Merge branch 'main' into fix/packaging-bugs

feat: secure skill env setup on load (core #688)

.env.example

@@ -201,6 +201,18 @@ 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

.gitignore

@@ -1,51 +1,55 @@
-/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

.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

@@ -31,7 +31,13 @@ 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
+│   └── 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
@@ -48,9 +54,10 @@ 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
 ```
 
@@ -121,6 +128,7 @@ 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
+- **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` (not in commands.py)
 - Skill slash commands: `agent/skill_commands.py` scans `~/.hermes/skills/`, injects as **user message** (not system prompt) to preserve prompt caching
 
@@ -195,8 +203,95 @@ 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` |
+| 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:**
@@ -210,6 +305,17 @@ 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
+
 ---
 
 ## Known Pitfalls
@@ -232,7 +338,7 @@ The `_isolate_hermes_home` autouse fixture in `tests/conftest.py` redirects `HER
 
 ```bash
 source .venv/bin/activate
-python -m pytest tests/ -q          # Full suite (~2500 tests, ~2 min)
+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

@@ -139,7 +139,8 @@ hermes-agent/
 │   ├── commands.py               # Slash command definitions + autocomplete
 │   ├── 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)
@@ -328,10 +329,20 @@ 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 +377,82 @@ 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 +462,56 @@ 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:

README.md

@@ -41,7 +41,6 @@ After installation:
 
 ```bash
 source ~/.bashrc    # reload shell (or: source ~/.zshrc)
-hermes setup        # configure your LLM provider
 hermes              # start chatting!
 ```
 
@@ -51,9 +50,12 @@ 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
 ```
@@ -86,6 +88,35 @@ 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.
@@ -93,8 +124,9 @@ 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
+git submodule update --init mini-swe-agent   # required terminal backend
 curl -LsSf https://astral.sh/uv/install.sh | sh
 uv venv .venv --python 3.11
 source .venv/bin/activate
@@ -103,6 +135,12 @@ uv pip install -e "./mini-swe-agent"
 python -m pytest tests/ -q
 ```
 
+> **RL Training (optional):** To work on the RL/Tinker-Atropos integration, also run:
+> ```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)

agent/anthropic_adapter.py

@@ -0,0 +1,615 @@
+"""Anthropic Messages API adapter for Hermes Agent.
+
+Translates between Hermes's internal OpenAI-style message format and
+Anthropic's Messages API. Follows the same pattern as the codex_responses
+adapter — all provider-specific logic is isolated here.
+
+Auth supports:
+  - Regular API keys (sk-ant-api*) → x-api-key header
+  - OAuth setup-tokens (sk-ant-oat*) → Bearer auth + beta header
+  - Claude Code credentials (~/.claude.json or ~/.claude/.credentials.json) → Bearer auth
+"""
+
+import json
+import logging
+import os
+from pathlib import Path
+from types import SimpleNamespace
+from typing import Any, Dict, List, Optional, Tuple
+
+try:
+    import anthropic as _anthropic_sdk
+except ImportError:
+    _anthropic_sdk = None  # type: ignore[assignment]
+
+logger = logging.getLogger(__name__)
+
+THINKING_BUDGET = {"xhigh": 32000, "high": 16000, "medium": 8000, "low": 4000}
+ADAPTIVE_EFFORT_MAP = {
+    "xhigh": "max",
+    "high": "high",
+    "medium": "medium",
+    "low": "low",
+    "minimal": "low",
+}
+
+
+def _supports_adaptive_thinking(model: str) -> bool:
+    """Return True for Claude 4.6 models that support adaptive thinking."""
+    return any(v in model for v in ("4-6", "4.6"))
+
+
+# Beta headers for enhanced features (sent with ALL auth types)
+_COMMON_BETAS = [
+    "interleaved-thinking-2025-05-14",
+    "fine-grained-tool-streaming-2025-05-14",
+]
+
+# Additional beta headers required for OAuth/subscription auth
+# Both clawdbot and OpenCode include claude-code-20250219 alongside oauth-2025-04-20.
+# Without claude-code-20250219, Anthropic's API rejects OAuth tokens with 401.
+_OAUTH_ONLY_BETAS = [
+    "claude-code-20250219",
+    "oauth-2025-04-20",
+]
+
+
+def _is_oauth_token(key: str) -> bool:
+    """Check if the key is an OAuth/setup token (not a regular Console API key).
+
+    Regular API keys start with 'sk-ant-api'. Everything else (setup-tokens
+    starting with 'sk-ant-oat', managed keys, JWTs, etc.) needs Bearer auth.
+    """
+    if not key:
+        return False
+    # Regular Console API keys use x-api-key header
+    if key.startswith("sk-ant-api"):
+        return False
+    # Everything else (setup-tokens, managed keys, JWTs) uses Bearer auth
+    return True
+
+
+def build_anthropic_client(api_key: str, base_url: str = None):
+    """Create an Anthropic client, auto-detecting setup-tokens vs API keys.
+
+    Returns an anthropic.Anthropic instance.
+    """
+    if _anthropic_sdk is None:
+        raise ImportError(
+            "The 'anthropic' package is required for the Anthropic provider. "
+            "Install it with: pip install 'anthropic>=0.39.0'"
+        )
+    from httpx import Timeout
+
+    kwargs = {
+        "timeout": Timeout(timeout=900.0, connect=10.0),
+    }
+    if base_url:
+        kwargs["base_url"] = base_url
+
+    if _is_oauth_token(api_key):
+        # OAuth access token / setup-token → Bearer auth + beta headers
+        all_betas = _COMMON_BETAS + _OAUTH_ONLY_BETAS
+        kwargs["auth_token"] = api_key
+        kwargs["default_headers"] = {"anthropic-beta": ",".join(all_betas)}
+    else:
+        # Regular API key → x-api-key header + common betas
+        kwargs["api_key"] = api_key
+        if _COMMON_BETAS:
+            kwargs["default_headers"] = {"anthropic-beta": ",".join(_COMMON_BETAS)}
+
+    return _anthropic_sdk.Anthropic(**kwargs)
+
+
+def read_claude_code_credentials() -> Optional[Dict[str, Any]]:
+    """Read credentials from Claude Code's config files.
+
+    Checks two locations (in order):
+      1. ~/.claude.json — top-level primaryApiKey (native binary, v2.x)
+      2. ~/.claude/.credentials.json — claudeAiOauth block (npm/legacy installs)
+
+    Returns dict with {accessToken, refreshToken?, expiresAt?} or None.
+    """
+    # 1. Native binary (v2.x): ~/.claude.json with top-level primaryApiKey
+    claude_json = Path.home() / ".claude.json"
+    if claude_json.exists():
+        try:
+            data = json.loads(claude_json.read_text(encoding="utf-8"))
+            primary_key = data.get("primaryApiKey", "")
+            if primary_key:
+                return {
+                    "accessToken": primary_key,
+                    "refreshToken": "",
+                    "expiresAt": 0,  # Managed keys don't have a user-visible expiry
+                }
+        except (json.JSONDecodeError, OSError, IOError) as e:
+            logger.debug("Failed to read ~/.claude.json: %s", e)
+
+    # 2. Legacy/npm installs: ~/.claude/.credentials.json
+    cred_path = Path.home() / ".claude" / ".credentials.json"
+    if cred_path.exists():
+        try:
+            data = json.loads(cred_path.read_text(encoding="utf-8"))
+            oauth_data = data.get("claudeAiOauth")
+            if oauth_data and isinstance(oauth_data, dict):
+                access_token = oauth_data.get("accessToken", "")
+                if access_token:
+                    return {
+                        "accessToken": access_token,
+                        "refreshToken": oauth_data.get("refreshToken", ""),
+                        "expiresAt": oauth_data.get("expiresAt", 0),
+                    }
+        except (json.JSONDecodeError, OSError, IOError) as e:
+            logger.debug("Failed to read ~/.claude/.credentials.json: %s", e)
+
+    return None
+
+
+def is_claude_code_token_valid(creds: Dict[str, Any]) -> bool:
+    """Check if Claude Code credentials have a non-expired access token."""
+    import time
+
+    expires_at = creds.get("expiresAt", 0)
+    if not expires_at:
+        # No expiry set (managed keys) — valid if token is present
+        return bool(creds.get("accessToken"))
+
+    # expiresAt is in milliseconds since epoch
+    now_ms = int(time.time() * 1000)
+    # Allow 60 seconds of buffer
+    return now_ms < (expires_at - 60_000)
+
+
+def _refresh_oauth_token(creds: Dict[str, Any]) -> Optional[str]:
+    """Attempt to refresh an expired Claude Code OAuth token.
+
+    Uses the same token endpoint and client_id as Claude Code / OpenCode.
+    Only works for credentials that have a refresh token (from claude /login
+    or claude setup-token with OAuth flow).
+
+    Returns the new access token, or None if refresh fails.
+    """
+    import urllib.parse
+    import urllib.request
+
+    refresh_token = creds.get("refreshToken", "")
+    if not refresh_token:
+        logger.debug("No refresh token available — cannot refresh")
+        return None
+
+    # Client ID used by Claude Code's OAuth flow
+    CLIENT_ID = "9d1c250a-e61b-44d9-88ed-5944d1962f5e"
+
+    data = urllib.parse.urlencode({
+        "grant_type": "refresh_token",
+        "refresh_token": refresh_token,
+        "client_id": CLIENT_ID,
+    }).encode()
+
+    req = urllib.request.Request(
+        "https://console.anthropic.com/v1/oauth/token",
+        data=data,
+        headers={"Content-Type": "application/x-www-form-urlencoded"},
+        method="POST",
+    )
+
+    try:
+        with urllib.request.urlopen(req, timeout=10) as resp:
+            result = json.loads(resp.read().decode())
+            new_access = result.get("access_token", "")
+            new_refresh = result.get("refresh_token", refresh_token)
+            expires_in = result.get("expires_in", 3600)  # seconds
+
+            if new_access:
+                import time
+                new_expires_ms = int(time.time() * 1000) + (expires_in * 1000)
+                # Write refreshed credentials back to ~/.claude/.credentials.json
+                _write_claude_code_credentials(new_access, new_refresh, new_expires_ms)
+                logger.debug("Successfully refreshed Claude Code OAuth token")
+                return new_access
+    except Exception as e:
+        logger.debug("Failed to refresh Claude Code token: %s", e)
+
+    return None
+
+
+def _write_claude_code_credentials(access_token: str, refresh_token: str, expires_at_ms: int) -> None:
+    """Write refreshed credentials back to ~/.claude/.credentials.json."""
+    cred_path = Path.home() / ".claude" / ".credentials.json"
+    try:
+        # Read existing file to preserve other fields
+        existing = {}
+        if cred_path.exists():
+            existing = json.loads(cred_path.read_text(encoding="utf-8"))
+
+        existing["claudeAiOauth"] = {
+            "accessToken": access_token,
+            "refreshToken": refresh_token,
+            "expiresAt": expires_at_ms,
+        }
+
+        cred_path.parent.mkdir(parents=True, exist_ok=True)
+        cred_path.write_text(json.dumps(existing, indent=2), encoding="utf-8")
+        # Restrict permissions (credentials file)
+        cred_path.chmod(0o600)
+    except (OSError, IOError) as e:
+        logger.debug("Failed to write refreshed credentials: %s", e)
+
+
+def resolve_anthropic_token() -> Optional[str]:
+    """Resolve an Anthropic token from all available sources.
+
+    Priority:
+      1. ANTHROPIC_TOKEN env var (OAuth/setup token saved by Hermes)
+      2. CLAUDE_CODE_OAUTH_TOKEN env var
+      3. Claude Code credentials (~/.claude.json or ~/.claude/.credentials.json)
+         — with automatic refresh if expired and a refresh token is available
+      4. ANTHROPIC_API_KEY env var (regular API key, or legacy fallback)
+
+    Returns the token string or None.
+    """
+    # 1. Hermes-managed OAuth/setup token env var
+    token = os.getenv("ANTHROPIC_TOKEN", "").strip()
+    if token:
+        return token
+
+    # 2. CLAUDE_CODE_OAUTH_TOKEN (used by Claude Code for setup-tokens)
+    cc_token = os.getenv("CLAUDE_CODE_OAUTH_TOKEN", "").strip()
+    if cc_token:
+        return cc_token
+
+    # 3. Claude Code credential file
+    creds = read_claude_code_credentials()
+    if creds and is_claude_code_token_valid(creds):
+        logger.debug("Using Claude Code credentials (auto-detected)")
+        return creds["accessToken"]
+    elif creds:
+        # Token expired — attempt to refresh
+        logger.debug("Claude Code credentials expired — attempting refresh")
+        refreshed = _refresh_oauth_token(creds)
+        if refreshed:
+            return refreshed
+        logger.debug("Token refresh failed — re-run 'claude setup-token' to reauthenticate")
+
+    # 4. Regular API key, or a legacy OAuth token saved in ANTHROPIC_API_KEY.
+    # This remains as a compatibility fallback for pre-migration Hermes configs.
+    api_key = os.getenv("ANTHROPIC_API_KEY", "").strip()
+    if api_key:
+        return api_key
+
+    return None
+
+
+def run_oauth_setup_token() -> Optional[str]:
+    """Run 'claude setup-token' interactively and return the resulting token.
+
+    Checks multiple sources after the subprocess completes:
+      1. Claude Code credential files (may be written by the subprocess)
+      2. CLAUDE_CODE_OAUTH_TOKEN / ANTHROPIC_TOKEN env vars
+
+    Returns the token string, or None if no credentials were obtained.
+    Raises FileNotFoundError if the 'claude' CLI is not installed.
+    """
+    import shutil
+    import subprocess
+
+    claude_path = shutil.which("claude")
+    if not claude_path:
+        raise FileNotFoundError(
+            "The 'claude' CLI is not installed. "
+            "Install it with: npm install -g @anthropic-ai/claude-code"
+        )
+
+    # Run interactively — stdin/stdout/stderr inherited so user can interact
+    try:
+        subprocess.run([claude_path, "setup-token"])
+    except (KeyboardInterrupt, EOFError):
+        return None
+
+    # Check if credentials were saved to Claude Code's config files
+    creds = read_claude_code_credentials()
+    if creds and is_claude_code_token_valid(creds):
+        return creds["accessToken"]
+
+    # Check env vars that may have been set
+    for env_var in ("CLAUDE_CODE_OAUTH_TOKEN", "ANTHROPIC_TOKEN"):
+        val = os.getenv(env_var, "").strip()
+        if val:
+            return val
+
+    return None
+
+
+# ---------------------------------------------------------------------------
+# Message / tool / response format conversion
+# ---------------------------------------------------------------------------
+
+
+def normalize_model_name(model: str) -> str:
+    """Normalize a model name for the Anthropic API.
+
+    - Strips 'anthropic/' prefix (OpenRouter format, case-insensitive)
+    - Converts dots to hyphens in version numbers (OpenRouter uses dots,
+      Anthropic uses hyphens: claude-opus-4.6 → claude-opus-4-6)
+    """
+    lower = model.lower()
+    if lower.startswith("anthropic/"):
+        model = model[len("anthropic/"):]
+    # OpenRouter uses dots for version separators (claude-opus-4.6),
+    # Anthropic uses hyphens (claude-opus-4-6). Convert dots to hyphens.
+    model = model.replace(".", "-")
+    return model
+
+
+def _sanitize_tool_id(tool_id: str) -> str:
+    """Sanitize a tool call ID for the Anthropic API.
+
+    Anthropic requires IDs matching [a-zA-Z0-9_-]. Replace invalid
+    characters with underscores and ensure non-empty.
+    """
+    import re
+    if not tool_id:
+        return "tool_0"
+    sanitized = re.sub(r"[^a-zA-Z0-9_-]", "_", tool_id)
+    return sanitized or "tool_0"
+
+
+def convert_tools_to_anthropic(tools: List[Dict]) -> List[Dict]:
+    """Convert OpenAI tool definitions to Anthropic format."""
+    if not tools:
+        return []
+    result = []
+    for t in tools:
+        fn = t.get("function", {})
+        result.append({
+            "name": fn.get("name", ""),
+            "description": fn.get("description", ""),
+            "input_schema": fn.get("parameters", {"type": "object", "properties": {}}),
+        })
+    return result
+
+
+def convert_messages_to_anthropic(
+    messages: List[Dict],
+) -> Tuple[Optional[Any], List[Dict]]:
+    """Convert OpenAI-format messages to Anthropic format.
+
+    Returns (system_prompt, anthropic_messages).
+    System messages are extracted since Anthropic takes them as a separate param.
+    system_prompt is a string or list of content blocks (when cache_control present).
+    """
+    system = None
+    result = []
+
+    for m in messages:
+        role = m.get("role", "user")
+        content = m.get("content", "")
+
+        if role == "system":
+            if isinstance(content, list):
+                # Preserve cache_control markers on content blocks
+                has_cache = any(
+                    p.get("cache_control") for p in content if isinstance(p, dict)
+                )
+                if has_cache:
+                    system = [p for p in content if isinstance(p, dict)]
+                else:
+                    system = "\n".join(
+                        p["text"] for p in content if p.get("type") == "text"
+                    )
+            else:
+                system = content
+            continue
+
+        if role == "assistant":
+            blocks = []
+            if content:
+                text = content if isinstance(content, str) else json.dumps(content)
+                blocks.append({"type": "text", "text": text})
+            for tc in m.get("tool_calls", []):
+                fn = tc.get("function", {})
+                args = fn.get("arguments", "{}")
+                try:
+                    parsed_args = json.loads(args) if isinstance(args, str) else args
+                except (json.JSONDecodeError, ValueError):
+                    parsed_args = {}
+                blocks.append({
+                    "type": "tool_use",
+                    "id": _sanitize_tool_id(tc.get("id", "")),
+                    "name": fn.get("name", ""),
+                    "input": parsed_args,
+                })
+            # Anthropic rejects empty assistant content
+            effective = blocks or content
+            if not effective or effective == "":
+                effective = [{"type": "text", "text": "(empty)"}]
+            result.append({"role": "assistant", "content": effective})
+            continue
+
+        if role == "tool":
+            # Sanitize tool_use_id and ensure non-empty content
+            result_content = content if isinstance(content, str) else json.dumps(content)
+            if not result_content:
+                result_content = "(no output)"
+            tool_result = {
+                "type": "tool_result",
+                "tool_use_id": _sanitize_tool_id(m.get("tool_call_id", "")),
+                "content": result_content,
+            }
+            # Merge consecutive tool results into one user message
+            if (
+                result
+                and result[-1]["role"] == "user"
+                and isinstance(result[-1]["content"], list)
+                and result[-1]["content"]
+                and result[-1]["content"][0].get("type") == "tool_result"
+            ):
+                result[-1]["content"].append(tool_result)
+            else:
+                result.append({"role": "user", "content": [tool_result]})
+            continue
+
+        # Regular user message
+        result.append({"role": "user", "content": content})
+
+    # Strip orphaned tool_use blocks (no matching tool_result follows)
+    tool_result_ids = set()
+    for m in result:
+        if m["role"] == "user" and isinstance(m["content"], list):
+            for block in m["content"]:
+                if block.get("type") == "tool_result":
+                    tool_result_ids.add(block.get("tool_use_id"))
+    for m in result:
+        if m["role"] == "assistant" and isinstance(m["content"], list):
+            m["content"] = [
+                b
+                for b in m["content"]
+                if b.get("type") != "tool_use" or b.get("id") in tool_result_ids
+            ]
+            if not m["content"]:
+                m["content"] = [{"type": "text", "text": "(tool call removed)"}]
+
+    # Enforce strict role alternation (Anthropic rejects consecutive same-role messages)
+    fixed = []
+    for m in result:
+        if fixed and fixed[-1]["role"] == m["role"]:
+            if m["role"] == "user":
+                # Merge consecutive user messages
+                prev_content = fixed[-1]["content"]
+                curr_content = m["content"]
+                if isinstance(prev_content, str) and isinstance(curr_content, str):
+                    fixed[-1]["content"] = prev_content + "\n" + curr_content
+                elif isinstance(prev_content, list) and isinstance(curr_content, list):
+                    fixed[-1]["content"] = prev_content + curr_content
+                else:
+                    # Mixed types — wrap string in list
+                    if isinstance(prev_content, str):
+                        prev_content = [{"type": "text", "text": prev_content}]
+                    if isinstance(curr_content, str):
+                        curr_content = [{"type": "text", "text": curr_content}]
+                    fixed[-1]["content"] = prev_content + curr_content
+            else:
+                # Consecutive assistant messages — merge text content
+                prev_blocks = fixed[-1]["content"]
+                curr_blocks = m["content"]
+                if isinstance(prev_blocks, list) and isinstance(curr_blocks, list):
+                    fixed[-1]["content"] = prev_blocks + curr_blocks
+                elif isinstance(prev_blocks, str) and isinstance(curr_blocks, str):
+                    fixed[-1]["content"] = prev_blocks + "\n" + curr_blocks
+                else:
+                    # Keep the later message
+                    fixed[-1] = m
+        else:
+            fixed.append(m)
+    result = fixed
+
+    return system, result
+
+
+def build_anthropic_kwargs(
+    model: str,
+    messages: List[Dict],
+    tools: Optional[List[Dict]],
+    max_tokens: Optional[int],
+    reasoning_config: Optional[Dict[str, Any]],
+    tool_choice: Optional[str] = None,
+) -> Dict[str, Any]:
+    """Build kwargs for anthropic.messages.create()."""
+    system, anthropic_messages = convert_messages_to_anthropic(messages)
+    anthropic_tools = convert_tools_to_anthropic(tools) if tools else []
+
+    model = normalize_model_name(model)
+    effective_max_tokens = max_tokens or 16384
+
+    kwargs: Dict[str, Any] = {
+        "model": model,
+        "messages": anthropic_messages,
+        "max_tokens": effective_max_tokens,
+    }
+
+    if system:
+        kwargs["system"] = system
+
+    if anthropic_tools:
+        kwargs["tools"] = anthropic_tools
+        # Map OpenAI tool_choice to Anthropic format
+        if tool_choice == "auto" or tool_choice is None:
+            kwargs["tool_choice"] = {"type": "auto"}
+        elif tool_choice == "required":
+            kwargs["tool_choice"] = {"type": "any"}
+        elif tool_choice == "none":
+            pass  # Don't send tool_choice — Anthropic will use tools if needed
+        elif isinstance(tool_choice, str):
+            # Specific tool name
+            kwargs["tool_choice"] = {"type": "tool", "name": tool_choice}
+
+    # Map reasoning_config to Anthropic's thinking parameter.
+    # Claude 4.6 models use adaptive thinking + output_config.effort.
+    # Older models use manual thinking with budget_tokens.
+    # Haiku models do NOT support extended thinking at all — skip entirely.
+    if reasoning_config and isinstance(reasoning_config, dict):
+        if reasoning_config.get("enabled") is not False and "haiku" not in model.lower():
+            effort = str(reasoning_config.get("effort", "medium")).lower()
+            budget = THINKING_BUDGET.get(effort, 8000)
+            if _supports_adaptive_thinking(model):
+                kwargs["thinking"] = {"type": "adaptive"}
+                kwargs["output_config"] = {
+                    "effort": ADAPTIVE_EFFORT_MAP.get(effort, "medium")
+                }
+            else:
+                kwargs["thinking"] = {"type": "enabled", "budget_tokens": budget}
+                # Anthropic requires temperature=1 when thinking is enabled on older models
+                kwargs["temperature"] = 1
+                kwargs["max_tokens"] = max(effective_max_tokens, budget + 4096)
+
+    return kwargs
+
+
+def normalize_anthropic_response(
+    response,
+) -> Tuple[SimpleNamespace, str]:
+    """Normalize Anthropic response to match the shape expected by AIAgent.
+
+    Returns (assistant_message, finish_reason) where assistant_message has
+    .content, .tool_calls, and .reasoning attributes.
+    """
+    text_parts = []
+    reasoning_parts = []
+    tool_calls = []
+
+    for block in response.content:
+        if block.type == "text":
+            text_parts.append(block.text)
+        elif block.type == "thinking":
+            reasoning_parts.append(block.thinking)
+        elif block.type == "tool_use":
+            tool_calls.append(
+                SimpleNamespace(
+                    id=block.id,
+                    type="function",
+                    function=SimpleNamespace(
+                        name=block.name,
+                        arguments=json.dumps(block.input),
+                    ),
+                )
+            )
+
+    # Map Anthropic stop_reason to OpenAI finish_reason
+    stop_reason_map = {
+        "end_turn": "stop",
+        "tool_use": "tool_calls",
+        "max_tokens": "length",
+        "stop_sequence": "stop",
+    }
+    finish_reason = stop_reason_map.get(response.stop_reason, "stop")
+
+    return (
+        SimpleNamespace(
+            content="\n".join(text_parts) if text_parts else None,
+            tool_calls=tool_calls or None,
+            reasoning="\n\n".join(reasoning_parts) if reasoning_parts else None,
+            reasoning_content=None,
+            reasoning_details=None,
+        ),
+        finish_reason,
+    )

