tool_preview(tool_name: str, args: dict, max_len: int = 40) -> str:
             return f"planning {len(todos_arg)} task(s)"
 
     if tool_name == "session_search":
-        query = args.get("query", "")
+        query = _oneline(args.get("query", ""))
         return f"recall: \"{query[:25]}{'...' if len(query) > 25 else ''}\""
 
     if tool_name == "memory":
         action = args.get("action", "")
         target = args.get("target", "")
         if action == "add":
-            content = args.get("content", "")
+            content = _oneline(args.get("content", ""))
             return f"+{target}: \"{content[:25]}{'...' if len(content) > 25 else ''}\""
         elif action == "replace":
-            return f"~{target}: \"{args.get('old_text', '')[:20]}\""
+            return f"~{target}: \"{_oneline(args.get('old_text', '')[:20])}\""
         elif action == "remove":
-            return f"-{target}: \"{args.get('old_text', '')[:20]}\""
+            return f"-{target}: \"{_oneline(args.get('old_text', '')[:20])}\""
         return action
 
     if tool_name == "send_message":
         target = args.get("target", "?")
-        msg = args.get("message", "")
+        msg = _oneline(args.get("message", ""))
         if len(msg) > 20:
             msg = msg[:17] + "..."
         return f"to {target}: \"{msg}\""
@@ -111,10 +210,10 @@ def build_tool_preview(tool_name: str, args: dict, max_len: int = 40) -> str:
     if isinstance(value, list):
         value = value[0] if value else ""
 
-    preview = str(value).strip()
+    preview = _oneline(str(value))
     if not preview:
         return None
-    if len(preview) > max_len:
+    if max_len > 0 and len(preview) > max_len:
         preview = preview[:max_len - 3] + "..."
     return preview
 
@@ -155,7 +254,7 @@ class KawaiiSpinner:
         "analyzing", "computing", "synthesizing", "formulating", "brainstorming",
     ]
 
-    def __init__(self, message: str = "", spinner_type: str = 'dots'):
+    def __init__(self, message: str = "", spinner_type: str = 'dots', print_fn=None):
         self.message = message
         self.spinner_frames = self.SPINNERS.get(spinner_type, self.SPINNERS['dots'])
         self.running = False
@@ -163,12 +262,26 @@ class KawaiiSpinner:
         self.frame_idx = 0
         self.start_time = None
         self.last_line_len = 0
+        # Optional callable to route all output through (e.g. a no-op for silent
+        # background agents).  When set, bypasses self._out entirely so that
+        # agents with _print_fn overridden remain fully silent.
+        self._print_fn = print_fn
         # Capture stdout NOW, before any redirect_stdout(devnull) from
         # child agents can replace sys.stdout with a black hole.
         self._out = sys.stdout
 
     def _write(self, text: str, end: str = '\n', flush: bool = False):
-        """Write to the stdout captured at spinner creation time."""
+        """Write to the stdout captured at spinner creation time.
+
+        If a print_fn was supplied at construction, all output is routed through
+        it instead — allowing callers to silence the spinner with a no-op lambda.
+        """
+        if self._print_fn is not None:
+            try:
+                self._print_fn(text)
+            except Exception:
+                pass
+            return
         try:
             self._out.write(text + end)
             if flush:
@@ -176,14 +289,65 @@ class KawaiiSpinner:
         except (ValueError, OSError):
             pass
 
+    @property
+    def _is_tty(self) -> bool:
+        """Check if output is a real terminal, safe against closed streams."""
+        try:
+            return hasattr(self._out, 'isatty') and self._out.isatty()
+        except (ValueError, OSError):
+            return False
+
+    def _is_patch_stdout_proxy(self) -> bool:
+        """Return True when stdout is prompt_toolkit's StdoutProxy.
+
+        patch_stdout wraps sys.stdout in a StdoutProxy that queues writes and
+        injects newlines around each flush().  The \\r overwrite never lands on
+        the correct line — each spinner frame ends up on its own line.
+
+        The CLI already drives a TUI widget (_spinner_text) for spinner display,
+        so KawaiiSpinner's \\r-based animation is redundant under StdoutProxy.
+        """
+        try:
+            from prompt_toolkit.patch_stdout import StdoutProxy
+            return isinstance(self._out, StdoutProxy)
+        except ImportError:
+            return False
+
     def _animate(self):
+        # When stdout is not a real terminal (e.g. Docker, systemd, pipe),
+        # skip the animation entirely — it creates massive log bloat.
+        # Just log the start once and let stop() log the completion.
+        if not self._is_tty:
+            self._write(f"  [tool] {self.message}", flush=True)
+            while self.running:
+                time.sleep(0.5)
+            return
+
+        # When running inside prompt_toolkit's patch_stdout context the CLI
+        # renders spinner state via a dedicated TUI widget (_spinner_text).
+        # Driving a \r-based animation here too causes visual overdraw: the
+        # StdoutProxy injects newlines around each flush, so every frame lands
+        # on a new line and overwrites the status bar.
+        if self._is_patch_stdout_proxy():
+            while self.running:
+                time.sleep(0.1)
+            return
+
+        # Cache skin wings at start (avoid per-frame imports)
+        skin = _get_skin()
+        wings = skin.get_spinner_wings() if skin else []
+
         while self.running:
             if os.getenv("HERMES_SPINNER_PAUSE"):
                 time.sleep(0.1)
                 continue
             frame = self.spinner_frames[self.frame_idx % len(self.spinner_frames)]
             elapsed = time.time() - self.start_time
-            line = f"  {frame} {self.message} ({elapsed:.1f}s)"
+            if wings:
+                left, right = wings[self.frame_idx % len(wings)]
+                line = f"  {left} {frame} {self.message} {right} ({elapsed:.1f}s)"
+            else:
+                line = f"  {frame} {self.message} ({elapsed:.1f}s)"
             pad = max(self.last_line_len - len(line), 0)
             self._write(f"\r{line}{' ' * pad}", end='', flush=True)
             self.last_line_len = len(line)
@@ -223,12 +387,19 @@ class KawaiiSpinner:
         self.running = False
         if self.thread:
             self.thread.join(timeout=0.5)
-        # Clear the spinner line with spaces instead of \033[K to avoid
-        # garbled escape codes when prompt_toolkit's patch_stdout is active.
-        blanks = ' ' * max(self.last_line_len + 5, 40)
-        self._write(f"\r{blanks}\r", end='', flush=True)
+
+        is_tty = self._is_tty
+        if is_tty:
+            # Clear the spinner line with spaces instead of \033[K to avoid
+            # garbled escape codes when prompt_toolkit's patch_stdout is active.
+            blanks = ' ' * max(self.last_line_len + 5, 40)
+            self._write(f"\r{blanks}\r", end='', flush=True)
         if final_message:
-            self._write(f"  {final_message}", flush=True)
+            elapsed = f" ({time.time() - self.start_time:.1f}s)" if self.start_time else ""
+            if is_tty:
+                self._write(f"  {final_message}", flush=True)
+            else:
+                self._write(f"  [done] {final_message}{elapsed}", flush=True)
 
     def __enter__(self):
         self.start()
@@ -300,7 +471,7 @@ def _detect_tool_failure(tool_name: str, result: str | None) -> tuple[bool, str]
             if exit_code is not None and exit_code != 0:
                 return True, f" [exit {exit_code}]"
         except (json.JSONDecodeError, TypeError, AttributeError):
-            pass
+            logger.debug("Could not parse terminal result as JSON for exit code check")
         return False, ""
 
     # Memory-specific: distinguish "full" from real errors
@@ -310,7 +481,7 @@ def _detect_tool_failure(tool_name: str, result: str | None) -> tuple[bool, str]
             if data.get("success") is False and "exceed the limit" in data.get("error", ""):
                 return True, " [full]"
         except (json.JSONDecodeError, TypeError, AttributeError):
-            pass
+            logger.debug("Could not parse memory result as JSON for capacity check")
 
     # Generic heuristic for non-terminal tools
     lower = result[:500].lower()
@@ -332,17 +503,24 @@ def get_cute_tool_message(
     """
     dur = f"{duration:.1f}s"
     is_failure, failure_suffix = _detect_tool_failure(tool_name, result)
+    skin_prefix = get_skin_tool_prefix()
 
     def _trunc(s, n=40):
         s = str(s)
+        if _tool_preview_max_len == 0:
+            return s  # no limit
         return (s[:n-3] + "...") if len(s) > n else s
 
     def _path(p, n=35):
         p = str(p)
+        if _tool_preview_max_len == 0:
+            return p  # no limit
         return ("..." + p[-(n-3):]) if len(p) > n else p
 
     def _wrap(line: str) -> str:
-        """Append failure suffix when the tool failed."""
+        """Apply skin tool prefix and failure suffix."""
+        if skin_prefix != "┊":
+            line = line.replace("┊", skin_prefix, 1)
         if not is_failure:
             return line
         return f"{line}{failure_suffix}"
@@ -440,12 +618,15 @@ def get_cute_tool_message(
         return _wrap(f"┊ 🧠 reason    {_trunc(args.get('user_prompt', ''), 30)}  {dur}")
     if tool_name == "send_message":
         return _wrap(f"┊ 📨 send      {args.get('target', '?')}: \"{_trunc(args.get('message', ''), 25)}\"  {dur}")
-    if tool_name == "schedule_cronjob":
-        return _wrap(f"┊ ⏰ schedule  {_trunc(args.get('name', args.get('prompt', 'task')), 30)}  {dur}")
-    if tool_name == "list_cronjobs":
-        return _wrap(f"┊ ⏰ jobs      listing  {dur}")
-    if tool_name == "remove_cronjob":
-        return _wrap(f"┊ ⏰ remove    job {args.get('job_id', '?')}  {dur}")
+    if tool_name == "cronjob":
+        action = args.get("action", "?")
+        if action == "create":
+            skills = args.get("skills") or ([] if not args.get("skill") else [args.get("skill")])
+            label = args.get("name") or (skills[0] if skills else None) or args.get("prompt", "task")
+            return _wrap(f"┊ ⏰ cron      create {_trunc(label, 24)}  {dur}")
+        if action == "list":
+            return _wrap(f"┊ ⏰ cron      listing  {dur}")
+        return _wrap(f"┊ ⏰ cron      {action} {args.get('job_id', '')}  {dur}")
     if tool_name.startswith("rl_"):
         rl = {
             "rl_list_environments": "list envs", "rl_select_environment": f"select {args.get('name', '')}",
@@ -467,3 +648,124 @@ def get_cute_tool_message(
 
     preview = build_tool_preview(tool_name, args) or ""
     return _wrap(f"┊ ⚡ {tool_name[:9]:9} {_trunc(preview, 35)}  {dur}")
+
+
+# =========================================================================
+# Honcho session line (one-liner with clickable OSC 8 hyperlink)
+# =========================================================================
+
+_DIM = "\033[2m"
+_SKY_BLUE = "\033[38;5;117m"
+_ANSI_RESET = "\033[0m"
+
+
+def honcho_session_url(workspace: str, session_name: str) -> str:
+    """Build a Honcho app URL for a session."""
+    from urllib.parse import quote
+    return (
+        f"https://app.honcho.dev/explore"
+        f"?workspace={quote(workspace, safe='')}"
+        f"&view=sessions"
+        f"&session={quote(session_name, safe='')}"
+    )
+
+
+def _osc8_link(url: str, text: str) -> str:
+    """OSC 8 terminal hyperlink (clickable in iTerm2, Ghostty, WezTerm, etc.)."""
+    return f"\033]8;;{url}\033\\{text}\033]8;;\033\\"
+
+
+def honcho_session_line(workspace: str, session_name: str) -> str:
+    """One-line session indicator: `Honcho session: <clickable name>`."""
+    url = honcho_session_url(workspace, session_name)
+    linked_name = _osc8_link(url, f"{_SKY_BLUE}{session_name}{_ANSI_RESET}")
+    return f"{_DIM}Honcho session:{_ANSI_RESET} {linked_name}"
+
+
+def write_tty(text: str) -> None:
+    """Write directly to /dev/tty, bypassing stdout capture."""
+    try:
+        fd = os.open("/dev/tty", os.O_WRONLY)
+        os.write(fd, text.encode("utf-8"))
+        os.close(fd)
+    except OSError:
+        sys.stdout.write(text)
+        sys.stdout.flush()
+
+
+# =========================================================================
+# Context pressure display (CLI user-facing warnings)
+# =========================================================================
+
+# ANSI color codes for context pressure tiers
+_CYAN = "\033[36m"
+_YELLOW = "\033[33m"
+_BOLD = "\033[1m"
+_DIM_ANSI = "\033[2m"
+
+# Bar characters
+_BAR_FILLED = "▰"
+_BAR_EMPTY = "▱"
+_BAR_WIDTH = 20
+
+
+def format_context_pressure(
+    compaction_progress: float,
+    threshold_tokens: int,
+    threshold_percent: float,
+    compression_enabled: bool = True,
+) -> str:
+    """Build a formatted context pressure line for CLI display.
+
+    The bar and percentage show progress toward the compaction threshold,
+    NOT the raw context window.  100% = compaction fires.
+
+    Args:
+        compaction_progress: How close to compaction (0.0–1.0, 1.0 = fires).
+        threshold_tokens: Compaction threshold in tokens.
+        threshold_percent: Compaction threshold as a fraction of context window.
+        compression_enabled: Whether auto-compression is active.
+    """
+    pct_int = min(int(compaction_progress * 100), 100)
+    filled = min(int(compaction_progress * _BAR_WIDTH), _BAR_WIDTH)
+    bar = _BAR_FILLED * filled + _BAR_EMPTY * (_BAR_WIDTH - filled)
+
+    threshold_k = f"{threshold_tokens // 1000}k" if threshold_tokens >= 1000 else str(threshold_tokens)
+    threshold_pct_int = int(threshold_percent * 100)
+
+    color = f"{_BOLD}{_YELLOW}"
+    icon = "⚠"
+    if compression_enabled:
+        hint = "compaction approaching"
+    else:
+        hint = "no auto-compaction"
+
+    return (
+        f"  {color}{icon} context {bar} {pct_int}% to compaction{_ANSI_RESET}"
+        f"  {_DIM_ANSI}{threshold_k} threshold ({threshold_pct_int}%) · {hint}{_ANSI_RESET}"
+    )
+
+
+def format_context_pressure_gateway(
+    compaction_progress: float,
+    threshold_percent: float,
+    compression_enabled: bool = True,
+) -> str:
+    """Build a plain-text context pressure notification for messaging platforms.
+
+    No ANSI — just Unicode and plain text suitable for Telegram/Discord/etc.
+    The percentage shows progress toward the compaction threshold.
+    """
+    pct_int = min(int(compaction_progress * 100), 100)
+    filled = min(int(compaction_progress * _BAR_WIDTH), _BAR_WIDTH)
+    bar = _BAR_FILLED * filled + _BAR_EMPTY * (_BAR_WIDTH - filled)
+
+    threshold_pct_int = int(threshold_percent * 100)
+
+    icon = "⚠️"
+    if compression_enabled:
+        hint = f"Context compaction approaching (threshold: {threshold_pct_int}% of window)."
+    else:
+        hint = "Auto-compaction is disabled — context may be truncated."
+
+    return f"{icon} Context: {bar} {pct_int}% to compaction\n{hint}"

agent/insights.py

@@ -20,65 +20,23 @@ import json
 import time
 from collections import Counter, defaultdict
 from datetime import datetime
-from typing import Any, Dict, List, Optional
+from typing import Any, Dict, List
 
-# =========================================================================
-# Model pricing (USD per million tokens) — approximate as of early 2026
-# =========================================================================
-MODEL_PRICING = {
-    # OpenAI
-    "gpt-4o": {"input": 2.50, "output": 10.00},
-    "gpt-4o-mini": {"input": 0.15, "output": 0.60},
-    "gpt-4.1": {"input": 2.00, "output": 8.00},
-    "gpt-4.1-mini": {"input": 0.40, "output": 1.60},
-    "gpt-4.1-nano": {"input": 0.10, "output": 0.40},
-    "gpt-4.5-preview": {"input": 75.00, "output": 150.00},
-    "gpt-5": {"input": 10.00, "output": 30.00},
-    "gpt-5.4": {"input": 10.00, "output": 30.00},
-    "o3": {"input": 10.00, "output": 40.00},
-    "o3-mini": {"input": 1.10, "output": 4.40},
-    "o4-mini": {"input": 1.10, "output": 4.40},
-    # Anthropic
-    "claude-opus-4-20250514": {"input": 15.00, "output": 75.00},
-    "claude-sonnet-4-20250514": {"input": 3.00, "output": 15.00},
-    "claude-3-5-sonnet-20241022": {"input": 3.00, "output": 15.00},
-    "claude-3-5-haiku-20241022": {"input": 0.80, "output": 4.00},
-    "claude-3-opus-20240229": {"input": 15.00, "output": 75.00},
-    "claude-3-haiku-20240307": {"input": 0.25, "output": 1.25},
-    # DeepSeek
-    "deepseek-chat": {"input": 0.14, "output": 0.28},
-    "deepseek-reasoner": {"input": 0.55, "output": 2.19},
-    # Google
-    "gemini-2.5-pro": {"input": 1.25, "output": 10.00},
-    "gemini-2.5-flash": {"input": 0.15, "output": 0.60},
-    "gemini-2.0-flash": {"input": 0.10, "output": 0.40},
-    # Meta (via providers)
-    "llama-4-maverick": {"input": 0.50, "output": 0.70},
-    "llama-4-scout": {"input": 0.20, "output": 0.30},
-    # Z.AI / GLM (direct provider — pricing not published externally, treat as local)
-    "glm-5": {"input": 0.0, "output": 0.0},
-    "glm-4.7": {"input": 0.0, "output": 0.0},
-    "glm-4.5": {"input": 0.0, "output": 0.0},
-    "glm-4.5-flash": {"input": 0.0, "output": 0.0},
-    # Kimi / Moonshot (direct provider — pricing not published externally, treat as local)
-    "kimi-k2.5": {"input": 0.0, "output": 0.0},
-    "kimi-k2-thinking": {"input": 0.0, "output": 0.0},
-    "kimi-k2-turbo-preview": {"input": 0.0, "output": 0.0},
-    "kimi-k2-0905-preview": {"input": 0.0, "output": 0.0},
-    # MiniMax (direct provider — pricing not published externally, treat as local)
-    "MiniMax-M2.5": {"input": 0.0, "output": 0.0},
-    "MiniMax-M2.5-highspeed": {"input": 0.0, "output": 0.0},
-    "MiniMax-M2.1": {"input": 0.0, "output": 0.0},
-}
+from agent.usage_pricing import (
+    CanonicalUsage,
+    DEFAULT_PRICING,
+    estimate_usage_cost,
+    format_duration_compact,
+    get_pricing,
+    has_known_pricing,
+)
 
-# Fallback: unknown/custom models get zero cost (we can't assume pricing
-# for self-hosted models, custom OAI endpoints, local inference, etc.)
-_DEFAULT_PRICING = {"input": 0.0, "output": 0.0}
+_DEFAULT_PRICING = DEFAULT_PRICING
 
 
-def _has_known_pricing(model_name: str) -> bool:
+def _has_known_pricing(model_name: str, provider: str = None, base_url: str = None) -> bool:
     """Check if a model has known pricing (vs unknown/custom endpoint)."""
-    return _get_pricing(model_name) is not _DEFAULT_PRICING
+    return has_known_pricing(model_name, provider=provider, base_url=base_url)
 
 
 def _get_pricing(model_name: str) -> Dict[str, float]:
@@ -87,67 +45,51 @@ def _get_pricing(model_name: str) -> Dict[str, float]:
     Returns _DEFAULT_PRICING (zero cost) for unknown/custom models —
     we can't assume costs for self-hosted endpoints, local inference, etc.
     """
-    if not model_name:
-        return _DEFAULT_PRICING
-
-    # Strip provider prefix (e.g., "anthropic/claude-..." -> "claude-...")
-    bare = model_name.split("/")[-1].lower()
-
-    # Exact match first
-    if bare in MODEL_PRICING:
-        return MODEL_PRICING[bare]
-
-    # Fuzzy prefix match — prefer the LONGEST matching key to avoid
-    # e.g. "gpt-4o" matching before "gpt-4o-mini" for "gpt-4o-mini-2024-07-18"
-    best_match = None
-    best_len = 0
-    for key, price in MODEL_PRICING.items():
-        if bare.startswith(key) and len(key) > best_len:
-            best_match = price
-            best_len = len(key)
-    if best_match:
-        return best_match
-
-    # Keyword heuristics (checked in most-specific-first order)
-    if "opus" in bare:
-        return {"input": 15.00, "output": 75.00}
-    if "sonnet" in bare:
-        return {"input": 3.00, "output": 15.00}
-    if "haiku" in bare:
-        return {"input": 0.80, "output": 4.00}
-    if "gpt-4o-mini" in bare:
-        return {"input": 0.15, "output": 0.60}
-    if "gpt-4o" in bare:
-        return {"input": 2.50, "output": 10.00}
-    if "gpt-5" in bare:
-        return {"input": 10.00, "output": 30.00}
-    if "deepseek" in bare:
-        return {"input": 0.14, "output": 0.28}
-    if "gemini" in bare:
-        return {"input": 0.15, "output": 0.60}
-
-    return _DEFAULT_PRICING
+    return get_pricing(model_name)
 
 
-def _estimate_cost(model: str, input_tokens: int, output_tokens: int) -> float:
-    """Estimate the USD cost for a given model and token counts."""
-    pricing = _get_pricing(model)
-    return (input_tokens * pricing["input"] + output_tokens * pricing["output"]) / 1_000_000
+def _estimate_cost(
+    session_or_model: Dict[str, Any] | str,
+    input_tokens: int = 0,
+    output_tokens: int = 0,
+    *,
+    cache_read_tokens: int = 0,
+    cache_write_tokens: int = 0,
+    provider: str = None,
+    base_url: str = None,
+) -> tuple[float, str]:
+    """Estimate the USD cost for a session row or a model/token tuple."""
+    if isinstance(session_or_model, dict):
+        session = session_or_model
+        model = session.get("model") or ""
+        usage = CanonicalUsage(
+            input_tokens=session.get("input_tokens") or 0,
+            output_tokens=session.get("output_tokens") or 0,
+            cache_read_tokens=session.get("cache_read_tokens") or 0,
+            cache_write_tokens=session.get("cache_write_tokens") or 0,
+        )
+        provider = session.get("billing_provider")
+        base_url = session.get("billing_base_url")
+    else:
+        model = session_or_model or ""
+        usage = CanonicalUsage(
+            input_tokens=input_tokens,
+            output_tokens=output_tokens,
+            cache_read_tokens=cache_read_tokens,
+            cache_write_tokens=cache_write_tokens,
+        )
+    result = estimate_usage_cost(
+        model,
+        usage,
+        provider=provider,
+        base_url=base_url,
+    )
+    return float(result.amount_usd or 0.0), result.status
 
 
 def _format_duration(seconds: float) -> str:
     """Format seconds into a human-readable duration string."""
-    if seconds < 60:
-        return f"{seconds:.0f}s"
-    minutes = seconds / 60
-    if minutes < 60:
-        return f"{minutes:.0f}m"
-    hours = minutes / 60
-    if hours < 24:
-        remaining_min = int(minutes % 60)
-        return f"{int(hours)}h {remaining_min}m" if remaining_min else f"{int(hours)}h"
-    days = hours / 24
-    return f"{days:.1f}d"
+    return format_duration_compact(seconds)
 
 
 def _bar_chart(values: List[int], max_width: int = 20) -> List[str]:
@@ -234,24 +176,30 @@ class InsightsEngine:
 
     # Columns we actually need (skip system_prompt, model_config blobs)
     _SESSION_COLS = ("id, source, model, started_at, ended_at, "
-                     "message_count, tool_call_count, input_tokens, output_tokens")
+                     "message_count, tool_call_count, input_tokens, output_tokens, "
+                     "cache_read_tokens, cache_write_tokens, billing_provider, "
+                     "billing_base_url, billing_mode, estimated_cost_usd, "
+                     "actual_cost_usd, cost_status, cost_source")
+
+    # Pre-computed query strings — f-string evaluated once at class definition,
+    # not at runtime, so no user-controlled value can alter the query structure.
+    _GET_SESSIONS_WITH_SOURCE = (
+        f"SELECT {_SESSION_COLS} FROM sessions"
+        " WHERE started_at >= ? AND source = ?"
+        " ORDER BY started_at DESC"
+    )
+    _GET_SESSIONS_ALL = (
+        f"SELECT {_SESSION_COLS} FROM sessions"
+        " WHERE started_at >= ?"
+        " ORDER BY started_at DESC"
+    )
 
     def _get_sessions(self, cutoff: float, source: str = None) -> List[Dict]:
         """Fetch sessions within the time window."""
         if source:
-            cursor = self._conn.execute(
-                f"""SELECT {self._SESSION_COLS} FROM sessions
-                    WHERE started_at >= ? AND source = ?
-                    ORDER BY started_at DESC""",
-                (cutoff, source),
-            )
+            cursor = self._conn.execute(self._GET_SESSIONS_WITH_SOURCE, (cutoff, source))
         else:
-            cursor = self._conn.execute(
-                f"""SELECT {self._SESSION_COLS} FROM sessions
-                    WHERE started_at >= ?
-                    ORDER BY started_at DESC""",
-                (cutoff,),
-            )
+            cursor = self._conn.execute(self._GET_SESSIONS_ALL, (cutoff,))
         return [dict(row) for row in cursor.fetchall()]
 
     def _get_tool_usage(self, cutoff: float, source: str = None) -> List[Dict]:
@@ -386,21 +334,30 @@ class InsightsEngine:
         """Compute high-level overview statistics."""
         total_input = sum(s.get("input_tokens") or 0 for s in sessions)
         total_output = sum(s.get("output_tokens") or 0 for s in sessions)
-        total_tokens = total_input + total_output
+        total_cache_read = sum(s.get("cache_read_tokens") or 0 for s in sessions)
+        total_cache_write = sum(s.get("cache_write_tokens") or 0 for s in sessions)
+        total_tokens = total_input + total_output + total_cache_read + total_cache_write
         total_tool_calls = sum(s.get("tool_call_count") or 0 for s in sessions)
         total_messages = sum(s.get("message_count") or 0 for s in sessions)
 
         # Cost estimation (weighted by model)
         total_cost = 0.0
+        actual_cost = 0.0
         models_with_pricing = set()
         models_without_pricing = set()
+        unknown_cost_sessions = 0
+        included_cost_sessions = 0
         for s in sessions:
             model = s.get("model") or ""
-            inp = s.get("input_tokens") or 0
-            out = s.get("output_tokens") or 0
-            total_cost += _estimate_cost(model, inp, out)
+            estimated, status = _estimate_cost(s)
+            total_cost += estimated
+            actual_cost += s.get("actual_cost_usd") or 0.0
             display = model.split("/")[-1] if "/" in model else (model or "unknown")
-            if _has_known_pricing(model):
+            if status == "included":
+                included_cost_sessions += 1
+            elif status == "unknown":
+                unknown_cost_sessions += 1
+            if _has_known_pricing(model, s.get("billing_provider"), s.get("billing_base_url")):
                 models_with_pricing.add(display)
             else:
                 models_without_pricing.add(display)
@@ -427,8 +384,11 @@ class InsightsEngine:
             "total_tool_calls": total_tool_calls,
             "total_input_tokens": total_input,
             "total_output_tokens": total_output,
+            "total_cache_read_tokens": total_cache_read,
+            "total_cache_write_tokens": total_cache_write,
             "total_tokens": total_tokens,
             "estimated_cost": total_cost,
+            "actual_cost": actual_cost,
             "total_hours": total_hours,
             "avg_session_duration": avg_duration,
             "avg_messages_per_session": total_messages / len(sessions) if sessions else 0,
@@ -440,12 +400,15 @@ class InsightsEngine:
             "date_range_end": date_range_end,
             "models_with_pricing": sorted(models_with_pricing),
             "models_without_pricing": sorted(models_without_pricing),
+            "unknown_cost_sessions": unknown_cost_sessions,
+            "included_cost_sessions": included_cost_sessions,
         }
 
     def _compute_model_breakdown(self, sessions: List[Dict]) -> List[Dict]:
         """Break down usage by model."""
         model_data = defaultdict(lambda: {
             "sessions": 0, "input_tokens": 0, "output_tokens": 0,
+            "cache_read_tokens": 0, "cache_write_tokens": 0,
             "total_tokens": 0, "tool_calls": 0, "cost": 0.0,
         })
 
@@ -457,12 +420,18 @@ class InsightsEngine:
             d["sessions"] += 1
             inp = s.get("input_tokens") or 0
             out = s.get("output_tokens") or 0
+            cache_read = s.get("cache_read_tokens") or 0
+            cache_write = s.get("cache_write_tokens") or 0
             d["input_tokens"] += inp
             d["output_tokens"] += out
-            d["total_tokens"] += inp + out
+            d["cache_read_tokens"] += cache_read
+            d["cache_write_tokens"] += cache_write
+            d["total_tokens"] += inp + out + cache_read + cache_write
             d["tool_calls"] += s.get("tool_call_count") or 0
-            d["cost"] += _estimate_cost(model, inp, out)
-            d["has_pricing"] = _has_known_pricing(model)
+            estimate, status = _estimate_cost(s)
+            d["cost"] += estimate
+            d["has_pricing"] = _has_known_pricing(model, s.get("billing_provider"), s.get("billing_base_url"))
+            d["cost_status"] = status
 
         result = [
             {"model": model, **data}
@@ -476,7 +445,8 @@ class InsightsEngine:
         """Break down usage by platform/source."""
         platform_data = defaultdict(lambda: {
             "sessions": 0, "messages": 0, "input_tokens": 0,
-            "output_tokens": 0, "total_tokens": 0, "tool_calls": 0,
+            "output_tokens": 0, "cache_read_tokens": 0,
+            "cache_write_tokens": 0, "total_tokens": 0, "tool_calls": 0,
         })
 
         for s in sessions:
@@ -486,9 +456,13 @@ class InsightsEngine:
             d["messages"] += s.get("message_count") or 0
             inp = s.get("input_tokens") or 0
             out = s.get("output_tokens") or 0
+            cache_read = s.get("cache_read_tokens") or 0
+            cache_write = s.get("cache_write_tokens") or 0
             d["input_tokens"] += inp
             d["output_tokens"] += out
-            d["total_tokens"] += inp + out
+            d["cache_read_tokens"] += cache_read
+            d["cache_write_tokens"] += cache_write
+            d["total_tokens"] += inp + out + cache_read + cache_write
             d["tool_calls"] += s.get("tool_call_count") or 0
 
         result = [
@@ -692,7 +666,7 @@ class InsightsEngine:
                     cost_cell = "     N/A"
                 lines.append(f"  {model_name:<30} {m['sessions']:>8} {m['total_tokens']:>12,} {cost_cell}")
             if o.get("models_without_pricing"):
-                lines.append(f"  * Cost N/A for custom/self-hosted models")
+                lines.append("  * Cost N/A for custom/self-hosted models")
             lines.append("")
 
         # Platform breakdown

agent/model_metadata.py

@@ -10,6 +10,7 @@ import re
 import time
 from pathlib import Path
 from typing import Any, Dict, List, Optional
+from urllib.parse import urlparse
 
 import requests
 import yaml
@@ -18,50 +19,356 @@ from hermes_constants import OPENROUTER_MODELS_URL
 
 logger = logging.getLogger(__name__)
 
+# Provider names that can appear as a "provider:" prefix before a model ID.
+# Only these are stripped — Ollama-style "model:tag" colons (e.g. "qwen3.5:27b")
+# are preserved so the full model name reaches cache lookups and server queries.
+_PROVIDER_PREFIXES: frozenset[str] = frozenset({
+    "openrouter", "nous", "openai-codex", "copilot", "copilot-acp",
+    "zai", "kimi-coding", "minimax", "minimax-cn", "anthropic", "deepseek",
+    "opencode-zen", "opencode-go", "ai-gateway", "kilocode", "alibaba",
+    "custom", "local",
+    # Common aliases
+    "glm", "z-ai", "z.ai", "zhipu", "github", "github-copilot",
+    "github-models", "kimi", "moonshot", "claude", "deep-seek",
+    "opencode", "zen", "go", "vercel", "kilo", "dashscope", "aliyun", "qwen",
+})
+
+
+_OLLAMA_TAG_PATTERN = re.compile(
+    r"^(\d+\.?\d*b|latest|stable|q\d|fp?\d|instruct|chat|coder|vision|text)",
+    re.IGNORECASE,
+)
+
+
+def _strip_provider_prefix(model: str) -> str:
+    """Strip a recognised provider prefix from a model string.
+
+    ``"local:my-model"`` → ``"my-model"``
+    ``"qwen3.5:27b"``   → ``"qwen3.5:27b"``  (unchanged — not a provider prefix)
+    ``"qwen:0.5b"``     → ``"qwen:0.5b"``    (unchanged — Ollama model:tag)
+    ``"deepseek:latest"``→ ``"deepseek:latest"``(unchanged — Ollama model:tag)
+    """
+    if ":" not in model or model.startswith("http"):
+        return model
+    prefix, suffix = model.split(":", 1)
+    prefix_lower = prefix.strip().lower()
+    if prefix_lower in _PROVIDER_PREFIXES:
+        # Don't strip if suffix looks like an Ollama tag (e.g. "7b", "latest", "q4_0")
+        if _OLLAMA_TAG_PATTERN.match(suffix.strip()):
+            return model
+        return suffix
+    return model
+
 _model_metadata_cache: Dict[str, Dict[str, Any]] = {}
 _model_metadata_cache_time: float = 0
 _MODEL_CACHE_TTL = 3600
+_endpoint_model_metadata_cache: Dict[str, Dict[str, Dict[str, Any]]] = {}
+_endpoint_model_metadata_cache_time: Dict[str, float] = {}
+_ENDPOINT_MODEL_CACHE_TTL = 300
 
 # Descending tiers for context length probing when the model is unknown.
-# We start high and step down on context-length errors until one works.
+# We start at 128K (a safe default for most modern models) and step down
+# on context-length errors until one works.
 CONTEXT_PROBE_TIERS = [
-    2_000_000,
-    1_000_000,
-    512_000,
-    200_000,
     128_000,
     64_000,
     32_000,
+    16_000,
+    8_000,
 ]
 
+# Default context length when no detection method succeeds.
+DEFAULT_FALLBACK_CONTEXT = CONTEXT_PROBE_TIERS[0]
+
+# Thin fallback defaults — only broad model family patterns.
+# These fire only when provider is unknown AND models.dev/OpenRouter/Anthropic
+# all miss. Replaced the previous 80+ entry dict.
+# For provider-specific context lengths, models.dev is the primary source.
 DEFAULT_CONTEXT_LENGTHS = {
-    "anthropic/claude-opus-4": 200000,
-    "anthropic/claude-opus-4.5": 200000,
-    "anthropic/claude-opus-4.6": 200000,
-    "anthropic/claude-sonnet-4": 200000,
-    "anthropic/claude-sonnet-4-20250514": 200000,
-    "anthropic/claude-haiku-4.5": 200000,
-    "openai/gpt-4o": 128000,
-    "openai/gpt-4-turbo": 128000,
-    "openai/gpt-4o-mini": 128000,
-    "google/gemini-2.0-flash": 1048576,
-    "google/gemini-2.5-pro": 1048576,
-    "meta-llama/llama-3.3-70b-instruct": 131072,
-    "deepseek/deepseek-chat-v3": 65536,
-    "qwen/qwen-2.5-72b-instruct": 32768,
-    "glm-4.7": 202752,
-    "glm-5": 202752,
-    "glm-4.5": 131072,
-    "glm-4.5-flash": 131072,
-    "kimi-k2.5": 262144,
-    "kimi-k2-thinking": 262144,
-    "kimi-k2-turbo-preview": 262144,
-    "kimi-k2-0905-preview": 131072,
-    "MiniMax-M2.5": 204800,
-    "MiniMax-M2.5-highspeed": 204800,
-    "MiniMax-M2.1": 204800,
+    # Anthropic Claude 4.6 (1M context) — bare IDs only to avoid
+    # fuzzy-match collisions (e.g. "anthropic/claude-sonnet-4" is a
+    # substring of "anthropic/claude-sonnet-4.6").
+    # OpenRouter-prefixed models resolve via OpenRouter live API or models.dev.
+    "claude-opus-4-6": 1000000,
+    "claude-sonnet-4-6": 1000000,
+    "claude-opus-4.6": 1000000,
+    "claude-sonnet-4.6": 1000000,
+    # Catch-all for older Claude models (must sort after specific entries)
+    "claude": 200000,
+    # OpenAI
+    "gpt-4.1": 1047576,
+    "gpt-5": 128000,
+    "gpt-4": 128000,
+    # Google
+    "gemini": 1048576,
+    # DeepSeek
+    "deepseek": 128000,
+    # Meta
+    "llama": 131072,
+    # Qwen
+    "qwen": 131072,
+    # MiniMax
+    "minimax": 204800,
+    # GLM
+    "glm": 202752,
+    # Kimi
+    "kimi": 262144,
+    # Hugging Face Inference Providers — model IDs use org/name format
+    "Qwen/Qwen3.5-397B-A17B": 131072,
+    "Qwen/Qwen3.5-35B-A3B": 131072,
+    "deepseek-ai/DeepSeek-V3.2": 65536,
+    "moonshotai/Kimi-K2.5": 262144,
+    "moonshotai/Kimi-K2-Thinking": 262144,
+    "MiniMaxAI/MiniMax-M2.5": 204800,
+    "XiaomiMiMo/MiMo-V2-Flash": 32768,
+    "zai-org/GLM-5": 202752,
 }
 
+_CONTEXT_LENGTH_KEYS = (
+    "context_length",
+    "context_window",
+    "max_context_length",
+    "max_position_embeddings",
+    "max_model_len",
+    "max_input_tokens",
+    "max_sequence_length",
+    "max_seq_len",
+    "n_ctx_train",
+    "n_ctx",
+)
+
+_MAX_COMPLETION_KEYS = (
+    "max_completion_tokens",
+    "max_output_tokens",
+    "max_tokens",
+)
+
+# Local server hostnames / address patterns
+_LOCAL_HOSTS = ("localhost", "127.0.0.1", "::1", "0.0.0.0")
+
+
+def _normalize_base_url(base_url: str) -> str:
+    return (base_url or "").strip().rstrip("/")
+
+
+def _is_openrouter_base_url(base_url: str) -> bool:
+    return "openrouter.ai" in _normalize_base_url(base_url).lower()
+
+
+def _is_custom_endpoint(base_url: str) -> bool:
+    normalized = _normalize_base_url(base_url)
+    return bool(normalized) and not _is_openrouter_base_url(normalized)
+
+
+_URL_TO_PROVIDER: Dict[str, str] = {
+    "api.openai.com": "openai",
+    "chatgpt.com": "openai",
+    "api.anthropic.com": "anthropic",
+    "api.z.ai": "zai",
+    "api.moonshot.ai": "kimi-coding",
+    "api.kimi.com": "kimi-coding",
+    "api.minimax": "minimax",
+    "dashscope.aliyuncs.com": "alibaba",
+    "dashscope-intl.aliyuncs.com": "alibaba",
+    "openrouter.ai": "openrouter",
+    "generativelanguage.googleapis.com": "google",
+    "inference-api.nousresearch.com": "nous",
+    "api.deepseek.com": "deepseek",
+    "api.githubcopilot.com": "copilot",
+    "models.github.ai": "copilot",
+}
+
+
+def _infer_provider_from_url(base_url: str) -> Optional[str]:
+    """Infer the models.dev provider name from a base URL.
+
+    This allows context length resolution via models.dev for custom endpoints
+    like DashScope (Alibaba), Z.AI, Kimi, etc. without requiring the user to
+    explicitly set the provider name in config.
+    """
+    normalized = _normalize_base_url(base_url)
+    if not normalized:
+        return None
+    parsed = urlparse(normalized if "://" in normalized else f"https://{normalized}")
+    host = parsed.netloc.lower() or parsed.path.lower()
+    for url_part, provider in _URL_TO_PROVIDER.items():
+        if url_part in host:
+            return provider
+    return None
+
+
+def _is_known_provider_base_url(base_url: str) -> bool:
+    return _infer_provider_from_url(base_url) is not None
+
+
+def is_local_endpoint(base_url: str) -> bool:
+    """Return True if base_url points to a local machine (localhost / RFC-1918 / WSL)."""
+    normalized = _normalize_base_url(base_url)
+    if not normalized:
+        return False
+    url = normalized if "://" in normalized else f"http://{normalized}"
+    try:
+        parsed = urlparse(url)
+        host = parsed.hostname or ""
+    except Exception:
+        return False
+    if host in _LOCAL_HOSTS:
+        return True
+    # RFC-1918 private ranges and link-local
+    import ipaddress
+    try:
+        addr = ipaddress.ip_address(host)
+        return addr.is_private or addr.is_loopback or addr.is_link_local
+    except ValueError:
+        pass
+    # Bare IP that looks like a private range (e.g. 172.26.x.x for WSL)
+    parts = host.split(".")
+    if len(parts) == 4:
+        try:
+            first, second = int(parts[0]), int(parts[1])
+            if first == 10:
+                return True
+            if first == 172 and 16 <= second <= 31:
+                return True
+            if first == 192 and second == 168:
+                return True
+        except ValueError:
+            pass
+    return False
+
+
+def detect_local_server_type(base_url: str) -> Optional[str]:
+    """Detect which local server is running at base_url by probing known endpoints.
+
+    Returns one of: "ollama", "lm-studio", "vllm", "llamacpp", or None.
+    """
+    import httpx
+
+    normalized = _normalize_base_url(base_url)
+    server_url = normalized
+    if server_url.endswith("/v1"):
+        server_url = server_url[:-3]
+
+    try:
+        with httpx.Client(timeout=2.0) as client:
+            # LM Studio exposes /api/v1/models — check first (most specific)
+            try:
+                r = client.get(f"{server_url}/api/v1/models")
+                if r.status_code == 200:
+                    return "lm-studio"
+            except Exception:
+                pass
+            # Ollama exposes /api/tags and responds with {"models": [...]}
+            # LM Studio returns {"error": "Unexpected endpoint"} with status 200
+            # on this path, so we must verify the response contains "models".
+            try:
+                r = client.get(f"{server_url}/api/tags")
+                if r.status_code == 200:
+                    try:
+                        data = r.json()
+                        if "models" in data:
+                            return "ollama"
+                    except Exception:
+                        pass
+            except Exception:
+                pass
+            # llama.cpp exposes /v1/props (older builds used /props without the /v1 prefix)
+            try:
+                r = client.get(f"{server_url}/v1/props")
+                if r.status_code != 200:
+                    r = client.get(f"{server_url}/props")  # fallback for older builds
+                if r.status_code == 200 and "default_generation_settings" in r.text:
+                    return "llamacpp"
+            except Exception:
+                pass
+            # vLLM: /version
+            try:
+                r = client.get(f"{server_url}/version")
+                if r.status_code == 200:
+                    data = r.json()
+                    if "version" in data:
+                        return "vllm"
+            except Exception:
+                pass
+    except Exception:
+        pass
+
+    return None
+
+
+def _iter_nested_dicts(value: Any):
+    if isinstance(value, dict):
+        yield value
+        for nested in value.values():
+            yield from _iter_nested_dicts(nested)
+    elif isinstance(value, list):
+        for item in value:
+            yield from _iter_nested_dicts(item)
+
+
+def _coerce_reasonable_int(value: Any, minimum: int = 1024, maximum: int = 10_000_000) -> Optional[int]:
+    try:
+        if isinstance(value, bool):
+            return None
+        if isinstance(value, str):
+            value = value.strip().replace(",", "")
+        result = int(value)
+    except (TypeError, ValueError):
+        return None
+    if minimum <= result <= maximum:
+        return result
+    return None
+
+
+def _extract_first_int(payload: Dict[str, Any], keys: tuple[str, ...]) -> Optional[int]:
+    keyset = {key.lower() for key in keys}
+    for mapping in _iter_nested_dicts(payload):
+        for key, value in mapping.items():
+            if str(key).lower() not in keyset:
+                continue
+            coerced = _coerce_reasonable_int(value)
+            if coerced is not None:
+                return coerced
+    return None
+
+
+def _extract_context_length(payload: Dict[str, Any]) -> Optional[int]:
+    return _extract_first_int(payload, _CONTEXT_LENGTH_KEYS)
+
+
+def _extract_max_completion_tokens(payload: Dict[str, Any]) -> Optional[int]:
+    return _extract_first_int(payload, _MAX_COMPLETION_KEYS)
+
+
+def _extract_pricing(payload: Dict[str, Any]) -> Dict[str, Any]:
+    alias_map = {
+        "prompt": ("prompt", "input", "input_cost_per_token", "prompt_token_cost"),
+        "completion": ("completion", "output", "output_cost_per_token", "completion_token_cost"),
+        "request": ("request", "request_cost"),
+        "cache_read": ("cache_read", "cached_prompt", "input_cache_read", "cache_read_cost_per_token"),
+        "cache_write": ("cache_write", "cache_creation", "input_cache_write", "cache_write_cost_per_token"),
+    }
+    for mapping in _iter_nested_dicts(payload):
+        normalized = {str(key).lower(): value for key, value in mapping.items()}
+        if not any(any(alias in normalized for alias in aliases) for aliases in alias_map.values()):
+            continue
+        pricing: Dict[str, Any] = {}
+        for target, aliases in alias_map.items():
+            for alias in aliases:
+                if alias in normalized and normalized[alias] not in (None, ""):
+                    pricing[target] = normalized[alias]
+                    break
+        if pricing:
+            return pricing
+    return {}
+
+
+def _add_model_aliases(cache: Dict[str, Dict[str, Any]], model_id: str, entry: Dict[str, Any]) -> None:
+    cache[model_id] = entry
+    if "/" in model_id:
+        bare_model = model_id.split("/", 1)[1]
+        cache.setdefault(bare_model, entry)
+
 
 def fetch_model_metadata(force_refresh: bool = False) -> Dict[str, Dict[str, Any]]:
     """Fetch model metadata from OpenRouter (cached for 1 hour)."""
@@ -78,15 +385,16 @@ def fetch_model_metadata(force_refresh: bool = False) -> Dict[str, Dict[str, Any
         cache = {}
         for model in data.get("data", []):
             model_id = model.get("id", "")
-            cache[model_id] = {
+            entry = {
                 "context_length": model.get("context_length", 128000),
                 "max_completion_tokens": model.get("top_provider", {}).get("max_completion_tokens", 4096),
                 "name": model.get("name", model_id),
                 "pricing": model.get("pricing", {}),
             }
+            _add_model_aliases(cache, model_id, entry)
             canonical = model.get("canonical_slug", "")
             if canonical and canonical != model_id:
-                cache[canonical] = cache[model_id]
+                _add_model_aliases(cache, canonical, entry)
 
         _model_metadata_cache = cache
         _model_metadata_cache_time = time.time()
@@ -98,6 +406,97 @@ def fetch_model_metadata(force_refresh: bool = False) -> Dict[str, Dict[str, Any
         return _model_metadata_cache or {}
 
 
+def fetch_endpoint_model_metadata(
+    base_url: str,
+    api_key: str = "",
+    force_refresh: bool = False,
+) -> Dict[str, Dict[str, Any]]:
+    """Fetch model metadata from an OpenAI-compatible ``/models`` endpoint.
+
+    This is used for explicit custom endpoints where hardcoded global model-name
+    defaults are unreliable. Results are cached in memory per base URL.
+    """
+    normalized = _normalize_base_url(base_url)
+    if not normalized or _is_openrouter_base_url(normalized):
+        return {}
+
+    if not force_refresh:
+        cached = _endpoint_model_metadata_cache.get(normalized)
+        cached_at = _endpoint_model_metadata_cache_time.get(normalized, 0)
+        if cached is not None and (time.time() - cached_at) < _ENDPOINT_MODEL_CACHE_TTL:
+            return cached
+
+    candidates = [normalized]
+    if normalized.endswith("/v1"):
+        alternate = normalized[:-3].rstrip("/")
+    else:
+        alternate = normalized + "/v1"
+    if alternate and alternate not in candidates:
+        candidates.append(alternate)
+
+    headers = {"Authorization": f"Bearer {api_key}"} if api_key else {}
+    last_error: Optional[Exception] = None
+
+    for candidate in candidates:
+        url = candidate.rstrip("/") + "/models"
+        try:
+            response = requests.get(url, headers=headers, timeout=10)
+            response.raise_for_status()
+            payload = response.json()
+            cache: Dict[str, Dict[str, Any]] = {}
+            for model in payload.get("data", []):
+                if not isinstance(model, dict):
+                    continue
+                model_id = model.get("id")
+                if not model_id:
+                    continue
+                entry: Dict[str, Any] = {"name": model.get("name", model_id)}
+                context_length = _extract_context_length(model)
+                if context_length is not None:
+                    entry["context_length"] = context_length
+                max_completion_tokens = _extract_max_completion_tokens(model)
+                if max_completion_tokens is not None:
+                    entry["max_completion_tokens"] = max_completion_tokens
+                pricing = _extract_pricing(model)
+                if pricing:
+                    entry["pricing"] = pricing
+                _add_model_aliases(cache, model_id, entry)
+
+            # If this is a llama.cpp server, query /props for actual allocated context
+            is_llamacpp = any(
+                m.get("owned_by") == "llamacpp"
+                for m in payload.get("data", []) if isinstance(m, dict)
+            )
+            if is_llamacpp:
+                try:
+                    # Try /v1/props first (current llama.cpp); fall back to /props for older builds
+                    base = candidate.rstrip("/").replace("/v1", "")
+                    props_resp = requests.get(base + "/v1/props", headers=headers, timeout=5)
+                    if not props_resp.ok:
+                        props_resp = requests.get(base + "/props", headers=headers, timeout=5)
+                    if props_resp.ok:
+                        props = props_resp.json()
+                        gen_settings = props.get("default_generation_settings", {})
+                        n_ctx = gen_settings.get("n_ctx")
+                        model_alias = props.get("model_alias", "")
+                        if n_ctx and model_alias and model_alias in cache:
+                            cache[model_alias]["context_length"] = n_ctx
+                except Exception:
+                    pass
+
+            _endpoint_model_metadata_cache[normalized] = cache
+            _endpoint_model_metadata_cache_time[normalized] = time.time()
+            return cache
+        except Exception as exc:
+            last_error = exc
+
+    if last_error:
+        logger.debug("Failed to fetch model metadata from %s/models: %s", normalized, last_error)
+    _endpoint_model_metadata_cache[normalized] = {}
+    _endpoint_model_metadata_cache_time[normalized] = time.time()
+    return {}
+
+
 def _get_context_cache_path() -> Path:
     """Return path to the persistent context length cache file."""
     hermes_home = Path(os.environ.get("HERMES_HOME", Path.home() / ".hermes"))
@@ -105,7 +504,7 @@ def _get_context_cache_path() -> Path:
 
 
 def _load_context_cache() -> Dict[str, int]:
-    """Load the model+provider → context_length cache from disk."""
+    """Load the model+provider -> context_length cache from disk."""
     path = _get_context_cache_path()
     if not path.exists():
         return {}
@@ -134,7 +533,7 @@ def save_context_length(model: str, base_url: str, length: int) -> None:
         path.parent.mkdir(parents=True, exist_ok=True)
         with open(path, "w") as f:
             yaml.dump({"context_lengths": cache}, f, default_flow_style=False)
-        logger.info("Cached context length %s → %s tokens", key, f"{length:,}")
+        logger.info("Cached context length %s -> %s tokens", key, f"{length:,}")
     except Exception as e:
         logger.debug("Failed to save context length cache: %s", e)
 
@@ -182,33 +581,317 @@ def parse_context_limit_from_error(error_msg: str) -> Optional[int]:
     return None
 
 
-def get_model_context_length(model: str, base_url: str = "") -> int:
+def _model_id_matches(candidate_id: str, lookup_model: str) -> bool:
+    """Return True if *candidate_id* (from server) matches *lookup_model* (configured).
+
+    Supports two forms:
+    - Exact match:  "nvidia-nemotron-super-49b-v1" == "nvidia-nemotron-super-49b-v1"
+    - Slug match:   "nvidia/nvidia-nemotron-super-49b-v1" matches "nvidia-nemotron-super-49b-v1"
+                    (the part after the last "/" equals lookup_model)
+
+    This covers LM Studio's native API which stores models as "publisher/slug"
+    while users typically configure only the slug after the "local:" prefix.
+    """
+    if candidate_id == lookup_model:
+        return True
+    # Slug match: basename of candidate equals the lookup name
+    if "/" in candidate_id and candidate_id.rsplit("/", 1)[1] == lookup_model:
+        return True
+    return False
+
+
+def _query_local_context_length(model: str, base_url: str) -> Optional[int]:
+    """Query a local server for the model's context length."""
+    import httpx
+
+    # Strip recognised provider prefix (e.g., "local:model-name" → "model-name").
+    # Ollama "model:tag" colons (e.g. "qwen3.5:27b") are intentionally preserved.
+    model = _strip_provider_prefix(model)
+
+    # Strip /v1 suffix to get the server root
+    server_url = base_url.rstrip("/")
+    if server_url.endswith("/v1"):
+        server_url = server_url[:-3]
+
+    try:
+        server_type = detect_local_server_type(base_url)
+    except Exception:
+        server_type = None
+
+    try:
+        with httpx.Client(timeout=3.0) as client:
+            # Ollama: /api/show returns model details with context info
+            if server_type == "ollama":
+                resp = client.post(f"{server_url}/api/show", json={"name": model})
+                if resp.status_code == 200:
+                    data = resp.json()
+                    # Check model_info for context length
+                    model_info = data.get("model_info", {})
+                    for key, value in model_info.items():
+                        if "context_length" in key and isinstance(value, (int, float)):
+                            return int(value)
+                    # Check parameters string for num_ctx
+                    params = data.get("parameters", "")
+                    if "num_ctx" in params:
+                        for line in params.split("\n"):
+                            if "num_ctx" in line:
+                                parts = line.strip().split()
+                                if len(parts) >= 2:
+                                    try:
+                                        return int(parts[-1])
+                                    except ValueError:
+                                        pass
+
+            # LM Studio native API: /api/v1/models returns max_context_length.
+            # This is more reliable than the OpenAI-compat /v1/models which
+            # doesn't include context window information for LM Studio servers.
+            # Use _model_id_matches for fuzzy matching: LM Studio stores models as
+            # "publisher/slug" but users configure only "slug" after "local:" prefix.
+            if server_type == "lm-studio":
+                resp = client.get(f"{server_url}/api/v1/models")
+                if resp.status_code == 200:
+                    data = resp.json()
+                    for m in data.get("models", []):
+                        if _model_id_matches(m.get("key", ""), model) or _model_id_matches(m.get("id", ""), model):
+                            # Prefer loaded instance context (actual runtime value)
+                            for inst in m.get("loaded_instances", []):
+                                cfg = inst.get("config", {})
+                                ctx = cfg.get("context_length")
+                                if ctx and isinstance(ctx, (int, float)):
+                                    return int(ctx)
+                            # Fall back to max_context_length (theoretical model max)
+                            ctx = m.get("max_context_length") or m.get("context_length")
+                            if ctx and isinstance(ctx, (int, float)):
+                                return int(ctx)
+
+            # LM Studio / vLLM / llama.cpp: try /v1/models/{model}
+            resp = client.get(f"{server_url}/v1/models/{model}")
+            if resp.status_code == 200:
+                data = resp.json()
+                # vLLM returns max_model_len
+                ctx = data.get("max_model_len") or data.get("context_length") or data.get("max_tokens")
+                if ctx and isinstance(ctx, (int, float)):
+                    return int(ctx)
+
+            # Try /v1/models and find the model in the list.
+            # Use _model_id_matches to handle "publisher/slug" vs bare "slug".
+            resp = client.get(f"{server_url}/v1/models")
+            if resp.status_code == 200:
+                data = resp.json()
+                models_list = data.get("data", [])
+                for m in models_list:
+                    if _model_id_matches(m.get("id", ""), model):
+                        ctx = m.get("max_model_len") or m.get("context_length") or m.get("max_tokens")
+                        if ctx and isinstance(ctx, (int, float)):
+                            return int(ctx)
+    except Exception:
+        pass
+
+    return None
+
+
+def _normalize_model_version(model: str) -> str:
+    """Normalize version separators for matching.
+
+    Nous uses dashes: claude-opus-4-6, claude-sonnet-4-5
+    OpenRouter uses dots: claude-opus-4.6, claude-sonnet-4.5
+    Normalize both to dashes for comparison.
+    """
+    return model.replace(".", "-")
+
+
+def _query_anthropic_context_length(model: str, base_url: str, api_key: str) -> Optional[int]:
+    """Query Anthropic's /v1/models endpoint for context length.
+
+    Only works with regular ANTHROPIC_API_KEY (sk-ant-api*).
+    OAuth tokens (sk-ant-oat*) from Claude Code return 401.
+    """
+    if not api_key or api_key.startswith("sk-ant-oat"):
+        return None  # OAuth tokens can't access /v1/models
+    try:
+        base = base_url.rstrip("/")
+        if base.endswith("/v1"):
+            base = base[:-3]
+        url = f"{base}/v1/models?limit=1000"
+        headers = {
+            "x-api-key": api_key,
+            "anthropic-version": "2023-06-01",
+        }
+        resp = requests.get(url, headers=headers, timeout=10)
+        if resp.status_code != 200:
+            return None
+        data = resp.json()
+        for m in data.get("data", []):
+            if m.get("id") == model:
+                ctx = m.get("max_input_tokens")
+                if isinstance(ctx, int) and ctx > 0:
+                    return ctx
+    except Exception as e:
+        logger.debug("Anthropic /v1/models query failed: %s", e)
+    return None
+
+
+def _resolve_nous_context_length(model: str) -> Optional[int]:
+    """Resolve Nous Portal model context length via OpenRouter metadata.
+
+    Nous model IDs are bare (e.g. 'claude-opus-4-6') while OpenRouter uses
+    prefixed IDs (e.g. 'anthropic/claude-opus-4.6'). Try suffix matching
+    with version normalization (dot↔dash).
+    """
+    metadata = fetch_model_metadata()  # OpenRouter cache
+    # Exact match first
+    if model in metadata:
+        return metadata[model].get("context_length")
+
+    normalized = _normalize_model_version(model).lower()
+
+    for or_id, entry in metadata.items():
+        bare = or_id.split("/", 1)[1] if "/" in or_id else or_id
+        if bare.lower() == model.lower() or _normalize_model_version(bare).lower() == normalized:
+            return entry.get("context_length")
+
+    # Partial prefix match for cases like gemini-3-flash → gemini-3-flash-preview
+    # Require match to be at a word boundary (followed by -, :, or end of string)
+    model_lower = model.lower()
+    for or_id, entry in metadata.items():
+        bare = or_id.split("/", 1)[1] if "/" in or_id else or_id
+        for candidate, query in [(bare.lower(), model_lower), (_normalize_model_version(bare).lower(), normalized)]:
+            if candidate.startswith(query) and (
+                len(candidate) == len(query) or candidate[len(query)] in "-:."
+            ):
+                return entry.get("context_length")
+
+    return None
+
+
+def get_model_context_length(
+    model: str,
+    base_url: str = "",
+    api_key: str = "",
+    config_context_length: int | None = None,
+    provider: str = "",
+) -> int:
     """Get the context length for a model.
 
     Resolution order:
+    0. Explicit config override (model.context_length or custom_providers per-model)
     1. Persistent cache (previously discovered via probing)
-    2. OpenRouter API metadata
-    3. Hardcoded DEFAULT_CONTEXT_LENGTHS (fuzzy match)
-    4. First probe tier (2M) — will be narrowed on first context error
+    2. Active endpoint metadata (/models for explicit custom endpoints)
+    3. Local server query (for local endpoints)
+    4. Anthropic /v1/models API (API-key users only, not OAuth)
+    5. OpenRouter live API metadata
+    6. Nous suffix-match via OpenRouter cache
+    7. models.dev registry lookup (provider-aware)
+    8. Thin hardcoded defaults (broad family patterns)
+    9. Default fallback (128K)
     """
+    # 0. Explicit config override — user knows best
+    if config_context_length is not None and isinstance(config_context_length, int) and config_context_length > 0:
+        return config_context_length
+
+    # Normalise provider-prefixed model names (e.g. "local:model-name" →
+    # "model-name") so cache lookups and server queries use the bare ID that
+    # local servers actually know about.  Ollama "model:tag" colons are preserved.
+    model = _strip_provider_prefix(model)
+
     # 1. Check persistent cache (model+provider)
     if base_url:
         cached = get_cached_context_length(model, base_url)
         if cached is not None:
             return cached
 
-    # 2. OpenRouter API metadata
+    # 2. Active endpoint metadata for truly custom/unknown endpoints.
+    # Known providers (Copilot, OpenAI, Anthropic, etc.) skip this — their
+    # /models endpoint may report a provider-imposed limit (e.g. Copilot
+    # returns 128k) instead of the model's full context (400k).  models.dev
+    # has the correct per-provider values and is checked at step 5+.
+    if _is_custom_endpoint(base_url) and not _is_known_provider_base_url(base_url):
+        endpoint_metadata = fetch_endpoint_model_metadata(base_url, api_key=api_key)
+        matched = endpoint_metadata.get(model)
+        if not matched:
+            # Single-model servers: if only one model is loaded, use it
+            if len(endpoint_metadata) == 1:
+                matched = next(iter(endpoint_metadata.values()))
+            else:
+                # Fuzzy match: substring in either direction
+                for key, entry in endpoint_metadata.items():
+                    if model in key or key in model:
+                        matched = entry
+                        break
+        if matched:
+            context_length = matched.get("context_length")
+            if isinstance(context_length, int):
+                return context_length
+        if not _is_known_provider_base_url(base_url):
+            # 3. Try querying local server directly
+            if is_local_endpoint(base_url):
+                local_ctx = _query_local_context_length(model, base_url)
+                if local_ctx and local_ctx > 0:
+                    save_context_length(model, base_url, local_ctx)
+                    return local_ctx
+            logger.info(
+                "Could not detect context length for model %r at %s — "
+                "defaulting to %s tokens (probe-down). Set model.context_length "
+                "in config.yaml to override.",
+                model, base_url, f"{DEFAULT_FALLBACK_CONTEXT:,}",
+            )
+            return DEFAULT_FALLBACK_CONTEXT
+
+    # 4. Anthropic /v1/models API (only for regular API keys, not OAuth)
+    if provider == "anthropic" or (
+        base_url and "api.anthropic.com" in base_url
+    ):
+        ctx = _query_anthropic_context_length(model, base_url or "https://api.anthropic.com", api_key)
+        if ctx:
+            return ctx
+
+    # 5. Provider-aware lookups (before generic OpenRouter cache)
+    # These are provider-specific and take priority over the generic OR cache,
+    # since the same model can have different context limits per provider
+    # (e.g. claude-opus-4.6 is 1M on Anthropic but 128K on GitHub Copilot).
+    # If provider is generic (openrouter/custom/empty), try to infer from URL.
+    effective_provider = provider
+    if not effective_provider or effective_provider in ("openrouter", "custom"):
+        if base_url:
+            inferred = _infer_provider_from_url(base_url)
+            if inferred:
+                effective_provider = inferred
+
+    if effective_provider == "nous":
+        ctx = _resolve_nous_context_length(model)
+        if ctx:
+            return ctx
+    if effective_provider:
+        from agent.models_dev import lookup_models_dev_context
+        ctx = lookup_models_dev_context(effective_provider, model)
+        if ctx:
+            return ctx
+
+    # 6. OpenRouter live API metadata (provider-unaware fallback)
     metadata = fetch_model_metadata()
     if model in metadata:
         return metadata[model].get("context_length", 128000)
 
-    # 3. Hardcoded defaults (fuzzy match)
-    for default_model, length in DEFAULT_CONTEXT_LENGTHS.items():
-        if default_model in model or model in default_model:
+    # 8. Hardcoded defaults (fuzzy match — longest key first for specificity)
+    # Only check `default_model in model` (is the key a substring of the input).
+    # The reverse (`model in default_model`) causes shorter names like
+    # "claude-sonnet-4" to incorrectly match "claude-sonnet-4-6" and return 1M.
+    model_lower = model.lower()
+    for default_model, length in sorted(
+        DEFAULT_CONTEXT_LENGTHS.items(), key=lambda x: len(x[0]), reverse=True
+    ):
+        if default_model in model_lower:
             return length
 
-    # 4. Unknown model — start at highest probe tier
-    return CONTEXT_PROBE_TIERS[0]
+    # 9. Query local server as last resort
+    if base_url and is_local_endpoint(base_url):
+        local_ctx = _query_local_context_length(model, base_url)
+        if local_ctx and local_ctx > 0:
+            save_context_length(model, base_url, local_ctx)
+            return local_ctx
+
+    # 10. Default fallback — 128K
+    return DEFAULT_FALLBACK_CONTEXT
 
 
 def estimate_tokens_rough(text: str) -> int:
@@ -222,3 +905,26 @@ def estimate_messages_tokens_rough(messages: List[Dict[str, Any]]) -> int:
     """Rough token estimate for a message list (pre-flight only)."""
     total_chars = sum(len(str(msg)) for msg in messages)
     return total_chars // 4
+
+
+def estimate_request_tokens_rough(
+    messages: List[Dict[str, Any]],
+    *,
+    system_prompt: str = "",
+    tools: Optional[List[Dict[str, Any]]] = None,
+) -> int:
+    """Rough token estimate for a full chat-completions request.
+
+    Includes the major payload buckets Hermes sends to providers:
+    system prompt, conversation messages, and tool schemas.  With 50+
+    tools enabled, schemas alone can add 20-30K tokens — a significant
+    blind spot when only counting messages.
+    """
+    total_chars = 0
+    if system_prompt:
+        total_chars += len(system_prompt)
+    if messages:
+        total_chars += sum(len(str(msg)) for msg in messages)
+    if tools:
+        total_chars += len(str(tools))
+    return total_chars // 4

agent/models_dev.py

@@ -0,0 +1,171 @@
+"""Models.dev registry integration for provider-aware context length detection.
+
+Fetches model metadata from https://models.dev/api.json — a community-maintained
+database of 3800+ models across 100+ providers, including per-provider context
+windows, pricing, and capabilities.
+
+Data is cached in memory (1hr TTL) and on disk (~/.hermes/models_dev_cache.json)
+to avoid cold-start network latency.
+"""
+
+import json
+import logging
+import os
+import time
+from pathlib import Path
+from typing import Any, Dict, Optional
+
+from utils import atomic_json_write
+
+import requests
+
+logger = logging.getLogger(__name__)
+
+MODELS_DEV_URL = "https://models.dev/api.json"
+_MODELS_DEV_CACHE_TTL = 3600  # 1 hour in-memory
+
+# In-memory cache
+_models_dev_cache: Dict[str, Any] = {}
+_models_dev_cache_time: float = 0
+
+# Provider ID mapping: Hermes provider names → models.dev provider IDs
+PROVIDER_TO_MODELS_DEV: Dict[str, str] = {
+    "openrouter": "openrouter",
+    "anthropic": "anthropic",
+    "zai": "zai",
+    "kimi-coding": "kimi-for-coding",
+    "minimax": "minimax",
+    "minimax-cn": "minimax-cn",
+    "deepseek": "deepseek",
+    "alibaba": "alibaba",
+    "copilot": "github-copilot",
+    "ai-gateway": "vercel",
+    "opencode-zen": "opencode",
+    "opencode-go": "opencode-go",
+    "kilocode": "kilo",
+}
+
+
+def _get_cache_path() -> Path:
+    """Return path to disk cache file."""
+    env_val = os.environ.get("HERMES_HOME", "")
+    hermes_home = Path(env_val) if env_val else Path.home() / ".hermes"
+    return hermes_home / "models_dev_cache.json"
+
+
+def _load_disk_cache() -> Dict[str, Any]:
+    """Load models.dev data from disk cache."""
+    try:
+        cache_path = _get_cache_path()
+        if cache_path.exists():
+            with open(cache_path, encoding="utf-8") as f:
+                return json.load(f)
+    except Exception as e:
+        logger.debug("Failed to load models.dev disk cache: %s", e)
+    return {}
+
+
+def _save_disk_cache(data: Dict[str, Any]) -> None:
+    """Save models.dev data to disk cache atomically."""
+    try:
+        cache_path = _get_cache_path()
+        atomic_json_write(cache_path, data, indent=None, separators=(",", ":"))
+    except Exception as e:
+        logger.debug("Failed to save models.dev disk cache: %s", e)
+
+
+def fetch_models_dev(force_refresh: bool = False) -> Dict[str, Any]:
+    """Fetch models.dev registry. In-memory cache (1hr) + disk fallback.
+
+    Returns the full registry dict keyed by provider ID, or empty dict on failure.
+    """
+    global _models_dev_cache, _models_dev_cache_time
+
+    # Check in-memory cache
+    if (
+        not force_refresh
+        and _models_dev_cache
+        and (time.time() - _models_dev_cache_time) < _MODELS_DEV_CACHE_TTL
+    ):
+        return _models_dev_cache
+
+    # Try network fetch
+    try:
+        response = requests.get(MODELS_DEV_URL, timeout=15)
+        response.raise_for_status()
+        data = response.json()
+        if isinstance(data, dict) and len(data) > 0:
+            _models_dev_cache = data
+            _models_dev_cache_time = time.time()
+            _save_disk_cache(data)
+            logger.debug(
+                "Fetched models.dev registry: %d providers, %d total models",
+                len(data),
+                sum(len(p.get("models", {})) for p in data.values() if isinstance(p, dict)),
+            )
+            return data
+    except Exception as e:
+        logger.debug("Failed to fetch models.dev: %s", e)
+
+    # Fall back to disk cache — use a short TTL (5 min) so we retry
+    # the network fetch soon instead of serving stale data for a full hour.
+    if not _models_dev_cache:
+        _models_dev_cache = _load_disk_cache()
+        if _models_dev_cache:
+            _models_dev_cache_time = time.time() - _MODELS_DEV_CACHE_TTL + 300
+            logger.debug("Loaded models.dev from disk cache (%d providers)", len(_models_dev_cache))
+
+    return _models_dev_cache
+
+
+def lookup_models_dev_context(provider: str, model: str) -> Optional[int]:
+    """Look up context_length for a provider+model combo in models.dev.
+
+    Returns the context window in tokens, or None if not found.
+    Handles case-insensitive matching and filters out context=0 entries.
+    """
+    mdev_provider_id = PROVIDER_TO_MODELS_DEV.get(provider)
+    if not mdev_provider_id:
+        return None
+
+    data = fetch_models_dev()
+    provider_data = data.get(mdev_provider_id)
+    if not isinstance(provider_data, dict):
+        return None
+
+    models = provider_data.get("models", {})
+    if not isinstance(models, dict):
+        return None
+
+    # Exact match
+    entry = models.get(model)
+    if entry:
+        ctx = _extract_context(entry)
+        if ctx:
+            return ctx
+
+    # Case-insensitive match
+    model_lower = model.lower()
+    for mid, mdata in models.items():
+        if mid.lower() == model_lower:
+            ctx = _extract_context(mdata)
+            if ctx:
+                return ctx
+
+    return None
+
+
+def _extract_context(entry: Dict[str, Any]) -> Optional[int]:
+    """Extract context_length from a models.dev model entry.
+
+    Returns None for invalid/zero values (some audio/image models have context=0).
+    """
+    if not isinstance(entry, dict):
+        return None
+    limit = entry.get("limit")
+    if not isinstance(limit, dict):
+        return None
+    ctx = limit.get("context")
+    if isinstance(ctx, (int, float)) and ctx > 0:
+        return int(ctx)
+    return None

agent/prompt_builder.py

@@ -4,12 +4,28 @@ All functions are stateless. AIAgent._build_system_prompt() calls these to
 assemble pieces, then combines them with memory and ephemeral prompts.
 """
 
+import json
 import logging
 import os
 import re
+import threading
+from collections import OrderedDict
 from pathlib import Path
+
+from hermes_constants import get_hermes_home
 from typing import Optional
 
+from agent.skill_utils import (
+    extract_skill_conditions,
+    extract_skill_description,
+    get_all_skills_dirs,
+    get_disabled_skill_names,
+    iter_skill_index_files,
+    parse_frontmatter,
+    skill_matches_platform,
+)
+from utils import atomic_json_write
+
 logger = logging.getLogger(__name__)
 
 # ---------------------------------------------------------------------------
@@ -56,6 +72,61 @@ def _scan_context_content(content: str, filename: str) -> str:
 
     return content
 
+
+def _find_git_root(start: Path) -> Optional[Path]:
+    """Walk *start* and its parents looking for a ``.git`` directory.
+
+    Returns the directory containing ``.git``, or ``None`` if we hit the
+    filesystem root without finding one.
+    """
+    current = start.resolve()
+    for parent in [current, *current.parents]:
+        if (parent / ".git").exists():
+            return parent
+    return None
+
+
+_HERMES_MD_NAMES = (".hermes.md", "HERMES.md")
+
+
+def _find_hermes_md(cwd: Path) -> Optional[Path]:
+    """Discover the nearest ``.hermes.md`` or ``HERMES.md``.
+
+    Search order: *cwd* first, then each parent directory up to (and
+    including) the git repository root.  Returns the first match, or
+    ``None`` if nothing is found.
+    """
+    stop_at = _find_git_root(cwd)
+    current = cwd.resolve()
+
+    for directory in [current, *current.parents]:
+        for name in _HERMES_MD_NAMES:
+            candidate = directory / name
+            if candidate.is_file():
+                return candidate
+        # Stop walking at the git root (or filesystem root).
+        if stop_at and directory == stop_at:
+            break
+    return None
+
+
+def _strip_yaml_frontmatter(content: str) -> str:
+    """Remove optional YAML frontmatter (``---`` delimited) from *content*.
+
+    The frontmatter may contain structured config (model overrides, tool
+    settings) that will be handled separately in a future PR.  For now we
+    strip it so only the human-readable markdown body is injected into the
+    system prompt.
+    """
+    if content.startswith("---"):
+        end = content.find("\n---", 3)
+        if end != -1:
+            # Skip past the closing --- and any trailing newline
+            body = content[end + 4:].lstrip("\n")
+            return body if body else content
+    return content
+
+
 # =========================================================================
 # Constants
 # =========================================================================
@@ -71,23 +142,53 @@ DEFAULT_AGENT_IDENTITY = (
 )
 
 MEMORY_GUIDANCE = (
-    "You have persistent memory across sessions. Proactively save important things "
-    "you learn (user preferences, environment details, useful approaches) and do "
-    "(like a diary!) using the memory tool -- don't wait to be asked."
+    "You have persistent memory across sessions. Save durable facts using the memory "
+    "tool: user preferences, environment details, tool quirks, and stable conventions. "
+    "Memory is injected into every turn, so keep it compact and focused on facts that "
+    "will still matter later.\n"
+    "Prioritize what reduces future user steering — the most valuable memory is one "
+    "that prevents the user from having to correct or remind you again. "
+    "User preferences and recurring corrections matter more than procedural task details.\n"
+    "Do NOT save task progress, session outcomes, completed-work logs, or temporary TODO "
+    "state to memory; use session_search to recall those from past transcripts. "
+    "If you've discovered a new way to do something, solved a problem that could be "
+    "necessary later, save it as a skill with the skill tool."
 )
 
 SESSION_SEARCH_GUIDANCE = (
     "When the user references something from a past conversation or you suspect "
-    "relevant prior context exists, use session_search to recall it before asking "
-    "them to repeat themselves."
+    "relevant cross-session context exists, use session_search to recall it before "
+    "asking them to repeat themselves."
 )
 
 SKILLS_GUIDANCE = (
     "After completing a complex task (5+ tool calls), fixing a tricky error, "
-    "or discovering a non-trivial workflow, consider saving the approach as a "
-    "skill with skill_manage so you can reuse it next time."
+    "or discovering a non-trivial workflow, save the approach as a "
+    "skill with skill_manage so you can reuse it next time.\n"
+    "When using a skill and finding it outdated, incomplete, or wrong, "
+    "patch it immediately with skill_manage(action='patch') — don't wait to be asked. "
+    "Skills that aren't maintained become liabilities."
 )
 
+TOOL_USE_ENFORCEMENT_GUIDANCE = (
+    "# Tool-use enforcement\n"
+    "You MUST use your tools to take action — do not describe what you would do "
+    "or plan to do without actually doing it. When you say you will perform an "
+    "action (e.g. 'I will run the tests', 'Let me check the file', 'I will create "
+    "the project'), you MUST immediately make the corresponding tool call in the same "
+    "response. Never end your turn with a promise of future action — execute it now.\n"
+    "Keep working until the task is actually complete. Do not stop with a summary of "
+    "what you plan to do next time. If you have tools available that can accomplish "
+    "the task, use them instead of telling the user what you would do.\n"
+    "Every response should either (a) contain tool calls that make progress, or "
+    "(b) deliver a final result to the user. Responses that only describe intentions "
+    "without acting are not acceptable."
+)
+
+# Model name substrings that trigger tool-use enforcement guidance.
+# Add new patterns here when a model family needs explicit steering.
+TOOL_USE_ENFORCEMENT_MODELS = ("gpt", "codex")
+
 PLATFORM_HINTS = {
     "whatsapp": (
         "You are on a text messaging communication platform, WhatsApp. "
@@ -131,10 +232,30 @@ PLATFORM_HINTS = {
         "files arrive as downloadable documents. You can also include image "
         "URLs in markdown format ![alt](url) and they will be sent as photos."
     ),
+    "email": (
+        "You are communicating via email. Write clear, well-structured responses "
+        "suitable for email. Use plain text formatting (no markdown). "
+        "Keep responses concise but complete. You can send file attachments — "
+        "include MEDIA:/absolute/path/to/file in your response. The subject line "
+        "is preserved for threading. Do not include greetings or sign-offs unless "
+        "contextually appropriate."
+    ),
+    "cron": (
+        "You are running as a scheduled cron job. There is no user present — you "
+        "cannot ask questions, request clarification, or wait for follow-up. Execute "
+        "the task fully and autonomously, making reasonable decisions where needed. "
+        "Your final response is automatically delivered to the job's configured "
+        "destination — put the primary content directly in your response."
+    ),
     "cli": (
         "You are a CLI AI Agent. Try not to use markdown but simple text "
         "renderable inside a terminal."
     ),
+    "sms": (
+        "You are communicating via SMS. Keep responses concise and use plain text "
+        "only — no markdown, no formatting. SMS messages are limited to ~1600 "
+        "characters, so be brief and direct."
+    ),
 }
 
 CONTEXT_FILE_MAX_CHARS = 20_000
@@ -142,130 +263,386 @@ CONTEXT_TRUNCATE_HEAD_RATIO = 0.7
 CONTEXT_TRUNCATE_TAIL_RATIO = 0.2
 
 
+# =========================================================================
+# Skills prompt cache
+# =========================================================================
+
+_SKILLS_PROMPT_CACHE_MAX = 8
+_SKILLS_PROMPT_CACHE: OrderedDict[tuple, str] = OrderedDict()
+_SKILLS_PROMPT_CACHE_LOCK = threading.Lock()
+_SKILLS_SNAPSHOT_VERSION = 1
+
+
+def _skills_prompt_snapshot_path() -> Path:
+    return get_hermes_home() / ".skills_prompt_snapshot.json"
+
+
+def clear_skills_system_prompt_cache(*, clear_snapshot: bool = False) -> None:
+    """Drop the in-process skills prompt cache (and optionally the disk snapshot)."""
+    with _SKILLS_PROMPT_CACHE_LOCK:
+        _SKILLS_PROMPT_CACHE.clear()
+    if clear_snapshot:
+        try:
+            _skills_prompt_snapshot_path().unlink(missing_ok=True)
+        except OSError as e:
+            logger.debug("Could not remove skills prompt snapshot: %s", e)
+
+
+def _build_skills_manifest(skills_dir: Path) -> dict[str, list[int]]:
+    """Build an mtime/size manifest of all SKILL.md and DESCRIPTION.md files."""
+    manifest: dict[str, list[int]] = {}
+    for filename in ("SKILL.md", "DESCRIPTION.md"):
+        for path in iter_skill_index_files(skills_dir, filename):
+            try:
+                st = path.stat()
+            except OSError:
+                continue
+            manifest[str(path.relative_to(skills_dir))] = [st.st_mtime_ns, st.st_size]
+    return manifest
+
+
+def _load_skills_snapshot(skills_dir: Path) -> Optional[dict]:
+    """Load the disk snapshot if it exists and its manifest still matches."""
+    snapshot_path = _skills_prompt_snapshot_path()
+    if not snapshot_path.exists():
+        return None
+    try:
+        snapshot = json.loads(snapshot_path.read_text(encoding="utf-8"))
+    except Exception:
+        return None
+    if not isinstance(snapshot, dict):
+        return None
+    if snapshot.get("version") != _SKILLS_SNAPSHOT_VERSION:
+        return None
+    if snapshot.get("manifest") != _build_skills_manifest(skills_dir):
+        return None
+    return snapshot
+
+
+def _write_skills_snapshot(
+    skills_dir: Path,
+    manifest: dict[str, list[int]],
+    skill_entries: list[dict],
+    category_descriptions: dict[str, str],
+) -> None:
+    """Persist skill metadata to disk for fast cold-start reuse."""
+    payload = {
+        "version": _SKILLS_SNAPSHOT_VERSION,
+        "manifest": manifest,
+        "skills": skill_entries,
+        "category_descriptions": category_descriptions,
+    }
+    try:
+        atomic_json_write(_skills_prompt_snapshot_path(), payload)
+    except Exception as e:
+        logger.debug("Could not write skills prompt snapshot: %s", e)
+
+
+def _build_snapshot_entry(
+    skill_file: Path,
+    skills_dir: Path,
+    frontmatter: dict,
+    description: str,
+) -> dict:
+    """Build a serialisable metadata dict for one skill."""
+    rel_path = skill_file.relative_to(skills_dir)
+    parts = rel_path.parts
+    if len(parts) >= 2:
+        skill_name = parts[-2]
+        category = "/".join(parts[:-2]) if len(parts) > 2 else parts[0]
+    else:
+        category = "general"
+        skill_name = skill_file.parent.name
+
+    platforms = frontmatter.get("platforms") or []
+    if isinstance(platforms, str):
+        platforms = [platforms]
+
+    return {
+        "skill_name": skill_name,
+        "category": category,
+        "frontmatter_name": str(frontmatter.get("name", skill_name)),
+        "description": description,
+        "platforms": [str(p).strip() for p in platforms if str(p).strip()],
+        "conditions": extract_skill_conditions(frontmatter),
+    }
+
+
 # =========================================================================
 # Skills index
 # =========================================================================
 
-def _read_skill_description(skill_file: Path, max_chars: int = 60) -> str:
-    """Read the description from a SKILL.md frontmatter, capped at max_chars."""
-    try:
-        raw = skill_file.read_text(encoding="utf-8")[:2000]
-        match = re.search(
-            r"^---\s*\n.*?description:\s*(.+?)\s*\n.*?^---",
-            raw, re.MULTILINE | re.DOTALL,
-        )
-        if match:
-            desc = match.group(1).strip().strip("'\"")
-            if len(desc) > max_chars:
-                desc = desc[:max_chars - 3] + "..."
-            return desc
-    except Exception:
-        pass
-    return ""
+def _parse_skill_file(skill_file: Path) -> tuple[bool, dict, str]:
+    """Read a SKILL.md once and return platform compatibility, frontmatter, and description.
 
-
-def _skill_is_platform_compatible(skill_file: Path) -> bool:
-    """Quick check if a SKILL.md is compatible with the current OS platform.
-
-    Reads just enough to parse the ``platforms`` frontmatter field.
-    Skills without the field (the vast majority) are always compatible.
+    Returns (is_compatible, frontmatter, description). On any error, returns
+    (True, {}, "") to err on the side of showing the skill.
     """
     try:
-        from tools.skills_tool import _parse_frontmatter, skill_matches_platform
         raw = skill_file.read_text(encoding="utf-8")[:2000]
-        frontmatter, _ = _parse_frontmatter(raw)
-        return skill_matches_platform(frontmatter)
-    except Exception:
-        return True  # Err on the side of showing the skill
+        frontmatter, _ = parse_frontmatter(raw)
+
+        if not skill_matches_platform(frontmatter):
+            return False, frontmatter, ""
+
+        return True, frontmatter, extract_skill_description(frontmatter)
+    except Exception as e:
+        logger.debug("Failed to parse skill file %s: %s", skill_file, e)
+        return True, {}, ""
 
 
-def build_skills_system_prompt() -> str:
+def _read_skill_conditions(skill_file: Path) -> dict:
+    """Extract conditional activation fields from SKILL.md frontmatter."""
+    try:
+        raw = skill_file.read_text(encoding="utf-8")[:2000]
+        frontmatter, _ = parse_frontmatter(raw)
+        return extract_skill_conditions(frontmatter)
+    except Exception as e:
+        logger.debug("Failed to read skill conditions from %s: %s", skill_file, e)
+        return {}
+
+
+def _skill_should_show(
+    conditions: dict,
+    available_tools: "set[str] | None",
+    available_toolsets: "set[str] | None",
+) -> bool:
+    """Return False if the skill's conditional activation rules exclude it."""
+    if available_tools is None and available_toolsets is None:
+        return True  # No filtering info — show everything (backward compat)
+
+    at = available_tools or set()
+    ats = available_toolsets or set()
+
+    # fallback_for: hide when the primary tool/toolset IS available
+    for ts in conditions.get("fallback_for_toolsets", []):
+        if ts in ats:
+            return False
+    for t in conditions.get("fallback_for_tools", []):
+        if t in at:
+            return False
+
+    # requires: hide when a required tool/toolset is NOT available
+    for ts in conditions.get("requires_toolsets", []):
+        if ts not in ats:
+            return False
+    for t in conditions.get("requires_tools", []):
+        if t not in at:
+            return False
+
+    return True
+
+
+def build_skills_system_prompt(
+    available_tools: "set[str] | None" = None,
+    available_toolsets: "set[str] | None" = None,
+) -> str:
     """Build a compact skill index for the system prompt.
 
-    Scans ~/.hermes/skills/ for SKILL.md files grouped by category.
-    Includes per-skill descriptions from frontmatter so the model can
-    match skills by meaning, not just name.
-    Filters out skills incompatible with the current OS platform.
+    Two-layer cache:
+      1. In-process LRU dict keyed by (skills_dir, tools, toolsets)
+      2. Disk snapshot (``.skills_prompt_snapshot.json``) validated by
+         mtime/size manifest — survives process restarts
+
+    Falls back to a full filesystem scan when both layers miss.
+
+    External skill directories (``skills.external_dirs`` in config.yaml) are
+    scanned alongside the local ``~/.hermes/skills/`` directory.  External dirs
+    are read-only — they appear in the index but new skills are always created
+    in the local dir.  Local skills take precedence when names collide.
     """
-    hermes_home = Path(os.getenv("HERMES_HOME", Path.home() / ".hermes"))
+    hermes_home = get_hermes_home()
     skills_dir = hermes_home / "skills"
+    external_dirs = get_all_skills_dirs()[1:]  # skip local (index 0)
 
-    if not skills_dir.exists():
+    if not skills_dir.exists() and not external_dirs:
         return ""
 
-    # Collect skills with descriptions, grouped by category
-    # Each entry: (skill_name, description)
-    # Supports sub-categories: skills/mlops/training/axolotl/SKILL.md
-    # → category "mlops/training", skill "axolotl"
+    # ── Layer 1: in-process LRU cache ─────────────────────────────────
+    cache_key = (
+        str(skills_dir.resolve()),
+        tuple(str(d) for d in external_dirs),
+        tuple(sorted(str(t) for t in (available_tools or set()))),
+        tuple(sorted(str(ts) for ts in (available_toolsets or set()))),
+    )
+    with _SKILLS_PROMPT_CACHE_LOCK:
+        cached = _SKILLS_PROMPT_CACHE.get(cache_key)
+        if cached is not None:
+            _SKILLS_PROMPT_CACHE.move_to_end(cache_key)
+            return cached
+
+    disabled = get_disabled_skill_names()
+
+    # ── Layer 2: disk snapshot ────────────────────────────────────────
+    snapshot = _load_skills_snapshot(skills_dir)
+
     skills_by_category: dict[str, list[tuple[str, str]]] = {}
-    for skill_file in skills_dir.rglob("SKILL.md"):
-        # Skip skills incompatible with the current OS platform
-        if not _skill_is_platform_compatible(skill_file):
-            continue
-        rel_path = skill_file.relative_to(skills_dir)
-        parts = rel_path.parts
-        if len(parts) >= 2:
-            # Category is everything between skills_dir and the skill folder
-            # e.g. parts = ("mlops", "training", "axolotl", "SKILL.md")
-            #   → category = "mlops/training", skill_name = "axolotl"
-            # e.g. parts = ("github", "github-auth", "SKILL.md")
-            #   → category = "github", skill_name = "github-auth"
-            skill_name = parts[-2]
-            category = "/".join(parts[:-2]) if len(parts) > 2 else parts[0]
-        else:
-            category = "general"
-            skill_name = skill_file.parent.name
-        desc = _read_skill_description(skill_file)
-        skills_by_category.setdefault(category, []).append((skill_name, desc))
+    category_descriptions: dict[str, str] = {}
 
-    if not skills_by_category:
-        return ""
+    if snapshot is not None:
+        # Fast path: use pre-parsed metadata from disk
+        for entry in snapshot.get("skills", []):
+            if not isinstance(entry, dict):
+                continue
+            skill_name = entry.get("skill_name") or ""
+            category = entry.get("category") or "general"
+            frontmatter_name = entry.get("frontmatter_name") or skill_name
+            platforms = entry.get("platforms") or []
+            if not skill_matches_platform({"platforms": platforms}):
+                continue
+            if frontmatter_name in disabled or skill_name in disabled:
+                continue
+            if not _skill_should_show(
+                entry.get("conditions") or {},
+                available_tools,
+                available_toolsets,
+            ):
+                continue
+            skills_by_category.setdefault(category, []).append(
+                (skill_name, entry.get("description", ""))
+            )
+        category_descriptions = {
+            str(k): str(v)
+            for k, v in (snapshot.get("category_descriptions") or {}).items()
+        }
+    else:
+        # Cold path: full filesystem scan + write snapshot for next time
+        skill_entries: list[dict] = []
+        for skill_file in iter_skill_index_files(skills_dir, "SKILL.md"):
+            is_compatible, frontmatter, desc = _parse_skill_file(skill_file)
+            entry = _build_snapshot_entry(skill_file, skills_dir, frontmatter, desc)
+            skill_entries.append(entry)
+            if not is_compatible:
+                continue
+            skill_name = entry["skill_name"]
+            if entry["frontmatter_name"] in disabled or skill_name in disabled:
+                continue
+            if not _skill_should_show(
+                extract_skill_conditions(frontmatter),
+                available_tools,
+                available_toolsets,
+            ):
+                continue
+            skills_by_category.setdefault(entry["category"], []).append(
+                (skill_name, entry["description"])
+            )
 
-    # Read category-level descriptions from DESCRIPTION.md
-    # Checks both the exact category path and parent directories
-    category_descriptions = {}
-    for category in skills_by_category:
-        cat_path = Path(category)
-        desc_file = skills_dir / cat_path / "DESCRIPTION.md"
-        if desc_file.exists():
+        # Read category-level DESCRIPTION.md files
+        for desc_file in iter_skill_index_files(skills_dir, "DESCRIPTION.md"):
             try:
                 content = desc_file.read_text(encoding="utf-8")
-                match = re.search(r"^---\s*\n.*?description:\s*(.+?)\s*\n.*?^---", content, re.MULTILINE | re.DOTALL)
-                if match:
-                    category_descriptions[category] = match.group(1).strip()
+                fm, _ = parse_frontmatter(content)
+                cat_desc = fm.get("description")
+                if not cat_desc:
+                    continue
+                rel = desc_file.relative_to(skills_dir)
+                cat = "/".join(rel.parts[:-1]) if len(rel.parts) > 1 else "general"
+                category_descriptions[cat] = str(cat_desc).strip().strip("'\"")
             except Exception as e:
                 logger.debug("Could not read skill description %s: %s", desc_file, e)
 
-    index_lines = []
-    for category in sorted(skills_by_category.keys()):
-        cat_desc = category_descriptions.get(category, "")
-        if cat_desc:
-            index_lines.append(f"  {category}: {cat_desc}")
-        else:
-            index_lines.append(f"  {category}:")
-        # Deduplicate and sort skills within each category
-        seen = set()
-        for name, desc in sorted(skills_by_category[category], key=lambda x: x[0]):
-            if name in seen:
-                continue
-            seen.add(name)
-            if desc:
-                index_lines.append(f"    - {name}: {desc}")
-            else:
-                index_lines.append(f"    - {name}")
+        _write_skills_snapshot(
+            skills_dir,
+            _build_skills_manifest(skills_dir),
+            skill_entries,
+            category_descriptions,
+        )
 
-    return (
-        "## Skills (mandatory)\n"
-        "Before replying, scan the skills below. If one clearly matches your task, "
-        "load it with skill_view(name) and follow its instructions. "
-        "If a skill has issues, fix it with skill_manage(action='patch').\n"
-        "\n"
-        "<available_skills>\n"
-        + "\n".join(index_lines) + "\n"
-        "</available_skills>\n"
-        "\n"
-        "If none match, proceed normally without loading a skill."
-    )
+    # ── External skill directories ─────────────────────────────────────
+    # Scan external dirs directly (no snapshot caching — they're read-only
+    # and typically small).  Local skills already in skills_by_category take
+    # precedence: we track seen names and skip duplicates from external dirs.
+    seen_skill_names: set[str] = set()
+    for cat_skills in skills_by_category.values():
+        for name, _desc in cat_skills:
+            seen_skill_names.add(name)
+
+    for ext_dir in external_dirs:
+        if not ext_dir.exists():
+            continue
+        for skill_file in iter_skill_index_files(ext_dir, "SKILL.md"):
+            try:
+                is_compatible, frontmatter, desc = _parse_skill_file(skill_file)
+                if not is_compatible:
+                    continue
+                entry = _build_snapshot_entry(skill_file, ext_dir, frontmatter, desc)
+                skill_name = entry["skill_name"]
+                if skill_name in seen_skill_names:
+                    continue
+                if entry["frontmatter_name"] in disabled or skill_name in disabled:
+                    continue
+                if not _skill_should_show(
+                    extract_skill_conditions(frontmatter),
+                    available_tools,
+                    available_toolsets,
+                ):
+                    continue
+                seen_skill_names.add(skill_name)
+                skills_by_category.setdefault(entry["category"], []).append(
+                    (skill_name, entry["description"])
+                )
+            except Exception as e:
+                logger.debug("Error reading external skill %s: %s", skill_file, e)
+
+        # External category descriptions
+        for desc_file in iter_skill_index_files(ext_dir, "DESCRIPTION.md"):
+            try:
+                content = desc_file.read_text(encoding="utf-8")
+                fm, _ = parse_frontmatter(content)
+                cat_desc = fm.get("description")
+                if not cat_desc:
+                    continue
+                rel = desc_file.relative_to(ext_dir)
+                cat = "/".join(rel.parts[:-1]) if len(rel.parts) > 1 else "general"
+                category_descriptions.setdefault(cat, str(cat_desc).strip().strip("'\""))
+            except Exception as e:
+                logger.debug("Could not read external skill description %s: %s", desc_file, e)
+
+    if not skills_by_category:
+        result = ""
+    else:
+        index_lines = []
+        for category in sorted(skills_by_category.keys()):
+            cat_desc = category_descriptions.get(category, "")
+            if cat_desc:
+                index_lines.append(f"  {category}: {cat_desc}")
+            else:
+                index_lines.append(f"  {category}:")
+            # Deduplicate and sort skills within each category
+            seen = set()
+            for name, desc in sorted(skills_by_category[category], key=lambda x: x[0]):
+                if name in seen:
+                    continue
+                seen.add(name)
+                if desc:
+                    index_lines.append(f"    - {name}: {desc}")
+                else:
+                    index_lines.append(f"    - {name}")
+
+        result = (
+            "## Skills (mandatory)\n"
+            "Before replying, scan the skills below. If one clearly matches your task, "
+            "load it with skill_view(name) and follow its instructions. "
+            "If a skill has issues, fix it with skill_manage(action='patch').\n"
+            "After difficult/iterative tasks, offer to save as a skill. "
+            "If a skill you loaded was missing steps, had wrong commands, or needed "
+            "pitfalls you discovered, update it before finishing.\n"
+            "\n"
+            "<available_skills>\n"
+            + "\n".join(index_lines) + "\n"
+            "</available_skills>\n"
+            "\n"
+            "If none match, proceed normally without loading a skill."
+        )
+
+    # ── Store in LRU cache ────────────────────────────────────────────
+    with _SKILLS_PROMPT_CACHE_LOCK:
+        _SKILLS_PROMPT_CACHE[cache_key] = result
+        _SKILLS_PROMPT_CACHE.move_to_end(cache_key)
+        while len(_SKILLS_PROMPT_CACHE) > _SKILLS_PROMPT_CACHE_MAX:
+            _SKILLS_PROMPT_CACHE.popitem(last=False)
+
+    return result
 
 
 # =========================================================================
@@ -284,51 +661,91 @@ def _truncate_content(content: str, filename: str, max_chars: int = CONTEXT_FILE
     return head + marker + tail
 
 
-def build_context_files_prompt(cwd: Optional[str] = None) -> str:
-    """Discover and load context files for the system prompt.
+def load_soul_md() -> Optional[str]:
+    """Load SOUL.md from HERMES_HOME and return its content, or None.
 
-    Discovery: AGENTS.md (recursive), .cursorrules / .cursor/rules/*.mdc,
-    SOUL.md (cwd then ~/.hermes/ fallback). Each capped at 20,000 chars.
+    Used as the agent identity (slot #1 in the system prompt).  When this
+    returns content, ``build_context_files_prompt`` should be called with
+    ``skip_soul=True`` so SOUL.md isn't injected twice.
     """
-    if cwd is None:
-        cwd = os.getcwd()
+    try:
+        from hermes_cli.config import ensure_hermes_home
+        ensure_hermes_home()
+    except Exception as e:
+        logger.debug("Could not ensure HERMES_HOME before loading SOUL.md: %s", e)
 
-    cwd_path = Path(cwd).resolve()
-    sections = []
+    soul_path = get_hermes_home() / "SOUL.md"
+    if not soul_path.exists():
+        return None
+    try:
+        content = soul_path.read_text(encoding="utf-8").strip()
+        if not content:
+            return None
+        content = _scan_context_content(content, "SOUL.md")
+        content = _truncate_content(content, "SOUL.md")
+        return content
+    except Exception as e:
+        logger.debug("Could not read SOUL.md from %s: %s", soul_path, e)
+        return None
 
-    # AGENTS.md (hierarchical, recursive)
-    top_level_agents = None
+
+def _load_hermes_md(cwd_path: Path) -> str:
+    """.hermes.md / HERMES.md — walk to git root."""
+    hermes_md_path = _find_hermes_md(cwd_path)
+    if not hermes_md_path:
+        return ""
+    try:
+        content = hermes_md_path.read_text(encoding="utf-8").strip()
+        if not content:
+            return ""
+        content = _strip_yaml_frontmatter(content)
+        rel = hermes_md_path.name
+        try:
+            rel = str(hermes_md_path.relative_to(cwd_path))
+        except ValueError:
+            pass
+        content = _scan_context_content(content, rel)
+        result = f"## {rel}\n\n{content}"
+        return _truncate_content(result, ".hermes.md")
+    except Exception as e:
+        logger.debug("Could not read %s: %s", hermes_md_path, e)
+        return ""
+
+
+def _load_agents_md(cwd_path: Path) -> str:
+    """AGENTS.md — top-level only (no recursive walk)."""
     for name in ["AGENTS.md", "agents.md"]:
         candidate = cwd_path / name
         if candidate.exists():
-            top_level_agents = candidate
-            break
-
-    if top_level_agents:
-        agents_files = []
-        for root, dirs, files in os.walk(cwd_path):
-            dirs[:] = [d for d in dirs if not d.startswith('.') and d not in ('node_modules', '__pycache__', 'venv', '.venv')]
-            for f in files:
-                if f.lower() == "agents.md":
-                    agents_files.append(Path(root) / f)
-        agents_files.sort(key=lambda p: len(p.parts))
-
-        total_agents_content = ""
-        for agents_path in agents_files:
             try:
-                content = agents_path.read_text(encoding="utf-8").strip()
+                content = candidate.read_text(encoding="utf-8").strip()
                 if content:
-                    rel_path = agents_path.relative_to(cwd_path)
-                    content = _scan_context_content(content, str(rel_path))
-                    total_agents_content += f"## {rel_path}\n\n{content}\n\n"
+                    content = _scan_context_content(content, name)
+                    result = f"## {name}\n\n{content}"
+                    return _truncate_content(result, "AGENTS.md")
             except Exception as e:
-                logger.debug("Could not read %s: %s", agents_path, e)
+                logger.debug("Could not read %s: %s", candidate, e)
+    return ""
 
-        if total_agents_content:
-            total_agents_content = _truncate_content(total_agents_content, "AGENTS.md")
-            sections.append(total_agents_content)
 
-    # .cursorrules
+def _load_claude_md(cwd_path: Path) -> str:
+    """CLAUDE.md / claude.md — cwd only."""
+    for name in ["CLAUDE.md", "claude.md"]:
+        candidate = cwd_path / name
+        if candidate.exists():
+            try:
+                content = candidate.read_text(encoding="utf-8").strip()
+                if content:
+                    content = _scan_context_content(content, name)
+                    result = f"## {name}\n\n{content}"
+                    return _truncate_content(result, "CLAUDE.md")
+            except Exception as e:
+                logger.debug("Could not read %s: %s", candidate, e)
+    return ""
+
+
+def _load_cursorrules(cwd_path: Path) -> str:
+    """.cursorrules + .cursor/rules/*.mdc — cwd only."""
     cursorrules_content = ""
     cursorrules_file = cwd_path / ".cursorrules"
     if cursorrules_file.exists():
@@ -352,35 +769,47 @@ def build_context_files_prompt(cwd: Optional[str] = None) -> str:
             except Exception as e:
                 logger.debug("Could not read %s: %s", mdc_file, e)
 
-    if cursorrules_content:
-        cursorrules_content = _truncate_content(cursorrules_content, ".cursorrules")
-        sections.append(cursorrules_content)
+    if not cursorrules_content:
+        return ""
+    return _truncate_content(cursorrules_content, ".cursorrules")
 
-    # SOUL.md (cwd first, then ~/.hermes/ fallback)
-    soul_path = None
-    for name in ["SOUL.md", "soul.md"]:
-        candidate = cwd_path / name
-        if candidate.exists():
-            soul_path = candidate
-            break
-    if not soul_path:
-        global_soul = Path.home() / ".hermes" / "SOUL.md"
-        if global_soul.exists():
-            soul_path = global_soul
 
-    if soul_path:
-        try:
-            content = soul_path.read_text(encoding="utf-8").strip()
-            if content:
-                content = _scan_context_content(content, "SOUL.md")
-                content = _truncate_content(content, "SOUL.md")
-                sections.append(
-                    f"## SOUL.md\n\nIf SOUL.md is present, embody its persona and tone. "
-                    f"Avoid stiff, generic replies; follow its guidance unless higher-priority "
-                    f"instructions override it.\n\n{content}"
-                )
-        except Exception as e:
-            logger.debug("Could not read SOUL.md from %s: %s", soul_path, e)
+def build_context_files_prompt(cwd: Optional[str] = None, skip_soul: bool = False) -> str:
+    """Discover and load context files for the system prompt.
+
+    Priority (first found wins — only ONE project context type is loaded):
+      1. .hermes.md / HERMES.md  (walk to git root)
+      2. AGENTS.md / agents.md   (cwd only)
+      3. CLAUDE.md / claude.md   (cwd only)
+      4. .cursorrules / .cursor/rules/*.mdc  (cwd only)
+
+    SOUL.md from HERMES_HOME is independent and always included when present.
+    Each context source is capped at 20,000 chars.
+
+    When *skip_soul* is True, SOUL.md is not included here (it was already
+    loaded via ``load_soul_md()`` for the identity slot).
+    """
+    if cwd is None:
+        cwd = os.getcwd()
+
+    cwd_path = Path(cwd).resolve()
+    sections = []
+
+    # Priority-based project context: first match wins
+    project_context = (
+        _load_hermes_md(cwd_path)
+        or _load_agents_md(cwd_path)
+        or _load_claude_md(cwd_path)
+        or _load_cursorrules(cwd_path)
+    )
+    if project_context:
+        sections.append(project_context)
+
+    # SOUL.md from HERMES_HOME only — skip when already loaded as identity
+    if not skip_soul:
+        soul_content = load_soul_md()
+        if soul_content:
+            sections.append(soul_content)
 
     if not sections:
         return ""

agent/prompt_caching.py

@@ -12,21 +12,24 @@ import copy
 from typing import Any, Dict, List
 
 
-def _apply_cache_marker(msg: dict, cache_marker: dict) -> None:
+def _apply_cache_marker(msg: dict, cache_marker: dict, native_anthropic: bool = False) -> None:
     """Add cache_control to a single message, handling all format variations."""
     role = msg.get("role", "")
     content = msg.get("content")
 
     if role == "tool":
-        msg["cache_control"] = cache_marker
+        if native_anthropic:
+            msg["cache_control"] = cache_marker
         return
 
-    if content is None:
+    if content is None or content == "":
         msg["cache_control"] = cache_marker
         return
 
     if isinstance(content, str):
-        msg["content"] = [{"type": "text", "text": content, "cache_control": cache_marker}]
+        msg["content"] = [
+            {"type": "text", "text": content, "cache_control": cache_marker}
+        ]
         return
 
     if isinstance(content, list) and content:
@@ -38,6 +41,7 @@ def _apply_cache_marker(msg: dict, cache_marker: dict) -> None:
 def apply_anthropic_cache_control(
     api_messages: List[Dict[str, Any]],
     cache_ttl: str = "5m",
+    native_anthropic: bool = False,
 ) -> List[Dict[str, Any]]:
     """Apply system_and_3 caching strategy to messages for Anthropic models.
 
@@ -57,12 +61,12 @@ def apply_anthropic_cache_control(
     breakpoints_used = 0
 
     if messages[0].get("role") == "system":
-        _apply_cache_marker(messages[0], marker)
+        _apply_cache_marker(messages[0], marker, native_anthropic=native_anthropic)
         breakpoints_used += 1
 
     remaining = 4 - breakpoints_used
     non_sys = [i for i in range(len(messages)) if messages[i].get("role") != "system"]
     for idx in non_sys[-remaining:]:
-        _apply_cache_marker(messages[idx], marker)
+        _apply_cache_marker(messages[idx], marker, native_anthropic=native_anthropic)
 
     return messages

agent/redact.py

@@ -10,7 +10,6 @@ the first 6 and last 4 characters for debuggability.
 import logging
 import os
 import re
-from typing import Optional
 
 logger = logging.getLogger(__name__)
 
@@ -38,6 +37,9 @@ _PREFIX_PATTERNS = [
     r"dop_v1_[A-Za-z0-9]{10,}",         # DigitalOcean PAT
     r"doo_v1_[A-Za-z0-9]{10,}",         # DigitalOcean OAuth
     r"am_[A-Za-z0-9_-]{10,}",           # AgentMail API key
+    r"sk_[A-Za-z0-9_]{10,}",            # ElevenLabs TTS key (sk_ underscore, not sk- dash)
+    r"tvly-[A-Za-z0-9]{10,}",           # Tavily search API key
+    r"exa_[A-Za-z0-9]{10,}",            # Exa search API key
 ]
 
 # ENV assignment patterns: KEY=value where KEY contains a secret-like name
@@ -48,7 +50,7 @@ _ENV_ASSIGN_RE = re.compile(
 )
 
 # JSON field patterns: "apiKey": "value", "token": "value", etc.
-_JSON_KEY_NAMES = r"(?:api_?[Kk]ey|token|secret|password|access_token|refresh_token|auth_token|bearer)"
+_JSON_KEY_NAMES = r"(?:api_?[Kk]ey|token|secret|password|access_token|refresh_token|auth_token|bearer|secret_value|raw_secret|secret_input|key_material)"
 _JSON_FIELD_RE = re.compile(
     rf'("{_JSON_KEY_NAMES}")\s*:\s*"([^"]+)"',
     re.IGNORECASE,
@@ -60,7 +62,8 @@ _AUTH_HEADER_RE = re.compile(
     re.IGNORECASE,
 )
 
-# Telegram bot tokens: bot<digits>:<token> or <digits>:<alphanum>
+# Telegram bot tokens: bot<digits>:<token> or <digits>:<token>,
+# where token part is restricted to [-A-Za-z0-9_] and length >= 30
 _TELEGRAM_RE = re.compile(
     r"(bot)?(\d{8,}):([-A-Za-z0-9_]{30,})",
 )
@@ -100,6 +103,10 @@ def redact_sensitive_text(text: str) -> str:
     Safe to call on any string -- non-matching text passes through unchanged.
     Disabled when security.redact_secrets is false in config.yaml.
     """
+    if text is None:
+        return None
+    if not isinstance(text, str):
+        text = str(text)
     if not text:
         return text
     if os.getenv("HERMES_REDACT_SECRETS", "").lower() in ("0", "false", "no", "off"):

agent/skill_commands.py

@@ -1,16 +1,155 @@
-"""Skill slash commands — scan installed skills and build invocation messages.
+"""Shared slash command helpers for skills and built-in prompt-style modes.
 
 Shared between CLI (cli.py) and gateway (gateway/run.py) so both surfaces
-can invoke skills via /skill-name commands.
+can invoke skills via /skill-name commands and prompt-only built-ins like
+/plan.
 """
 
+import json
 import logging
+import re
+from datetime import datetime
 from pathlib import Path
 from typing import Any, Dict, Optional
 
 logger = logging.getLogger(__name__)
 
 _skill_commands: Dict[str, Dict[str, Any]] = {}
+_PLAN_SLUG_RE = re.compile(r"[^a-z0-9]+")
+
+
+def build_plan_path(
+    user_instruction: str = "",
+    *,
+    now: datetime | None = None,
+) -> Path:
+    """Return the default workspace-relative markdown path for a /plan invocation.
+
+    Relative paths are intentional: file tools are task/backend-aware and resolve
+    them against the active working directory for local, docker, ssh, modal,
+    daytona, and similar terminal backends. That keeps the plan with the active
+    workspace instead of the Hermes host's global home directory.
+    """
+    slug_source = (user_instruction or "").strip().splitlines()[0] if user_instruction else ""
+    slug = _PLAN_SLUG_RE.sub("-", slug_source.lower()).strip("-")
+    if slug:
+        slug = "-".join(part for part in slug.split("-")[:8] if part)[:48].strip("-")
+    slug = slug or "conversation-plan"
+    timestamp = (now or datetime.now()).strftime("%Y-%m-%d_%H%M%S")
+    return Path(".hermes") / "plans" / f"{timestamp}-{slug}.md"
+
+
+def _load_skill_payload(skill_identifier: str, task_id: str | None = None) -> tuple[dict[str, Any], Path | None, str] | None:
+    """Load a skill by name/path and return (loaded_payload, skill_dir, display_name)."""
+    raw_identifier = (skill_identifier or "").strip()
+    if not raw_identifier:
+        return None
+
+    try:
+        from tools.skills_tool import SKILLS_DIR, skill_view
+
+        identifier_path = Path(raw_identifier).expanduser()
+        if identifier_path.is_absolute():
+            try:
+                normalized = str(identifier_path.resolve().relative_to(SKILLS_DIR.resolve()))
+            except Exception:
+                normalized = raw_identifier
+        else:
+            normalized = raw_identifier.lstrip("/")
+
+        loaded_skill = json.loads(skill_view(normalized, task_id=task_id))
+    except Exception:
+        return None
+
+    if not loaded_skill.get("success"):
+        return None
+
+    skill_name = str(loaded_skill.get("name") or normalized)
+    skill_path = str(loaded_skill.get("path") or "")
+    skill_dir = None
+    if skill_path:
+        try:
+            skill_dir = SKILLS_DIR / Path(skill_path).parent
+        except Exception:
+            skill_dir = None
+
+    return loaded_skill, skill_dir, skill_name
+
+
+def _build_skill_message(
+    loaded_skill: dict[str, Any],
+    skill_dir: Path | None,
+    activation_note: str,
+    user_instruction: str = "",
+    runtime_note: str = "",
+) -> str:
+    """Format a loaded skill into a user/system message payload."""
+    from tools.skills_tool import SKILLS_DIR
+
+    content = str(loaded_skill.get("content") or "")
+
+    parts = [activation_note, "", content.strip()]
+
+    if loaded_skill.get("setup_skipped"):
+        parts.extend(
+            [
+                "",
+                "[Skill setup note: Required environment setup was skipped. Continue loading the skill and explain any reduced functionality if it matters.]",
+            ]
+        )
+    elif loaded_skill.get("gateway_setup_hint"):
+        parts.extend(
+            [
+                "",
+                f"[Skill setup note: {loaded_skill['gateway_setup_hint']}]",
+            ]
+        )
+    elif loaded_skill.get("setup_needed") and loaded_skill.get("setup_note"):
+        parts.extend(
+            [
+                "",
+                f"[Skill setup note: {loaded_skill['setup_note']}]",
+            ]
+        )
+
+    supporting = []
+    linked_files = loaded_skill.get("linked_files") or {}
+    for entries in linked_files.values():
+        if isinstance(entries, list):
+            supporting.extend(entries)
+
+    if not supporting and skill_dir:
+        for subdir in ("references", "templates", "scripts", "assets"):
+            subdir_path = skill_dir / subdir
+            if subdir_path.exists():
+                for f in sorted(subdir_path.rglob("*")):
+                    if f.is_file():
+                        rel = str(f.relative_to(skill_dir))
+                        supporting.append(rel)
+
+    if supporting and skill_dir:
+        try:
+            skill_view_target = str(skill_dir.relative_to(SKILLS_DIR))
+        except ValueError:
+            # Skill is from an external dir — use the skill name instead
+            skill_view_target = skill_dir.name
+        parts.append("")
+        parts.append("[This skill has supporting files you can load with the skill_view tool:]")
+        for sf in supporting:
+            parts.append(f"- {sf}")
+        parts.append(
+            f'\nTo view any of these, use: skill_view(name="{skill_view_target}", file_path="<path>")'
+        )
+
+    if user_instruction:
+        parts.append("")
+        parts.append(f"The user has provided the following instruction alongside the skill invocation: {user_instruction}")
+
+    if runtime_note:
+        parts.append("")
+        parts.append(f"[Runtime note: {runtime_note}]")
+
+    return "\n".join(parts)
 
 
 def scan_skill_commands() -> Dict[str, Dict[str, Any]]:
@@ -22,35 +161,50 @@ def scan_skill_commands() -> Dict[str, Dict[str, Any]]:
     global _skill_commands
     _skill_commands = {}
     try:
-        from tools.skills_tool import SKILLS_DIR, _parse_frontmatter, skill_matches_platform
-        if not SKILLS_DIR.exists():
-            return _skill_commands
-        for skill_md in SKILLS_DIR.rglob("SKILL.md"):
-            if any(part in ('.git', '.github', '.hub') for part in skill_md.parts):
-                continue
-            try:
-                content = skill_md.read_text(encoding='utf-8')
-                frontmatter, body = _parse_frontmatter(content)
-                # Skip skills incompatible with the current OS platform
-                if not skill_matches_platform(frontmatter):
+        from tools.skills_tool import SKILLS_DIR, _parse_frontmatter, skill_matches_platform, _get_disabled_skill_names
+        from agent.skill_utils import get_external_skills_dirs
+        disabled = _get_disabled_skill_names()
+        seen_names: set = set()
+
+        # Scan local dir first, then external dirs
+        dirs_to_scan = []
+        if SKILLS_DIR.exists():
+            dirs_to_scan.append(SKILLS_DIR)
+        dirs_to_scan.extend(get_external_skills_dirs())
+
+        for scan_dir in dirs_to_scan:
+            for skill_md in scan_dir.rglob("SKILL.md"):
+                if any(part in ('.git', '.github', '.hub') for part in skill_md.parts):
+                    continue
+                try:
+                    content = skill_md.read_text(encoding='utf-8')
+                    frontmatter, body = _parse_frontmatter(content)
+                    # Skip skills incompatible with the current OS platform
+                    if not skill_matches_platform(frontmatter):
+                        continue
+                    name = frontmatter.get('name', skill_md.parent.name)
+                    if name in seen_names:
+                        continue
+                    # Respect user's disabled skills config
+                    if name in disabled:
+                        continue
+                    description = frontmatter.get('description', '')
+                    if not description:
+                        for line in body.strip().split('\n'):
+                            line = line.strip()
+                            if line and not line.startswith('#'):
+                                description = line[:80]
+                                break
+                    seen_names.add(name)
+                    cmd_name = name.lower().replace(' ', '-').replace('_', '-')
+                    _skill_commands[f"/{cmd_name}"] = {
+                        "name": name,
+                        "description": description or f"Invoke the {name} skill",
+                        "skill_md_path": str(skill_md),
+                        "skill_dir": str(skill_md.parent),
+                    }
+                except Exception:
                     continue
-                name = frontmatter.get('name', skill_md.parent.name)
-                description = frontmatter.get('description', '')
-                if not description:
-                    for line in body.strip().split('\n'):
-                        line = line.strip()
-                        if line and not line.startswith('#'):
-                            description = line[:80]
-                            break
-                cmd_name = name.lower().replace(' ', '-').replace('_', '-')
-                _skill_commands[f"/{cmd_name}"] = {
-                    "name": name,
-                    "description": description or f"Invoke the {name} skill",
-                    "skill_md_path": str(skill_md),
-                    "skill_dir": str(skill_md.parent),
-                }
-            except Exception:
-                continue
     except Exception:
         pass
     return _skill_commands
@@ -63,7 +217,12 @@ def get_skill_commands() -> Dict[str, Dict[str, Any]]:
     return _skill_commands
 
 
-def build_skill_invocation_message(cmd_key: str, user_instruction: str = "") -> Optional[str]:
+def build_skill_invocation_message(
+    cmd_key: str,
+    user_instruction: str = "",
+    task_id: str | None = None,
+    runtime_note: str = "",
+) -> Optional[str]:
     """Build the user message content for a skill slash command invocation.
 
     Args:
@@ -78,39 +237,61 @@ def build_skill_invocation_message(cmd_key: str, user_instruction: str = "") ->
     if not skill_info:
         return None
 
-    skill_md_path = Path(skill_info["skill_md_path"])
-    skill_dir = Path(skill_info["skill_dir"])
-    skill_name = skill_info["name"]
+    loaded = _load_skill_payload(skill_info["skill_dir"], task_id=task_id)
+    if not loaded:
+        return f"[Failed to load skill: {skill_info['name']}]"
 
-    try:
-        content = skill_md_path.read_text(encoding='utf-8')
-    except Exception:
-        return f"[Failed to load skill: {skill_name}]"
+    loaded_skill, skill_dir, skill_name = loaded
+    activation_note = (
+        f'[SYSTEM: The user has invoked the "{skill_name}" skill, indicating they want '
+        "you to follow its instructions. The full skill content is loaded below.]"
+    )
+    return _build_skill_message(
+        loaded_skill,
+        skill_dir,
+        activation_note,
+        user_instruction=user_instruction,
+        runtime_note=runtime_note,
+    )
 
-    parts = [
-        f'[SYSTEM: The user has invoked the "{skill_name}" skill, indicating they want you to follow its instructions. The full skill content is loaded below.]',
-        "",
-        content.strip(),
-    ]
 
-    supporting = []
-    for subdir in ("references", "templates", "scripts", "assets"):
-        subdir_path = skill_dir / subdir
-        if subdir_path.exists():
-            for f in sorted(subdir_path.rglob("*")):
-                if f.is_file():
-                    rel = str(f.relative_to(skill_dir))
-                    supporting.append(rel)
+def build_preloaded_skills_prompt(
+    skill_identifiers: list[str],
+    task_id: str | None = None,
+) -> tuple[str, list[str], list[str]]:
+    """Load one or more skills for session-wide CLI preloading.
 
-    if supporting:
-        parts.append("")
-        parts.append("[This skill has supporting files you can load with the skill_view tool:]")
-        for sf in supporting:
-            parts.append(f"- {sf}")
-        parts.append(f'\nTo view any of these, use: skill_view(name="{skill_name}", file="<path>")')
+    Returns (prompt_text, loaded_skill_names, missing_identifiers).
+    """
+    prompt_parts: list[str] = []
+    loaded_names: list[str] = []
+    missing: list[str] = []
 
-    if user_instruction:
-        parts.append("")
-        parts.append(f"The user has provided the following instruction alongside the skill invocation: {user_instruction}")
+    seen: set[str] = set()
+    for raw_identifier in skill_identifiers:
+        identifier = (raw_identifier or "").strip()
+        if not identifier or identifier in seen:
+            continue
+        seen.add(identifier)
 
-    return "\n".join(parts)
+        loaded = _load_skill_payload(identifier, task_id=task_id)
+        if not loaded:
+            missing.append(identifier)
+            continue
+
+        loaded_skill, skill_dir, skill_name = loaded
+        activation_note = (
+            f'[SYSTEM: The user launched this CLI session with the "{skill_name}" skill '
+            "preloaded. Treat its instructions as active guidance for the duration of this "
+            "session unless the user overrides them.]"
+        )
+        prompt_parts.append(
+            _build_skill_message(
+                loaded_skill,
+                skill_dir,
+                activation_note,
+            )
+        )
+        loaded_names.append(skill_name)
+
+    return "\n\n".join(prompt_parts), loaded_names, missing

agent/skill_utils.py

@@ -0,0 +1,270 @@
+"""Lightweight skill metadata utilities shared by prompt_builder and skills_tool.
+
+This module intentionally avoids importing the tool registry, CLI config, or any
+heavy dependency chain.  It is safe to import at module level without triggering
+tool registration or provider resolution.
+"""
+
+import logging
+import os
+import re
+import sys
+from pathlib import Path
+from typing import Any, Dict, List, Optional, Set, Tuple
+
+from hermes_constants import get_hermes_home
+
+logger = logging.getLogger(__name__)
+
+# ── Platform mapping ──────────────────────────────────────────────────────
+
+PLATFORM_MAP = {
+    "macos": "darwin",
+    "linux": "linux",
+    "windows": "win32",
+}
+
+EXCLUDED_SKILL_DIRS = frozenset((".git", ".github", ".hub"))
+
+# ── Lazy YAML loader ─────────────────────────────────────────────────────
+
+_yaml_load_fn = None
+
+
+def yaml_load(content: str):
+    """Parse YAML with lazy import and CSafeLoader preference."""
+    global _yaml_load_fn
+    if _yaml_load_fn is None:
+        import yaml
+
+        loader = getattr(yaml, "CSafeLoader", None) or yaml.SafeLoader
+
+        def _load(value: str):
+            return yaml.load(value, Loader=loader)
+
+        _yaml_load_fn = _load
+    return _yaml_load_fn(content)
+
+
+# ── Frontmatter parsing ──────────────────────────────────────────────────
+
+
+def parse_frontmatter(content: str) -> Tuple[Dict[str, Any], str]:
+    """Parse YAML frontmatter from a markdown string.
+
+    Uses yaml with CSafeLoader for full YAML support (nested metadata, lists)
+    with a fallback to simple key:value splitting for robustness.
+
+    Returns:
+        (frontmatter_dict, remaining_body)
+    """
+    frontmatter: Dict[str, Any] = {}
+    body = content
+
+    if not content.startswith("---"):
+        return frontmatter, body
+
+    end_match = re.search(r"\n---\s*\n", content[3:])
+    if not end_match:
+        return frontmatter, body
+
+    yaml_content = content[3 : end_match.start() + 3]
+    body = content[end_match.end() + 3 :]
+
+    try:
+        parsed = yaml_load(yaml_content)
+        if isinstance(parsed, dict):
+            frontmatter = parsed
+    except Exception:
+        # Fallback: simple key:value parsing for malformed YAML
+        for line in yaml_content.strip().split("\n"):
+            if ":" not in line:
+                continue
+            key, value = line.split(":", 1)
+            frontmatter[key.strip()] = value.strip()
+
+    return frontmatter, body
+
+
+# ── Platform matching ─────────────────────────────────────────────────────
+
+
+def skill_matches_platform(frontmatter: Dict[str, Any]) -> bool:
+    """Return True when the skill is compatible with the current OS.
+
+    Skills declare platform requirements via a top-level ``platforms`` list
+    in their YAML frontmatter::
+
+        platforms: [macos]          # macOS only
+        platforms: [macos, linux]   # macOS and Linux
+
+    If the field is absent or empty the skill is compatible with **all**
+    platforms (backward-compatible default).
+    """
+    platforms = frontmatter.get("platforms")
+    if not platforms:
+        return True
+    if not isinstance(platforms, list):
+        platforms = [platforms]
+    current = sys.platform
+    for platform in platforms:
+        normalized = str(platform).lower().strip()
+        mapped = PLATFORM_MAP.get(normalized, normalized)
+        if current.startswith(mapped):
+            return True
+    return False
+
+
+# ── Disabled skills ───────────────────────────────────────────────────────
+
+
+def get_disabled_skill_names() -> Set[str]:
+    """Read disabled skill names from config.yaml.
+
+    Resolves platform from ``HERMES_PLATFORM`` env var, falls back to
+    the global disabled list.  Reads the config file directly (no CLI
+    config imports) to stay lightweight.
+    """
+    config_path = get_hermes_home() / "config.yaml"
+    if not config_path.exists():
+        return set()
+    try:
+        parsed = yaml_load(config_path.read_text(encoding="utf-8"))
+    except Exception as e:
+        logger.debug("Could not read skill config %s: %s", config_path, e)
+        return set()
+    if not isinstance(parsed, dict):
+        return set()
+
+    skills_cfg = parsed.get("skills")
+    if not isinstance(skills_cfg, dict):
+        return set()
+
+    resolved_platform = os.getenv("HERMES_PLATFORM")
+    if resolved_platform:
+        platform_disabled = (skills_cfg.get("platform_disabled") or {}).get(
+            resolved_platform
+        )
+        if platform_disabled is not None:
+            return _normalize_string_set(platform_disabled)
+    return _normalize_string_set(skills_cfg.get("disabled"))
+
+
+def _normalize_string_set(values) -> Set[str]:
+    if values is None:
+        return set()
+    if isinstance(values, str):
+        values = [values]
+    return {str(v).strip() for v in values if str(v).strip()}
+
+
+# ── External skills directories ──────────────────────────────────────────
+
+
+def get_external_skills_dirs() -> List[Path]:
+    """Read ``skills.external_dirs`` from config.yaml and return validated paths.
+
+    Each entry is expanded (``~`` and ``${VAR}``) and resolved to an absolute
+    path.  Only directories that actually exist are returned.  Duplicates and
+    paths that resolve to the local ``~/.hermes/skills/`` are silently skipped.
+    """
+    config_path = get_hermes_home() / "config.yaml"
+    if not config_path.exists():
+        return []
+    try:
+        parsed = yaml_load(config_path.read_text(encoding="utf-8"))
+    except Exception:
+        return []
+    if not isinstance(parsed, dict):
+        return []
+
+    skills_cfg = parsed.get("skills")
+    if not isinstance(skills_cfg, dict):
+        return []
+
+    raw_dirs = skills_cfg.get("external_dirs")
+    if not raw_dirs:
+        return []
+    if isinstance(raw_dirs, str):
+        raw_dirs = [raw_dirs]
+    if not isinstance(raw_dirs, list):
+        return []
+
+    local_skills = (get_hermes_home() / "skills").resolve()
+    seen: Set[Path] = set()
+    result: List[Path] = []
+
+    for entry in raw_dirs:
+        entry = str(entry).strip()
+        if not entry:
+            continue
+        # Expand ~ and environment variables
+        expanded = os.path.expanduser(os.path.expandvars(entry))
+        p = Path(expanded).resolve()
+        if p == local_skills:
+            continue
+        if p in seen:
+            continue
+        if p.is_dir():
+            seen.add(p)
+            result.append(p)
+        else:
+            logger.debug("External skills dir does not exist, skipping: %s", p)
+
+    return result
+
+
+def get_all_skills_dirs() -> List[Path]:
+    """Return all skill directories: local ``~/.hermes/skills/`` first, then external.
+
+    The local dir is always first (and always included even if it doesn't exist
+    yet — callers handle that).  External dirs follow in config order.
+    """
+    dirs = [get_hermes_home() / "skills"]
+    dirs.extend(get_external_skills_dirs())
+    return dirs
+
+
+# ── Condition extraction ──────────────────────────────────────────────────
+
+
+def extract_skill_conditions(frontmatter: Dict[str, Any]) -> Dict[str, List]:
+    """Extract conditional activation fields from parsed frontmatter."""
+    hermes = (frontmatter.get("metadata") or {}).get("hermes") or {}
+    return {
+        "fallback_for_toolsets": hermes.get("fallback_for_toolsets", []),
+        "requires_toolsets": hermes.get("requires_toolsets", []),
+        "fallback_for_tools": hermes.get("fallback_for_tools", []),
+        "requires_tools": hermes.get("requires_tools", []),
+    }
+
+
+# ── Description extraction ────────────────────────────────────────────────
+
+
+def extract_skill_description(frontmatter: Dict[str, Any]) -> str:
+    """Extract a truncated description from parsed frontmatter."""
+    raw_desc = frontmatter.get("description", "")
+    if not raw_desc:
+        return ""
+    desc = str(raw_desc).strip().strip("'\"")
+    if len(desc) > 60:
+        return desc[:57] + "..."
+    return desc
+
+
+# ── File iteration ────────────────────────────────────────────────────────
+
+
+def iter_skill_index_files(skills_dir: Path, filename: str):
+    """Walk skills_dir yielding sorted paths matching *filename*.
+
+    Excludes ``.git``, ``.github``, ``.hub`` directories.
+    """
+    matches = []
+    for root, dirs, files in os.walk(skills_dir):
+        dirs[:] = [d for d in dirs if d not in EXCLUDED_SKILL_DIRS]
+        if filename in files:
+            matches.append(Path(root) / filename)
+    for path in sorted(matches, key=lambda p: str(p.relative_to(skills_dir))):
+        yield path

agent/smart_model_routing.py

@@ -0,0 +1,196 @@
+"""Helpers for optional cheap-vs-strong model routing."""
+
+from __future__ import annotations
+
+import os
+import re
+from typing import Any, Dict, Optional
+
+_COMPLEX_KEYWORDS = {
+    "debug",
+    "debugging",
+    "implement",
+    "implementation",
+    "refactor",
+    "patch",
+    "traceback",
+    "stacktrace",
+    "exception",
+    "error",
+    "analyze",
+    "analysis",
+    "investigate",
+    "architecture",
+    "design",
+    "compare",
+    "benchmark",
+    "optimize",
+    "optimise",
+    "review",
+    "terminal",
+    "shell",
+    "tool",
+    "tools",
+    "pytest",
+    "test",
+    "tests",
+    "plan",
+    "planning",
+    "delegate",
+    "subagent",
+    "cron",
+    "docker",
+    "kubernetes",
+}
+
+_URL_RE = re.compile(r"https?://|www\.", re.IGNORECASE)
+
+
+def _coerce_bool(value: Any, default: bool = False) -> bool:
+    if value is None:
+        return default
+    if isinstance(value, bool):
+        return value
+    if isinstance(value, str):
+        return value.strip().lower() in {"1", "true", "yes", "on"}
+    return bool(value)
+
+
+def _coerce_int(value: Any, default: int) -> int:
+    try:
+        return int(value)
+    except (TypeError, ValueError):
+        return default
+
+
+def choose_cheap_model_route(user_message: str, routing_config: Optional[Dict[str, Any]]) -> Optional[Dict[str, Any]]:
+    """Return the configured cheap-model route when a message looks simple.
+
+    Conservative by design: if the message has signs of code/tool/debugging/
+    long-form work, keep the primary model.
+    """
+    cfg = routing_config or {}
+    if not _coerce_bool(cfg.get("enabled"), False):
+        return None
+
+    cheap_model = cfg.get("cheap_model") or {}
+    if not isinstance(cheap_model, dict):
+        return None
+    provider = str(cheap_model.get("provider") or "").strip().lower()
+    model = str(cheap_model.get("model") or "").strip()
+    if not provider or not model:
+        return None
+
+    text = (user_message or "").strip()
+    if not text:
+        return None
+
+    max_chars = _coerce_int(cfg.get("max_simple_chars"), 160)
+    max_words = _coerce_int(cfg.get("max_simple_words"), 28)
+
+    if len(text) > max_chars:
+        return None
+    if len(text.split()) > max_words:
+        return None
+    if text.count("\n") > 1:
+        return None
+    if "```" in text or "`" in text:
+        return None
+    if _URL_RE.search(text):
+        return None
+
+    lowered = text.lower()
+    words = {token.strip(".,:;!?()[]{}\"'`") for token in lowered.split()}
+    if words & _COMPLEX_KEYWORDS:
+        return None
+
+    route = dict(cheap_model)
+    route["provider"] = provider
+    route["model"] = model
+    route["routing_reason"] = "simple_turn"
+    return route
+
+
+def resolve_turn_route(user_message: str, routing_config: Optional[Dict[str, Any]], primary: Dict[str, Any]) -> Dict[str, Any]:
+    """Resolve the effective model/runtime for one turn.
+
+    Returns a dict with model/runtime/signature/label fields.
+    """
+    route = choose_cheap_model_route(user_message, routing_config)
+    if not route:
+        return {
+            "model": primary.get("model"),
+            "runtime": {
+                "api_key": primary.get("api_key"),
+                "base_url": primary.get("base_url"),
+                "provider": primary.get("provider"),
+                "api_mode": primary.get("api_mode"),
+                "command": primary.get("command"),
+                "args": list(primary.get("args") or []),
+            },
+            "label": None,
+            "signature": (
+                primary.get("model"),
+                primary.get("provider"),
+                primary.get("base_url"),
+                primary.get("api_mode"),
+                primary.get("command"),
+                tuple(primary.get("args") or ()),
+            ),
+        }
+
+    from hermes_cli.runtime_provider import resolve_runtime_provider
+
+    explicit_api_key = None
+    api_key_env = str(route.get("api_key_env") or "").strip()
+    if api_key_env:
+        explicit_api_key = os.getenv(api_key_env) or None
+
+    try:
+        runtime = resolve_runtime_provider(
+            requested=route.get("provider"),
+            explicit_api_key=explicit_api_key,
+            explicit_base_url=route.get("base_url"),
+        )
+    except Exception:
+        return {
+            "model": primary.get("model"),
+            "runtime": {
+                "api_key": primary.get("api_key"),
+                "base_url": primary.get("base_url"),
+                "provider": primary.get("provider"),
+                "api_mode": primary.get("api_mode"),
+                "command": primary.get("command"),
+                "args": list(primary.get("args") or []),
+            },
+            "label": None,
+            "signature": (
+                primary.get("model"),
+                primary.get("provider"),
+                primary.get("base_url"),
+                primary.get("api_mode"),
+                primary.get("command"),
+                tuple(primary.get("args") or ()),
+            ),
+        }
+
+    return {
+        "model": route.get("model"),
+        "runtime": {
+            "api_key": runtime.get("api_key"),
+            "base_url": runtime.get("base_url"),
+            "provider": runtime.get("provider"),
+            "api_mode": runtime.get("api_mode"),
+            "command": runtime.get("command"),
+            "args": list(runtime.get("args") or []),
+        },
+        "label": f"smart route → {route.get('model')} ({runtime.get('provider')})",
+        "signature": (
+            route.get("model"),
+            runtime.get("provider"),
+            runtime.get("base_url"),
+            runtime.get("api_mode"),
+            runtime.get("command"),
+            tuple(runtime.get("args") or ()),
+        ),
+    }

agent/title_generator.py

@@ -0,0 +1,125 @@
+"""Auto-generate short session titles from the first user/assistant exchange.
+
+Runs asynchronously after the first response is delivered so it never
+adds latency to the user-facing reply.
+"""
+
+import logging
+import threading
+from typing import Optional
+
+from agent.auxiliary_client import call_llm
+
+logger = logging.getLogger(__name__)
+
+_TITLE_PROMPT = (
+    "Generate a short, descriptive title (3-7 words) for a conversation that starts with the "
+    "following exchange. The title should capture the main topic or intent. "
+    "Return ONLY the title text, nothing else. No quotes, no punctuation at the end, no prefixes."
+)
+
+
+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).
+    Returns the title string or None on failure.
+    """
+    # Truncate long messages to keep the request small
+    user_snippet = user_message[:500] if user_message else ""
+    assistant_snippet = assistant_response[:500] if assistant_response else ""
+
+    messages = [
+        {"role": "system", "content": _TITLE_PROMPT},
+        {"role": "user", "content": f"User: {user_snippet}\n\nAssistant: {assistant_snippet}"},
+    ]
+
+    try:
+        response = call_llm(
+            task="compression",  # reuse compression task config (cheap/fast model)
+            messages=messages,
+            max_tokens=30,
+            temperature=0.3,
+            timeout=timeout,
+        )
+        title = (response.choices[0].message.content or "").strip()
+        # Clean up: remove quotes, trailing punctuation, prefixes like "Title: "
+        title = title.strip('"\'')
+        if title.lower().startswith("title:"):
+            title = title[6:].strip()
+        # Enforce reasonable length
+        if len(title) > 80:
+            title = title[:77] + "..."
+        return title if title else None
+    except Exception as e:
+        logger.debug("Title generation failed: %s", e)
+        return None
+
+
+def auto_title_session(
+    session_db,
+    session_id: str,
+    user_message: str,
+    assistant_response: str,
+) -> None:
+    """Generate and set a session title if one doesn't already exist.
+
+    Called in a background thread after the first exchange completes.
+    Silently skips if:
+    - session_db is None
+    - session already has a title (user-set or previously auto-generated)
+    - title generation fails
+    """
+    if not session_db or not session_id:
+        return
+
+    # Check if title already exists (user may have set one via /title before first response)
+    try:
+        existing = session_db.get_session_title(session_id)
+        if existing:
+            return
+    except Exception:
+        return
+
+    title = generate_title(user_message, assistant_response)
+    if not title:
+        return
+
+    try:
+        session_db.set_session_title(session_id, title)
+        logger.debug("Auto-generated session title: %s", title)
+    except Exception as e:
+        logger.debug("Failed to set auto-generated title: %s", e)
+
+
+def maybe_auto_title(
+    session_db,
+    session_id: str,
+    user_message: str,
+    assistant_response: str,
+    conversation_history: list,
+) -> None:
+    """Fire-and-forget title generation after the first exchange.
+
+    Only generates a title when:
+    - This appears to be the first user→assistant exchange
+    - No title is already set
+    """
+    if not session_db or not session_id or not user_message or not assistant_response:
+        return
+
+    # Count user messages in history to detect first exchange.
+    # conversation_history includes the exchange that just happened,
+    # so for a first exchange we expect exactly 1 user message
+    # (or 2 counting system). Be generous: generate on first 2 exchanges.
+    user_msg_count = sum(1 for m in (conversation_history or []) if m.get("role") == "user")
+    if user_msg_count > 2:
+        return
+
+    thread = threading.Thread(
+        target=auto_title_session,
+        args=(session_db, session_id, user_message, assistant_response),
+        daemon=True,
+        name="auto-title",
+    )
+    thread.start()