agent/auxiliary_client.py

@@ -17,7 +17,10 @@ Resolution order for text tasks (auto mode):
 Resolution order for vision/multimodal tasks (auto mode):
   1. OpenRouter
   2. Nous Portal
-  3. None  (steps 3-5 are skipped — they may not support multimodal)
+  3. Codex OAuth (gpt-5.3-codex supports vision via Responses API)
+  4. Custom endpoint (for local vision models: Qwen-VL, LLaVA, Pixtral, etc.)
+  5. None  (API-key providers like z.ai/Kimi/MiniMax are skipped —
+     they may not support multimodal)
 
 Per-task provider overrides (e.g. AUXILIARY_VISION_PROVIDER,
 CONTEXT_COMPRESSION_PROVIDER) can force a specific provider for each task:
@@ -48,11 +51,12 @@ _API_KEY_PROVIDER_AUX_MODELS: Dict[str, str] = {
     "kimi-coding": "kimi-k2-turbo-preview",
     "minimax": "MiniMax-M2.5-highspeed",
     "minimax-cn": "MiniMax-M2.5-highspeed",
+    "anthropic": "claude-haiku-4-5-20251001",
 }
 
 # OpenRouter app attribution headers
 _OR_HEADERS = {
-    "HTTP-Referer": "https://github.com/NousResearch/hermes-agent",
+    "HTTP-Referer": "https://hermes-agent.nousresearch.com",
     "X-OpenRouter-Title": "Hermes Agent",
     "X-OpenRouter-Categories": "productivity,cli-agent",
 }
@@ -440,7 +444,7 @@ def _try_custom_endpoint() -> Tuple[Optional[OpenAI], Optional[str]]:
     custom_key = os.getenv("OPENAI_API_KEY")
     if not custom_base or not custom_key:
         return None, None
-    model = os.getenv("OPENAI_MODEL") or os.getenv("LLM_MODEL") or "gpt-4o-mini"
+    model = os.getenv("OPENAI_MODEL") or "gpt-4o-mini"
     logger.debug("Auxiliary client: custom endpoint (%s)", model)
     return OpenAI(api_key=custom_key, base_url=custom_base), model
 
@@ -499,6 +503,205 @@ def _resolve_auto() -> Tuple[Optional[OpenAI], Optional[str]]:
     return None, None
 