agent/usage_pricing.py

@@ -0,0 +1,656 @@
+from __future__ import annotations
+
+from dataclasses import dataclass
+from datetime import datetime, timezone
+from decimal import Decimal
+from typing import Any, Dict, Literal, Optional
+
+from agent.model_metadata import fetch_endpoint_model_metadata, fetch_model_metadata
+
+DEFAULT_PRICING = {"input": 0.0, "output": 0.0}
+
+_ZERO = Decimal("0")
+_ONE_MILLION = Decimal("1000000")
+
+CostStatus = Literal["actual", "estimated", "included", "unknown"]
+CostSource = Literal[
+    "provider_cost_api",
+    "provider_generation_api",
+    "provider_models_api",
+    "official_docs_snapshot",
+    "user_override",
+    "custom_contract",
+    "none",
+]
+
+
+@dataclass(frozen=True)
+class CanonicalUsage:
+    input_tokens: int = 0
+    output_tokens: int = 0
+    cache_read_tokens: int = 0
+    cache_write_tokens: int = 0
+    reasoning_tokens: int = 0
+    request_count: int = 1
+    raw_usage: Optional[dict[str, Any]] = None
+
+    @property
+    def prompt_tokens(self) -> int:
+        return self.input_tokens + self.cache_read_tokens + self.cache_write_tokens
+
+    @property
+    def total_tokens(self) -> int:
+        return self.prompt_tokens + self.output_tokens
+
+
+@dataclass(frozen=True)
+class BillingRoute:
+    provider: str
+    model: str
+    base_url: str = ""
+    billing_mode: str = "unknown"
+
+
+@dataclass(frozen=True)
+class PricingEntry:
+    input_cost_per_million: Optional[Decimal] = None
+    output_cost_per_million: Optional[Decimal] = None
+    cache_read_cost_per_million: Optional[Decimal] = None
+    cache_write_cost_per_million: Optional[Decimal] = None
+    request_cost: Optional[Decimal] = None
+    source: CostSource = "none"
+    source_url: Optional[str] = None
+    pricing_version: Optional[str] = None
+    fetched_at: Optional[datetime] = None
+
+
+@dataclass(frozen=True)
+class CostResult:
+    amount_usd: Optional[Decimal]
+    status: CostStatus
+    source: CostSource
+    label: str
+    fetched_at: Optional[datetime] = None
+    pricing_version: Optional[str] = None
+    notes: tuple[str, ...] = ()
+
+
+_UTC_NOW = lambda: datetime.now(timezone.utc)
+
+
+# Official docs snapshot entries. Models whose published pricing and cache
+# semantics are stable enough to encode exactly.
+_OFFICIAL_DOCS_PRICING: Dict[tuple[str, str], PricingEntry] = {
+    (
+        "anthropic",
+        "claude-opus-4-20250514",
+    ): PricingEntry(
+        input_cost_per_million=Decimal("15.00"),
+        output_cost_per_million=Decimal("75.00"),
+        cache_read_cost_per_million=Decimal("1.50"),
+        cache_write_cost_per_million=Decimal("18.75"),
+        source="official_docs_snapshot",
+        source_url="https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching",
+        pricing_version="anthropic-prompt-caching-2026-03-16",
+    ),
+    (
+        "anthropic",
+        "claude-sonnet-4-20250514",
+    ): PricingEntry(
+        input_cost_per_million=Decimal("3.00"),
+        output_cost_per_million=Decimal("15.00"),
+        cache_read_cost_per_million=Decimal("0.30"),
+        cache_write_cost_per_million=Decimal("3.75"),
+        source="official_docs_snapshot",
+        source_url="https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching",
+        pricing_version="anthropic-prompt-caching-2026-03-16",
+    ),
+    # OpenAI
+    (
+        "openai",
+        "gpt-4o",
+    ): PricingEntry(
+        input_cost_per_million=Decimal("2.50"),
+        output_cost_per_million=Decimal("10.00"),
+        cache_read_cost_per_million=Decimal("1.25"),
+        source="official_docs_snapshot",
+        source_url="https://openai.com/api/pricing/",
+        pricing_version="openai-pricing-2026-03-16",
+    ),
+    (
+        "openai",
+        "gpt-4o-mini",
+    ): PricingEntry(
+        input_cost_per_million=Decimal("0.15"),
+        output_cost_per_million=Decimal("0.60"),
+        cache_read_cost_per_million=Decimal("0.075"),
+        source="official_docs_snapshot",
+        source_url="https://openai.com/api/pricing/",
+        pricing_version="openai-pricing-2026-03-16",
+    ),
+    (
+        "openai",
+        "gpt-4.1",
+    ): PricingEntry(
+        input_cost_per_million=Decimal("2.00"),
+        output_cost_per_million=Decimal("8.00"),
+        cache_read_cost_per_million=Decimal("0.50"),
+        source="official_docs_snapshot",
+        source_url="https://openai.com/api/pricing/",
+        pricing_version="openai-pricing-2026-03-16",
+    ),
+    (
+        "openai",
+        "gpt-4.1-mini",
+    ): PricingEntry(
+        input_cost_per_million=Decimal("0.40"),
+        output_cost_per_million=Decimal("1.60"),
+        cache_read_cost_per_million=Decimal("0.10"),
+        source="official_docs_snapshot",
+        source_url="https://openai.com/api/pricing/",
+        pricing_version="openai-pricing-2026-03-16",
+    ),
+    (
+        "openai",
+        "gpt-4.1-nano",
+    ): PricingEntry(
+        input_cost_per_million=Decimal("0.10"),
+        output_cost_per_million=Decimal("0.40"),
+        cache_read_cost_per_million=Decimal("0.025"),
+        source="official_docs_snapshot",
+        source_url="https://openai.com/api/pricing/",
+        pricing_version="openai-pricing-2026-03-16",
+    ),
+    (
+        "openai",
+        "o3",
+    ): PricingEntry(
+        input_cost_per_million=Decimal("10.00"),
+        output_cost_per_million=Decimal("40.00"),
+        cache_read_cost_per_million=Decimal("2.50"),
+        source="official_docs_snapshot",
+        source_url="https://openai.com/api/pricing/",
+        pricing_version="openai-pricing-2026-03-16",
+    ),
+    (
+        "openai",
+        "o3-mini",
+    ): PricingEntry(
+        input_cost_per_million=Decimal("1.10"),
+        output_cost_per_million=Decimal("4.40"),
+        cache_read_cost_per_million=Decimal("0.55"),
+        source="official_docs_snapshot",
+        source_url="https://openai.com/api/pricing/",
+        pricing_version="openai-pricing-2026-03-16",
+    ),
+    # Anthropic older models (pre-4.6 generation)
+    (
+        "anthropic",
+        "claude-3-5-sonnet-20241022",
+    ): PricingEntry(
+        input_cost_per_million=Decimal("3.00"),
+        output_cost_per_million=Decimal("15.00"),
+        cache_read_cost_per_million=Decimal("0.30"),
+        cache_write_cost_per_million=Decimal("3.75"),
+        source="official_docs_snapshot",
+        source_url="https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching",
+        pricing_version="anthropic-pricing-2026-03-16",
+    ),
+    (
+        "anthropic",
+        "claude-3-5-haiku-20241022",
+    ): PricingEntry(
+        input_cost_per_million=Decimal("0.80"),
+        output_cost_per_million=Decimal("4.00"),
+        cache_read_cost_per_million=Decimal("0.08"),
+        cache_write_cost_per_million=Decimal("1.00"),
+        source="official_docs_snapshot",
+        source_url="https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching",
+        pricing_version="anthropic-pricing-2026-03-16",
+    ),
+    (
+        "anthropic",
+        "claude-3-opus-20240229",
+    ): PricingEntry(
+        input_cost_per_million=Decimal("15.00"),
+        output_cost_per_million=Decimal("75.00"),
+        cache_read_cost_per_million=Decimal("1.50"),
+        cache_write_cost_per_million=Decimal("18.75"),
+        source="official_docs_snapshot",
+        source_url="https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching",
+        pricing_version="anthropic-pricing-2026-03-16",
+    ),
+    (
+        "anthropic",
+        "claude-3-haiku-20240307",
+    ): PricingEntry(
+        input_cost_per_million=Decimal("0.25"),
+        output_cost_per_million=Decimal("1.25"),
+        cache_read_cost_per_million=Decimal("0.03"),
+        cache_write_cost_per_million=Decimal("0.30"),
+        source="official_docs_snapshot",
+        source_url="https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching",
+        pricing_version="anthropic-pricing-2026-03-16",
+    ),
+    # DeepSeek
+    (
+        "deepseek",
+        "deepseek-chat",
+    ): PricingEntry(
+        input_cost_per_million=Decimal("0.14"),
+        output_cost_per_million=Decimal("0.28"),
+        source="official_docs_snapshot",
+        source_url="https://api-docs.deepseek.com/quick_start/pricing",
+        pricing_version="deepseek-pricing-2026-03-16",
+    ),
+    (
+        "deepseek",
+        "deepseek-reasoner",
+    ): PricingEntry(
+        input_cost_per_million=Decimal("0.55"),
+        output_cost_per_million=Decimal("2.19"),
+        source="official_docs_snapshot",
+        source_url="https://api-docs.deepseek.com/quick_start/pricing",
+        pricing_version="deepseek-pricing-2026-03-16",
+    ),
+    # Google Gemini
+    (
+        "google",
+        "gemini-2.5-pro",
+    ): PricingEntry(
+        input_cost_per_million=Decimal("1.25"),
+        output_cost_per_million=Decimal("10.00"),
+        source="official_docs_snapshot",
+        source_url="https://ai.google.dev/pricing",
+        pricing_version="google-pricing-2026-03-16",
+    ),
+    (
+        "google",
+        "gemini-2.5-flash",
+    ): PricingEntry(
+        input_cost_per_million=Decimal("0.15"),
+        output_cost_per_million=Decimal("0.60"),
+        source="official_docs_snapshot",
+        source_url="https://ai.google.dev/pricing",
+        pricing_version="google-pricing-2026-03-16",
+    ),
+    (
+        "google",
+        "gemini-2.0-flash",
+    ): PricingEntry(
+        input_cost_per_million=Decimal("0.10"),
+        output_cost_per_million=Decimal("0.40"),
+        source="official_docs_snapshot",
+        source_url="https://ai.google.dev/pricing",
+        pricing_version="google-pricing-2026-03-16",
+    ),
+}
+
+
+def _to_decimal(value: Any) -> Optional[Decimal]:
+    if value is None:
+        return None
+    try:
+        return Decimal(str(value))
+    except Exception:
+        return None
+
+
+def _to_int(value: Any) -> int:
+    try:
+        return int(value or 0)
+    except Exception:
+        return 0
+
+
+def resolve_billing_route(
+    model_name: str,
+    provider: Optional[str] = None,
+    base_url: Optional[str] = None,
+) -> BillingRoute:
+    provider_name = (provider or "").strip().lower()
+    base = (base_url or "").strip().lower()
+    model = (model_name or "").strip()
+    if not provider_name and "/" in model:
+        inferred_provider, bare_model = model.split("/", 1)
+        if inferred_provider in {"anthropic", "openai", "google"}:
+            provider_name = inferred_provider
+            model = bare_model
+
+    if provider_name == "openai-codex":
+        return BillingRoute(provider="openai-codex", model=model, base_url=base_url or "", billing_mode="subscription_included")
+    if provider_name == "openrouter" or "openrouter.ai" in base:
+        return BillingRoute(provider="openrouter", model=model, base_url=base_url or "", billing_mode="official_models_api")
+    if provider_name == "anthropic":
+        return BillingRoute(provider="anthropic", model=model.split("/")[-1], base_url=base_url or "", billing_mode="official_docs_snapshot")
+    if provider_name == "openai":
+        return BillingRoute(provider="openai", model=model.split("/")[-1], base_url=base_url or "", billing_mode="official_docs_snapshot")
+    if provider_name in {"custom", "local"} or (base and "localhost" in base):
+        return BillingRoute(provider=provider_name or "custom", model=model, base_url=base_url or "", billing_mode="unknown")
+    return BillingRoute(provider=provider_name or "unknown", model=model.split("/")[-1] if model else "", base_url=base_url or "", billing_mode="unknown")
+
+
+def _lookup_official_docs_pricing(route: BillingRoute) -> Optional[PricingEntry]:
+    return _OFFICIAL_DOCS_PRICING.get((route.provider, route.model.lower()))
+
+
+def _openrouter_pricing_entry(route: BillingRoute) -> Optional[PricingEntry]:
+    return _pricing_entry_from_metadata(
+        fetch_model_metadata(),
+        route.model,
+        source_url="https://openrouter.ai/docs/api/api-reference/models/get-models",
+        pricing_version="openrouter-models-api",
+    )
+
+
+def _pricing_entry_from_metadata(
+    metadata: Dict[str, Dict[str, Any]],
+    model_id: str,
+    *,
+    source_url: str,
+    pricing_version: str,
+) -> Optional[PricingEntry]:
+    if model_id not in metadata:
+        return None
+    pricing = metadata[model_id].get("pricing") or {}
+    prompt = _to_decimal(pricing.get("prompt"))
+    completion = _to_decimal(pricing.get("completion"))
+    request = _to_decimal(pricing.get("request"))
+    cache_read = _to_decimal(
+        pricing.get("cache_read")
+        or pricing.get("cached_prompt")
+        or pricing.get("input_cache_read")
+    )
+    cache_write = _to_decimal(
+        pricing.get("cache_write")
+        or pricing.get("cache_creation")
+        or pricing.get("input_cache_write")
+    )
+    if prompt is None and completion is None and request is None:
+        return None
+
+    def _per_token_to_per_million(value: Optional[Decimal]) -> Optional[Decimal]:
+        if value is None:
+            return None
+        return value * _ONE_MILLION
+
+    return PricingEntry(
+        input_cost_per_million=_per_token_to_per_million(prompt),
+        output_cost_per_million=_per_token_to_per_million(completion),
+        cache_read_cost_per_million=_per_token_to_per_million(cache_read),
+        cache_write_cost_per_million=_per_token_to_per_million(cache_write),
+        request_cost=request,
+        source="provider_models_api",
+        source_url=source_url,
+        pricing_version=pricing_version,
+        fetched_at=_UTC_NOW(),
+    )
+
+
+def get_pricing_entry(
+    model_name: str,
+    provider: Optional[str] = None,
+    base_url: Optional[str] = None,
+    api_key: Optional[str] = None,
+) -> Optional[PricingEntry]:
+    route = resolve_billing_route(model_name, provider=provider, base_url=base_url)
+    if route.billing_mode == "subscription_included":
+        return PricingEntry(
+            input_cost_per_million=_ZERO,
+            output_cost_per_million=_ZERO,
+            cache_read_cost_per_million=_ZERO,
+            cache_write_cost_per_million=_ZERO,
+            source="none",
+            pricing_version="included-route",
+        )
+    if route.provider == "openrouter":
+        return _openrouter_pricing_entry(route)
+    if route.base_url:
+        entry = _pricing_entry_from_metadata(
+            fetch_endpoint_model_metadata(route.base_url, api_key=api_key or ""),
+            route.model,
+            source_url=f"{route.base_url.rstrip('/')}/models",
+            pricing_version="openai-compatible-models-api",
+        )
+        if entry:
+            return entry
+    return _lookup_official_docs_pricing(route)
+
+
+def normalize_usage(
+    response_usage: Any,
+    *,
+    provider: Optional[str] = None,
+    api_mode: Optional[str] = None,
+) -> CanonicalUsage:
+    """Normalize raw API response usage into canonical token buckets.
+
+    Handles three API shapes:
+    - Anthropic: input_tokens/output_tokens/cache_read_input_tokens/cache_creation_input_tokens
+    - Codex Responses: input_tokens includes cache tokens; input_tokens_details.cached_tokens separates them
+    - OpenAI Chat Completions: prompt_tokens includes cache tokens; prompt_tokens_details.cached_tokens separates them
+
+    In both Codex and OpenAI modes, input_tokens is derived by subtracting cache
+    tokens from the total — the API contract is that input/prompt totals include
+    cached tokens and the details object breaks them out.
+    """
+    if not response_usage:
+        return CanonicalUsage()
+
+    provider_name = (provider or "").strip().lower()
+    mode = (api_mode or "").strip().lower()
+
+    if mode == "anthropic_messages" or provider_name == "anthropic":
+        input_tokens = _to_int(getattr(response_usage, "input_tokens", 0))
+        output_tokens = _to_int(getattr(response_usage, "output_tokens", 0))
+        cache_read_tokens = _to_int(getattr(response_usage, "cache_read_input_tokens", 0))
+        cache_write_tokens = _to_int(getattr(response_usage, "cache_creation_input_tokens", 0))
+    elif mode == "codex_responses":
+        input_total = _to_int(getattr(response_usage, "input_tokens", 0))
+        output_tokens = _to_int(getattr(response_usage, "output_tokens", 0))
+        details = getattr(response_usage, "input_tokens_details", None)
+        cache_read_tokens = _to_int(getattr(details, "cached_tokens", 0) if details else 0)
+        cache_write_tokens = _to_int(
+            getattr(details, "cache_creation_tokens", 0) if details else 0
+        )
+        input_tokens = max(0, input_total - cache_read_tokens - cache_write_tokens)
+    else:
+        prompt_total = _to_int(getattr(response_usage, "prompt_tokens", 0))
+        output_tokens = _to_int(getattr(response_usage, "completion_tokens", 0))
+        details = getattr(response_usage, "prompt_tokens_details", None)
+        cache_read_tokens = _to_int(getattr(details, "cached_tokens", 0) if details else 0)
+        cache_write_tokens = _to_int(
+            getattr(details, "cache_write_tokens", 0) if details else 0
+        )
+        input_tokens = max(0, prompt_total - cache_read_tokens - cache_write_tokens)
+
+    reasoning_tokens = 0
+    output_details = getattr(response_usage, "output_tokens_details", None)
+    if output_details:
+        reasoning_tokens = _to_int(getattr(output_details, "reasoning_tokens", 0))
+
+    return CanonicalUsage(
+        input_tokens=input_tokens,
+        output_tokens=output_tokens,
+        cache_read_tokens=cache_read_tokens,
+        cache_write_tokens=cache_write_tokens,
+        reasoning_tokens=reasoning_tokens,
+    )
+
+
+def estimate_usage_cost(
+    model_name: str,
+    usage: CanonicalUsage,
+    *,
+    provider: Optional[str] = None,
+    base_url: Optional[str] = None,
+    api_key: Optional[str] = None,
+) -> CostResult:
+    route = resolve_billing_route(model_name, provider=provider, base_url=base_url)
+    if route.billing_mode == "subscription_included":
+        return CostResult(
+            amount_usd=_ZERO,
+            status="included",
+            source="none",
+            label="included",
+            pricing_version="included-route",
+        )
+
+    entry = get_pricing_entry(model_name, provider=provider, base_url=base_url, api_key=api_key)
+    if not entry:
+        return CostResult(amount_usd=None, status="unknown", source="none", label="n/a")
+
+    notes: list[str] = []
+    amount = _ZERO
+
+    if usage.input_tokens and entry.input_cost_per_million is None:
+        return CostResult(amount_usd=None, status="unknown", source=entry.source, label="n/a")
+    if usage.output_tokens and entry.output_cost_per_million is None:
+        return CostResult(amount_usd=None, status="unknown", source=entry.source, label="n/a")
+    if usage.cache_read_tokens:
+        if entry.cache_read_cost_per_million is None:
+            return CostResult(
+                amount_usd=None,
+                status="unknown",
+                source=entry.source,
+                label="n/a",
+                notes=("cache-read pricing unavailable for route",),
+            )
+    if usage.cache_write_tokens:
+        if entry.cache_write_cost_per_million is None:
+            return CostResult(
+                amount_usd=None,
+                status="unknown",
+                source=entry.source,
+                label="n/a",
+                notes=("cache-write pricing unavailable for route",),
+            )
+
+    if entry.input_cost_per_million is not None:
+        amount += Decimal(usage.input_tokens) * entry.input_cost_per_million / _ONE_MILLION
+    if entry.output_cost_per_million is not None:
+        amount += Decimal(usage.output_tokens) * entry.output_cost_per_million / _ONE_MILLION
+    if entry.cache_read_cost_per_million is not None:
+        amount += Decimal(usage.cache_read_tokens) * entry.cache_read_cost_per_million / _ONE_MILLION
+    if entry.cache_write_cost_per_million is not None:
+        amount += Decimal(usage.cache_write_tokens) * entry.cache_write_cost_per_million / _ONE_MILLION
+    if entry.request_cost is not None and usage.request_count:
+        amount += Decimal(usage.request_count) * entry.request_cost
+
+    status: CostStatus = "estimated"
+    label = f"~${amount:.2f}"
+    if entry.source == "none" and amount == _ZERO:
+        status = "included"
+        label = "included"
+
+    if route.provider == "openrouter":
+        notes.append("OpenRouter cost is estimated from the models API until reconciled.")
+
+    return CostResult(
+        amount_usd=amount,
+        status=status,
+        source=entry.source,
+        label=label,
+        fetched_at=entry.fetched_at,
+        pricing_version=entry.pricing_version,
+        notes=tuple(notes),
+    )
+
+
+def has_known_pricing(
+    model_name: str,
+    provider: Optional[str] = None,
+    base_url: Optional[str] = None,
+    api_key: Optional[str] = None,
+) -> bool:
+    """Check whether we have pricing data for this model+route.
+
+    Uses direct lookup instead of routing through the full estimation
+    pipeline — avoids creating dummy usage objects just to check status.
+    """
+    route = resolve_billing_route(model_name, provider=provider, base_url=base_url)
+    if route.billing_mode == "subscription_included":
+        return True
+    entry = get_pricing_entry(model_name, provider=provider, base_url=base_url, api_key=api_key)
+    return entry is not None
+
+
+def get_pricing(
+    model_name: str,
+    provider: Optional[str] = None,
+    base_url: Optional[str] = None,
+    api_key: Optional[str] = None,
+) -> Dict[str, float]:
+    """Backward-compatible thin wrapper for legacy callers.
+
+    Returns only non-cache input/output fields when a pricing entry exists.
+    Unknown routes return zeroes.
+    """
+    entry = get_pricing_entry(model_name, provider=provider, base_url=base_url, api_key=api_key)
+    if not entry:
+        return {"input": 0.0, "output": 0.0}
+    return {
+        "input": float(entry.input_cost_per_million or _ZERO),
+        "output": float(entry.output_cost_per_million or _ZERO),
+    }
+
+
+def estimate_cost_usd(
+    model: str,
+    input_tokens: int,
+    output_tokens: int,
+    *,
+    provider: Optional[str] = None,
+    base_url: Optional[str] = None,
+    api_key: Optional[str] = None,
+) -> float:
+    """Backward-compatible helper for legacy callers.
+
+    This uses non-cached input/output only. New code should call
+    `estimate_usage_cost()` with canonical usage buckets.
+    """
+    result = estimate_usage_cost(
+        model,
+        CanonicalUsage(input_tokens=input_tokens, output_tokens=output_tokens),
+        provider=provider,
+        base_url=base_url,
+        api_key=api_key,
+    )
+    return float(result.amount_usd or _ZERO)
+
+
+def format_duration_compact(seconds: float) -> str:
+    if seconds < 60:
+        return f"{seconds:.0f}s"
+    minutes = seconds / 60
+    if minutes < 60:
+        return f"{minutes:.0f}m"
+    hours = minutes / 60
+    if hours < 24:
+        remaining_min = int(minutes % 60)
+        return f"{int(hours)}h {remaining_min}m" if remaining_min else f"{int(hours)}h"
+    days = hours / 24
+    return f"{days:.1f}d"
+
+
+def format_token_count_compact(value: int) -> str:
+    abs_value = abs(int(value))
+    if abs_value < 1_000:
+        return str(int(value))
+
+    sign = "-" if value < 0 else ""
+    units = ((1_000_000_000, "B"), (1_000_000, "M"), (1_000, "K"))
+    for threshold, suffix in units:
+        if abs_value >= threshold:
+            scaled = abs_value / threshold
+            if scaled < 10:
+                text = f"{scaled:.2f}"
+            elif scaled < 100:
+                text = f"{scaled:.1f}"
+            else:
+                text = f"{scaled:.0f}"
+            if "." in text:
+                text = text.rstrip("0").rstrip(".")
+            return f"{sign}{text}{suffix}"
+
+    return f"{value:,}"

batch_runner.py

@@ -128,6 +128,7 @@ def _extract_tool_stats(messages: List[Dict[str, Any]]) -> Dict[str, Dict[str, i
         # Track tool calls from assistant messages
         if msg["role"] == "assistant" and "tool_calls" in msg and msg["tool_calls"]:
             for tool_call in msg["tool_calls"]:
+                if not tool_call or not isinstance(tool_call, dict): continue
                 tool_name = tool_call["function"]["name"]
                 tool_call_id = tool_call["id"]
                 
@@ -606,7 +607,7 @@ class BatchRunner:
         # Create batches
         self.batches = self._create_batches()
         
-        print(f"📊 Batch Runner Initialized")
+        print("📊 Batch Runner Initialized")
         print(f"   Dataset: {self.dataset_file} ({len(self.dataset)} prompts)")
         print(f"   Batch size: {self.batch_size}")
         print(f"   Total batches: {len(self.batches)}")
@@ -826,7 +827,7 @@ class BatchRunner:
             print("=" * 70)
             print(f"   Original dataset size:     {len(self.dataset):,} prompts")
             print(f"   Already completed:         {len(skipped_indices):,} prompts")
-            print(f"   ─────────────────────────────────────────")
+            print("   ─────────────────────────────────────────")
             print(f"   🎯 RESUMING WITH:          {len(filtered_entries):,} prompts")
             print(f"   New batches created:       {len(batches_to_process)}")
             print("=" * 70 + "\n")
@@ -888,7 +889,7 @@ class BatchRunner:
             ]
             
             print(f"✅ Created {len(tasks)} batch tasks")
-            print(f"🚀 Starting parallel batch processing...\n")
+            print("🚀 Starting parallel batch processing...\n")
             
             # Use rich Progress for better visual tracking with persistent bottom bar
             # redirect_stdout/stderr lets rich manage all output so progress bar stays clean
@@ -1057,7 +1058,7 @@ class BatchRunner:
         print(f"✅ Total trajectories in merged file: {total_entries - filtered_entries}")
         print(f"✅ Total batch files merged: {batch_files_found}")
         print(f"⏱️  Total duration: {round(time.time() - start_time, 2)}s")
-        print(f"\n📈 Tool Usage Statistics:")
+        print("\n📈 Tool Usage Statistics:")
         print("-" * 70)
         
         if total_tool_stats:
@@ -1084,7 +1085,7 @@ class BatchRunner:
         # Print reasoning coverage stats
         total_discarded = sum(r.get("discarded_no_reasoning", 0) for r in results)
         
-        print(f"\n🧠 Reasoning Coverage:")
+        print("\n🧠 Reasoning Coverage:")
         print("-" * 70)
         total_turns = total_reasoning_stats["total_assistant_turns"]
         with_reasoning = total_reasoning_stats["turns_with_reasoning"]
@@ -1101,8 +1102,8 @@ class BatchRunner:
             print(f"   🚫 Samples discarded (zero reasoning): {total_discarded:,}")
         
         print(f"\n💾 Results saved to: {self.output_dir}")
-        print(f"   - Trajectories: trajectories.jsonl (combined)")
-        print(f"   - Individual batches: batch_*.jsonl (for debugging)")
+        print("   - Trajectories: trajectories.jsonl (combined)")
+        print("   - Individual batches: batch_*.jsonl (for debugging)")
         print(f"   - Statistics: {self.stats_file.name}")
         print(f"   - Checkpoint: {self.checkpoint_file.name}")
 
@@ -1238,7 +1239,7 @@ def main(
             with open(prefill_messages_file, 'r', encoding='utf-8') as f:
                 prefill_messages = json.load(f)
             if not isinstance(prefill_messages, list):
-                print(f"❌ Error: prefill_messages_file must contain a JSON array of messages")
+                print("❌ Error: prefill_messages_file must contain a JSON array of messages")
                 return
             print(f"💬 Loaded {len(prefill_messages)} prefill messages from {prefill_messages_file}")
         except Exception as e:

cli-config.yaml.example

@@ -7,16 +7,33 @@
 # =============================================================================
 model:
   # Default model to use (can be overridden with --model flag)
+  # Both "default" and "model" work as the key name here.
   default: "anthropic/claude-opus-4.6"
   
   # Inference provider selection:
-  #   "auto"       - Use Nous Portal if logged in, otherwise OpenRouter/env vars (default)
-  #   "openrouter" - Always use OpenRouter API key from OPENROUTER_API_KEY
-  #   "nous"       - Always use Nous Portal (requires: hermes login)
-  #   "zai"        - Use z.ai / ZhipuAI GLM models (requires: GLM_API_KEY)
-  #   "kimi-coding"- Use Kimi / Moonshot AI models (requires: KIMI_API_KEY)
-  #   "minimax"    - Use MiniMax global endpoint (requires: MINIMAX_API_KEY)
-  #   "minimax-cn" - Use MiniMax China endpoint (requires: MINIMAX_CN_API_KEY)
+  #   "auto"         - Auto-detect from credentials (default)
+  #   "openrouter"   - OpenRouter (requires: OPENROUTER_API_KEY or OPENAI_API_KEY)
+  #   "nous"         - Nous Portal OAuth (requires: hermes login)
+  #   "nous-api"     - Nous Portal API key (requires: NOUS_API_KEY)
+  #   "anthropic"    - Direct Anthropic API (requires: ANTHROPIC_API_KEY)
+  #   "openai-codex" - OpenAI Codex (requires: hermes login --provider openai-codex)
+  #   "copilot"      - GitHub Copilot / GitHub Models (requires: GITHUB_TOKEN)
+  #   "zai"          - z.ai / ZhipuAI GLM (requires: GLM_API_KEY)
+  #   "kimi-coding"  - Kimi / Moonshot AI (requires: KIMI_API_KEY)
+  #   "minimax"      - MiniMax global (requires: MINIMAX_API_KEY)
+  #   "minimax-cn"   - MiniMax China (requires: MINIMAX_CN_API_KEY)
+  #   "huggingface"  - Hugging Face Inference (requires: HF_TOKEN)
+  #   "kilocode"     - KiloCode gateway (requires: KILOCODE_API_KEY)
+  #   "ai-gateway"   - Vercel AI Gateway (requires: AI_GATEWAY_API_KEY)
+  #
+  # Local servers (LM Studio, Ollama, vLLM, llama.cpp):
+  #   "custom"       - Any OpenAI-compatible endpoint. Set base_url below.
+  #   Aliases: "lmstudio", "ollama", "vllm", "llamacpp" all map to "custom".
+  #   Example for LM Studio:
+  #     provider: "lmstudio"
+  #     base_url: "http://localhost:1234/v1"
+  #   No API key needed — local servers typically ignore auth.
+  #
   # Can also be overridden with --provider flag or HERMES_INFERENCE_PROVIDER env var.
   provider: "auto"
   
@@ -50,6 +67,20 @@ model:
 #   # Data policy: "allow" (default) or "deny" to exclude providers that may store data
 #   # data_collection: "deny"
 
+# =============================================================================
+# Smart Model Routing (optional)
+# =============================================================================
+# Use a cheaper model for short/simple turns while keeping your main model for
+# more complex requests. Disabled by default.
+#
+# smart_model_routing:
+#   enabled: true
+#   max_simple_chars: 160
+#   max_simple_words: 28
+#   cheap_model:
+#     provider: openrouter
+#     model: google/gemini-2.5-flash
+
 # =============================================================================
 # Git Worktree Isolation
 # =============================================================================
@@ -75,8 +106,9 @@ model:
 #   - Messaging (Telegram/Discord): Uses MESSAGING_CWD from .env (default: home)
 terminal:
   backend: "local"
-  cwd: "."  # For local backend: "." = current directory. Ignored for remote backends.
+  cwd: "."  # For local backend: "." = current directory. Ignored for remote backends unless a backend documents otherwise.
   timeout: 180
+  docker_mount_cwd_to_workspace: false  # SECURITY: off by default. Opt in to mount the launch cwd into Docker /workspace.
   lifetime_seconds: 300
   # sudo_password: ""  # Enable sudo commands (pipes via sudo -S) - SECURITY WARNING: plaintext!
 
@@ -106,6 +138,13 @@ terminal:
 #   timeout: 180
 #   lifetime_seconds: 300
 #   docker_image: "nikolaik/python-nodejs:python3.11-nodejs20"
+#   docker_mount_cwd_to_workspace: true   # Explicit opt-in: mount your launch cwd into /workspace
+#   # Optional: explicitly forward selected env vars into Docker.
+#   # These values come from your current shell first, then ~/.hermes/.env.
+#   # Warning: anything forwarded here is visible to commands run in the container.
+#   docker_forward_env:
+#     - "GITHUB_TOKEN"
+#     - "NPM_TOKEN"
 
 # -----------------------------------------------------------------------------
 # OPTION 4: Singularity/Apptainer container
@@ -177,6 +216,20 @@ terminal:
 # Example (add to your terminal section):
 #   sudo_password: "your-password-here"
 
+# =============================================================================
+# Security Scanning (tirith)
+# =============================================================================
+# Optional pre-exec command security scanning via tirith.
+# Detects homograph URLs, pipe-to-shell, terminal injection, env manipulation.
+# Install: brew install sheeki03/tap/tirith
+# Docs: https://github.com/sheeki03/tirith
+#
+# security:
+#   tirith_enabled: true        # Enable/disable tirith scanning
+#   tirith_path: "tirith"       # Path to tirith binary (supports ~ expansion)
+#   tirith_timeout: 5           # Scan timeout in seconds
+#   tirith_fail_open: true      # Allow commands if tirith unavailable
+
 # =============================================================================
 # Browser Tool Configuration
 # =============================================================================
@@ -195,19 +248,34 @@ browser:
 # 1. Tracks actual token usage from API responses (not estimates)
 # 2. When prompt_tokens >= threshold% of model's context_length, triggers compression
 # 3. Protects first 3 turns (system prompt, initial request, first response)
-# 4. Protects last 4 turns (recent context is most relevant)
+# 4. Protects last N turns (default 20 messages = ~10 full turns of recent context)
 # 5. Summarizes middle turns using a fast/cheap model
 # 6. Inserts summary as a user message, continues conversation seamlessly
 #
+# Post-compression tail budget is target_ratio × threshold × context_length:
+#   200K context, threshold 0.50, ratio 0.20 → 20K tokens of recent tail preserved
+#   1M   context, threshold 0.50, ratio 0.20 → 100K tokens of recent tail preserved
+#
 compression:
   # Enable automatic context compression (default: true)
   # Set to false if you prefer to manage context manually or want errors on overflow
   enabled: true
   
-  # Trigger compression at this % of model's context limit (default: 0.85 = 85%)
+  # Trigger compression at this % of model's context limit (default: 0.50 = 50%)
   # Lower values = more aggressive compression, higher values = compress later
-  threshold: 0.85
+  threshold: 0.50
   
+  # Fraction of the threshold to preserve as recent tail (default: 0.20 = 20%)
+  # e.g. 20% of 50% threshold = 10% of total context kept as recent messages.
+  # Summary output is separately capped at 12K tokens (Gemini output limit).
+  # Range: 0.10 - 0.80
+  target_ratio: 0.20
+
+  # Number of most-recent messages to always preserve (default: 20 ≈ 10 full turns)
+  # Higher values keep more recent conversation intact at the cost of more aggressive
+  # compression of older turns.
+  protect_last_n: 20
+
   # Model to use for generating summaries (fast/cheap recommended)
   # This model compresses the middle turns into a concise summary.
   # IMPORTANT: it receives the full middle section of the conversation, so it
@@ -256,6 +324,9 @@ compression:
 #   vision:
 #     provider: "auto"
 #     model: ""              # e.g. "google/gemini-2.5-flash", "openai/gpt-4o"
+#     timeout: 30            # LLM API call timeout (seconds)
+#     download_timeout: 30   # Image HTTP download timeout (seconds)
+#                            # Increase for slow connections or self-hosted image servers
 #
 #   # Web page scraping / summarization + browser page text extraction
 #   web_extract:
@@ -318,6 +389,25 @@ session_reset:
   idle_minutes: 1440   # Inactivity timeout in minutes (default: 1440 = 24 hours)
   at_hour: 4           # Daily reset hour, 0-23 local time (default: 4 AM)
 
+# When true, group/channel chats use one session per participant when the platform
+# provides a user ID. This is the secure default and prevents users in the same
+# room from sharing context, interrupts, and token costs. Set false only if you
+# explicitly want one shared "room brain" per group/channel.
+group_sessions_per_user: true
+
+# ─────────────────────────────────────────────────────────────────────────────
+# Gateway Streaming
+# ─────────────────────────────────────────────────────────────────────────────
+# Stream tokens to messaging platforms in real-time. The bot sends a message
+# on first token, then progressively edits it as more tokens arrive.
+# Disabled by default — enable to try the streaming UX on Telegram/Discord/Slack.
+streaming:
+  enabled: false
+  # transport: edit           # "edit" = progressive editMessageText
+  # edit_interval: 0.3        # seconds between message edits
+  # buffer_threshold: 40      # chars before forcing an edit flush
+  # cursor: " ▉"              # cursor shown during streaming
+
 # =============================================================================
 # Skills Configuration
 # =============================================================================
@@ -330,6 +420,15 @@ skills:
   # Set to 0 to disable.
   creation_nudge_interval: 15
 
+  # External skill directories — share skills across tools/agents without
+  # copying them into ~/.hermes/skills/.  Each path is expanded (~ and ${VAR})
+  # and resolved to an absolute path.  External dirs are read-only: skill
+  # creation always writes to ~/.hermes/skills/.  Local skills take precedence
+  # when names collide.
+  # external_dirs:
+  #   - ~/.agents/skills
+  #   - /home/shared/team-skills
+
 # =============================================================================
 # Agent Behavior
 # =============================================================================
@@ -368,7 +467,7 @@ agent:
 # Toolsets
 # =============================================================================
 # Control which tools the agent has access to.
-# Use "all" to enable everything, or specify individual toolsets.
+# Use `hermes tools` to interactively enable/disable tools per platform.
 
 # =============================================================================
 # Platform Toolsets (per-platform tool configuration)
@@ -402,11 +501,13 @@ agent:
 #     discord: [web, vision, skills, todo]
 #
 # If not set, defaults are:
-#   cli:      hermes-cli      (everything + cronjob management)
-#   telegram: hermes-telegram  (terminal, file, web, vision, image, tts, browser, skills, todo, cronjob, messaging)
-#   discord:  hermes-discord   (same as telegram)
-#   whatsapp: hermes-whatsapp  (same as telegram)
-#   slack:    hermes-slack     (same as telegram)
+#   cli:           hermes-cli            (everything + cronjob management)
+#   telegram:      hermes-telegram       (terminal, file, web, vision, image, tts, browser, skills, todo, cronjob, messaging)
+#   discord:       hermes-discord        (same as telegram)
+#   whatsapp:      hermes-whatsapp       (same as telegram)
+#   slack:         hermes-slack          (same as telegram)
+#   signal:        hermes-signal         (same as telegram)
+#   homeassistant: hermes-homeassistant  (same as telegram)
 #
 platform_toolsets:
   cli: [hermes-cli]
@@ -414,6 +515,8 @@ platform_toolsets:
   discord: [hermes-discord]
   whatsapp: [hermes-whatsapp]
   slack: [hermes-slack]
+  signal: [hermes-signal]
+  homeassistant: [hermes-homeassistant]
 
 # ─────────────────────────────────────────────────────────────────────────────
 # Available toolsets (use these names in platform_toolsets or the toolsets list)
@@ -437,7 +540,7 @@ platform_toolsets:
 #   moa          - mixture_of_agents  (requires OPENROUTER_API_KEY)
 #   todo         - todo (in-memory task planning, no deps)
 #   tts          - text_to_speech  (Edge TTS free, or ELEVENLABS/OPENAI key)
-#   cronjob      - schedule_cronjob, list_cronjobs, remove_cronjob
+#   cronjob      - cronjob (create/list/update/pause/resume/run/remove scheduled tasks)
 #   rl           - rl_list_environments, rl_start_training, etc. (requires TINKER_API_KEY)
 #
 # PRESETS (curated bundles):
@@ -473,53 +576,11 @@ platform_toolsets:
 #   debugging    - terminal + web + file (for troubleshooting)
 #   safe         - web + vision + moa (no terminal access)
 
-# -----------------------------------------------------------------------------
-# OPTION 1: Enable all tools (default)
-# -----------------------------------------------------------------------------
-toolsets:
-  - all
-
-# -----------------------------------------------------------------------------
-# OPTION 2: Minimal - just web search and terminal
-# Great for: Simple coding tasks, quick lookups
-# -----------------------------------------------------------------------------
-# toolsets:
-#   - web
-#   - terminal
-
-# -----------------------------------------------------------------------------
-# OPTION 3: Research mode - no execution capabilities
-# Great for: Safe information gathering, research tasks
-# -----------------------------------------------------------------------------
-# toolsets:
-#   - web
-#   - vision
-#   - skills
-
-# -----------------------------------------------------------------------------
-# OPTION 4: Full automation - browser + terminal
-# Great for: Web scraping, automation tasks, testing
-# -----------------------------------------------------------------------------
-# toolsets:
-#   - terminal
-#   - browser
-#   - web
-
-# -----------------------------------------------------------------------------
-# OPTION 5: Creative mode - vision + image generation
-# Great for: Design work, image analysis, creative tasks
-# -----------------------------------------------------------------------------
-# toolsets:
-#   - vision
-#   - image_gen
-#   - web
-
-# -----------------------------------------------------------------------------
-# OPTION 6: Safe mode - no terminal or browser
-# Great for: Restricted environments, untrusted queries
-# -----------------------------------------------------------------------------
-# toolsets:
-#   - safe
+# NOTE: The top-level "toolsets" key is deprecated and ignored.
+# Tool configuration is managed per-platform via platform_toolsets above.
+# Use `hermes tools` to configure interactively, or edit platform_toolsets directly.
+#
+# CLI override: hermes chat --toolsets terminal,web,file
 
 # =============================================================================
 # MCP (Model Context Protocol) Servers
@@ -621,6 +682,10 @@ code_execution:
 delegation:
   max_iterations: 50                          # Max tool-calling turns per child (default: 50)
   default_toolsets: ["terminal", "file", "web"]  # Default toolsets for subagents
+  # model: "google/gemini-3-flash-preview"    # Override model for subagents (empty = inherit parent)
+  # provider: "openrouter"                    # Override provider for subagents (empty = inherit parent)
+  #                                           # Resolves full credentials (base_url, api_key) automatically.
+  #                                           # Supported: openrouter, nous, zai, kimi-coding, minimax
 
 # =============================================================================
 # Honcho Integration (Cross-Session User Modeling)
@@ -651,7 +716,86 @@ display:
   # Toggle at runtime with /verbose in the CLI
   tool_progress: all
 
+  # What Enter does when Hermes is already busy in the CLI.
+  #   interrupt: Interrupt the current run and redirect Hermes (default)
+  #   queue:     Queue your message for the next turn
+  # Ctrl+C always interrupts regardless of this setting.
+  busy_input_mode: interrupt
+
+  # Background process notifications (gateway/messaging only).
+  # Controls how chatty the process watcher is when you use
+  # terminal(background=true, check_interval=...) from Telegram/Discord/etc.
+  #   off:     No watcher messages at all
+  #   result:  Only the final completion message
+  #   error:   Only the final message when exit code != 0
+  #   all:     Running output updates + final message (default)
+  background_process_notifications: all
+
+
   # Play terminal bell when agent finishes a response.
   # Useful for long-running tasks — your terminal will ding when the agent is done.
   # Works over SSH. Most terminals can be configured to flash the taskbar or play a sound.
   bell_on_complete: false
+
+  # Show model reasoning/thinking before each response.
+  # When enabled, a dim box shows the model's thought process above the response.
+  # Toggle at runtime with /reasoning show or /reasoning hide.
+  show_reasoning: false
+
+  # Stream tokens to the terminal as they arrive instead of waiting for the
+  # full response. The response box opens on first token and text appears
+  # line-by-line. Tool calls are still captured silently.
+  # Stream tokens to the terminal in real-time. Disable to wait for full responses.
+  streaming: true
+
+  # ───────────────────────────────────────────────────────────────────────────
+  # Skin / Theme
+  # ───────────────────────────────────────────────────────────────────────────
+  # Customize CLI visual appearance — banner colors, spinner faces, tool prefix,
+  # response box label, and branding text. Change at runtime with /skin <name>.
+  #
+  # Built-in skins:
+  #   default  — Classic Hermes gold/kawaii
+  #   ares     — Crimson/bronze war-god theme with spinner wings
+  #   mono     — Clean grayscale monochrome
+  #   slate    — Cool blue developer-focused
+  #
+  # Custom skins: drop a YAML file in ~/.hermes/skins/<name>.yaml
+  # Schema (all fields optional, missing values inherit from default):
+  #
+  #   name: my-theme
+  #   description: Short description
+  #   colors:
+  #     banner_border: "#HEX"    # Panel border
+  #     banner_title: "#HEX"     # Panel title
+  #     banner_accent: "#HEX"    # Section headers (Available Tools, etc.)
+  #     banner_dim: "#HEX"       # Dim/muted text
+  #     banner_text: "#HEX"      # Body text (tool names, skill names)
+  #     ui_accent: "#HEX"        # UI accent color
+  #     response_border: "#HEX"  # Response box border color
+  #   spinner:
+  #     waiting_faces: ["(⚔)", "(⛨)"]       # Faces shown while waiting
+  #     thinking_faces: ["(⚔)", "(⌁)"]      # Faces shown while thinking
+  #     thinking_verbs: ["forging", "plotting"]  # Verbs for spinner messages
+  #     wings:                                # Optional left/right spinner decorations
+  #       - ["⟪⚔", "⚔⟫"]
+  #       - ["⟪▲", "▲⟫"]
+  #   branding:
+  #     agent_name: "My Agent"               # Banner title and branding
+  #     welcome: "Welcome message"           # Shown at CLI startup
+  #     response_label: " ⚔ Agent "         # Response box header label
+  #     prompt_symbol: "⚔ ❯ "              # Prompt symbol
+  #   tool_prefix: "╎"                       # Tool output line prefix (default: ┊)
+  #
+  skin: default
+
+# =============================================================================
+# Privacy
+# =============================================================================
+# privacy:
+#   # Redact PII from the LLM context prompt.
+#   # When true, phone numbers are stripped and user/chat IDs are replaced
+#   # with deterministic hashes before being sent to the model.
+#   # Names and usernames are NOT affected (user-chosen, publicly visible).
+#   # Routing/delivery still uses the original values internally.
+#   redact_pii: false

cron/__init__.py

@@ -7,7 +7,8 @@ This module provides scheduled task execution, allowing the agent to:
 - Execute tasks in isolated sessions (no prior context)
 
 Cron jobs are executed automatically by the gateway daemon:
-    hermes gateway install    # Install as system service (recommended)
+    hermes gateway install    # Install as a user service
+    sudo hermes gateway install --system  # Linux servers: boot-time system service
     hermes gateway            # Or run in foreground
 
 The gateway ticks the scheduler every 60 seconds. A file lock prevents
@@ -20,6 +21,9 @@ from cron.jobs import (
     list_jobs,
     remove_job,
     update_job,
+    pause_job,
+    resume_job,
+    trigger_job,
     JOBS_FILE,
 )
 from cron.scheduler import tick
@@ -30,6 +34,9 @@ __all__ = [
     "list_jobs",
     "remove_job",
     "update_job",
+    "pause_job",
+    "resume_job",
+    "trigger_job",
     "tick",
     "JOBS_FILE",
 ]

cron/jobs.py

@@ -5,15 +5,20 @@ Jobs are stored in ~/.hermes/cron/jobs.json
 Output is saved to ~/.hermes/cron/output/{job_id}/{timestamp}.md
 """
 
+import copy
 import json
+import logging
 import tempfile
 import os
 import re
 import uuid
 from datetime import datetime, timedelta
 from pathlib import Path
+from hermes_constants import get_hermes_home
 from typing import Optional, Dict, List, Any
 
+logger = logging.getLogger(__name__)
+
 from hermes_time import now as _hermes_now
 
 try:
@@ -26,16 +31,62 @@ except ImportError:
 # Configuration
 # =============================================================================
 
-HERMES_DIR = Path.home() / ".hermes"
+HERMES_DIR = get_hermes_home()
 CRON_DIR = HERMES_DIR / "cron"
 JOBS_FILE = CRON_DIR / "jobs.json"
 OUTPUT_DIR = CRON_DIR / "output"
+ONESHOT_GRACE_SECONDS = 120
+
+
+def _normalize_skill_list(skill: Optional[str] = None, skills: Optional[Any] = None) -> List[str]:
+    """Normalize legacy/single-skill and multi-skill inputs into a unique ordered list."""
+    if skills is None:
+        raw_items = [skill] if skill else []
+    elif isinstance(skills, str):
+        raw_items = [skills]
+    else:
+        raw_items = list(skills)
+
+    normalized: List[str] = []
+    for item in raw_items:
+        text = str(item or "").strip()
+        if text and text not in normalized:
+            normalized.append(text)
+    return normalized
+
+
+def _apply_skill_fields(job: Dict[str, Any]) -> Dict[str, Any]:
+    """Return a job dict with canonical `skills` and legacy `skill` fields aligned."""
+    normalized = dict(job)
+    skills = _normalize_skill_list(normalized.get("skill"), normalized.get("skills"))
+    normalized["skills"] = skills
+    normalized["skill"] = skills[0] if skills else None
+    return normalized
+
+
+def _secure_dir(path: Path):
+    """Set directory to owner-only access (0700). No-op on Windows."""
+    try:
+        os.chmod(path, 0o700)
+    except (OSError, NotImplementedError):
+        pass  # Windows or other platforms where chmod is not supported
+
+
+def _secure_file(path: Path):
+    """Set file to owner-only read/write (0600). No-op on Windows."""
+    try:
+        if path.exists():
+            os.chmod(path, 0o600)
+    except (OSError, NotImplementedError):
+        pass
 
 
 def ensure_dirs():
-    """Ensure cron directories exist."""
+    """Ensure cron directories exist with secure permissions."""
     CRON_DIR.mkdir(parents=True, exist_ok=True)
     OUTPUT_DIR.mkdir(parents=True, exist_ok=True)
+    _secure_dir(CRON_DIR)
+    _secure_dir(OUTPUT_DIR)
 
 
 # =============================================================================
@@ -119,6 +170,10 @@ def parse_schedule(schedule: str) -> Dict[str, Any]:
         try:
             # Parse and validate
             dt = datetime.fromisoformat(schedule.replace('Z', '+00:00'))
+            # Make naive timestamps timezone-aware at parse time so the stored
+            # value doesn't depend on the system timezone matching at check time.
+            if dt.tzinfo is None:
+                dt = dt.astimezone()  # Interpret as local timezone
             return {
                 "kind": "once",
                 "run_at": dt.isoformat(),
@@ -149,16 +204,81 @@ def parse_schedule(schedule: str) -> Dict[str, Any]:
 
 
 def _ensure_aware(dt: datetime) -> datetime:
-    """Make a naive datetime tz-aware using the configured timezone.
+    """Return a timezone-aware datetime in Hermes configured timezone.
 
-    Handles backward compatibility: timestamps stored before timezone support
-    are naive (server-local).  We assume they were in the same timezone as
-    the current configuration so comparisons work without crashing.
+    Backward compatibility:
+    - Older stored timestamps may be naive.
+    - Naive values are interpreted as *system-local wall time* (the timezone
+      `datetime.now()` used when they were created), then converted to the
+      configured Hermes timezone.
+
+    This preserves relative ordering for legacy naive timestamps across
+    timezone changes and avoids false not-due results.
     """
+    target_tz = _hermes_now().tzinfo
     if dt.tzinfo is None:
-        tz = _hermes_now().tzinfo
-        return dt.replace(tzinfo=tz)
-    return dt
+        local_tz = datetime.now().astimezone().tzinfo
+        return dt.replace(tzinfo=local_tz).astimezone(target_tz)
+    return dt.astimezone(target_tz)
+
+
+def _recoverable_oneshot_run_at(
+    schedule: Dict[str, Any],
+    now: datetime,
+    *,
+    last_run_at: Optional[str] = None,
+) -> Optional[str]:
+    """Return a one-shot run time if it is still eligible to fire.
+
+    One-shot jobs get a small grace window so jobs created a few seconds after
+    their requested minute still run on the next tick. Once a one-shot has
+    already run, it is never eligible again.
+    """
+    if schedule.get("kind") != "once":
+        return None
+    if last_run_at:
+        return None
+
+    run_at = schedule.get("run_at")
+    if not run_at:
+        return None
+
+    run_at_dt = _ensure_aware(datetime.fromisoformat(run_at))
+    if run_at_dt >= now - timedelta(seconds=ONESHOT_GRACE_SECONDS):
+        return run_at
+    return None
+
+
+def _compute_grace_seconds(schedule: dict) -> int:
+    """Compute how late a job can be and still catch up instead of fast-forwarding.
+
+    Uses half the schedule period, clamped between 120 seconds and 2 hours.
+    This ensures daily jobs can catch up if missed by up to 2 hours,
+    while frequent jobs (every 5-10 min) still fast-forward quickly.
+    """
+    MIN_GRACE = 120
+    MAX_GRACE = 7200  # 2 hours
+
+    kind = schedule.get("kind")
+
+    if kind == "interval":
+        period_seconds = schedule.get("minutes", 1) * 60
+        grace = period_seconds // 2
+        return max(MIN_GRACE, min(grace, MAX_GRACE))
+
+    if kind == "cron" and HAS_CRONITER:
+        try:
+            now = _hermes_now()
+            cron = croniter(schedule["expr"], now)
+            first = cron.get_next(datetime)
+            second = cron.get_next(datetime)
+            period_seconds = int((second - first).total_seconds())
+            grace = period_seconds // 2
+            return max(MIN_GRACE, min(grace, MAX_GRACE))
+        except Exception:
+            pass
+
+    return MIN_GRACE
 
 
 def compute_next_run(schedule: Dict[str, Any], last_run_at: Optional[str] = None) -> Optional[str]:
@@ -170,9 +290,7 @@ def compute_next_run(schedule: Dict[str, Any], last_run_at: Optional[str] = None
     now = _hermes_now()
 
     if schedule["kind"] == "once":
-        run_at = _ensure_aware(datetime.fromisoformat(schedule["run_at"]))
-        # If in the future, return it; if in the past, no more runs
-        return schedule["run_at"] if run_at > now else None
+        return _recoverable_oneshot_run_at(schedule, now, last_run_at=last_run_at)
 
     elif schedule["kind"] == "interval":
         minutes = schedule["minutes"]
@@ -209,7 +327,20 @@ def load_jobs() -> List[Dict[str, Any]]:
         with open(JOBS_FILE, 'r', encoding='utf-8') as f:
             data = json.load(f)
             return data.get("jobs", [])
-    except (json.JSONDecodeError, IOError):
+    except json.JSONDecodeError:
+        # Retry with strict=False to handle bare control chars in string values
+        try:
+            with open(JOBS_FILE, 'r', encoding='utf-8') as f:
+                data = json.loads(f.read(), strict=False)
+                jobs = data.get("jobs", [])
+                if jobs:
+                    # Auto-repair: rewrite with proper escaping
+                    save_jobs(jobs)
+                    logger.warning("Auto-repaired jobs.json (had invalid control characters)")
+                return jobs
+        except Exception:
+            return []
+    except IOError:
         return []
 
 
@@ -223,6 +354,7 @@ def save_jobs(jobs: List[Dict[str, Any]]):
             f.flush()
             os.fsync(f.fileno())
         os.replace(tmp_path, JOBS_FILE)
+        _secure_file(JOBS_FILE)
     except BaseException:
         try:
             os.unlink(tmp_path)
@@ -237,39 +369,67 @@ def create_job(
     name: Optional[str] = None,
     repeat: Optional[int] = None,
     deliver: Optional[str] = None,
-    origin: Optional[Dict[str, Any]] = None
+    origin: Optional[Dict[str, Any]] = None,
+    skill: Optional[str] = None,
+    skills: Optional[List[str]] = None,
+    model: Optional[str] = None,
+    provider: Optional[str] = None,
+    base_url: Optional[str] = None,
 ) -> Dict[str, Any]:
     """
     Create a new cron job.
-    
+
     Args:
-        prompt: The prompt to run (must be self-contained)
+        prompt: The prompt to run (must be self-contained, or a task instruction when skill is set)
         schedule: Schedule string (see parse_schedule)
         name: Optional friendly name
         repeat: How many times to run (None = forever, 1 = once)
         deliver: Where to deliver output ("origin", "local", "telegram", etc.)
         origin: Source info where job was created (for "origin" delivery)
-    
+        skill: Optional legacy single skill name to load before running the prompt
+        skills: Optional ordered list of skills to load before running the prompt
+        model: Optional per-job model override
+        provider: Optional per-job provider override
+        base_url: Optional per-job base URL override
+
     Returns:
         The created job dict
     """
     parsed_schedule = parse_schedule(schedule)
-    
+
+    # Normalize repeat: treat 0 or negative values as None (infinite)
+    if repeat is not None and repeat <= 0:
+        repeat = None
+
     # Auto-set repeat=1 for one-shot schedules if not specified
     if parsed_schedule["kind"] == "once" and repeat is None:
         repeat = 1
-    
+
     # Default delivery to origin if available, otherwise local
     if deliver is None:
         deliver = "origin" if origin else "local"
-    
+
     job_id = uuid.uuid4().hex[:12]
     now = _hermes_now().isoformat()
-    
+
+    normalized_skills = _normalize_skill_list(skill, skills)
+    normalized_model = str(model).strip() if isinstance(model, str) else None
+    normalized_provider = str(provider).strip() if isinstance(provider, str) else None
+    normalized_base_url = str(base_url).strip().rstrip("/") if isinstance(base_url, str) else None
+    normalized_model = normalized_model or None
+    normalized_provider = normalized_provider or None
+    normalized_base_url = normalized_base_url or None
+
+    label_source = (prompt or (normalized_skills[0] if normalized_skills else None)) or "cron job"
     job = {
         "id": job_id,
-        "name": name or prompt[:50].strip(),
+        "name": name or label_source[:50].strip(),
         "prompt": prompt,
+        "skills": normalized_skills,
+        "skill": normalized_skills[0] if normalized_skills else None,
+        "model": normalized_model,
+        "provider": normalized_provider,
+        "base_url": normalized_base_url,
         "schedule": parsed_schedule,
         "schedule_display": parsed_schedule.get("display", schedule),
         "repeat": {
@@ -277,6 +437,9 @@ def create_job(
             "completed": 0
         },
         "enabled": True,
+        "state": "scheduled",
+        "paused_at": None,
+        "paused_reason": None,
         "created_at": now,
         "next_run_at": compute_next_run(parsed_schedule),
         "last_run_at": None,
@@ -286,11 +449,11 @@ def create_job(
         "deliver": deliver,
         "origin": origin,  # Tracks where job was created for "origin" delivery
     }
-    
+
     jobs = load_jobs()
     jobs.append(job)
     save_jobs(jobs)
-    
+
     return job
 
 
@@ -299,29 +462,100 @@ def get_job(job_id: str) -> Optional[Dict[str, Any]]:
     jobs = load_jobs()
     for job in jobs:
         if job["id"] == job_id:
-            return job
+            return _apply_skill_fields(job)
     return None
 
 
 def list_jobs(include_disabled: bool = False) -> List[Dict[str, Any]]:
     """List all jobs, optionally including disabled ones."""
-    jobs = load_jobs()
+    jobs = [_apply_skill_fields(j) for j in load_jobs()]
     if not include_disabled:
         jobs = [j for j in jobs if j.get("enabled", True)]
     return jobs
 
 
 def update_job(job_id: str, updates: Dict[str, Any]) -> Optional[Dict[str, Any]]:
-    """Update a job by ID."""
+    """Update a job by ID, refreshing derived schedule fields when needed."""
     jobs = load_jobs()
     for i, job in enumerate(jobs):
-        if job["id"] == job_id:
-            jobs[i] = {**job, **updates}
-            save_jobs(jobs)
-            return jobs[i]
+        if job["id"] != job_id:
+            continue
+
+        updated = _apply_skill_fields({**job, **updates})
+        schedule_changed = "schedule" in updates
+
+        if "skills" in updates or "skill" in updates:
+            normalized_skills = _normalize_skill_list(updated.get("skill"), updated.get("skills"))
+            updated["skills"] = normalized_skills
+            updated["skill"] = normalized_skills[0] if normalized_skills else None
+
+        if schedule_changed:
+            updated_schedule = updated["schedule"]
+            updated["schedule_display"] = updates.get(
+                "schedule_display",
+                updated_schedule.get("display", updated.get("schedule_display")),
+            )
+            if updated.get("state") != "paused":
+                updated["next_run_at"] = compute_next_run(updated_schedule)
+
+        if updated.get("enabled", True) and updated.get("state") != "paused" and not updated.get("next_run_at"):
+            updated["next_run_at"] = compute_next_run(updated["schedule"])
+
+        jobs[i] = updated
+        save_jobs(jobs)
+        return _apply_skill_fields(jobs[i])
     return None
 
 
+def pause_job(job_id: str, reason: Optional[str] = None) -> Optional[Dict[str, Any]]:
+    """Pause a job without deleting it."""
+    return update_job(
+        job_id,
+        {
+            "enabled": False,
+            "state": "paused",
+            "paused_at": _hermes_now().isoformat(),
+            "paused_reason": reason,
+        },
+    )
+
+
+def resume_job(job_id: str) -> Optional[Dict[str, Any]]:
+    """Resume a paused job and compute the next future run from now."""
+    job = get_job(job_id)
+    if not job:
+        return None
+
+    next_run_at = compute_next_run(job["schedule"])
+    return update_job(
+        job_id,
+        {
+            "enabled": True,
+            "state": "scheduled",
+            "paused_at": None,
+            "paused_reason": None,
+            "next_run_at": next_run_at,
+        },
+    )
+
+
+def trigger_job(job_id: str) -> Optional[Dict[str, Any]]:
+    """Schedule a job to run on the next scheduler tick."""
+    job = get_job(job_id)
+    if not job:
+        return None
+    return update_job(
+        job_id,
+        {
+            "enabled": True,
+            "state": "scheduled",
+            "paused_at": None,
+            "paused_reason": None,
+            "next_run_at": _hermes_now().isoformat(),
+        },
+    )
+
+
 def remove_job(job_id: str) -> bool:
     """Remove a job by ID."""
     jobs = load_jobs()
@@ -355,7 +589,7 @@ def mark_job_run(job_id: str, success: bool, error: Optional[str] = None):
                 # Check if we've hit the repeat limit
                 times = job["repeat"].get("times")
                 completed = job["repeat"]["completed"]
-                if times is not None and completed >= times:
+                if times is not None and times > 0 and completed >= times:
                     # Remove the job (limit reached)
                     jobs.pop(i)
                     save_jobs(jobs)
@@ -363,35 +597,124 @@ def mark_job_run(job_id: str, success: bool, error: Optional[str] = None):
             
             # Compute next run
             job["next_run_at"] = compute_next_run(job["schedule"], now)
-            
+
             # If no next run (one-shot completed), disable
             if job["next_run_at"] is None:
                 job["enabled"] = False
-            
+                job["state"] = "completed"
+            elif job.get("state") != "paused":
+                job["state"] = "scheduled"
+
             save_jobs(jobs)
             return
     
     save_jobs(jobs)
 
 
-def get_due_jobs() -> List[Dict[str, Any]]:
-    """Get all jobs that are due to run now."""
-    now = _hermes_now()
+def advance_next_run(job_id: str) -> bool:
+    """Preemptively advance next_run_at for a recurring job before execution.
+
+    Call this BEFORE run_job() so that if the process crashes mid-execution,
+    the job won't re-fire on the next gateway restart.  This converts the
+    scheduler from at-least-once to at-most-once for recurring jobs — missing
+    one run is far better than firing dozens of times in a crash loop.
+
+    One-shot jobs are left unchanged so they can still retry on restart.
+
+    Returns True if next_run_at was advanced, False otherwise.
+    """
     jobs = load_jobs()
+    for job in jobs:
+        if job["id"] == job_id:
+            kind = job.get("schedule", {}).get("kind")
+            if kind not in ("cron", "interval"):
+                return False
+            now = _hermes_now().isoformat()
+            new_next = compute_next_run(job["schedule"], now)
+            if new_next and new_next != job.get("next_run_at"):
+                job["next_run_at"] = new_next
+                save_jobs(jobs)
+                return True
+            return False
+    return False
+
+
+def get_due_jobs() -> List[Dict[str, Any]]:
+    """Get all jobs that are due to run now.
+
+    For recurring jobs (cron/interval), if the scheduled time is stale
+    (more than one period in the past, e.g. because the gateway was down),
+    the job is fast-forwarded to the next future run instead of firing
+    immediately.  This prevents a burst of missed jobs on gateway restart.
+    """
+    now = _hermes_now()
+    raw_jobs = load_jobs()
+    jobs = [_apply_skill_fields(j) for j in copy.deepcopy(raw_jobs)]
     due = []
-    
+    needs_save = False
+
     for job in jobs:
         if not job.get("enabled", True):
             continue
-        
+
         next_run = job.get("next_run_at")
         if not next_run:
-            continue
-        
+            recovered_next = _recoverable_oneshot_run_at(
+                job.get("schedule", {}),
+                now,
+                last_run_at=job.get("last_run_at"),
+            )
+            if not recovered_next:
+                continue
+
+            job["next_run_at"] = recovered_next
+            next_run = recovered_next
+            logger.info(
+                "Job '%s' had no next_run_at; recovering one-shot run at %s",
+                job.get("name", job["id"]),
+                recovered_next,
+            )
+            for rj in raw_jobs:
+                if rj["id"] == job["id"]:
+                    rj["next_run_at"] = recovered_next
+                    needs_save = True
+                    break
+
         next_run_dt = _ensure_aware(datetime.fromisoformat(next_run))
         if next_run_dt <= now:
+            schedule = job.get("schedule", {})
+            kind = schedule.get("kind")
+
+            # For recurring jobs, check if the scheduled time is stale
+            # (gateway was down and missed the window). Fast-forward to
+            # the next future occurrence instead of firing a stale run.
+            grace = _compute_grace_seconds(schedule)
+            if kind in ("cron", "interval") and (now - next_run_dt).total_seconds() > grace:
+                # Job is past its catch-up grace window — this is a stale missed run.
+                # Grace scales with schedule period: daily=2h, hourly=30m, 10min=5m.
+                new_next = compute_next_run(schedule, now.isoformat())
+                if new_next:
+                    logger.info(
+                        "Job '%s' missed its scheduled time (%s, grace=%ds). "
+                        "Fast-forwarding to next run: %s",
+                        job.get("name", job["id"]),
+                        next_run,
+                        grace,
+                        new_next,
+                    )
+                    # Update the job in storage
+                    for rj in raw_jobs:
+                        if rj["id"] == job["id"]:
+                            rj["next_run_at"] = new_next
+                            needs_save = True
+                            break
+                    continue  # Skip this run
+
             due.append(job)
-    
+
+    if needs_save:
+        save_jobs(raw_jobs)
+
     return due
 
 
@@ -400,11 +723,24 @@ def save_job_output(job_id: str, output: str):
     ensure_dirs()
     job_output_dir = OUTPUT_DIR / job_id
     job_output_dir.mkdir(parents=True, exist_ok=True)
+    _secure_dir(job_output_dir)
     
     timestamp = _hermes_now().strftime("%Y-%m-%d_%H-%M-%S")
     output_file = job_output_dir / f"{timestamp}.md"
     
-    with open(output_file, 'w', encoding='utf-8') as f:
-        f.write(output)
+    fd, tmp_path = tempfile.mkstemp(dir=str(job_output_dir), suffix='.tmp', prefix='.output_')
+    try:
+        with os.fdopen(fd, 'w', encoding='utf-8') as f:
+            f.write(output)
+            f.flush()
+            os.fsync(f.fileno())
+        os.replace(tmp_path, output_file)
+        _secure_file(output_file)
+    except BaseException:
+        try:
+            os.unlink(tmp_path)
+        except OSError:
+            pass
+        raise
     
     return output_file

cron/scheduler.py

@@ -9,6 +9,7 @@ runs at a time if multiple processes overlap.
 """
 
 import asyncio
+import json
 import logging
 import os
 import sys
@@ -23,8 +24,9 @@ except ImportError:
         import msvcrt
     except ImportError:
         msvcrt = None
-from datetime import datetime
 from pathlib import Path
+from hermes_constants import get_hermes_home
+from hermes_cli.config import load_config
 from typing import Optional
 
 from hermes_time import now as _hermes_now
@@ -34,10 +36,15 @@ logger = logging.getLogger(__name__)
 # Add parent directory to path for imports
 sys.path.insert(0, str(Path(__file__).parent.parent))
 
-from cron.jobs import get_due_jobs, mark_job_run, save_job_output
+from cron.jobs import get_due_jobs, mark_job_run, save_job_output, advance_next_run
+
+# Sentinel: when a cron agent has nothing new to report, it can start its
+# response with this marker to suppress delivery.  Output is still saved
+# locally for audit.
+SILENT_MARKER = "[SILENT]"
 
 # Resolve Hermes home directory (respects HERMES_HOME override)
-_hermes_home = Path(os.getenv("HERMES_HOME", Path.home() / ".hermes"))
+_hermes_home = get_hermes_home()
 
 # File-based lock prevents concurrent ticks from gateway + daemon + systemd timer
 _LOCK_DIR = _hermes_home / "cron"
@@ -45,7 +52,7 @@ _LOCK_FILE = _LOCK_DIR / ".tick.lock"
 
 
 def _resolve_origin(job: dict) -> Optional[dict]:
-    """Extract origin info from a job, returning {platform, chat_id, chat_name} or None."""
+    """Extract origin info from a job, preserving any extra routing metadata."""
     origin = job.get("origin")
     if not origin:
         return None
@@ -56,6 +63,71 @@ def _resolve_origin(job: dict) -> Optional[dict]:
     return None
 
 
+def _resolve_delivery_target(job: dict) -> Optional[dict]:
+    """Resolve the concrete auto-delivery target for a cron job, if any."""
+    deliver = job.get("deliver", "local")
+    origin = _resolve_origin(job)
+
+    if deliver == "local":
+        return None
+
+    if deliver == "origin":
+        if not origin:
+            return None
+        return {
+            "platform": origin["platform"],
+            "chat_id": str(origin["chat_id"]),
+            "thread_id": origin.get("thread_id"),
+        }
+
+    if ":" in deliver:
+        platform_name, rest = deliver.split(":", 1)
+        # Check for thread_id suffix (e.g. "telegram:-1003724596514:17")
+        if ":" in rest:
+            chat_id, thread_id = rest.split(":", 1)
+        else:
+            chat_id, thread_id = rest, None
+
+        # Resolve human-friendly labels like "Alice (dm)" to real IDs.
+        # send_message(action="list") shows labels with display suffixes
+        # that aren't valid platform IDs (e.g. WhatsApp JIDs).
+        try:
+            from gateway.channel_directory import resolve_channel_name
+            target = chat_id
+            # Strip display suffix like " (dm)" or " (group)"
+            if target.endswith(")") and " (" in target:
+                target = target.rsplit(" (", 1)[0].strip()
+            resolved = resolve_channel_name(platform_name.lower(), target)
+            if resolved:
+                chat_id = resolved
+        except Exception:
+            pass
+
+        return {
+            "platform": platform_name,
+            "chat_id": chat_id,
+            "thread_id": thread_id,
+        }
+
+    platform_name = deliver
+    if origin and origin.get("platform") == platform_name:
+        return {
+            "platform": platform_name,
+            "chat_id": str(origin["chat_id"]),
+            "thread_id": origin.get("thread_id"),
+        }
+
+    chat_id = os.getenv(f"{platform_name.upper()}_HOME_CHANNEL", "")
+    if not chat_id:
+        return None
+
+    return {
+        "platform": platform_name,
+        "chat_id": chat_id,
+        "thread_id": None,
+    }
+
+
 def _deliver_result(job: dict, content: str) -> None:
     """
     Deliver job output to the configured target (origin chat, specific platform, etc.).
@@ -63,32 +135,19 @@ def _deliver_result(job: dict, content: str) -> None:
     Uses the standalone platform send functions from send_message_tool so delivery
     works whether or not the gateway is running.
     """
-    deliver = job.get("deliver", "local")
-    origin = _resolve_origin(job)
-
-    if deliver == "local":
+    target = _resolve_delivery_target(job)
+    if not target:
+        if job.get("deliver", "local") != "local":
+            logger.warning(
+                "Job '%s' deliver=%s but no concrete delivery target could be resolved",
+                job["id"],
+                job.get("deliver", "local"),
+            )
         return
 
-    # Resolve target platform + chat_id
-    if deliver == "origin":
-        if not origin:
-            logger.warning("Job '%s' deliver=origin but no origin stored, skipping delivery", job["id"])
-            return
-        platform_name = origin["platform"]
-        chat_id = origin["chat_id"]
-    elif ":" in deliver:
-        platform_name, chat_id = deliver.split(":", 1)
-    else:
-        # Bare platform name like "telegram" — need to resolve to origin or home channel
-        platform_name = deliver
-        if origin and origin.get("platform") == platform_name:
-            chat_id = origin["chat_id"]
-        else:
-            # Fall back to home channel
-            chat_id = os.getenv(f"{platform_name.upper()}_HOME_CHANNEL", "")
-            if not chat_id:
-                logger.warning("Job '%s' deliver=%s but no chat_id or home channel. Set via: hermes config set %s_HOME_CHANNEL <channel_id>", job["id"], deliver, platform_name.upper())
-                return
+    platform_name = target["platform"]
+    chat_id = target["chat_id"]
+    thread_id = target.get("thread_id")
 
     from tools.send_message_tool import _send_to_platform
     from gateway.config import load_gateway_config, Platform
@@ -99,6 +158,14 @@ def _deliver_result(job: dict, content: str) -> None:
         "slack": Platform.SLACK,
         "whatsapp": Platform.WHATSAPP,
         "signal": Platform.SIGNAL,
+        "matrix": Platform.MATRIX,
+        "mattermost": Platform.MATTERMOST,
+        "homeassistant": Platform.HOMEASSISTANT,
+        "dingtalk": Platform.DINGTALK,
+        "feishu": Platform.FEISHU,
+        "wecom": Platform.WECOM,
+        "email": Platform.EMAIL,
+        "sms": Platform.SMS,
     }
     platform = platform_map.get(platform_name.lower())
     if not platform:
@@ -116,15 +183,40 @@ def _deliver_result(job: dict, content: str) -> None:
         logger.warning("Job '%s': platform '%s' not configured/enabled", job["id"], platform_name)
         return
 
-    # Run the async send in a fresh event loop (safe from any thread)
+    # Optionally wrap the content with a header/footer so the user knows this
+    # is a cron delivery.  Wrapping is on by default; set cron.wrap_response: false
+    # in config.yaml for clean output.
+    wrap_response = True
     try:
-        result = asyncio.run(_send_to_platform(platform, pconfig, chat_id, content))
+        user_cfg = load_config()
+        wrap_response = user_cfg.get("cron", {}).get("wrap_response", True)
+    except Exception:
+        pass
+
+    if wrap_response:
+        task_name = job.get("name", job["id"])
+        delivery_content = (
+            f"Cronjob Response: {task_name}\n"
+            f"-------------\n\n"
+            f"{content}\n\n"
+            f"Note: The agent cannot see this message, and therefore cannot respond to it."
+        )
+    else:
+        delivery_content = content
+
+    # Run the async send in a fresh event loop (safe from any thread)
+    coro = _send_to_platform(platform, pconfig, chat_id, delivery_content, thread_id=thread_id)
+    try:
+        result = asyncio.run(coro)
     except RuntimeError:
-        # asyncio.run() fails if there's already a running loop in this thread;
-        # spin up a new thread to avoid that.
+        # asyncio.run() checks for a running loop before awaiting the coroutine;
+        # when it raises, the original coro was never started — close it to
+        # prevent "coroutine was never awaited" RuntimeWarning, then retry in a
+        # fresh thread that has no running loop.
+        coro.close()
         import concurrent.futures
         with concurrent.futures.ThreadPoolExecutor(max_workers=1) as pool:
-            future = pool.submit(asyncio.run, _send_to_platform(platform, pconfig, chat_id, content))
+            future = pool.submit(asyncio.run, _send_to_platform(platform, pconfig, chat_id, delivery_content, thread_id=thread_id))
             result = future.result(timeout=30)
     except Exception as e:
         logger.error("Job '%s': delivery to %s:%s failed: %s", job["id"], platform_name, chat_id, e)
@@ -134,12 +226,67 @@ def _deliver_result(job: dict, content: str) -> None:
         logger.error("Job '%s': delivery error: %s", job["id"], result["error"])
     else:
         logger.info("Job '%s': delivered to %s:%s", job["id"], platform_name, chat_id)
-        # Mirror the delivered content into the target's gateway session
-        try:
-            from gateway.mirror import mirror_to_session
-            mirror_to_session(platform_name, chat_id, content, source_label="cron")
-        except Exception:
-            pass
+
+
+def _build_job_prompt(job: dict) -> str:
+    """Build the effective prompt for a cron job, optionally loading one or more skills first."""
+    prompt = job.get("prompt", "")
+    skills = job.get("skills")
+
+    # Always prepend [SILENT] guidance so the cron agent can suppress
+    # delivery when it has nothing new or noteworthy to report.
+    silent_hint = (
+        "[SYSTEM: If you have a meaningful status report or findings, "
+        "send them — that is the whole point of this job. Only respond "
+        "with exactly \"[SILENT]\" (nothing else) when there is genuinely "
+        "nothing new to report. [SILENT] suppresses delivery to the user. "
+        "Never combine [SILENT] with content — either report your "
+        "findings normally, or say [SILENT] and nothing more.]\n\n"
+    )
+    prompt = silent_hint + prompt
+    if skills is None:
+        legacy = job.get("skill")
+        skills = [legacy] if legacy else []
+
+    skill_names = [str(name).strip() for name in skills if str(name).strip()]
+    if not skill_names:
+        return prompt
+
+    from tools.skills_tool import skill_view
+
+    parts = []
+    skipped: list[str] = []
+    for skill_name in skill_names:
+        loaded = json.loads(skill_view(skill_name))
+        if not loaded.get("success"):
+            error = loaded.get("error") or f"Failed to load skill '{skill_name}'"
+            logger.warning("Cron job '%s': skill not found, skipping — %s", job.get("name", job.get("id")), error)
+            skipped.append(skill_name)
+            continue
+
+        content = str(loaded.get("content") or "").strip()
+        if parts:
+            parts.append("")
+        parts.extend(
+            [
+                f'[SYSTEM: The user has invoked the "{skill_name}" skill, indicating they want you to follow its instructions. The full skill content is loaded below.]',
+                "",
+                content,
+            ]
+        )
+
+    if skipped:
+        notice = (
+            f"[SYSTEM: The following skill(s) were listed for this job but could not be found "
+            f"and were skipped: {', '.join(skipped)}. "
+            f"Start your response with a brief notice so the user is aware, e.g.: "
+            f"'⚠️ Skill(s) not found and skipped: {', '.join(skipped)}']"
+        )
+        parts.insert(0, notice)
+
+    if prompt:
+        parts.extend(["", f"The user has provided the following instruction alongside the skill invocation: {prompt}"])
+    return "\n".join(parts)
 
 
 def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:
@@ -151,11 +298,21 @@ def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:
     """
     from run_agent import AIAgent
     
+    # Initialize SQLite session store so cron job messages are persisted
+    # and discoverable via session_search (same pattern as gateway/run.py).
+    _session_db = None
+    try:
+        from hermes_state import SessionDB
+        _session_db = SessionDB()
+    except Exception as e:
+        logger.debug("Job '%s': SQLite session store not available: %s", job.get("id", "?"), e)
+    
     job_id = job["id"]
     job_name = job["name"]
-    prompt = job["prompt"]
+    prompt = _build_job_prompt(job)
     origin = _resolve_origin(job)
-    
+    _cron_session_id = f"cron_{job_id}_{_hermes_now().strftime('%Y%m%d_%H%M%S')}"
+
     logger.info("Running job '%s' (ID: %s)", job_name, job_id)
     logger.info("Prompt: %s", prompt[:100])
 
@@ -175,7 +332,14 @@ def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:
         except UnicodeDecodeError:
             load_dotenv(str(_hermes_home / ".env"), override=True, encoding="latin-1")
 
-        model = os.getenv("HERMES_MODEL") or os.getenv("LLM_MODEL") or "anthropic/claude-opus-4.6"
+        delivery_target = _resolve_delivery_target(job)
+        if delivery_target:
+            os.environ["HERMES_CRON_AUTO_DELIVER_PLATFORM"] = delivery_target["platform"]
+            os.environ["HERMES_CRON_AUTO_DELIVER_CHAT_ID"] = str(delivery_target["chat_id"])
+            if delivery_target.get("thread_id") is not None:
+                os.environ["HERMES_CRON_AUTO_DELIVER_THREAD_ID"] = str(delivery_target["thread_id"])
+
+        model = job.get("model") or os.getenv("HERMES_MODEL") or ""
 
         # Load config.yaml for model, reasoning, prefill, toolsets, provider routing
         _cfg = {}
@@ -186,24 +350,20 @@ def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:
                 with open(_cfg_path) as _f:
                     _cfg = yaml.safe_load(_f) or {}
                 _model_cfg = _cfg.get("model", {})
-                if isinstance(_model_cfg, str):
-                    model = _model_cfg
-                elif isinstance(_model_cfg, dict):
-                    model = _model_cfg.get("default", model)
-        except Exception:
-            pass
+                if not job.get("model"):
+                    if isinstance(_model_cfg, str):
+                        model = _model_cfg
+                    elif isinstance(_model_cfg, dict):
+                        model = _model_cfg.get("default", model)
+        except Exception as e:
+            logger.warning("Job '%s': failed to load config.yaml, using defaults: %s", job_id, e)
 
         # Reasoning config from env or config.yaml
-        reasoning_config = None
+        from hermes_constants import parse_reasoning_effort
         effort = os.getenv("HERMES_REASONING_EFFORT", "")
         if not effort:
             effort = str(_cfg.get("agent", {}).get("reasoning_effort", "")).strip()
-        if effort and effort.lower() != "none":
-            valid = ("xhigh", "high", "medium", "low", "minimal")
-            if effort.lower() in valid:
-                reasoning_config = {"enabled": True, "effort": effort.lower()}
-        elif effort.lower() == "none":
-            reasoning_config = {"enabled": False}
+        reasoning_config = parse_reasoning_effort(effort)
 
         # Prefill messages from env or config.yaml
         prefill_messages = None
@@ -219,7 +379,8 @@ def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:
                         prefill_messages = _json.load(_pf)
                     if not isinstance(prefill_messages, list):
                         prefill_messages = None
-                except Exception:
+                except Exception as e:
+                    logger.warning("Job '%s': failed to parse prefill messages file '%s': %s", job_id, pfpath, e)
                     prefill_messages = None
 
         # Max iterations
@@ -227,25 +388,46 @@ def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:
 
         # Provider routing
         pr = _cfg.get("provider_routing", {})
+        smart_routing = _cfg.get("smart_model_routing", {}) or {}
 
         from hermes_cli.runtime_provider import (
             resolve_runtime_provider,
             format_runtime_provider_error,
         )
         try:
-            runtime = resolve_runtime_provider(
-                requested=os.getenv("HERMES_INFERENCE_PROVIDER"),
-            )
+            runtime_kwargs = {
+                "requested": job.get("provider") or os.getenv("HERMES_INFERENCE_PROVIDER"),
+            }
+            if job.get("base_url"):
+                runtime_kwargs["explicit_base_url"] = job.get("base_url")
+            runtime = resolve_runtime_provider(**runtime_kwargs)
         except Exception as exc:
             message = format_runtime_provider_error(exc)
             raise RuntimeError(message) from exc
 
+        from agent.smart_model_routing import resolve_turn_route
+        turn_route = resolve_turn_route(
+            prompt,
+            smart_routing,
+            {
+                "model": model,
+                "api_key": runtime.get("api_key"),
+                "base_url": runtime.get("base_url"),
+                "provider": runtime.get("provider"),
+                "api_mode": runtime.get("api_mode"),
+                "command": runtime.get("command"),
+                "args": list(runtime.get("args") or []),
+            },
+        )
+
         agent = AIAgent(
-            model=model,
-            api_key=runtime.get("api_key"),
-            base_url=runtime.get("base_url"),
-            provider=runtime.get("provider"),
-            api_mode=runtime.get("api_mode"),
+            model=turn_route["model"],
+            api_key=turn_route["runtime"].get("api_key"),
+            base_url=turn_route["runtime"].get("base_url"),
+            provider=turn_route["runtime"].get("provider"),
+            api_mode=turn_route["runtime"].get("api_mode"),
+            acp_command=turn_route["runtime"].get("command"),
+            acp_args=turn_route["runtime"].get("args"),
             max_iterations=max_iterations,
             reasoning_config=reasoning_config,
             prefill_messages=prefill_messages,
@@ -253,15 +435,19 @@ def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:
             providers_ignored=pr.get("ignore"),
             providers_order=pr.get("order"),
             provider_sort=pr.get("sort"),
+            disabled_toolsets=["cronjob", "messaging", "clarify"],
             quiet_mode=True,
-            session_id=f"cron_{job_id}_{_hermes_now().strftime('%Y%m%d_%H%M%S')}"
+            platform="cron",
+            session_id=_cron_session_id,
+            session_db=_session_db,
         )
         
         result = agent.run_conversation(prompt)
         
-        final_response = result.get("final_response", "")
-        if not final_response:
-            final_response = "(No response generated)"
+        final_response = result.get("final_response", "") or ""
+        # Use a separate variable for log display; keep final_response clean
+        # for delivery logic (empty response = no delivery).
+        logged_response = final_response if final_response else "(No response generated)"
         
         output = f"""# Cron Job: {job_name}
 
@@ -275,7 +461,7 @@ def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:
 
 ## Response
 
-{final_response}
+{logged_response}
 """
         
         logger.info("Job '%s' completed successfully", job_name)
@@ -307,8 +493,24 @@ def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:
 
     finally:
         # Clean up injected env vars so they don't leak to other jobs
-        for key in ("HERMES_SESSION_PLATFORM", "HERMES_SESSION_CHAT_ID", "HERMES_SESSION_CHAT_NAME"):
+        for key in (
+            "HERMES_SESSION_PLATFORM",
+            "HERMES_SESSION_CHAT_ID",
+            "HERMES_SESSION_CHAT_NAME",
+            "HERMES_CRON_AUTO_DELIVER_PLATFORM",
+            "HERMES_CRON_AUTO_DELIVER_CHAT_ID",
+            "HERMES_CRON_AUTO_DELIVER_THREAD_ID",
+        ):
             os.environ.pop(key, None)
+        if _session_db:
+            try:
+                _session_db.end_session(_cron_session_id, "cron_complete")
+            except (Exception, KeyboardInterrupt) as e:
+                logger.debug("Job '%s': failed to end session: %s", job_id, e)
+            try:
+                _session_db.close()
+            except (Exception, KeyboardInterrupt) as e:
+                logger.debug("Job '%s': failed to close SQLite session store: %s", job_id, e)
 
 
 def tick(verbose: bool = True) -> int:
@@ -353,15 +555,28 @@ def tick(verbose: bool = True) -> int:
         executed = 0
         for job in due_jobs:
             try:
+                # For recurring jobs (cron/interval), advance next_run_at to the
+                # next future occurrence BEFORE execution.  This way, if the
+                # process crashes mid-run, the job won't re-fire on restart.
+                # One-shot jobs are left alone so they can retry on restart.
+                advance_next_run(job["id"])
+
                 success, output, final_response, error = run_job(job)
 
                 output_file = save_job_output(job["id"], output)
                 if verbose:
                     logger.info("Output saved to: %s", output_file)
 
-                # Deliver the final response to the origin/target chat
+                # Deliver the final response to the origin/target chat.
+                # If the agent responded with [SILENT], skip delivery (but
+                # output is already saved above).  Failed jobs always deliver.
                 deliver_content = final_response if success else f"⚠️ Cron job '{job.get('name', job['id'])}' failed:\n{error}"
-                if deliver_content:
+                should_deliver = bool(deliver_content)
+                if should_deliver and success and deliver_content.strip().upper().startswith(SILENT_MARKER):
+                    logger.info("Job '%s': agent returned %s — skipping delivery", job["id"], SILENT_MARKER)
+                    should_deliver = False
+
+                if should_deliver:
                     try:
                         _deliver_result(job, deliver_content)
                     except Exception as de:

docker/SOUL.md

@@ -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.
+-->

docker/entrypoint.sh

@@ -0,0 +1,34 @@
+#!/bin/bash
+# Docker entrypoint: bootstrap config files into the mounted volume, then run hermes.
+set -e
+
+HERMES_HOME="/opt/data"
+INSTALL_DIR="/opt/hermes"
+
+# Create essential directory structure.  Cache and platform directories
+# (cache/images, cache/audio, platforms/whatsapp, etc.) are created on
+# demand by the application — don't pre-create them here so new installs
+# get the consolidated layout from get_hermes_dir().
+mkdir -p "$HERMES_HOME"/{cron,sessions,logs,hooks,memories,skills}
+
+# .env
+if [ ! -f "$HERMES_HOME/.env" ]; then
+    cp "$INSTALL_DIR/.env.example" "$HERMES_HOME/.env"
+fi
+
+# config.yaml
+if [ ! -f "$HERMES_HOME/config.yaml" ]; then
+    cp "$INSTALL_DIR/cli-config.yaml.example" "$HERMES_HOME/config.yaml"
+fi
+
+# SOUL.md
+if [ ! -f "$HERMES_HOME/SOUL.md" ]; then
+    cp "$INSTALL_DIR/docker/SOUL.md" "$HERMES_HOME/SOUL.md"
+fi
+
+# Sync bundled skills (manifest-based so user edits are preserved)
+if [ -d "$INSTALL_DIR/skills" ]; then
+    python3 "$INSTALL_DIR/tools/skills_sync.py"
+fi
+
+exec hermes "$@"

docs/acp-setup.md

@@ -0,0 +1,229 @@
+# Hermes Agent — ACP (Agent Client Protocol) Setup Guide
+
+Hermes Agent supports the **Agent Client Protocol (ACP)**, allowing it to run as
+a coding agent inside your editor. ACP lets your IDE send tasks to Hermes, and
+Hermes responds with file edits, terminal commands, and explanations — all shown
+natively in the editor UI.
+
+---
+
+## Prerequisites
+
+- Hermes Agent installed and configured (`hermes setup` completed)
+- An API key / provider set up in `~/.hermes/.env` or via `hermes login`
+- Python 3.11+
+
+Install the ACP extra:
+
+```bash
+pip install -e ".[acp]"
+```
+
+---
+
+## VS Code Setup
+
+### 1. Install the ACP Client extension
+
+Open VS Code and install **ACP Client** from the marketplace:
+
+- Press `Ctrl+Shift+X` (or `Cmd+Shift+X` on macOS)
+- Search for **"ACP Client"**
+- Click **Install**
+
+Or install from the command line:
+
+```bash
+code --install-extension anysphere.acp-client
+```
+
+### 2. Configure settings.json
+
+Open your VS Code settings (`Ctrl+,` → click the `{}` icon for JSON) and add:
+
+```json
+{
+  "acpClient.agents": [
+    {
+      "name": "hermes-agent",
+      "registryDir": "/path/to/hermes-agent/acp_registry"
+    }
+  ]
+}
+```
+
+Replace `/path/to/hermes-agent` with the actual path to your Hermes Agent
+installation (e.g. `~/.hermes/hermes-agent`).
+
+Alternatively, if `hermes` is on your PATH, the ACP Client can discover it
+automatically via the registry directory.
+
+### 3. Restart VS Code
+
+After configuring, restart VS Code. You should see **Hermes Agent** appear in
+the ACP agent picker in the chat/agent panel.
+
+---
+
+## Zed Setup
+
+Zed has built-in ACP support.
+
+### 1. Configure Zed settings
+
+Open Zed settings (`Cmd+,` on macOS or `Ctrl+,` on Linux) and add to your
+`settings.json`:
+
+```json
+{
+  "acp": {
+    "agents": [
+      {
+        "name": "hermes-agent",
+        "registry_dir": "/path/to/hermes-agent/acp_registry"
+      }
+    ]
+  }
+}
+```
+
+### 2. Restart Zed
+
+Hermes Agent will appear in the agent panel. Select it and start a conversation.
+
+---
+
+## JetBrains Setup (IntelliJ, PyCharm, WebStorm, etc.)
+
+### 1. Install the ACP plugin
+
+- Open **Settings** → **Plugins** → **Marketplace**
+- Search for **"ACP"** or **"Agent Client Protocol"**
+- Install and restart the IDE
+
+### 2. Configure the agent
+
+- Open **Settings** → **Tools** → **ACP Agents**
+- Click **+** to add a new agent
+- Set the registry directory to your `acp_registry/` folder:
+  `/path/to/hermes-agent/acp_registry`
+- Click **OK**
+
+### 3. Use the agent
+
+Open the ACP panel (usually in the right sidebar) and select **Hermes Agent**.
+
+---
+
+## What You Will See
+
+Once connected, your editor provides a native interface to Hermes Agent:
+
+### Chat Panel
+A conversational interface where you can describe tasks, ask questions, and
+give instructions. Hermes responds with explanations and actions.
+
+### File Diffs
+When Hermes edits files, you see standard diffs in the editor. You can:
+- **Accept** individual changes
+- **Reject** changes you don't want
+- **Review** the full diff before applying
+
+### Terminal Commands
+When Hermes needs to run shell commands (builds, tests, installs), the editor
+shows them in an integrated terminal. Depending on your settings:
+- Commands may run automatically
+- Or you may be prompted to **approve** each command
+
+### Approval Flow
+For potentially destructive operations, the editor will prompt you for
+approval before Hermes proceeds. This includes:
+- File deletions
+- Shell commands
+- Git operations
+
+---
+
+## Configuration
+
+Hermes Agent under ACP uses the **same configuration** as the CLI:
+
+- **API keys / providers**: `~/.hermes/.env`
+- **Agent config**: `~/.hermes/config.yaml`
+- **Skills**: `~/.hermes/skills/`
+- **Sessions**: `~/.hermes/state.db`
+
+You can run `hermes setup` to configure providers, or edit `~/.hermes/.env`
+directly.
+
+### Changing the model
+
+Edit `~/.hermes/config.yaml`:
+
+```yaml
+model: openrouter/nous/hermes-3-llama-3.1-70b
+```
+
+Or set the `HERMES_MODEL` environment variable.
+
+### Toolsets
+
+ACP sessions use the curated `hermes-acp` toolset by default. It is designed for editor workflows and intentionally excludes things like messaging delivery, cronjob management, and audio-first UX features.
+
+---
+
+## Troubleshooting
+
+### Agent doesn't appear in the editor
+
+1. **Check the registry path** — make sure the `acp_registry/` directory path
+   in your editor settings is correct and contains `agent.json`.
+2. **Check `hermes` is on PATH** — run `which hermes` in a terminal. If not
+   found, you may need to activate your virtualenv or add it to PATH.
+3. **Restart the editor** after changing settings.
+
+### Agent starts but errors immediately
+
+1. Run `hermes doctor` to check your configuration.
+2. Check that you have a valid API key: `hermes status`
+3. Try running `hermes acp` directly in a terminal to see error output.
+
+### "Module not found" errors
+
+Make sure you installed the ACP extra:
+
+```bash
+pip install -e ".[acp]"
+```
+
+### Slow responses
+
+- ACP streams responses, so you should see incremental output. If the agent
+  appears stuck, check your network connection and API provider status.
+- Some providers have rate limits. Try switching to a different model/provider.
+
+### Permission denied for terminal commands
+
+If the editor blocks terminal commands, check your ACP Client extension
+settings for auto-approval or manual-approval preferences.
+
+### Logs
+
+Hermes logs are written to stderr when running in ACP mode. Check:
+- VS Code: **Output** panel → select **ACP Client** or **Hermes Agent**
+- Zed: **View** → **Toggle Terminal** and check the process output
+- JetBrains: **Event Log** or the ACP tool window
+
+You can also enable verbose logging:
+
+```bash
+HERMES_LOG_LEVEL=DEBUG hermes acp
+```
+
+---
+
+## Further Reading
+
+- [ACP Specification](https://github.com/anysphere/acp)
+- [Hermes Agent Documentation](https://github.com/NousResearch/hermes-agent)
+- Run `hermes --help` for all CLI options

docs/honcho-integration-spec.html

@@ -0,0 +1,698 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+<meta charset="UTF-8">
+<meta name="viewport" content="width=device-width, initial-scale=1.0">
+<title>honcho-integration-spec</title>
+<style>
+  :root {
+    --bg:             #0b0e14;
+    --bg-surface:     #11151c;
+    --bg-elevated:    #181d27;
+    --bg-code:        #0d1018;
+    --fg:             #c9d1d9;
+    --fg-bright:      #e6edf3;
+    --fg-muted:       #6e7681;
+    --fg-subtle:      #484f58;
+    --accent:         #7eb8f6;
+    --accent-dim:     #3d6ea5;
+    --accent-glow:    rgba(126, 184, 246, 0.08);
+    --green:          #7ee6a8;
+    --green-dim:      #2ea04f;
+    --orange:         #e6a855;
+    --red:            #f47067;
+    --purple:         #bc8cff;
+    --cyan:           #56d4dd;
+    --border:         #21262d;
+    --border-subtle:  #161b22;
+    --radius:         6px;
+    --font-sans:      'New York', ui-serif, 'Iowan Old Style', 'Apple Garamond', Baskerville, 'Times New Roman', 'Noto Emoji', serif;
+    --font-mono:      'Departure Mono', 'Noto Emoji', monospace;
+  }
+
+  *, *::before, *::after { box-sizing: border-box; margin: 0; padding: 0; }
+  html { scroll-behavior: smooth; scroll-padding-top: 2rem; }
+  body {
+    font-family: var(--font-sans);
+    background: var(--bg);
+    color: var(--fg);
+    line-height: 1.7;
+    font-size: 15px;
+    -webkit-font-smoothing: antialiased;
+  }
+
+  .container { max-width: 860px; margin: 0 auto; padding: 3rem 2rem 6rem; }
+
+  .hero {
+    text-align: center;
+    padding: 4rem 0 3rem;
+    border-bottom: 1px solid var(--border);
+    margin-bottom: 3rem;
+  }
+  .hero h1 { font-family: var(--font-mono); font-size: 2.2rem; font-weight: 700; color: var(--fg-bright); letter-spacing: -0.03em; margin-bottom: 0.5rem; }
+  .hero h1 span { color: var(--accent); }
+  .hero .subtitle { font-family: var(--font-sans); color: var(--fg-muted); font-size: 0.92rem; max-width: 560px; margin: 0 auto; line-height: 1.6; }
+  .hero .meta { margin-top: 1.5rem; display: flex; justify-content: center; gap: 1.5rem; flex-wrap: wrap; }
+  .hero .meta span { font-size: 0.8rem; color: var(--fg-subtle); font-family: var(--font-mono); }
+
+  .toc { background: var(--bg-surface); border: 1px solid var(--border); border-radius: var(--radius); padding: 1.5rem 2rem; margin-bottom: 3rem; }
+  .toc h2 { font-size: 0.75rem; text-transform: uppercase; letter-spacing: 0.1em; color: var(--fg-muted); margin-bottom: 1rem; }
+  .toc ol { list-style: none; counter-reset: toc; columns: 2; column-gap: 2rem; }
+  .toc li { counter-increment: toc; break-inside: avoid; margin-bottom: 0.35rem; }
+  .toc li::before { content: counter(toc, decimal-leading-zero) " "; color: var(--fg-subtle); font-family: var(--font-mono); font-size: 0.75rem; margin-right: 0.25rem; }
+  .toc a { font-family: var(--font-mono); color: var(--fg); text-decoration: none; font-size: 0.82rem; transition: color 0.15s; }
+  .toc a:hover { color: var(--accent); }
+
+  section { margin-bottom: 4rem; }
+  section + section { padding-top: 1rem; }
+
+  h2 { font-family: var(--font-mono); font-size: 1.3rem; font-weight: 700; color: var(--fg-bright); letter-spacing: -0.01em; margin-bottom: 1.25rem; padding-bottom: 0.5rem; border-bottom: 1px solid var(--border); }
+  h3 { font-family: var(--font-mono); font-size: 1rem; font-weight: 600; color: var(--fg-bright); margin-top: 2rem; margin-bottom: 0.75rem; }
+  h4 { font-family: var(--font-mono); font-size: 0.9rem; font-weight: 600; color: var(--accent); margin-top: 1.5rem; margin-bottom: 0.5rem; }
+
+  p { margin-bottom: 1rem; font-size: 0.95rem; line-height: 1.75; }
+  strong { color: var(--fg-bright); font-weight: 600; }
+  a { color: var(--accent); text-decoration: none; }
+  a:hover { text-decoration: underline; }
+
+  ul, ol { margin-bottom: 1rem; padding-left: 1.5rem; font-size: 0.93rem; line-height: 1.7; }
+  li { margin-bottom: 0.35rem; }
+  li::marker { color: var(--fg-subtle); }
+
+  .table-wrap { overflow-x: auto; margin-bottom: 1.5rem; }
+  table { width: 100%; border-collapse: collapse; font-size: 0.88rem; }
+  th, td { text-align: left; padding: 0.6rem 1rem; border-bottom: 1px solid var(--border-subtle); }
+  th { font-family: var(--font-mono); font-size: 0.72rem; text-transform: uppercase; letter-spacing: 0.06em; color: var(--fg-muted); background: var(--bg-surface); border-bottom-color: var(--border); white-space: nowrap; }
+  td { font-family: var(--font-sans); font-size: 0.88rem; color: var(--fg); }
+  tr:hover td { background: var(--accent-glow); }
+  td code { background: var(--bg-elevated); padding: 0.15em 0.4em; border-radius: 3px; font-family: var(--font-mono); font-size: 0.82em; color: var(--cyan); }
+
+  pre { background: var(--bg-code); border: 1px solid var(--border); border-radius: var(--radius); padding: 1.25rem 1.5rem; overflow-x: auto; margin-bottom: 1.5rem; font-family: var(--font-mono); font-size: 0.82rem; line-height: 1.65; color: var(--fg); }
+  pre code { background: none; padding: 0; color: inherit; font-size: inherit; }
+  code { font-family: var(--font-mono); font-size: 0.85em; }
+  p code, li code { background: var(--bg-elevated); padding: 0.15em 0.4em; border-radius: 3px; color: var(--cyan); font-size: 0.85em; }
+
+  .kw { color: var(--purple); }
+  .str { color: var(--green); }
+  .cm { color: var(--fg-subtle); font-style: italic; }
+  .num { color: var(--orange); }
+  .key { color: var(--accent); }
+
+  .mermaid { margin: 1.5rem 0 2rem; text-align: center; }
+  .mermaid svg { max-width: 100%; height: auto; }
+
+  .callout { font-family: var(--font-sans); background: var(--bg-surface); border-left: 3px solid var(--accent-dim); border-radius: 0 var(--radius) var(--radius) 0; padding: 1rem 1.25rem; margin-bottom: 1.5rem; font-size: 0.88rem; color: var(--fg-muted); line-height: 1.6; }
+  .callout strong { font-family: var(--font-mono); color: var(--fg-bright); }
+  .callout.success { border-left-color: var(--green-dim); }
+  .callout.warn { border-left-color: var(--orange); }
+
+  .badge { display: inline-block; font-family: var(--font-mono); font-size: 0.65rem; font-weight: 600; text-transform: uppercase; letter-spacing: 0.05em; padding: 0.2em 0.6em; border-radius: 3px; vertical-align: middle; margin-left: 0.4rem; }
+  .badge-done { background: var(--green-dim); color: #fff; }
+  .badge-wip { background: var(--orange); color: #0b0e14; }
+  .badge-todo { background: var(--fg-subtle); color: var(--fg); }
+
+  .checklist { list-style: none; padding-left: 0; }
+  .checklist li { padding-left: 1.5rem; position: relative; margin-bottom: 0.5rem; }
+  .checklist li::before { position: absolute; left: 0; font-family: var(--font-mono); font-size: 0.85rem; }
+  .checklist li.done { color: var(--fg-muted); }
+  .checklist li.done::before { content: "\2713"; color: var(--green); }
+  .checklist li.todo::before { content: "\25CB"; color: var(--fg-subtle); }
+  .checklist li.wip::before { content: "\25D4"; color: var(--orange); }
+
+  .compare { display: grid; grid-template-columns: 1fr 1fr; gap: 1rem; margin-bottom: 2rem; }
+  .compare-card { background: var(--bg-surface); border: 1px solid var(--border); border-radius: var(--radius); padding: 1.25rem; }
+  .compare-card h4 { margin-top: 0; font-size: 0.82rem; }
+  .compare-card.after { border-color: var(--accent-dim); }
+  .compare-card ul { font-family: var(--font-mono); padding-left: 1.25rem; font-size: 0.8rem; }
+
+  hr { border: none; border-top: 1px solid var(--border); margin: 3rem 0; }
+
+  .progress-bar { position: fixed; top: 0; left: 0; height: 2px; background: var(--accent); z-index: 999; transition: width 0.1s linear; }
+
+  @media (max-width: 640px) {
+    .container { padding: 2rem 1rem 4rem; }
+    .hero h1 { font-size: 1.6rem; }
+    .toc ol { columns: 1; }
+    .compare { grid-template-columns: 1fr; }
+    table { font-size: 0.8rem; }
+    th, td { padding: 0.4rem 0.6rem; }
+  }
+</style>
+<link rel="preconnect" href="https://fonts.googleapis.com">
+<link href="https://fonts.googleapis.com/css2?family=Noto+Emoji&display=swap" rel="stylesheet">
+<style>
+  @font-face {
+    font-family: 'Departure Mono';
+    src: url('https://cdn.jsdelivr.net/gh/rektdeckard/departure-mono@latest/fonts/DepartureMono-Regular.woff2') format('woff2');
+    font-weight: normal;
+    font-style: normal;
+    font-display: swap;
+  }
+</style>
+</head>
+<body>
+
+<div class="progress-bar" id="progress"></div>
+
+<div class="container">
+
+<header class="hero">
+  <h1>honcho<span>-integration-spec</span></h1>
+  <p class="subtitle">Comparison of Hermes Agent vs. openclaw-honcho — and a porting spec for bringing Hermes patterns into other Honcho integrations.</p>
+  <div class="meta">
+    <span>hermes-agent / openclaw-honcho</span>
+    <span>Python + TypeScript</span>
+    <span>2026-03-09</span>
+  </div>
+</header>
+
+<nav class="toc">
+  <h2>Contents</h2>
+  <ol>
+    <li><a href="#overview">Overview</a></li>
+    <li><a href="#architecture">Architecture comparison</a></li>
+    <li><a href="#diff-table">Diff table</a></li>
+    <li><a href="#patterns">Hermes patterns to port</a></li>
+    <li><a href="#spec-async">Spec: async prefetch</a></li>
+    <li><a href="#spec-reasoning">Spec: dynamic reasoning level</a></li>
+    <li><a href="#spec-modes">Spec: per-peer memory modes</a></li>
+    <li><a href="#spec-identity">Spec: AI peer identity formation</a></li>
+    <li><a href="#spec-sessions">Spec: session naming strategies</a></li>
+    <li><a href="#spec-cli">Spec: CLI surface injection</a></li>
+    <li><a href="#openclaw-checklist">openclaw-honcho checklist</a></li>
+    <li><a href="#nanobot-checklist">nanobot-honcho checklist</a></li>
+  </ol>
+</nav>
+
+<!-- OVERVIEW -->
+<section id="overview">
+  <h2>Overview</h2>
+
+  <p>Two independent Honcho integrations have been built for two different agent runtimes: <strong>Hermes Agent</strong> (Python, baked into the runner) and <strong>openclaw-honcho</strong> (TypeScript plugin via hook/tool API). Both use the same Honcho peer paradigm — dual peer model, <code>session.context()</code>, <code>peer.chat()</code> — but they made different tradeoffs at every layer.</p>
+
+  <p>This document maps those tradeoffs and defines a porting spec: a set of Hermes-originated patterns, each stated as an integration-agnostic interface, that any Honcho integration can adopt regardless of runtime or language.</p>
+
+  <div class="callout">
+    <strong>Scope</strong> Both integrations work correctly today. This spec is about the delta — patterns in Hermes that are worth propagating and patterns in openclaw-honcho that Hermes should eventually adopt. The spec is additive, not prescriptive.
+  </div>
+</section>
+
+<!-- ARCHITECTURE -->
+<section id="architecture">
+  <h2>Architecture comparison</h2>
+
+  <h3>Hermes: baked-in runner</h3>
+  <p>Honcho is initialised directly inside <code>AIAgent.__init__</code>. There is no plugin boundary. Session management, context injection, async prefetch, and CLI surface are all first-class concerns of the runner. Context is injected once per session (baked into <code>_cached_system_prompt</code>) and never re-fetched mid-session — this maximises prefix cache hits at the LLM provider.</p>
+
+  <div class="mermaid">
+%%{init: {'theme': 'dark', 'themeVariables': { 'primaryColor': '#1f3150', 'primaryTextColor': '#c9d1d9', 'primaryBorderColor': '#3d6ea5', 'lineColor': '#3d6ea5', 'secondaryColor': '#162030', 'tertiaryColor': '#11151c' }}}%%
+flowchart TD
+    U["user message"] --> P["_honcho_prefetch()<br/>(reads cache — no HTTP)"]
+    P --> SP["_build_system_prompt()<br/>(first turn only, cached)"]
+    SP --> LLM["LLM call"]
+    LLM --> R["response"]
+    R --> FP["_honcho_fire_prefetch()<br/>(daemon threads, turn end)"]
+    FP --> C1["prefetch_context() thread"]
+    FP --> C2["prefetch_dialectic() thread"]
+    C1 --> CACHE["_context_cache / _dialectic_cache"]
+    C2 --> CACHE
+
+    style U fill:#162030,stroke:#3d6ea5,color:#c9d1d9
+    style P fill:#1f3150,stroke:#3d6ea5,color:#c9d1d9
+    style SP fill:#1f3150,stroke:#3d6ea5,color:#c9d1d9
+    style LLM fill:#162030,stroke:#3d6ea5,color:#c9d1d9
+    style R fill:#162030,stroke:#3d6ea5,color:#c9d1d9
+    style FP fill:#2a1a40,stroke:#bc8cff,color:#c9d1d9
+    style C1 fill:#2a1a40,stroke:#bc8cff,color:#c9d1d9
+    style C2 fill:#2a1a40,stroke:#bc8cff,color:#c9d1d9
+    style CACHE fill:#11151c,stroke:#484f58,color:#6e7681
+  </div>
+
+  <h3>openclaw-honcho: hook-based plugin</h3>
+  <p>The plugin registers hooks against OpenClaw's event bus. Context is fetched synchronously inside <code>before_prompt_build</code> on every turn. Message capture happens in <code>agent_end</code>. The multi-agent hierarchy is tracked via <code>subagent_spawned</code>. This model is correct but every turn pays a blocking Honcho round-trip before the LLM call can begin.</p>
+
+  <div class="mermaid">
+%%{init: {'theme': 'dark', 'themeVariables': { 'primaryColor': '#1f3150', 'primaryTextColor': '#c9d1d9', 'primaryBorderColor': '#3d6ea5', 'lineColor': '#3d6ea5', 'secondaryColor': '#162030', 'tertiaryColor': '#11151c' }}}%%
+flowchart TD
+    U2["user message"] --> BPB["before_prompt_build<br/>(BLOCKING HTTP — every turn)"]
+    BPB --> CTX["session.context()"]
+    CTX --> SP2["system prompt assembled"]
+    SP2 --> LLM2["LLM call"]
+    LLM2 --> R2["response"]
+    R2 --> AE["agent_end hook"]
+    AE --> SAVE["session.addMessages()<br/>session.setMetadata()"]
+
+    style U2 fill:#162030,stroke:#3d6ea5,color:#c9d1d9
+    style BPB fill:#3a1515,stroke:#f47067,color:#c9d1d9
+    style CTX fill:#3a1515,stroke:#f47067,color:#c9d1d9
+    style SP2 fill:#1f3150,stroke:#3d6ea5,color:#c9d1d9
+    style LLM2 fill:#162030,stroke:#3d6ea5,color:#c9d1d9
+    style R2 fill:#162030,stroke:#3d6ea5,color:#c9d1d9
+    style AE fill:#162030,stroke:#3d6ea5,color:#c9d1d9
+    style SAVE fill:#11151c,stroke:#484f58,color:#6e7681
+  </div>
+</section>
+
+<!-- DIFF TABLE -->
+<section id="diff-table">
+  <h2>Diff table</h2>
+
+  <div class="table-wrap">
+    <table>
+      <thead>
+        <tr>
+          <th>Dimension</th>
+          <th>Hermes Agent</th>
+          <th>openclaw-honcho</th>
+        </tr>
+      </thead>
+      <tbody>
+        <tr>
+          <td><strong>Context injection timing</strong></td>
+          <td>Once per session (cached). Zero HTTP on response path after turn 1.</td>
+          <td>Every turn, blocking. Fresh context per turn but adds latency.</td>
+        </tr>
+        <tr>
+          <td><strong>Prefetch strategy</strong></td>
+          <td>Daemon threads fire at turn end; consumed next turn from cache.</td>
+          <td>None. Blocking call at prompt-build time.</td>
+        </tr>
+        <tr>
+          <td><strong>Dialectic (peer.chat)</strong></td>
+          <td>Prefetched async; result injected into system prompt next turn.</td>
+          <td>On-demand via <code>honcho_recall</code> / <code>honcho_analyze</code> tools.</td>
+        </tr>
+        <tr>
+          <td><strong>Reasoning level</strong></td>
+          <td>Dynamic: scales with message length. Floor = config default. Cap = "high".</td>
+          <td>Fixed per tool: recall=minimal, analyze=medium.</td>
+        </tr>
+        <tr>
+          <td><strong>Memory modes</strong></td>
+          <td><code>user_memory_mode</code> / <code>agent_memory_mode</code>: hybrid / honcho / local.</td>
+          <td>None. Always writes to Honcho.</td>
+        </tr>
+        <tr>
+          <td><strong>Write frequency</strong></td>
+          <td>async (background queue), turn, session, N turns.</td>
+          <td>After every agent_end (no control).</td>
+        </tr>
+        <tr>
+          <td><strong>AI peer identity</strong></td>
+          <td><code>observe_me=True</code>, <code>seed_ai_identity()</code>, <code>get_ai_representation()</code>, SOUL.md → AI peer.</td>
+          <td>Agent files uploaded to agent peer at setup. No ongoing self-observation seeding.</td>
+        </tr>
+        <tr>
+          <td><strong>Context scope</strong></td>
+          <td>User peer + AI peer representation, both injected.</td>
+          <td>User peer (owner) representation + conversation summary. <code>peerPerspective</code> on context call.</td>
+        </tr>
+        <tr>
+          <td><strong>Session naming</strong></td>
+          <td>per-directory / global / manual map / title-based.</td>
+          <td>Derived from platform session key.</td>
+        </tr>
+        <tr>
+          <td><strong>Multi-agent</strong></td>
+          <td>Single-agent only.</td>
+          <td>Parent observer hierarchy via <code>subagent_spawned</code>.</td>
+        </tr>
+        <tr>
+          <td><strong>Tool surface</strong></td>
+          <td>Single <code>query_user_context</code> tool (on-demand dialectic).</td>
+          <td>6 tools: session, profile, search, context (fast) + recall, analyze (LLM).</td>
+        </tr>
+        <tr>
+          <td><strong>Platform metadata</strong></td>
+          <td>Not stripped.</td>
+          <td>Explicitly stripped before Honcho storage.</td>
+        </tr>
+        <tr>
+          <td><strong>Message dedup</strong></td>
+          <td>None (sends on every save cycle).</td>
+          <td><code>lastSavedIndex</code> in session metadata prevents re-sending.</td>
+        </tr>
+        <tr>
+          <td><strong>CLI surface in prompt</strong></td>
+          <td>Management commands injected into system prompt. Agent knows its own CLI.</td>
+          <td>Not injected.</td>
+        </tr>
+        <tr>
+          <td><strong>AI peer name in identity</strong></td>
+          <td>Replaces "Hermes Agent" in DEFAULT_AGENT_IDENTITY when configured.</td>
+          <td>Not implemented.</td>
+        </tr>
+        <tr>
+          <td><strong>QMD / local file search</strong></td>
+          <td>Not implemented.</td>
+          <td>Passthrough tools when QMD backend configured.</td>
+        </tr>
+        <tr>
+          <td><strong>Workspace metadata</strong></td>
+          <td>Not implemented.</td>
+          <td><code>agentPeerMap</code> in workspace metadata tracks agent&#8594;peer ID.</td>
+        </tr>
+      </tbody>
+    </table>
+  </div>
+</section>
+
+<!-- PATTERNS -->
+<section id="patterns">
+  <h2>Hermes patterns to port</h2>
+
+  <p>Six patterns from Hermes are worth adopting in any Honcho integration. They are described below as integration-agnostic interfaces — the implementation will differ per runtime, but the contract is the same.</p>
+
+  <div class="compare">
+    <div class="compare-card">
+      <h4>Patterns Hermes contributes</h4>
+      <ul>
+        <li>Async prefetch (zero-latency)</li>
+        <li>Dynamic reasoning level</li>
+        <li>Per-peer memory modes</li>
+        <li>AI peer identity formation</li>
+        <li>Session naming strategies</li>
+        <li>CLI surface injection</li>
+      </ul>
+    </div>
+    <div class="compare-card after">
+      <h4>Patterns openclaw contributes back</h4>
+      <ul>
+        <li>lastSavedIndex dedup</li>
+        <li>Platform metadata stripping</li>
+        <li>Multi-agent observer hierarchy</li>
+        <li>peerPerspective on context()</li>
+        <li>Tiered tool surface (fast/LLM)</li>
+        <li>Workspace agentPeerMap</li>
+      </ul>
+    </div>
+  </div>
+</section>
+
+<!-- SPEC: ASYNC PREFETCH -->
+<section id="spec-async">
+  <h2>Spec: async prefetch</h2>
+
+  <h3>Problem</h3>
+  <p>Calling <code>session.context()</code> and <code>peer.chat()</code> synchronously before each LLM call adds 200–800ms of Honcho round-trip latency to every turn. Users experience this as the agent "thinking slowly."</p>
+
+  <h3>Pattern</h3>
+  <p>Fire both calls as non-blocking background work at the <strong>end</strong> of each turn. Store results in a per-session cache keyed by session ID. At the <strong>start</strong> of the next turn, pop from cache — the HTTP is already done. First turn is cold (empty cache); all subsequent turns are zero-latency on the response path.</p>
+
+  <h3>Interface contract</h3>
+  <pre><code><span class="cm">// TypeScript (openclaw / nanobot plugin shape)</span>
+
+<span class="kw">interface</span> <span class="key">AsyncPrefetch</span> {
+  <span class="cm">// Fire context + dialectic fetches at turn end. Non-blocking.</span>
+  firePrefetch(sessionId: <span class="str">string</span>, userMessage: <span class="str">string</span>): <span class="kw">void</span>;
+
+  <span class="cm">// Pop cached results at turn start. Returns empty if cache is cold.</span>
+  popContextResult(sessionId: <span class="str">string</span>): ContextResult | <span class="kw">null</span>;
+  popDialecticResult(sessionId: <span class="str">string</span>): <span class="str">string</span> | <span class="kw">null</span>;
+}
+
+<span class="kw">type</span> <span class="key">ContextResult</span> = {
+  representation: <span class="str">string</span>;
+  card: <span class="str">string</span>[];
+  aiRepresentation?: <span class="str">string</span>;  <span class="cm">// AI peer context if enabled</span>
+  summary?: <span class="str">string</span>;            <span class="cm">// conversation summary if fetched</span>
+};</code></pre>
+
+  <h3>Implementation notes</h3>
+  <ul>
+    <li>Python: <code>threading.Thread(daemon=True)</code>. Write to <code>dict[session_id, result]</code> — GIL makes this safe for simple writes.</li>
+    <li>TypeScript: <code>Promise</code> stored in <code>Map&lt;string, Promise&lt;ContextResult&gt;&gt;</code>. Await at pop time. If not resolved yet, skip (return null) — do not block.</li>
+    <li>The pop is destructive: clears the cache entry after reading so stale data never accumulates.</li>
+    <li>Prefetch should also fire on first turn (even though it won't be consumed until turn 2) — this ensures turn 2 is never cold.</li>
+  </ul>
+
+  <h3>openclaw-honcho adoption</h3>
+  <p>Move <code>session.context()</code> from <code>before_prompt_build</code> to a post-<code>agent_end</code> background task. Store result in <code>state.contextCache</code>. In <code>before_prompt_build</code>, read from cache instead of calling Honcho. If cache is empty (turn 1), inject nothing — the prompt is still valid without Honcho context on the first turn.</p>
+</section>
+
+<!-- SPEC: DYNAMIC REASONING LEVEL -->
+<section id="spec-reasoning">
+  <h2>Spec: dynamic reasoning level</h2>
+
+  <h3>Problem</h3>
+  <p>Honcho's dialectic endpoint supports reasoning levels from <code>minimal</code> to <code>max</code>. A fixed level per tool wastes budget on simple queries and under-serves complex ones.</p>
+
+  <h3>Pattern</h3>
+  <p>Select the reasoning level dynamically based on the user's message. Use the configured default as a floor. Bump by message length. Cap auto-selection at <code>high</code> — never select <code>max</code> automatically.</p>
+
+  <h3>Interface contract</h3>
+  <pre><code><span class="cm">// Shared helper — identical logic in any language</span>
+
+<span class="kw">const</span> LEVELS = [<span class="str">"minimal"</span>, <span class="str">"low"</span>, <span class="str">"medium"</span>, <span class="str">"high"</span>, <span class="str">"max"</span>];
+
+<span class="kw">function</span> <span class="key">dynamicReasoningLevel</span>(
+  query: <span class="str">string</span>,
+  configDefault: <span class="str">string</span> = <span class="str">"low"</span>
+): <span class="str">string</span> {
+  <span class="kw">const</span> baseIdx = Math.max(<span class="num">0</span>, LEVELS.indexOf(configDefault));
+  <span class="kw">const</span> n = query.length;
+  <span class="kw">const</span> bump = n &lt; <span class="num">120</span> ? <span class="num">0</span> : n &lt; <span class="num">400</span> ? <span class="num">1</span> : <span class="num">2</span>;
+  <span class="kw">return</span> LEVELS[Math.min(baseIdx + bump, <span class="num">3</span>)]; <span class="cm">// cap at "high" (idx 3)</span>
+}</code></pre>
+
+  <h3>Config key</h3>
+  <p>Add a <code>dialecticReasoningLevel</code> config field (string, default <code>"low"</code>). This sets the floor. Users can raise or lower it. The dynamic bump always applies on top.</p>
+
+  <h3>openclaw-honcho adoption</h3>
+  <p>Apply in <code>honcho_recall</code> and <code>honcho_analyze</code>: replace the fixed <code>reasoningLevel</code> with the dynamic selector. <code>honcho_recall</code> should use floor <code>"minimal"</code> and <code>honcho_analyze</code> floor <code>"medium"</code> — both still bump with message length.</p>
+</section>
+
+<!-- SPEC: PER-PEER MEMORY MODES -->
+<section id="spec-modes">
+  <h2>Spec: per-peer memory modes</h2>
+
+  <h3>Problem</h3>
+  <p>Users want independent control over whether user context and agent context are written locally, to Honcho, or both. A single <code>memoryMode</code> shorthand is not granular enough.</p>
+
+  <h3>Pattern</h3>
+  <p>Three modes per peer: <code>hybrid</code> (write both local + Honcho), <code>honcho</code> (Honcho only, disable local files), <code>local</code> (local files only, skip Honcho sync for this peer). Two orthogonal axes: user peer and agent peer.</p>
+
+  <h3>Config schema</h3>
+  <pre><code><span class="cm">// ~/.openclaw/openclaw.json  (or ~/.nanobot/config.json)</span>
+{
+  <span class="str">"plugins"</span>: {
+    <span class="str">"openclaw-honcho"</span>: {
+      <span class="str">"config"</span>: {
+        <span class="str">"apiKey"</span>: <span class="str">"..."</span>,
+        <span class="str">"memoryMode"</span>: <span class="str">"hybrid"</span>,          <span class="cm">// shorthand: both peers</span>
+        <span class="str">"userMemoryMode"</span>: <span class="str">"honcho"</span>,       <span class="cm">// override for user peer</span>
+        <span class="str">"agentMemoryMode"</span>: <span class="str">"hybrid"</span>       <span class="cm">// override for agent peer</span>
+      }
+    }
+  }
+}</code></pre>
+
+  <h3>Resolution order</h3>
+  <ol>
+    <li>Per-peer field (<code>userMemoryMode</code> / <code>agentMemoryMode</code>) — wins if present.</li>
+    <li>Shorthand <code>memoryMode</code> — applies to both peers as default.</li>
+    <li>Hardcoded default: <code>"hybrid"</code>.</li>
+  </ol>
+
+  <h3>Effect on Honcho sync</h3>
+  <ul>
+    <li><code>userMemoryMode=local</code>: skip adding user peer messages to Honcho.</li>
+    <li><code>agentMemoryMode=local</code>: skip adding assistant peer messages to Honcho.</li>
+    <li>Both local: skip <code>session.addMessages()</code> entirely.</li>
+    <li><code>userMemoryMode=honcho</code>: disable local USER.md writes.</li>
+    <li><code>agentMemoryMode=honcho</code>: disable local MEMORY.md / SOUL.md writes.</li>
+  </ul>
+</section>
+
+<!-- SPEC: AI PEER IDENTITY -->
+<section id="spec-identity">
+  <h2>Spec: AI peer identity formation</h2>
+
+  <h3>Problem</h3>
+  <p>Honcho builds the user's representation organically by observing what the user says. The same mechanism exists for the AI peer — but only if <code>observe_me=True</code> is set for the agent peer. Without it, the agent peer accumulates nothing and Honcho's AI-side model never forms.</p>
+
+  <p>Additionally, existing persona files (SOUL.md, IDENTITY.md) should seed the AI peer's Honcho representation at first activation, rather than waiting for it to emerge from scratch.</p>
+
+  <h3>Part A: observe_me=True for agent peer</h3>
+  <pre><code><span class="cm">// TypeScript — in session.addPeers() call</span>
+<span class="kw">await</span> session.addPeers([
+  [ownerPeer.id, { observeMe: <span class="kw">true</span>,  observeOthers: <span class="kw">false</span> }],
+  [agentPeer.id, { observeMe: <span class="kw">true</span>,  observeOthers: <span class="kw">true</span>  }], <span class="cm">// was false</span>
+]);</code></pre>
+
+  <p>This is a one-line change but foundational. Without it, Honcho's AI peer representation stays empty regardless of what the agent says.</p>
+
+  <h3>Part B: seedAiIdentity()</h3>
+  <pre><code><span class="kw">async function</span> <span class="key">seedAiIdentity</span>(
+  session: HonchoSession,
+  agentPeer: Peer,
+  content: <span class="str">string</span>,
+  source: <span class="str">string</span>
+): Promise&lt;<span class="kw">boolean</span>&gt; {
+  <span class="kw">const</span> wrapped = [
+    <span class="str">`&lt;ai_identity_seed&gt;`</span>,
+    <span class="str">`&lt;source&gt;${source}&lt;/source&gt;`</span>,
+    <span class="str">``</span>,
+    content.trim(),
+    <span class="str">`&lt;/ai_identity_seed&gt;`</span>,
+  ].join(<span class="str">"\n"</span>);
+
+  <span class="kw">await</span> agentPeer.addMessage(<span class="str">"assistant"</span>, wrapped);
+  <span class="kw">return true</span>;
+}</code></pre>
+
+  <h3>Part C: migrate agent files at setup</h3>
+  <p>During <code>openclaw honcho setup</code>, upload agent-self files (SOUL.md, IDENTITY.md, AGENTS.md, BOOTSTRAP.md) to the agent peer using <code>seedAiIdentity()</code> instead of <code>session.uploadFile()</code>. This routes the content through Honcho's observation pipeline rather than the file store.</p>
+
+  <h3>Part D: AI peer name in identity</h3>
+  <p>When the agent has a configured name (non-default), inject it into the agent's self-identity prefix. In OpenClaw this means adding to the injected system prompt section:</p>
+  <pre><code><span class="cm">// In context hook return value</span>
+<span class="kw">return</span> {
+  systemPrompt: [
+    agentName ? <span class="str">`You are ${agentName}.`</span> : <span class="str">""</span>,
+    <span class="str">"## User Memory Context"</span>,
+    ...sections,
+  ].filter(Boolean).join(<span class="str">"\n\n"</span>)
+};</code></pre>
+
+  <h3>CLI surface: honcho identity subcommand</h3>
+  <pre><code>openclaw honcho identity &lt;file&gt;    <span class="cm"># seed from file</span>
+openclaw honcho identity --show    <span class="cm"># show current AI peer representation</span></code></pre>
+</section>
+
+<!-- SPEC: SESSION NAMING -->
+<section id="spec-sessions">
+  <h2>Spec: session naming strategies</h2>
+
+  <h3>Problem</h3>
+  <p>When Honcho is used across multiple projects or directories, a single global session means every project shares the same context. Per-directory sessions provide isolation without requiring users to name sessions manually.</p>
+
+  <h3>Strategies</h3>
+  <div class="table-wrap">
+    <table>
+      <thead><tr><th>Strategy</th><th>Session key</th><th>When to use</th></tr></thead>
+      <tbody>
+        <tr><td><code>per-directory</code></td><td>basename of CWD</td><td>Default. Each project gets its own session.</td></tr>
+        <tr><td><code>global</code></td><td>fixed string <code>"global"</code></td><td>Single cross-project session.</td></tr>
+        <tr><td>manual map</td><td>user-configured per path</td><td><code>sessions</code> config map overrides directory basename.</td></tr>
+        <tr><td>title-based</td><td>sanitized session title</td><td>When agent supports named sessions; title set mid-conversation.</td></tr>
+      </tbody>
+    </table>
+  </div>
+
+  <h3>Config schema</h3>
+  <pre><code>{
+  <span class="str">"sessionStrategy"</span>: <span class="str">"per-directory"</span>,   <span class="cm">// "per-directory" | "global"</span>
+  <span class="str">"sessionPeerPrefix"</span>: <span class="kw">false</span>,            <span class="cm">// prepend peer name to session key</span>
+  <span class="str">"sessions"</span>: {                            <span class="cm">// manual overrides</span>
+    <span class="str">"/home/user/projects/foo"</span>: <span class="str">"foo-project"</span>
+  }
+}</code></pre>
+
+  <h3>CLI surface</h3>
+  <pre><code>openclaw honcho sessions              <span class="cm"># list all mappings</span>
+openclaw honcho map &lt;name&gt;           <span class="cm"># map cwd to session name</span>
+openclaw honcho map                   <span class="cm"># no-arg = list mappings</span></code></pre>
+
+  <p>Resolution order: manual map wins &rarr; session title &rarr; directory basename &rarr; platform key.</p>
+</section>
+
+<!-- SPEC: CLI SURFACE INJECTION -->
+<section id="spec-cli">
+  <h2>Spec: CLI surface injection</h2>
+
+  <h3>Problem</h3>
+  <p>When a user asks "how do I change my memory settings?" or "what Honcho commands are available?" the agent either hallucinates or says it doesn't know. The agent should know its own management interface.</p>
+
+  <h3>Pattern</h3>
+  <p>When Honcho is active, append a compact command reference to the system prompt. The agent can cite these commands directly instead of guessing.</p>
+
+  <pre><code><span class="cm">// In context hook, append to systemPrompt</span>
+<span class="kw">const</span> honchoSection = [
+  <span class="str">"# Honcho memory integration"</span>,
+  <span class="str">`Active. Session: ${sessionKey}. Mode: ${mode}.`</span>,
+  <span class="str">"Management commands:"</span>,
+  <span class="str">"  openclaw honcho status                    — show config + connection"</span>,
+  <span class="str">"  openclaw honcho mode [hybrid|honcho|local] — show or set memory mode"</span>,
+  <span class="str">"  openclaw honcho sessions                  — list session mappings"</span>,
+  <span class="str">"  openclaw honcho map &lt;name&gt;                — map directory to session"</span>,
+  <span class="str">"  openclaw honcho identity [file] [--show]  — seed or show AI identity"</span>,
+  <span class="str">"  openclaw honcho setup                     — full interactive wizard"</span>,
+].join(<span class="str">"\n"</span>);</code></pre>
+
+  <div class="callout warn">
+    <strong>Keep it compact.</strong> This section is injected every turn. Keep it under 300 chars of context. List commands, not explanations — the agent can explain them on request.
+  </div>
+</section>
+
+<!-- OPENCLAW CHECKLIST -->
+<section id="openclaw-checklist">
+  <h2>openclaw-honcho checklist</h2>
+
+  <p>Ordered by impact. Each item maps to a spec section above.</p>
+
+  <ul class="checklist">
+    <li class="todo"><strong>Async prefetch</strong> — move <code>session.context()</code> out of <code>before_prompt_build</code> into post-<code>agent_end</code> background Promise. Pop from cache at prompt build. (<a href="#spec-async">spec</a>)</li>
+    <li class="todo"><strong>observe_me=True for agent peer</strong> — one-line change in <code>session.addPeers()</code> config for agent peer. (<a href="#spec-identity">spec</a>)</li>
+    <li class="todo"><strong>Dynamic reasoning level</strong> — add <code>dynamicReasoningLevel()</code> helper; apply in <code>honcho_recall</code> and <code>honcho_analyze</code>. Add <code>dialecticReasoningLevel</code> to config schema. (<a href="#spec-reasoning">spec</a>)</li>
+    <li class="todo"><strong>Per-peer memory modes</strong> — add <code>userMemoryMode</code> / <code>agentMemoryMode</code> to config; gate Honcho sync and local writes accordingly. (<a href="#spec-modes">spec</a>)</li>
+    <li class="todo"><strong>seedAiIdentity()</strong> — add helper; apply during setup migration for SOUL.md / IDENTITY.md instead of <code>session.uploadFile()</code>. (<a href="#spec-identity">spec</a>)</li>
+    <li class="todo"><strong>Session naming strategies</strong> — add <code>sessionStrategy</code>, <code>sessions</code> map, <code>sessionPeerPrefix</code> to config; implement resolution function. (<a href="#spec-sessions">spec</a>)</li>
+    <li class="todo"><strong>CLI surface injection</strong> — append command reference to <code>before_prompt_build</code> return value when Honcho is active. (<a href="#spec-cli">spec</a>)</li>
+    <li class="todo"><strong>honcho identity subcommand</strong> — add <code>openclaw honcho identity</code> CLI command. (<a href="#spec-identity">spec</a>)</li>
+    <li class="todo"><strong>AI peer name injection</strong> — if <code>aiPeer</code> name configured, prepend to injected system prompt. (<a href="#spec-identity">spec</a>)</li>
+    <li class="todo"><strong>honcho mode / honcho sessions / honcho map</strong> — CLI parity with Hermes. (<a href="#spec-sessions">spec</a>)</li>
+  </ul>
+
+  <div class="callout success">
+    <strong>Already done in openclaw-honcho (do not re-implement):</strong> lastSavedIndex dedup, platform metadata stripping, multi-agent parent observer hierarchy, peerPerspective on context(), tiered tool surface (fast/LLM), workspace agentPeerMap, QMD passthrough, self-hosted Honcho support.
+  </div>
+</section>
+
+<!-- NANOBOT CHECKLIST -->
+<section id="nanobot-checklist">
+  <h2>nanobot-honcho checklist</h2>
+
+  <p>nanobot-honcho is a greenfield integration. Start from openclaw-honcho's architecture (hook-based, dual peer) and apply all Hermes patterns from day one rather than retrofitting. Priority order:</p>
+
+  <h3>Phase 1 — core correctness</h3>
+  <ul class="checklist">
+    <li class="todo">Dual peer model (owner + agent peer), both with <code>observe_me=True</code></li>
+    <li class="todo">Message capture at turn end with <code>lastSavedIndex</code> dedup</li>
+    <li class="todo">Platform metadata stripping before Honcho storage</li>
+    <li class="todo">Async prefetch from day one — do not implement blocking context injection</li>
+    <li class="todo">Legacy file migration at first activation (USER.md → owner peer, SOUL.md → <code>seedAiIdentity()</code>)</li>
+  </ul>
+
+  <h3>Phase 2 — configuration</h3>
+  <ul class="checklist">
+    <li class="todo">Config schema: <code>apiKey</code>, <code>workspaceId</code>, <code>baseUrl</code>, <code>memoryMode</code>, <code>userMemoryMode</code>, <code>agentMemoryMode</code>, <code>dialecticReasoningLevel</code>, <code>sessionStrategy</code>, <code>sessions</code></li>
+    <li class="todo">Per-peer memory mode gating</li>
+    <li class="todo">Dynamic reasoning level</li>
+    <li class="todo">Session naming strategies</li>
+  </ul>
+
+  <h3>Phase 3 — tools and CLI</h3>
+  <ul class="checklist">
+    <li class="todo">Tool surface: <code>honcho_profile</code>, <code>honcho_recall</code>, <code>honcho_analyze</code>, <code>honcho_search</code>, <code>honcho_context</code></li>
+    <li class="todo">CLI: <code>setup</code>, <code>status</code>, <code>sessions</code>, <code>map</code>, <code>mode</code>, <code>identity</code></li>
+    <li class="todo">CLI surface injection into system prompt</li>
+    <li class="todo">AI peer name wired into agent identity</li>
+  </ul>
+</section>
+
+</div>
+
+<script type="module">
+  import mermaid from 'https://cdn.jsdelivr.net/npm/mermaid@11/dist/mermaid.esm.min.mjs';
+  mermaid.initialize({ startOnLoad: true, securityLevel: 'loose', fontFamily: 'Departure Mono, Noto Emoji, monospace' });
+</script>
+<script>
+  window.addEventListener('scroll', () => {
+    const bar = document.getElementById('progress');
+    const max = document.documentElement.scrollHeight - window.innerHeight;
+    bar.style.width = (max > 0 ? (window.scrollY / max) * 100 : 0) + '%';
+  });
+</script>
+</body>
+</html>

docs/honcho-integration-spec.md

@@ -0,0 +1,377 @@
+# honcho-integration-spec
+
+Comparison of Hermes Agent vs. openclaw-honcho — and a porting spec for bringing Hermes patterns into other Honcho integrations.
+
+---
+
+## Overview
+
+Two independent Honcho integrations have been built for two different agent runtimes: **Hermes Agent** (Python, baked into the runner) and **openclaw-honcho** (TypeScript plugin via hook/tool API). Both use the same Honcho peer paradigm — dual peer model, `session.context()`, `peer.chat()` — but they made different tradeoffs at every layer.
+
+This document maps those tradeoffs and defines a porting spec: a set of Hermes-originated patterns, each stated as an integration-agnostic interface, that any Honcho integration can adopt regardless of runtime or language.
+
+> **Scope** Both integrations work correctly today. This spec is about the delta — patterns in Hermes that are worth propagating and patterns in openclaw-honcho that Hermes should eventually adopt. The spec is additive, not prescriptive.
+
+---
+
+## Architecture comparison
+
+### Hermes: baked-in runner
+
+Honcho is initialised directly inside `AIAgent.__init__`. There is no plugin boundary. Session management, context injection, async prefetch, and CLI surface are all first-class concerns of the runner. Context is injected once per session (baked into `_cached_system_prompt`) and never re-fetched mid-session — this maximises prefix cache hits at the LLM provider.
+
+Turn flow:
+
+```
+user message
+  → _honcho_prefetch()       (reads cache — no HTTP)
+  → _build_system_prompt()   (first turn only, cached)
+  → LLM call
+  → response
+  → _honcho_fire_prefetch()  (daemon threads, turn end)
+       → prefetch_context() thread  ──┐
+       → prefetch_dialectic() thread ─┴→ _context_cache / _dialectic_cache
+```
+
+### openclaw-honcho: hook-based plugin
+
+The plugin registers hooks against OpenClaw's event bus. Context is fetched synchronously inside `before_prompt_build` on every turn. Message capture happens in `agent_end`. The multi-agent hierarchy is tracked via `subagent_spawned`. This model is correct but every turn pays a blocking Honcho round-trip before the LLM call can begin.
+
+Turn flow:
+
+```
+user message
+  → before_prompt_build (BLOCKING HTTP — every turn)
+       → session.context()
+  → system prompt assembled
+  → LLM call
+  → response
+  → agent_end hook
+       → session.addMessages()
+       → session.setMetadata()
+```
+
+---
+
+## Diff table
+
+| Dimension | Hermes Agent | openclaw-honcho |
+|---|---|---|
+| **Context injection timing** | Once per session (cached). Zero HTTP on response path after turn 1. | Every turn, blocking. Fresh context per turn but adds latency. |
+| **Prefetch strategy** | Daemon threads fire at turn end; consumed next turn from cache. | None. Blocking call at prompt-build time. |
+| **Dialectic (peer.chat)** | Prefetched async; result injected into system prompt next turn. | On-demand via `honcho_recall` / `honcho_analyze` tools. |
+| **Reasoning level** | Dynamic: scales with message length. Floor = config default. Cap = "high". | Fixed per tool: recall=minimal, analyze=medium. |
+| **Memory modes** | `user_memory_mode` / `agent_memory_mode`: hybrid / honcho / local. | None. Always writes to Honcho. |
+| **Write frequency** | async (background queue), turn, session, N turns. | After every agent_end (no control). |
+| **AI peer identity** | `observe_me=True`, `seed_ai_identity()`, `get_ai_representation()`, SOUL.md → AI peer. | Agent files uploaded to agent peer at setup. No ongoing self-observation. |
+| **Context scope** | User peer + AI peer representation, both injected. | User peer (owner) representation + conversation summary. `peerPerspective` on context call. |
+| **Session naming** | per-directory / global / manual map / title-based. | Derived from platform session key. |
+| **Multi-agent** | Single-agent only. | Parent observer hierarchy via `subagent_spawned`. |
+| **Tool surface** | Single `query_user_context` tool (on-demand dialectic). | 6 tools: session, profile, search, context (fast) + recall, analyze (LLM). |
+| **Platform metadata** | Not stripped. | Explicitly stripped before Honcho storage. |
+| **Message dedup** | None. | `lastSavedIndex` in session metadata prevents re-sending. |
+| **CLI surface in prompt** | Management commands injected into system prompt. Agent knows its own CLI. | Not injected. |
+| **AI peer name in identity** | Replaces "Hermes Agent" in DEFAULT_AGENT_IDENTITY when configured. | Not implemented. |
+| **QMD / local file search** | Not implemented. | Passthrough tools when QMD backend configured. |
+| **Workspace metadata** | Not implemented. | `agentPeerMap` in workspace metadata tracks agent→peer ID. |
+
+---
+
+## Patterns
+
+Six patterns from Hermes are worth adopting in any Honcho integration. Each is described as an integration-agnostic interface.
+
+**Hermes contributes:**
+- Async prefetch (zero-latency)
+- Dynamic reasoning level
+- Per-peer memory modes
+- AI peer identity formation
+- Session naming strategies
+- CLI surface injection
+
+**openclaw-honcho contributes back (Hermes should adopt):**
+- `lastSavedIndex` dedup
+- Platform metadata stripping
+- Multi-agent observer hierarchy
+- `peerPerspective` on `context()`
+- Tiered tool surface (fast/LLM)
+- Workspace `agentPeerMap`
+
+---
+
+## Spec: async prefetch
+
+### Problem
+
+Calling `session.context()` and `peer.chat()` synchronously before each LLM call adds 200–800ms of Honcho round-trip latency to every turn.
+
+### Pattern
+
+Fire both calls as non-blocking background work at the **end** of each turn. Store results in a per-session cache keyed by session ID. At the **start** of the next turn, pop from cache — the HTTP is already done. First turn is cold (empty cache); all subsequent turns are zero-latency on the response path.
+
+### Interface contract
+
+```typescript
+interface AsyncPrefetch {
+  // Fire context + dialectic fetches at turn end. Non-blocking.
+  firePrefetch(sessionId: string, userMessage: string): void;
+
+  // Pop cached results at turn start. Returns empty if cache is cold.
+  popContextResult(sessionId: string): ContextResult | null;
+  popDialecticResult(sessionId: string): string | null;
+}
+
+type ContextResult = {
+  representation: string;
+  card: string[];
+  aiRepresentation?: string;  // AI peer context if enabled
+  summary?: string;           // conversation summary if fetched
+};
+```
+
+### Implementation notes
+
+- **Python:** `threading.Thread(daemon=True)`. Write to `dict[session_id, result]` — GIL makes this safe for simple writes.
+- **TypeScript:** `Promise` stored in `Map<string, Promise<ContextResult>>`. Await at pop time. If not resolved yet, return null — do not block.
+- The pop is destructive: clears the cache entry after reading so stale data never accumulates.
+- Prefetch should also fire on first turn (even though it won't be consumed until turn 2).
+
+### openclaw-honcho adoption
+
+Move `session.context()` from `before_prompt_build` to a post-`agent_end` background task. Store result in `state.contextCache`. In `before_prompt_build`, read from cache instead of calling Honcho. If cache is empty (turn 1), inject nothing — the prompt is still valid without Honcho context on the first turn.
+
+---
+
+## Spec: dynamic reasoning level
+
+### Problem
+
+Honcho's dialectic endpoint supports reasoning levels from `minimal` to `max`. A fixed level per tool wastes budget on simple queries and under-serves complex ones.
+
+### Pattern
+
+Select the reasoning level dynamically based on the user's message. Use the configured default as a floor. Bump by message length. Cap auto-selection at `high` — never select `max` automatically.
+
+### Logic
+
+```
+< 120 chars  → default (typically "low")
+120–400 chars → one level above default (cap at "high")
+> 400 chars  → two levels above default (cap at "high")
+```
+
+### Config key
+
+Add `dialecticReasoningLevel` (string, default `"low"`). This sets the floor. The dynamic bump always applies on top.
+
+### openclaw-honcho adoption
+
+Apply in `honcho_recall` and `honcho_analyze`: replace fixed `reasoningLevel` with the dynamic selector. `honcho_recall` uses floor `"minimal"`, `honcho_analyze` uses floor `"medium"` — both still bump with message length.
+
+---
+
+## Spec: per-peer memory modes
+
+### Problem
+
+Users want independent control over whether user context and agent context are written locally, to Honcho, or both.
+
+### Modes
+
+| Mode | Effect |
+|---|---|
+| `hybrid` | Write to both local files and Honcho (default) |
+| `honcho` | Honcho only — disable corresponding local file writes |
+| `local` | Local files only — skip Honcho sync for this peer |
+
+### Config schema
+
+```json
+{
+  "memoryMode": "hybrid",
+  "userMemoryMode": "honcho",
+  "agentMemoryMode": "hybrid"
+}
+```
+
+Resolution order: per-peer field wins → shorthand `memoryMode` → default `"hybrid"`.
+
+### Effect on Honcho sync
+
+- `userMemoryMode=local`: skip adding user peer messages to Honcho
+- `agentMemoryMode=local`: skip adding assistant peer messages to Honcho
+- Both local: skip `session.addMessages()` entirely
+- `userMemoryMode=honcho`: disable local USER.md writes
+- `agentMemoryMode=honcho`: disable local MEMORY.md / SOUL.md writes
+
+---
+
+## Spec: AI peer identity formation
+
+### Problem
+
+Honcho builds the user's representation organically by observing what the user says. The same mechanism exists for the AI peer — but only if `observe_me=True` is set for the agent peer. Without it, the agent peer accumulates nothing.
+
+Additionally, existing persona files (SOUL.md, IDENTITY.md) should seed the AI peer's Honcho representation at first activation.
+
+### Part A: observe_me=True for agent peer
+
+```typescript
+await session.addPeers([
+  [ownerPeer.id, { observeMe: true,  observeOthers: false }],
+  [agentPeer.id, { observeMe: true,  observeOthers: true  }], // was false
+]);
+```
+
+One-line change. Foundational. Without it, the AI peer representation stays empty regardless of what the agent says.
+
+### Part B: seedAiIdentity()
+
+```typescript
+async function seedAiIdentity(
+  agentPeer: Peer,
+  content: string,
+  source: string
+): Promise<boolean> {
+  const wrapped = [
+    `<ai_identity_seed>`,
+    `<source>${source}</source>`,
+    ``,
+    content.trim(),
+    `</ai_identity_seed>`,
+  ].join("\n");
+
+  await agentPeer.addMessage("assistant", wrapped);
+  return true;
+}
+```
+
+### Part C: migrate agent files at setup
+
+During `honcho setup`, upload agent-self files (SOUL.md, IDENTITY.md, AGENTS.md) to the agent peer via `seedAiIdentity()` instead of `session.uploadFile()`. This routes content through Honcho's observation pipeline.
+
+### Part D: AI peer name in identity
+
+When the agent has a configured name, prepend it to the injected system prompt:
+
+```typescript
+const namePrefix = agentName ? `You are ${agentName}.\n\n` : "";
+return { systemPrompt: namePrefix + "## User Memory Context\n\n" + sections };
+```
+
+### CLI surface
+
+```
+honcho identity <file>    # seed from file
+honcho identity --show    # show current AI peer representation
+```
+
+---
+
+## Spec: session naming strategies
+
+### Problem
+
+A single global session means every project shares the same Honcho context. Per-directory sessions provide isolation without requiring users to name sessions manually.
+
+### Strategies
+
+| Strategy | Session key | When to use |
+|---|---|---|
+| `per-directory` | basename of CWD | Default. Each project gets its own session. |
+| `global` | fixed string `"global"` | Single cross-project session. |
+| manual map | user-configured per path | `sessions` config map overrides directory basename. |
+| title-based | sanitized session title | When agent supports named sessions set mid-conversation. |
+
+### Config schema
+
+```json
+{
+  "sessionStrategy": "per-directory",
+  "sessionPeerPrefix": false,
+  "sessions": {
+    "/home/user/projects/foo": "foo-project"
+  }
+}
+```
+
+### CLI surface
+
+```
+honcho sessions              # list all mappings
+honcho map <name>            # map cwd to session name
+honcho map                   # no-arg = list mappings
+```
+
+Resolution order: manual map → session title → directory basename → platform key.
+
+---
+
+## Spec: CLI surface injection
+
+### Problem
+
+When a user asks "how do I change my memory settings?" the agent either hallucinates or says it doesn't know. The agent should know its own management interface.
+
+### Pattern
+
+When Honcho is active, append a compact command reference to the system prompt. Keep it under 300 chars.
+
+```
+# Honcho memory integration
+Active. Session: {sessionKey}. Mode: {mode}.
+Management commands:
+  honcho status                    — show config + connection
+  honcho mode [hybrid|honcho|local] — show or set memory mode
+  honcho sessions                  — list session mappings
+  honcho map <name>                — map directory to session
+  honcho identity [file] [--show]  — seed or show AI identity
+  honcho setup                     — full interactive wizard
+```
+
+---
+
+## openclaw-honcho checklist
+
+Ordered by impact:
+
+- [ ] **Async prefetch** — move `session.context()` out of `before_prompt_build` into post-`agent_end` background Promise
+- [ ] **observe_me=True for agent peer** — one-line change in `session.addPeers()`
+- [ ] **Dynamic reasoning level** — add helper; apply in `honcho_recall` and `honcho_analyze`; add `dialecticReasoningLevel` to config
+- [ ] **Per-peer memory modes** — add `userMemoryMode` / `agentMemoryMode` to config; gate Honcho sync and local writes
+- [ ] **seedAiIdentity()** — add helper; use during setup migration for SOUL.md / IDENTITY.md
+- [ ] **Session naming strategies** — add `sessionStrategy`, `sessions` map, `sessionPeerPrefix`
+- [ ] **CLI surface injection** — append command reference to `before_prompt_build` return value
+- [ ] **honcho identity subcommand** — seed from file or `--show` current representation
+- [ ] **AI peer name injection** — if `aiPeer` name configured, prepend to injected system prompt
+- [ ] **honcho mode / sessions / map** — CLI parity with Hermes
+
+Already done in openclaw-honcho (do not re-implement): `lastSavedIndex` dedup, platform metadata stripping, multi-agent parent observer, `peerPerspective` on `context()`, tiered tool surface, workspace `agentPeerMap`, QMD passthrough, self-hosted Honcho.
+
+---
+
+## nanobot-honcho checklist
+
+Greenfield integration. Start from openclaw-honcho's architecture and apply all Hermes patterns from day one.
+
+### Phase 1 — core correctness
+
+- [ ] Dual peer model (owner + agent peer), both with `observe_me=True`
+- [ ] Message capture at turn end with `lastSavedIndex` dedup
+- [ ] Platform metadata stripping before Honcho storage
+- [ ] Async prefetch from day one — do not implement blocking context injection
+- [ ] Legacy file migration at first activation (USER.md → owner peer, SOUL.md → `seedAiIdentity()`)
+
+### Phase 2 — configuration
+
+- [ ] Config schema: `apiKey`, `workspaceId`, `baseUrl`, `memoryMode`, `userMemoryMode`, `agentMemoryMode`, `dialecticReasoningLevel`, `sessionStrategy`, `sessions`
+- [ ] Per-peer memory mode gating
+- [ ] Dynamic reasoning level
+- [ ] Session naming strategies
+
+### Phase 3 — tools and CLI
+
+- [ ] Tool surface: `honcho_profile`, `honcho_recall`, `honcho_analyze`, `honcho_search`, `honcho_context`
+- [ ] CLI: `setup`, `status`, `sessions`, `map`, `mode`, `identity`
+- [ ] CLI surface injection into system prompt
+- [ ] AI peer name wired into agent identity

docs/migration/openclaw.md

@@ -0,0 +1,110 @@
+# Migrating from OpenClaw to Hermes Agent
+
+This guide covers how to import your OpenClaw settings, memories, skills, and API keys into Hermes Agent.
+
+## Three Ways to Migrate
+
+### 1. Automatic (during first-time setup)
+
+When you run `hermes setup` for the first time and Hermes detects `~/.openclaw`, it automatically offers to import your OpenClaw data before configuration begins. Just accept the prompt and everything is handled for you.
+
+### 2. CLI Command (quick, scriptable)
+
+```bash
+hermes claw migrate                      # Full migration with confirmation prompt
+hermes claw migrate --dry-run            # Preview what would happen
+hermes claw migrate --preset user-data   # Migrate without API keys/secrets
+hermes claw migrate --yes                # Skip confirmation prompt
+```
+
+**All options:**
+
+| Flag | Description |
+|------|-------------|
+| `--source PATH` | Path to OpenClaw directory (default: `~/.openclaw`) |
+| `--dry-run` | Preview only — no files are modified |
+| `--preset {user-data,full}` | Migration preset (default: `full`). `user-data` excludes secrets |
+| `--overwrite` | Overwrite existing files (default: skip conflicts) |
+| `--migrate-secrets` | Include allowlisted secrets (auto-enabled with `full` preset) |
+| `--workspace-target PATH` | Copy workspace instructions (AGENTS.md) to this absolute path |
+| `--skill-conflict {skip,overwrite,rename}` | How to handle skill name conflicts (default: `skip`) |
+| `--yes`, `-y` | Skip confirmation prompts |
+
+### 3. Agent-Guided (interactive, with previews)
+
+Ask the agent to run the migration for you:
+
+```
+> Migrate my OpenClaw setup to Hermes
+```
+
+The agent will use the `openclaw-migration` skill to:
+1. Run a dry-run first to preview changes
+2. Ask about conflict resolution (SOUL.md, skills, etc.)
+3. Let you choose between `user-data` and `full` presets
+4. Execute the migration with your choices
+5. Print a detailed summary of what was migrated
+
+## What Gets Migrated
+
+### `user-data` preset
+| Item | Source | Destination |
+|------|--------|-------------|
+| SOUL.md | `~/.openclaw/workspace/SOUL.md` | `~/.hermes/SOUL.md` |
+| Memory entries | `~/.openclaw/workspace/MEMORY.md` | `~/.hermes/memories/MEMORY.md` |
+| User profile | `~/.openclaw/workspace/USER.md` | `~/.hermes/memories/USER.md` |
+| Skills | `~/.openclaw/workspace/skills/` | `~/.hermes/skills/openclaw-imports/` |
+| Command allowlist | `~/.openclaw/workspace/exec_approval_patterns.yaml` | Merged into `~/.hermes/config.yaml` |
+| Messaging settings | `~/.openclaw/config.yaml` (TELEGRAM_ALLOWED_USERS, MESSAGING_CWD) | `~/.hermes/.env` |
+| TTS assets | `~/.openclaw/workspace/tts/` | `~/.hermes/tts/` |
+
+### `full` preset (adds to `user-data`)
+| Item | Source | Destination |
+|------|--------|-------------|
+| Telegram bot token | `~/.openclaw/config.yaml` | `~/.hermes/.env` |
+| OpenRouter API key | `~/.openclaw/.env` or config | `~/.hermes/.env` |
+| OpenAI API key | `~/.openclaw/.env` or config | `~/.hermes/.env` |
+| Anthropic API key | `~/.openclaw/.env` or config | `~/.hermes/.env` |
+| ElevenLabs API key | `~/.openclaw/.env` or config | `~/.hermes/.env` |
+
+Only these 6 allowlisted secrets are ever imported. Other credentials are skipped and reported.
+
+## Conflict Handling
+
+By default, the migration **will not overwrite** existing Hermes data:
+
+- **SOUL.md** — skipped if one already exists in `~/.hermes/`
+- **Memory entries** — skipped if memories already exist (to avoid duplicates)
+- **Skills** — skipped if a skill with the same name already exists
+- **API keys** — skipped if the key is already set in `~/.hermes/.env`
+
+To overwrite conflicts, use `--overwrite`. The migration creates backups before overwriting.
+
+For skills, you can also use `--skill-conflict rename` to import conflicting skills under a new name (e.g., `skill-name-imported`).
+
+## Migration Report
+
+Every migration (including dry runs) produces a report showing:
+- **Migrated items** — what was successfully imported
+- **Conflicts** — items skipped because they already exist
+- **Skipped items** — items not found in the source
+- **Errors** — items that failed to import
+
+For execute runs, the full report is saved to `~/.hermes/migration/openclaw/<timestamp>/`.
+
+## Troubleshooting
+
+### "OpenClaw directory not found"
+The migration looks for `~/.openclaw` by default. If your OpenClaw is installed elsewhere, use `--source`:
+```bash
+hermes claw migrate --source /path/to/.openclaw
+```
+
+### "Migration script not found"
+The migration script ships with Hermes Agent. If you installed via pip (not git clone), the `optional-skills/` directory may not be present. Install the skill from the Skills Hub:
+```bash
+hermes skills install openclaw-migration
+```
+
+### Memory overflow
+If your OpenClaw MEMORY.md or USER.md exceeds Hermes' character limits, excess entries are exported to an overflow file in the migration report directory. You can manually review and add the most important ones.