 
+# ── Centralized Provider Router ─────────────────────────────────────────────
+#
+# resolve_provider_client() is the single entry point for creating a properly
+# configured client given a (provider, model) pair.  It handles auth lookup,
+# base URL resolution, provider-specific headers, and API format differences
+# (Chat Completions vs Responses API for Codex).
+#
+# All auxiliary consumer code should go through this or the public helpers
+# below — never look up auth env vars ad-hoc.
+
+
+def _to_async_client(sync_client, model: str):
+    """Convert a sync client to its async counterpart, preserving Codex routing."""
+    from openai import AsyncOpenAI
+
+    if isinstance(sync_client, CodexAuxiliaryClient):
+        return AsyncCodexAuxiliaryClient(sync_client), model
+
+    async_kwargs = {
+        "api_key": sync_client.api_key,
+        "base_url": str(sync_client.base_url),
+    }
+    base_lower = str(sync_client.base_url).lower()
+    if "openrouter" in base_lower:
+        async_kwargs["default_headers"] = dict(_OR_HEADERS)
+    elif "api.kimi.com" in base_lower:
+        async_kwargs["default_headers"] = {"User-Agent": "KimiCLI/1.0"}
+    return AsyncOpenAI(**async_kwargs), model
+
+
+def resolve_provider_client(
+    provider: str,
+    model: str = None,
+    async_mode: bool = False,
+    raw_codex: bool = False,
+) -> Tuple[Optional[Any], Optional[str]]:
+    """Central router: given a provider name and optional model, return a
+    configured client with the correct auth, base URL, and API format.
+
+    The returned client always exposes ``.chat.completions.create()`` — for
+    Codex/Responses API providers, an adapter handles the translation
+    transparently.
+
+    Args:
+        provider: Provider identifier.  One of:
+            "openrouter", "nous", "openai-codex" (or "codex"),
+            "zai", "kimi-coding", "minimax", "minimax-cn",
+            "custom" (OPENAI_BASE_URL + OPENAI_API_KEY),
+            "auto" (full auto-detection chain).
+        model: Model slug override.  If None, uses the provider's default
+               auxiliary model.
+        async_mode: If True, return an async-compatible client.
+        raw_codex: If True, return a raw OpenAI client for Codex providers
+            instead of wrapping in CodexAuxiliaryClient.  Use this when
+            the caller needs direct access to responses.stream() (e.g.,
+            the main agent loop).
+
+    Returns:
+        (client, resolved_model) or (None, None) if auth is unavailable.
+    """
+    # Normalise aliases
+    provider = (provider or "auto").strip().lower()
+    if provider == "codex":
+        provider = "openai-codex"
+    if provider == "main":
+        provider = "custom"
+
+    # ── Auto: try all providers in priority order ────────────────────
+    if provider == "auto":
+        client, resolved = _resolve_auto()
+        if client is None:
+            return None, None
+        final_model = model or resolved
+        return (_to_async_client(client, final_model) if async_mode
+                else (client, final_model))
+
+    # ── OpenRouter ───────────────────────────────────────────────────
+    if provider == "openrouter":
+        client, default = _try_openrouter()
+        if client is None:
+            logger.warning("resolve_provider_client: openrouter requested "
+                           "but OPENROUTER_API_KEY not set")
+            return None, None
+        final_model = model or default
+        return (_to_async_client(client, final_model) if async_mode
+                else (client, final_model))
+
+    # ── Nous Portal (OAuth) ──────────────────────────────────────────
+    if provider == "nous":
+        client, default = _try_nous()
+        if client is None:
+            logger.warning("resolve_provider_client: nous requested "
+                           "but Nous Portal not configured (run: hermes login)")
+            return None, None
+        final_model = model or default
+        return (_to_async_client(client, final_model) if async_mode
+                else (client, final_model))
+
+    # ── OpenAI Codex (OAuth → Responses API) ─────────────────────────
+    if provider == "openai-codex":
+        if raw_codex:
+            # Return the raw OpenAI client for callers that need direct
+            # access to responses.stream() (e.g., the main agent loop).
+            codex_token = _read_codex_access_token()
+            if not codex_token:
+                logger.warning("resolve_provider_client: openai-codex requested "
+                               "but no Codex OAuth token found (run: hermes model)")
+                return None, None
+            final_model = model or _CODEX_AUX_MODEL
+            raw_client = OpenAI(api_key=codex_token, base_url=_CODEX_AUX_BASE_URL)
+            return (raw_client, final_model)
+        # Standard path: wrap in CodexAuxiliaryClient adapter
+        client, default = _try_codex()
+        if client is None:
+            logger.warning("resolve_provider_client: openai-codex requested "
+                           "but no Codex OAuth token found (run: hermes model)")
+            return None, None
+        final_model = model or default
+        return (_to_async_client(client, final_model) if async_mode
+                else (client, final_model))
+
+    # ── Custom endpoint (OPENAI_BASE_URL + OPENAI_API_KEY) ───────────
+    if provider == "custom":
+        # Try custom first, then codex, then API-key providers
+        for try_fn in (_try_custom_endpoint, _try_codex,
+                       _resolve_api_key_provider):
+            client, default = try_fn()
+            if client is not None:
+                final_model = model or default
+                return (_to_async_client(client, final_model) if async_mode
+                        else (client, final_model))
+        logger.warning("resolve_provider_client: custom/main requested "
+                       "but no endpoint credentials found")
+        return None, None
+
+    # ── API-key providers from PROVIDER_REGISTRY ─────────────────────
+    try:
+        from hermes_cli.auth import PROVIDER_REGISTRY, _resolve_kimi_base_url
+    except ImportError:
+        logger.debug("hermes_cli.auth not available for provider %s", provider)
+        return None, None
+
+    pconfig = PROVIDER_REGISTRY.get(provider)
+    if pconfig is None:
+        logger.warning("resolve_provider_client: unknown provider %r", provider)
+        return None, None
+
+    if pconfig.auth_type == "api_key":
+        # Find the first configured API key
+        api_key = ""
+        for env_var in pconfig.api_key_env_vars:
+            api_key = os.getenv(env_var, "").strip()
+            if api_key:
+                break
+        if not api_key:
+            logger.warning("resolve_provider_client: provider %s has no API "
+                           "key configured (tried: %s)",
+                           provider, ", ".join(pconfig.api_key_env_vars))
+            return None, None
+
+        # Resolve base URL (env override → provider-specific logic → default)
+        base_url_override = os.getenv(pconfig.base_url_env_var, "").strip() if pconfig.base_url_env_var else ""
+        if provider == "kimi-coding":
+            base_url = _resolve_kimi_base_url(api_key, pconfig.inference_base_url, base_url_override)
+        elif base_url_override:
+            base_url = base_url_override
+        else:
+            base_url = pconfig.inference_base_url
+
+        default_model = _API_KEY_PROVIDER_AUX_MODELS.get(provider, "")
+        final_model = model or default_model
+
+        # Provider-specific headers
+        headers = {}
+        if "api.kimi.com" in base_url.lower():
+            headers["User-Agent"] = "KimiCLI/1.0"
+
+        client = OpenAI(api_key=api_key, base_url=base_url,
+                        **({"default_headers": headers} if headers else {}))
+        logger.debug("resolve_provider_client: %s (%s)", provider, final_model)
+        return (_to_async_client(client, final_model) if async_mode
+                else (client, final_model))
+
+    elif pconfig.auth_type in ("oauth_device_code", "oauth_external"):
+        # OAuth providers — route through their specific try functions
+        if provider == "nous":
+            return resolve_provider_client("nous", model, async_mode)
+        if provider == "openai-codex":
+            return resolve_provider_client("openai-codex", model, async_mode)
+        # Other OAuth providers not directly supported
+        logger.warning("resolve_provider_client: OAuth provider %s not "
+                       "directly supported, try 'auto'", provider)
+        return None, None
+
+    logger.warning("resolve_provider_client: unhandled auth_type %s for %s",
+                   pconfig.auth_type, provider)
+    return None, None
+
+
 # ── Public API ──────────────────────────────────────────────────────────────
 
 def get_text_auxiliary_client(task: str = "") -> Tuple[Optional[OpenAI], Optional[str]]:
@@ -513,8 +716,8 @@ def get_text_auxiliary_client(task: str = "") -> Tuple[Optional[OpenAI], Optiona
     """
     forced = _get_auxiliary_provider(task)
     if forced != "auto":
-        return _resolve_forced_provider(forced)
-    return _resolve_auto()
+        return resolve_provider_client(forced)
+    return resolve_provider_client("auto")
 
 
 def get_async_text_auxiliary_client(task: str = ""):
@@ -524,24 +727,10 @@ def get_async_text_auxiliary_client(task: str = ""):
     (AsyncCodexAuxiliaryClient, model) which wraps the Responses API.
     Returns (None, None) when no provider is available.
     """
-    from openai import AsyncOpenAI
-
-    sync_client, model = get_text_auxiliary_client(task)
-    if sync_client is None:
-        return None, None
-
-    if isinstance(sync_client, CodexAuxiliaryClient):
-        return AsyncCodexAuxiliaryClient(sync_client), model
-
-    async_kwargs = {
-        "api_key": sync_client.api_key,
-        "base_url": str(sync_client.base_url),
-    }
-    if "openrouter" in str(sync_client.base_url).lower():
-        async_kwargs["default_headers"] = dict(_OR_HEADERS)
-    elif "api.kimi.com" in str(sync_client.base_url).lower():
-        async_kwargs["default_headers"] = {"User-Agent": "KimiCLI/1.0"}
-    return AsyncOpenAI(**async_kwargs), model
+    forced = _get_auxiliary_provider(task)
+    if forced != "auto":
+        return resolve_provider_client(forced, async_mode=True)
+    return resolve_provider_client("auto", async_mode=True)
 
 
 def get_vision_auxiliary_client() -> Tuple[Optional[OpenAI], Optional[str]]:
@@ -559,7 +748,7 @@ def get_vision_auxiliary_client() -> Tuple[Optional[OpenAI], Optional[str]]:
     """
     forced = _get_auxiliary_provider("vision")
     if forced != "auto":
-        return _resolve_forced_provider(forced)
+        return resolve_provider_client(forced)
     # Auto: try providers known to support multimodal first, then fall
     # back to the user's custom endpoint.  Many local models (Qwen-VL,
     # LLaVA, Pixtral, etc.) support vision — skipping them entirely
@@ -573,6 +762,21 @@ def get_vision_auxiliary_client() -> Tuple[Optional[OpenAI], Optional[str]]:
     return None, None
 
 
+def get_async_vision_auxiliary_client():
+    """Return (async_client, model_slug) for async vision consumers.
+
+    Properly handles Codex routing — unlike manually constructing
+    AsyncOpenAI from a sync client, this preserves the Responses API
+    adapter for Codex providers.
+
+    Returns (None, None) when no provider is available.
+    """
+    sync_client, model = get_vision_auxiliary_client()
+    if sync_client is None:
+        return None, None
+    return _to_async_client(sync_client, model)
+
+
 def get_auxiliary_extra_body() -> dict:
     """Return extra_body kwargs for auxiliary API calls.
     
@@ -598,3 +802,253 @@ def auxiliary_max_tokens_param(value: int) -> dict:
             and "api.openai.com" in custom_base.lower()):
         return {"max_completion_tokens": value}
     return {"max_tokens": value}
+
+
+# ── Centralized LLM Call API ────────────────────────────────────────────────
+#
+# call_llm() and async_call_llm() own the full request lifecycle:
+#   1. Resolve provider + model from task config (or explicit args)
+#   2. Get or create a cached client for that provider
+#   3. Format request args for the provider + model (max_tokens handling, etc.)
+#   4. Make the API call
+#   5. Return the response
+#
+# Every auxiliary LLM consumer should use these instead of manually
+# constructing clients and calling .chat.completions.create().
+
+# Client cache: (provider, async_mode) -> (client, default_model)
+_client_cache: Dict[tuple, tuple] = {}
+
+
+def _get_cached_client(
+    provider: str, model: str = None, async_mode: bool = False,
+) -> Tuple[Optional[Any], Optional[str]]:
+    """Get or create a cached client for the given provider."""
+    cache_key = (provider, async_mode)
+    if cache_key in _client_cache:
+        cached_client, cached_default = _client_cache[cache_key]
+        return cached_client, model or cached_default
+    client, default_model = resolve_provider_client(provider, model, async_mode)
+    if client is not None:
+        _client_cache[cache_key] = (client, default_model)
+    return client, model or default_model
+
+
+def _resolve_task_provider_model(
+    task: str = None,
+    provider: str = None,
+    model: str = None,
+) -> Tuple[str, Optional[str]]:
+    """Determine provider + model for a call.
+
+    Priority:
+      1. Explicit provider/model args (always win)
+      2. Env var overrides (AUXILIARY_{TASK}_PROVIDER, etc.)
+      3. Config file (auxiliary.{task}.provider/model or compression.*)
+      4. "auto" (full auto-detection chain)
+
+    Returns (provider, model) where model may be None (use provider default).
+    """
+    if provider:
+        return provider, model
+
+    if task:
+        # Check env var overrides first
+        env_provider = _get_auxiliary_provider(task)
+        if env_provider != "auto":
+            # Check for env var model override too
+            env_model = None
+            for prefix in ("AUXILIARY_", "CONTEXT_"):
+                val = os.getenv(f"{prefix}{task.upper()}_MODEL", "").strip()
+                if val:
+                    env_model = val
+                    break
+            return env_provider, model or env_model
+
+        # Read from config file
+        try:
+            from hermes_cli.config import load_config
+            config = load_config()
+        except ImportError:
+            return "auto", model
+
+        # Check auxiliary.{task} section
+        aux = config.get("auxiliary", {})
+        task_config = aux.get(task, {})
+        cfg_provider = task_config.get("provider", "").strip() or None
+        cfg_model = task_config.get("model", "").strip() or None
+
+        # Backwards compat: compression section has its own keys
+        if task == "compression" and not cfg_provider:
+            comp = config.get("compression", {})
+            cfg_provider = comp.get("summary_provider", "").strip() or None
+            cfg_model = cfg_model or comp.get("summary_model", "").strip() or None
+
+        if cfg_provider and cfg_provider != "auto":
+            return cfg_provider, model or cfg_model
+        return "auto", model or cfg_model
+
+    return "auto", model
+
+
+def _build_call_kwargs(
+    provider: str,
+    model: str,
+    messages: list,
+    temperature: Optional[float] = None,
+    max_tokens: Optional[int] = None,
+    tools: Optional[list] = None,
+    timeout: float = 30.0,
+    extra_body: Optional[dict] = None,
+) -> dict:
+    """Build kwargs for .chat.completions.create() with model/provider adjustments."""
+    kwargs: Dict[str, Any] = {
+        "model": model,
+        "messages": messages,
+        "timeout": timeout,
+    }
+
+    if temperature is not None:
+        kwargs["temperature"] = temperature
+
+    if max_tokens is not None:
+        # Codex adapter handles max_tokens internally; OpenRouter/Nous use max_tokens.
+        # Direct OpenAI api.openai.com with newer models needs max_completion_tokens.
+        if provider == "custom":
+            custom_base = os.getenv("OPENAI_BASE_URL", "")
+            if "api.openai.com" in custom_base.lower():
+                kwargs["max_completion_tokens"] = max_tokens
+            else:
+                kwargs["max_tokens"] = max_tokens
+        else:
+            kwargs["max_tokens"] = max_tokens
+
+    if tools:
+        kwargs["tools"] = tools
+
+    # Provider-specific extra_body
+    merged_extra = dict(extra_body or {})
+    if provider == "nous" or auxiliary_is_nous:
+        merged_extra.setdefault("tags", []).extend(["product=hermes-agent"])
+    if merged_extra:
+        kwargs["extra_body"] = merged_extra
+
+    return kwargs
+
+
+def call_llm(
+    task: str = None,
+    *,
+    provider: str = None,
+    model: str = None,
+    messages: list,
+    temperature: float = None,
+    max_tokens: int = None,
+    tools: list = None,
+    timeout: float = 30.0,
+    extra_body: dict = None,
+) -> Any:
+    """Centralized synchronous LLM call.
+
+    Resolves provider + model (from task config, explicit args, or auto-detect),
+    handles auth, request formatting, and model-specific arg adjustments.
+
+    Args:
+        task: Auxiliary task name ("compression", "vision", "web_extract",
+              "session_search", "skills_hub", "mcp", "flush_memories").
+              Reads provider:model from config/env. Ignored if provider is set.
+        provider: Explicit provider override.
+        model: Explicit model override.
+        messages: Chat messages list.
+        temperature: Sampling temperature (None = provider default).
+        max_tokens: Max output tokens (handles max_tokens vs max_completion_tokens).
+        tools: Tool definitions (for function calling).
+        timeout: Request timeout in seconds.
+        extra_body: Additional request body fields.
+
+    Returns:
+        Response object with .choices[0].message.content
+
+    Raises:
+        RuntimeError: If no provider is configured.
+    """
+    resolved_provider, resolved_model = _resolve_task_provider_model(
+        task, provider, model)
+
+    client, final_model = _get_cached_client(resolved_provider, resolved_model)
+    if client is None:
+        # Fallback: try openrouter
+        if resolved_provider != "openrouter":
+            logger.warning("Provider %s unavailable, falling back to openrouter",
+                           resolved_provider)
+            client, final_model = _get_cached_client(
+                "openrouter", resolved_model or _OPENROUTER_MODEL)
+    if client is None:
+        raise RuntimeError(
+            f"No LLM provider configured for task={task} provider={resolved_provider}. "
+            f"Run: hermes setup")
+
+    kwargs = _build_call_kwargs(
+        resolved_provider, final_model, messages,
+        temperature=temperature, max_tokens=max_tokens,
+        tools=tools, timeout=timeout, extra_body=extra_body)
+
+    # Handle max_tokens vs max_completion_tokens retry
+    try:
+        return client.chat.completions.create(**kwargs)
+    except Exception as first_err:
+        err_str = str(first_err)
+        if "max_tokens" in err_str or "unsupported_parameter" in err_str:
+            kwargs.pop("max_tokens", None)
+            kwargs["max_completion_tokens"] = max_tokens
+            return client.chat.completions.create(**kwargs)
+        raise
+
+
+async def async_call_llm(
+    task: str = None,
+    *,
+    provider: str = None,
+    model: str = None,
+    messages: list,
+    temperature: float = None,
+    max_tokens: int = None,
+    tools: list = None,
+    timeout: float = 30.0,
+    extra_body: dict = None,
+) -> Any:
+    """Centralized asynchronous LLM call.
+
+    Same as call_llm() but async. See call_llm() for full documentation.
+    """
+    resolved_provider, resolved_model = _resolve_task_provider_model(
+        task, provider, model)
+
+    client, final_model = _get_cached_client(
+        resolved_provider, resolved_model, async_mode=True)
+    if client is None:
+        if resolved_provider != "openrouter":
+            logger.warning("Provider %s unavailable, falling back to openrouter",
+                           resolved_provider)
+            client, final_model = _get_cached_client(
+                "openrouter", resolved_model or _OPENROUTER_MODEL,
+                async_mode=True)
+    if client is None:
+        raise RuntimeError(
+            f"No LLM provider configured for task={task} provider={resolved_provider}. "
+            f"Run: hermes setup")
+
+    kwargs = _build_call_kwargs(
+        resolved_provider, final_model, messages,
+        temperature=temperature, max_tokens=max_tokens,
+        tools=tools, timeout=timeout, extra_body=extra_body)
+
+    try:
+        return await client.chat.completions.create(**kwargs)
+    except Exception as first_err:
+        err_str = str(first_err)
+        if "max_tokens" in err_str or "unsupported_parameter" in err_str:
+            kwargs.pop("max_tokens", None)
+            kwargs["max_completion_tokens"] = max_tokens
+            return await client.chat.completions.create(**kwargs)
+        raise

agent/context_compressor.py

@@ -9,7 +9,7 @@ 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,
@@ -28,7 +28,7 @@ class ContextCompressor:
     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,
@@ -53,8 +53,7 @@ class ContextCompressor:
         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 ""
 
     def update_from_response(self, usage: Dict[str, Any]):
         """Update tracked token usage from API response."""
@@ -120,84 +119,30 @@ TURNS TO SUMMARIZE:
 
 Write only the summary, starting with "[CONTEXT SUMMARY]:" prefix."""
 
-        # 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}")
-
-        # 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}")
-
-        # 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
-
-    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.
+        # Use the centralized LLM router — handles provider resolution,
+        # auth, and fallback internally.
         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
-
-        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
+            call_kwargs = {
+                "task": "compression",
+                "messages": [{"role": "user", "content": prompt}],
+                "temperature": 0.3,
+                "max_tokens": self.summary_target_tokens * 2,
+                "timeout": 30.0,
+            }
+            if self.summary_model:
+                call_kwargs["model"] = self.summary_model
+            response = call_llm(**call_kwargs)
+            summary = response.choices[0].message.content.strip()
+            if not summary.startswith("[CONTEXT SUMMARY]:"):
+                summary = "[CONTEXT SUMMARY]: " + summary
+            return 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
 
     # ------------------------------------------------------------------
     # Tool-call / tool-result pair integrity helpers

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 +15,63 @@ import time
 _RED = "\033[31m"
 _RESET = "\033[0m"
 
+logger = logging.getLogger(__name__)
+
+
+# =========================================================================
+# 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 "┊"
+
 
 # =========================================================================
 # Tool preview (one-line summary of a tool call's primary argument)
 # =========================================================================
 
+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 = 40) -> str:
     """Build a short preview of a tool call's primary argument for display."""
+    if not args:
+        return None
     primary_args = {
         "terminal": "command", "web_search": "query", "web_extract": "urls",
         "read_file": "path", "write_file": "path", "patch": "path",
@@ -44,7 +94,7 @@ 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 +110,24 @@ 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}\""
@@ -111,7 +161,7 @@ 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:
@@ -163,6 +213,7 @@ class KawaiiSpinner:
         self.frame_idx = 0
         self.start_time = None
         self.last_line_len = 0
+        self._last_flush_time = 0.0  # Rate-limit flushes for patch_stdout compat
         # Capture stdout NOW, before any redirect_stdout(devnull) from
         # child agents can replace sys.stdout with a black hole.
         self._out = sys.stdout
@@ -177,15 +228,34 @@ class KawaiiSpinner:
             pass
 
     def _animate(self):
+        # 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)
+            # Rate-limit flush() calls to avoid spinner spam under
+            # prompt_toolkit's patch_stdout.  Each flush() pushes a queue
+            # item that may trigger a separate run_in_terminal() call; if
+            # items are processed one-at-a-time the \r overwrite is lost
+            # and every frame appears on its own line.  By flushing at
+            # most every 0.4s we guarantee multiple \r-frames are batched
+            # into a single write, so the terminal collapses them correctly.
+            now = time.time()
+            should_flush = (now - self._last_flush_time) >= 0.4
+            self._write(f"\r{line}{' ' * pad}", end='', flush=should_flush)
+            if should_flush:
+                self._last_flush_time = now
             self.last_line_len = len(line)
             self.frame_idx += 1
             time.sleep(0.12)
@@ -300,7 +370,7 @@ 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 +380,7 @@ 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()
@@ -332,6 +402,7 @@ 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)
@@ -342,7 +413,9 @@ def get_cute_tool_message(
         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}"
@@ -467,3 +540,46 @@ 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()

agent/model_metadata.py

@@ -41,6 +41,15 @@ DEFAULT_CONTEXT_LENGTHS = {
     "anthropic/claude-sonnet-4": 200000,
     "anthropic/claude-sonnet-4-20250514": 200000,
     "anthropic/claude-haiku-4.5": 200000,
+    # Bare Anthropic model IDs (for native API provider)
+    "claude-opus-4-6": 200000,
+    "claude-sonnet-4-6": 200000,
+    "claude-opus-4-5-20251101": 200000,
+    "claude-sonnet-4-5-20250929": 200000,
+    "claude-opus-4-1-20250805": 200000,
+    "claude-opus-4-20250514": 200000,
+    "claude-sonnet-4-20250514": 200000,
+    "claude-haiku-4-5-20251001": 200000,
     "openai/gpt-4o": 128000,
     "openai/gpt-4-turbo": 128000,
     "openai/gpt-4o-mini": 128000,
@@ -53,8 +62,10 @@ DEFAULT_CONTEXT_LENGTHS = {
     "glm-5": 202752,
     "glm-4.5": 131072,
     "glm-4.5-flash": 131072,
+    "kimi-for-coding": 262144,
     "kimi-k2.5": 262144,
     "kimi-k2-thinking": 262144,
+    "kimi-k2-thinking-turbo": 262144,
     "kimi-k2-turbo-preview": 262144,
     "kimi-k2-0905-preview": 131072,
     "MiniMax-M2.5": 204800,

agent/prompt_builder.py

@@ -131,6 +131,14 @@ 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."
+    ),
     "cli": (
         "You are a CLI AI Agent. Try not to use markdown but simple text "
         "renderable inside a terminal."
@@ -146,40 +154,85 @@ CONTEXT_TRUNCATE_TAIL_RATIO = 0.2
 # 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)
+
+        if not skill_matches_platform(frontmatter):
+            return False, {}, ""
+
+        desc = ""
+        raw_desc = frontmatter.get("description", "")
+        if raw_desc:
+            desc = str(raw_desc).strip().strip("'\"")
+            if len(desc) > 60:
+                desc = desc[:57] + "..."
+
+        return True, frontmatter, desc
     except Exception:
-        return True  # Err on the side of showing the skill
+        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:
+        from tools.skills_tool import _parse_frontmatter
+        raw = skill_file.read_text(encoding="utf-8")[:2000]
+        frontmatter, _ = _parse_frontmatter(raw)
+        hermes = frontmatter.get("metadata", {}).get("hermes", {})
+        return {
+            "fallback_for_toolsets": hermes.get("fallback_for_toolsets", []),
+            "requires_toolsets": hermes.get("requires_toolsets", []),
+            "fallback_for_tools": hermes.get("fallback_for_tools", []),
+            "requires_tools": hermes.get("requires_tools", []),
+        }
+    except Exception:
+        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.
@@ -193,14 +246,18 @@ def build_skills_system_prompt() -> str:
     if not skills_dir.exists():
         return ""
 
-    # Collect skills with descriptions, grouped by category
+    # 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"
+    # -> category "mlops/training", skill "axolotl"
     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):
+        is_compatible, _, desc = _parse_skill_file(skill_file)
+        if not is_compatible:
+            continue
+        # Skip skills whose conditional activation rules exclude them
+        conditions = _read_skill_conditions(skill_file)
+        if not _skill_should_show(conditions, available_tools, available_toolsets):
             continue
         rel_path = skill_file.relative_to(skills_dir)
         parts = rel_path.parts
@@ -215,7 +272,6 @@ def build_skills_system_prompt() -> str:
         else:
             category = "general"
             skill_name = skill_file.parent.name
-        desc = _read_skill_description(skill_file)
         skills_by_category.setdefault(category, []).append((skill_name, desc))
 
     if not skills_by_category:

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__)
 
@@ -48,7 +47,7 @@ _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 +59,8 @@ _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,})",
 )

agent/skill_commands.py

@@ -4,6 +4,7 @@ Shared between CLI (cli.py) and gateway (gateway/run.py) so both surfaces
 can invoke skills via /skill-name commands.
 """
 
+import json
 import logging
 from pathlib import Path
 from typing import Any, Dict, Optional
@@ -63,7 +64,11 @@ 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,
+) -> Optional[str]:
     """Build the user message content for a skill slash command invocation.
 
     Args:
@@ -78,36 +83,74 @@ 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"]
+    skill_path = skill_info["skill_dir"]
 
     try:
-        content = skill_md_path.read_text(encoding='utf-8')
+        from tools.skills_tool import SKILLS_DIR, skill_view
+
+        loaded_skill = json.loads(skill_view(skill_path, task_id=task_id))
     except Exception:
         return f"[Failed to load skill: {skill_name}]"
 
+    if not loaded_skill.get("success"):
+        return f"[Failed to load skill: {skill_name}]"
+
+    content = str(loaded_skill.get("content") or "")
+    skill_dir = Path(skill_info["skill_dir"])
+
     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(),
     ]
 
+    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 = []
-    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)
+    linked_files = loaded_skill.get("linked_files") or {}
+    for entries in linked_files.values():
+        if isinstance(entries, list):
+            supporting.extend(entries)
+
+    if not 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)
 
     if supporting:
+        skill_view_target = str(Path(skill_path).relative_to(SKILLS_DIR))
         parts.append("")
         parts.append("[This skill has supporting files you can load with the skill_view tool:]")
         for sf in supporting:
             parts.append(f"- {sf}")
-        parts.append(f'\nTo view any of these, use: skill_view(name="{skill_name}", file="<path>")')
+        parts.append(
+            f'\nTo view any of these, use: skill_view(name="{skill_view_target}", file_path="<path>")'
+        )
 
     if user_instruction:
         parts.append("")

batch_runner.py

@@ -606,7 +606,7 @@ 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 +826,7 @@ 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 +888,7 @@ 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 +1057,7 @@ 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 +1084,7 @@ 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 +1101,8 @@ 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 +1238,7 @@ 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

@@ -11,6 +11,7 @@ model:
   
   # Inference provider selection:
   #   "auto"       - Use Nous Portal if logged in, otherwise OpenRouter/env vars (default)
+  #   "nous-api"   - Use Nous Portal via API key (requires: NOUS_API_KEY)
   #   "openrouter" - Always use OpenRouter API key from OPENROUTER_API_KEY
   #   "nous"       - Always use Nous Portal (requires: hermes login)
   #   "zai"        - Use z.ai / ZhipuAI GLM models (requires: GLM_API_KEY)
@@ -402,11 +403,13 @@ 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 +417,8 @@ 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)
@@ -621,6 +626,10 @@ 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 +660,63 @@ display:
   # Toggle at runtime with /verbose in the CLI
   tool_progress: all
 
+  # 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
+
+  # ───────────────────────────────────────────────────────────────────────────
+  # 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

cron/jobs.py

@@ -26,16 +26,35 @@ except ImportError:
 # Configuration
 # =============================================================================
 
-HERMES_DIR = Path.home() / ".hermes"
+HERMES_DIR = Path(os.getenv("HERMES_HOME", Path.home() / ".hermes"))
 CRON_DIR = HERMES_DIR / "cron"
 JOBS_FILE = CRON_DIR / "jobs.json"
 OUTPUT_DIR = CRON_DIR / "output"
 
 
+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)
 
 
 # =============================================================================
@@ -149,16 +168,22 @@ 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 compute_next_run(schedule: Dict[str, Any], last_run_at: Optional[str] = None) -> Optional[str]:
@@ -223,6 +248,7 @@ 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)
@@ -400,11 +426,13 @@ 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)
+    _secure_file(output_file)
     
     return output_file

cron/scheduler.py

@@ -45,7 +45,7 @@ _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
@@ -69,6 +69,8 @@ def _deliver_result(job: dict, content: str) -> None:
     if deliver == "local":
         return
 
+    thread_id = None
+
     # Resolve target platform + chat_id
     if deliver == "origin":
         if not origin:
@@ -76,6 +78,7 @@ def _deliver_result(job: dict, content: str) -> None:
             return
         platform_name = origin["platform"]
         chat_id = origin["chat_id"]
+        thread_id = origin.get("thread_id")
     elif ":" in deliver:
         platform_name, chat_id = deliver.split(":", 1)
     else:
@@ -83,6 +86,7 @@ def _deliver_result(job: dict, content: str) -> None:
         platform_name = deliver
         if origin and origin.get("platform") == platform_name:
             chat_id = origin["chat_id"]
+            thread_id = origin.get("thread_id")
         else:
             # Fall back to home channel
             chat_id = os.getenv(f"{platform_name.upper()}_HOME_CHANNEL", "")
@@ -99,6 +103,7 @@ def _deliver_result(job: dict, content: str) -> None:
         "slack": Platform.SLACK,
         "whatsapp": Platform.WHATSAPP,
         "signal": Platform.SIGNAL,
+        "email": Platform.EMAIL,
     }
     platform = platform_map.get(platform_name.lower())
     if not platform:
@@ -118,13 +123,13 @@ def _deliver_result(job: dict, content: str) -> None:
 