docs/plans/2026-03-16-pricing-accuracy-architecture-design.md

@@ -0,0 +1,608 @@
+# Pricing Accuracy Architecture
+
+Date: 2026-03-16
+
+## Goal
+
+Hermes should only show dollar costs when they are backed by an official source for the user's actual billing path.
+
+This design replaces the current static, heuristic pricing flow in:
+
+- `run_agent.py`
+- `agent/usage_pricing.py`
+- `agent/insights.py`
+- `cli.py`
+
+with a provider-aware pricing system that:
+
+- handles cache billing correctly
+- distinguishes `actual` vs `estimated` vs `included` vs `unknown`
+- reconciles post-hoc costs when providers expose authoritative billing data
+- supports direct providers, OpenRouter, subscriptions, enterprise pricing, and custom endpoints
+
+## Problems In The Current Design
+
+Current Hermes behavior has four structural issues:
+
+1. It stores only `prompt_tokens` and `completion_tokens`, which is insufficient for providers that bill cache reads and cache writes separately.
+2. It uses a static model price table and fuzzy heuristics, which can drift from current official pricing.
+3. It assumes public API list pricing matches the user's real billing path.
+4. It has no distinction between live estimates and reconciled billed cost.
+
+## Design Principles
+
+1. Normalize usage before pricing.
+2. Never fold cached tokens into plain input cost.
+3. Track certainty explicitly.
+4. Treat the billing path as part of the model identity.
+5. Prefer official machine-readable sources over scraped docs.
+6. Use post-hoc provider cost APIs when available.
+7. Show `n/a` rather than inventing precision.
+
+## High-Level Architecture
+
+The new system has four layers:
+
+1. `usage_normalization`
+   Converts raw provider usage into a canonical usage record.
+2. `pricing_source_resolution`
+   Determines the billing path, source of truth, and applicable pricing source.
+3. `cost_estimation_and_reconciliation`
+   Produces an immediate estimate when possible, then replaces or annotates it with actual billed cost later.
+4. `presentation`
+   `/usage`, `/insights`, and the status bar display cost with certainty metadata.
+
+## Canonical Usage Record
+
+Add a canonical usage model that every provider path maps into before any pricing math happens.
+
+Suggested structure:
+
+```python
+@dataclass
+class CanonicalUsage:
+    provider: str
+    billing_provider: str
+    model: str
+    billing_route: str
+
+    input_tokens: int = 0
+    output_tokens: int = 0
+    cache_read_tokens: int = 0
+    cache_write_tokens: int = 0
+    reasoning_tokens: int = 0
+    request_count: int = 1
+
+    raw_usage: dict[str, Any] | None = None
+    raw_usage_fields: dict[str, str] | None = None
+    computed_fields: set[str] | None = None
+
+    provider_request_id: str | None = None
+    provider_generation_id: str | None = None
+    provider_response_id: str | None = None
+```
+
+Rules:
+
+- `input_tokens` means non-cached input only.
+- `cache_read_tokens` and `cache_write_tokens` are never merged into `input_tokens`.
+- `output_tokens` excludes cache metrics.
+- `reasoning_tokens` is telemetry unless a provider officially bills it separately.
+
+This is the same normalization pattern used by `opencode`, extended with provenance and reconciliation ids.
+
+## Provider Normalization Rules
+
+### OpenAI Direct
+
+Source usage fields:
+
+- `prompt_tokens`
+- `completion_tokens`
+- `prompt_tokens_details.cached_tokens`
+
+Normalization:
+
+- `cache_read_tokens = cached_tokens`
+- `input_tokens = prompt_tokens - cached_tokens`
+- `cache_write_tokens = 0` unless OpenAI exposes it in the relevant route
+- `output_tokens = completion_tokens`
+
+### Anthropic Direct
+
+Source usage fields:
+
+- `input_tokens`
+- `output_tokens`
+- `cache_read_input_tokens`
+- `cache_creation_input_tokens`
+
+Normalization:
+
+- `input_tokens = input_tokens`
+- `output_tokens = output_tokens`
+- `cache_read_tokens = cache_read_input_tokens`
+- `cache_write_tokens = cache_creation_input_tokens`
+
+### OpenRouter
+
+Estimate-time usage normalization should use the response usage payload with the same rules as the underlying provider when possible.
+
+Reconciliation-time records should also store:
+
+- OpenRouter generation id
+- native token fields when available
+- `total_cost`
+- `cache_discount`
+- `upstream_inference_cost`
+- `is_byok`
+
+### Gemini / Vertex
+
+Use official Gemini or Vertex usage fields where available.
+
+If cached content tokens are exposed:
+
+- map them to `cache_read_tokens`
+
+If a route exposes no cache creation metric:
+
+- store `cache_write_tokens = 0`
+- preserve the raw usage payload for later extension
+
+### DeepSeek And Other Direct Providers
+
+Normalize only the fields that are officially exposed.
+
+If a provider does not expose cache buckets:
+
+- do not infer them unless the provider explicitly documents how to derive them
+
+### Subscription / Included-Cost Routes
+
+These still use the canonical usage model.
+
+Tokens are tracked normally. Cost depends on billing mode, not on whether usage exists.
+
+## Billing Route Model
+
+Hermes must stop keying pricing solely by `model`.
+
+Introduce a billing route descriptor:
+
+```python
+@dataclass
+class BillingRoute:
+    provider: str
+    base_url: str | None
+    model: str
+    billing_mode: str
+    organization_hint: str | None = None
+```
+
+`billing_mode` values:
+
+- `official_cost_api`
+- `official_generation_api`
+- `official_models_api`
+- `official_docs_snapshot`
+- `subscription_included`
+- `user_override`
+- `custom_contract`
+- `unknown`
+
+Examples:
+
+- OpenAI direct API with Costs API access: `official_cost_api`
+- Anthropic direct API with Usage & Cost API access: `official_cost_api`
+- OpenRouter request before reconciliation: `official_models_api`
+- OpenRouter request after generation lookup: `official_generation_api`
+- GitHub Copilot style subscription route: `subscription_included`
+- local OpenAI-compatible server: `unknown`
+- enterprise contract with configured rates: `custom_contract`
+
+## Cost Status Model
+
+Every displayed cost should have:
+
+```python
+@dataclass
+class CostResult:
+    amount_usd: Decimal | None
+    status: Literal["actual", "estimated", "included", "unknown"]
+    source: Literal[
+        "provider_cost_api",
+        "provider_generation_api",
+        "provider_models_api",
+        "official_docs_snapshot",
+        "user_override",
+        "custom_contract",
+        "none",
+    ]
+    label: str
+    fetched_at: datetime | None
+    pricing_version: str | None
+    notes: list[str]
+```
+
+Presentation rules:
+
+- `actual`: show dollar amount as final
+- `estimated`: show dollar amount with estimate labeling
+- `included`: show `included` or `$0.00 (included)` depending on UX choice
+- `unknown`: show `n/a`
+
+## Official Source Hierarchy
+
+Resolve cost using this order:
+
+1. Request-level or account-level official billed cost
+2. Official machine-readable model pricing
+3. Official docs snapshot
+4. User override or custom contract
+5. Unknown
+
+The system must never skip to a lower level if a higher-confidence source exists for the current billing route.
+
+## Provider-Specific Truth Rules
+
+### OpenAI Direct
+
+Preferred truth:
+
+1. Costs API for reconciled spend
+2. Official pricing page for live estimate
+
+### Anthropic Direct
+
+Preferred truth:
+
+1. Usage & Cost API for reconciled spend
+2. Official pricing docs for live estimate
+
+### OpenRouter
+
+Preferred truth:
+
+1. `GET /api/v1/generation` for reconciled `total_cost`
+2. `GET /api/v1/models` pricing for live estimate
+
+Do not use underlying provider public pricing as the source of truth for OpenRouter billing.
+
+### Gemini / Vertex
+
+Preferred truth:
+
+1. official billing export or billing API for reconciled spend when available for the route
+2. official pricing docs for estimate
+
+### DeepSeek
+
+Preferred truth:
+
+1. official machine-readable cost source if available in the future
+2. official pricing docs snapshot today
+
+### Subscription-Included Routes
+
+Preferred truth:
+
+1. explicit route config marking the model as included in subscription
+
+These should display `included`, not an API list-price estimate.
+
+### Custom Endpoint / Local Model
+
+Preferred truth:
+
+1. user override
+2. custom contract config
+3. unknown
+
+These should default to `unknown`.
+
+## Pricing Catalog
+
+Replace the current `MODEL_PRICING` dict with a richer pricing catalog.
+
+Suggested record:
+
+```python
+@dataclass
+class PricingEntry:
+    provider: str
+    route_pattern: str
+    model_pattern: str
+
+    input_cost_per_million: Decimal | None = None
+    output_cost_per_million: Decimal | None = None
+    cache_read_cost_per_million: Decimal | None = None
+    cache_write_cost_per_million: Decimal | None = None
+    request_cost: Decimal | None = None
+    image_cost: Decimal | None = None
+
+    source: str = "official_docs_snapshot"
+    source_url: str | None = None
+    fetched_at: datetime | None = None
+    pricing_version: str | None = None
+```
+
+The catalog should be route-aware:
+
+- `openai:gpt-5`
+- `anthropic:claude-opus-4-6`
+- `openrouter:anthropic/claude-opus-4.6`
+- `copilot:gpt-4o`
+
+This avoids conflating direct-provider billing with aggregator billing.
+
+## Pricing Sync Architecture
+
+Introduce a pricing sync subsystem instead of manually maintaining a single hardcoded table.
+
+Suggested modules:
+
+- `agent/pricing/catalog.py`
+- `agent/pricing/sources.py`
+- `agent/pricing/sync.py`
+- `agent/pricing/reconcile.py`
+- `agent/pricing/types.py`
+
+### Sync Sources
+
+- OpenRouter models API
+- official provider docs snapshots where no API exists
+- user overrides from config
+
+### Sync Output
+
+Cache pricing entries locally with:
+
+- source URL
+- fetch timestamp
+- version/hash
+- confidence/source type
+
+### Sync Frequency
+
+- startup warm cache
+- background refresh every 6 to 24 hours depending on source
+- manual `hermes pricing sync`
+
+## Reconciliation Architecture
+
+Live requests may produce only an estimate initially. Hermes should reconcile them later when a provider exposes actual billed cost.
+
+Suggested flow:
+
+1. Agent call completes.
+2. Hermes stores canonical usage plus reconciliation ids.
+3. Hermes computes an immediate estimate if a pricing source exists.
+4. A reconciliation worker fetches actual cost when supported.
+5. Session and message records are updated with `actual` cost.
+
+This can run:
+
+- inline for cheap lookups
+- asynchronously for delayed provider accounting
+
+## Persistence Changes
+
+Session storage should stop storing only aggregate prompt/completion totals.
+
+Add fields for both usage and cost certainty:
+
+- `input_tokens`
+- `output_tokens`
+- `cache_read_tokens`
+- `cache_write_tokens`
+- `reasoning_tokens`
+- `estimated_cost_usd`
+- `actual_cost_usd`
+- `cost_status`
+- `cost_source`
+- `pricing_version`
+- `billing_provider`
+- `billing_mode`
+
+If schema expansion is too large for one PR, add a new pricing events table:
+
+```text
+session_cost_events
+  id
+  session_id
+  request_id
+  provider
+  model
+  billing_mode
+  input_tokens
+  output_tokens
+  cache_read_tokens
+  cache_write_tokens
+  estimated_cost_usd
+  actual_cost_usd
+  cost_status
+  cost_source
+  pricing_version
+  created_at
+  updated_at
+```
+
+## Hermes Touchpoints
+
+### `run_agent.py`
+
+Current responsibility:
+
+- parse raw provider usage
+- update session token counters
+
+New responsibility:
+
+- build `CanonicalUsage`
+- update canonical counters
+- store reconciliation ids
+- emit usage event to pricing subsystem
+
+### `agent/usage_pricing.py`
+
+Current responsibility:
+
+- static lookup table
+- direct cost arithmetic
+
+New responsibility:
+
+- move or replace with pricing catalog facade
+- no fuzzy model-family heuristics
+- no direct pricing without billing-route context
+
+### `cli.py`
+
+Current responsibility:
+
+- compute session cost directly from prompt/completion totals
+
+New responsibility:
+
+- display `CostResult`
+- show status badges:
+  - `actual`
+  - `estimated`
+  - `included`
+  - `n/a`
+
+### `agent/insights.py`
+
+Current responsibility:
+
+- recompute historical estimates from static pricing
+
+New responsibility:
+
+- aggregate stored pricing events
+- prefer actual cost over estimate
+- surface estimates only when reconciliation is unavailable
+
+## UX Rules
+
+### Status Bar
+
+Show one of:
+
+- `$1.42`
+- `~$1.42`
+- `included`
+- `cost n/a`
+
+Where:
+
+- `$1.42` means `actual`
+- `~$1.42` means `estimated`
+- `included` means subscription-backed or explicitly zero-cost route
+- `cost n/a` means unknown
+
+### `/usage`
+
+Show:
+
+- token buckets
+- estimated cost
+- actual cost if available
+- cost status
+- pricing source
+
+### `/insights`
+
+Aggregate:
+
+- actual cost totals
+- estimated-only totals
+- unknown-cost sessions count
+- included-cost sessions count
+
+## Config And Overrides
+
+Add user-configurable pricing overrides in config:
+
+```yaml
+pricing:
+  mode: hybrid
+  sync_on_startup: true
+  sync_interval_hours: 12
+  overrides:
+    - provider: openrouter
+      model: anthropic/claude-opus-4.6
+      billing_mode: custom_contract
+      input_cost_per_million: 4.25
+      output_cost_per_million: 22.0
+      cache_read_cost_per_million: 0.5
+      cache_write_cost_per_million: 6.0
+  included_routes:
+    - provider: copilot
+      model: "*"
+    - provider: codex-subscription
+      model: "*"
+```
+
+Overrides must win over catalog defaults for the matching billing route.
+
+## Rollout Plan
+
+### Phase 1
+
+- add canonical usage model
+- split cache token buckets in `run_agent.py`
+- stop pricing cache-inflated prompt totals
+- preserve current UI with improved backend math
+
+### Phase 2
+
+- add route-aware pricing catalog
+- integrate OpenRouter models API sync
+- add `estimated` vs `included` vs `unknown`
+
+### Phase 3
+
+- add reconciliation for OpenRouter generation cost
+- add actual cost persistence
+- update `/insights` to prefer actual cost
+
+### Phase 4
+
+- add direct OpenAI and Anthropic reconciliation paths
+- add user overrides and contract pricing
+- add pricing sync CLI command
+
+## Testing Strategy
+
+Add tests for:
+
+- OpenAI cached token subtraction
+- Anthropic cache read/write separation
+- OpenRouter estimated vs actual reconciliation
+- subscription-backed models showing `included`
+- custom endpoints showing `n/a`
+- override precedence
+- stale catalog fallback behavior
+
+Current tests that assume heuristic pricing should be replaced with route-aware expectations.
+
+## Non-Goals
+
+- exact enterprise billing reconstruction without an official source or user override
+- backfilling perfect historical cost for old sessions that lack cache bucket data
+- scraping arbitrary provider web pages at request time
+
+## Recommendation
+
+Do not expand the existing `MODEL_PRICING` dict.
+
+That path cannot satisfy the product requirement. Hermes should instead migrate to:
+
+- canonical usage normalization
+- route-aware pricing sources
+- estimate-then-reconcile cost lifecycle
+- explicit certainty states in the UI
+
+This is the minimum architecture that makes the statement "Hermes pricing is backed by official sources where possible, and otherwise clearly labeled" defensible.

docs/skins/example-skin.yaml

@@ -0,0 +1,89 @@
+# ============================================================================
+# Hermes Agent — Example Skin Template
+# ============================================================================
+#
+# Copy this file to ~/.hermes/skins/<name>.yaml to create a custom skin.
+# All fields are optional — missing values inherit from the default skin.
+# Activate with: /skin <name>  or  display.skin: <name> in config.yaml
+#
+# See hermes_cli/skin_engine.py for the full schema reference.
+# ============================================================================
+
+# Required: unique skin name (used in /skin command and config)
+name: example
+description: An example custom skin — copy and modify this template
+
+# ── Colors ──────────────────────────────────────────────────────────────────
+# Hex color values for Rich markup. These control the CLI's visual palette.
+colors:
+  # Banner panel (the startup welcome box)
+  banner_border: "#CD7F32"        # Panel border
+  banner_title: "#FFD700"         # Panel title text
+  banner_accent: "#FFBF00"        # Section headers (Available Tools, Skills, etc.)
+  banner_dim: "#B8860B"           # Dim/muted text (separators, model info)
+  banner_text: "#FFF8DC"          # Body text (tool names, skill names)
+
+  # UI elements
+  ui_accent: "#FFBF00"            # General accent color
+  ui_label: "#4dd0e1"             # Labels
+  ui_ok: "#4caf50"                # Success indicators
+  ui_error: "#ef5350"             # Error indicators
+  ui_warn: "#ffa726"              # Warning indicators
+
+  # Input area
+  prompt: "#FFF8DC"               # Prompt text color
+  input_rule: "#CD7F32"           # Horizontal rule around input
+
+  # Response box
+  response_border: "#FFD700"      # Response box border (ANSI color)
+
+  # Session display
+  session_label: "#DAA520"        # Session label
+  session_border: "#8B8682"       # Session ID dim color
+
+# ── Spinner ─────────────────────────────────────────────────────────────────
+# Customize the animated spinner shown during API calls and tool execution.
+spinner:
+  # Faces shown while waiting for the API response
+  waiting_faces:
+    - "(｡◕‿◕｡)"
+    - "(◕‿◕✿)"
+    - "٩(◕‿◕｡)۶"
+
+  # Faces shown during extended thinking/reasoning
+  thinking_faces:
+    - "(｡•́︿•̀｡)"
+    - "(◔_◔)"
+    - "(¬‿¬)"
+
+  # Verbs used in spinner messages (e.g., "pondering your request...")
+  thinking_verbs:
+    - "pondering"
+    - "contemplating"
+    - "musing"
+    - "ruminating"
+
+  # Optional: left/right decorations around the spinner
+  # Each entry is a [left, right] pair. Omit entirely for no wings.
+  # wings:
+  #   - ["⟪⚔", "⚔⟫"]
+  #   - ["⟪▲", "▲⟫"]
+
+# ── Branding ────────────────────────────────────────────────────────────────
+# Text strings used throughout the CLI interface.
+branding:
+  agent_name: "Hermes Agent"          # Banner title, about display
+  welcome: "Welcome! Type your message or /help for commands."
+  goodbye: "Goodbye! ⚕"              # Exit message
+  response_label: " ⚕ Hermes "       # Response box header label
+  prompt_symbol: "❯ "                 # Input prompt symbol
+  help_header: "(^_^)? Available Commands"  # /help header text
+
+# ── Tool Output ─────────────────────────────────────────────────────────────
+# Character used as the prefix for tool output lines.
+# Default is "┊" (thin dotted vertical line). Some alternatives:
+#   "╎" (light triple dash vertical)
+#   "▏" (left one-eighth block)
+#   "│" (box drawing light vertical)
+#   "┃" (box drawing heavy vertical)
+tool_prefix: "┊"

environments/README.md

@@ -101,21 +101,11 @@ Available methods:
 
 ### Patches (`patches.py`)
 
-**Problem**: Some hermes-agent tools use `asyncio.run()` internally (e.g., mini-swe-agent's Modal backend via SWE-ReX). This crashes when called from inside Atropos's event loop because `asyncio.run()` cannot be nested.
+**Problem**: Some hermes-agent tools use `asyncio.run()` internally (e.g., the Modal backend). This crashes when called from inside Atropos's event loop because `asyncio.run()` cannot be nested.
 
-**Solution**: `patches.py` monkey-patches `SwerexModalEnvironment` to use a dedicated background thread (`_AsyncWorker`) with its own event loop. The calling code sees the same sync interface, but internally the async work happens on a separate thread that doesn't conflict with Atropos's loop.
+**Solution**: `ModalEnvironment` uses a dedicated `_AsyncWorker` background thread with its own event loop. The calling code sees a sync interface, but internally all async Modal SDK calls happen on the worker thread so they don't conflict with Atropos's loop. This is built directly into `tools/environments/modal.py` — no monkey-patching required.
 
-What gets patched:
-- `SwerexModalEnvironment.__init__` -- creates Modal deployment on a background thread
-- `SwerexModalEnvironment.execute` -- runs commands on the same background thread
-- `SwerexModalEnvironment.stop` -- stops deployment on the background thread
-
-The patches are:
-- **Idempotent** -- calling `apply_patches()` multiple times is safe
-- **Transparent** -- same interface and behavior, only the internal async execution changes
-- **Universal** -- works identically in normal CLI use (no running event loop)
-
-Applied automatically at import time by `hermes_base_env.py`.
+`patches.py` is now a no-op (kept for backward compatibility with imports).
 
 ### Tool Call Parsers (`tool_call_parsers/`)
 

environments/__init__.py

@@ -18,9 +18,14 @@ Benchmarks (eval-only):
     - benchmarks/terminalbench_2/: Terminal-Bench 2.0 evaluation
 """
 
-from environments.agent_loop import AgentResult, HermesAgentLoop
-from environments.tool_context import ToolContext
-from environments.hermes_base_env import HermesAgentBaseEnv, HermesAgentEnvConfig
+try:
+    from environments.agent_loop import AgentResult, HermesAgentLoop
+    from environments.tool_context import ToolContext
+    from environments.hermes_base_env import HermesAgentBaseEnv, HermesAgentEnvConfig
+except ImportError:
+    # atroposlib not installed — environments are unavailable but
+    # submodules like tool_call_parsers can still be imported directly.
+    pass
 
 __all__ = [
     "AgentResult",

environments/agent_loop.py

@@ -23,7 +23,7 @@ from typing import Any, Dict, List, Optional, Set
 from model_tools import handle_function_call
 
 # Thread pool for running sync tool calls that internally use asyncio.run()
-# (e.g., mini-swe-agent's modal/docker/daytona backends). Running them in a separate
+# (e.g., the Modal/Docker/Daytona terminal backends). Running them in a separate
 # thread gives them a clean event loop so they don't deadlock inside Atropos's loop.
 # Size must be large enough for concurrent eval tasks (e.g., 89 TB2 tasks all
 # making tool calls). Too small = thread pool starvation, tasks queue for minutes.
@@ -39,7 +39,9 @@ def resize_tool_pool(max_workers: int):
     Safe to call before any tasks are submitted.
     """
     global _tool_executor
+    old_executor = _tool_executor
     _tool_executor = concurrent.futures.ThreadPoolExecutor(max_workers=max_workers)
+    old_executor.shutdown(wait=False)
     logger.info("Tool thread pool resized to %d workers", max_workers)
 
 logger = logging.getLogger(__name__)
@@ -249,23 +251,62 @@ class HermesAgentLoop:
             reasoning = _extract_reasoning_from_message(assistant_msg)
             reasoning_per_turn.append(reasoning)
 
-            # Check for tool calls -- standard OpenAI spec
+            # Check for tool calls -- standard OpenAI spec.
+            # Fallback: if response has no structured tool_calls but content
+            # contains raw tool call tags (e.g. <tool_call>), parse them using
+            # hermes-agent's standalone parsers. This handles the case where
+            # ManagedServer's ToolCallTranslator couldn't parse because vLLM
+            # isn't installed.
+            if (
+                not assistant_msg.tool_calls
+                and assistant_msg.content
+                and self.tool_schemas
+                and "<tool_call>" in (assistant_msg.content or "")
+            ):
+                try:
+                    from environments.tool_call_parsers import get_parser
+                    fallback_parser = get_parser("hermes")
+                    parsed_content, parsed_calls = fallback_parser.parse(
+                        assistant_msg.content
+                    )
+                    if parsed_calls:
+                        assistant_msg.tool_calls = parsed_calls
+                        if parsed_content is not None:
+                            assistant_msg.content = parsed_content
+                        logger.debug(
+                            "Fallback parser extracted %d tool calls from raw content",
+                            len(parsed_calls),
+                        )
+                except Exception:
+                    pass  # Fall through to no tool calls
+
             if assistant_msg.tool_calls:
+                # Normalize tool calls to dicts — they may come as objects
+                # (OpenAI API) or dicts (vLLM ToolCallTranslator).
+                def _tc_to_dict(tc):
+                    if isinstance(tc, dict):
+                        return {
+                            "id": tc.get("id", f"call_{uuid.uuid4().hex[:8]}"),
+                            "type": "function",
+                            "function": {
+                                "name": tc.get("function", {}).get("name", tc.get("name", "")),
+                                "arguments": tc.get("function", {}).get("arguments", tc.get("arguments", "{}")),
+                            },
+                        }
+                    return {
+                        "id": tc.id,
+                        "type": "function",
+                        "function": {
+                            "name": tc.function.name,
+                            "arguments": tc.function.arguments,
+                        },
+                    }
+
                 # Build the assistant message dict for conversation history
                 msg_dict: Dict[str, Any] = {
                     "role": "assistant",
                     "content": assistant_msg.content or "",
-                    "tool_calls": [
-                        {
-                            "id": tc.id,
-                            "type": "function",
-                            "function": {
-                                "name": tc.function.name,
-                                "arguments": tc.function.arguments,
-                            },
-                        }
-                        for tc in assistant_msg.tool_calls
-                    ],
+                    "tool_calls": [_tc_to_dict(tc) for tc in assistant_msg.tool_calls],
                 }
 
                 # Preserve reasoning_content for multi-turn chat template handling
@@ -278,8 +319,13 @@ class HermesAgentLoop:
 
                 # Execute each tool call via hermes-agent's dispatch
                 for tc in assistant_msg.tool_calls:
-                    tool_name = tc.function.name
-                    tool_args_raw = tc.function.arguments
+                    # Handle both object (OpenAI) and dict (vLLM) formats
+                    if isinstance(tc, dict):
+                        tool_name = tc.get("function", {}).get("name", tc.get("name", ""))
+                        tool_args_raw = tc.get("function", {}).get("arguments", tc.get("arguments", "{}"))
+                    else:
+                        tool_name = tc.function.name
+                        tool_args_raw = tc.function.arguments
 
                     # Validate tool name
                     if tool_name not in self.valid_tool_names:
@@ -300,78 +346,89 @@ class HermesAgentLoop:
                             tool_name, turn + 1,
                         )
                     else:
-                        # Parse arguments and dispatch
+                        # Parse arguments
                         try:
                             args = json.loads(tool_args_raw)
-                        except json.JSONDecodeError:
-                            args = {}
+                        except json.JSONDecodeError as e:
+                            args = None
+                            tool_result = json.dumps(
+                                {"error": f"Invalid JSON in tool arguments: {e}. Please retry with valid JSON."}
+                            )
+                            tool_errors.append(ToolError(
+                                turn=turn + 1, tool_name=tool_name,
+                                arguments=tool_args_raw[:200],
+                                error=f"Invalid JSON: {e}",
+                                tool_result=tool_result,
+                            ))
                             logger.warning(
                                 "Invalid JSON in tool call arguments for '%s': %s",
                                 tool_name, tool_args_raw[:200],
                             )
 
-                        try:
-                            if tool_name == "terminal":
-                                backend = os.getenv("TERMINAL_ENV", "local")
-                                cmd_preview = args.get("command", "")[:80]
-                                logger.info(
-                                    "[%s] $ %s", self.task_id[:8], cmd_preview,
-                                )
+                        # Dispatch tool only if arguments parsed successfully
+                        if args is not None:
+                            try:
+                                if tool_name == "terminal":
+                                    backend = os.getenv("TERMINAL_ENV", "local")
+                                    cmd_preview = args.get("command", "")[:80]
+                                    logger.info(
+                                        "[%s] $ %s", self.task_id[:8], cmd_preview,
+                                    )
 
-                            tool_submit_time = _time.monotonic()
+                                tool_submit_time = _time.monotonic()
 
-                            # Todo tool -- handle locally (needs per-loop TodoStore)
-                            if tool_name == "todo":
-                                tool_result = _todo_tool(
-                                    todos=args.get("todos"),
-                                    merge=args.get("merge", False),
-                                    store=_todo_store,
-                                )
-                                tool_elapsed = _time.monotonic() - tool_submit_time
-                            elif tool_name == "memory":
-                                tool_result = json.dumps({"error": "Memory is not available in RL environments."})
-                                tool_elapsed = _time.monotonic() - tool_submit_time
-                            elif tool_name == "session_search":
-                                tool_result = json.dumps({"error": "Session search is not available in RL environments."})
-                                tool_elapsed = _time.monotonic() - tool_submit_time
-                            else:
-                                # Run tool calls in a thread pool so backends that
-                                # use asyncio.run() internally (modal, docker, daytona) get
-                                # a clean event loop instead of deadlocking.
-                                loop = asyncio.get_event_loop()
-                                # Capture current tool_name/args for the lambda
-                                _tn, _ta, _tid = tool_name, args, self.task_id
-                                tool_result = await loop.run_in_executor(
-                                    _tool_executor,
-                                    lambda: handle_function_call(
-                                        _tn, _ta, task_id=_tid,
-                                        user_task=_user_task,
-                                    ),
-                                )
-                                tool_elapsed = _time.monotonic() - tool_submit_time
+                                # Todo tool -- handle locally (needs per-loop TodoStore)
+                                if tool_name == "todo":
+                                    tool_result = _todo_tool(
+                                        todos=args.get("todos"),
+                                        merge=args.get("merge", False),
+                                        store=_todo_store,
+                                    )
+                                    tool_elapsed = _time.monotonic() - tool_submit_time
+                                elif tool_name == "memory":
+                                    tool_result = json.dumps({"error": "Memory is not available in RL environments."})
+                                    tool_elapsed = _time.monotonic() - tool_submit_time
+                                elif tool_name == "session_search":
+                                    tool_result = json.dumps({"error": "Session search is not available in RL environments."})
+                                    tool_elapsed = _time.monotonic() - tool_submit_time
+                                else:
+                                    # Run tool calls in a thread pool so backends that
+                                    # use asyncio.run() internally (modal, docker, daytona) get
+                                    # a clean event loop instead of deadlocking.
+                                    loop = asyncio.get_event_loop()
+                                    # Capture current tool_name/args for the lambda
+                                    _tn, _ta, _tid = tool_name, args, self.task_id
+                                    tool_result = await loop.run_in_executor(
+                                        _tool_executor,
+                                        lambda: handle_function_call(
+                                            _tn, _ta, task_id=_tid,
+                                            user_task=_user_task,
+                                        ),
+                                    )
+                                    tool_elapsed = _time.monotonic() - tool_submit_time
 
-                            # Log slow tools and thread pool stats for debugging
-                            pool_active = _tool_executor._work_queue.qsize()
-                            if tool_elapsed > 30:
-                                logger.warning(
-                                    "[%s] turn %d: %s took %.1fs (pool queue=%d)",
-                                    self.task_id[:8], turn + 1, tool_name,
-                                    tool_elapsed, pool_active,
+                                # Log slow tools and thread pool stats for debugging
+                                pool_active = _tool_executor._work_queue.qsize()
+                                if tool_elapsed > 30:
+                                    logger.warning(
+                                        "[%s] turn %d: %s took %.1fs (pool queue=%d)",
+                                        self.task_id[:8], turn + 1, tool_name,
+                                        tool_elapsed, pool_active,
+                                    )
+                            except Exception as e:
+                                tool_result = json.dumps(
+                                    {"error": f"Tool execution failed: {type(e).__name__}: {str(e)}"}
+                                )
+                                tool_errors.append(ToolError(
+                                    turn=turn + 1, tool_name=tool_name,
+                                    arguments=tool_args_raw[:200],
+                                    error=f"{type(e).__name__}: {str(e)}",
+                                    tool_result=tool_result,
+                                ))
+                                logger.error(
+                                    "Tool '%s' execution failed on turn %d: %s",
+                                    tool_name, turn + 1, e,
                                 )
-                        except Exception as e:
-                            tool_result = json.dumps(
-                                {"error": f"Tool execution failed: {type(e).__name__}: {str(e)}"}
-                            )
-                            tool_errors.append(ToolError(
-                                turn=turn + 1, tool_name=tool_name,
-                                arguments=tool_args_raw[:200],
-                                error=f"{type(e).__name__}: {str(e)}",
-                                tool_result=tool_result,
-                            ))
-                            logger.error(
-                                "Tool '%s' execution failed on turn %d: %s",
-                                tool_name, turn + 1, e,
-                            )
 
                         # Also check if the tool returned an error in its JSON result
                         try:
@@ -390,10 +447,11 @@ class HermesAgentLoop:
                             pass
 
                     # Add tool response to conversation
+                    tc_id = tc.get("id", "") if isinstance(tc, dict) else tc.id
                     messages.append(
                         {
                             "role": "tool",
-                            "tool_call_id": tc.id,
+                            "tool_call_id": tc_id,
                             "content": tool_result,
                         }
                     )

environments/benchmarks/tblite/local.yaml

@@ -0,0 +1,38 @@
+# OpenThoughts-TBLite Evaluation -- Docker Backend (Local Compute)
+#
+# Runs tasks in Docker containers on the local machine.
+# Sandboxed like Modal but no cloud costs. Good for dev/testing.
+#
+# Usage:
+#   python environments/benchmarks/tblite/tblite_env.py evaluate \
+#       --config environments/benchmarks/tblite/local.yaml
+#
+#   # Override concurrency:
+#   python environments/benchmarks/tblite/tblite_env.py evaluate \
+#       --config environments/benchmarks/tblite/local.yaml \
+#       --env.eval_concurrency 4
+
+env:
+  enabled_toolsets: ["terminal", "file"]
+  max_agent_turns: 60
+  max_token_length: 32000
+  agent_temperature: 0.8
+  terminal_backend: "docker"
+  terminal_timeout: 300
+  tool_pool_size: 16
+  dataset_name: "NousResearch/openthoughts-tblite"
+  test_timeout: 600
+  task_timeout: 1200
+  eval_concurrency: 8          # max 8 tasks at once
+  tokenizer_name: "NousResearch/Hermes-3-Llama-3.1-8B"
+  use_wandb: false
+  wandb_name: "openthoughts-tblite-local"
+  ensure_scores_are_not_same: false
+  data_dir_to_save_evals: "environments/benchmarks/evals/openthoughts-tblite-local"
+
+openai:
+  base_url: "https://openrouter.ai/api/v1"
+  model_name: "anthropic/claude-sonnet-4"
+  server_type: "openai"
+  health_check: false
+  # api_key loaded from OPENROUTER_API_KEY in .env

environments/benchmarks/tblite/local_vllm.yaml

@@ -0,0 +1,40 @@
+# OpenThoughts-TBLite Evaluation -- Local vLLM Backend
+#
+# Runs against a local vLLM server with Docker sandboxes.
+#
+# Start the vLLM server from the atropos directory:
+#   python -m example_trainer.vllm_api_server \
+#       --model Qwen/Qwen3-4B-Instruct-2507 \
+#       --port 9001 \
+#       --gpu-memory-utilization 0.8 \
+#       --max-model-len=32000
+#
+# Then run:
+#   python environments/benchmarks/tblite/tblite_env.py evaluate \
+#       --config environments/benchmarks/tblite/local_vllm.yaml
+
+env:
+  enabled_toolsets: ["terminal", "file"]
+  max_agent_turns: 60
+  max_token_length: 16000
+  agent_temperature: 0.6
+  terminal_backend: "docker"
+  terminal_timeout: 300
+  tool_pool_size: 16
+  dataset_name: "NousResearch/openthoughts-tblite"
+  test_timeout: 600
+  task_timeout: 1200
+  eval_concurrency: 8
+  tool_call_parser: "hermes"
+  system_prompt: "You are an expert terminal agent. You MUST use the provided tools to complete tasks. Use the terminal tool to run shell commands, read_file to read files, write_file to write files, search_files to search, and patch to edit files. Do NOT write out solutions as text - execute them using the tools. Always start by exploring the environment with terminal commands."
+  tokenizer_name: "Qwen/Qwen3-4B-Instruct-2507"
+  use_wandb: false
+  wandb_name: "tblite-qwen3-4b-instruct"
+  ensure_scores_are_not_same: false
+  data_dir_to_save_evals: "environments/benchmarks/evals/tblite-qwen3-4b-local"
+
+openai:
+  base_url: "http://localhost:9001"
+  model_name: "Qwen/Qwen3-4B-Instruct-2507"
+  server_type: "vllm"
+  health_check: false

environments/benchmarks/terminalbench_2/default.yaml

@@ -29,6 +29,10 @@ env:
   wandb_name: "terminal-bench-2"
   ensure_scores_are_not_same: false
   data_dir_to_save_evals: "environments/benchmarks/evals/terminal-bench-2"
+  # CRITICAL: Limit concurrent Modal sandbox creations to avoid deadlocks.
+  # Modal's blocking calls (App.lookup, etc.) deadlock when too many sandboxes
+  # are created simultaneously inside thread pool workers via asyncio.run().
+  max_concurrent_tasks: 8
 
 openai:
   base_url: "https://openrouter.ai/api/v1"

environments/benchmarks/terminalbench_2/terminalbench2_env.py

@@ -118,6 +118,23 @@ class TerminalBench2EvalConfig(HermesAgentEnvConfig):
         "Tasks exceeding this are scored as FAIL. Default 30 minutes.",
     )
 
+    # --- Concurrency control ---
+    max_concurrent_tasks: int = Field(
+        default=8,
+        description="Maximum number of tasks to run concurrently. "
+        "Limits concurrent Modal sandbox creations to avoid async/threading deadlocks. "
+        "Modal has internal limits and creating too many sandboxes simultaneously "
+        "causes blocking calls to deadlock inside the thread pool.",
+    )
+
+    # --- Eval concurrency ---
+    eval_concurrency: int = Field(
+        default=0,
+        description="Maximum number of tasks to evaluate in parallel. "
+        "0 means unlimited (all tasks run concurrently). "
+        "Set to 8 for local backends to avoid overwhelming the machine.",
+    )
+
 
 # Tasks that cannot run properly on Modal and are excluded from scoring.
 MODAL_INCOMPATIBLE_TASKS = {
@@ -429,8 +446,14 @@ class TerminalBench2EvalEnv(HermesAgentBaseEnv):
                     "error": "no_image",
                 }
 
-            # --- 2. Register per-task Modal image override ---
-            register_task_env_overrides(task_id, {"modal_image": modal_image})
+            # --- 2. Register per-task image override ---
+            # Set both modal_image and docker_image so the task image is used
+            # regardless of which backend is configured.
+            register_task_env_overrides(task_id, {
+                "modal_image": modal_image,
+                "docker_image": modal_image,
+                "cwd": "/app",
+            })
             logger.info(
                 "Task %s: registered image override for task_id %s",
                 task_name, task_id[:8],
@@ -445,17 +468,37 @@ class TerminalBench2EvalEnv(HermesAgentBaseEnv):
             messages.append({"role": "user", "content": self.format_prompt(eval_item)})
 
             # --- 4. Run agent loop ---
-            agent = HermesAgentLoop(
-                server=self.server,
-                tool_schemas=tools,
-                valid_tool_names=valid_names,
-                max_turns=self.config.max_agent_turns,
-                task_id=task_id,
-                temperature=self.config.agent_temperature,
-                max_tokens=self.config.max_token_length,
-                extra_body=self.config.extra_body,
-            )
-            result = await agent.run(messages)
+            # Use ManagedServer (Phase 2) for vLLM/SGLang backends to get
+            # token-level tracking via /generate. Falls back to direct
+            # ServerManager (Phase 1) for OpenAI endpoints.
+            if self._use_managed_server():
+                async with self.server.managed_server(
+                    tokenizer=self.tokenizer,
+                    preserve_think_blocks=bool(self.config.thinking_mode),
+                ) as managed:
+                    agent = HermesAgentLoop(
+                        server=managed,
+                        tool_schemas=tools,
+                        valid_tool_names=valid_names,
+                        max_turns=self.config.max_agent_turns,
+                        task_id=task_id,
+                        temperature=self.config.agent_temperature,
+                        max_tokens=self.config.max_token_length,
+                        extra_body=self.config.extra_body,
+                    )
+                    result = await agent.run(messages)
+            else:
+                agent = HermesAgentLoop(
+                    server=self.server,
+                    tool_schemas=tools,
+                    valid_tool_names=valid_names,
+                    max_turns=self.config.max_agent_turns,
+                    task_id=task_id,
+                    temperature=self.config.agent_temperature,
+                    max_tokens=self.config.max_token_length,
+                    extra_body=self.config.extra_body,
+                )
+                result = await agent.run(messages)
 
             # --- 5. Verify -- run test suite in the agent's sandbox ---
             # Skip verification if the agent produced no meaningful output
@@ -733,12 +776,23 @@ class TerminalBench2EvalEnv(HermesAgentBaseEnv):
         print(f"  Tool thread pool: {self.config.tool_pool_size}")
         print(f"  Terminal timeout: {self.config.terminal_timeout}s/cmd")
         print(f"  Terminal lifetime: {self.config.terminal_lifetime}s (auto: task_timeout + 120)")
+        print(f"  Max concurrent tasks: {self.config.max_concurrent_tasks}")
         print(f"{'='*60}\n")
 
+        # Semaphore to limit concurrent Modal sandbox creations.
+        # Without this, all 86 tasks fire simultaneously, each creating a Modal
+        # sandbox via asyncio.run() inside a thread pool worker. Modal's blocking
+        # calls (App.lookup, etc.) deadlock when too many are created at once.
+        semaphore = asyncio.Semaphore(self.config.max_concurrent_tasks)
+
+        async def _eval_with_semaphore(item):
+            async with semaphore:
+                return await self._eval_with_timeout(item)
+
         # Fire all tasks with wall-clock timeout, track live accuracy on the bar
         total_tasks = len(self.all_eval_items)
         eval_tasks = [
-            asyncio.ensure_future(self._eval_with_timeout(item))
+            asyncio.ensure_future(_eval_with_semaphore(item))
             for item in self.all_eval_items
         ]
 

environments/hermes_base_env.py

@@ -229,6 +229,12 @@ class HermesAgentBaseEnv(BaseEnv):
         from environments.agent_loop import resize_tool_pool
         resize_tool_pool(config.tool_pool_size)
 
+        # Set tool_parser on the ServerManager so ManagedServer uses it
+        # for bidirectional tool call translation (raw text ↔ OpenAI tool_calls).
+        if hasattr(self.server, 'tool_parser'):
+            self.server.tool_parser = config.tool_call_parser
+            print(f"🔧 Tool parser: {config.tool_call_parser}")
+
         # Current group's resolved tools (set in collect_trajectories)
         self._current_group_tools: Optional[Tuple[List[Dict], Set[str]]] = None
 
@@ -466,22 +472,14 @@ class HermesAgentBaseEnv(BaseEnv):
         # Run the agent loop
         result: AgentResult
         if self._use_managed_server():
-            # Phase 2: ManagedServer with parser -- exact tokens + logprobs
-            # Load the tool call parser from registry based on config
-            from environments.tool_call_parsers import get_parser
-            try:
-                tc_parser = get_parser(self.config.tool_call_parser)
-            except KeyError:
-                logger.warning(
-                    "Tool call parser '%s' not found, falling back to 'hermes'",
-                    self.config.tool_call_parser,
-                )
-                tc_parser = get_parser("hermes")
-
+            # Phase 2: ManagedServer with ToolCallTranslator -- exact tokens + logprobs
+            # tool_parser is set on ServerManager in __init__ and passed through
+            # to ManagedServer, which uses ToolCallTranslator for bidirectional
+            # translation between raw text and OpenAI tool_calls.
             try:
                 async with self.server.managed_server(
                     tokenizer=self.tokenizer,
-                    tool_call_parser=tc_parser,
+                    preserve_think_blocks=bool(self.config.thinking_mode),
                 ) as managed:
                     agent = HermesAgentLoop(
                         server=managed,

environments/patches.py

@@ -2,187 +2,41 @@
 Monkey patches for making hermes-agent tools work inside async frameworks (Atropos).
 
 Problem:
-    Some tools use asyncio.run() internally (e.g., mini-swe-agent's Modal backend,
+    Some tools use asyncio.run() internally (e.g., Modal backend via SWE-ReX,
     web_extract). This crashes when called from inside Atropos's event loop because
     asyncio.run() can't be nested.
 
 Solution:
-    Replace the problematic methods with versions that use a dedicated background
-    thread with its own event loop. The calling code sees the same sync interface --
-    call a function, get a result -- but internally the async work happens on a
-    separate thread that doesn't conflict with Atropos's loop.
+    The Modal environment (tools/environments/modal.py) now uses a dedicated
+    _AsyncWorker thread internally, making it safe for both CLI and Atropos use.
+    No monkey-patching is required.
 
-    These patches are safe for normal CLI use too: when there's no running event
-    loop, the behavior is identical (the background thread approach works regardless).
-
-What gets patched:
-    - SwerexModalEnvironment.__init__ -- creates Modal deployment on a background thread
-    - SwerexModalEnvironment.execute -- runs commands on the same background thread
-    - SwerexModalEnvironment.stop -- stops deployment on the background thread
+    This module is kept for backward compatibility — apply_patches() is now a no-op.
 
 Usage:
     Call apply_patches() once at import time (done automatically by hermes_base_env.py).
-    This is idempotent -- calling it multiple times is safe.
+    This is idempotent — calling it multiple times is safe.
 """
 
-import asyncio
 import logging
-import threading
-from typing import Any
 
 logger = logging.getLogger(__name__)
 
 _patches_applied = False
 
 
-class _AsyncWorker:
-    """
-    A dedicated background thread with its own event loop.
-
-    Allows sync code to submit async coroutines and block for results,
-    even when called from inside another running event loop. Used to
-    bridge sync tool interfaces with async backends (Modal, SWE-ReX).
-    """
-
-    def __init__(self):
-        self._loop: asyncio.AbstractEventLoop = None
-        self._thread: threading.Thread = None
-        self._started = threading.Event()
-
-    def start(self):
-        """Start the background event loop thread."""
-        self._thread = threading.Thread(target=self._run_loop, daemon=True)
-        self._thread.start()
-        self._started.wait(timeout=30)
-
-    def _run_loop(self):
-        """Background thread entry point -- runs the event loop forever."""
-        self._loop = asyncio.new_event_loop()
-        asyncio.set_event_loop(self._loop)
-        self._started.set()
-        self._loop.run_forever()
-
-    def run_coroutine(self, coro, timeout=600):
-        """
-        Submit a coroutine to the background loop and block until it completes.
-
-        Safe to call from any thread, including threads that already have
-        a running event loop.
-        """
-        if self._loop is None or self._loop.is_closed():
-            raise RuntimeError("AsyncWorker loop is not running")
-        future = asyncio.run_coroutine_threadsafe(coro, self._loop)
-        return future.result(timeout=timeout)
-
-    def stop(self):
-        """Stop the background event loop and join the thread."""
-        if self._loop and self._loop.is_running():
-            self._loop.call_soon_threadsafe(self._loop.stop)
-        if self._thread:
-            self._thread.join(timeout=10)
-
-
-def _patch_swerex_modal():
-    """
-    Monkey patch SwerexModalEnvironment to use a background thread event loop
-    instead of asyncio.run(). This makes it safe to call from inside Atropos's
-    async event loop.
-
-    The patched methods have the exact same interface and behavior -- the only
-    difference is HOW the async work is executed internally.
-    """
-    try:
-        from minisweagent.environments.extra.swerex_modal import (
-            SwerexModalEnvironment,
-            SwerexModalEnvironmentConfig,
-        )
-        from swerex.deployment.modal import ModalDeployment
-        from swerex.runtime.abstract import Command as RexCommand
-    except ImportError:
-        # mini-swe-agent or swe-rex not installed -- nothing to patch
-        logger.debug("mini-swe-agent Modal backend not available, skipping patch")
-        return
-
-    # Save original methods so we can refer to config handling
-    _original_init = SwerexModalEnvironment.__init__
-
-    def _patched_init(self, **kwargs):
-        """Patched __init__: creates Modal deployment on a background thread."""
-        self.config = SwerexModalEnvironmentConfig(**kwargs)
-
-        # Start a dedicated event loop thread for all Modal async operations
-        self._worker = _AsyncWorker()
-        self._worker.start()
-
-        # Create AND start the deployment entirely on the worker's loop/thread
-        # so all gRPC channels and async state are bound to that loop
-        async def _create_and_start():
-            deployment = ModalDeployment(
-                image=self.config.image,
-                startup_timeout=self.config.startup_timeout,
-                runtime_timeout=self.config.runtime_timeout,
-                deployment_timeout=self.config.deployment_timeout,
-                install_pipx=self.config.install_pipx,
-                modal_sandbox_kwargs=self.config.modal_sandbox_kwargs,
-            )
-            await deployment.start()
-            return deployment
-
-        self.deployment = self._worker.run_coroutine(_create_and_start())
-
-    def _patched_execute(self, command: str, cwd: str = "", *, timeout: int | None = None) -> dict[str, Any]:
-        """Patched execute: runs commands on the background thread's loop."""
-        async def _do_execute():
-            return await self.deployment.runtime.execute(
-                RexCommand(
-                    command=command,
-                    shell=True,
-                    check=False,
-                    cwd=cwd or self.config.cwd,
-                    timeout=timeout or self.config.timeout,
-                    merge_output_streams=True,
-                    env=self.config.env if self.config.env else None,
-                )
-            )
-
-        output = self._worker.run_coroutine(_do_execute())
-        return {
-            "output": output.stdout,
-            "returncode": output.exit_code,
-        }
-
-    def _patched_stop(self):
-        """Patched stop: stops deployment on the background thread, then stops the thread."""
-        try:
-            self._worker.run_coroutine(
-                asyncio.wait_for(self.deployment.stop(), timeout=10),
-                timeout=15,
-            )
-        except Exception:
-            pass
-        finally:
-            self._worker.stop()
-
-    # Apply the patches
-    SwerexModalEnvironment.__init__ = _patched_init
-    SwerexModalEnvironment.execute = _patched_execute
-    SwerexModalEnvironment.stop = _patched_stop
-
-    logger.debug("Patched SwerexModalEnvironment for async-safe operation")
-
-
 def apply_patches():
-    """
-    Apply all monkey patches needed for Atropos compatibility.
+    """Apply all monkey patches needed for Atropos compatibility.
 
-    Safe to call multiple times -- patches are only applied once.
-    Safe for normal CLI use -- patched code works identically when
-    there is no running event loop.
+    Now a no-op — Modal async safety is built directly into ModalEnvironment.
+    Safe to call multiple times.
     """
     global _patches_applied
     if _patches_applied:
         return
 
-    _patch_swerex_modal()
+    # Modal async-safety is now built into tools/environments/modal.py
+    # via the _AsyncWorker class. No monkey-patching needed.
+    logger.debug("apply_patches() called — no patches needed (async safety is built-in)")
 
     _patches_applied = True

environments/tool_call_parsers/deepseek_v3_parser.py

@@ -10,12 +10,13 @@ Format uses special unicode tokens:
     <｜tool▁call▁end｜>
     <｜tool▁calls▁end｜>
 
-Based on VLLM's DeepSeekV3ToolParser.extract_tool_calls()
+Fixes Issue #989: Support for multiple simultaneous tool calls.
 """
 
 import re
 import uuid
-from typing import List, Optional
+import logging
+from typing import List, Optional, Tuple
 
 from openai.types.chat.chat_completion_message_tool_call import (
     ChatCompletionMessageToolCall,
@@ -24,6 +25,7 @@ from openai.types.chat.chat_completion_message_tool_call import (
 
 from environments.tool_call_parsers import ParseResult, ToolCallParser, register_parser
 
+logger = logging.getLogger(__name__)
 
 @register_parser("deepseek_v3")
 class DeepSeekV3ToolCallParser(ToolCallParser):
@@ -32,45 +34,56 @@ class DeepSeekV3ToolCallParser(ToolCallParser):
 
     Uses special unicode tokens with fullwidth angle brackets and block elements.
     Extracts type, function name, and JSON arguments from the structured format.
+    Ensures all tool calls are captured when the model executes multiple actions.
     """
 
     START_TOKEN = "<｜tool▁calls▁begin｜>"
 
-    # Regex captures: type, function_name, function_arguments
+    # Updated PATTERN: Using \s* instead of literal \n for increased robustness
+    # against variations in model formatting (Issue #989).
     PATTERN = re.compile(
-        r"<｜tool▁call▁begin｜>(?P<type>.*)<｜tool▁sep｜>(?P<function_name>.*)\n```json\n(?P<function_arguments>.*)\n```<｜tool▁call▁end｜>",
+        r"<｜tool▁call▁begin｜>(?P<type>.*?)<｜tool▁sep｜>(?P<function_name>.*?)\s*```json\s*(?P<function_arguments>.*?)\s*```\s*<｜tool▁call▁end｜>",
         re.DOTALL,
     )
 
     def parse(self, text: str) -> ParseResult:
+        """
+        Parses the input text and extracts all available tool calls.
+        """
         if self.START_TOKEN not in text:
             return text, None
 
         try:
-            matches = self.PATTERN.findall(text)
+            # Using finditer to capture ALL tool calls in the sequence
+            matches = list(self.PATTERN.finditer(text))
             if not matches:
                 return text, None
 
             tool_calls: List[ChatCompletionMessageToolCall] = []
+            
             for match in matches:
-                tc_type, func_name, func_args = match
+                func_name = match.group("function_name").strip()
+                func_args = match.group("function_arguments").strip()
+                
                 tool_calls.append(
                     ChatCompletionMessageToolCall(
                         id=f"call_{uuid.uuid4().hex[:8]}",
                         type="function",
                         function=Function(
-                            name=func_name.strip(),
-                            arguments=func_args.strip(),
+                            name=func_name,
+                            arguments=func_args,
                         ),
                     )
                 )
 
-            if not tool_calls:
-                return text, None
+            if tool_calls:
+                # Content is text before the first tool call block
+                content_index = text.find(self.START_TOKEN)
+                content = text[:content_index].strip()
+                return content if content else None, tool_calls
 
-            # Content is everything before the tool calls section
-            content = text[: text.find(self.START_TOKEN)].strip()
-            return content if content else None, tool_calls
-
-        except Exception:
+            return text, None
+
+        except Exception as e:
+            logger.error(f"Error parsing DeepSeek V3 tool calls: {e}")
             return text, None

environments/tool_call_parsers/mistral_parser.py

@@ -10,7 +10,6 @@ The [TOOL_CALLS] token is the bot_token used by Mistral models.
 """
 
 import json
-import re
 import uuid
 from typing import List, Optional
 
@@ -42,9 +41,6 @@ class MistralToolCallParser(ToolCallParser):
     # The [TOOL_CALLS] token -- may appear as different strings depending on tokenizer
     BOT_TOKEN = "[TOOL_CALLS]"
 
-    # Fallback regex for pre-v11 format when JSON parsing fails
-    TOOL_CALL_REGEX = re.compile(r"\[?\s*(\{.*?\})\s*\]?", re.DOTALL)
-
     def parse(self, text: str) -> ParseResult:
         if self.BOT_TOKEN not in text:
             return text, None
@@ -71,6 +67,13 @@ class MistralToolCallParser(ToolCallParser):
                     tool_name = raw[:brace_idx].strip()
                     args_str = raw[brace_idx:]
 
+                    # Validate and clean the JSON arguments
+                    try:
+                        parsed_args = json.loads(args_str)
+                        args_str = json.dumps(parsed_args, ensure_ascii=False)
+                    except json.JSONDecodeError:
+                        pass  # Keep raw if parsing fails
+
                     tool_calls.append(
                         ChatCompletionMessageToolCall(
                             id=_generate_mistral_id(),
@@ -100,13 +103,14 @@ class MistralToolCallParser(ToolCallParser):
                             )
                         )
                 except json.JSONDecodeError:
-                    # Fallback regex extraction
-                    match = self.TOOL_CALL_REGEX.findall(first_raw)
-                    if match:
-                        for raw_json in match:
-                            try:
-                                tc = json.loads(raw_json)
-                                args = tc.get("arguments", {})
+                    # Fallback: extract JSON objects using raw_decode
+                    decoder = json.JSONDecoder()
+                    idx = 0
+                    while idx < len(first_raw):
+                        try:
+                            obj, end_idx = decoder.raw_decode(first_raw, idx)
+                            if isinstance(obj, dict) and "name" in obj:
+                                args = obj.get("arguments", {})
                                 if isinstance(args, dict):
                                     args = json.dumps(args, ensure_ascii=False)
                                 tool_calls.append(
@@ -114,12 +118,13 @@ class MistralToolCallParser(ToolCallParser):
                                         id=_generate_mistral_id(),
                                         type="function",
                                         function=Function(
-                                            name=tc["name"], arguments=args
+                                            name=obj["name"], arguments=args
                                         ),
                                     )
                                 )
-                            except (json.JSONDecodeError, KeyError):
-                                continue
+                            idx = end_idx
+                        except json.JSONDecodeError:
+                            idx += 1
 
             if not tool_calls:
                 return text, None

environments/web_research_env.py

@@ -356,10 +356,19 @@ class WebResearchEnv(HermesAgentBaseEnv):
           efficiency_weight  * efficiency   — penalizes wasteful tool usage
           + diversity_bonus                 — source diversity (≥2 distinct domains)
         """
-        final_response: str = result.final_response or ""
-        tools_used: list[str] = [
-            tc.tool_name for tc in (result.tool_calls or [])
-        ] if hasattr(result, "tool_calls") and result.tool_calls else []
+        # Extract final response from messages (last assistant message with content)
+        final_response = ""
+        tools_used: list[str] = []
+        for msg in reversed(result.messages):
+            if msg.get("role") == "assistant" and msg.get("content") and not final_response:
+                final_response = msg["content"]
+            # Collect tool names from tool call messages
+            if msg.get("role") == "assistant" and msg.get("tool_calls"):
+                for tc in msg["tool_calls"]:
+                    fn = tc.get("function", {}) if isinstance(tc, dict) else {}
+                    name = fn.get("name", "")
+                    if name:
+                        tools_used.append(name)
         tool_call_count: int = result.turns_used or len(tools_used)
 
         cfg = self.config
@@ -416,8 +425,16 @@ class WebResearchEnv(HermesAgentBaseEnv):
     # ------------------------------------------------------------------
 
     async def evaluate(self, *args, **kwargs) -> None:
-        """Run evaluation on the held-out split using the agent loop."""
+        """Run evaluation on the held-out split using the full agent loop with tools.
+
+        Each eval item runs through the same agent loop as training —
+        the model can use web_search, web_extract, etc. to research answers.
+        This measures actual agentic research capability, not just knowledge.
+        """
         import time
+        import uuid
+        from environments.agent_loop import HermesAgentLoop
+        from environments.tool_context import ToolContext
 
         items = self._eval_items
         if not items:
@@ -427,43 +444,88 @@ class WebResearchEnv(HermesAgentBaseEnv):
         eval_size = min(self.config.eval_size, len(items))
         eval_items = items[:eval_size]
 
-        logger.info(f"Running eval on {len(eval_items)} questions...")
+        logger.info(f"Running eval on {len(eval_items)} questions (with agent loop + tools)...")
         start_time = time.time()
         samples = []
 
-        for item in eval_items:
+        # Resolve tools once for all eval items
+        tools, valid_names = self._resolve_tools_for_group()
+
+        for i, item in enumerate(eval_items):
+            task_id = str(uuid.uuid4())
+            logger.info(f"Eval [{i+1}/{len(eval_items)}]: {item['question'][:80]}...")
+
             try:
-                # Use the base env's agent loop for eval (same as training)
-                prompt = self.format_prompt(item)
-                completion = await self.server.chat_completion(
-                    messages=[
-                        {"role": "system", "content": self.config.system_prompt or ""},
-                        {"role": "user", "content": prompt},
-                    ],
-                    n=1,
+                # Build messages
+                messages: List[Dict[str, Any]] = []
+                if self.config.system_prompt:
+                    messages.append({"role": "system", "content": self.config.system_prompt})
+                messages.append({"role": "user", "content": self.format_prompt(item)})
+
+                # Run the full agent loop with tools
+                agent = HermesAgentLoop(
+                    server=self.server,
+                    tool_schemas=tools,
+                    valid_tool_names=valid_names,
+                    max_turns=self.config.max_agent_turns,
+                    task_id=task_id,
+                    temperature=0.0,  # Deterministic for eval
                     max_tokens=self.config.max_token_length,
-                    temperature=0.0,
-                    split="eval",
+                    extra_body=self.config.extra_body,
                 )
+                result = await agent.run(messages)
 
-                response_content = (
-                    completion.choices[0].message.content if completion.choices else ""
-                )
+                # Extract final response and tool usage from messages
+                final_response = ""
+                tool_call_count = 0
+                for msg in reversed(result.messages):
+                    if msg.get("role") == "assistant" and msg.get("content") and not final_response:
+                        final_response = msg["content"]
+                    if msg.get("role") == "assistant" and msg.get("tool_calls"):
+                        tool_call_count += len(msg["tool_calls"])
 
-                # Score the response
-                correctness = await self._llm_judge(
-                    question=item["question"],
-                    expected=item["answer"],
-                    model_answer=response_content,
+                # Compute reward (includes LLM judge for correctness)
+                # Temporarily save buffer lengths so we can extract the
+                # correctness score without calling judge twice, and avoid
+                # polluting training metric buffers with eval data.
+                buf_len = len(self._correctness_buffer)
+                ctx = ToolContext(task_id)
+                try:
+                    reward = await self.compute_reward(item, result, ctx)
+                finally:
+                    ctx.cleanup()
+
+                # Extract correctness from the buffer (compute_reward appended it)
+                # then remove eval entries from training buffers
+                correctness = (
+                    self._correctness_buffer[buf_len]
+                    if len(self._correctness_buffer) > buf_len
+                    else 0.0
                 )
+                # Roll back buffers to avoid polluting training metrics
+                for buf in (
+                    self._reward_buffer, self._correctness_buffer,
+                    self._tool_usage_buffer, self._efficiency_buffer,
+                    self._diversity_buffer,
+                ):
+                    if len(buf) > buf_len:
+                        buf.pop()
 
                 samples.append({
                     "prompt": item["question"],
-                    "response": response_content,
+                    "response": final_response[:500],
                     "expected": item["answer"],
                     "correctness": correctness,
+                    "reward": reward,
+                    "tool_calls": tool_call_count,
+                    "turns": result.turns_used,
                 })
 
+                logger.info(
+                    f"  → correctness={correctness:.2f}, reward={reward:.3f}, "
+                    f"tools={tool_call_count}, turns={result.turns_used}"
+                )
+
             except Exception as e:
                 logger.error(f"Eval error on item: {e}")
                 samples.append({
@@ -471,20 +533,33 @@ class WebResearchEnv(HermesAgentBaseEnv):
                     "response": f"ERROR: {e}",
                     "expected": item["answer"],
                     "correctness": 0.0,
+                    "reward": 0.0,
+                    "tool_calls": 0,
+                    "turns": 0,
                 })
 
         end_time = time.time()
 
-        # Compute metrics
+        # Compute aggregate metrics
         correctness_scores = [s["correctness"] for s in samples]
+        rewards = [s["reward"] for s in samples]
+        tool_counts = [s["tool_calls"] for s in samples]
+        n = len(samples)
+
         eval_metrics = {
-            "eval/mean_correctness": (
-                sum(correctness_scores) / len(correctness_scores)
-                if correctness_scores else 0.0
-            ),
-            "eval/n_items": len(samples),
+            "eval/mean_correctness": sum(correctness_scores) / n if n else 0.0,
+            "eval/mean_reward": sum(rewards) / n if n else 0.0,
+            "eval/mean_tool_calls": sum(tool_counts) / n if n else 0.0,
+            "eval/tool_usage_rate": sum(1 for t in tool_counts if t > 0) / n if n else 0.0,
+            "eval/n_items": n,
         }
 