     # Run the async send in a fresh event loop (safe from any thread)
     try:
-        result = asyncio.run(_send_to_platform(platform, pconfig, chat_id, content))
+        result = asyncio.run(_send_to_platform(platform, pconfig, chat_id, content, thread_id=thread_id))
     except RuntimeError:
         # asyncio.run() fails if there's already a running loop in this thread;
         # spin up a new thread to avoid that.
         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, 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)
@@ -137,9 +142,9 @@ def _deliver_result(job: dict, content: str) -> None:
         # 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
+            mirror_to_session(platform_name, chat_id, content, source_label="cron", thread_id=thread_id)
+        except Exception as e:
+            logger.warning("Job '%s': mirror_to_session failed: %s", job["id"], e)
 
 
 def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:
@@ -175,7 +180,7 @@ 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"
+        model = os.getenv("HERMES_MODEL") or "anthropic/claude-opus-4.6"
 
         # Load config.yaml for model, reasoning, prefill, toolsets, provider routing
         _cfg = {}
@@ -190,8 +195,8 @@ def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:
                     model = _model_cfg
                 elif isinstance(_model_cfg, dict):
                     model = _model_cfg.get("default", model)
-        except Exception:
-            pass
+        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
@@ -219,7 +224,8 @@ 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

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/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/__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

@@ -249,23 +249,62 @@ 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 +317,13 @@ 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:
@@ -390,10 +434,11 @@ 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 = {
@@ -192,7 +209,7 @@ class TerminalBench2EvalEnv(HermesAgentBaseEnv):
 
             # Agent settings -- TB2 tasks are complex, need many turns
             max_agent_turns=60,
-            max_token_length=16000,
+            max_token_length=***
             agent_temperature=0.6,
             system_prompt=None,
 
@@ -216,7 +233,7 @@ class TerminalBench2EvalEnv(HermesAgentBaseEnv):
             steps_per_eval=1,
             total_steps=1,
 
-            tokenizer_name="NousResearch/Hermes-3-Llama-3.1-8B",
+            tokenizer_name="NousRe...1-8B",
             use_wandb=True,
             wandb_name="terminal-bench-2",
             ensure_scores_are_not_same=False,  # Binary rewards may all be 0 or 1
@@ -228,7 +245,7 @@ class TerminalBench2EvalEnv(HermesAgentBaseEnv):
                 base_url="https://openrouter.ai/api/v1",
                 model_name="anthropic/claude-sonnet-4",
                 server_type="openai",
-                api_key=os.getenv("OPENROUTER_API_KEY", ""),
+                api_key=os.get...EY", ""),
                 health_check=False,
             )
         ]
@@ -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
@@ -470,435 +513,3 @@ class TerminalBench2EvalEnv(HermesAgentBaseEnv):
                 reward = 0.0
             else:
                 # Run tests in a thread so the blocking ctx.terminal() calls
-                # don't freeze the entire event loop (which would stall all
-                # other tasks, tqdm updates, and timeout timers).
-                ctx = ToolContext(task_id)
-                try:
-                    loop = asyncio.get_event_loop()
-                    reward = await loop.run_in_executor(
-                        None,  # default thread pool
-                        self._run_tests, eval_item, ctx, task_name,
-                    )
-                except Exception as e:
-                    logger.error("Task %s: test verification failed: %s", task_name, e)
-                    reward = 0.0
-                finally:
-                    ctx.cleanup()
-
-            passed = reward == 1.0
-            status = "PASS" if passed else "FAIL"
-            elapsed = time.time() - task_start
-            tqdm.write(f"  [{status}] {task_name} (turns={result.turns_used}, {elapsed:.0f}s)")
-            logger.info(
-                "Task %s: reward=%.1f, turns=%d, finished=%s",
-                task_name, reward, result.turns_used, result.finished_naturally,
-            )
-
-            out = {
-                "passed": passed,
-                "reward": reward,
-                "task_name": task_name,
-                "category": category,
-                "turns_used": result.turns_used,
-                "finished_naturally": result.finished_naturally,
-                "messages": result.messages,
-            }
-            self._save_result(out)
-            return out
-
-        except Exception as e:
-            elapsed = time.time() - task_start
-            logger.error("Task %s: rollout failed: %s", task_name, e, exc_info=True)
-            tqdm.write(f"  [ERROR] {task_name}: {e} ({elapsed:.0f}s)")
-            out = {
-                "passed": False, "reward": 0.0,
-                "task_name": task_name, "category": category,
-                "error": str(e),
-            }
-            self._save_result(out)
-            return out
-
-        finally:
-            # --- Cleanup: clear overrides, sandbox, and temp files ---
-            clear_task_env_overrides(task_id)
-            try:
-                cleanup_vm(task_id)
-            except Exception as e:
-                logger.debug("VM cleanup for %s: %s", task_id[:8], e)
-            if task_dir and task_dir.exists():
-                shutil.rmtree(task_dir, ignore_errors=True)
-
-    def _run_tests(
-        self, item: Dict[str, Any], ctx: ToolContext, task_name: str
-    ) -> float:
-        """
-        Upload and execute the test suite in the agent's sandbox, then
-        download the verifier output locally to read the reward.
-
-        Follows Harbor's verification pattern:
-        1. Upload tests/ directory into the sandbox
-        2. Execute test.sh inside the sandbox
-        3. Download /logs/verifier/ directory to a local temp dir
-        4. Read reward.txt locally with native Python I/O
-
-        Downloading locally avoids issues with the file_read tool on
-        the Modal VM and matches how Harbor handles verification.
-
-        TB2 test scripts (test.sh) typically:
-        1. Install pytest via uv/pip
-        2. Run pytest against the test files in /tests/
-        3. Write results to /logs/verifier/reward.txt
-
-        Args:
-            item: The TB2 task dict (contains tests_tar, test_sh)
-            ctx: ToolContext scoped to this task's sandbox
-            task_name: For logging
-
-        Returns:
-            1.0 if tests pass, 0.0 otherwise
-        """
-        tests_tar = item.get("tests_tar", "")
-        test_sh = item.get("test_sh", "")
-
-        if not test_sh:
-            logger.warning("Task %s: no test_sh content, reward=0", task_name)
-            return 0.0
-
-        # Create required directories in the sandbox
-        ctx.terminal("mkdir -p /tests /logs/verifier")
-
-        # Upload test files into the sandbox (binary-safe via base64)
-        if tests_tar:
-            tests_temp = Path(tempfile.mkdtemp(prefix=f"tb2-tests-{task_name}-"))
-            try:
-                _extract_base64_tar(tests_tar, tests_temp)
-                ctx.upload_dir(str(tests_temp), "/tests")
-            except Exception as e:
-                logger.warning("Task %s: failed to upload test files: %s", task_name, e)
-            finally:
-                shutil.rmtree(tests_temp, ignore_errors=True)
-
-        # Write the test runner script (test.sh)
-        ctx.write_file("/tests/test.sh", test_sh)
-        ctx.terminal("chmod +x /tests/test.sh")
-
-        # Execute the test suite
-        logger.info(
-            "Task %s: running test suite (timeout=%ds)",
-            task_name, self.config.test_timeout,
-        )
-        test_result = ctx.terminal(
-            "bash /tests/test.sh",
-            timeout=self.config.test_timeout,
-        )
-
-        exit_code = test_result.get("exit_code", -1)
-        output = test_result.get("output", "")
-
-        # Download the verifier output directory locally, then read reward.txt
-        # with native Python I/O. This avoids issues with file_read on the
-        # Modal VM and matches Harbor's verification pattern.
-        reward = 0.0
-        local_verifier_dir = Path(tempfile.mkdtemp(prefix=f"tb2-verifier-{task_name}-"))
-        try:
-            ctx.download_dir("/logs/verifier", str(local_verifier_dir))
-
-            reward_file = local_verifier_dir / "reward.txt"
-            if reward_file.exists() and reward_file.stat().st_size > 0:
-                content = reward_file.read_text().strip()
-                if content == "1":
-                    reward = 1.0
-                elif content == "0":
-                    reward = 0.0
-                else:
-                    # Unexpected content -- try parsing as float
-                    try:
-                        reward = float(content)
-                    except (ValueError, TypeError):
-                        logger.warning(
-                            "Task %s: reward.txt content unexpected (%r), "
-                            "falling back to exit_code=%d",
-                            task_name, content, exit_code,
-                        )
-                        reward = 1.0 if exit_code == 0 else 0.0
-            else:
-                # reward.txt not written -- fall back to exit code
-                logger.warning(
-                    "Task %s: reward.txt not found after download, "
-                    "falling back to exit_code=%d",
-                    task_name, exit_code,
-                )
-                reward = 1.0 if exit_code == 0 else 0.0
-        except Exception as e:
-            logger.warning(
-                "Task %s: failed to download verifier dir: %s, "
-                "falling back to exit_code=%d",
-                task_name, e, exit_code,
-            )
-            reward = 1.0 if exit_code == 0 else 0.0
-        finally:
-            shutil.rmtree(local_verifier_dir, ignore_errors=True)
-
-        # Log test output for debugging failures
-        if reward == 0.0:
-            output_preview = output[-500:] if output else "(no output)"
-            logger.info(
-                "Task %s: FAIL (exit_code=%d)\n%s",
-                task_name, exit_code, output_preview,
-            )
-
-        return reward
-
-    # =========================================================================
-    # Evaluate -- main entry point for the eval subcommand
-    # =========================================================================
-
-    async def _eval_with_timeout(self, item: Dict[str, Any]) -> Dict:
-        """
-        Wrap rollout_and_score_eval with a per-task wall-clock timeout.
-
-        If the task exceeds task_timeout seconds, it's automatically scored
-        as FAIL. This prevents any single task from hanging indefinitely.
-        """
-        task_name = item.get("task_name", "unknown")
-        category = item.get("category", "unknown")
-        try:
-            return await asyncio.wait_for(
-                self.rollout_and_score_eval(item),
-                timeout=self.config.task_timeout,
-            )
-        except asyncio.TimeoutError:
-            from tqdm import tqdm
-            elapsed = self.config.task_timeout
-            tqdm.write(f"  [TIMEOUT] {task_name} (exceeded {elapsed}s wall-clock limit)")
-            logger.error("Task %s: wall-clock timeout after %ds", task_name, elapsed)
-            out = {
-                "passed": False, "reward": 0.0,
-                "task_name": task_name, "category": category,
-                "error": f"timeout ({elapsed}s)",
-            }
-            self._save_result(out)
-            return out
-
-    async def evaluate(self, *args, **kwargs) -> None:
-        """
-        Run Terminal-Bench 2.0 evaluation over all tasks.
-
-        This is the main entry point when invoked via:
-            python environments/terminalbench2_env.py evaluate
-
-        Runs all tasks through rollout_and_score_eval() via asyncio.gather()
-        (same pattern as GPQA and other Atropos eval envs). Each task is
-        wrapped with a wall-clock timeout so hung tasks auto-fail.
-
-        Suppresses noisy Modal/terminal output (HERMES_QUIET) so the tqdm
-        bar stays visible.
-        """
-        start_time = time.time()
-
-        # Route all logging through tqdm.write() so the progress bar stays
-        # pinned at the bottom while log lines scroll above it.
-        from tqdm import tqdm
-
-        class _TqdmHandler(logging.Handler):
-            def emit(self, record):
-                try:
-                    tqdm.write(self.format(record))
-                except Exception:
-                    self.handleError(record)
-
-        handler = _TqdmHandler()
-        handler.setFormatter(logging.Formatter(
-            "%(asctime)s [%(name)s] %(levelname)s: %(message)s",
-            datefmt="%H:%M:%S",
-        ))
-        root = logging.getLogger()
-        root.handlers = [handler]  # Replace any existing handlers
-        root.setLevel(logging.INFO)
-
-        # Silence noisy third-party loggers that flood the output
-        logging.getLogger("httpx").setLevel(logging.WARNING)      # Every HTTP request
-        logging.getLogger("openai").setLevel(logging.WARNING)     # OpenAI client retries
-        logging.getLogger("rex-deploy").setLevel(logging.WARNING) # Swerex deployment
-        logging.getLogger("rex_image_builder").setLevel(logging.WARNING)  # Image builds
-
-        print(f"\n{'='*60}")
-        print("Starting Terminal-Bench 2.0 Evaluation")
-        print(f"{'='*60}")
-        print(f"  Dataset: {self.config.dataset_name}")
-        print(f"  Total tasks: {len(self.all_eval_items)}")
-        print(f"  Max agent turns: {self.config.max_agent_turns}")
-        print(f"  Task timeout: {self.config.task_timeout}s")
-        print(f"  Terminal backend: {self.config.terminal_backend}")
-        print(f"  Tool thread pool: {self.config.tool_pool_size}")
-        print(f"  Terminal timeout: {self.config.terminal_timeout}s/cmd")
-        print(f"  Terminal lifetime: {self.config.terminal_lifetime}s (auto: task_timeout + 120)")
-        print(f"{'='*60}\n")
-
-        # 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))
-            for item in self.all_eval_items
-        ]
-
-        results = []
-        passed_count = 0
-        pbar = tqdm(total=total_tasks, desc="Evaluating TB2", dynamic_ncols=True)
-        try:
-            for coro in asyncio.as_completed(eval_tasks):
-                result = await coro
-                results.append(result)
-                if result and result.get("passed"):
-                    passed_count += 1
-                done = len(results)
-                pct = (passed_count / done * 100) if done else 0
-                pbar.set_postfix_str(f"pass={passed_count}/{done} ({pct:.1f}%)")
-                pbar.update(1)
-        except (KeyboardInterrupt, asyncio.CancelledError):
-            pbar.close()
-            print(f"\n\nInterrupted! Cleaning up {len(eval_tasks)} tasks...")
-            # Cancel all pending tasks
-            for task in eval_tasks:
-                task.cancel()
-            # Let cancellations propagate (finally blocks run cleanup_vm)
-            await asyncio.gather(*eval_tasks, return_exceptions=True)
-            # Belt-and-suspenders: clean up any remaining sandboxes
-            from tools.terminal_tool import cleanup_all_environments
-            cleanup_all_environments()
-            print("All sandboxes cleaned up.")
-            return
-        finally:
-            pbar.close()
-
-        end_time = time.time()
-
-        # Filter out None results (shouldn't happen, but be safe)
-        valid_results = [r for r in results if r is not None]
-
-        if not valid_results:
-            print("Warning: No valid evaluation results obtained")
-            return
-
-        # ---- Compute metrics ----
-        total = len(valid_results)
-        passed = sum(1 for r in valid_results if r.get("passed"))
-        overall_pass_rate = passed / total if total > 0 else 0.0
-
-        # Per-category breakdown
-        cat_results: Dict[str, List[Dict]] = defaultdict(list)
-        for r in valid_results:
-            cat_results[r.get("category", "unknown")].append(r)
-
-        # Build metrics dict
-        eval_metrics = {
-            "eval/pass_rate": overall_pass_rate,
-            "eval/total_tasks": total,
-            "eval/passed_tasks": passed,
-            "eval/evaluation_time_seconds": end_time - start_time,
-        }
-
-        # Per-category metrics
-        for category, cat_items in sorted(cat_results.items()):
-            cat_passed = sum(1 for r in cat_items if r.get("passed"))
-            cat_total = len(cat_items)
-            cat_pass_rate = cat_passed / cat_total if cat_total > 0 else 0.0
-            cat_key = category.replace(" ", "_").replace("-", "_").lower()
-            eval_metrics[f"eval/pass_rate_{cat_key}"] = cat_pass_rate
-
-        # Store metrics for wandb_log
-        self.eval_metrics = [(k, v) for k, v in eval_metrics.items()]
-
-        # ---- Print summary ----
-        print(f"\n{'='*60}")
-        print("Terminal-Bench 2.0 Evaluation Results")
-        print(f"{'='*60}")
-        print(f"Overall Pass Rate: {overall_pass_rate:.4f} ({passed}/{total})")
-        print(f"Evaluation Time: {end_time - start_time:.1f} seconds")
-
-        print("\nCategory Breakdown:")
-        for category, cat_items in sorted(cat_results.items()):
-            cat_passed = sum(1 for r in cat_items if r.get("passed"))
-            cat_total = len(cat_items)
-            cat_rate = cat_passed / cat_total if cat_total > 0 else 0.0
-            print(f"  {category}: {cat_rate:.1%} ({cat_passed}/{cat_total})")
-
-        # Print individual task results
-        print("\nTask Results:")
-        for r in sorted(valid_results, key=lambda x: x.get("task_name", "")):
-            status = "PASS" if r.get("passed") else "FAIL"
-            turns = r.get("turns_used", "?")
-            error = r.get("error", "")
-            extra = f" (error: {error})" if error else ""
-            print(f"  [{status}] {r['task_name']} (turns={turns}){extra}")
-
-        print(f"{'='*60}\n")
-
-        # Build sample records for evaluate_log (includes full conversations)
-        samples = [
-            {
-                "task_name": r.get("task_name"),
-                "category": r.get("category"),
-                "passed": r.get("passed"),
-                "reward": r.get("reward"),
-                "turns_used": r.get("turns_used"),
-                "error": r.get("error"),
-                "messages": r.get("messages"),
-            }
-            for r in valid_results
-        ]
-
-        # Log evaluation results
-        try:
-            await self.evaluate_log(
-                metrics=eval_metrics,
-                samples=samples,
-                start_time=start_time,
-                end_time=end_time,
-                generation_parameters={
-                    "temperature": self.config.agent_temperature,
-                    "max_tokens": self.config.max_token_length,
-                    "max_agent_turns": self.config.max_agent_turns,
-                    "terminal_backend": self.config.terminal_backend,
-                },
-            )
-        except Exception as e:
-            print(f"Error logging evaluation results: {e}")
-
-        # Close streaming file
-        if hasattr(self, "_streaming_file") and not self._streaming_file.closed:
-            self._streaming_file.close()
-            print(f"  Live results saved to: {self._streaming_path}")
-
-        # Kill all remaining sandboxes. Timed-out tasks leave orphaned thread
-        # pool workers still executing commands -- cleanup_all stops them.
-        from tools.terminal_tool import cleanup_all_environments
-        print("\nCleaning up all sandboxes...")
-        cleanup_all_environments()
-
-        # Shut down the tool thread pool so orphaned workers from timed-out
-        # tasks are killed immediately instead of retrying against dead
-        # sandboxes and spamming the console with TimeoutError warnings.
-        from environments.agent_loop import _tool_executor
-        _tool_executor.shutdown(wait=False, cancel_futures=True)
-        print("Done.")
-
-    # =========================================================================
-    # Wandb logging
-    # =========================================================================
-
-    async def wandb_log(self, wandb_metrics: Optional[Dict] = None):
-        """Log TB2-specific metrics to wandb."""
-        if wandb_metrics is None:
-            wandb_metrics = {}
-
-        # Add stored eval metrics
-        for metric_name, metric_value in self.eval_metrics:
-            wandb_metrics[metric_name] = metric_value
-        self.eval_metrics = []
-
-        await super().wandb_log(wandb_metrics)
-
-
-if __name__ == "__main__":
-    TerminalBench2EvalEnv.cli()

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

@@ -114,11 +114,27 @@ def _patch_swerex_modal():
         self._worker = _AsyncWorker()
         self._worker.start()
 
+        # Pre-build a modal.Image with pip fix for Modal's legacy image builder.
+        # Modal requires `python -m pip` to work during image build, but some
+        # task images (e.g., TBLite's broken-python) have intentionally broken pip.
+        # Fix: remove stale pip dist-info and reinstall via ensurepip before Modal
+        # tries to use it. This is a no-op for images where pip already works.
+        import modal as _modal
+        image_spec = self.config.image
+        if isinstance(image_spec, str):
+            image_spec = _modal.Image.from_registry(
+                image_spec,
+                setup_dockerfile_commands=[
+                    "RUN rm -rf /usr/local/lib/python*/site-packages/pip* 2>/dev/null; "
+                    "python -m ensurepip --upgrade --default-pip 2>/dev/null || true",
+                ],
+            )
+
         # 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,
+                image=image_spec,
                 startup_timeout=self.config.startup_timeout,
                 runtime_timeout=self.config.runtime_timeout,
                 deployment_timeout=self.config.deployment_timeout,

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,

gateway/channel_directory.py

@@ -17,6 +17,26 @@ logger = logging.getLogger(__name__)
 DIRECTORY_PATH = Path.home() / ".hermes" / "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}"
+
+
 # ---------------------------------------------------------------------------
 # Build / refresh
 # ---------------------------------------------------------------------------
@@ -41,7 +61,7 @@ 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"):
         if plat_name not in platforms:
             platforms[plat_name] = _build_from_sessions(plat_name)
 
@@ -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

@@ -28,6 +28,7 @@ class Platform(Enum):
     SLACK = "slack"
     SIGNAL = "signal"
     HOMEASSISTANT = "homeassistant"
+    EMAIL = "email"
 
 
 @dataclass
@@ -167,6 +168,9 @@ 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)
         return connected
     
     def get_home_channel(self, platform: Platform) -> Optional[HomeChannel]:
@@ -270,7 +274,7 @@ def load_gateway_config() -> GatewayConfig:
     gateway_config_path = Path.home() / ".hermes" / "gateway.json"
     if gateway_config_path.exists():
         try:
-            with open(gateway_config_path, "r") as f:
+            with open(gateway_config_path, "r", encoding="utf-8") as f:
                 data = json.load(f)
                 config = GatewayConfig.from_dict(data)
         except Exception as e:
@@ -283,11 +287,23 @@ def load_gateway_config() -> GatewayConfig:
         import yaml
         config_yaml_path = Path.home() / ".hermes" / "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 {}
             sr = yaml_cfg.get("session_reset")
             if sr and isinstance(sr, dict):
                 config.default_reset_policy = SessionResetPolicy.from_dict(sr)
+
+            # Bridge discord settings from config.yaml to env vars
+            # (env vars take precedence — only set if not already defined)
+            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)
     except Exception:
         pass
 
@@ -420,6 +436,28 @@ 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:
+            config.platforms[Platform.EMAIL].home_channel = HomeChannel(
+                platform=Platform.EMAIL,
+                chat_id=email_home,
+                name=os.getenv("EMAIL_HOME_ADDRESS_NAME", "Home"),
+            )
+
     # Session settings
     idle_minutes = os.getenv("SESSION_IDLE_MINUTES")
     if idle_minutes:
@@ -441,5 +479,5 @@ def save_gateway_config(config: GatewayConfig) -> None:
     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:
+    with open(gateway_config_path, "w", encoding="utf-8") as f:
         json.dump(config.to_dict(), f, indent=2)

gateway/delivery.py

@@ -37,6 +37,7 @@ 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 +59,7 @@ class DeliveryTarget:
                 return cls(
                     platform=origin.platform,
                     chat_id=origin.chat_id,
+                    thread_id=origin.thread_id,
                     is_origin=True,
                 )
             else:
@@ -150,7 +152,7 @@ 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)
@@ -285,7 +287,10 @@ 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(

gateway/mirror.py

@@ -26,6 +26,7 @@ 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 +38,9 @@ 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 +58,11 @@ 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 +92,9 @@ 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 +115,7 @@ 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 +126,6 @@ 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/platforms/base.py

@@ -24,7 +24,13 @@ 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
+
+
+GATEWAY_SECRET_CAPTURE_UNSUPPORTED_MESSAGE = (
+    "Secure secret entry is not supported over messaging. "
+    "Run `hermes setup` or update ~/.hermes/.env locally."
+)
 
 
 # ---------------------------------------------------------------------------
@@ -413,11 +419,12 @@ 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
     
@@ -515,6 +522,7 @@ 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.
@@ -534,6 +542,7 @@ class BasePlatformAdapter(ABC):
         video_path: str,
         caption: Optional[str] = None,
         reply_to: Optional[str] = None,
+        **kwargs,
     ) -> SendResult:
         """
         Send a video natively via the platform API.
@@ -553,6 +562,7 @@ 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 +581,7 @@ 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.
@@ -620,7 +631,7 @@ class BasePlatformAdapter(ABC):
         
         return media, cleaned
     
-    async def _keep_typing(self, chat_id: str, interval: float = 2.0) -> None:
+    async def _keep_typing(self, chat_id: str, interval: float = 2.0, metadata=None) -> None:
         """
         Continuously send typing indicator until cancelled.
         
@@ -629,7 +640,7 @@ 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
@@ -645,7 +656,7 @@ class BasePlatformAdapter(ABC):
         if not self._message_handler:
             return
         
-        session_key = event.source.chat_id
+        session_key = build_session_key(event.source)
         
         # Check if there's already an active handler for this session
         if session_key in self._active_sessions:
@@ -687,7 +698,8 @@ class BasePlatformAdapter(ABC):
         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:
             # Call the handler (this can take a while with tool calls)
@@ -711,7 +723,8 @@ class BasePlatformAdapter(ABC):
                     result = await self.send(
                         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)
@@ -721,7 +734,8 @@ class BasePlatformAdapter(ABC):
                         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
+                            reply_to=event.message_id,
+                            metadata=_thread_metadata,
                         )
                         if not fallback_result.success:
                             print(f"[{self.name}] Fallback send also failed: {fallback_result.error}")
@@ -743,12 +757,14 @@ 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)
@@ -769,21 +785,25 @@ 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:

gateway/platforms/discord.py

@@ -72,11 +72,11 @@ class DiscordAdapter(BasePlatformAdapter):
     async def connect(self) -> bool:
         """Connect to Discord and start receiving events."""
         if not DISCORD_AVAILABLE:
-            print(f"[{self.name}] discord.py not installed. Run: pip install discord.py")
+            logger.error("[%s] discord.py not installed. Run: pip install discord.py", self.name)
             return False
         
         if not self.config.token:
-            print(f"[{self.name}] No bot token configured")
+            logger.error("[%s] No bot token configured", self.name)
             return False
         
         try:
@@ -105,7 +105,7 @@ class DiscordAdapter(BasePlatformAdapter):
             # Register event handlers
             @self._client.event
             async def on_ready():
-                print(f"[{adapter_self.name}] Connected as {adapter_self._client.user}")
+                logger.info("[%s] Connected as %s", adapter_self.name, adapter_self._client.user)
                 
                 # Resolve any usernames in the allowed list to numeric IDs
                 await adapter_self._resolve_allowed_usernames()
@@ -113,16 +113,30 @@ class DiscordAdapter(BasePlatformAdapter):
                 # Sync slash commands with Discord
                 try:
                     synced = await adapter_self._client.tree.sync()
-                    print(f"[{adapter_self.name}] Synced {len(synced)} slash command(s)")
-                except Exception as e:
-                    print(f"[{adapter_self.name}] Slash command sync failed: {e}")
+                    logger.info("[%s] Synced %d slash command(s)", adapter_self.name, len(synced))
+                except Exception as e:  # pragma: no cover - defensive logging
+                    logger.warning("[%s] Slash command sync failed: %s", adapter_self.name, e, exc_info=True)
                 adapter_self._ready_event.set()
             
             @self._client.event
             async def on_message(message: DiscordMessage):
-                # Ignore bot's own messages
+                # Always ignore our own messages
                 if message.author == self._client.user:
                     return
+                
+                # Bot message filtering (DISCORD_ALLOW_BOTS):
+                #   "none"     — ignore all other bots (default)
+                #   "mentions" — accept bot messages only when they @mention us
+                #   "all"      — accept all bot messages
+                if getattr(message.author, "bot", False):
+                    allow_bots = os.getenv("DISCORD_ALLOW_BOTS", "none").lower().strip()
+                    if allow_bots == "none":
+                        return
+                    elif allow_bots == "mentions":
+                        if not self._client.user or self._client.user not in message.mentions:
+                            return
+                    # "all" falls through to handle_message
+                
                 await self._handle_message(message)
             
             # Register slash commands
@@ -138,10 +152,10 @@ class DiscordAdapter(BasePlatformAdapter):
             return True
             
         except asyncio.TimeoutError:
-            print(f"[{self.name}] Timeout waiting for connection")
+            logger.error("[%s] Timeout waiting for connection to Discord", self.name, exc_info=True)
             return False
-        except Exception as e:
-            print(f"[{self.name}] Failed to connect: {e}")
+        except Exception as e:  # pragma: no cover - defensive logging
+            logger.error("[%s] Failed to connect to Discord: %s", self.name, e, exc_info=True)
             return False
     
     async def disconnect(self) -> None:
@@ -149,13 +163,13 @@ class DiscordAdapter(BasePlatformAdapter):
         if self._client:
             try:
                 await self._client.close()
-            except Exception as e:
-                print(f"[{self.name}] Error during disconnect: {e}")
+            except Exception as e:  # pragma: no cover - defensive logging
+                logger.warning("[%s] Error during disconnect: %s", self.name, e, exc_info=True)
         
         self._running = False
         self._client = None
         self._ready_event.clear()
-        print(f"[{self.name}] Disconnected")
+        logger.info("[%s] Disconnected", self.name)
     
     async def send(
         self,
@@ -204,7 +218,8 @@ class DiscordAdapter(BasePlatformAdapter):
                 raw_response={"message_ids": message_ids}
             )
             
-        except Exception as e:
+        except Exception as e:  # pragma: no cover - defensive logging
+            logger.error("[%s] Failed to send Discord message: %s", self.name, e, exc_info=True)
             return SendResult(success=False, error=str(e))
 
     async def edit_message(
@@ -226,7 +241,8 @@ class DiscordAdapter(BasePlatformAdapter):
                 formatted = formatted[:self.MAX_MESSAGE_LENGTH - 3] + "..."
             await msg.edit(content=formatted)
             return SendResult(success=True, message_id=message_id)
-        except Exception as e:
+        except Exception as e:  # pragma: no cover - defensive logging
+            logger.error("[%s] Failed to edit Discord message %s: %s", self.name, message_id, e, exc_info=True)
             return SendResult(success=False, error=str(e))
 
     async def send_voice(
@@ -263,8 +279,8 @@ class DiscordAdapter(BasePlatformAdapter):
                 )
                 return SendResult(success=True, message_id=str(msg.id))
         