+        logger.info(
+            f"Eval complete — correctness={eval_metrics['eval/mean_correctness']:.3f}, "
+            f"reward={eval_metrics['eval/mean_reward']:.3f}, "
+            f"tool_usage={eval_metrics['eval/tool_usage_rate']:.0%}"
+        )
+
         await self.evaluate_log(
             metrics=eval_metrics,
             samples=samples,

flake.lock

@@ -0,0 +1,181 @@
+{
+  "nodes": {
+    "flake-parts": {
+      "inputs": {
+        "nixpkgs-lib": [
+          "nixpkgs"
+        ]
+      },
+      "locked": {
+        "lastModified": 1772408722,
+        "narHash": "sha256-rHuJtdcOjK7rAHpHphUb1iCvgkU3GpfvicLMwwnfMT0=",
+        "owner": "hercules-ci",
+        "repo": "flake-parts",
+        "rev": "f20dc5d9b8027381c474144ecabc9034d6a839a3",
+        "type": "github"
+      },
+      "original": {
+        "owner": "hercules-ci",
+        "repo": "flake-parts",
+        "type": "github"
+      }
+    },
+    "nixpkgs": {
+      "locked": {
+        "lastModified": 1751274312,
+        "narHash": "sha256-/bVBlRpECLVzjV19t5KMdMFWSwKLtb5RyXdjz3LJT+g=",
+        "owner": "NixOS",
+        "repo": "nixpkgs",
+        "rev": "50ab793786d9de88ee30ec4e4c24fb4236fc2674",
+        "type": "github"
+      },
+      "original": {
+        "owner": "NixOS",
+        "ref": "nixos-24.11",
+        "repo": "nixpkgs",
+        "type": "github"
+      }
+    },
+    "pyproject-build-systems": {
+      "inputs": {
+        "nixpkgs": [
+          "nixpkgs"
+        ],
+        "pyproject-nix": "pyproject-nix",
+        "uv2nix": "uv2nix"
+      },
+      "locked": {
+        "lastModified": 1772555609,
+        "narHash": "sha256-3BA3HnUvJSbHJAlJj6XSy0Jmu7RyP2gyB/0fL7XuEDo=",
+        "owner": "pyproject-nix",
+        "repo": "build-system-pkgs",
+        "rev": "c37f66a953535c394244888598947679af231863",
+        "type": "github"
+      },
+      "original": {
+        "owner": "pyproject-nix",
+        "repo": "build-system-pkgs",
+        "type": "github"
+      }
+    },
+    "pyproject-nix": {
+      "inputs": {
+        "nixpkgs": [
+          "pyproject-build-systems",
+          "nixpkgs"
+        ]
+      },
+      "locked": {
+        "lastModified": 1769936401,
+        "narHash": "sha256-kwCOegKLZJM9v/e/7cqwg1p/YjjTAukKPqmxKnAZRgA=",
+        "owner": "nix-community",
+        "repo": "pyproject.nix",
+        "rev": "b0d513eeeebed6d45b4f2e874f9afba2021f7812",
+        "type": "github"
+      },
+      "original": {
+        "owner": "nix-community",
+        "repo": "pyproject.nix",
+        "type": "github"
+      }
+    },
+    "pyproject-nix_2": {
+      "inputs": {
+        "nixpkgs": [
+          "nixpkgs"
+        ]
+      },
+      "locked": {
+        "lastModified": 1772865871,
+        "narHash": "sha256-/ZTSg97aouL0SlPHaokA4r3iuH9QzHVuWPACD2CUCFY=",
+        "owner": "pyproject-nix",
+        "repo": "pyproject.nix",
+        "rev": "e537db02e72d553cea470976b9733581bcf5b3ed",
+        "type": "github"
+      },
+      "original": {
+        "owner": "pyproject-nix",
+        "repo": "pyproject.nix",
+        "type": "github"
+      }
+    },
+    "pyproject-nix_3": {
+      "inputs": {
+        "nixpkgs": [
+          "uv2nix",
+          "nixpkgs"
+        ]
+      },
+      "locked": {
+        "lastModified": 1771518446,
+        "narHash": "sha256-nFJSfD89vWTu92KyuJWDoTQJuoDuddkJV3TlOl1cOic=",
+        "owner": "pyproject-nix",
+        "repo": "pyproject.nix",
+        "rev": "eb204c6b3335698dec6c7fc1da0ebc3c6df05937",
+        "type": "github"
+      },
+      "original": {
+        "owner": "pyproject-nix",
+        "repo": "pyproject.nix",
+        "type": "github"
+      }
+    },
+    "root": {
+      "inputs": {
+        "flake-parts": "flake-parts",
+        "nixpkgs": "nixpkgs",
+        "pyproject-build-systems": "pyproject-build-systems",
+        "pyproject-nix": "pyproject-nix_2",
+        "uv2nix": "uv2nix_2"
+      }
+    },
+    "uv2nix": {
+      "inputs": {
+        "nixpkgs": [
+          "pyproject-build-systems",
+          "nixpkgs"
+        ],
+        "pyproject-nix": [
+          "pyproject-build-systems",
+          "pyproject-nix"
+        ]
+      },
+      "locked": {
+        "lastModified": 1770770348,
+        "narHash": "sha256-A2GzkmzdYvdgmMEu5yxW+xhossP+txrYb7RuzRaqhlg=",
+        "owner": "pyproject-nix",
+        "repo": "uv2nix",
+        "rev": "5d1b2cb4fe3158043fbafbbe2e46238abbc954b0",
+        "type": "github"
+      },
+      "original": {
+        "owner": "pyproject-nix",
+        "repo": "uv2nix",
+        "type": "github"
+      }
+    },
+    "uv2nix_2": {
+      "inputs": {
+        "nixpkgs": [
+          "nixpkgs"
+        ],
+        "pyproject-nix": "pyproject-nix_3"
+      },
+      "locked": {
+        "lastModified": 1773039484,
+        "narHash": "sha256-+boo33KYkJDw9KItpeEXXv8+65f7hHv/earxpcyzQ0I=",
+        "owner": "pyproject-nix",
+        "repo": "uv2nix",
+        "rev": "b68be7cfeacbed9a3fa38a2b5adc0cfb81d9bb1f",
+        "type": "github"
+      },
+      "original": {
+        "owner": "pyproject-nix",
+        "repo": "uv2nix",
+        "type": "github"
+      }
+    }
+  },
+  "root": "root",
+  "version": 7
+}

flake.nix

@@ -0,0 +1,35 @@
+{
+  description = "Hermes Agent - AI agent framework by Nous Research";
+
+  inputs = {
+    nixpkgs.url = "github:NixOS/nixpkgs/nixos-24.11";
+    flake-parts = {
+      url = "github:hercules-ci/flake-parts";
+      inputs.nixpkgs-lib.follows = "nixpkgs";
+    };
+    pyproject-nix = {
+      url = "github:pyproject-nix/pyproject.nix";
+      inputs.nixpkgs.follows = "nixpkgs";
+    };
+    uv2nix = {
+      url = "github:pyproject-nix/uv2nix";
+      inputs.nixpkgs.follows = "nixpkgs";
+    };
+    pyproject-build-systems = {
+      url = "github:pyproject-nix/build-system-pkgs";
+      inputs.nixpkgs.follows = "nixpkgs";
+    };
+  };
+
+  outputs = inputs:
+    inputs.flake-parts.lib.mkFlake { inherit inputs; } {
+      systems = [ "x86_64-linux" "aarch64-linux" "aarch64-darwin" ];
+
+      imports = [
+        ./nix/packages.nix
+        ./nix/nixosModules.nix
+        ./nix/checks.nix
+        ./nix/devShell.nix
+      ];
+    };
+}

gateway/builtin_hooks/__init__.py

@@ -0,0 +1 @@
+"""Built-in gateway hooks that are always registered."""

gateway/builtin_hooks/boot_md.py

@@ -0,0 +1,86 @@
+"""Built-in boot-md hook — run ~/.hermes/BOOT.md on gateway startup.
+
+This hook is always registered. It silently skips if no BOOT.md exists.
+To activate, create ``~/.hermes/BOOT.md`` with instructions for the
+agent to execute on every gateway restart.
+
+Example BOOT.md::
+
+    # Startup Checklist
+
+    1. Check if any cron jobs failed overnight
+    2. Send a status update to Discord #general
+    3. If there are errors in /opt/app/deploy.log, summarize them
+
+The agent runs in a background thread so it doesn't block gateway
+startup. If nothing needs attention, it replies with [SILENT] to
+suppress delivery.
+"""
+
+import logging
+import os
+import threading
+from pathlib import Path
+
+logger = logging.getLogger("hooks.boot-md")
+
+HERMES_HOME = Path(os.environ.get("HERMES_HOME", Path.home() / ".hermes"))
+BOOT_FILE = HERMES_HOME / "BOOT.md"
+
+
+def _build_boot_prompt(content: str) -> str:
+    """Wrap BOOT.md content in a system-level instruction."""
+    return (
+        "You are running a startup boot checklist. Follow the BOOT.md "
+        "instructions below exactly.\n\n"
+        "---\n"
+        f"{content}\n"
+        "---\n\n"
+        "Execute each instruction. If you need to send a message to a "
+        "platform, use the send_message tool.\n"
+        "If nothing needs attention and there is nothing to report, "
+        "reply with ONLY: [SILENT]"
+    )
+
+
+def _run_boot_agent(content: str) -> None:
+    """Spawn a one-shot agent session to execute the boot instructions."""
+    try:
+        from run_agent import AIAgent
+
+        prompt = _build_boot_prompt(content)
+        agent = AIAgent(
+            quiet_mode=True,
+            skip_context_files=True,
+            skip_memory=True,
+            max_iterations=20,
+        )
+        result = agent.run_conversation(prompt)
+        response = result.get("final_response", "")
+        if response and "[SILENT]" not in response:
+            logger.info("boot-md completed: %s", response[:200])
+        else:
+            logger.info("boot-md completed (nothing to report)")
+    except Exception as e:
+        logger.error("boot-md agent failed: %s", e)
+
+
+async def handle(event_type: str, context: dict) -> None:
+    """Gateway startup handler — run BOOT.md if it exists."""
+    if not BOOT_FILE.exists():
+        return
+
+    content = BOOT_FILE.read_text(encoding="utf-8").strip()
+    if not content:
+        return
+
+    logger.info("Running BOOT.md (%d chars)", len(content))
+
+    # Run in a background thread so we don't block gateway startup.
+    thread = threading.Thread(
+        target=_run_boot_agent,
+        args=(content,),
+        name="boot-md",
+        daemon=True,
+    )
+    thread.start()

gateway/channel_directory.py

@@ -9,12 +9,33 @@ action="list" and for resolving human-friendly channel names to numeric IDs.
 import json
 import logging
 from datetime import datetime
-from pathlib import Path
 from typing import Any, Dict, List, Optional
 
+from hermes_cli.config import get_hermes_home
+
 logger = logging.getLogger(__name__)
 
-DIRECTORY_PATH = Path.home() / ".hermes" / "channel_directory.json"
+DIRECTORY_PATH = get_hermes_home() / "channel_directory.json"
+
+
+def _session_entry_id(origin: Dict[str, Any]) -> Optional[str]:
+    chat_id = origin.get("chat_id")
+    if not chat_id:
+        return None
+    thread_id = origin.get("thread_id")
+    if thread_id:
+        return f"{chat_id}:{thread_id}"
+    return str(chat_id)
+
+
+def _session_entry_name(origin: Dict[str, Any]) -> str:
+    base_name = origin.get("chat_name") or origin.get("user_name") or str(origin.get("chat_id"))
+    thread_id = origin.get("thread_id")
+    if not thread_id:
+        return base_name
+
+    topic_label = origin.get("chat_topic") or f"topic {thread_id}"
+    return f"{base_name} / {topic_label}"
 
 
 # ---------------------------------------------------------------------------
@@ -41,7 +62,7 @@ def build_channel_directory(adapters: Dict[Any, Any]) -> Dict[str, Any]:
             logger.warning("Channel directory: failed to build %s: %s", platform.value, e)
 
     # Telegram, WhatsApp & Signal can't enumerate chats -- pull from session history
-    for plat_name in ("telegram", "whatsapp", "signal"):
+    for plat_name in ("telegram", "whatsapp", "signal", "email", "sms"):
         if plat_name not in platforms:
             platforms[plat_name] = _build_from_sessions(plat_name)
 
@@ -68,7 +89,7 @@ def _build_discord(adapter) -> List[Dict[str, str]]:
         return channels
 
     try:
-        import discord as _discord
+        import discord as _discord  # noqa: F401 — SDK presence check
     except ImportError:
         return channels
 
@@ -97,7 +118,6 @@ def _build_slack(adapter) -> List[Dict[str, str]]:
         return _build_from_sessions("slack")
 
     try:
-        import asyncio
         from tools.send_message_tool import _send_slack  # noqa: F401
         # Use the Slack Web API directly if available
     except Exception:
@@ -109,7 +129,7 @@ def _build_slack(adapter) -> List[Dict[str, str]]:
 
 def _build_from_sessions(platform_name: str) -> List[Dict[str, str]]:
     """Pull known channels/contacts from sessions.json origin data."""
-    sessions_path = Path.home() / ".hermes" / "sessions" / "sessions.json"
+    sessions_path = get_hermes_home() / "sessions" / "sessions.json"
     if not sessions_path.exists():
         return []
 
@@ -123,14 +143,15 @@ def _build_from_sessions(platform_name: str) -> List[Dict[str, str]]:
             origin = session.get("origin") or {}
             if origin.get("platform") != platform_name:
                 continue
-            chat_id = origin.get("chat_id")
-            if not chat_id or chat_id in seen_ids:
+            entry_id = _session_entry_id(origin)
+            if not entry_id or entry_id in seen_ids:
                 continue
-            seen_ids.add(chat_id)
+            seen_ids.add(entry_id)
             entries.append({
-                "id": str(chat_id),
-                "name": origin.get("chat_name") or origin.get("user_name") or str(chat_id),
+                "id": entry_id,
+                "name": _session_entry_name(origin),
                 "type": session.get("chat_type", "dm"),
+                "thread_id": origin.get("thread_id"),
             })
     except Exception as e:
         logger.debug("Channel directory: failed to read sessions for %s: %s", platform_name, e)

gateway/config.py

@@ -16,9 +16,31 @@ from dataclasses import dataclass, field
 from typing import Dict, List, Optional, Any
 from enum import Enum
 
+from hermes_cli.config import get_hermes_home
+
 logger = logging.getLogger(__name__)
 
 
+def _coerce_bool(value: Any, default: bool = True) -> bool:
+    """Coerce bool-ish config values, preserving a caller-provided default."""
+    if value is None:
+        return default
+    if isinstance(value, bool):
+        return value
+    if isinstance(value, str):
+        return value.strip().lower() in ("true", "1", "yes", "on")
+    return bool(value)
+
+
+def _normalize_unauthorized_dm_behavior(value: Any, default: str = "pair") -> str:
+    """Normalize unauthorized DM behavior to a supported value."""
+    if isinstance(value, str):
+        normalized = value.strip().lower()
+        if normalized in {"pair", "ignore"}:
+            return normalized
+    return default
+
+
 class Platform(Enum):
     """Supported messaging platforms."""
     LOCAL = "local"
@@ -27,7 +49,16 @@ class Platform(Enum):
     WHATSAPP = "whatsapp"
     SLACK = "slack"
     SIGNAL = "signal"
+    MATTERMOST = "mattermost"
+    MATRIX = "matrix"
     HOMEASSISTANT = "homeassistant"
+    EMAIL = "email"
+    SMS = "sms"
+    DINGTALK = "dingtalk"
+    API_SERVER = "api_server"
+    WEBHOOK = "webhook"
+    FEISHU = "feishu"
+    WECOM = "wecom"
 
 
 @dataclass
@@ -72,20 +103,32 @@ class SessionResetPolicy:
     mode: str = "both"  # "daily", "idle", "both", or "none"
     at_hour: int = 4  # Hour for daily reset (0-23, local time)
     idle_minutes: int = 1440  # Minutes of inactivity before reset (24 hours)
+    notify: bool = True  # Send a notification to the user when auto-reset occurs
+    notify_exclude_platforms: tuple = ("api_server", "webhook")  # Platforms that don't get reset notifications
     
     def to_dict(self) -> Dict[str, Any]:
         return {
             "mode": self.mode,
             "at_hour": self.at_hour,
             "idle_minutes": self.idle_minutes,
+            "notify": self.notify,
+            "notify_exclude_platforms": list(self.notify_exclude_platforms),
         }
     
     @classmethod
     def from_dict(cls, data: Dict[str, Any]) -> "SessionResetPolicy":
+        # Handle both missing keys and explicit null values (YAML null → None)
+        mode = data.get("mode")
+        at_hour = data.get("at_hour")
+        idle_minutes = data.get("idle_minutes")
+        notify = data.get("notify")
+        exclude = data.get("notify_exclude_platforms")
         return cls(
-            mode=data.get("mode", "both"),
-            at_hour=data.get("at_hour", 4),
-            idle_minutes=data.get("idle_minutes", 1440),
+            mode=mode if mode is not None else "both",
+            at_hour=at_hour if at_hour is not None else 4,
+            idle_minutes=idle_minutes if idle_minutes is not None else 1440,
+            notify=notify if notify is not None else True,
+            notify_exclude_platforms=tuple(exclude) if exclude is not None else ("api_server", "webhook"),
         )
 
 
@@ -97,6 +140,12 @@ class PlatformConfig:
     api_key: Optional[str] = None  # API key if different from token
     home_channel: Optional[HomeChannel] = None
     
+    # Reply threading mode (Telegram/Slack)
+    # - "off": Never thread replies to original message
+    # - "first": Only first chunk threads to user's message (default)
+    # - "all": All chunks in multi-part replies thread to user's message
+    reply_to_mode: str = "first"
+    
     # Platform-specific settings
     extra: Dict[str, Any] = field(default_factory=dict)
     
@@ -104,6 +153,7 @@ class PlatformConfig:
         result = {
             "enabled": self.enabled,
             "extra": self.extra,
+            "reply_to_mode": self.reply_to_mode,
         }
         if self.token:
             result["token"] = self.token
@@ -124,10 +174,42 @@ class PlatformConfig:
             token=data.get("token"),
             api_key=data.get("api_key"),
             home_channel=home_channel,
+            reply_to_mode=data.get("reply_to_mode", "first"),
             extra=data.get("extra", {}),
         )
 
 
+@dataclass
+class StreamingConfig:
+    """Configuration for real-time token streaming to messaging platforms."""
+    enabled: bool = False
+    transport: str = "edit"       # "edit" (progressive editMessageText) or "off"
+    edit_interval: float = 0.3    # Seconds between message edits
+    buffer_threshold: int = 40    # Chars before forcing an edit
+    cursor: str = " ▉"           # Cursor shown during streaming
+
+    def to_dict(self) -> Dict[str, Any]:
+        return {
+            "enabled": self.enabled,
+            "transport": self.transport,
+            "edit_interval": self.edit_interval,
+            "buffer_threshold": self.buffer_threshold,
+            "cursor": self.cursor,
+        }
+
+    @classmethod
+    def from_dict(cls, data: Dict[str, Any]) -> "StreamingConfig":
+        if not data:
+            return cls()
+        return cls(
+            enabled=data.get("enabled", False),
+            transport=data.get("transport", "edit"),
+            edit_interval=float(data.get("edit_interval", 0.3)),
+            buffer_threshold=int(data.get("buffer_threshold", 40)),
+            cursor=data.get("cursor", " ▉"),
+        )
+
+
 @dataclass
 class GatewayConfig:
     """
@@ -145,13 +227,28 @@ class GatewayConfig:
     
     # Reset trigger commands
     reset_triggers: List[str] = field(default_factory=lambda: ["/new", "/reset"])
+
+    # User-defined quick commands (slash commands that bypass the agent loop)
+    quick_commands: Dict[str, Any] = field(default_factory=dict)
     
     # Storage paths
-    sessions_dir: Path = field(default_factory=lambda: Path.home() / ".hermes" / "sessions")
+    sessions_dir: Path = field(default_factory=lambda: get_hermes_home() / "sessions")
     
     # Delivery settings
     always_log_local: bool = True  # Always save cron outputs to local files
-    
+
+    # STT settings
+    stt_enabled: bool = True  # Whether to auto-transcribe inbound voice messages
+
+    # Session isolation in shared chats
+    group_sessions_per_user: bool = True  # Isolate group/channel sessions per participant when user IDs are available
+
+    # Unauthorized DM policy
+    unauthorized_dm_behavior: str = "pair"  # "pair" or "ignore"
+
+    # Streaming configuration
+    streaming: StreamingConfig = field(default_factory=StreamingConfig)
+
     def get_connected_platforms(self) -> List[Platform]:
         """Return list of platforms that are enabled and configured."""
         connected = []
@@ -167,6 +264,24 @@ class GatewayConfig:
             # Signal uses extra dict for config (http_url + account)
             elif platform == Platform.SIGNAL and config.extra.get("http_url"):
                 connected.append(platform)
+            # Email uses extra dict for config (address + imap_host + smtp_host)
+            elif platform == Platform.EMAIL and config.extra.get("address"):
+                connected.append(platform)
+            # SMS uses api_key (Twilio auth token) — SID checked via env
+            elif platform == Platform.SMS and os.getenv("TWILIO_ACCOUNT_SID"):
+                connected.append(platform)
+            # API Server uses enabled flag only (no token needed)
+            elif platform == Platform.API_SERVER:
+                connected.append(platform)
+            # Webhook uses enabled flag only (secrets are per-route)
+            elif platform == Platform.WEBHOOK:
+                connected.append(platform)
+            # Feishu uses extra dict for app credentials
+            elif platform == Platform.FEISHU and config.extra.get("app_id"):
+                connected.append(platform)
+            # WeCom uses extra dict for bot credentials
+            elif platform == Platform.WECOM and config.extra.get("bot_id"):
+                connected.append(platform)
         return connected
     
     def get_home_channel(self, platform: Platform) -> Optional[HomeChannel]:
@@ -209,8 +324,13 @@ class GatewayConfig:
                 p.value: v.to_dict() for p, v in self.reset_by_platform.items()
             },
             "reset_triggers": self.reset_triggers,
+            "quick_commands": self.quick_commands,
             "sessions_dir": str(self.sessions_dir),
             "always_log_local": self.always_log_local,
+            "stt_enabled": self.stt_enabled,
+            "group_sessions_per_user": self.group_sessions_per_user,
+            "unauthorized_dm_behavior": self.unauthorized_dm_behavior,
+            "streaming": self.streaming.to_dict(),
         }
     
     @classmethod
@@ -239,57 +359,213 @@ class GatewayConfig:
         if "default_reset_policy" in data:
             default_policy = SessionResetPolicy.from_dict(data["default_reset_policy"])
         
-        sessions_dir = Path.home() / ".hermes" / "sessions"
+        sessions_dir = get_hermes_home() / "sessions"
         if "sessions_dir" in data:
             sessions_dir = Path(data["sessions_dir"])
         
+        quick_commands = data.get("quick_commands", {})
+        if not isinstance(quick_commands, dict):
+            quick_commands = {}
+
+        stt_enabled = data.get("stt_enabled")
+        if stt_enabled is None:
+            stt_enabled = data.get("stt", {}).get("enabled") if isinstance(data.get("stt"), dict) else None
+
+        group_sessions_per_user = data.get("group_sessions_per_user")
+        unauthorized_dm_behavior = _normalize_unauthorized_dm_behavior(
+            data.get("unauthorized_dm_behavior"),
+            "pair",
+        )
+
         return cls(
             platforms=platforms,
             default_reset_policy=default_policy,
             reset_by_type=reset_by_type,
             reset_by_platform=reset_by_platform,
             reset_triggers=data.get("reset_triggers", ["/new", "/reset"]),
+            quick_commands=quick_commands,
             sessions_dir=sessions_dir,
             always_log_local=data.get("always_log_local", True),
+            stt_enabled=_coerce_bool(stt_enabled, True),
+            group_sessions_per_user=_coerce_bool(group_sessions_per_user, True),
+            unauthorized_dm_behavior=unauthorized_dm_behavior,
+            streaming=StreamingConfig.from_dict(data.get("streaming", {})),
         )
 
+    def get_unauthorized_dm_behavior(self, platform: Optional[Platform] = None) -> str:
+        """Return the effective unauthorized-DM behavior for a platform."""
+        if platform:
+            platform_cfg = self.platforms.get(platform)
+            if platform_cfg and "unauthorized_dm_behavior" in platform_cfg.extra:
+                return _normalize_unauthorized_dm_behavior(
+                    platform_cfg.extra.get("unauthorized_dm_behavior"),
+                    self.unauthorized_dm_behavior,
+                )
+        return self.unauthorized_dm_behavior
+
 
 def load_gateway_config() -> GatewayConfig:
     """
     Load gateway configuration from multiple sources.
-    
+
     Priority (highest to lowest):
     1. Environment variables
-    2. ~/.hermes/gateway.json
-    3. cli-config.yaml gateway section
-    4. Defaults
+    2. ~/.hermes/config.yaml (primary user-facing config)
+    3. ~/.hermes/gateway.json (legacy — provides defaults under config.yaml)
+    4. Built-in defaults
     """
-    config = GatewayConfig()
-    
-    # Try loading from ~/.hermes/gateway.json
-    gateway_config_path = Path.home() / ".hermes" / "gateway.json"
-    if gateway_config_path.exists():
+    _home = get_hermes_home()
+    gw_data: dict = {}
+
+    # Legacy fallback: gateway.json provides the base layer.
+    # config.yaml keys always win when both specify the same setting.
+    gateway_json_path = _home / "gateway.json"
+    if gateway_json_path.exists():
         try:
-            with open(gateway_config_path, "r") as f:
-                data = json.load(f)
-                config = GatewayConfig.from_dict(data)
+            with open(gateway_json_path, "r", encoding="utf-8") as f:
+                gw_data = json.load(f) or {}
+            logger.info(
+                "Loaded legacy %s — consider moving settings to config.yaml",
+                gateway_json_path,
+            )
         except Exception as e:
-            print(f"[gateway] Warning: Failed to load {gateway_config_path}: {e}")
-    
-    # Bridge session_reset from config.yaml (the user-facing config file)
-    # into the gateway config. config.yaml takes precedence over gateway.json
-    # for session reset policy since that's where hermes setup writes it.
+            logger.warning("Failed to load %s: %s", gateway_json_path, e)
+
+    # Primary source: config.yaml
     try:
         import yaml
-        config_yaml_path = Path.home() / ".hermes" / "config.yaml"
+        config_yaml_path = _home / "config.yaml"
         if config_yaml_path.exists():
-            with open(config_yaml_path) as f:
+            with open(config_yaml_path, encoding="utf-8") as f:
                 yaml_cfg = yaml.safe_load(f) or {}
+
+            # Map config.yaml keys → GatewayConfig.from_dict() schema.
+            # Each key overwrites whatever gateway.json may have set.
             sr = yaml_cfg.get("session_reset")
             if sr and isinstance(sr, dict):
-                config.default_reset_policy = SessionResetPolicy.from_dict(sr)
-    except Exception:
-        pass
+                gw_data["default_reset_policy"] = sr
+
+            qc = yaml_cfg.get("quick_commands")
+            if qc is not None:
+                if isinstance(qc, dict):
+                    gw_data["quick_commands"] = qc
+                else:
+                    logger.warning(
+                        "Ignoring invalid quick_commands in config.yaml "
+                        "(expected mapping, got %s)",
+                        type(qc).__name__,
+                    )
+
+            stt_cfg = yaml_cfg.get("stt")
+            if isinstance(stt_cfg, dict):
+                gw_data["stt"] = stt_cfg
+
+            if "group_sessions_per_user" in yaml_cfg:
+                gw_data["group_sessions_per_user"] = yaml_cfg["group_sessions_per_user"]
+
+            streaming_cfg = yaml_cfg.get("streaming")
+            if isinstance(streaming_cfg, dict):
+                gw_data["streaming"] = streaming_cfg
+
+            if "reset_triggers" in yaml_cfg:
+                gw_data["reset_triggers"] = yaml_cfg["reset_triggers"]
+
+            if "always_log_local" in yaml_cfg:
+                gw_data["always_log_local"] = yaml_cfg["always_log_local"]
+
+            if "unauthorized_dm_behavior" in yaml_cfg:
+                gw_data["unauthorized_dm_behavior"] = _normalize_unauthorized_dm_behavior(
+                    yaml_cfg.get("unauthorized_dm_behavior"),
+                    "pair",
+                )
+
+            # Merge platforms section from config.yaml into gw_data so that
+            # nested keys like platforms.webhook.extra.routes are loaded.
+            yaml_platforms = yaml_cfg.get("platforms")
+            platforms_data = gw_data.setdefault("platforms", {})
+            if not isinstance(platforms_data, dict):
+                platforms_data = {}
+                gw_data["platforms"] = platforms_data
+            if isinstance(yaml_platforms, dict):
+                for plat_name, plat_block in yaml_platforms.items():
+                    if not isinstance(plat_block, dict):
+                        continue
+                    existing = platforms_data.get(plat_name, {})
+                    if not isinstance(existing, dict):
+                        existing = {}
+                    # Deep-merge extra dicts so gateway.json defaults survive
+                    merged_extra = {**existing.get("extra", {}), **plat_block.get("extra", {})}
+                    merged = {**existing, **plat_block}
+                    if merged_extra:
+                        merged["extra"] = merged_extra
+                    platforms_data[plat_name] = merged
+                gw_data["platforms"] = platforms_data
+            for plat in Platform:
+                if plat == Platform.LOCAL:
+                    continue
+                platform_cfg = yaml_cfg.get(plat.value)
+                if not isinstance(platform_cfg, dict):
+                    continue
+                # Collect bridgeable keys from this platform section
+                bridged = {}
+                if "unauthorized_dm_behavior" in platform_cfg:
+                    bridged["unauthorized_dm_behavior"] = _normalize_unauthorized_dm_behavior(
+                        platform_cfg.get("unauthorized_dm_behavior"),
+                        gw_data.get("unauthorized_dm_behavior", "pair"),
+                    )
+                if "reply_prefix" in platform_cfg:
+                    bridged["reply_prefix"] = platform_cfg["reply_prefix"]
+                if "require_mention" in platform_cfg:
+                    bridged["require_mention"] = platform_cfg["require_mention"]
+                if "mention_patterns" in platform_cfg:
+                    bridged["mention_patterns"] = platform_cfg["mention_patterns"]
+                if not bridged:
+                    continue
+                plat_data = platforms_data.setdefault(plat.value, {})
+                if not isinstance(plat_data, dict):
+                    plat_data = {}
+                    platforms_data[plat.value] = plat_data
+                extra = plat_data.setdefault("extra", {})
+                if not isinstance(extra, dict):
+                    extra = {}
+                    plat_data["extra"] = extra
+                extra.update(bridged)
+
+            # Discord settings → env vars (env vars take precedence)
+            discord_cfg = yaml_cfg.get("discord", {})
+            if isinstance(discord_cfg, dict):
+                if "require_mention" in discord_cfg and not os.getenv("DISCORD_REQUIRE_MENTION"):
+                    os.environ["DISCORD_REQUIRE_MENTION"] = str(discord_cfg["require_mention"]).lower()
+                frc = discord_cfg.get("free_response_channels")
+                if frc is not None and not os.getenv("DISCORD_FREE_RESPONSE_CHANNELS"):
+                    if isinstance(frc, list):
+                        frc = ",".join(str(v) for v in frc)
+                    os.environ["DISCORD_FREE_RESPONSE_CHANNELS"] = str(frc)
+                if "auto_thread" in discord_cfg and not os.getenv("DISCORD_AUTO_THREAD"):
+                    os.environ["DISCORD_AUTO_THREAD"] = str(discord_cfg["auto_thread"]).lower()
+
+            # Telegram settings → env vars (env vars take precedence)
+            telegram_cfg = yaml_cfg.get("telegram", {})
+            if isinstance(telegram_cfg, dict):
+                if "require_mention" in telegram_cfg and not os.getenv("TELEGRAM_REQUIRE_MENTION"):
+                    os.environ["TELEGRAM_REQUIRE_MENTION"] = str(telegram_cfg["require_mention"]).lower()
+                if "mention_patterns" in telegram_cfg and not os.getenv("TELEGRAM_MENTION_PATTERNS"):
+                    import json as _json
+                    os.environ["TELEGRAM_MENTION_PATTERNS"] = _json.dumps(telegram_cfg["mention_patterns"])
+                frc = telegram_cfg.get("free_response_chats")
+                if frc is not None and not os.getenv("TELEGRAM_FREE_RESPONSE_CHATS"):
+                    if isinstance(frc, list):
+                        frc = ",".join(str(v) for v in frc)
+                    os.environ["TELEGRAM_FREE_RESPONSE_CHATS"] = str(frc)
+    except Exception as e:
+        logger.warning(
+            "Failed to process config.yaml — falling back to .env / gateway.json values. "
+            "Check %s for syntax errors. Error: %s",
+            _home / "config.yaml",
+            e,
+        )
+
+    config = GatewayConfig.from_dict(gw_data)
 
     # Override with environment variables
     _apply_env_overrides(config)
@@ -316,6 +592,8 @@ def load_gateway_config() -> GatewayConfig:
         Platform.TELEGRAM: "TELEGRAM_BOT_TOKEN",
         Platform.DISCORD: "DISCORD_BOT_TOKEN",
         Platform.SLACK: "SLACK_BOT_TOKEN",
+        Platform.MATTERMOST: "MATTERMOST_TOKEN",
+        Platform.MATRIX: "MATRIX_ACCESS_TOKEN",
     }
     for platform, pconfig in config.platforms.items():
         if not pconfig.enabled:
@@ -342,6 +620,21 @@ def _apply_env_overrides(config: GatewayConfig) -> None:
         config.platforms[Platform.TELEGRAM].enabled = True
         config.platforms[Platform.TELEGRAM].token = telegram_token
     
+    # Reply threading mode for Telegram (off/first/all)
+    telegram_reply_mode = os.getenv("TELEGRAM_REPLY_TO_MODE", "").lower()
+    if telegram_reply_mode in ("off", "first", "all"):
+        if Platform.TELEGRAM not in config.platforms:
+            config.platforms[Platform.TELEGRAM] = PlatformConfig()
+        config.platforms[Platform.TELEGRAM].reply_to_mode = telegram_reply_mode
+    
+    telegram_fallback_ips = os.getenv("TELEGRAM_FALLBACK_IPS", "")
+    if telegram_fallback_ips:
+        if Platform.TELEGRAM not in config.platforms:
+            config.platforms[Platform.TELEGRAM] = PlatformConfig()
+        config.platforms[Platform.TELEGRAM].extra["fallback_ips"] = [
+            ip.strip() for ip in telegram_fallback_ips.split(",") if ip.strip()
+        ]
+
     telegram_home = os.getenv("TELEGRAM_HOME_CHANNEL")
     if telegram_home and Platform.TELEGRAM in config.platforms:
         config.platforms[Platform.TELEGRAM].home_channel = HomeChannel(
@@ -380,14 +673,13 @@ def _apply_env_overrides(config: GatewayConfig) -> None:
             config.platforms[Platform.SLACK] = PlatformConfig()
         config.platforms[Platform.SLACK].enabled = True
         config.platforms[Platform.SLACK].token = slack_token
-        # Home channel
-        slack_home = os.getenv("SLACK_HOME_CHANNEL")
-        if slack_home:
-            config.platforms[Platform.SLACK].home_channel = HomeChannel(
-                platform=Platform.SLACK,
-                chat_id=slack_home,
-                name=os.getenv("SLACK_HOME_CHANNEL_NAME", ""),
-            )
+    slack_home = os.getenv("SLACK_HOME_CHANNEL")
+    if slack_home and Platform.SLACK in config.platforms:
+        config.platforms[Platform.SLACK].home_channel = HomeChannel(
+            platform=Platform.SLACK,
+            chat_id=slack_home,
+            name=os.getenv("SLACK_HOME_CHANNEL_NAME", ""),
+        )
     
     # Signal
     signal_url = os.getenv("SIGNAL_HTTP_URL")
@@ -401,13 +693,60 @@ def _apply_env_overrides(config: GatewayConfig) -> None:
             "account": signal_account,
             "ignore_stories": os.getenv("SIGNAL_IGNORE_STORIES", "true").lower() in ("true", "1", "yes"),
         })
-        signal_home = os.getenv("SIGNAL_HOME_CHANNEL")
-        if signal_home:
-            config.platforms[Platform.SIGNAL].home_channel = HomeChannel(
-                platform=Platform.SIGNAL,
-                chat_id=signal_home,
-                name=os.getenv("SIGNAL_HOME_CHANNEL_NAME", "Home"),
-            )
+    signal_home = os.getenv("SIGNAL_HOME_CHANNEL")
+    if signal_home and Platform.SIGNAL in config.platforms:
+        config.platforms[Platform.SIGNAL].home_channel = HomeChannel(
+            platform=Platform.SIGNAL,
+            chat_id=signal_home,
+            name=os.getenv("SIGNAL_HOME_CHANNEL_NAME", "Home"),
+        )
+
+    # Mattermost
+    mattermost_token = os.getenv("MATTERMOST_TOKEN")
+    if mattermost_token:
+        mattermost_url = os.getenv("MATTERMOST_URL", "")
+        if not mattermost_url:
+            logger.warning("MATTERMOST_TOKEN set but MATTERMOST_URL is missing")
+        if Platform.MATTERMOST not in config.platforms:
+            config.platforms[Platform.MATTERMOST] = PlatformConfig()
+        config.platforms[Platform.MATTERMOST].enabled = True
+        config.platforms[Platform.MATTERMOST].token = mattermost_token
+        config.platforms[Platform.MATTERMOST].extra["url"] = mattermost_url
+    mattermost_home = os.getenv("MATTERMOST_HOME_CHANNEL")
+    if mattermost_home and Platform.MATTERMOST in config.platforms:
+        config.platforms[Platform.MATTERMOST].home_channel = HomeChannel(
+            platform=Platform.MATTERMOST,
+            chat_id=mattermost_home,
+            name=os.getenv("MATTERMOST_HOME_CHANNEL_NAME", "Home"),
+        )
+
+    # Matrix
+    matrix_token = os.getenv("MATRIX_ACCESS_TOKEN")
+    matrix_homeserver = os.getenv("MATRIX_HOMESERVER", "")
+    if matrix_token or os.getenv("MATRIX_PASSWORD"):
+        if not matrix_homeserver:
+            logger.warning("MATRIX_ACCESS_TOKEN/MATRIX_PASSWORD set but MATRIX_HOMESERVER is missing")
+        if Platform.MATRIX not in config.platforms:
+            config.platforms[Platform.MATRIX] = PlatformConfig()
+        config.platforms[Platform.MATRIX].enabled = True
+        if matrix_token:
+            config.platforms[Platform.MATRIX].token = matrix_token
+        config.platforms[Platform.MATRIX].extra["homeserver"] = matrix_homeserver
+        matrix_user = os.getenv("MATRIX_USER_ID", "")
+        if matrix_user:
+            config.platforms[Platform.MATRIX].extra["user_id"] = matrix_user
+        matrix_password = os.getenv("MATRIX_PASSWORD", "")
+        if matrix_password:
+            config.platforms[Platform.MATRIX].extra["password"] = matrix_password
+        matrix_e2ee = os.getenv("MATRIX_ENCRYPTION", "").lower() in ("true", "1", "yes")
+        config.platforms[Platform.MATRIX].extra["encryption"] = matrix_e2ee
+    matrix_home = os.getenv("MATRIX_HOME_ROOM")
+    if matrix_home and Platform.MATRIX in config.platforms:
+        config.platforms[Platform.MATRIX].home_channel = HomeChannel(
+            platform=Platform.MATRIX,
+            chat_id=matrix_home,
+            name=os.getenv("MATRIX_HOME_ROOM_NAME", "Home"),
+        )
 
     # Home Assistant
     hass_token = os.getenv("HASS_TOKEN")
@@ -420,6 +759,132 @@ def _apply_env_overrides(config: GatewayConfig) -> None:
         if hass_url:
             config.platforms[Platform.HOMEASSISTANT].extra["url"] = hass_url
 
+    # Email
+    email_addr = os.getenv("EMAIL_ADDRESS")
+    email_pwd = os.getenv("EMAIL_PASSWORD")
+    email_imap = os.getenv("EMAIL_IMAP_HOST")
+    email_smtp = os.getenv("EMAIL_SMTP_HOST")
+    if all([email_addr, email_pwd, email_imap, email_smtp]):
+        if Platform.EMAIL not in config.platforms:
+            config.platforms[Platform.EMAIL] = PlatformConfig()
+        config.platforms[Platform.EMAIL].enabled = True
+        config.platforms[Platform.EMAIL].extra.update({
+            "address": email_addr,
+            "imap_host": email_imap,
+            "smtp_host": email_smtp,
+        })
+    email_home = os.getenv("EMAIL_HOME_ADDRESS")
+    if email_home and Platform.EMAIL in config.platforms:
+        config.platforms[Platform.EMAIL].home_channel = HomeChannel(
+            platform=Platform.EMAIL,
+            chat_id=email_home,
+            name=os.getenv("EMAIL_HOME_ADDRESS_NAME", "Home"),
+        )
+
+    # SMS (Twilio)
+    twilio_sid = os.getenv("TWILIO_ACCOUNT_SID")
+    if twilio_sid:
+        if Platform.SMS not in config.platforms:
+            config.platforms[Platform.SMS] = PlatformConfig()
+        config.platforms[Platform.SMS].enabled = True
+        config.platforms[Platform.SMS].api_key = os.getenv("TWILIO_AUTH_TOKEN", "")
+    sms_home = os.getenv("SMS_HOME_CHANNEL")
+    if sms_home and Platform.SMS in config.platforms:
+        config.platforms[Platform.SMS].home_channel = HomeChannel(
+            platform=Platform.SMS,
+            chat_id=sms_home,
+            name=os.getenv("SMS_HOME_CHANNEL_NAME", "Home"),
+        )
+
+    # API Server
+    api_server_enabled = os.getenv("API_SERVER_ENABLED", "").lower() in ("true", "1", "yes")
+    api_server_key = os.getenv("API_SERVER_KEY", "")
+    api_server_cors_origins = os.getenv("API_SERVER_CORS_ORIGINS", "")
+    api_server_port = os.getenv("API_SERVER_PORT")
+    api_server_host = os.getenv("API_SERVER_HOST")
+    if api_server_enabled or api_server_key:
+        if Platform.API_SERVER not in config.platforms:
+            config.platforms[Platform.API_SERVER] = PlatformConfig()
+        config.platforms[Platform.API_SERVER].enabled = True
+        if api_server_key:
+            config.platforms[Platform.API_SERVER].extra["key"] = api_server_key
+        if api_server_cors_origins:
+            origins = [origin.strip() for origin in api_server_cors_origins.split(",") if origin.strip()]
+            if origins:
+                config.platforms[Platform.API_SERVER].extra["cors_origins"] = origins
+        if api_server_port:
+            try:
+                config.platforms[Platform.API_SERVER].extra["port"] = int(api_server_port)
+            except ValueError:
+                pass
+        if api_server_host:
+            config.platforms[Platform.API_SERVER].extra["host"] = api_server_host
+
+    # Webhook platform
+    webhook_enabled = os.getenv("WEBHOOK_ENABLED", "").lower() in ("true", "1", "yes")
+    webhook_port = os.getenv("WEBHOOK_PORT")
+    webhook_secret = os.getenv("WEBHOOK_SECRET", "")
+    if webhook_enabled:
+        if Platform.WEBHOOK not in config.platforms:
+            config.platforms[Platform.WEBHOOK] = PlatformConfig()
+        config.platforms[Platform.WEBHOOK].enabled = True
+        if webhook_port:
+            try:
+                config.platforms[Platform.WEBHOOK].extra["port"] = int(webhook_port)
+            except ValueError:
+                pass
+        if webhook_secret:
+            config.platforms[Platform.WEBHOOK].extra["secret"] = webhook_secret
+
+    # Feishu / Lark
+    feishu_app_id = os.getenv("FEISHU_APP_ID")
+    feishu_app_secret = os.getenv("FEISHU_APP_SECRET")
+    if feishu_app_id and feishu_app_secret:
+        if Platform.FEISHU not in config.platforms:
+            config.platforms[Platform.FEISHU] = PlatformConfig()
+        config.platforms[Platform.FEISHU].enabled = True
+        config.platforms[Platform.FEISHU].extra.update({
+            "app_id": feishu_app_id,
+            "app_secret": feishu_app_secret,
+            "domain": os.getenv("FEISHU_DOMAIN", "feishu"),
+            "connection_mode": os.getenv("FEISHU_CONNECTION_MODE", "websocket"),
+        })
+        feishu_encrypt_key = os.getenv("FEISHU_ENCRYPT_KEY", "")
+        if feishu_encrypt_key:
+            config.platforms[Platform.FEISHU].extra["encrypt_key"] = feishu_encrypt_key
+        feishu_verification_token = os.getenv("FEISHU_VERIFICATION_TOKEN", "")
+        if feishu_verification_token:
+            config.platforms[Platform.FEISHU].extra["verification_token"] = feishu_verification_token
+        feishu_home = os.getenv("FEISHU_HOME_CHANNEL")
+        if feishu_home:
+            config.platforms[Platform.FEISHU].home_channel = HomeChannel(
+                platform=Platform.FEISHU,
+                chat_id=feishu_home,
+                name=os.getenv("FEISHU_HOME_CHANNEL_NAME", "Home"),
+            )
+
+    # WeCom (Enterprise WeChat)
+    wecom_bot_id = os.getenv("WECOM_BOT_ID")
+    wecom_secret = os.getenv("WECOM_SECRET")
+    if wecom_bot_id and wecom_secret:
+        if Platform.WECOM not in config.platforms:
+            config.platforms[Platform.WECOM] = PlatformConfig()
+        config.platforms[Platform.WECOM].enabled = True
+        config.platforms[Platform.WECOM].extra.update({
+            "bot_id": wecom_bot_id,
+            "secret": wecom_secret,
+        })
+        wecom_ws_url = os.getenv("WECOM_WEBSOCKET_URL", "")
+        if wecom_ws_url:
+            config.platforms[Platform.WECOM].extra["websocket_url"] = wecom_ws_url
+        wecom_home = os.getenv("WECOM_HOME_CHANNEL")
+        if wecom_home:
+            config.platforms[Platform.WECOM].home_channel = HomeChannel(
+                platform=Platform.WECOM,
+                chat_id=wecom_home,
+                name=os.getenv("WECOM_HOME_CHANNEL_NAME", "Home"),
+            )
+
     # Session settings
     idle_minutes = os.getenv("SESSION_IDLE_MINUTES")
     if idle_minutes:
@@ -436,10 +901,3 @@ def _apply_env_overrides(config: GatewayConfig) -> None:
             pass
 
 
-def save_gateway_config(config: GatewayConfig) -> None:
-    """Save gateway configuration to ~/.hermes/gateway.json."""
-    gateway_config_path = Path.home() / ".hermes" / "gateway.json"
-    gateway_config_path.parent.mkdir(parents=True, exist_ok=True)
-    
-    with open(gateway_config_path, "w") as f:
-        json.dump(config.to_dict(), f, indent=2)

gateway/delivery.py

@@ -13,7 +13,8 @@ from pathlib import Path
 from datetime import datetime
 from dataclasses import dataclass
 from typing import Dict, List, Optional, Any, Union
-from enum import Enum
+
+from hermes_cli.config import get_hermes_home
 
 logger = logging.getLogger(__name__)
 
@@ -37,6 +38,7 @@ class DeliveryTarget:
     """
     platform: Platform
     chat_id: Optional[str] = None  # None means use home channel
+    thread_id: Optional[str] = None
     is_origin: bool = False
     is_explicit: bool = False  # True if chat_id was explicitly specified
     
@@ -58,6 +60,7 @@ class DeliveryTarget:
                 return cls(
                     platform=origin.platform,
                     chat_id=origin.chat_id,
+                    thread_id=origin.thread_id,
                     is_origin=True,
                 )
             else:
@@ -114,7 +117,7 @@ class DeliveryRouter:
         """
         self.config = config
         self.adapters = adapters or {}
-        self.output_dir = Path.home() / ".hermes" / "cron" / "output"
+        self.output_dir = get_hermes_home() / "cron" / "output"
     
     def resolve_targets(
         self,
@@ -150,14 +153,14 @@ class DeliveryRouter:
                     continue
             
             # Deduplicate
-            key = (target.platform, target.chat_id)
+            key = (target.platform, target.chat_id, target.thread_id)
             if key not in seen_platforms:
                 seen_platforms.add(key)
                 targets.append(target)
         
         # Always include local if configured
         if self.config.always_log_local:
-            local_key = (Platform.LOCAL, None)
+            local_key = (Platform.LOCAL, None, None)
             if local_key not in seen_platforms:
                 targets.append(DeliveryTarget(platform=Platform.LOCAL))
         
@@ -254,7 +257,7 @@ class DeliveryRouter:
     def _save_full_output(self, content: str, job_id: str) -> Path:
         """Save full cron output to disk and return the file path."""
         timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
-        out_dir = Path.home() / ".hermes" / "cron" / "output"
+        out_dir = get_hermes_home() / "cron" / "output"
         out_dir.mkdir(parents=True, exist_ok=True)
         path = out_dir / f"{job_id}_{timestamp}.txt"
         path.write_text(content)
@@ -285,7 +288,10 @@ class DeliveryRouter:
                 + f"\n\n... [truncated, full output saved to {saved_path}]"
             )
         
-        return await adapter.send(target.chat_id, content, metadata=metadata)
+        send_metadata = dict(metadata or {})
+        if target.thread_id and "thread_id" not in send_metadata:
+            send_metadata["thread_id"] = target.thread_id
+        return await adapter.send(target.chat_id, content, metadata=send_metadata or None)
 
 
 def parse_deliver_spec(
@@ -308,7 +314,7 @@ def build_delivery_context_for_tool(
     origin: Optional[SessionSource] = None
 ) -> Dict[str, Any]:
     """
-    Build context for the schedule_cronjob tool to understand delivery options.
+    Build context for the unified cronjob tool to understand delivery options.
     
     This is passed to the tool so it can validate and explain delivery targets.
     """

gateway/hooks.py

@@ -8,8 +8,9 @@ Hooks are discovered from ~/.hermes/hooks/ directories, each containing:
 
 Events:
   - gateway:startup     -- Gateway process starts
-  - session:start       -- New session created
-  - session:reset       -- User ran /new or /reset
+  - session:start       -- New session created (first message of a new session)
+  - session:end         -- Session ends (user ran /new or /reset)
+  - session:reset       -- Session reset completed (new session entry created)
   - agent:start         -- Agent begins processing a message
   - agent:step          -- Each turn in the tool-calling loop
   - agent:end           -- Agent finishes processing
@@ -20,14 +21,14 @@ Errors in hooks are caught and logged but never block the main pipeline.
 
 import asyncio
 import importlib.util
-import os
-from pathlib import Path
 from typing import Any, Callable, Dict, List, Optional
 
 import yaml
 
+from hermes_cli.config import get_hermes_home
 
-HOOKS_DIR = Path(os.path.expanduser("~/.hermes/hooks"))
+
+HOOKS_DIR = get_hermes_home() / "hooks"
 
 
 class HookRegistry:
@@ -50,14 +51,33 @@ class HookRegistry:
         """Return metadata about all loaded hooks."""
         return list(self._loaded_hooks)
 
+    def _register_builtin_hooks(self) -> None:
+        """Register built-in hooks that are always active."""
+        try:
+            from gateway.builtin_hooks.boot_md import handle as boot_md_handle
+
+            self._handlers.setdefault("gateway:startup", []).append(boot_md_handle)
+            self._loaded_hooks.append({
+                "name": "boot-md",
+                "description": "Run ~/.hermes/BOOT.md on gateway startup",
+                "events": ["gateway:startup"],
+                "path": "(builtin)",
+            })
+        except Exception as e:
+            print(f"[hooks] Could not load built-in boot-md hook: {e}", flush=True)
+
     def discover_and_load(self) -> None:
         """
         Scan the hooks directory for hook directories and load their handlers.
 
+        Also registers built-in hooks that are always active.
+
         Each hook directory must contain:
           - HOOK.yaml with at least 'name' and 'events' keys
           - handler.py with a top-level 'handle' function (sync or async)
         """
+        self._register_builtin_hooks()
+
         if not HOOKS_DIR.exists():
             return
 

gateway/mirror.py

@@ -12,12 +12,13 @@ the full SessionStore machinery.
 import json
 import logging
 from datetime import datetime
-from pathlib import Path
 from typing import Optional
 
+from hermes_cli.config import get_hermes_home
+
 logger = logging.getLogger(__name__)
 
-_SESSIONS_DIR = Path.home() / ".hermes" / "sessions"
+_SESSIONS_DIR = get_hermes_home() / "sessions"
 _SESSIONS_INDEX = _SESSIONS_DIR / "sessions.json"
 
 
@@ -26,6 +27,7 @@ def mirror_to_session(
     chat_id: str,
     message_text: str,
     source_label: str = "cli",
+    thread_id: Optional[str] = None,
 ) -> bool:
     """
     Append a delivery-mirror message to the target session's transcript.
@@ -37,9 +39,9 @@ def mirror_to_session(
     All errors are caught -- this is never fatal.
     """
     try:
-        session_id = _find_session_id(platform, str(chat_id))
+        session_id = _find_session_id(platform, str(chat_id), thread_id=thread_id)
         if not session_id:
-            logger.debug("Mirror: no session found for %s:%s", platform, chat_id)
+            logger.debug("Mirror: no session found for %s:%s:%s", platform, chat_id, thread_id)
             return False
 
         mirror_msg = {
@@ -57,11 +59,11 @@ def mirror_to_session(
         return True
 
     except Exception as e:
-        logger.debug("Mirror failed for %s:%s: %s", platform, chat_id, e)
+        logger.debug("Mirror failed for %s:%s:%s: %s", platform, chat_id, thread_id, e)
         return False
 
 
-def _find_session_id(platform: str, chat_id: str) -> Optional[str]:
+def _find_session_id(platform: str, chat_id: str, thread_id: Optional[str] = None) -> Optional[str]:
     """
     Find the active session_id for a platform + chat_id pair.
 
@@ -91,6 +93,9 @@ def _find_session_id(platform: str, chat_id: str) -> Optional[str]:
 
         origin_chat_id = str(origin.get("chat_id", ""))
         if origin_chat_id == str(chat_id):
+            origin_thread_id = origin.get("thread_id")
+            if thread_id is not None and str(origin_thread_id or "") != str(thread_id):
+                continue
             updated = entry.get("updated_at", "")
             if updated > best_updated:
                 best_updated = updated
@@ -111,6 +116,7 @@ def _append_to_jsonl(session_id: str, message: dict) -> None:
 
 def _append_to_sqlite(session_id: str, message: dict) -> None:
     """Append a message to the SQLite session database."""
+    db = None
     try:
         from hermes_state import SessionDB
         db = SessionDB()
@@ -121,3 +127,6 @@ def _append_to_sqlite(session_id: str, message: dict) -> None:
         )
     except Exception as e:
         logger.debug("Mirror SQLite write failed: %s", e)
+    finally:
+        if db is not None:
+            db.close()

gateway/pairing.py

@@ -25,6 +25,8 @@ import time
 from pathlib import Path
 from typing import Optional
 
+from hermes_constants import get_hermes_dir
+
 
 # Unambiguous alphabet -- excludes 0/O, 1/I to prevent confusion
 ALPHABET = "ABCDEFGHJKLMNPQRSTUVWXYZ23456789"
@@ -39,7 +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 = Path(os.path.expanduser("~/.hermes/pairing"))
+PAIRING_DIR = get_hermes_dir("platforms/pairing", "pairing")
 
 
 def _secure_write(path: Path, data: str) -> None:

gateway/platforms/ADDING_A_PLATFORM.md

@@ -173,7 +173,7 @@ platform_map = {
 }
 ```
 
-Without this, `schedule_cronjob(deliver="your_platform")` silently fails.
+Without this, `cronjob(action="create", deliver="your_platform", ...)` silently fails.
 
 ---
 

gateway/platforms/base.py

@@ -8,6 +8,7 @@ and implement the required methods.
 import asyncio
 import logging
 import os
+import random
 import re
 import uuid
 from abc import ABC, abstractmethod
@@ -24,7 +25,15 @@ from pathlib import Path as _Path
 sys.path.insert(0, str(_Path(__file__).resolve().parents[2]))
 
 from gateway.config import Platform, PlatformConfig
-from gateway.session import SessionSource
+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 = (
+    "Secure secret entry is not supported over messaging. "
+    "Load this skill in the local CLI to be prompted, or add the key to ~/.hermes/.env manually."
+)
 
 
 # ---------------------------------------------------------------------------
@@ -36,8 +45,8 @@ from gateway.session import SessionSource
 # (e.g. Telegram file URLs expire after ~1 hour).
 # ---------------------------------------------------------------------------
 
-# Default location: ~/.hermes/image_cache/
-IMAGE_CACHE_DIR = Path(os.path.expanduser("~/.hermes/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:
@@ -64,31 +73,51 @@ def cache_image_from_bytes(data: bytes, ext: str = ".jpg") -> str:
     return str(filepath)
 
 
-async def cache_image_from_url(url: str, ext: str = ".jpg") -> str:
+async def cache_image_from_url(url: str, ext: str = ".jpg", retries: int = 2) -> str:
     """
     Download an image from a URL and save it to the local cache.
 
-    Uses httpx for async download with a reasonable timeout.
+    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. ".jpg", ".png").
+        retries: Number of retry attempts on transient failures.
 
     Returns:
         Absolute path to the cached image file as a string.
     """
+    import asyncio
     import httpx
+    import logging as _logging
+    _log = _logging.getLogger(__name__)
 
+    last_exc = None
     async with httpx.AsyncClient(timeout=30.0, follow_redirects=True) as client:
-        response = await client.get(
-            url,
-            headers={
-                "User-Agent": "Mozilla/5.0 (compatible; HermesAgent/1.0)",
-                "Accept": "image/*,*/*;q=0.8",
-            },
-        )
-        response.raise_for_status()
-        return cache_image_from_bytes(response.content, ext)
+        for attempt in range(retries + 1):
+            try:
+                response = await client.get(
+                    url,
+                    headers={
+                        "User-Agent": "Mozilla/5.0 (compatible; HermesAgent/1.0)",
+                        "Accept": "image/*,*/*;q=0.8",
+                    },
+                )
+                response.raise_for_status()
+                return cache_image_from_bytes(response.content, ext)
+            except (httpx.TimeoutException, httpx.HTTPStatusError) as exc:
+                last_exc = exc
+                if isinstance(exc, httpx.HTTPStatusError) and exc.response.status_code < 429:
+                    raise
+                if attempt < retries:
+                    wait = 1.5 * (attempt + 1)
+                    _log.debug("Media cache retry %d/%d for %s (%.1fs): %s",
+                               attempt + 1, retries, url[:80], wait, exc)
+                    await asyncio.sleep(wait)
+                    continue
+                raise
+    raise last_exc
 
 
 def cleanup_image_cache(max_age_hours: int = 24) -> int:
@@ -119,7 +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 = Path(os.path.expanduser("~/.hermes/audio_cache"))
+AUDIO_CACHE_DIR = get_hermes_dir("cache/audio", "audio_cache")
 
 
 def get_audio_cache_dir() -> Path:
@@ -146,29 +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
 
 
 # ---------------------------------------------------------------------------
@@ -178,7 +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 = Path(os.path.expanduser("~/.hermes/document_cache"))
+DOCUMENT_CACHE_DIR = get_hermes_dir("cache/documents", "document_cache")
 
 SUPPORTED_DOCUMENT_TYPES = {
     ".pdf": "application/pdf",
@@ -281,11 +332,16 @@ class MessageEvent:
     message_id: Optional[str] = None
     
     # Media attachments
+    # media_urls: local file paths (for vision tool access)
     media_urls: List[str] = field(default_factory=list)
     media_types: List[str] = field(default_factory=list)
     
     # Reply context
     reply_to_message_id: Optional[str] = None
+    reply_to_text: Optional[str] = None  # Text of the replied-to message (for context injection)
+    
+    # Auto-loaded skill for topic/channel bindings (e.g., Telegram DM Topics)
+    auto_skill: Optional[str] = None
     
     # Timestamps
     timestamp: datetime = field(default_factory=datetime.now)
@@ -300,7 +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."""
@@ -317,6 +376,24 @@ class SendResult:
     message_id: Optional[str] = None
     error: Optional[str] = None
     raw_response: Any = None
+    retryable: bool = False  # True for transient errors (network, timeout) — base will retry automatically
+
+
+# Error substrings that indicate a transient network failure worth retrying
+_RETRYABLE_ERROR_PATTERNS = (
+    "connecterror",
+    "connectionerror",
+    "connectionreset",
+    "connectionrefused",
+    "timeout",
+    "timed out",
+    "network",
+    "broken pipe",
+    "remotedisconnected",
+    "eoferror",
+    "readtimeout",
+    "writetimeout",
+)
 
 
 # Type for message handlers
@@ -339,11 +416,85 @@ class BasePlatformAdapter(ABC):
         self.platform = platform
         self._message_handler: Optional[MessageHandler] = None
         self._running = False
+        self._fatal_error_code: Optional[str] = None
+        self._fatal_error_message: Optional[str] = None
+        self._fatal_error_retryable = True
+        self._fatal_error_handler: Optional[Callable[["BasePlatformAdapter"], Awaitable[None] | None]] = None
         
         # Track active message handlers per session for interrupt support
         # Key: session_key (e.g., chat_id), Value: (event, asyncio.Event for interrupt)
         self._active_sessions: Dict[str, asyncio.Event] = {}
         self._pending_messages: Dict[str, MessageEvent] = {}
+        # Background message-processing tasks spawned by handle_message().
+        # Gateway shutdown cancels these so an old gateway instance doesn't keep
+        # working on a task after --replace or manual restarts.
+        self._background_tasks: set[asyncio.Task] = set()
+        # Chats where auto-TTS on voice input is disabled (set by /voice off)
+        self._auto_tts_disabled_chats: set = set()
+
+    @property
+    def has_fatal_error(self) -> bool:
+        return self._fatal_error_message is not None
+
+    @property
+    def fatal_error_message(self) -> Optional[str]:
+        return self._fatal_error_message
+
+    @property
+    def fatal_error_code(self) -> Optional[str]:
+        return self._fatal_error_code
+
+    @property
+    def fatal_error_retryable(self) -> bool:
+        return self._fatal_error_retryable
+
+    def set_fatal_error_handler(self, handler: Callable[["BasePlatformAdapter"], Awaitable[None] | None]) -> None:
+        self._fatal_error_handler = handler
+
+    def _mark_connected(self) -> None:
+        self._running = True
+        self._fatal_error_code = None
+        self._fatal_error_message = None
+        self._fatal_error_retryable = True
+        try:
+            from gateway.status import write_runtime_status
+            write_runtime_status(platform=self.platform.value, platform_state="connected", error_code=None, error_message=None)
+        except Exception:
+            pass
+
+    def _mark_disconnected(self) -> None:
+        self._running = False
+        if self.has_fatal_error:
+            return
+        try:
+            from gateway.status import write_runtime_status
+            write_runtime_status(platform=self.platform.value, platform_state="disconnected", error_code=None, error_message=None)
+        except Exception:
+            pass
+
+    def _set_fatal_error(self, code: str, message: str, *, retryable: bool) -> None:
+        self._running = False
+        self._fatal_error_code = code
+        self._fatal_error_message = message
+        self._fatal_error_retryable = retryable
+        try:
+            from gateway.status import write_runtime_status
+            write_runtime_status(
+                platform=self.platform.value,
+                platform_state="fatal",
+                error_code=code,
+                error_message=message,
+            )
+        except Exception:
+            pass
+
+    async def _notify_fatal_error(self) -> None:
+        handler = self._fatal_error_handler
+        if not handler:
+            return
+        result = handler(self)
+        if asyncio.iscoroutine(result):
+            await result
     
     @property
     def name(self) -> str:
@@ -413,11 +564,20 @@ class BasePlatformAdapter(ABC):
         """
         return SendResult(success=False, error="Not supported")
 
-    async def send_typing(self, chat_id: str) -> None:
+    async def send_typing(self, chat_id: str, metadata=None) -> None:
         """
         Send a typing indicator.
         
         Override in subclasses if the platform supports it.
+        metadata: optional dict with platform-specific context (e.g. thread_id for Slack).
+        """
+        pass
+
+    async def stop_typing(self, chat_id: str) -> None:
+        """Stop a persistent typing indicator (if the platform uses one).
+
+        Override in subclasses that start background typing loops.
+        Default is a no-op for platforms with one-shot typing indicators.
         """
         pass
     
@@ -427,6 +587,7 @@ class BasePlatformAdapter(ABC):
         image_url: str,
         caption: Optional[str] = None,
         reply_to: Optional[str] = None,
+        metadata: Optional[Dict[str, Any]] = None,
     ) -> SendResult:
         """
         Send an image natively via the platform API.
@@ -445,6 +606,7 @@ class BasePlatformAdapter(ABC):
         animation_url: str,
         caption: Optional[str] = None,
         reply_to: Optional[str] = None,
+        metadata: Optional[Dict[str, Any]] = None,
     ) -> SendResult:
         """
         Send an animated GIF natively via the platform API.
@@ -453,7 +615,7 @@ class BasePlatformAdapter(ABC):
         (e.g., Telegram send_animation) so they auto-play inline.
         Default falls back to send_image.
         """
-        return await self.send_image(chat_id=chat_id, image_url=animation_url, caption=caption, reply_to=reply_to)
+        return await self.send_image(chat_id=chat_id, image_url=animation_url, caption=caption, reply_to=reply_to, metadata=metadata)
     
     @staticmethod
     def _is_animation_url(url: str) -> bool:
@@ -515,6 +677,7 @@ class BasePlatformAdapter(ABC):
         audio_path: str,
         caption: Optional[str] = None,
         reply_to: Optional[str] = None,
+        **kwargs,
     ) -> SendResult:
         """
         Send an audio file as a native voice message via the platform API.
@@ -528,12 +691,27 @@ class BasePlatformAdapter(ABC):
             text = f"{caption}\n{text}"
         return await self.send(chat_id=chat_id, content=text, reply_to=reply_to)
 
+    async def play_tts(
+        self,
+        chat_id: str,
+        audio_path: str,
+        **kwargs,
+    ) -> SendResult:
+        """
+        Play auto-TTS audio for voice replies.
+
+        Override in subclasses for invisible playback (e.g. Web UI).
+        Default falls back to send_voice (shows audio player).
+        """
+        return await self.send_voice(chat_id=chat_id, audio_path=audio_path, **kwargs)
+
     async def send_video(
         self,
         chat_id: str,
         video_path: str,
         caption: Optional[str] = None,
         reply_to: Optional[str] = None,
+        **kwargs,
     ) -> SendResult:
         """
         Send a video natively via the platform API.
@@ -553,6 +731,7 @@ class BasePlatformAdapter(ABC):
         caption: Optional[str] = None,
         file_name: Optional[str] = None,
         reply_to: Optional[str] = None,
+        **kwargs,
     ) -> SendResult:
         """
         Send a document/file natively via the platform API.
@@ -571,6 +750,7 @@ class BasePlatformAdapter(ABC):
         image_path: str,
         caption: Optional[str] = None,
         reply_to: Optional[str] = None,
+        **kwargs,
     ) -> SendResult:
         """
         Send a local image file natively via the platform API.
@@ -606,21 +786,95 @@ class BasePlatformAdapter(ABC):
         has_voice_tag = "[[audio_as_voice]]" in content
         cleaned = cleaned.replace("[[audio_as_voice]]", "")
         
-        # Extract MEDIA:<path> tags (path may contain spaces)
-        media_pattern = r'MEDIA:(\S+)'
-        for match in re.finditer(media_pattern, content):
-            path = match.group(1).strip()
+        # Extract MEDIA:<path> tags, allowing optional whitespace after the colon
+        # and quoted/backticked paths for LLM-formatted outputs.
+        media_pattern = re.compile(
+            r'''[`"']?MEDIA:\s*(?P<path>`[^`\n]+`|"[^"\n]+"|'[^'\n]+'|(?:~/|/)\S+(?:[^\S\n]+\S+)*?\.(?:png|jpe?g|gif|webp|mp4|mov|avi|mkv|webm|ogg|opus|mp3|wav|m4a)(?=[\s`"',;:)\]}]|$)|\S+)[`"']?'''
+        )
+        for match in media_pattern.finditer(content):
+            path = match.group("path").strip()
+            if len(path) >= 2 and path[0] == path[-1] and path[0] in "`\"'":
+                path = path[1:-1].strip()
+            path = path.lstrip("`\"'").rstrip("`\"',.;:)}]")
             if path:
                 media.append((path, has_voice_tag))
-        
-        # Remove MEDIA tags from content
+
+        # Remove MEDIA tags from content (including surrounding quote/backtick wrappers)
         if media:
-            cleaned = re.sub(media_pattern, '', cleaned)
+            cleaned = media_pattern.sub('', cleaned)
             cleaned = re.sub(r'\n{3,}', '\n\n', cleaned).strip()
         
         return media, cleaned
-    
-    async def _keep_typing(self, chat_id: str, interval: float = 2.0) -> None:
+
+    @staticmethod
+    def extract_local_files(content: str) -> Tuple[List[str], str]:
+        """
+        Detect bare local file paths in response text for native media delivery.
+
+        Matches absolute paths (/...) and tilde paths (~/) ending in common
+        image or video extensions.  Validates each candidate with
+        ``os.path.isfile()`` to avoid false positives from URLs or
+        non-existent paths.
+
+        Paths inside fenced code blocks (``` ... ```) and inline code
+        (`...`) are ignored so that code samples are never mutilated.
+
+        Returns:
+            Tuple of (list of expanded file paths, cleaned text with the
+            raw path strings removed).
+        """
+        _LOCAL_MEDIA_EXTS = (
+            '.png', '.jpg', '.jpeg', '.gif', '.webp',
+            '.mp4', '.mov', '.avi', '.mkv', '.webm',
+        )
+        ext_part = '|'.join(e.lstrip('.') for e in _LOCAL_MEDIA_EXTS)
+
+        # (?<![/:\w.]) prevents matching inside URLs (e.g. https://…/img.png)
+        #             and relative paths (./foo.png)
+        # (?:~/|/)    anchors to absolute or home-relative paths
+        path_re = re.compile(
+            r'(?<![/:\w.])(?:~/|/)(?:[\w.\-]+/)*[\w.\-]+\.(?:' + ext_part + r')\b',
+            re.IGNORECASE,
+        )
+
+        # Build spans covered by fenced code blocks and inline code
+        code_spans: list = []
+        for m in re.finditer(r'```[^\n]*\n.*?```', content, re.DOTALL):
+            code_spans.append((m.start(), m.end()))
+        for m in re.finditer(r'`[^`\n]+`', content):
+            code_spans.append((m.start(), m.end()))
+
+        def _in_code(pos: int) -> bool:
+            return any(s <= pos < e for s, e in code_spans)
+
+        found: list = []  # (raw_match_text, expanded_path)
+        for match in path_re.finditer(content):
+            if _in_code(match.start()):
+                continue
+            raw = match.group(0)
+            expanded = os.path.expanduser(raw)
+            if os.path.isfile(expanded):
+                found.append((raw, expanded))
+
+        # Deduplicate by expanded path, preserving discovery order
+        seen: set = set()
+        unique: list = []
+        for raw, expanded in found:
+            if expanded not in seen:
+                seen.add(expanded)
+                unique.append((raw, expanded))
+
+        paths = [expanded for _, expanded in unique]
+
+        cleaned = content
+        if unique:
+            for raw, _exp in unique:
+                cleaned = cleaned.replace(raw, '')
+            cleaned = re.sub(r'\n{3,}', '\n\n', cleaned).strip()
+
+        return paths, cleaned
+
+    async def _keep_typing(self, chat_id: str, interval: float = 2.0, metadata=None) -> None:
         """
         Continuously send typing indicator until cancelled.
         
@@ -629,11 +883,126 @@ class BasePlatformAdapter(ABC):
         """
         try:
             while True:
-                await self.send_typing(chat_id)
+                await self.send_typing(chat_id, metadata=metadata)
                 await asyncio.sleep(interval)
         except asyncio.CancelledError:
             pass  # Normal cancellation when handler completes
+        finally:
+            # Ensure the underlying platform typing loop is stopped.
+            # _keep_typing may have called send_typing() after an outer
+            # stop_typing() cleared the task dict, recreating the loop.
+            # Cancelling _keep_typing alone won't clean that up.
+            if hasattr(self, "stop_typing"):
+                try:
+                    await self.stop_typing(chat_id)
+                except Exception:
+                    pass
     
+    # ── Processing lifecycle hooks ──────────────────────────────────────────
+    # Subclasses override these to react to message processing events
+    # (e.g. Discord adds 👀/✅/❌ reactions).
+
+    async def on_processing_start(self, event: MessageEvent) -> None:
+        """Hook called when background processing begins."""
+
+    async def on_processing_complete(self, event: MessageEvent, success: bool) -> None:
+        """Hook called when background processing completes."""
+
+    async def _run_processing_hook(self, hook_name: str, *args: Any, **kwargs: Any) -> None:
+        """Run a lifecycle hook without letting failures break message flow."""
+        hook = getattr(self, hook_name, None)
+        if not callable(hook):
+            return
+        try:
+            await hook(*args, **kwargs)
+        except Exception as e:
+            logger.warning("[%s] %s hook failed: %s", self.name, hook_name, e)
+
+    @staticmethod
+    def _is_retryable_error(error: Optional[str]) -> bool:
+        """Return True if the error string looks like a transient network failure."""
+        if not error:
+            return False
+        lowered = error.lower()
+        return any(pat in lowered for pat in _RETRYABLE_ERROR_PATTERNS)
+
+    async def _send_with_retry(
+        self,
+        chat_id: str,
+        content: str,
+        reply_to: Optional[str] = None,
+        metadata: Any = None,
+        max_retries: int = 2,
+        base_delay: float = 2.0,
+    ) -> "SendResult":
+        """
+        Send a message with automatic retry for transient network errors.
+
+        On permanent failures (e.g. formatting / permission errors) falls back
+        to a plain-text version before giving up. If all attempts fail due to
+        network errors, sends the user a brief delivery-failure notice so they
+        know to retry rather than waiting indefinitely.
+        """
+
+        result = await self.send(
+            chat_id=chat_id,
+            content=content,
+            reply_to=reply_to,
+            metadata=metadata,
+        )
+
+        if result.success:
+            return result
+
+        error_str = result.error or ""
+        is_network = result.retryable or self._is_retryable_error(error_str)
+
+        if is_network:
+            # Retry with exponential backoff for transient errors
+            for attempt in range(1, max_retries + 1):
+                delay = base_delay * (2 ** (attempt - 1)) + random.uniform(0, 1)
+                logger.warning(
+                    "[%s] Send failed (attempt %d/%d, retrying in %.1fs): %s",
+                    self.name, attempt, max_retries, delay, error_str,
+                )
+                await asyncio.sleep(delay)
+                result = await self.send(
+                    chat_id=chat_id,
+                    content=content,
+                    reply_to=reply_to,
+                    metadata=metadata,
+                )
+                if result.success:
+                    logger.info("[%s] Send succeeded on retry %d", self.name, attempt)
+                    return result
+                error_str = result.error or ""
+                if not (result.retryable or self._is_retryable_error(error_str)):
+                    break  # error switched to non-transient — fall through to plain-text fallback
+            else:
+                # All retries exhausted (loop completed without break) — notify user
+                logger.error("[%s] Failed to deliver response after %d retries: %s", self.name, max_retries, error_str)
+                notice = (
+                    "\u26a0\ufe0f Message delivery failed after multiple attempts. "
+                    "Please try again \u2014 your request was processed but the response could not be sent."
+                )
+                try:
+                    await self.send(chat_id=chat_id, content=notice, reply_to=reply_to, metadata=metadata)
+                except Exception as notify_err:
+                    logger.debug("[%s] Could not send delivery-failure notice: %s", self.name, notify_err)
+                return result
+
+        # Non-network / post-retry formatting failure: try plain text as fallback
+        logger.warning("[%s] Send failed: %s — trying plain-text fallback", self.name, error_str)
+        fallback_result = await self.send(
+            chat_id=chat_id,
+            content=f"(Response formatting failed, plain text:)\n\n{content[:3500]}",
+            reply_to=reply_to,
+            metadata=metadata,
+        )
+        if not fallback_result.success:
+            logger.error("[%s] Fallback send also failed: %s", self.name, fallback_result.error)
+        return fallback_result
+
     async def handle_message(self, event: MessageEvent) -> None:
         """
         Process an incoming message.
@@ -645,19 +1014,48 @@ class BasePlatformAdapter(ABC):
         if not self._message_handler:
             return
         
-        session_key = event.source.chat_id
+        session_key = build_session_key(
+            event.source,
+            group_sessions_per_user=self.config.extra.get("group_sessions_per_user", True),
+        )
         
         # Check if there's already an active handler for this session
         if session_key in self._active_sessions:
-            # Store this as a pending message - it will interrupt the running agent
-            print(f"[{self.name}] ⚡ New message while session {session_key} is active - triggering interrupt")
+            # Special case: photo bursts/albums frequently arrive as multiple near-
+            # simultaneous messages. Queue them without interrupting the active run,
+            # then process them immediately after the current task finishes.
+            if event.message_type == MessageType.PHOTO:
+                logger.debug("[%s] Queuing photo follow-up for session %s without interrupt", self.name, session_key)
+                existing = self._pending_messages.get(session_key)
+                if existing and existing.message_type == MessageType.PHOTO:
+                    existing.media_urls.extend(event.media_urls)
+                    existing.media_types.extend(event.media_types)
+                    if event.text:
+                        if not existing.text:
+                            existing.text = event.text
+                        elif event.text not in existing.text:
+                            existing.text = f"{existing.text}\n\n{event.text}".strip()
+                else:
+                    self._pending_messages[session_key] = event
+                return  # Don't interrupt now - will run after current task completes
+
+            # Default behavior for non-photo follow-ups: interrupt the running agent
+            logger.debug("[%s] New message while session %s is active — triggering interrupt", self.name, session_key)
             self._pending_messages[session_key] = event
             # Signal the interrupt (the processing task checks this)
             self._active_sessions[session_key].set()
             return  # Don't process now - will be handled after current task finishes
         
         # Spawn background task to process this message
-        asyncio.create_task(self._process_message_background(event, session_key))
+        task = asyncio.create_task(self._process_message_background(event, session_key))
+        try:
+            self._background_tasks.add(task)
+        except TypeError:
+            # Some tests stub create_task() with lightweight sentinels that are not
+            # hashable and do not support lifecycle callbacks.
+            return
+        if hasattr(task, "add_done_callback"):
+            task.add_done_callback(self._background_tasks.discard)
     
     @staticmethod
     def _get_human_delay() -> float:
@@ -682,14 +1080,29 @@ class BasePlatformAdapter(ABC):
 
     async def _process_message_background(self, event: MessageEvent, session_key: str) -> None:
         """Background task that actually processes the message."""
+        # Track delivery outcomes for the processing-complete hook
+        delivery_attempted = False
+        delivery_succeeded = False
+
+        def _record_delivery(result):
+            nonlocal delivery_attempted, delivery_succeeded
+            if result is None:
+                return
+            delivery_attempted = True
+            if getattr(result, "success", False):
+                delivery_succeeded = True
+
         # Create interrupt event for this session
         interrupt_event = asyncio.Event()
         self._active_sessions[session_key] = interrupt_event
         
         # Start continuous typing indicator (refreshes every 2 seconds)
-        typing_task = asyncio.create_task(self._keep_typing(event.source.chat_id))
+        _thread_metadata = {"thread_id": event.source.thread_id} if event.source.thread_id else None
+        typing_task = asyncio.create_task(self._keep_typing(event.source.chat_id, metadata=_thread_metadata))
         
         try:
+            await self._run_processing_hook("on_processing_start", event)
+
             # Call the handler (this can take a while with tool calls)
             response = await self._message_handler(event)
             
@@ -702,33 +1115,68 @@ class BasePlatformAdapter(ABC):
                 
                 # Extract image URLs and send them as native platform attachments
                 images, text_content = self.extract_images(response)
+                # Strip any remaining internal directives from message body (fixes #1561)
+                text_content = text_content.replace("[[audio_as_voice]]", "").strip()
+                text_content = re.sub(r"MEDIA:\s*\S+", "", text_content).strip()
                 if images:
                     logger.info("[%s] extract_images found %d image(s) in response (%d chars)", self.name, len(images), len(response))
+
+                # Auto-detect bare local file paths for native media delivery
+                # (helps small models that don't use MEDIA: syntax)
+                local_files, text_content = self.extract_local_files(text_content)
+                if local_files:
+                    logger.info("[%s] extract_local_files found %d file(s) in response", self.name, len(local_files))
                 
-                # Send the text portion first (if any remains after extractions)
+                # Auto-TTS: if voice message, generate audio FIRST (before sending text)
+                # Skipped when the chat has voice mode disabled (/voice off)
+                _tts_path = None
+                if (event.message_type == MessageType.VOICE
+                        and text_content
+                        and not media_files
+                        and event.source.chat_id not in self._auto_tts_disabled_chats):
+                    try:
+                        from tools.tts_tool import text_to_speech_tool, check_tts_requirements
+                        if check_tts_requirements():
+                            import json as _json
+                            speech_text = re.sub(r'[*_`#\[\]()]', '', text_content)[:4000].strip()
+                            if not speech_text:
+                                raise ValueError("Empty text after markdown cleanup")
+                            tts_result_str = await asyncio.to_thread(
+                                text_to_speech_tool, text=speech_text
+                            )
+                            tts_data = _json.loads(tts_result_str)
+                            _tts_path = tts_data.get("file_path")
+                    except Exception as tts_err:
+                        logger.warning("[%s] Auto-TTS failed: %s", self.name, tts_err)
+
+                # Play TTS audio before text (voice-first experience)
+                if _tts_path and Path(_tts_path).exists():
+                    try:
+                        await self.play_tts(
+                            chat_id=event.source.chat_id,
+                            audio_path=_tts_path,
+                            metadata=_thread_metadata,
+                        )
+                    finally:
+                        try:
+                            os.remove(_tts_path)
+                        except OSError:
+                            pass
+
+                # Send the text portion
                 if text_content:
                     logger.info("[%s] Sending response (%d chars) to %s", self.name, len(text_content), event.source.chat_id)
-                    result = await self.send(
+                    result = await self._send_with_retry(
                         chat_id=event.source.chat_id,
                         content=text_content,
-                        reply_to=event.message_id
+                        reply_to=event.message_id,
+                        metadata=_thread_metadata,
                     )
-                    
-                    # Log send failures (don't raise - user already saw tool progress)
-                    if not result.success:
-                        print(f"[{self.name}] Failed to send response: {result.error}")
-                        # Try sending without markdown as fallback
-                        fallback_result = await self.send(
-                            chat_id=event.source.chat_id,
-                            content=f"(Response formatting failed, plain text:)\n\n{text_content[:3500]}",
-                            reply_to=event.message_id
-                        )
-                        if not fallback_result.success:
-                            print(f"[{self.name}] Fallback send also failed: {fallback_result.error}")
-                
+                    _record_delivery(result)
+
                 # Human-like pacing delay between text and media
                 human_delay = self._get_human_delay()
-                
+
                 # Send extracted images as native attachments
                 if images:
                     logger.info("[%s] Extracted %d image(s) to send as attachments", self.name, len(images))
@@ -743,21 +1191,23 @@ class BasePlatformAdapter(ABC):
                                 chat_id=event.source.chat_id,
                                 animation_url=image_url,
                                 caption=alt_text if alt_text else None,
+                                metadata=_thread_metadata,
                             )
                         else:
                             img_result = await self.send_image(
                                 chat_id=event.source.chat_id,
                                 image_url=image_url,
                                 caption=alt_text if alt_text else None,
+                                metadata=_thread_metadata,
                             )
                         if not img_result.success:
                             logger.error("[%s] Failed to send image: %s", self.name, img_result.error)
                     except Exception as img_err:
                         logger.error("[%s] Error sending image: %s", self.name, img_err, exc_info=True)
-                
+
                 # Send extracted media files — route by file type
                 _AUDIO_EXTS = {'.ogg', '.opus', '.mp3', '.wav', '.m4a'}
-                _VIDEO_EXTS = {'.mp4', '.mov', '.avi', '.mkv', '.3gp'}
+                _VIDEO_EXTS = {'.mp4', '.mov', '.avi', '.mkv', '.webm', '.3gp'}
                 _IMAGE_EXTS = {'.jpg', '.jpeg', '.png', '.webp', '.gif'}
 
                 for media_path, is_voice in media_files:
@@ -769,32 +1219,67 @@ class BasePlatformAdapter(ABC):
                             media_result = await self.send_voice(
                                 chat_id=event.source.chat_id,
                                 audio_path=media_path,
+                                metadata=_thread_metadata,
                             )
                         elif ext in _VIDEO_EXTS:
                             media_result = await self.send_video(
                                 chat_id=event.source.chat_id,
                                 video_path=media_path,
+                                metadata=_thread_metadata,
                             )
                         elif ext in _IMAGE_EXTS:
                             media_result = await self.send_image_file(
                                 chat_id=event.source.chat_id,
                                 image_path=media_path,
+                                metadata=_thread_metadata,
                             )
                         else:
                             media_result = await self.send_document(
                                 chat_id=event.source.chat_id,
                                 file_path=media_path,
+                                metadata=_thread_metadata,
                             )
 
                         if not media_result.success:
-                            print(f"[{self.name}] Failed to send media ({ext}): {media_result.error}")
+                            logger.warning("[%s] Failed to send media (%s): %s", self.name, ext, media_result.error)
                     except Exception as media_err:
-                        print(f"[{self.name}] Error sending media: {media_err}")
-            
+                        logger.warning("[%s] Error sending media: %s", self.name, media_err)
+
+                # Send auto-detected local files as native attachments
+                for file_path in local_files:
+                    if human_delay > 0:
+                        await asyncio.sleep(human_delay)
+                    try:
+                        ext = Path(file_path).suffix.lower()
+                        if ext in _IMAGE_EXTS:
+                            await self.send_image_file(
+                                chat_id=event.source.chat_id,
+                                image_path=file_path,
+                                metadata=_thread_metadata,
+                            )
+                        elif ext in _VIDEO_EXTS:
+                            await self.send_video(
+                                chat_id=event.source.chat_id,
+                                video_path=file_path,
+                                metadata=_thread_metadata,
+                            )
+                        else:
+                            await self.send_document(
+                                chat_id=event.source.chat_id,
+                                file_path=file_path,
+                                metadata=_thread_metadata,
+                            )
+                    except Exception as file_err:
+                        logger.error("[%s] Error sending local file %s: %s", self.name, file_path, file_err)
+
+            # Determine overall success for the processing hook
+            processing_ok = delivery_succeeded if delivery_attempted else not bool(response)
+            await self._run_processing_hook("on_processing_complete", event, processing_ok)
+
             # Check if there's a pending message that was queued during our processing
             if session_key in self._pending_messages:
                 pending_event = self._pending_messages.pop(session_key)
-                print(f"[{self.name}] 📨 Processing queued message from interrupt")
+                logger.debug("[%s] Processing queued message from interrupt", self.name)
                 # Clean up current session before processing pending
                 if session_key in self._active_sessions:
                     del self._active_sessions[session_key]
@@ -807,10 +1292,28 @@ class BasePlatformAdapter(ABC):
                 await self._process_message_background(pending_event, session_key)
                 return  # Already cleaned up
                 
+        except asyncio.CancelledError:
+            await self._run_processing_hook("on_processing_complete", event, False)
+            raise
         except Exception as e:
-            print(f"[{self.name}] Error handling message: {e}")
-            import traceback
-            traceback.print_exc()
+            await self._run_processing_hook("on_processing_complete", event, False)
+            logger.error("[%s] Error handling message: %s", self.name, e, exc_info=True)
+            # Send the error to the user so they aren't left with radio silence
+            try:
+                error_type = type(e).__name__
+                error_detail = str(e)[:300] if str(e) else "no details available"
+                _thread_metadata = {"thread_id": event.source.thread_id} if event.source.thread_id else None
+                await self.send(
+                    chat_id=event.source.chat_id,
+                    content=(
+                        f"Sorry, I encountered an error ({error_type}).\n"
+                        f"{error_detail}\n"
+                        "Try again or use /reset to start a fresh session."
+                    ),
+                    metadata=_thread_metadata,
+                )
+            except Exception:
+                pass  # Last resort — don't let error reporting crash the handler
         finally:
             # Stop typing indicator
             typing_task.cancel()
@@ -818,10 +1321,32 @@ class BasePlatformAdapter(ABC):
                 await typing_task
             except asyncio.CancelledError:
                 pass
+            # Also cancel any platform-level persistent typing tasks (e.g. Discord)
+            # that may have been recreated by _keep_typing after the last stop_typing()
+            try:
+                if hasattr(self, "stop_typing"):
+                    await self.stop_typing(event.source.chat_id)
+            except Exception:
+                pass
             # Clean up session tracking
             if session_key in self._active_sessions:
                 del self._active_sessions[session_key]
     
+    async def cancel_background_tasks(self) -> None:
+        """Cancel any in-flight background message-processing tasks.
+
+        Used during gateway shutdown/replacement so active sessions from the old
+        process do not keep running after adapters are being torn down.
+        """
+        tasks = [task for task in self._background_tasks if not task.done()]
+        for task in tasks:
+            task.cancel()
+        if tasks:
+            await asyncio.gather(*tasks, return_exceptions=True)
+        self._background_tasks.clear()
+        self._pending_messages.clear()
+        self._active_sessions.clear()
+
     def has_pending_interrupt(self, session_key: str) -> bool:
         """Check if there's a pending interrupt for a session."""
         return session_key in self._active_sessions and self._active_sessions[session_key].is_set()
@@ -881,7 +1406,8 @@ class BasePlatformAdapter(ABC):
         """
         return content
     
-    def truncate_message(self, content: str, max_length: int = 4096) -> List[str]:
+    @staticmethod
+    def truncate_message(content: str, max_length: int = 4096) -> List[str]:
         """
         Split a long message into chunks, preserving code block boundaries.
 
@@ -933,6 +1459,27 @@ class BasePlatformAdapter(ABC):
             if split_at < 1:
                 split_at = headroom
 
+            # Avoid splitting inside an inline code span (`...`).
+            # If the text before split_at has an odd number of unescaped
+            # backticks, the split falls inside inline code — the resulting
+            # chunk would have an unpaired backtick and any special characters
+            # (like parentheses) inside the broken span would be unescaped,
+            # causing MarkdownV2 parse errors on Telegram.
+            candidate = remaining[:split_at]
+            backtick_count = candidate.count("`") - candidate.count("\\`")
+            if backtick_count % 2 == 1:
+                # Find the last unescaped backtick and split before it
+                last_bt = candidate.rfind("`")
+                while last_bt > 0 and candidate[last_bt - 1] == "\\":
+                    last_bt = candidate.rfind("`", 0, last_bt)
+                if last_bt > 0:
+                    # Try to find a space or newline just before the backtick
+                    safe_split = candidate.rfind(" ", 0, last_bt)
+                    nl_split = candidate.rfind("\n", 0, last_bt)
+                    safe_split = max(safe_split, nl_split)
+                    if safe_split > headroom // 4:
+                        split_at = safe_split
+
             chunk_body = remaining[:split_at]
             remaining = remaining[split_at:].lstrip()
 

gateway/platforms/dingtalk.py

@@ -0,0 +1,340 @@
+"""
+DingTalk platform adapter using Stream Mode.
+
+Uses dingtalk-stream SDK for real-time message reception without webhooks.
+Responses are sent via DingTalk's session webhook (markdown format).
+
+Requires:
+    pip install dingtalk-stream httpx
+    DINGTALK_CLIENT_ID and DINGTALK_CLIENT_SECRET env vars
+
+Configuration in config.yaml:
+    platforms:
+      dingtalk:
+        enabled: true
+        extra:
+          client_id: "your-app-key"      # or DINGTALK_CLIENT_ID env var
+          client_secret: "your-secret"   # or DINGTALK_CLIENT_SECRET env var
+"""
+
+import asyncio
+import logging
+import os
+import time
+import uuid
+from datetime import datetime, timezone
+from typing import Any, Dict, Optional
+
+try:
+    import dingtalk_stream
+    from dingtalk_stream import ChatbotHandler, ChatbotMessage
+    DINGTALK_STREAM_AVAILABLE = True
+except ImportError:
+    DINGTALK_STREAM_AVAILABLE = False
+    dingtalk_stream = None  # type: ignore[assignment]
+
+try:
+    import httpx
+    HTTPX_AVAILABLE = True
+except ImportError:
+    HTTPX_AVAILABLE = False
+    httpx = None  # type: ignore[assignment]
+
+from gateway.config import Platform, PlatformConfig
+from gateway.platforms.base import (
+    BasePlatformAdapter,
+    MessageEvent,
+    MessageType,
+    SendResult,
+)
+
+logger = logging.getLogger(__name__)
+
+MAX_MESSAGE_LENGTH = 20000
+DEDUP_WINDOW_SECONDS = 300
+DEDUP_MAX_SIZE = 1000
+RECONNECT_BACKOFF = [2, 5, 10, 30, 60]
+
+
+def check_dingtalk_requirements() -> bool:
+    """Check if DingTalk dependencies are available and configured."""
+    if not DINGTALK_STREAM_AVAILABLE or not HTTPX_AVAILABLE:
+        return False
+    if not os.getenv("DINGTALK_CLIENT_ID") or not os.getenv("DINGTALK_CLIENT_SECRET"):
+        return False
+    return True
+
+
+class DingTalkAdapter(BasePlatformAdapter):
+    """DingTalk chatbot adapter using Stream Mode.
+
+    The dingtalk-stream SDK maintains a long-lived WebSocket connection.
+    Incoming messages arrive via a ChatbotHandler callback. Replies are
+    sent via the incoming message's session_webhook URL using httpx.
+    """
+
+    MAX_MESSAGE_LENGTH = MAX_MESSAGE_LENGTH
+
+    def __init__(self, config: PlatformConfig):
+        super().__init__(config, Platform.DINGTALK)
+
+        extra = config.extra or {}
+        self._client_id: str = extra.get("client_id") or os.getenv("DINGTALK_CLIENT_ID", "")
+        self._client_secret: str = extra.get("client_secret") or os.getenv("DINGTALK_CLIENT_SECRET", "")
+
+        self._stream_client: Any = None
+        self._stream_task: Optional[asyncio.Task] = None
+        self._http_client: Optional["httpx.AsyncClient"] = None
+
+        # Message deduplication: msg_id -> timestamp
+        self._seen_messages: Dict[str, float] = {}
+        # Map chat_id -> session_webhook for reply routing
+        self._session_webhooks: Dict[str, str] = {}
+
+    # -- Connection lifecycle -----------------------------------------------
+
+    async def connect(self) -> bool:
+        """Connect to DingTalk via Stream Mode."""
+        if not DINGTALK_STREAM_AVAILABLE:
+            logger.warning("[%s] dingtalk-stream not installed. Run: pip install dingtalk-stream", self.name)
+            return False
+        if not HTTPX_AVAILABLE:
+            logger.warning("[%s] httpx not installed. Run: pip install httpx", self.name)
+            return False
+        if not self._client_id or not self._client_secret:
+            logger.warning("[%s] DINGTALK_CLIENT_ID and DINGTALK_CLIENT_SECRET required", self.name)
+            return False
+
+        try:
+            self._http_client = httpx.AsyncClient(timeout=30.0)
+
+            credential = dingtalk_stream.Credential(self._client_id, self._client_secret)
+            self._stream_client = dingtalk_stream.DingTalkStreamClient(credential)
+
+            # Capture the current event loop for cross-thread dispatch
+            loop = asyncio.get_running_loop()
+            handler = _IncomingHandler(self, loop)
+            self._stream_client.register_callback_handler(
+                dingtalk_stream.ChatbotMessage.TOPIC, handler
+            )
+
+            self._stream_task = asyncio.create_task(self._run_stream())
+            self._mark_connected()
+            logger.info("[%s] Connected via Stream Mode", self.name)
+            return True
+        except Exception as e:
+            logger.error("[%s] Failed to connect: %s", self.name, e)
+            return False
+
+    async def _run_stream(self) -> None:
+        """Run the blocking stream client with auto-reconnection."""
+        backoff_idx = 0
+        while self._running:
+            try:
+                logger.debug("[%s] Starting stream client...", self.name)
+                await asyncio.to_thread(self._stream_client.start)
+            except asyncio.CancelledError:
+                return
+            except Exception as e:
+                if not self._running:
+                    return
+                logger.warning("[%s] Stream client error: %s", self.name, e)
+
+            if not self._running:
+                return
+
+            delay = RECONNECT_BACKOFF[min(backoff_idx, len(RECONNECT_BACKOFF) - 1)]
+            logger.info("[%s] Reconnecting in %ds...", self.name, delay)
+            await asyncio.sleep(delay)
+            backoff_idx += 1
+
+    async def disconnect(self) -> None:
+        """Disconnect from DingTalk."""
+        self._running = False
+        self._mark_disconnected()
+
+        if self._stream_task:
+            self._stream_task.cancel()
+            try:
+                await self._stream_task
+            except asyncio.CancelledError:
+                pass
+            self._stream_task = None
+
+        if self._http_client:
+            await self._http_client.aclose()
+            self._http_client = None
+
+        self._stream_client = None
+        self._session_webhooks.clear()
+        self._seen_messages.clear()
+        logger.info("[%s] Disconnected", self.name)
+
+    # -- Inbound message processing -----------------------------------------
+
+    async def _on_message(self, message: "ChatbotMessage") -> None:
+        """Process an incoming DingTalk chatbot message."""
+        msg_id = getattr(message, "message_id", None) or uuid.uuid4().hex
+        if self._is_duplicate(msg_id):
+            logger.debug("[%s] Duplicate message %s, skipping", self.name, msg_id)
+            return
+
+        text = self._extract_text(message)
+        if not text:
+            logger.debug("[%s] Empty message, skipping", self.name)
+            return
+
+        # Chat context
+        conversation_id = getattr(message, "conversation_id", "") or ""
+        conversation_type = getattr(message, "conversation_type", "1")
+        is_group = str(conversation_type) == "2"
+        sender_id = getattr(message, "sender_id", "") or ""
+        sender_nick = getattr(message, "sender_nick", "") or sender_id
+        sender_staff_id = getattr(message, "sender_staff_id", "") or ""
+
+        chat_id = conversation_id or sender_id
+        chat_type = "group" if is_group else "dm"
+
+        # Store session webhook for reply routing
+        session_webhook = getattr(message, "session_webhook", None) or ""
+        if session_webhook and chat_id:
+            self._session_webhooks[chat_id] = session_webhook
+
+        source = self.build_source(
+            chat_id=chat_id,
+            chat_name=getattr(message, "conversation_title", None),
+            chat_type=chat_type,
+            user_id=sender_id,
+            user_name=sender_nick,
+            user_id_alt=sender_staff_id if sender_staff_id else None,
+        )
+
+        # Parse timestamp
+        create_at = getattr(message, "create_at", None)
+        try:
+            timestamp = datetime.fromtimestamp(int(create_at) / 1000, tz=timezone.utc) if create_at else datetime.now(tz=timezone.utc)
+        except (ValueError, OSError, TypeError):
+            timestamp = datetime.now(tz=timezone.utc)
+
+        event = MessageEvent(
+            text=text,
+            message_type=MessageType.TEXT,
+            source=source,
+            message_id=msg_id,
+            raw_message=message,
+            timestamp=timestamp,
+        )
+
+        logger.debug("[%s] Message from %s in %s: %s",
+                      self.name, sender_nick, chat_id[:20] if chat_id else "?", text[:50])
+        await self.handle_message(event)
+
+    @staticmethod
+    def _extract_text(message: "ChatbotMessage") -> str:
+        """Extract plain text from a DingTalk chatbot message."""
+        text = getattr(message, "text", None) or ""
+        if isinstance(text, dict):
+            content = text.get("content", "").strip()
+        else:
+            content = str(text).strip()
+
+        # Fall back to rich text if present
+        if not content:
+            rich_text = getattr(message, "rich_text", None)
+            if rich_text and isinstance(rich_text, list):
+                parts = [item["text"] for item in rich_text
+                         if isinstance(item, dict) and item.get("text")]
+                content = " ".join(parts).strip()
+        return content
+
+    # -- Deduplication ------------------------------------------------------
+
+    def _is_duplicate(self, msg_id: str) -> bool:
+        """Check and record a message ID. Returns True if already seen."""
+        now = time.time()
+        if len(self._seen_messages) > DEDUP_MAX_SIZE:
+            cutoff = now - DEDUP_WINDOW_SECONDS
+            self._seen_messages = {k: v for k, v in self._seen_messages.items() if v > cutoff}
+
+        if msg_id in self._seen_messages:
+            return True
+        self._seen_messages[msg_id] = now
+        return False
+
+    # -- Outbound messaging -------------------------------------------------
+
+    async def send(
+        self,
+        chat_id: str,
+        content: str,
+        reply_to: Optional[str] = None,
+        metadata: Optional[Dict[str, Any]] = None,
+    ) -> SendResult:
+        """Send a markdown reply via DingTalk session webhook."""
+        metadata = metadata or {}
+
+        session_webhook = metadata.get("session_webhook") or self._session_webhooks.get(chat_id)
+        if not session_webhook:
+            return SendResult(success=False,
+                              error="No session_webhook available. Reply must follow an incoming message.")
+
+        if not self._http_client:
+            return SendResult(success=False, error="HTTP client not initialized")
+
+        payload = {
+            "msgtype": "markdown",
+            "markdown": {"title": "Hermes", "text": content[:self.MAX_MESSAGE_LENGTH]},
+        }
+
+        try:
+            resp = await self._http_client.post(session_webhook, json=payload, timeout=15.0)
+            if resp.status_code < 300:
+                return SendResult(success=True, message_id=uuid.uuid4().hex[:12])
+            body = resp.text
+            logger.warning("[%s] Send failed HTTP %d: %s", self.name, resp.status_code, body[:200])
+            return SendResult(success=False, error=f"HTTP {resp.status_code}: {body[:200]}")
+        except httpx.TimeoutException:
+            return SendResult(success=False, error="Timeout sending message to DingTalk")
+        except Exception as e:
+            logger.error("[%s] Send error: %s", self.name, e)
+            return SendResult(success=False, error=str(e))
+
+    async def send_typing(self, chat_id: str, metadata=None) -> None:
+        """DingTalk does not support typing indicators."""
+        pass
+
+    async def get_chat_info(self, chat_id: str) -> Dict[str, Any]:
+        """Return basic info about a DingTalk conversation."""
+        return {"name": chat_id, "type": "group" if "group" in chat_id.lower() else "dm"}
+
+
+# ---------------------------------------------------------------------------
+# Internal stream handler
+# ---------------------------------------------------------------------------
+
+class _IncomingHandler(ChatbotHandler if DINGTALK_STREAM_AVAILABLE else object):
+    """dingtalk-stream ChatbotHandler that forwards messages to the adapter."""
+
+    def __init__(self, adapter: DingTalkAdapter, loop: asyncio.AbstractEventLoop):
+        if DINGTALK_STREAM_AVAILABLE:
+            super().__init__()
+        self._adapter = adapter
+        self._loop = loop
+
+    def process(self, message: "ChatbotMessage"):
+        """Called by dingtalk-stream in its thread when a message arrives.
+
+        Schedules the async handler on the main event loop.
+        """
+        loop = self._loop
+        if loop is None or loop.is_closed():
+            logger.error("[DingTalk] Event loop unavailable, cannot dispatch message")
+            return dingtalk_stream.AckMessage.STATUS_OK, "OK"
+
+        future = asyncio.run_coroutine_threadsafe(self._adapter._on_message(message), loop)
+        try:
+            future.result(timeout=60)
+        except Exception:
+            logger.exception("[DingTalk] Error processing incoming message")
+
+        return dingtalk_stream.AckMessage.STATUS_OK, "OK"

gateway/platforms/email.py

@@ -0,0 +1,621 @@
+"""
+Email platform adapter for the Hermes gateway.
+
+Allows users to interact with Hermes by sending emails.
+Uses IMAP to receive and SMTP to send messages.
+
+Environment variables:
+    EMAIL_IMAP_HOST     — IMAP server host (e.g., imap.gmail.com)
+    EMAIL_IMAP_PORT     — IMAP server port (default: 993)
+    EMAIL_SMTP_HOST     — SMTP server host (e.g., smtp.gmail.com)
+    EMAIL_SMTP_PORT     — SMTP server port (default: 587)
+    EMAIL_ADDRESS       — Email address for the agent
+    EMAIL_PASSWORD      — Email password or app-specific password
+    EMAIL_POLL_INTERVAL — Seconds between mailbox checks (default: 15)
+    EMAIL_ALLOWED_USERS — Comma-separated list of allowed sender addresses
+"""
+
+import asyncio
+import email as email_lib
+import imaplib
+import logging
+import os
+import re
+import smtplib
+import ssl
+import uuid
+from email.header import decode_header
+from email.mime.multipart import MIMEMultipart
+from email.mime.text import MIMEText
+from email.mime.base import MIMEBase
+from email import encoders
+from pathlib import Path
+from typing import Any, Dict, List, Optional
+
+from gateway.platforms.base import (
+    BasePlatformAdapter,
+    MessageEvent,
+    MessageType,
+    SendResult,
+    cache_document_from_bytes,
+    cache_image_from_bytes,
+)
+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
+
+# 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")
+    pwd = os.getenv("EMAIL_PASSWORD")
+    imap = os.getenv("EMAIL_IMAP_HOST")
+    smtp = os.getenv("EMAIL_SMTP_HOST")
+    if not all([addr, pwd, imap, smtp]):
+        return False
+    return True
+
+
+def _decode_header_value(raw: str) -> str:
+    """Decode an RFC 2047 encoded email header into a plain string."""
+    parts = decode_header(raw)
+    decoded = []
+    for part, charset in parts:
+        if isinstance(part, bytes):
+            decoded.append(part.decode(charset or "utf-8", errors="replace"))
+        else:
+            decoded.append(part)
+    return " ".join(decoded)
+
+
+def _extract_text_body(msg: email_lib.message.Message) -> str:
+    """Extract the plain-text body from a potentially multipart email."""
+    if msg.is_multipart():
+        for part in msg.walk():
+            content_type = part.get_content_type()
+            disposition = str(part.get("Content-Disposition", ""))
+            # Skip attachments
+            if "attachment" in disposition:
+                continue
+            if content_type == "text/plain":
+                payload = part.get_payload(decode=True)
+                if payload:
+                    charset = part.get_content_charset() or "utf-8"
+                    return payload.decode(charset, errors="replace")
+        # Fallback: try text/html and strip tags
+        for part in msg.walk():
+            content_type = part.get_content_type()
+            disposition = str(part.get("Content-Disposition", ""))
+            if "attachment" in disposition:
+                continue
+            if content_type == "text/html":
+                payload = part.get_payload(decode=True)
+                if payload:
+                    charset = part.get_content_charset() or "utf-8"
+                    html = payload.decode(charset, errors="replace")
+                    return _strip_html(html)
+        return ""
+    else:
+        payload = msg.get_payload(decode=True)
+        if payload:
+            charset = msg.get_content_charset() or "utf-8"
+            text = payload.decode(charset, errors="replace")
+            if msg.get_content_type() == "text/html":
+                return _strip_html(text)
+            return text
+        return ""
+
+
+def _strip_html(html: str) -> str:
+    """Naive HTML tag stripper for fallback text extraction."""
+    text = re.sub(r"<br\s*/?>", "\n", html, flags=re.IGNORECASE)
+    text = re.sub(r"<p[^>]*>", "\n", text, flags=re.IGNORECASE)
+    text = re.sub(r"</p>", "\n", text, flags=re.IGNORECASE)
+    text = re.sub(r"<[^>]+>", "", text)
+    text = re.sub(r"&nbsp;", " ", text)
+    text = re.sub(r"&amp;", "&", text)
+    text = re.sub(r"&lt;", "<", text)
+    text = re.sub(r"&gt;", ">", text)
+    text = re.sub(r"\n{3,}", "\n\n", text)
+    return text.strip()
+
+
+def _extract_email_address(raw: str) -> str:
+    """Extract bare email address from 'Name <addr>' format."""
+    match = re.search(r"<([^>]+)>", raw)
+    if match:
+        return match.group(1).strip().lower()
+    return raw.strip().lower()
+
+
+def _extract_attachments(
+    msg: email_lib.message.Message,
+    skip_attachments: bool = False,
+) -> List[Dict[str, Any]]:
+    """Extract attachment metadata and cache files locally.
+
+    When *skip_attachments* is True, all attachment/inline parts are ignored
+    (useful for malware protection or bandwidth savings).
+    """
+    attachments = []
+    if not msg.is_multipart():
+        return attachments
+
+    for part in msg.walk():
+        disposition = str(part.get("Content-Disposition", ""))
+        if skip_attachments and ("attachment" in disposition or "inline" in disposition):
+            continue
+        if "attachment" not in disposition and "inline" not in disposition:
+            continue
+        # Skip text/plain and text/html body parts
+        content_type = part.get_content_type()
+        if content_type in ("text/plain", "text/html") and "attachment" not in disposition:
+            continue
+
+        filename = part.get_filename()
+        if filename:
+            filename = _decode_header_value(filename)
+        else:
+            ext = part.get_content_subtype() or "bin"
+            filename = f"attachment.{ext}"
+
+        payload = part.get_payload(decode=True)
+        if not payload:
+            continue
+
+        ext = Path(filename).suffix.lower()
+        if ext in _IMAGE_EXTS:
+            cached_path = cache_image_from_bytes(payload, ext)
+            attachments.append({
+                "path": cached_path,
+                "filename": filename,
+                "type": "image",
+                "media_type": content_type,
+            })
+        else:
+            cached_path = cache_document_from_bytes(payload, filename)
+            attachments.append({
+                "path": cached_path,
+                "filename": filename,
+                "type": "document",
+                "media_type": content_type,
+            })
+
+    return attachments
+
+
+class EmailAdapter(BasePlatformAdapter):
+    """Email gateway adapter using IMAP (receive) and SMTP (send)."""
+
+    def __init__(self, config: PlatformConfig):
+        super().__init__(config, Platform.EMAIL)
+
+        self._address = os.getenv("EMAIL_ADDRESS", "")
+        self._password = os.getenv("EMAIL_PASSWORD", "")
+        self._imap_host = os.getenv("EMAIL_IMAP_HOST", "")
+        self._imap_port = int(os.getenv("EMAIL_IMAP_PORT", "993"))
+        self._smtp_host = os.getenv("EMAIL_SMTP_HOST", "")
+        self._smtp_port = int(os.getenv("EMAIL_SMTP_PORT", "587"))
+        self._poll_interval = int(os.getenv("EMAIL_POLL_INTERVAL", "15"))
+
+        # Skip attachments — configured via config.yaml:
+        #   platforms:
+        #     email:
+        #       skip_attachments: true
+        extra = config.extra or {}
+        self._skip_attachments = extra.get("skip_attachments", False)
+
+        # Track message IDs we've already processed to avoid duplicates
+        self._seen_uids: set = set()
+        self._seen_uids_max: int = 2000   # cap to prevent unbounded memory growth
+        self._poll_task: Optional[asyncio.Task] = None
+
+        # Map chat_id (sender email) -> last subject + message-id for threading
+        self._thread_context: Dict[str, Dict[str, str]] = {}
+
+        logger.info("[Email] Adapter initialized for %s", self._address)
+
+    def _trim_seen_uids(self) -> None:
+        """Keep only the most recent UIDs to prevent unbounded memory growth.
+
+        IMAP UIDs are monotonically increasing integers. When the set grows
+        beyond the cap, we keep only the highest half — old UIDs are safe to
+        drop because new messages always have higher UIDs and IMAP's UNSEEN
+        flag prevents re-delivery regardless.
+        """
+        if len(self._seen_uids) <= self._seen_uids_max:
+            return
+        try:
+            # UIDs are bytes like b'1234' — sort numerically and keep top half
+            sorted_uids = sorted(self._seen_uids, key=lambda u: int(u))
+            keep = self._seen_uids_max // 2
+            self._seen_uids = set(sorted_uids[-keep:])
+            logger.debug("[Email] Trimmed seen UIDs to %d entries", len(self._seen_uids))
+        except (ValueError, TypeError):
+            # Fallback: just clear old entries if sort fails
+            self._seen_uids = set(list(self._seen_uids)[-self._seen_uids_max // 2:])
+
+    async def connect(self) -> bool:
+        """Connect to the IMAP server and start polling for new messages."""
+        try:
+            # Test IMAP connection
+            imap = imaplib.IMAP4_SSL(self._imap_host, self._imap_port, timeout=30)
+            imap.login(self._address, self._password)
+            # Mark all existing messages as seen so we only process new ones
+            imap.select("INBOX")
+            status, data = imap.uid("search", None, "ALL")
+            if status == "OK" and data and data[0]:
+                for uid in data[0].split():
+                    self._seen_uids.add(uid)
+            # Keep only the most recent UIDs to prevent unbounded growth
+            self._trim_seen_uids()
+            imap.logout()
+            logger.info("[Email] IMAP connection test passed. %d existing messages skipped.", len(self._seen_uids))
+        except Exception as e:
+            logger.error("[Email] IMAP connection failed: %s", e)
+            return False
+
+        try:
+            # Test SMTP connection
+            smtp = smtplib.SMTP(self._smtp_host, self._smtp_port, timeout=30)
+            smtp.starttls(context=ssl.create_default_context())
+            smtp.login(self._address, self._password)
+            smtp.quit()
+            logger.info("[Email] SMTP connection test passed.")
+        except Exception as e:
+            logger.error("[Email] SMTP connection failed: %s", e)
+            return False
+
+        self._running = True
+        self._poll_task = asyncio.create_task(self._poll_loop())
+        print(f"[Email] Connected as {self._address}")
+        return True
+
+    async def disconnect(self) -> None:
+        """Stop polling and disconnect."""
+        self._running = False
+        if self._poll_task:
+            self._poll_task.cancel()
+            try:
+                await self._poll_task
+            except asyncio.CancelledError:
+                pass
+            self._poll_task = None
+        logger.info("[Email] Disconnected.")
+
+    async def _poll_loop(self) -> None:
+        """Poll IMAP for new messages at regular intervals."""
+        while self._running:
+            try:
+                await self._check_inbox()
+            except asyncio.CancelledError:
+                break
+            except Exception as e:
+                logger.error("[Email] Poll error: %s", e)
+            await asyncio.sleep(self._poll_interval)
+
+    async def _check_inbox(self) -> None:
+        """Check INBOX for unseen messages and dispatch them."""
+        # Run IMAP operations in a thread to avoid blocking the event loop
+        loop = asyncio.get_running_loop()
+        messages = await loop.run_in_executor(None, self._fetch_new_messages)
+        for msg_data in messages:
+            await self._dispatch_message(msg_data)
+
+    def _fetch_new_messages(self) -> List[Dict[str, Any]]:
+        """Fetch new (unseen) messages from IMAP. Runs in executor thread."""
+        results = []
+        try:
+            imap = imaplib.IMAP4_SSL(self._imap_host, self._imap_port, timeout=30)
+            try:
+                imap.login(self._address, self._password)
+                imap.select("INBOX")
+
+                status, data = imap.uid("search", None, "UNSEEN")
+                if status != "OK" or not data or not data[0]:
+                    return results
+
+                for uid in data[0].split():
+                    if uid in self._seen_uids:
+                        continue
+                    self._seen_uids.add(uid)
+                    # Trim periodically to prevent unbounded memory growth
+                    if len(self._seen_uids) > self._seen_uids_max:
+                        self._trim_seen_uids()
+
+                    status, msg_data = imap.uid("fetch", uid, "(RFC822)")
+                    if status != "OK":
+                        continue
+
+                    raw_email = msg_data[0][1]
+                    msg = email_lib.message_from_bytes(raw_email)
+
+                    sender_raw = msg.get("From", "")
+                    sender_addr = _extract_email_address(sender_raw)
+                    sender_name = _decode_header_value(sender_raw)
+                    # Remove email from name if present
+                    if "<" in sender_name:
+                        sender_name = sender_name.split("<")[0].strip().strip('"')
+
+                    subject = _decode_header_value(msg.get("Subject", "(no subject)"))
+                    message_id = msg.get("Message-ID", "")
+                    in_reply_to = msg.get("In-Reply-To", "")
+                    # Skip automated/noreply senders before any processing
+                    msg_headers = dict(msg.items())
+                    if _is_automated_sender(sender_addr, msg_headers):
+                        logger.debug("[Email] Skipping automated sender: %s", sender_addr)
+                        continue
+                    body = _extract_text_body(msg)
+                    attachments = _extract_attachments(msg, skip_attachments=self._skip_attachments)
+
+                    results.append({
+                        "uid": uid,
+                        "sender_addr": sender_addr,
+                        "sender_name": sender_name,
+                        "subject": subject,
+                        "message_id": message_id,
+                        "in_reply_to": in_reply_to,
+                        "body": body,
+                        "attachments": attachments,
+                        "date": msg.get("Date", ""),
+                    })
+            finally:
+                try:
+                    imap.logout()
+                except Exception:
+                    pass
+        except Exception as e:
+            logger.error("[Email] IMAP fetch error: %s", e)
+        return results
+
+    async def _dispatch_message(self, msg_data: Dict[str, Any]) -> None:
+        """Convert a fetched email into a MessageEvent and dispatch it."""
+        sender_addr = msg_data["sender_addr"]
+
+        # Skip self-messages
+        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"]
+
+        # Build message text: include subject as context
+        text = body
+        if subject and not subject.startswith("Re:"):
+            text = f"[Subject: {subject}]\n\n{body}"
+
+        # Determine message type and media
+        media_urls = []
+        media_types = []
+        msg_type = MessageType.TEXT
+
+        for att in attachments:
+            media_urls.append(att["path"])
+            media_types.append(att["media_type"])
+            if att["type"] == "image":
+                msg_type = MessageType.PHOTO
+
+        # Store thread context for reply threading
+        self._thread_context[sender_addr] = {
+            "subject": subject,
+            "message_id": msg_data["message_id"],
+        }
+
+        source = self.build_source(
+            chat_id=sender_addr,
+            chat_name=msg_data["sender_name"] or sender_addr,
+            chat_type="dm",
+            user_id=sender_addr,
+            user_name=msg_data["sender_name"] or sender_addr,
+        )
+
+        event = MessageEvent(
+            text=text or "(empty email)",
+            message_type=msg_type,
+            source=source,
+            message_id=msg_data["message_id"],
+            media_urls=media_urls,
+            media_types=media_types,
+            reply_to_message_id=msg_data["in_reply_to"] or None,
+        )
+
+        logger.info("[Email] New message from %s: %s", sender_addr, subject)
+        await self.handle_message(event)
+
+    async def send(
+        self,
+        chat_id: str,
+        content: str,
+        reply_to: Optional[str] = None,
+        metadata: Optional[Dict[str, Any]] = None,
+    ) -> SendResult:
+        """Send an email reply to the given address."""
+        try:
+            loop = asyncio.get_running_loop()
+            message_id = await loop.run_in_executor(
+                None, self._send_email, chat_id, content, reply_to
+            )
+            return SendResult(success=True, message_id=message_id)
+        except Exception as e:
+            logger.error("[Email] Send failed to %s: %s", chat_id, e)
+            return SendResult(success=False, error=str(e))
+
+    def _send_email(
+        self,
+        to_addr: str,
+        body: str,
+        reply_to_msg_id: Optional[str] = None,
+    ) -> str:
+        """Send an email via SMTP. Runs in executor thread."""
+        msg = MIMEMultipart()
+        msg["From"] = self._address
+        msg["To"] = to_addr
+
+        # Thread context for reply
+        ctx = self._thread_context.get(to_addr, {})
+        subject = ctx.get("subject", "Hermes Agent")
+        if not subject.startswith("Re:"):
+            subject = f"Re: {subject}"
+        msg["Subject"] = subject
+
+        # Threading headers
+        original_msg_id = reply_to_msg_id or ctx.get("message_id")
+        if original_msg_id:
+            msg["In-Reply-To"] = original_msg_id
+            msg["References"] = original_msg_id
+
+        msg_id = f"<hermes-{uuid.uuid4().hex[:12]}@{self._address.split('@')[1]}>"
+        msg["Message-ID"] = msg_id
+
+        msg.attach(MIMEText(body, "plain", "utf-8"))
+
+        smtp = smtplib.SMTP(self._smtp_host, self._smtp_port, timeout=30)
+        try:
+            smtp.starttls(context=ssl.create_default_context())
+            smtp.login(self._address, self._password)
+            smtp.send_message(msg)
+        finally:
+            try:
+                smtp.quit()
+            except Exception:
+                smtp.close()
+
+        logger.info("[Email] Sent reply to %s (subject: %s)", to_addr, subject)
+        return msg_id
+
+    async def send_typing(self, chat_id: str, metadata: Optional[Dict[str, Any]] = None) -> None:
+        """Email has no typing indicator — no-op."""
+
+    async def send_image(
+        self,
+        chat_id: str,
+        image_url: str,
+        caption: Optional[str] = None,
+        reply_to: Optional[str] = None,
+    ) -> SendResult:
+        """Send an image URL as part of an email body."""
+        text = caption or ""
+        text += f"\n\nImage: {image_url}"
+        return await self.send(chat_id, text.strip(), reply_to)
+
+    async def send_document(
+        self,
+        chat_id: str,
+        file_path: str,
+        caption: Optional[str] = None,
+        file_name: Optional[str] = None,
+        reply_to: Optional[str] = None,
+    ) -> SendResult:
+        """Send a file as an email attachment."""
+        try:
+            loop = asyncio.get_running_loop()
+            message_id = await loop.run_in_executor(
+                None,
+                self._send_email_with_attachment,
+                chat_id,
+                caption or "",
+                file_path,
+                file_name,
+            )
+            return SendResult(success=True, message_id=message_id)
+        except Exception as e:
+            logger.error("[Email] Send document failed: %s", e)
+            return SendResult(success=False, error=str(e))
+
+    def _send_email_with_attachment(
+        self,
+        to_addr: str,
+        body: str,
+        file_path: str,
+        file_name: Optional[str] = None,
+    ) -> str:
+        """Send an email with a file attachment via SMTP."""
+        msg = MIMEMultipart()
+        msg["From"] = self._address
+        msg["To"] = to_addr
+
+        ctx = self._thread_context.get(to_addr, {})
+        subject = ctx.get("subject", "Hermes Agent")
+        if not subject.startswith("Re:"):
+            subject = f"Re: {subject}"
+        msg["Subject"] = subject
+
+        original_msg_id = ctx.get("message_id")
+        if original_msg_id:
+            msg["In-Reply-To"] = original_msg_id
+            msg["References"] = original_msg_id
+
+        msg_id = f"<hermes-{uuid.uuid4().hex[:12]}@{self._address.split('@')[1]}>"
+        msg["Message-ID"] = msg_id
+
+        if body:
+            msg.attach(MIMEText(body, "plain", "utf-8"))
+
+        # Attach file
+        p = Path(file_path)
+        fname = file_name or p.name
+        with open(p, "rb") as f:
+            part = MIMEBase("application", "octet-stream")
+            part.set_payload(f.read())
+            encoders.encode_base64(part)
+            part.add_header("Content-Disposition", f"attachment; filename={fname}")
+            msg.attach(part)
+
+        smtp = smtplib.SMTP(self._smtp_host, self._smtp_port, timeout=30)
+        try:
+            smtp.starttls(context=ssl.create_default_context())
+            smtp.login(self._address, self._password)
+            smtp.send_message(msg)
+        finally:
+            try:
+                smtp.quit()
+            except Exception:
+                smtp.close()
+
+        return msg_id
+
+    async def get_chat_info(self, chat_id: str) -> Dict[str, Any]:
+        """Return basic info about the email chat."""
+        ctx = self._thread_context.get(chat_id, {})
+        return {
+            "name": chat_id,
+            "type": "dm",
+            "chat_id": chat_id,
+            "subject": ctx.get("subject", ""),
+        }

gateway/platforms/homeassistant.py

@@ -19,7 +19,7 @@ import os
 import time
 import uuid
 from datetime import datetime
-from typing import Any, Dict, List, Optional, Set
+from typing import Any, Dict, Optional, Set
 
 try:
     import aiohttp
@@ -83,6 +83,7 @@ class HomeAssistantAdapter(BasePlatformAdapter):
         self._watch_domains: Set[str] = set(extra.get("watch_domains", []))
         self._watch_entities: Set[str] = set(extra.get("watch_entities", []))
         self._ignore_entities: Set[str] = set(extra.get("ignore_entities", []))
+        self._watch_all: bool = bool(extra.get("watch_all", False))
         self._cooldown_seconds: int = int(extra.get("cooldown_seconds", 30))
 
         # Cooldown tracking: entity_id -> last_event_timestamp
@@ -113,7 +114,18 @@ class HomeAssistantAdapter(BasePlatformAdapter):
                 return False
 
             # Dedicated REST session for send() calls
-            self._rest_session = aiohttp.ClientSession()
+            self._rest_session = aiohttp.ClientSession(
+                timeout=aiohttp.ClientTimeout(total=30)
+            )
+
+            # Warn if no event filters are configured
+            if not self._watch_domains and not self._watch_entities and not self._watch_all:
+                logger.warning(
+                    "[%s] No watch_domains, watch_entities, or watch_all configured. "
+                    "All state_changed events will be dropped. Configure filters in "
+                    "your HA platform config to receive events.",
+                    self.name,
+                )
 
             # Start background listener
             self._listen_task = asyncio.create_task(self._listen_loop())
@@ -130,8 +142,10 @@ class HomeAssistantAdapter(BasePlatformAdapter):
         ws_url = self._hass_url.replace("http://", "ws://").replace("https://", "wss://")
         ws_url = f"{ws_url}/api/websocket"
 
-        self._session = aiohttp.ClientSession()
-        self._ws = await self._session.ws_connect(ws_url, heartbeat=30)
+        self._session = aiohttp.ClientSession(
+            timeout=aiohttp.ClientTimeout(total=30)
+        )
+        self._ws = await self._session.ws_connect(ws_url, heartbeat=30, timeout=30)
 
         # Step 1: Receive auth_required
         msg = await self._ws.receive_json()
@@ -257,13 +271,17 @@ class HomeAssistantAdapter(BasePlatformAdapter):
         if entity_id in self._ignore_entities:
             return
 
-        # Apply domain/entity watch filters
+        # Apply domain/entity watch filters (closed by default — require
+        # explicit watch_domains, watch_entities, or watch_all to forward)
         domain = entity_id.split(".")[0] if "." in entity_id else ""
         if self._watch_domains or self._watch_entities:
             domain_match = domain in self._watch_domains if self._watch_domains else False
             entity_match = entity_id in self._watch_entities if self._watch_entities else False
             if not domain_match and not entity_match:
                 return
+        elif not self._watch_all:
+            # No filters configured and watch_all is off — drop the event
+            return
 
         # Apply cooldown
         now = time.time()
@@ -419,9 +437,8 @@ class HomeAssistantAdapter(BasePlatformAdapter):
         except Exception as e:
             return SendResult(success=False, error=str(e))
 
-    async def send_typing(self, chat_id: str) -> None:
+    async def send_typing(self, chat_id: str, metadata=None) -> None:
         """No typing indicator for Home Assistant."""
-        pass
 
     async def get_chat_info(self, chat_id: str) -> Dict[str, Any]:
         """Return basic info about the HA event channel."""

gateway/platforms/mattermost.py

@@ -0,0 +1,723 @@
+"""Mattermost gateway adapter.
+
+Connects to a self-hosted (or cloud) Mattermost instance via its REST API
+(v4) and WebSocket for real-time events.  No external Mattermost library
+required — uses aiohttp which is already a Hermes dependency.
+
+Environment variables:
+    MATTERMOST_URL              Server URL (e.g. https://mm.example.com)
+    MATTERMOST_TOKEN            Bot token or personal-access token
+    MATTERMOST_ALLOWED_USERS    Comma-separated user IDs
+    MATTERMOST_HOME_CHANNEL     Channel ID for cron/notification delivery
+"""
+
+from __future__ import annotations
+
+import asyncio
+import json
+import logging
+import os
+import re
+import time
+from pathlib import Path
+from typing import Any, Dict, List, Optional
+
+from gateway.config import Platform, PlatformConfig
+from gateway.platforms.base import (
+    BasePlatformAdapter,
+    MessageEvent,
+    MessageType,
+    SendResult,
+)
+
+logger = logging.getLogger(__name__)
+
+# Mattermost post size limit (server default is 16383, but 4000 is the
+# practical limit for readable messages — matching OpenClaw's choice).
+MAX_POST_LENGTH = 4000
+
+# Channel type codes returned by the Mattermost API.
+_CHANNEL_TYPE_MAP = {
+    "D": "dm",
+    "G": "group",
+    "P": "group",   # private channel → treat as group
+    "O": "channel",
+}
+
+# Reconnect parameters (exponential backoff).
+_RECONNECT_BASE_DELAY = 2.0
+_RECONNECT_MAX_DELAY = 60.0
+_RECONNECT_JITTER = 0.2
+
+
+def check_mattermost_requirements() -> bool:
+    """Return True if the Mattermost adapter can be used."""
+    token = os.getenv("MATTERMOST_TOKEN", "")
+    url = os.getenv("MATTERMOST_URL", "")
+    if not token:
+        logger.debug("Mattermost: MATTERMOST_TOKEN not set")
+        return False
+    if not url:
+        logger.warning("Mattermost: MATTERMOST_URL not set")
+        return False
+    try:
+        import aiohttp  # noqa: F401
+        return True
+    except ImportError:
+        logger.warning("Mattermost: aiohttp not installed")
+        return False
+
+
+class MattermostAdapter(BasePlatformAdapter):
+    """Gateway adapter for Mattermost (self-hosted or cloud)."""
+
+    def __init__(self, config: PlatformConfig):
+        super().__init__(config, Platform.MATTERMOST)
+
+        self._base_url: str = (
+            config.extra.get("url", "")
+            or os.getenv("MATTERMOST_URL", "")
+        ).rstrip("/")
+        self._token: str = config.token or os.getenv("MATTERMOST_TOKEN", "")
+
+        self._bot_user_id: str = ""
+        self._bot_username: str = ""
+
+        # aiohttp session + websocket handle
+        self._session: Any = None  # aiohttp.ClientSession
+        self._ws: Any = None       # aiohttp.ClientWebSocketResponse
+        self._ws_task: Optional[asyncio.Task] = None
+        self._reconnect_task: Optional[asyncio.Task] = None
+        self._closing = False
+
+        # Reply mode: "thread" to nest replies, "off" for flat messages.
+        self._reply_mode: str = (
+            config.extra.get("reply_mode", "")
+            or os.getenv("MATTERMOST_REPLY_MODE", "off")
+        ).lower()
+
+        # Dedup cache: post_id → timestamp (prevent reprocessing)
+        self._seen_posts: Dict[str, float] = {}
+        self._SEEN_MAX = 2000
+        self._SEEN_TTL = 300  # 5 minutes
+
+    # ------------------------------------------------------------------
+    # HTTP helpers
+    # ------------------------------------------------------------------
+
+    def _headers(self) -> Dict[str, str]:
+        return {
+            "Authorization": f"Bearer {self._token}",
+            "Content-Type": "application/json",
+        }
+
+    async def _api_get(self, path: str) -> Dict[str, Any]:
+        """GET /api/v4/{path}."""
+        import aiohttp
+        url = f"{self._base_url}/api/v4/{path.lstrip('/')}"
+        try:
+            async with self._session.get(url, headers=self._headers(), timeout=aiohttp.ClientTimeout(total=30)) as resp:
+                if resp.status >= 400:
+                    body = await resp.text()
+                    logger.error("MM API GET %s → %s: %s", path, resp.status, body[:200])
+                    return {}
+                return await resp.json()
+        except aiohttp.ClientError as exc:
+            logger.error("MM API GET %s network error: %s", path, exc)
+            return {}
+
+    async def _api_post(
+        self, path: str, payload: Dict[str, Any]
+    ) -> Dict[str, Any]:
+        """POST /api/v4/{path} with JSON body."""
+        import aiohttp
+        url = f"{self._base_url}/api/v4/{path.lstrip('/')}"
+        try:
+            async with self._session.post(
+                url, headers=self._headers(), json=payload,
+                timeout=aiohttp.ClientTimeout(total=30)
+            ) as resp:
+                if resp.status >= 400:
+                    body = await resp.text()
+                    logger.error("MM API POST %s → %s: %s", path, resp.status, body[:200])
+                    return {}
+                return await resp.json()
+        except aiohttp.ClientError as exc:
+            logger.error("MM API POST %s network error: %s", path, exc)
+            return {}
+
+    async def _api_put(
+        self, path: str, payload: Dict[str, Any]
+    ) -> Dict[str, Any]:
+        """PUT /api/v4/{path} with JSON body."""
+        import aiohttp
+        url = f"{self._base_url}/api/v4/{path.lstrip('/')}"
+        try:
+            async with self._session.put(
+                url, headers=self._headers(), json=payload
+            ) as resp:
+                if resp.status >= 400:
+                    body = await resp.text()
+                    logger.error("MM API PUT %s → %s: %s", path, resp.status, body[:200])
+                    return {}
+                return await resp.json()
+        except aiohttp.ClientError as exc:
+            logger.error("MM API PUT %s network error: %s", path, exc)
+            return {}
+
+    async def _upload_file(
+        self, channel_id: str, file_data: bytes, filename: str, content_type: str = "application/octet-stream"
+    ) -> Optional[str]:
+        """Upload a file and return its file ID, or None on failure."""
+        import aiohttp
+
+        url = f"{self._base_url}/api/v4/files"
+        form = aiohttp.FormData()
+        form.add_field("channel_id", channel_id)
+        form.add_field(
+            "files",
+            file_data,
+            filename=filename,
+            content_type=content_type,
+        )
+        headers = {"Authorization": f"Bearer {self._token}"}
+        async with self._session.post(url, headers=headers, data=form, timeout=aiohttp.ClientTimeout(total=60)) as resp:
+            if resp.status >= 400:
+                body = await resp.text()
+                logger.error("MM file upload → %s: %s", resp.status, body[:200])
+                return None
+            data = await resp.json()
+            infos = data.get("file_infos", [])
+            return infos[0]["id"] if infos else None
+
+    # ------------------------------------------------------------------
+    # Required overrides
+    # ------------------------------------------------------------------
+
+    async def connect(self) -> bool:
+        """Connect to Mattermost and start the WebSocket listener."""
+        import aiohttp
+
+        if not self._base_url or not self._token:
+            logger.error("Mattermost: URL or token not configured")
+            return False
+
+        self._session = aiohttp.ClientSession(
+            timeout=aiohttp.ClientTimeout(total=30)
+        )
+        self._closing = False
+
+        # Verify credentials and fetch bot identity.
+        me = await self._api_get("users/me")
+        if not me or "id" not in me:
+            logger.error("Mattermost: failed to authenticate — check MATTERMOST_TOKEN and MATTERMOST_URL")
+            await self._session.close()
+            return False
+
+        self._bot_user_id = me["id"]
+        self._bot_username = me.get("username", "")
+        logger.info(
+            "Mattermost: authenticated as @%s (%s) on %s",
+            self._bot_username,
+            self._bot_user_id,
+            self._base_url,
+        )
+
+        # Start WebSocket in background.
+        self._ws_task = asyncio.create_task(self._ws_loop())
+        self._mark_connected()
+        return True
+
+    async def disconnect(self) -> None:
+        """Disconnect from Mattermost."""
+        self._closing = True
+
+        if self._ws_task and not self._ws_task.done():
+            self._ws_task.cancel()
+            try:
+                await self._ws_task
+            except (asyncio.CancelledError, Exception):
+                pass
+
+        if self._reconnect_task and not self._reconnect_task.done():
+            self._reconnect_task.cancel()
+
+        if self._ws:
+            await self._ws.close()
+            self._ws = None
+
+        if self._session and not self._session.closed:
+            await self._session.close()
+
+        logger.info("Mattermost: disconnected")
+
+    async def send(
+        self,
+        chat_id: str,
+        content: str,
+        reply_to: Optional[str] = None,
+        metadata: Optional[Dict[str, Any]] = None,
+    ) -> SendResult:
+        """Send a message (or multiple chunks) to a channel."""
+        if not content:
+            return SendResult(success=True)
+
+        formatted = self.format_message(content)
+        chunks = self.truncate_message(formatted, MAX_POST_LENGTH)
+
+        last_id = None
+        for chunk in chunks:
+            payload: Dict[str, Any] = {
+                "channel_id": chat_id,
+                "message": chunk,
+            }
+            # Thread support: reply_to is the root post ID.
+            if reply_to and self._reply_mode == "thread":
+                payload["root_id"] = reply_to
+
+            data = await self._api_post("posts", payload)
+            if not data or "id" not in data:
+                return SendResult(success=False, error="Failed to create post")
+            last_id = data["id"]
+
+        return SendResult(success=True, message_id=last_id)
+
+    async def get_chat_info(self, chat_id: str) -> Dict[str, Any]:
+        """Return channel name and type."""
+        data = await self._api_get(f"channels/{chat_id}")
+        if not data:
+            return {"name": chat_id, "type": "channel"}
+
+        ch_type = _CHANNEL_TYPE_MAP.get(data.get("type", "O"), "channel")
+        display_name = data.get("display_name") or data.get("name") or chat_id
+        return {"name": display_name, "type": ch_type}
+
+    # ------------------------------------------------------------------
+    # Optional overrides
+    # ------------------------------------------------------------------
+
+    async def send_typing(
+        self, chat_id: str, metadata: Optional[Dict[str, Any]] = None
+    ) -> None:
+        """Send a typing indicator."""
+        await self._api_post(
+            f"users/{self._bot_user_id}/typing",
+            {"channel_id": chat_id},
+        )
+
+    async def edit_message(
+        self, chat_id: str, message_id: str, content: str
+    ) -> SendResult:
+        """Edit an existing post."""
+        formatted = self.format_message(content)
+        data = await self._api_put(
+            f"posts/{message_id}/patch",
+            {"message": formatted},
+        )
+        if not data or "id" not in data:
+            return SendResult(success=False, error="Failed to edit post")
+        return SendResult(success=True, message_id=data["id"])
+
+    async def send_image(
+        self,
+        chat_id: str,
+        image_url: str,
+        caption: Optional[str] = None,
+        reply_to: Optional[str] = None,
+        metadata: Optional[Dict[str, Any]] = None,
+    ) -> SendResult:
+        """Download an image and upload it as a file attachment."""
+        return await self._send_url_as_file(
+            chat_id, image_url, caption, reply_to, "image"
+        )
+
+    async def send_image_file(
+        self,
+        chat_id: str,
+        image_path: str,
+        caption: Optional[str] = None,
+        reply_to: Optional[str] = None,
+        metadata: Optional[Dict[str, Any]] = None,
+    ) -> SendResult:
+        """Upload a local image file."""
+        return await self._send_local_file(
+            chat_id, image_path, caption, reply_to
+        )
+
+    async def send_document(
+        self,
+        chat_id: str,
+        file_path: str,
+        caption: Optional[str] = None,
+        file_name: Optional[str] = None,
+        reply_to: Optional[str] = None,
+        metadata: Optional[Dict[str, Any]] = None,
+    ) -> SendResult:
+        """Upload a local file as a document."""
+        return await self._send_local_file(
+            chat_id, file_path, caption, reply_to, file_name
+        )
+
+    async def send_voice(
+        self,
+        chat_id: str,
+        audio_path: str,
+        caption: Optional[str] = None,
+        reply_to: Optional[str] = None,
+        metadata: Optional[Dict[str, Any]] = None,
+    ) -> SendResult:
+        """Upload an audio file."""
+        return await self._send_local_file(
+            chat_id, audio_path, caption, reply_to
+        )
+
+    async def send_video(
+        self,
+        chat_id: str,
+        video_path: str,
+        caption: Optional[str] = None,
+        reply_to: Optional[str] = None,
+        metadata: Optional[Dict[str, Any]] = None,
+    ) -> SendResult:
+        """Upload a video file."""
+        return await self._send_local_file(
+            chat_id, video_path, caption, reply_to
+        )
+
+    def format_message(self, content: str) -> str:
+        """Mattermost uses standard Markdown — mostly pass through.
+
+        Strip image markdown into plain links (files are uploaded separately).
+        """
+        # Convert ![alt](url) to just the URL — Mattermost renders
+        # image URLs as inline previews automatically.
+        content = re.sub(r"!\[([^\]]*)\]\(([^)]+)\)", r"\2", content)
+        return content
+
+    # ------------------------------------------------------------------
+    # File helpers
+    # ------------------------------------------------------------------
+
+    async def _send_url_as_file(
+        self,
+        chat_id: str,
+        url: str,
+        caption: Optional[str],
+        reply_to: Optional[str],
+        kind: str = "file",
+    ) -> SendResult:
+        """Download a URL and upload it as a file attachment."""
+        import asyncio
+        import aiohttp
+
+        last_exc = None
+        file_data = None
+        ct = "application/octet-stream"
+        fname = url.rsplit("/", 1)[-1].split("?")[0] or f"{kind}.png"
+
+        for attempt in range(3):
+            try:
+                async with self._session.get(url, timeout=aiohttp.ClientTimeout(total=30)) as resp:
+                    if resp.status >= 500 or resp.status == 429:
+                        if attempt < 2:
+                            logger.debug("Mattermost download retry %d/2 for %s (status %d)",
+                                         attempt + 1, url[:80], resp.status)
+                            await asyncio.sleep(1.5 * (attempt + 1))
+                            continue
+                    if resp.status >= 400:
+                        return await self.send(chat_id, f"{caption or ''}\n{url}".strip(), reply_to)
+                    file_data = await resp.read()
+                    ct = resp.content_type or "application/octet-stream"
+                    break
+            except (aiohttp.ClientError, asyncio.TimeoutError) as exc:
+                last_exc = exc
+                if attempt < 2:
+                    await asyncio.sleep(1.5 * (attempt + 1))
+                    continue
+                logger.warning("Mattermost: failed to download %s after %d attempts: %s", url, attempt + 1, exc)
+                return await self.send(chat_id, f"{caption or ''}\n{url}".strip(), reply_to)
+
+        if file_data is None:
+            logger.warning("Mattermost: download returned no data for %s", url)
+            return await self.send(chat_id, f"{caption or ''}\n{url}".strip(), reply_to)
+
+        file_id = await self._upload_file(chat_id, file_data, fname, ct)
+        if not file_id:
+            return await self.send(chat_id, f"{caption or ''}\n{url}".strip(), reply_to)
+
+        payload: Dict[str, Any] = {
+            "channel_id": chat_id,
+            "message": caption or "",
+            "file_ids": [file_id],
+        }
+        if reply_to and self._reply_mode == "thread":
+            payload["root_id"] = reply_to
+
+        data = await self._api_post("posts", payload)
+        if not data or "id" not in data:
+            return SendResult(success=False, error="Failed to post with file")
+        return SendResult(success=True, message_id=data["id"])
+
+    async def _send_local_file(
+        self,
+        chat_id: str,
+        file_path: str,
+        caption: Optional[str],
+        reply_to: Optional[str],
+        file_name: Optional[str] = None,
+    ) -> SendResult:
+        """Upload a local file and attach it to a post."""
+        import mimetypes
+
+        p = Path(file_path)
+        if not p.exists():
+            return await self.send(
+                chat_id, f"{caption or ''}\n(file not found: {file_path})", reply_to
+            )
+
+        fname = file_name or p.name
+        ct = mimetypes.guess_type(fname)[0] or "application/octet-stream"
+        file_data = p.read_bytes()
+
+        file_id = await self._upload_file(chat_id, file_data, fname, ct)
+        if not file_id:
+            return SendResult(success=False, error="File upload failed")
+
+        payload: Dict[str, Any] = {
+            "channel_id": chat_id,
+            "message": caption or "",
+            "file_ids": [file_id],
+        }
+        if reply_to and self._reply_mode == "thread":
+            payload["root_id"] = reply_to
+
+        data = await self._api_post("posts", payload)
+        if not data or "id" not in data:
+            return SendResult(success=False, error="Failed to post with file")
+        return SendResult(success=True, message_id=data["id"])
+
+    # ------------------------------------------------------------------
+    # WebSocket
+    # ------------------------------------------------------------------
+
+    async def _ws_loop(self) -> None:
+        """Connect to the WebSocket and listen for events, reconnecting on failure."""
+        delay = _RECONNECT_BASE_DELAY
+        while not self._closing:
+            try:
+                await self._ws_connect_and_listen()
+                # Clean disconnect — reset delay.
+                delay = _RECONNECT_BASE_DELAY
+            except asyncio.CancelledError:
+                return
+            except Exception as exc:
+                if self._closing:
+                    return
+                logger.warning("Mattermost WS error: %s — reconnecting in %.0fs", exc, delay)
+
+            if self._closing:
+                return
+
+            # Exponential backoff with jitter.
+            import random
+            jitter = delay * _RECONNECT_JITTER * random.random()
+            await asyncio.sleep(delay + jitter)
+            delay = min(delay * 2, _RECONNECT_MAX_DELAY)
+
+    async def _ws_connect_and_listen(self) -> None:
+        """Single WebSocket session: connect, authenticate, process events."""
+        # Build WS URL: https:// → wss://, http:// → ws://
+        ws_url = re.sub(r"^http", "ws", self._base_url) + "/api/v4/websocket"
+        logger.info("Mattermost: connecting to %s", ws_url)
+
+        self._ws = await self._session.ws_connect(ws_url, heartbeat=30.0)
+
+        # Authenticate via the WebSocket.
+        auth_msg = {
+            "seq": 1,
+            "action": "authentication_challenge",
+            "data": {"token": self._token},
+        }
+        await self._ws.send_json(auth_msg)
+        logger.info("Mattermost: WebSocket connected and authenticated")
+
+        async for raw_msg in self._ws:
+            if self._closing:
+                return
+
+            if raw_msg.type in (
+                raw_msg.type.TEXT,
+                raw_msg.type.BINARY,
+            ):
+                try:
+                    event = json.loads(raw_msg.data)
+                except (json.JSONDecodeError, TypeError):
+                    continue
+                await self._handle_ws_event(event)
+            elif raw_msg.type in (
+                raw_msg.type.ERROR,
+                raw_msg.type.CLOSE,
+                raw_msg.type.CLOSING,
+                raw_msg.type.CLOSED,
+            ):
+                logger.info("Mattermost: WebSocket closed (%s)", raw_msg.type)
+                break
+
+    async def _handle_ws_event(self, event: Dict[str, Any]) -> None:
+        """Process a single WebSocket event."""
+        event_type = event.get("event")
+        if event_type != "posted":
+            return
+
+        data = event.get("data", {})
+        raw_post_str = data.get("post")
+        if not raw_post_str:
+            return
+
+        try:
+            post = json.loads(raw_post_str)
+        except (json.JSONDecodeError, TypeError):
+            return
+
+        # Ignore own messages.
+        if post.get("user_id") == self._bot_user_id:
+            return
+
+        # Ignore system posts.
+        if post.get("type"):
+            return
+
+        post_id = post.get("id", "")
+
+        # Dedup.
+        self._prune_seen()
+        if post_id in self._seen_posts:
+            return
+        self._seen_posts[post_id] = time.time()
+
+        # Build message event.
+        channel_id = post.get("channel_id", "")
+        channel_type_raw = data.get("channel_type", "O")
+        chat_type = _CHANNEL_TYPE_MAP.get(channel_type_raw, "channel")
+
+        # For DMs, user_id is sufficient.  For channels, check for @mention.
+        message_text = post.get("message", "")
+
+        # Mention-gating for non-DM channels.
+        # Config (env vars):
+        #   MATTERMOST_REQUIRE_MENTION: Require @mention in channels (default: true)
+        #   MATTERMOST_FREE_RESPONSE_CHANNELS: Channel IDs where bot responds without mention
+        if channel_type_raw != "D":
+            require_mention = os.getenv(
+                "MATTERMOST_REQUIRE_MENTION", "true"
+            ).lower() not in ("false", "0", "no")
+
+            free_channels_raw = os.getenv("MATTERMOST_FREE_RESPONSE_CHANNELS", "")
+            free_channels = {ch.strip() for ch in free_channels_raw.split(",") if ch.strip()}
+            is_free_channel = channel_id in free_channels
+
+            mention_patterns = [
+                f"@{self._bot_username}",
+                f"@{self._bot_user_id}",
+            ]
+            has_mention = any(
+                pattern.lower() in message_text.lower()
+                for pattern in mention_patterns
+            )
+
+            if require_mention and not is_free_channel and not has_mention:
+                logger.debug(
+                    "Mattermost: skipping non-DM message without @mention (channel=%s)",
+                    channel_id,
+                )
+                return
+
+            # Strip @mention from the message text so the agent sees clean input.
+            if has_mention:
+                for pattern in mention_patterns:
+                    message_text = re.sub(
+                        re.escape(pattern), "", message_text, flags=re.IGNORECASE
+                    ).strip()
+
+        # Resolve sender info.
+        sender_id = post.get("user_id", "")
+        sender_name = data.get("sender_name", "").lstrip("@") or sender_id
+
+        # Thread support: if the post is in a thread, use root_id.
+        thread_id = post.get("root_id") or None
+
+        # Determine message type.
+        file_ids = post.get("file_ids") or []
+        msg_type = MessageType.TEXT
+        if message_text.startswith("/"):
+            msg_type = MessageType.COMMAND
+
+        # Download file attachments immediately (URLs require auth headers
+        # that downstream tools won't have).
+        media_urls: List[str] = []
+        media_types: List[str] = []
+        for fid in file_ids:
+            try:
+                file_info = await self._api_get(f"files/{fid}/info")
+                fname = file_info.get("name", f"file_{fid}")
+                ext = Path(fname).suffix or ""
+                mime = file_info.get("mime_type", "application/octet-stream")
+
+                import aiohttp
+                dl_url = f"{self._base_url}/api/v4/files/{fid}"
+                async with self._session.get(
+                    dl_url,
+                    headers={"Authorization": f"Bearer {self._token}"},
+                    timeout=aiohttp.ClientTimeout(total=30),
+                ) as resp:
+                    if resp.status < 400:
+                        file_data = await resp.read()
+                        from gateway.platforms.base import cache_image_from_bytes, cache_document_from_bytes
+                        if mime.startswith("image/"):
+                            local_path = cache_image_from_bytes(file_data, ext or ".png")
+                            media_urls.append(local_path)
+                            media_types.append(mime)
+                        elif mime.startswith("audio/"):
+                            from gateway.platforms.base import cache_audio_from_bytes
+                            local_path = cache_audio_from_bytes(file_data, ext or ".ogg")
+                            media_urls.append(local_path)
+                            media_types.append(mime)
+                        else:
+                            local_path = cache_document_from_bytes(file_data, fname)
+                            media_urls.append(local_path)
+                            media_types.append(mime)
+                    else:
+                        logger.warning("Mattermost: failed to download file %s: HTTP %s", fid, resp.status)
+            except Exception as exc:
+                logger.warning("Mattermost: error downloading file %s: %s", fid, exc)
+
+        source = self.build_source(
+            chat_id=channel_id,
+            chat_type=chat_type,
+            user_id=sender_id,
+            user_name=sender_name,
+            thread_id=thread_id,
+        )
+
+        msg_event = MessageEvent(
+            text=message_text,
+            message_type=msg_type,
+            source=source,
+            raw_message=post,
+            message_id=post_id,
+            media_urls=media_urls if media_urls else None,
+            media_types=media_types if media_types else None,
+        )
+
+        await self.handle_message(msg_event)
+
+    def _prune_seen(self) -> None:
+        """Remove expired entries from the dedup cache."""
+        if len(self._seen_posts) < self._SEEN_MAX:
+            return
+        now = time.time()
+        self._seen_posts = {
+            pid: ts
+            for pid, ts in self._seen_posts.items()
+            if now - ts < self._SEEN_TTL
+        }

gateway/platforms/signal.py

@@ -22,7 +22,7 @@ import time
 from datetime import datetime, timezone
 from pathlib import Path
 from typing import Dict, List, Optional, Any
-from urllib.parse import unquote
+from urllib.parse import quote, unquote
 
 import httpx
 
@@ -104,6 +104,20 @@ def _is_audio_ext(ext: str) -> bool:
     return ext.lower() in (".mp3", ".wav", ".ogg", ".m4a", ".aac")
 
 
+_EXT_TO_MIME = {
+    ".jpg": "image/jpeg", ".jpeg": "image/jpeg", ".png": "image/png",
+    ".gif": "image/gif", ".webp": "image/webp",
+    ".ogg": "audio/ogg", ".mp3": "audio/mpeg", ".wav": "audio/wav",
+    ".m4a": "audio/mp4", ".aac": "audio/aac",
+    ".mp4": "video/mp4", ".pdf": "application/pdf", ".zip": "application/zip",
+}
+
+
+def _ext_to_mime(ext: str) -> str:
+    """Map file extension to MIME type."""
+    return _EXT_TO_MIME.get(ext.lower(), "application/octet-stream")
+
+
 def _render_mentions(text: str, mentions: list) -> str:
     """Replace Signal mention placeholders (\\uFFFC) with readable @identifiers.
 
@@ -165,6 +179,13 @@ class SignalAdapter(BasePlatformAdapter):
         # Normalize account for self-message filtering
         self._account_normalized = self.account.strip()
 
+        # Track recently sent message timestamps to prevent echo-back loops
+        # in Note to Self / self-chat mode (mirrors WhatsApp recentlySentIds)
+        self._recent_sent_timestamps: set = set()
+        self._max_recent_timestamps = 50
+
+        self._phone_lock_identity: Optional[str] = None
+
         logger.info("Signal adapter initialized: url=%s account=%s groups=%s",
                      self.http_url, _redact_phone(self.account),
                      "enabled" if self.group_allow_from else "disabled")
@@ -179,6 +200,29 @@ class SignalAdapter(BasePlatformAdapter):
             logger.error("Signal: SIGNAL_HTTP_URL and SIGNAL_ACCOUNT are required")
             return False
 
+        # Acquire scoped lock to prevent duplicate Signal listeners for the same phone
+        try:
+            from gateway.status import acquire_scoped_lock
+
+            self._phone_lock_identity = self.account
+            acquired, existing = acquire_scoped_lock(
+                "signal-phone",
+                self._phone_lock_identity,
+                metadata={"platform": self.platform.value},
+            )
+            if not acquired:
+                owner_pid = existing.get("pid") if isinstance(existing, dict) else None
+                message = (
+                    "Another local Hermes gateway is already using this Signal account"
+                    + (f" (PID {owner_pid})." if owner_pid else ".")
+                    + " Stop the other gateway before starting a second Signal listener."
+                )
+                logger.error("Signal: %s", message)
+                self._set_fatal_error("signal_phone_lock", message, retryable=False)
+                return False
+        except Exception as e:
+            logger.warning("Signal: Could not acquire phone lock (non-fatal): %s", e)
+
         self.client = httpx.AsyncClient(timeout=30.0)
 
         # Health check — verify signal-cli daemon is reachable
@@ -226,6 +270,14 @@ class SignalAdapter(BasePlatformAdapter):
             await self.client.aclose()
             self.client = None
 
+        if self._phone_lock_identity:
+            try:
+                from gateway.status import release_scoped_lock
+                release_scoped_lock("signal-phone", self._phone_lock_identity)
+            except Exception as e:
+                logger.warning("Signal: Error releasing phone lock: %s", e, exc_info=True)
+            self._phone_lock_identity = None
+
         logger.info("Signal: disconnected")
 
     # ------------------------------------------------------------------
@@ -234,7 +286,7 @@ class SignalAdapter(BasePlatformAdapter):
 
     async def _sse_listener(self) -> None:
         """Listen for SSE events from signal-cli daemon."""
-        url = f"{self.http_url}/api/v1/events?account={self.account}"
+        url = f"{self.http_url}/api/v1/events?account={quote(self.account, safe='')}"
         backoff = SSE_RETRY_DELAY_INITIAL
 
         while self._running:
@@ -260,6 +312,12 @@ class SignalAdapter(BasePlatformAdapter):
                             line = line.strip()
                             if not line:
                                 continue
+                            # SSE keepalive comments (":") prove the connection
+                            # is alive — update activity so the health monitor
+                            # doesn't report false idle warnings.
+                            if line.startswith(":"):
+                                self._last_sse_activity = time.time()
+                                continue
                             # Parse SSE data lines
                             if line.startswith("data:"):
                                 data_str = line[5:].strip()
@@ -325,7 +383,9 @@ class SignalAdapter(BasePlatformAdapter):
         """Force SSE reconnection by closing the current response."""
         if self._sse_response and not self._sse_response.is_stream_consumed:
             try:
-                asyncio.create_task(self._sse_response.aclose())
+                task = asyncio.create_task(self._sse_response.aclose())
+                self._background_tasks.add(task)
+                task.add_done_callback(self._background_tasks.discard)
             except Exception:
                 pass
             self._sse_response = None
@@ -339,10 +399,26 @@ class SignalAdapter(BasePlatformAdapter):
         # Unwrap nested envelope if present
         envelope_data = envelope.get("envelope", envelope)
 
-        # Filter syncMessage envelopes (sent transcripts, read receipts, etc.)
-        # signal-cli may set syncMessage to null vs omitting it, so check key existence
+        # Handle syncMessage: extract "Note to Self" messages (sent to own account)
+        # while still filtering other sync events (read receipts, typing, etc.)
+        is_note_to_self = False
         if "syncMessage" in envelope_data:
-            return
+            sync_msg = envelope_data.get("syncMessage")
+            if sync_msg and isinstance(sync_msg, dict):
+                sent_msg = sync_msg.get("sentMessage")
+                if sent_msg and isinstance(sent_msg, dict):
+                    dest = sent_msg.get("destinationNumber") or sent_msg.get("destination")
+                    sent_ts = sent_msg.get("timestamp")
+                    if dest == self._account_normalized:
+                        # Check if this is an echo of our own outbound reply
+                        if sent_ts and sent_ts in self._recent_sent_timestamps:
+                            self._recent_sent_timestamps.discard(sent_ts)
+                            return
+                        # Genuine user Note to Self — promote to dataMessage
+                        is_note_to_self = True
+                        envelope_data = {**envelope_data, "dataMessage": sent_msg}
+            if not is_note_to_self:
+                return
 
         # Extract sender info
         sender = (
@@ -357,8 +433,8 @@ class SignalAdapter(BasePlatformAdapter):
             logger.debug("Signal: ignoring envelope with no sender")
             return
 
-        # Self-message filtering — prevent reply loops
-        if self._account_normalized and sender == self._account_normalized:
+        # Self-message filtering — prevent reply loops (but allow Note to Self)
+        if self._account_normalized and sender == self._account_normalized and not is_note_to_self:
             return
 
         # Filter stories
@@ -404,9 +480,8 @@ class SignalAdapter(BasePlatformAdapter):
 
         # Process attachments
         attachments_data = data_message.get("attachments", [])
-        image_paths = []
-        audio_path = None
-        document_paths = []
+        media_urls = []
+        media_types = []
 
         if attachments_data and not getattr(self, "ignore_attachments", False):
             for att in attachments_data:
@@ -420,12 +495,10 @@ class SignalAdapter(BasePlatformAdapter):
                 try:
                     cached_path, ext = await self._fetch_attachment(att_id)
                     if cached_path:
-                        if _is_image_ext(ext):
-                            image_paths.append(cached_path)
-                        elif _is_audio_ext(ext):
-                            audio_path = cached_path
-                        else:
-                            document_paths.append(cached_path)
+                        # Use contentType from Signal if available, else map from extension
+                        content_type = att.get("contentType") or _ext_to_mime(ext)
+                        media_urls.append(cached_path)
+                        media_types.append(content_type)
                 except Exception:
                     logger.exception("Signal: failed to fetch attachment %s", att_id)
 
@@ -440,12 +513,13 @@ class SignalAdapter(BasePlatformAdapter):
             chat_id_alt=group_id if is_group else None,
         )
 
-        # Determine message type
+        # Determine message type from media
         msg_type = MessageType.TEXT
-        if audio_path:
-            msg_type = MessageType.VOICE
-        elif image_paths:
-            msg_type = MessageType.IMAGE
+        if media_types:
+            if any(mt.startswith("audio/") for mt in media_types):
+                msg_type = MessageType.VOICE
+            elif any(mt.startswith("image/") for mt in media_types):
+                msg_type = MessageType.PHOTO
 
         # Parse timestamp from envelope data (milliseconds since epoch)
         ts_ms = envelope_data.get("timestamp", 0)
@@ -462,9 +536,8 @@ class SignalAdapter(BasePlatformAdapter):
             source=source,
             text=text or "",
             message_type=msg_type,
-            image_paths=image_paths,
-            audio_path=audio_path,
-            document_paths=document_paths,
+            media_urls=media_urls,
+            media_types=media_types,
             timestamp=timestamp,
         )
 
@@ -481,12 +554,19 @@ class SignalAdapter(BasePlatformAdapter):
         """Fetch an attachment via JSON-RPC and cache it. Returns (path, ext)."""
         result = await self._rpc("getAttachment", {
             "account": self.account,
-            "attachmentId": attachment_id,
+            "id": attachment_id,
         })
 
         if not result:
             return None, ""
 
+        # Handle dict response (signal-cli returns {"data": "base64..."})
+        if isinstance(result, dict):
+            result = result.get("data")
+            if not result:
+                logger.warning("Signal: attachment response missing 'data' key")
+                return None, ""
+
         # Result is base64-encoded file content
         raw_data = base64.b64decode(result)
         ext = _guess_extension(raw_data)
@@ -546,16 +626,16 @@ class SignalAdapter(BasePlatformAdapter):
     async def send(
         self,
         chat_id: str,
-        text: str,
-        reply_to_message_id: Optional[str] = None,
-        **kwargs,
+        content: str,
+        reply_to: Optional[str] = None,
+        metadata: Optional[Dict[str, Any]] = None,
     ) -> SendResult:
         """Send a text message."""
         await self._stop_typing_indicator(chat_id)
 
         params: Dict[str, Any] = {
             "account": self.account,
-            "message": text,
+            "message": content,
         }
 
         if chat_id.startswith("group:"):
@@ -566,10 +646,19 @@ class SignalAdapter(BasePlatformAdapter):
         result = await self._rpc("send", params)
 
         if result is not None:
+            self._track_sent_timestamp(result)
             return SendResult(success=True)
         return SendResult(success=False, error="RPC send failed")
 
-    async def send_typing(self, chat_id: str) -> None:
+    def _track_sent_timestamp(self, rpc_result) -> None:
+        """Record outbound message timestamp for echo-back filtering."""
+        ts = rpc_result.get("timestamp") if isinstance(rpc_result, dict) else None
+        if ts:
+            self._recent_sent_timestamps.add(ts)
+            if len(self._recent_sent_timestamps) > self._max_recent_timestamps:
+                self._recent_sent_timestamps.pop()
+
+    async def send_typing(self, chat_id: str, metadata=None) -> None:
         """Send a typing indicator."""
         params: Dict[str, Any] = {
             "account": self.account,
@@ -624,6 +713,7 @@ class SignalAdapter(BasePlatformAdapter):
 
         result = await self._rpc("send", params)
         if result is not None:
+            self._track_sent_timestamp(result)
             return SendResult(success=True)
         return SendResult(success=False, error="RPC send with attachment failed")
 
@@ -654,6 +744,7 @@ class SignalAdapter(BasePlatformAdapter):
 
         result = await self._rpc("send", params)
         if result is not None:
+            self._track_sent_timestamp(result)
             return SendResult(success=True)
         return SendResult(success=False, error="RPC send document failed")
 

gateway/platforms/slack.py

@@ -9,9 +9,11 @@ Uses slack-bolt (Python) with Socket Mode for:
 """
 
 import asyncio
+import json
+import logging
 import os
 import re
-from typing import Dict, List, Optional, Any
+from typing import Dict, Optional, Any
 
 try:
     from slack_bolt.async_app import AsyncApp
@@ -36,11 +38,12 @@ from gateway.platforms.base import (
     SendResult,
     SUPPORTED_DOCUMENT_TYPES,
     cache_document_from_bytes,
-    cache_image_from_url,
-    cache_audio_from_url,
 )
 
 
+logger = logging.getLogger(__name__)
+
+
 def check_slack_requirements() -> bool:
     """Check if Slack dependencies are available."""
     return SLACK_AVAILABLE
@@ -62,37 +65,92 @@ class SlackAdapter(BasePlatformAdapter):
       - Typing indicators (not natively supported by Slack bots)
     """
 
-    MAX_MESSAGE_LENGTH = 4000  # Slack's limit is higher but mrkdwn can inflate
+    MAX_MESSAGE_LENGTH = 39000  # Slack API allows 40,000 chars; leave margin
 
     def __init__(self, config: PlatformConfig):
         super().__init__(config, Platform.SLACK)
         self._app: Optional[AsyncApp] = None
         self._handler: Optional[AsyncSocketModeHandler] = None
         self._bot_user_id: Optional[str] = None
+        self._user_name_cache: Dict[str, str] = {}  # user_id → display name
+        self._socket_mode_task: Optional[asyncio.Task] = None
+        # Multi-workspace support
+        self._team_clients: Dict[str, AsyncWebClient] = {}   # team_id → WebClient
+        self._team_bot_user_ids: Dict[str, str] = {}          # team_id → bot_user_id
+        self._channel_team: Dict[str, str] = {}                # channel_id → team_id
 
     async def connect(self) -> bool:
         """Connect to Slack via Socket Mode."""
         if not SLACK_AVAILABLE:
-            print("[Slack] slack-bolt not installed. Run: pip install slack-bolt")
+            logger.error(
+                "[Slack] slack-bolt not installed. Run: pip install slack-bolt",
+            )
             return False
 
-        bot_token = self.config.token
+        raw_token = self.config.token
         app_token = os.getenv("SLACK_APP_TOKEN")
 
-        if not bot_token:
-            print("[Slack] SLACK_BOT_TOKEN not set")
+        if not raw_token:
+            logger.error("[Slack] SLACK_BOT_TOKEN not set")
             return False
         if not app_token:
-            print("[Slack] SLACK_APP_TOKEN not set")
+            logger.error("[Slack] SLACK_APP_TOKEN not set")
             return False
 
-        try:
-            self._app = AsyncApp(token=bot_token)
+        # Support comma-separated bot tokens for multi-workspace
+        bot_tokens = [t.strip() for t in raw_token.split(",") if t.strip()]
 
-            # Get our own bot user ID for mention detection
-            auth_response = await self._app.client.auth_test()
-            self._bot_user_id = auth_response.get("user_id")
-            bot_name = auth_response.get("user", "unknown")
+        # Also load tokens from OAuth token file
+        from hermes_constants import get_hermes_home
+        tokens_file = get_hermes_home() / "slack_tokens.json"
+        if tokens_file.exists():
+            try:
+                saved = json.loads(tokens_file.read_text(encoding="utf-8"))
+                for team_id, entry in saved.items():
+                    tok = entry.get("token", "") if isinstance(entry, dict) else ""
+                    if tok and tok not in bot_tokens:
+                        bot_tokens.append(tok)
+                        team_label = entry.get("team_name", team_id) if isinstance(entry, dict) else team_id
+                        logger.info("[Slack] Loaded saved token for workspace %s", team_label)
+            except Exception as e:
+                logger.warning("[Slack] Failed to read %s: %s", tokens_file, e)
+
+        try:
+            # Acquire scoped lock to prevent duplicate app token usage
+            from gateway.status import acquire_scoped_lock
+            self._token_lock_identity = app_token
+            acquired, existing = acquire_scoped_lock('slack-app-token', app_token, metadata={'platform': 'slack'})
+            if not acquired:
+                owner_pid = existing.get('pid') if isinstance(existing, dict) else None
+                message = f'Slack app token already in use' + (f' (PID {owner_pid})' if owner_pid else '') + '. Stop the other gateway first.'
+                logger.error('[%s] %s', self.name, message)
+                self._set_fatal_error('slack_token_lock', message, retryable=False)
+                return False
+
+            # First token is the primary — used for AsyncApp / Socket Mode
+            primary_token = bot_tokens[0]
+            self._app = AsyncApp(token=primary_token)
+
+            # Register each bot token and map team_id → client
+            for token in bot_tokens:
+                client = AsyncWebClient(token=token)
+                auth_response = await client.auth_test()
+                team_id = auth_response.get("team_id", "")
+                bot_user_id = auth_response.get("user_id", "")
+                bot_name = auth_response.get("user", "unknown")
+                team_name = auth_response.get("team", "unknown")
+
+                self._team_clients[team_id] = client
+                self._team_bot_user_ids[team_id] = bot_user_id
+
+                # First token sets the primary bot_user_id (backward compat)
+                if self._bot_user_id is None:
+                    self._bot_user_id = bot_user_id
+
+                logger.info(
+                    "[Slack] Authenticated as @%s in workspace %s (team: %s)",
+                    bot_name, team_name, team_id,
+                )
 
             # Register message event handler
             @self._app.event("message")
@@ -114,22 +172,45 @@ class SlackAdapter(BasePlatformAdapter):
 
             # Start Socket Mode handler in background
             self._handler = AsyncSocketModeHandler(self._app, app_token)
-            asyncio.create_task(self._handler.start_async())
+            self._socket_mode_task = asyncio.create_task(self._handler.start_async())
 
             self._running = True
-            print(f"[Slack] Connected as @{bot_name} (Socket Mode)")
+            logger.info(
+                "[Slack] Socket Mode connected (%d workspace(s))",
+                len(self._team_clients),
+            )
             return True
 
-        except Exception as e:
-            print(f"[Slack] Connection failed: {e}")
+        except Exception as e:  # pragma: no cover - defensive logging
+            logger.error("[Slack] Connection failed: %s", e, exc_info=True)
             return False
 
     async def disconnect(self) -> None:
         """Disconnect from Slack."""
         if self._handler:
-            await self._handler.close_async()
+            try:
+                await self._handler.close_async()
+            except Exception as e:  # pragma: no cover - defensive logging
+                logger.warning("[Slack] Error while closing Socket Mode handler: %s", e, exc_info=True)
         self._running = False
-        print("[Slack] Disconnected")
+
+        # Release the token lock (use stored identity, not re-read env)
+        try:
+            from gateway.status import release_scoped_lock
+            if getattr(self, '_token_lock_identity', None):
+                release_scoped_lock('slack-app-token', self._token_lock_identity)
+                self._token_lock_identity = None
+        except Exception:
+            pass
+
+        logger.info("[Slack] Disconnected")
+
+    def _get_client(self, chat_id: str) -> AsyncWebClient:
+        """Return the workspace-specific WebClient for a channel."""
+        team_id = self._channel_team.get(chat_id)
+        if team_id and team_id in self._team_clients:
+            return self._team_clients[team_id]
+        return self._app.client  # fallback to primary
 
     async def send(
         self,
@@ -143,27 +224,40 @@ class SlackAdapter(BasePlatformAdapter):
             return SendResult(success=False, error="Not connected")
 
         try:
-            kwargs = {
-                "channel": chat_id,
-                "text": content,
-            }
+            # Convert standard markdown → Slack mrkdwn
+            formatted = self.format_message(content)
 
-            # Reply in thread if thread_ts is available
-            if reply_to:
-                kwargs["thread_ts"] = reply_to
-            elif metadata and metadata.get("thread_ts"):
-                kwargs["thread_ts"] = metadata["thread_ts"]
+            # Split long messages, preserving code block boundaries
+            chunks = self.truncate_message(formatted, self.MAX_MESSAGE_LENGTH)
 
-            result = await self._app.client.chat_postMessage(**kwargs)
+            thread_ts = self._resolve_thread_ts(reply_to, metadata)
+            last_result = None
+
+            # reply_broadcast: also post thread replies to the main channel.
+            # Controlled via platform config: gateway.slack.reply_broadcast
+            broadcast = self.config.extra.get("reply_broadcast", False)
+
+            for i, chunk in enumerate(chunks):
+                kwargs = {
+                    "channel": chat_id,
+                    "text": chunk,
+                }
+                if thread_ts:
+                    kwargs["thread_ts"] = thread_ts
+                    # Only broadcast the first chunk of the first reply
+                    if broadcast and i == 0:
+                        kwargs["reply_broadcast"] = True
+
+                last_result = await self._get_client(chat_id).chat_postMessage(**kwargs)
 
             return SendResult(
                 success=True,
-                message_id=result.get("ts"),
-                raw_response=result,
+                message_id=last_result.get("ts") if last_result else None,
+                raw_response=last_result,
             )
 
-        except Exception as e:
-            print(f"[Slack] Send error: {e}")
+        except Exception as e:  # pragma: no cover - defensive logging
+            logger.error("[Slack] Send error: %s", e, exc_info=True)
             return SendResult(success=False, error=str(e))
 
     async def edit_message(
@@ -176,18 +270,239 @@ class SlackAdapter(BasePlatformAdapter):
         if not self._app:
             return SendResult(success=False, error="Not connected")
         try:
-            await self._app.client.chat_update(
+            await self._get_client(chat_id).chat_update(
                 channel=chat_id,
                 ts=message_id,
                 text=content,
             )
             return SendResult(success=True, message_id=message_id)
-        except Exception as e:
+        except Exception as e:  # pragma: no cover - defensive logging
+            logger.error(
+                "[Slack] Failed to edit message %s in channel %s: %s",
+                message_id,
+                chat_id,
+                e,
+                exc_info=True,
+            )
             return SendResult(success=False, error=str(e))
 
-    async def send_typing(self, chat_id: str) -> None:
-        """Slack doesn't have a direct typing indicator API for bots."""
-        pass
+    async def send_typing(self, chat_id: str, metadata=None) -> None:
+        """Show a typing/status indicator using assistant.threads.setStatus.
+
+        Displays "is thinking..." next to the bot name in a thread.
+        Requires the assistant:write or chat:write scope.
+        Auto-clears when the bot sends a reply to the thread.
+        """
+        if not self._app:
+            return
+
+        thread_ts = None
+        if metadata:
+            thread_ts = metadata.get("thread_id") or metadata.get("thread_ts")
+
+        if not thread_ts:
+            return  # Can only set status in a thread context
+
+        try:
+            await self._get_client(chat_id).assistant_threads_setStatus(
+                channel_id=chat_id,
+                thread_ts=thread_ts,
+                status="is thinking...",
+            )
+        except Exception as e:
+            # Silently ignore — may lack assistant:write scope or not be
+            # in an assistant-enabled context. Falls back to reactions.
+            logger.debug("[Slack] assistant.threads.setStatus failed: %s", e)
+
+    def _resolve_thread_ts(
+        self,
+        reply_to: Optional[str] = None,
+        metadata: Optional[Dict[str, Any]] = None,
+    ) -> Optional[str]:
+        """Resolve the correct thread_ts for a Slack API call.
+
+        Prefers metadata thread_id (the thread parent's ts, set by the
+        gateway) over reply_to (which may be a child message's ts).
+        """
+        if metadata:
+            if metadata.get("thread_id"):
+                return metadata["thread_id"]
+            if metadata.get("thread_ts"):
+                return metadata["thread_ts"]
+        return reply_to
+
+    async def _upload_file(
+        self,
+        chat_id: str,
+        file_path: str,
+        caption: Optional[str] = None,
+        reply_to: Optional[str] = None,
+        metadata: Optional[Dict[str, Any]] = None,
+    ) -> SendResult:
+        """Upload a local file to Slack."""
+        if not self._app:
+            return SendResult(success=False, error="Not connected")
+
+        if not os.path.exists(file_path):
+            raise FileNotFoundError(f"File not found: {file_path}")
+
+        result = await self._get_client(chat_id).files_upload_v2(
+            channel=chat_id,
+            file=file_path,
+            filename=os.path.basename(file_path),
+            initial_comment=caption or "",
+            thread_ts=self._resolve_thread_ts(reply_to, metadata),
+        )
+        return SendResult(success=True, raw_response=result)
+
+    # ----- Markdown → mrkdwn conversion -----
+
+    def format_message(self, content: str) -> str:
+        """Convert standard markdown to Slack mrkdwn format.
+
+        Protected regions (code blocks, inline code) are extracted first so
+        their contents are never modified.  Standard markdown constructs
+        (headers, bold, italic, links) are translated to mrkdwn syntax.
+        """
+        if not content:
+            return content
+
+        placeholders: dict = {}
+        counter = [0]
+
+        def _ph(value: str) -> str:
+            """Stash value behind a placeholder that survives later passes."""
+            key = f"\x00SL{counter[0]}\x00"
+            counter[0] += 1
+            placeholders[key] = value
+            return key
+
+        text = content
+
+        # 1) Protect fenced code blocks (``` ... ```)
+        text = re.sub(
+            r'(```(?:[^\n]*\n)?[\s\S]*?```)',
+            lambda m: _ph(m.group(0)),
+            text,
+        )
+
+        # 2) Protect inline code (`...`)
+        text = re.sub(r'(`[^`]+`)', lambda m: _ph(m.group(0)), text)
+
+        # 3) Convert markdown links [text](url) → <url|text>
+        text = re.sub(
+            r'\[([^\]]+)\]\(([^)]+)\)',
+            lambda m: _ph(f'<{m.group(2)}|{m.group(1)}>'),
+            text,
+        )
+
+        # 4) Convert headers (## Title) → *Title* (bold)
+        def _convert_header(m):
+            inner = m.group(1).strip()
+            # Strip redundant bold markers inside a header
+            inner = re.sub(r'\*\*(.+?)\*\*', r'\1', inner)
+            return _ph(f'*{inner}*')
+
+        text = re.sub(
+            r'^#{1,6}\s+(.+)$', _convert_header, text, flags=re.MULTILINE
+        )
+
+        # 5) Convert bold: **text** → *text* (Slack bold)
+        text = re.sub(
+            r'\*\*(.+?)\*\*',
+            lambda m: _ph(f'*{m.group(1)}*'),
+            text,
+        )
+
+        # 6) Convert italic: _text_ stays as _text_ (already Slack italic)
+        #    Single *text* → _text_ (Slack italic)
+        text = re.sub(
+            r'(?<!\*)\*([^*\n]+)\*(?!\*)',
+            lambda m: _ph(f'_{m.group(1)}_'),
+            text,
+        )
+
+        # 7) Convert strikethrough: ~~text~~ → ~text~
+        text = re.sub(
+            r'~~(.+?)~~',
+            lambda m: _ph(f'~{m.group(1)}~'),
+            text,
+        )
+
+        # 8) Convert blockquotes: > text → > text (same syntax, just ensure
+        #    no extra escaping happens to the > character)
+        # Slack uses the same > prefix, so this is a no-op for content.
+
+        # 9) Restore placeholders in reverse order
+        for key in reversed(list(placeholders.keys())):
+            text = text.replace(key, placeholders[key])
+
+        return text
+
+    # ----- Reactions -----
+
+    async def _add_reaction(
+        self, channel: str, timestamp: str, emoji: str
+    ) -> bool:
+        """Add an emoji reaction to a message. Returns True on success."""
+        if not self._app:
+            return False
+        try:
+            await self._get_client(channel).reactions_add(
+                channel=channel, timestamp=timestamp, name=emoji
+            )
+            return True
+        except Exception as e:
+            # Don't log as error — may fail if already reacted or missing scope
+            logger.debug("[Slack] reactions.add failed (%s): %s", emoji, e)
+            return False
+
+    async def _remove_reaction(
+        self, channel: str, timestamp: str, emoji: str
+    ) -> bool:
+        """Remove an emoji reaction from a message. Returns True on success."""
+        if not self._app:
+            return False
+        try:
+            await self._get_client(channel).reactions_remove(
+                channel=channel, timestamp=timestamp, name=emoji
+            )
+            return True
+        except Exception as e:
+            logger.debug("[Slack] reactions.remove failed (%s): %s", emoji, e)
+            return False
+
+    # ----- User identity resolution -----
+
+    async def _resolve_user_name(self, user_id: str, chat_id: str = "") -> str:
+        """Resolve a Slack user ID to a display name, with caching."""
+        if not user_id:
+            return ""
+        if user_id in self._user_name_cache:
+            return self._user_name_cache[user_id]
+
+        if not self._app:
+            return user_id
+
+        try:
+            client = self._get_client(chat_id) if chat_id else self._app.client
+            result = await client.users_info(user=user_id)
+            user = result.get("user", {})
+            # Prefer display_name → real_name → user_id
+            profile = user.get("profile", {})
+            name = (
+                profile.get("display_name")
+                or profile.get("real_name")
+                or user.get("real_name")
+                or user.get("name")
+                or user_id
+            )
+            self._user_name_cache[user_id] = name
+            return name
+        except Exception as e:
+            logger.debug("[Slack] users.info failed for %s: %s", user_id, e)
+            self._user_name_cache[user_id] = user_id
+            return user_id
 
     async def send_image_file(
         self,
@@ -195,28 +510,25 @@ class SlackAdapter(BasePlatformAdapter):
         image_path: str,
         caption: Optional[str] = None,
         reply_to: Optional[str] = None,
+        metadata: Optional[Dict[str, Any]] = None,
     ) -> SendResult:
         """Send a local image file to Slack by uploading it."""
-        if not self._app:
-            return SendResult(success=False, error="Not connected")
-
         try:
-            import os
-            if not os.path.exists(image_path):
-                return SendResult(success=False, error=f"Image file not found: {image_path}")
-
-            result = await self._app.client.files_upload_v2(
-                channel=chat_id,
-                file=image_path,
-                filename=os.path.basename(image_path),
-                initial_comment=caption or "",
-                thread_ts=reply_to,
+            return await self._upload_file(chat_id, image_path, caption, reply_to, metadata)
+        except FileNotFoundError:
+            return SendResult(success=False, error=f"Image file not found: {image_path}")
+        except Exception as e:  # pragma: no cover - defensive logging
+            logger.error(
+                "[%s] Failed to send local Slack image %s: %s",
+                self.name,
+                image_path,
+                e,
+                exc_info=True,
             )
-            return SendResult(success=True, raw_response=result)
-
-        except Exception as e:
-            print(f"[{self.name}] Failed to send local image: {e}")
-            return await super().send_image_file(chat_id, image_path, caption, reply_to)
+            text = f"🖼️ Image: {image_path}"
+            if caption:
+                text = f"{caption}\n{text}"
+            return await self.send(chat_id, text, reply_to=reply_to, metadata=metadata)
 
     async def send_image(
         self,
@@ -224,6 +536,7 @@ class SlackAdapter(BasePlatformAdapter):
         image_url: str,
         caption: Optional[str] = None,
         reply_to: Optional[str] = None,
+        metadata: Optional[Dict[str, Any]] = None,
     ) -> SendResult:
         """Send an image to Slack by uploading the URL as a file."""
         if not self._app:
@@ -237,17 +550,23 @@ class SlackAdapter(BasePlatformAdapter):
                 response = await client.get(image_url)
                 response.raise_for_status()
 
-            result = await self._app.client.files_upload_v2(
+            result = await self._get_client(chat_id).files_upload_v2(
                 channel=chat_id,
                 content=response.content,
                 filename="image.png",
                 initial_comment=caption or "",
-                thread_ts=reply_to,
+                thread_ts=self._resolve_thread_ts(reply_to, metadata),
             )
 
             return SendResult(success=True, raw_response=result)
 
-        except Exception as e:
+        except Exception as e:  # pragma: no cover - defensive logging
+            logger.warning(
+                "[Slack] Failed to upload image from URL %s, falling back to text: %s",
+                image_url,
+                e,
+                exc_info=True,
+            )
             # Fall back to sending the URL as text
             text = f"{caption}\n{image_url}" if caption else image_url
             return await self.send(chat_id=chat_id, content=text, reply_to=reply_to)
@@ -258,22 +577,21 @@ class SlackAdapter(BasePlatformAdapter):
         audio_path: str,
         caption: Optional[str] = None,
         reply_to: Optional[str] = None,
+        metadata: Optional[Dict[str, Any]] = None,
+        **kwargs,
     ) -> SendResult:
         """Send an audio file to Slack."""
-        if not self._app:
-            return SendResult(success=False, error="Not connected")
-
         try:
-            result = await self._app.client.files_upload_v2(
-                channel=chat_id,
-                file=audio_path,
-                filename=os.path.basename(audio_path),
-                initial_comment=caption or "",
-                thread_ts=reply_to,
+            return await self._upload_file(chat_id, audio_path, caption, reply_to, metadata)
+        except FileNotFoundError:
+            return SendResult(success=False, error=f"Audio file not found: {audio_path}")
+        except Exception as e:  # pragma: no cover - defensive logging
+            logger.error(
+                "[Slack] Failed to send audio file %s: %s",
+                audio_path,
+                e,
+                exc_info=True,
             )
-            return SendResult(success=True, raw_response=result)
-
-        except Exception as e:
             return SendResult(success=False, error=str(e))
 
     async def send_video(
@@ -282,6 +600,7 @@ class SlackAdapter(BasePlatformAdapter):
         video_path: str,
         caption: Optional[str] = None,
         reply_to: Optional[str] = None,
+        metadata: Optional[Dict[str, Any]] = None,
     ) -> SendResult:
         """Send a video file to Slack."""
         if not self._app:
@@ -291,18 +610,27 @@ class SlackAdapter(BasePlatformAdapter):
             return SendResult(success=False, error=f"Video file not found: {video_path}")
 
         try:
-            result = await self._app.client.files_upload_v2(
+            result = await self._get_client(chat_id).files_upload_v2(
                 channel=chat_id,
                 file=video_path,
                 filename=os.path.basename(video_path),
                 initial_comment=caption or "",
-                thread_ts=reply_to,
+                thread_ts=self._resolve_thread_ts(reply_to, metadata),
             )
             return SendResult(success=True, raw_response=result)
 
-        except Exception as e:
-            print(f"[{self.name}] Failed to send video: {e}")
-            return await super().send_video(chat_id, video_path, caption, reply_to)
+        except Exception as e:  # pragma: no cover - defensive logging
+            logger.error(
+                "[%s] Failed to send video %s: %s",
+                self.name,
+                video_path,
+                e,
+                exc_info=True,
+            )
+            text = f"🎬 Video: {video_path}"
+            if caption:
+                text = f"{caption}\n{text}"
+            return await self.send(chat_id, text, reply_to=reply_to, metadata=metadata)
 
     async def send_document(
         self,
@@ -311,6 +639,7 @@ class SlackAdapter(BasePlatformAdapter):
         caption: Optional[str] = None,
         file_name: Optional[str] = None,
         reply_to: Optional[str] = None,
+        metadata: Optional[Dict[str, Any]] = None,
     ) -> SendResult:
         """Send a document/file attachment to Slack."""
         if not self._app:
@@ -322,18 +651,27 @@ class SlackAdapter(BasePlatformAdapter):
         display_name = file_name or os.path.basename(file_path)
 
         try:
-            result = await self._app.client.files_upload_v2(
+            result = await self._get_client(chat_id).files_upload_v2(
                 channel=chat_id,
                 file=file_path,
                 filename=display_name,
                 initial_comment=caption or "",
-                thread_ts=reply_to,
+                thread_ts=self._resolve_thread_ts(reply_to, metadata),
             )
             return SendResult(success=True, raw_response=result)
 
-        except Exception as e:
-            print(f"[{self.name}] Failed to send document: {e}")
-            return await super().send_document(chat_id, file_path, caption, file_name, reply_to)
+        except Exception as e:  # pragma: no cover - defensive logging
+            logger.error(
+                "[%s] Failed to send document %s: %s",
+                self.name,
+                file_path,
+                e,
+                exc_info=True,
+            )
+            text = f"📎 File: {file_path}"
+            if caption:
+                text = f"{caption}\n{text}"
+            return await self.send(chat_id, text, reply_to=reply_to, metadata=metadata)
 
     async def get_chat_info(self, chat_id: str) -> Dict[str, Any]:
         """Get information about a Slack channel."""
@@ -341,14 +679,20 @@ class SlackAdapter(BasePlatformAdapter):
             return {"name": chat_id, "type": "unknown"}
 
         try:
-            result = await self._app.client.conversations_info(channel=chat_id)
+            result = await self._get_client(chat_id).conversations_info(channel=chat_id)
             channel = result.get("channel", {})
             is_dm = channel.get("is_im", False)
             return {
                 "name": channel.get("name", chat_id),
                 "type": "dm" if is_dm else "group",
             }
-        except Exception:
+        except Exception as e:  # pragma: no cover - defensive logging
+            logger.error(
+                "[Slack] Failed to fetch chat info for %s: %s",
+                chat_id,
+                e,
+                exc_info=True,
+            )
             return {"name": chat_id, "type": "unknown"}
 
     # ----- Internal handlers -----
@@ -367,19 +711,34 @@ class SlackAdapter(BasePlatformAdapter):
         text = event.get("text", "")
         user_id = event.get("user", "")
         channel_id = event.get("channel", "")
-        thread_ts = event.get("thread_ts") or event.get("ts")
         ts = event.get("ts", "")
+        team_id = event.get("team", "")
+
+        # Track which workspace owns this channel
+        if team_id and channel_id:
+            self._channel_team[channel_id] = team_id
 
         # Determine if this is a DM or channel message
         channel_type = event.get("channel_type", "")
         is_dm = channel_type == "im"
 
+        # Build thread_ts for session keying.
+        # In channels: fall back to ts so each top-level @mention starts a
+        #   new thread/session (the bot always replies in a thread).
+        # In DMs: only use the real thread_ts — top-level DMs should share
+        #   one continuous session, threaded DMs get their own session.
+        if is_dm:
+            thread_ts = event.get("thread_ts")  # None for top-level DMs
+        else:
+            thread_ts = event.get("thread_ts") or ts  # ts fallback for channels
+
         # In channels, only respond if bot is mentioned
-        if not is_dm and self._bot_user_id:
-            if f"<@{self._bot_user_id}>" not in text:
+        bot_uid = self._team_bot_user_ids.get(team_id, self._bot_user_id)
+        if not is_dm and bot_uid:
+            if f"<@{bot_uid}>" not in text:
                 return
             # Strip the bot mention from the text
-            text = text.replace(f"<@{self._bot_user_id}>", "").strip()
+            text = text.replace(f"<@{bot_uid}>", "").strip()
 
         # Determine message type
         msg_type = MessageType.TEXT
@@ -399,23 +758,23 @@ class SlackAdapter(BasePlatformAdapter):
                     if ext not in (".jpg", ".jpeg", ".png", ".gif", ".webp"):
                         ext = ".jpg"
                     # Slack private URLs require the bot token as auth header
-                    cached = await self._download_slack_file(url, ext)
+                    cached = await self._download_slack_file(url, ext, team_id=team_id)
                     media_urls.append(cached)
                     media_types.append(mimetype)
                     msg_type = MessageType.PHOTO
-                except Exception as e:
-                    print(f"[Slack] Failed to cache image: {e}", flush=True)
+                except Exception as e:  # pragma: no cover - defensive logging
+                    logger.warning("[Slack] Failed to cache image from %s: %s", url, e, exc_info=True)
             elif mimetype.startswith("audio/") and url:
                 try:
                     ext = "." + mimetype.split("/")[-1].split(";")[0]
                     if ext not in (".ogg", ".mp3", ".wav", ".webm", ".m4a"):
                         ext = ".ogg"
-                    cached = await self._download_slack_file(url, ext, audio=True)
+                    cached = await self._download_slack_file(url, ext, audio=True, team_id=team_id)
                     media_urls.append(cached)
                     media_types.append(mimetype)
                     msg_type = MessageType.VOICE
-                except Exception as e:
-                    print(f"[Slack] Failed to cache audio: {e}", flush=True)
+                except Exception as e:  # pragma: no cover - defensive logging
+                    logger.warning("[Slack] Failed to cache audio from %s: %s", url, e, exc_info=True)
             elif url:
                 # Try to handle as a document attachment
                 try:
@@ -437,11 +796,11 @@ class SlackAdapter(BasePlatformAdapter):
                     file_size = f.get("size", 0)
                     MAX_DOC_BYTES = 20 * 1024 * 1024
                     if not file_size or file_size > MAX_DOC_BYTES:
-                        print(f"[Slack] Document too large or unknown size: {file_size}", flush=True)
+                        logger.warning("[Slack] Document too large or unknown size: %s", file_size)
                         continue
 
                     # Download and cache
-                    raw_bytes = await self._download_slack_file_bytes(url)
+                    raw_bytes = await self._download_slack_file_bytes(url, team_id=team_id)
                     cached_path = cache_document_from_bytes(
                         raw_bytes, original_filename or f"document{ext}"
                     )
@@ -449,7 +808,7 @@ class SlackAdapter(BasePlatformAdapter):
                     media_urls.append(cached_path)
                     media_types.append(doc_mime)
                     msg_type = MessageType.DOCUMENT
-                    print(f"[Slack] Cached user document: {cached_path}", flush=True)
+                    logger.debug("[Slack] Cached user document: %s", cached_path)
 
                     # Inject text content for .txt/.md files (capped at 100 KB)
                     MAX_TEXT_INJECT_BYTES = 100 * 1024
@@ -466,8 +825,11 @@ class SlackAdapter(BasePlatformAdapter):
                         except UnicodeDecodeError:
                             pass  # Binary content, skip injection
 
-                except Exception as e:
-                    print(f"[Slack] Failed to cache document: {e}", flush=True)
+                except Exception as e:  # pragma: no cover - defensive logging
+                    logger.warning("[Slack] Failed to cache document from %s: %s", url, e, exc_info=True)
+
+        # Resolve user display name (cached after first lookup)
+        user_name = await self._resolve_user_name(user_id, chat_id=channel_id)
 
         # Build source
         source = self.build_source(
@@ -475,6 +837,7 @@ class SlackAdapter(BasePlatformAdapter):
             chat_name=channel_id,  # Will be resolved later if needed
             chat_type="dm" if is_dm else "group",
             user_id=user_id,
+            user_name=user_name,
             thread_id=thread_ts,
         )
 
@@ -489,22 +852,31 @@ class SlackAdapter(BasePlatformAdapter):
             reply_to_message_id=thread_ts if thread_ts != ts else None,
         )
 
+        # Add 👀 reaction to acknowledge receipt
+        await self._add_reaction(channel_id, ts, "eyes")
+
         await self.handle_message(msg_event)
 
+        # Replace 👀 with ✅ when done
+        await self._remove_reaction(channel_id, ts, "eyes")
+        await self._add_reaction(channel_id, ts, "white_check_mark")
+
     async def _handle_slash_command(self, command: dict) -> None:
         """Handle /hermes slash command."""
         text = command.get("text", "").strip()
         user_id = command.get("user_id", "")
         channel_id = command.get("channel_id", "")
+        team_id = command.get("team_id", "")
 
-        # Map subcommands to gateway commands
-        subcommand_map = {
-            "new": "/reset", "reset": "/reset",
-            "status": "/status", "stop": "/stop",
-            "help": "/help",
-            "model": "/model", "personality": "/personality",
-            "retry": "/retry", "undo": "/undo",
-        }
+        # Track which workspace owns this channel
+        if team_id and channel_id:
+            self._channel_team[channel_id] = team_id
+
+        # Map subcommands to gateway commands — derived from central registry.
+        # Also keep "compact" as a Slack-specific alias for /compress.
+        from hermes_cli.commands import slack_subcommand_map
+        subcommand_map = slack_subcommand_map()
+        subcommand_map["compact"] = "/compress"
         first_word = text.split()[0] if text else ""
         if first_word in subcommand_map:
             # Preserve arguments after the subcommand
@@ -530,34 +902,66 @@ class SlackAdapter(BasePlatformAdapter):
 
         await self.handle_message(event)
 
-    async def _download_slack_file(self, url: str, ext: str, audio: bool = False) -> str:
-        """Download a Slack file using the bot token for auth."""
+    async def _download_slack_file(self, url: str, ext: str, audio: bool = False, team_id: str = "") -> str:
+        """Download a Slack file using the bot token for auth, with retry."""
+        import asyncio
         import httpx
 
-        bot_token = self.config.token
+        bot_token = self._team_clients[team_id].token if team_id and team_id in self._team_clients else self.config.token
+        last_exc = None
+
         async with httpx.AsyncClient(timeout=30.0, follow_redirects=True) as client:
-            response = await client.get(
-                url,
-                headers={"Authorization": f"Bearer {bot_token}"},
-            )
-            response.raise_for_status()
+            for attempt in range(3):
+                try:
+                    response = await client.get(
+                        url,
+                        headers={"Authorization": f"Bearer {bot_token}"},
+                    )
+                    response.raise_for_status()
 
-        if audio:
-            from gateway.platforms.base import cache_audio_from_bytes
-            return cache_audio_from_bytes(response.content, ext)
-        else:
-            from gateway.platforms.base import cache_image_from_bytes
-            return cache_image_from_bytes(response.content, ext)
+                    if audio:
+                        from gateway.platforms.base import cache_audio_from_bytes
+                        return cache_audio_from_bytes(response.content, ext)
+                    else:
+                        from gateway.platforms.base import cache_image_from_bytes
+                        return cache_image_from_bytes(response.content, ext)
+                except (httpx.TimeoutException, httpx.HTTPStatusError) as exc:
+                    last_exc = exc
+                    if isinstance(exc, httpx.HTTPStatusError) and exc.response.status_code < 429:
+                        raise
+                    if attempt < 2:
+                        logger.debug("Slack file download retry %d/2 for %s: %s",
+                                     attempt + 1, url[:80], exc)
+                        await asyncio.sleep(1.5 * (attempt + 1))
+                        continue
+                    raise
+        raise last_exc
 
-    async def _download_slack_file_bytes(self, url: str) -> bytes:
-        """Download a Slack file and return raw bytes."""
+    async def _download_slack_file_bytes(self, url: str, team_id: str = "") -> bytes:
+        """Download a Slack file and return raw bytes, with retry."""
+        import asyncio
         import httpx
 
-        bot_token = self.config.token
+        bot_token = self._team_clients[team_id].token if team_id and team_id in self._team_clients else self.config.token
+        last_exc = None
+
         async with httpx.AsyncClient(timeout=30.0, follow_redirects=True) as client:
-            response = await client.get(
-                url,
-                headers={"Authorization": f"Bearer {bot_token}"},
-            )
-            response.raise_for_status()
-        return response.content
+            for attempt in range(3):
+                try:
+                    response = await client.get(
+                        url,
+                        headers={"Authorization": f"Bearer {bot_token}"},
+                    )
+                    response.raise_for_status()
+                    return response.content
+                except (httpx.TimeoutException, httpx.HTTPStatusError) as exc:
+                    last_exc = exc
+                    if isinstance(exc, httpx.HTTPStatusError) and exc.response.status_code < 429:
+                        raise
+                    if attempt < 2:
+                        logger.debug("Slack file download retry %d/2 for %s: %s",
+                                     attempt + 1, url[:80], exc)
+                        await asyncio.sleep(1.5 * (attempt + 1))
+                        continue
+                    raise
+        raise last_exc

gateway/platforms/sms.py

@@ -0,0 +1,276 @@
+"""SMS (Twilio) platform adapter.
+
+Connects to the Twilio REST API for outbound SMS and runs an aiohttp
+webhook server to receive inbound messages.
+
+Shares credentials with the optional telephony skill — same env vars:
+  - TWILIO_ACCOUNT_SID
+  - TWILIO_AUTH_TOKEN
+  - TWILIO_PHONE_NUMBER  (E.164 from-number, e.g. +15551234567)
+
+Gateway-specific env vars:
+  - SMS_WEBHOOK_PORT     (default 8080)
+  - SMS_ALLOWED_USERS    (comma-separated E.164 phone numbers)
+  - SMS_ALLOW_ALL_USERS  (true/false)
+  - SMS_HOME_CHANNEL     (phone number for cron delivery)
+"""
+
+import asyncio
+import base64
+import logging
+import os
+import re
+import urllib.parse
+from typing import Any, Dict, Optional
+
+from gateway.config import Platform, PlatformConfig
+from gateway.platforms.base import (
+    BasePlatformAdapter,
+    MessageEvent,
+    MessageType,
+    SendResult,
+)
+
+logger = logging.getLogger(__name__)
+
+TWILIO_API_BASE = "https://api.twilio.com/2010-04-01/Accounts"
+MAX_SMS_LENGTH = 1600  # ~10 SMS segments
+DEFAULT_WEBHOOK_PORT = 8080
+
+# E.164 phone number pattern for redaction
+_PHONE_RE = re.compile(r"\+[1-9]\d{6,14}")
+
+
+def _redact_phone(phone: str) -> str:
+    """Redact a phone number for logging: +15551234567 -> +1555***4567."""
+    if not phone:
+        return "<none>"
+    if len(phone) <= 8:
+        return phone[:2] + "***" + phone[-2:] if len(phone) > 4 else "****"
+    return phone[:5] + "***" + phone[-4:]
+
+
+def check_sms_requirements() -> bool:
+    """Check if SMS adapter dependencies are available."""
+    try:
+        import aiohttp  # noqa: F401
+    except ImportError:
+        return False
+    return bool(os.getenv("TWILIO_ACCOUNT_SID") and os.getenv("TWILIO_AUTH_TOKEN"))
+
+
+class SmsAdapter(BasePlatformAdapter):
+    """
+    Twilio SMS <-> Hermes gateway adapter.
+
+    Each inbound phone number gets its own Hermes session (multi-tenant).
+    Replies are always sent from the configured TWILIO_PHONE_NUMBER.
+    """
+
+    MAX_MESSAGE_LENGTH = MAX_SMS_LENGTH
+
+    def __init__(self, config: PlatformConfig):
+        super().__init__(config, Platform.SMS)
+        self._account_sid: str = os.environ["TWILIO_ACCOUNT_SID"]
+        self._auth_token: str = os.environ["TWILIO_AUTH_TOKEN"]
+        self._from_number: str = os.getenv("TWILIO_PHONE_NUMBER", "")
+        self._webhook_port: int = int(
+            os.getenv("SMS_WEBHOOK_PORT", str(DEFAULT_WEBHOOK_PORT))
+        )
+        self._runner = None
+        self._http_session: Optional["aiohttp.ClientSession"] = None
+
+    def _basic_auth_header(self) -> str:
+        """Build HTTP Basic auth header value for Twilio."""
+        creds = f"{self._account_sid}:{self._auth_token}"
+        encoded = base64.b64encode(creds.encode("ascii")).decode("ascii")
+        return f"Basic {encoded}"
+
+    # ------------------------------------------------------------------
+    # Required abstract methods
+    # ------------------------------------------------------------------
+
+    async def connect(self) -> bool:
+        import aiohttp
+        from aiohttp import web
+
+        if not self._from_number:
+            logger.error("[sms] TWILIO_PHONE_NUMBER not set — cannot send replies")
+            return False
+
+        app = web.Application()
+        app.router.add_post("/webhooks/twilio", self._handle_webhook)
+        app.router.add_get("/health", lambda _: web.Response(text="ok"))
+
+        self._runner = web.AppRunner(app)
+        await self._runner.setup()
+        site = web.TCPSite(self._runner, "0.0.0.0", self._webhook_port)
+        await site.start()
+        self._http_session = aiohttp.ClientSession(
+            timeout=aiohttp.ClientTimeout(total=30),
+        )
+        self._running = True
+
+        logger.info(
+            "[sms] Twilio webhook server listening on port %d, from: %s",
+            self._webhook_port,
+            _redact_phone(self._from_number),
+        )
+        return True
+
+    async def disconnect(self) -> None:
+        if self._http_session:
+            await self._http_session.close()
+            self._http_session = None
+        if self._runner:
+            await self._runner.cleanup()
+            self._runner = None
+        self._running = False
+        logger.info("[sms] Disconnected")
+
+    async def send(
+        self,
+        chat_id: str,
+        content: str,
+        reply_to: Optional[str] = None,
+        metadata: Optional[Dict[str, Any]] = None,
+    ) -> SendResult:
+        import aiohttp
+
+        formatted = self.format_message(content)
+        chunks = self.truncate_message(formatted)
+        last_result = SendResult(success=True)
+
+        url = f"{TWILIO_API_BASE}/{self._account_sid}/Messages.json"
+        headers = {
+            "Authorization": self._basic_auth_header(),
+        }
+
+        session = self._http_session or aiohttp.ClientSession(
+            timeout=aiohttp.ClientTimeout(total=30),
+        )
+        try:
+            for chunk in chunks:
+                form_data = aiohttp.FormData()
+                form_data.add_field("From", self._from_number)
+                form_data.add_field("To", chat_id)
+                form_data.add_field("Body", chunk)
+
+                try:
+                    async with session.post(url, data=form_data, headers=headers) as resp:
+                        body = await resp.json()
+                        if resp.status >= 400:
+                            error_msg = body.get("message", str(body))
+                            logger.error(
+                                "[sms] send failed to %s: %s %s",
+                                _redact_phone(chat_id),
+                                resp.status,
+                                error_msg,
+                            )
+                            return SendResult(
+                                success=False,
+                                error=f"Twilio {resp.status}: {error_msg}",
+                            )
+                        msg_sid = body.get("sid", "")
+                        last_result = SendResult(success=True, message_id=msg_sid)
+                except Exception as e:
+                    logger.error("[sms] send error to %s: %s", _redact_phone(chat_id), e)
+                    return SendResult(success=False, error=str(e))
+        finally:
+            # Close session only if we created a fallback (no persistent session)
+            if not self._http_session and session:
+                await session.close()
+
+        return last_result
+
+    async def get_chat_info(self, chat_id: str) -> Dict[str, Any]:
+        return {"name": chat_id, "type": "dm"}
+
+    # ------------------------------------------------------------------
+    # SMS-specific formatting
+    # ------------------------------------------------------------------
+
+    def format_message(self, content: str) -> str:
+        """Strip markdown — SMS renders it as literal characters."""
+        content = re.sub(r"\*\*(.+?)\*\*", r"\1", content, flags=re.DOTALL)
+        content = re.sub(r"\*(.+?)\*", r"\1", content, flags=re.DOTALL)
+        content = re.sub(r"__(.+?)__", r"\1", content, flags=re.DOTALL)
+        content = re.sub(r"_(.+?)_", r"\1", content, flags=re.DOTALL)
+        content = re.sub(r"```[a-z]*\n?", "", content)
+        content = re.sub(r"`(.+?)`", r"\1", content)
+        content = re.sub(r"^#{1,6}\s+", "", content, flags=re.MULTILINE)
+        content = re.sub(r"\[([^\]]+)\]\([^\)]+\)", r"\1", content)
+        content = re.sub(r"\n{3,}", "\n\n", content)
+        return content.strip()
+
+    # ------------------------------------------------------------------
+    # Twilio webhook handler
+    # ------------------------------------------------------------------
+
+    async def _handle_webhook(self, request) -> "aiohttp.web.Response":
+        from aiohttp import web
+
+        try:
+            raw = await request.read()
+            # Twilio sends form-encoded data, not JSON
+            form = urllib.parse.parse_qs(raw.decode("utf-8"))
+        except Exception as e:
+            logger.error("[sms] webhook parse error: %s", e)
+            return web.Response(
+                text='<?xml version="1.0" encoding="UTF-8"?><Response></Response>',
+                content_type="application/xml",
+                status=400,
+            )
+
+        # Extract fields (parse_qs returns lists)
+        from_number = (form.get("From", [""]))[0].strip()
+        to_number = (form.get("To", [""]))[0].strip()
+        text = (form.get("Body", [""]))[0].strip()
+        message_sid = (form.get("MessageSid", [""]))[0].strip()
+
+        if not from_number or not text:
+            return web.Response(
+                text='<?xml version="1.0" encoding="UTF-8"?><Response></Response>',
+                content_type="application/xml",
+            )
+
+        # Ignore messages from our own number (echo prevention)
+        if from_number == self._from_number:
+            logger.debug("[sms] ignoring echo from own number %s", _redact_phone(from_number))
+            return web.Response(
+                text='<?xml version="1.0" encoding="UTF-8"?><Response></Response>',
+                content_type="application/xml",
+            )
+
+        logger.info(
+            "[sms] inbound from %s -> %s: %s",
+            _redact_phone(from_number),
+            _redact_phone(to_number),
+            text[:80],
+        )
+
+        source = self.build_source(
+            chat_id=from_number,
+            chat_name=from_number,
+            chat_type="dm",
+            user_id=from_number,
+            user_name=from_number,
+        )
+        event = MessageEvent(
+            text=text,
+            message_type=MessageType.TEXT,
+            source=source,
+            raw_message=form,
+            message_id=message_sid,
+        )
+
+        # Non-blocking: Twilio expects a fast response
+        task = asyncio.create_task(self.handle_message(event))
+        self._background_tasks.add(task)
+        task.add_done_callback(self._background_tasks.discard)
+
+        # Return empty TwiML — we send replies via the REST API, not inline TwiML
+        return web.Response(
+            text='<?xml version="1.0" encoding="UTF-8"?><Response></Response>',
+            content_type="application/xml",
+        )

gateway/platforms/telegram_network.py

@@ -0,0 +1,245 @@
+"""Telegram-specific network helpers.
+
+Provides a hostname-preserving fallback transport for networks where
+api.telegram.org resolves to an endpoint that is unreachable from the current
+host. The transport keeps the logical request host and TLS SNI as
+api.telegram.org while retrying the TCP connection against one or more fallback
+IPv4 addresses.
+"""
+
+from __future__ import annotations
+
+import asyncio
+import ipaddress
+import logging
+import os
+import socket
+from typing import Iterable, Optional
+
+import httpx
+
+logger = logging.getLogger(__name__)
+
+_TELEGRAM_API_HOST = "api.telegram.org"
+
+# DNS-over-HTTPS providers used to discover Telegram API IPs that may differ
+# from the (potentially unreachable) IP returned by the local system resolver.
+_DOH_TIMEOUT = 4.0  # seconds — bounded so connect() isn't noticeably delayed
+
+_DOH_PROVIDERS: list[dict] = [
+    {
+        "url": "https://dns.google/resolve",
+        "params": {"name": _TELEGRAM_API_HOST, "type": "A"},
+        "headers": {},
+    },
+    {
+        "url": "https://cloudflare-dns.com/dns-query",
+        "params": {"name": _TELEGRAM_API_HOST, "type": "A"},
+        "headers": {"Accept": "application/dns-json"},
+    },
+]
+
+# Last-resort IPs when DoH is also blocked.  These are stable Telegram Bot API
+# endpoints in the 149.154.160.0/20 block (same seed used by OpenClaw).
+_SEED_FALLBACK_IPS: list[str] = ["149.154.167.220"]
+
+
+def _resolve_proxy_url() -> str | None:
+    for key in ("HTTPS_PROXY", "HTTP_PROXY", "ALL_PROXY", "https_proxy", "http_proxy", "all_proxy"):
+        value = (os.environ.get(key) or "").strip()
+        if value:
+            return value
+    return None
+
+
+class TelegramFallbackTransport(httpx.AsyncBaseTransport):
+    """Retry Telegram Bot API requests via fallback IPs while preserving TLS/SNI.
+
+    Requests continue to target https://api.telegram.org/... logically, but on
+    connect failures the underlying TCP connection is retried against a known
+    reachable IP. This is effectively the programmatic equivalent of
+    ``curl --resolve api.telegram.org:443:<ip>``.
+    """
+
+    def __init__(self, fallback_ips: Iterable[str], **transport_kwargs):
+        self._fallback_ips = [ip for ip in dict.fromkeys(_normalize_fallback_ips(fallback_ips))]
+        proxy_url = _resolve_proxy_url()
+        if proxy_url and "proxy" not in transport_kwargs:
+            transport_kwargs["proxy"] = proxy_url
+        self._primary = httpx.AsyncHTTPTransport(**transport_kwargs)
+        self._fallbacks = {
+            ip: httpx.AsyncHTTPTransport(**transport_kwargs) for ip in self._fallback_ips
+        }
+        self._sticky_ip: Optional[str] = None
+        self._sticky_lock = asyncio.Lock()
+
+    async def handle_async_request(self, request: httpx.Request) -> httpx.Response:
+        if request.url.host != _TELEGRAM_API_HOST or not self._fallback_ips:
+            return await self._primary.handle_async_request(request)
+
+        sticky_ip = self._sticky_ip
+        attempt_order: list[Optional[str]] = [sticky_ip] if sticky_ip else [None]
+        for ip in self._fallback_ips:
+            if ip != sticky_ip:
+                attempt_order.append(ip)
+
+        last_error: Exception | None = None
+        for ip in attempt_order:
+            candidate = request if ip is None else _rewrite_request_for_ip(request, ip)
+            transport = self._primary if ip is None else self._fallbacks[ip]
+            try:
+                response = await transport.handle_async_request(candidate)
+                if ip is not None and self._sticky_ip != ip:
+                    async with self._sticky_lock:
+                        if self._sticky_ip != ip:
+                            self._sticky_ip = ip
+                            logger.warning(
+                                "[Telegram] Primary api.telegram.org path unreachable; using sticky fallback IP %s",
+                                ip,
+                            )
+                return response
+            except Exception as exc:
+                last_error = exc
+                if not _is_retryable_connect_error(exc):
+                    raise
+                if ip is None:
+                    logger.warning(
+                        "[Telegram] Primary api.telegram.org connection failed (%s); trying fallback IPs %s",
+                        exc,
+                        ", ".join(self._fallback_ips),
+                    )
+                    continue
+                logger.warning("[Telegram] Fallback IP %s failed: %s", ip, exc)
+                continue
+
+        assert last_error is not None
+        raise last_error
+
+    async def aclose(self) -> None:
+        await self._primary.aclose()
+        for transport in self._fallbacks.values():
+            await transport.aclose()
+
+
+def _normalize_fallback_ips(values: Iterable[str]) -> list[str]:
+    normalized: list[str] = []
+    for value in values:
+        raw = str(value).strip()
+        if not raw:
+            continue
+        try:
+            addr = ipaddress.ip_address(raw)
+        except ValueError:
+            logger.warning("Ignoring invalid Telegram fallback IP: %r", raw)
+            continue
+        if addr.version != 4:
+            logger.warning("Ignoring non-IPv4 Telegram fallback IP: %s", raw)
+            continue
+        normalized.append(str(addr))
+    return normalized
+
+
+def parse_fallback_ip_env(value: str | None) -> list[str]:
+    if not value:
+        return []
+    parts = [part.strip() for part in value.split(",")]
+    return _normalize_fallback_ips(parts)
+
+
+def _resolve_system_dns() -> set[str]:
+    """Return the IPv4 addresses that the OS resolver gives for api.telegram.org."""
+    try:
+        results = socket.getaddrinfo(_TELEGRAM_API_HOST, 443, socket.AF_INET)
+        return {addr[4][0] for addr in results}
+    except Exception:
+        return set()
+
+
+async def _query_doh_provider(
+    client: httpx.AsyncClient, provider: dict
+) -> list[str]:
+    """Query one DoH provider and return A-record IPs."""
+    try:
+        resp = await client.get(
+            provider["url"], params=provider["params"], headers=provider["headers"]
+        )
+        resp.raise_for_status()
+        data = resp.json()
+        ips: list[str] = []
+        for answer in data.get("Answer", []):
+            if answer.get("type") != 1:  # A record
+                continue
+            raw = answer.get("data", "").strip()
+            try:
+                ipaddress.ip_address(raw)
+                ips.append(raw)
+            except ValueError:
+                continue
+        return ips
+    except Exception as exc:
+        logger.debug("DoH query to %s failed: %s", provider["url"], exc)
+        return []
+
+
+async def discover_fallback_ips() -> list[str]:
+    """Auto-discover Telegram API IPs via DNS-over-HTTPS.
+
+    Resolves api.telegram.org through Google and Cloudflare DoH, collects all
+    unique IPs, and excludes the system-DNS-resolved IP (which is presumably
+    unreachable on this network).  Falls back to a hardcoded seed list when DoH
+    is also unavailable.
+    """
+    async with httpx.AsyncClient(timeout=httpx.Timeout(_DOH_TIMEOUT)) as client:
+        doh_tasks = [_query_doh_provider(client, p) for p in _DOH_PROVIDERS]
+        system_dns_task = asyncio.to_thread(_resolve_system_dns)
+        results = await asyncio.gather(system_dns_task, *doh_tasks, return_exceptions=True)
+
+    # results[0] = system DNS IPs (set), results[1:] = DoH IP lists
+    system_ips: set[str] = results[0] if isinstance(results[0], set) else set()
+
+    doh_ips: list[str] = []
+    for r in results[1:]:
+        if isinstance(r, list):
+            doh_ips.extend(r)
+
+    # Deduplicate preserving order, exclude system-DNS IPs
+    seen: set[str] = set()
+    candidates: list[str] = []
+    for ip in doh_ips:
+        if ip not in seen and ip not in system_ips:
+            seen.add(ip)
+            candidates.append(ip)
+
+    # Validate through existing normalization
+    validated = _normalize_fallback_ips(candidates)
+
+    if validated:
+        logger.debug("Discovered Telegram fallback IPs via DoH: %s", ", ".join(validated))
+        return validated
+
+    logger.info(
+        "DoH discovery yielded no new IPs (system DNS: %s); using seed fallback IPs %s",
+        ", ".join(system_ips) or "unknown",
+        ", ".join(_SEED_FALLBACK_IPS),
+    )
+    return list(_SEED_FALLBACK_IPS)
+
+
+def _rewrite_request_for_ip(request: httpx.Request, ip: str) -> httpx.Request:
+    original_host = request.url.host or _TELEGRAM_API_HOST
+    url = request.url.copy_with(host=ip)
+    headers = request.headers.copy()
+    headers["host"] = original_host
+    extensions = dict(request.extensions)
+    extensions["sni_hostname"] = original_host
+    return httpx.Request(
+        method=request.method,
+        url=url,
+        headers=headers,
+        stream=request.stream,
+        extensions=extensions,
+    )
+
+
+def _is_retryable_connect_error(exc: Exception) -> bool:
+    return isinstance(exc, (httpx.ConnectTimeout, httpx.ConnectError))