-        except Exception as e:
-            print(f"[{self.name}] Failed to send audio: {e}")
+        except Exception as e:  # pragma: no cover - defensive logging
+            logger.error("[%s] Failed to send audio, falling back to base adapter: %s", self.name, e, exc_info=True)
             return await super().send_voice(chat_id, audio_path, caption, reply_to)
     
     async def send_image_file(
@@ -300,8 +316,8 @@ class DiscordAdapter(BasePlatformAdapter):
                 )
                 return SendResult(success=True, message_id=str(msg.id))
         
-        except Exception as e:
-            print(f"[{self.name}] Failed to send local image: {e}")
+        except Exception as e:  # pragma: no cover - defensive logging
+            logger.error("[%s] Failed to send local image, falling back to base adapter: %s", self.name, e, exc_info=True)
             return await super().send_image_file(chat_id, image_path, caption, reply_to)
 
     async def send_image(
@@ -353,13 +369,22 @@ class DiscordAdapter(BasePlatformAdapter):
                     return SendResult(success=True, message_id=str(msg.id))
         
         except ImportError:
-            print(f"[{self.name}] aiohttp not installed, falling back to URL. Run: pip install aiohttp")
+            logger.warning(
+                "[%s] aiohttp not installed, falling back to URL. Run: pip install aiohttp",
+                self.name,
+                exc_info=True,
+            )
             return await super().send_image(chat_id, image_url, caption, reply_to)
-        except Exception as e:
-            print(f"[{self.name}] Failed to send image attachment, falling back to URL: {e}")
+        except Exception as e:  # pragma: no cover - defensive logging
+            logger.error(
+                "[%s] Failed to send image attachment, falling back to URL: %s",
+                self.name,
+                e,
+                exc_info=True,
+            )
             return await super().send_image(chat_id, image_url, caption, reply_to)
     
-    async def send_typing(self, chat_id: str) -> None:
+    async def send_typing(self, chat_id: str, metadata=None) -> None:
         """Send typing indicator."""
         if self._client:
             try:
@@ -404,7 +429,8 @@ class DiscordAdapter(BasePlatformAdapter):
                 "guild_id": str(channel.guild.id) if hasattr(channel, "guild") and channel.guild else None,
                 "guild_name": channel.guild.name if hasattr(channel, "guild") and channel.guild else None,
             }
-        except Exception as e:
+        except Exception as e:  # pragma: no cover - defensive logging
+            logger.error("[%s] Failed to get chat info for %s: %s", self.name, chat_id, e, exc_info=True)
             return {"name": str(chat_id), "type": "dm", "error": str(e)}
     
     async def _resolve_allowed_usernames(self) -> None:
@@ -749,6 +775,46 @@ class DiscordAdapter(BasePlatformAdapter):
         except Exception as e:
             return SendResult(success=False, error=str(e))
 
+    def _get_parent_channel_id(self, channel: Any) -> Optional[str]:
+        """Return the parent channel ID for a Discord thread-like channel, if present."""
+        parent = getattr(channel, "parent", None)
+        if parent is not None and getattr(parent, "id", None) is not None:
+            return str(parent.id)
+        parent_id = getattr(channel, "parent_id", None)
+        if parent_id is not None:
+            return str(parent_id)
+        return None
+
+    def _is_forum_parent(self, channel: Any) -> bool:
+        """Best-effort check for whether a Discord channel is a forum channel."""
+        if channel is None:
+            return False
+        forum_cls = getattr(discord, "ForumChannel", None)
+        if forum_cls and isinstance(channel, forum_cls):
+            return True
+        channel_type = getattr(channel, "type", None)
+        if channel_type is not None:
+            type_value = getattr(channel_type, "value", channel_type)
+            if type_value == 15:
+                return True
+        return False
+
+    def _format_thread_chat_name(self, thread: Any) -> str:
+        """Build a readable chat name for thread-like Discord channels, including forum context when available."""
+        thread_name = getattr(thread, "name", None) or str(getattr(thread, "id", "thread"))
+        parent = getattr(thread, "parent", None)
+        guild = getattr(thread, "guild", None) or getattr(parent, "guild", None)
+        guild_name = getattr(guild, "name", None)
+        parent_name = getattr(parent, "name", None)
+
+        if self._is_forum_parent(parent) and guild_name and parent_name:
+            return f"{guild_name} / {parent_name} / {thread_name}"
+        if parent_name and guild_name:
+            return f"{guild_name} / #{parent_name} / {thread_name}"
+        if parent_name:
+            return f"{parent_name} / {thread_name}"
+        return thread_name
+
     async def _handle_message(self, message: DiscordMessage) -> None:
         """Handle incoming Discord messages."""
         # In server channels (not DMs), require the bot to be @mentioned
@@ -759,28 +825,33 @@ class DiscordAdapter(BasePlatformAdapter):
         #       bot responds to every message without needing a mention.
         #   DISCORD_REQUIRE_MENTION: Set to "false" to disable mention requirement
         #       globally (all channels become free-response). Default: "true".
-        
+        #       Can also be set via discord.require_mention in config.yaml.
+
+        thread_id = None
+        parent_channel_id = None
+        is_thread = isinstance(message.channel, discord.Thread)
+        if is_thread:
+            thread_id = str(message.channel.id)
+            parent_channel_id = self._get_parent_channel_id(message.channel)
+
         if not isinstance(message.channel, discord.DMChannel):
-            # Check if this channel is in the free-response list
             free_channels_raw = os.getenv("DISCORD_FREE_RESPONSE_CHANNELS", "")
             free_channels = {ch.strip() for ch in free_channels_raw.split(",") if ch.strip()}
-            channel_id = str(message.channel.id)
-            
-            # Global override: if DISCORD_REQUIRE_MENTION=false, all channels are free
+            channel_ids = {str(message.channel.id)}
+            if parent_channel_id:
+                channel_ids.add(parent_channel_id)
+
             require_mention = os.getenv("DISCORD_REQUIRE_MENTION", "true").lower() not in ("false", "0", "no")
-            
-            is_free_channel = channel_id in free_channels
-            
+            is_free_channel = bool(channel_ids & free_channels)
+
             if require_mention and not is_free_channel:
-                # Must be @mentioned to respond
                 if self._client.user not in message.mentions:
-                    return  # Silently ignore messages that don't mention the bot
-            
-            # Strip the bot mention from the message text so the agent sees clean input
+                    return
+
             if self._client.user and self._client.user in message.mentions:
                 message.content = message.content.replace(f"<@{self._client.user.id}>", "").strip()
                 message.content = message.content.replace(f"<@!{self._client.user.id}>", "").strip()
-        
+
         # Determine message type
         msg_type = MessageType.TEXT
         if message.content.startswith("/"):
@@ -803,20 +874,15 @@ class DiscordAdapter(BasePlatformAdapter):
         if isinstance(message.channel, discord.DMChannel):
             chat_type = "dm"
             chat_name = message.author.name
-        elif isinstance(message.channel, discord.Thread):
+        elif is_thread:
             chat_type = "thread"
-            chat_name = message.channel.name
+            chat_name = self._format_thread_chat_name(message.channel)
         else:
-            chat_type = "group"  # Treat server channels as groups
+            chat_type = "group"
             chat_name = getattr(message.channel, "name", str(message.channel.id))
             if hasattr(message.channel, "guild") and message.channel.guild:
                 chat_name = f"{message.channel.guild.name} / #{chat_name}"
-        
-        # Get thread ID if in a thread
-        thread_id = None
-        if isinstance(message.channel, discord.Thread):
-            thread_id = str(message.channel.id)
-        
+
         # Get channel topic (if available - TextChannels have topics, DMs/threads don't)
         chat_topic = getattr(message.channel, "topic", None)
         

gateway/platforms/email.py

@@ -0,0 +1,533 @@
+"""
+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 uuid
+from datetime import datetime
+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__)
+
+# 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 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) -> List[Dict[str, Any]]:
+    """Extract attachment metadata and cache files locally."""
+    attachments = []
+    if not msg.is_multipart():
+        return attachments
+
+    for part in msg.walk():
+        disposition = str(part.get("Content-Disposition", ""))
+        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"))
+
+        # Track message IDs we've already processed to avoid duplicates
+        self._seen_uids: set = set()
+        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)
+
+    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)
+            imap.login(self._address, self._password)
+            # Mark all existing messages as seen so we only process new ones
+            imap.select("INBOX")
+            status, data = imap.search(None, "ALL")
+            if status == "OK" and data[0]:
+                for uid in data[0].split():
+                    self._seen_uids.add(uid)
+            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)
+            smtp.starttls()
+            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)
+            imap.login(self._address, self._password)
+            imap.select("INBOX")
+
+            status, data = imap.search(None, "UNSEEN")
+            if status != "OK" or not data[0]:
+                imap.logout()
+                return results
+
+            for uid in data[0].split():
+                if uid in self._seen_uids:
+                    continue
+                self._seen_uids.add(uid)
+
+                status, msg_data = imap.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", "")
+                body = _extract_text_body(msg)
+                attachments = _extract_attachments(msg)
+
+                results.append({
+                    "uid": uid,
+                    "sender_addr": sender_addr,
+                    "sender_name": sender_name,
+                    "subject": subject,
+                    "message_id": message_id,
+                    "in_reply_to": in_reply_to,
+                    "body": body,
+                    "attachments": attachments,
+                    "date": msg.get("Date", ""),
+                })
+
+            imap.logout()
+        except Exception as e:
+            logger.error("[Email] IMAP fetch error: %s", e)
+        return results
+
+    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
+
+        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)
+        smtp.starttls()
+        smtp.login(self._address, self._password)
+        smtp.send_message(msg)
+        smtp.quit()
+
+        logger.info("[Email] Sent reply to %s (subject: %s)", to_addr, subject)
+        return msg_id
+
+    async def send_typing(self, chat_id: str) -> None:
+        """Email has no typing indicator — no-op."""
+        pass
+
+    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)
+        smtp.starttls()
+        smtp.login(self._address, self._password)
+        smtp.send_message(msg)
+        smtp.quit()
+
+        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

@@ -419,7 +419,7 @@ 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
 

gateway/platforms/signal.py

@@ -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.
 
@@ -404,9 +418,8 @@ 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 +433,10 @@ 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 +451,13 @@ 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.IMAGE
 
         # Parse timestamp from envelope data (milliseconds since epoch)
         ts_ms = envelope_data.get("timestamp", 0)
@@ -462,9 +474,8 @@ 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,
         )
 
@@ -546,16 +557,16 @@ 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:"):
@@ -569,7 +580,7 @@ class SignalAdapter(BasePlatformAdapter):
             return SendResult(success=True)
         return SendResult(success=False, error="RPC send failed")
 
-    async def send_typing(self, chat_id: str) -> None:
+    async def send_typing(self, chat_id: str, metadata=None) -> None:
         """Send a typing indicator."""
         params: Dict[str, Any] = {
             "account": self.account,

gateway/platforms/slack.py

@@ -9,6 +9,7 @@ Uses slack-bolt (Python) with Socket Mode for:
 """
 
 import asyncio
+import logging
 import os
 import re
 from typing import Dict, List, Optional, Any
@@ -41,6 +42,9 @@ from gateway.platforms.base import (
 )
 
 
+logger = logging.getLogger(__name__)
+
+
 def check_slack_requirements() -> bool:
     """Check if Slack dependencies are available."""
     return SLACK_AVAILABLE
@@ -62,28 +66,31 @@ 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
 
     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
         app_token = os.getenv("SLACK_APP_TOKEN")
 
         if not bot_token:
-            print("[Slack] SLACK_BOT_TOKEN not set")
+            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:
@@ -117,19 +124,22 @@ class SlackAdapter(BasePlatformAdapter):
             asyncio.create_task(self._handler.start_async())
 
             self._running = True
-            print(f"[Slack] Connected as @{bot_name} (Socket Mode)")
+            logger.info("[Slack] Connected as @%s (Socket Mode)", bot_name)
             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")
+        logger.info("[Slack] Disconnected")
 
     async def send(
         self,
@@ -143,27 +153,40 @@ 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._app.client.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(
@@ -182,12 +205,208 @@ class SlackAdapter(BasePlatformAdapter):
                 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._app.client.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
+
+    # ----- 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._app.client.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._app.client.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) -> 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:
+            result = await self._app.client.users_info(user=user_id)
+            user = result.get("user", {})
+            # Prefer display_name → real_name → user_id
+            profile = user.get("profile", {})
+            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,
@@ -195,6 +414,7 @@ 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:
@@ -210,13 +430,22 @@ class SlackAdapter(BasePlatformAdapter):
                 file=image_path,
                 filename=os.path.basename(image_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 local image: {e}")
-            return await super().send_image_file(chat_id, image_path, caption, reply_to)
+        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,
+            )
+            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 +453,7 @@ 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:
@@ -242,12 +472,18 @@ class SlackAdapter(BasePlatformAdapter):
                 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)
@@ -258,6 +494,7 @@ class SlackAdapter(BasePlatformAdapter):
         audio_path: str,
         caption: Optional[str] = None,
         reply_to: Optional[str] = None,
+        metadata: Optional[Dict[str, Any]] = None,
     ) -> SendResult:
         """Send an audio file to Slack."""
         if not self._app:
@@ -269,11 +506,17 @@ class SlackAdapter(BasePlatformAdapter):
                 file=audio_path,
                 filename=os.path.basename(audio_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:
+        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=False, error=str(e))
 
     async def send_video(
@@ -282,6 +525,7 @@ 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:
@@ -296,13 +540,22 @@ class SlackAdapter(BasePlatformAdapter):
                 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 +564,7 @@ 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:
@@ -327,13 +581,22 @@ class SlackAdapter(BasePlatformAdapter):
                 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."""
@@ -348,7 +611,13 @@ class SlackAdapter(BasePlatformAdapter):
                 "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 -----
@@ -367,13 +636,22 @@ 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", "")
 
         # 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:
@@ -403,8 +681,8 @@ class SlackAdapter(BasePlatformAdapter):
                     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]
@@ -414,8 +692,8 @@ class SlackAdapter(BasePlatformAdapter):
                     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:
@@ -437,7 +715,7 @@ 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
@@ -449,7 +727,7 @@ 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 +744,11 @@ 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)
 
         # Build source
         source = self.build_source(
@@ -475,6 +756,7 @@ 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,
         )
 
@@ -489,8 +771,15 @@ 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()
@@ -504,6 +793,15 @@ class SlackAdapter(BasePlatformAdapter):
             "help": "/help",
             "model": "/model", "personality": "/personality",
             "retry": "/retry", "undo": "/undo",
+            "compact": "/compress", "compress": "/compress",
+            "resume": "/resume",
+            "background": "/background",
+            "usage": "/usage",
+            "insights": "/insights",
+            "title": "/title",
+            "reasoning": "/reasoning",
+            "provider": "/provider",
+            "rollback": "/rollback",
         }
         first_word = text.split()[0] if text else ""
         if first_word in subcommand_map:

gateway/platforms/telegram.py

@@ -86,6 +86,9 @@ def _strip_mdv2(text: str) -> str:
     cleaned = re.sub(r'\\([_*\[\]()~`>#\+\-=|{}.!\\])', r'\1', text)
     # Remove MarkdownV2 bold markers that format_message converted from **bold**
     cleaned = re.sub(r'\*([^*]+)\*', r'\1', cleaned)
+    # Remove MarkdownV2 italic markers that format_message converted from *italic*
+    # Use word boundary (\b) to avoid breaking snake_case like my_variable_name
+    cleaned = re.sub(r'(?<!\w)_([^_]+)_(?!\w)', r'\1', cleaned)
     return cleaned
 
 
@@ -111,11 +114,14 @@ class TelegramAdapter(BasePlatformAdapter):
     async def connect(self) -> bool:
         """Connect to Telegram and start polling for updates."""
         if not TELEGRAM_AVAILABLE:
-            print(f"[{self.name}] python-telegram-bot not installed. Run: pip install python-telegram-bot")
+            logger.error(
+                "[%s] python-telegram-bot not installed. Run: pip install python-telegram-bot",
+                self.name,
+            )
             return False
         
         if not self.config.token:
-            print(f"[{self.name}] No bot token configured")
+            logger.error("[%s] No bot token configured", self.name)
             return False
         
         try:
@@ -170,14 +176,19 @@ class TelegramAdapter(BasePlatformAdapter):
                     BotCommand("help", "Show available commands"),
                 ])
             except Exception as e:
-                print(f"[{self.name}] Could not register command menu: {e}")
+                logger.warning(
+                    "[%s] Could not register Telegram command menu: %s",
+                    self.name,
+                    e,
+                    exc_info=True,
+                )
             
             self._running = True
-            print(f"[{self.name}] Connected and polling for updates")
+            logger.info("[%s] Connected and polling for Telegram updates", self.name)
             return True
             
         except Exception as e:
-            print(f"[{self.name}] Failed to connect: {e}")
+            logger.error("[%s] Failed to connect to Telegram: %s", self.name, e, exc_info=True)
             return False
     
     async def disconnect(self) -> None:
@@ -188,12 +199,12 @@ class TelegramAdapter(BasePlatformAdapter):
                 await self._app.stop()
                 await self._app.shutdown()
             except Exception as e:
-                print(f"[{self.name}] Error during disconnect: {e}")
+                logger.warning("[%s] Error during Telegram disconnect: %s", self.name, e, exc_info=True)
         
         self._running = False
         self._app = None
         self._bot = None
-        print(f"[{self.name}] Disconnected")
+        logger.info("[%s] Disconnected from Telegram", self.name)
     
     async def send(
         self,
@@ -249,6 +260,7 @@ class TelegramAdapter(BasePlatformAdapter):
             )
             
         except Exception as e:
+            logger.error("[%s] Failed to send Telegram message: %s", self.name, e, exc_info=True)
             return SendResult(success=False, error=str(e))
 
     async def edit_message(
@@ -278,6 +290,13 @@ class TelegramAdapter(BasePlatformAdapter):
                 )
             return SendResult(success=True, message_id=message_id)
         except Exception as e:
+            logger.error(
+                "[%s] Failed to edit Telegram message %s: %s",
+                self.name,
+                message_id,
+                e,
+                exc_info=True,
+            )
             return SendResult(success=False, error=str(e))
 
     async def send_voice(
@@ -286,6 +305,7 @@ class TelegramAdapter(BasePlatformAdapter):
         audio_path: str,
         caption: Optional[str] = None,
         reply_to: Optional[str] = None,
+        metadata: Optional[Dict[str, Any]] = None,
     ) -> SendResult:
         """Send audio as a native Telegram voice message or audio file."""
         if not self._bot:
@@ -299,23 +319,32 @@ class TelegramAdapter(BasePlatformAdapter):
             with open(audio_path, "rb") as audio_file:
                 # .ogg files -> send as voice (round playable bubble)
                 if audio_path.endswith(".ogg") or audio_path.endswith(".opus"):
+                    _voice_thread = metadata.get("thread_id") if metadata else None
                     msg = await self._bot.send_voice(
                         chat_id=int(chat_id),
                         voice=audio_file,
                         caption=caption[:1024] if caption else None,
                         reply_to_message_id=int(reply_to) if reply_to else None,
+                        message_thread_id=int(_voice_thread) if _voice_thread else None,
                     )
                 else:
                     # .mp3 and others -> send as audio file
+                    _audio_thread = metadata.get("thread_id") if metadata else None
                     msg = await self._bot.send_audio(
                         chat_id=int(chat_id),
                         audio=audio_file,
                         caption=caption[:1024] if caption else None,
                         reply_to_message_id=int(reply_to) if reply_to else None,
+                        message_thread_id=int(_audio_thread) if _audio_thread else None,
                     )
             return SendResult(success=True, message_id=str(msg.message_id))
         except Exception as e:
-            print(f"[{self.name}] Failed to send voice/audio: {e}")
+            logger.error(
+                "[%s] Failed to send Telegram voice/audio, falling back to base adapter: %s",
+                self.name,
+                e,
+                exc_info=True,
+            )
             return await super().send_voice(chat_id, audio_path, caption, reply_to)
     
     async def send_image_file(
@@ -324,6 +353,7 @@ class TelegramAdapter(BasePlatformAdapter):
         image_path: str,
         caption: Optional[str] = None,
         reply_to: Optional[str] = None,
+        **kwargs,
     ) -> SendResult:
         """Send a local image file natively as a Telegram photo."""
         if not self._bot:
@@ -343,15 +373,81 @@ class TelegramAdapter(BasePlatformAdapter):
                 )
             return SendResult(success=True, message_id=str(msg.message_id))
         except Exception as e:
-            print(f"[{self.name}] Failed to send local image: {e}")
+            logger.error(
+                "[%s] Failed to send Telegram local image, falling back to base adapter: %s",
+                self.name,
+                e,
+                exc_info=True,
+            )
             return await super().send_image_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,
+        **kwargs,
+    ) -> SendResult:
+        """Send a document/file natively as a Telegram file attachment."""
+        if not self._bot:
+            return SendResult(success=False, error="Not connected")
+
+        try:
+            if not os.path.exists(file_path):
+                return SendResult(success=False, error=f"File not found: {file_path}")
+
+            display_name = file_name or os.path.basename(file_path)
+
+            with open(file_path, "rb") as f:
+                msg = await self._bot.send_document(
+                    chat_id=int(chat_id),
+                    document=f,
+                    filename=display_name,
+                    caption=caption[:1024] if caption else None,
+                    reply_to_message_id=int(reply_to) if reply_to else None,
+                )
+            return SendResult(success=True, message_id=str(msg.message_id))
+        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)
+
+    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 as a Telegram video message."""
+        if not self._bot:
+            return SendResult(success=False, error="Not connected")
+
+        try:
+            if not os.path.exists(video_path):
+                return SendResult(success=False, error=f"Video file not found: {video_path}")
+
+            with open(video_path, "rb") as f:
+                msg = await self._bot.send_video(
+                    chat_id=int(chat_id),
+                    video=f,
+                    caption=caption[:1024] if caption else None,
+                    reply_to_message_id=int(reply_to) if reply_to else None,
+                )
+            return SendResult(success=True, message_id=str(msg.message_id))
+        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)
+
     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:
         """Send an image natively as a Telegram photo.
         
@@ -363,15 +459,22 @@ class TelegramAdapter(BasePlatformAdapter):
         
         try:
             # Telegram can send photos directly from URLs (up to ~5MB)
+            _photo_thread = metadata.get("thread_id") if metadata else None
             msg = await self._bot.send_photo(
                 chat_id=int(chat_id),
                 photo=image_url,
                 caption=caption[:1024] if caption else None,  # Telegram caption limit
                 reply_to_message_id=int(reply_to) if reply_to else None,
+                message_thread_id=int(_photo_thread) if _photo_thread else None,
             )
             return SendResult(success=True, message_id=str(msg.message_id))
         except Exception as e:
-            logger.warning("[%s] URL-based send_photo failed (%s), trying file upload", self.name, e)
+            logger.warning(
+                "[%s] URL-based send_photo failed, trying file upload: %s",
+                self.name,
+                e,
+                exc_info=True,
+            )
             # Fallback: download and upload as file (supports up to 10MB)
             try:
                 import httpx
@@ -388,7 +491,12 @@ class TelegramAdapter(BasePlatformAdapter):
                 )
                 return SendResult(success=True, message_id=str(msg.message_id))
             except Exception as e2:
-                logger.error("[%s] File upload send_photo also failed: %s", self.name, e2)
+                logger.error(
+                    "[%s] File upload send_photo also failed: %s",
+                    self.name,
+                    e2,
+                    exc_info=True,
+                )
                 # Final fallback: send URL as text
                 return await super().send_image(chat_id, image_url, caption, reply_to)
     
@@ -398,34 +506,50 @@ class TelegramAdapter(BasePlatformAdapter):
         animation_url: str,
         caption: Optional[str] = None,
         reply_to: Optional[str] = None,
+        metadata: Optional[Dict[str, Any]] = None,
     ) -> SendResult:
         """Send an animated GIF natively as a Telegram animation (auto-plays inline)."""
         if not self._bot:
             return SendResult(success=False, error="Not connected")
         
         try:
+            _anim_thread = metadata.get("thread_id") if metadata else None
             msg = await self._bot.send_animation(
                 chat_id=int(chat_id),
                 animation=animation_url,
                 caption=caption[:1024] if caption else None,
                 reply_to_message_id=int(reply_to) if reply_to else None,
+                message_thread_id=int(_anim_thread) if _anim_thread else None,
             )
             return SendResult(success=True, message_id=str(msg.message_id))
         except Exception as e:
-            print(f"[{self.name}] Failed to send animation, falling back to photo: {e}")
+            logger.error(
+                "[%s] Failed to send Telegram animation, falling back to photo: %s",
+                self.name,
+                e,
+                exc_info=True,
+            )
             # Fallback: try as a regular photo
             return await self.send_image(chat_id, animation_url, caption, reply_to)
 
-    async def send_typing(self, chat_id: str) -> None:
+    async def send_typing(self, chat_id: str, metadata: Optional[Dict[str, Any]] = None) -> None:
         """Send typing indicator."""
         if self._bot:
             try:
+                _typing_thread = metadata.get("thread_id") if metadata else None
                 await self._bot.send_chat_action(
                     chat_id=int(chat_id),
-                    action="typing"
+                    action="typing",
+                    message_thread_id=int(_typing_thread) if _typing_thread else None,
+                )
+            except Exception as e:
+                # Typing failures are non-fatal; log at debug level only.
+                logger.debug(
+                    "[%s] Failed to send Telegram typing indicator: %s",
+                    self.name,
+                    e,
+                    exc_info=True,
                 )
-            except Exception:
-                pass  # Ignore typing indicator failures
     
     async def get_chat_info(self, chat_id: str) -> Dict[str, Any]:
         """Get information about a Telegram chat."""
@@ -452,6 +576,13 @@ class TelegramAdapter(BasePlatformAdapter):
                 "is_forum": getattr(chat, "is_forum", False),
             }
         except Exception as e:
+            logger.error(
+                "[%s] Failed to get Telegram chat info for %s: %s",
+                self.name,
+                chat_id,
+                e,
+                exc_info=True,
+            )
             return {"name": str(chat_id), "type": "dm", "error": str(e)}
     
     def format_message(self, content: str) -> str:
@@ -640,9 +771,9 @@ class TelegramAdapter(BasePlatformAdapter):
                 cached_path = cache_image_from_bytes(bytes(image_bytes), ext=ext)
                 event.media_urls = [cached_path]
                 event.media_types = [f"image/{ext.lstrip('.')}"]
-                print(f"[Telegram] Cached user photo: {cached_path}", flush=True)
+                logger.info("[Telegram] Cached user photo at %s", cached_path)
             except Exception as e:
-                print(f"[Telegram] Failed to cache photo: {e}", flush=True)
+                logger.warning("[Telegram] Failed to cache photo: %s", e, exc_info=True)
         
         # Download voice/audio messages to cache for STT transcription
         if msg.voice:
@@ -652,9 +783,9 @@ class TelegramAdapter(BasePlatformAdapter):
                 cached_path = cache_audio_from_bytes(bytes(audio_bytes), ext=".ogg")
                 event.media_urls = [cached_path]
                 event.media_types = ["audio/ogg"]
-                print(f"[Telegram] Cached user voice: {cached_path}", flush=True)
+                logger.info("[Telegram] Cached user voice at %s", cached_path)
             except Exception as e:
-                print(f"[Telegram] Failed to cache voice: {e}", flush=True)
+                logger.warning("[Telegram] Failed to cache voice: %s", e, exc_info=True)
         elif msg.audio:
             try:
                 file_obj = await msg.audio.get_file()
@@ -662,9 +793,9 @@ class TelegramAdapter(BasePlatformAdapter):
                 cached_path = cache_audio_from_bytes(bytes(audio_bytes), ext=".mp3")
                 event.media_urls = [cached_path]
                 event.media_types = ["audio/mp3"]
-                print(f"[Telegram] Cached user audio: {cached_path}", flush=True)
+                logger.info("[Telegram] Cached user audio at %s", cached_path)
             except Exception as e:
-                print(f"[Telegram] Failed to cache audio: {e}", flush=True)
+                logger.warning("[Telegram] Failed to cache audio: %s", e, exc_info=True)
 
         # Download document files to cache for agent processing
         elif msg.document:
@@ -689,7 +820,7 @@ class TelegramAdapter(BasePlatformAdapter):
                         f"Unsupported document type '{ext or 'unknown'}'. "
                         f"Supported types: {supported_list}"
                     )
-                    print(f"[Telegram] Unsupported document type: {ext or 'unknown'}", flush=True)
+                    logger.info("[Telegram] Unsupported document type: %s", ext or "unknown")
                     await self.handle_message(event)
                     return
 
@@ -700,7 +831,7 @@ class TelegramAdapter(BasePlatformAdapter):
                         "The document is too large or its size could not be verified. "
                         "Maximum: 20 MB."
                     )
-                    print(f"[Telegram] Document too large: {doc.file_size} bytes", flush=True)
+                    logger.info("[Telegram] Document too large: %s bytes", doc.file_size)
                     await self.handle_message(event)
                     return
 
@@ -712,7 +843,7 @@ class TelegramAdapter(BasePlatformAdapter):
                 mime_type = SUPPORTED_DOCUMENT_TYPES[ext]
                 event.media_urls = [cached_path]
                 event.media_types = [mime_type]
-                print(f"[Telegram] Cached user document: {cached_path}", flush=True)
+                logger.info("[Telegram] Cached user document at %s", cached_path)
 
                 # For text files, inject content into event.text (capped at 100 KB)
                 MAX_TEXT_INJECT_BYTES = 100 * 1024
@@ -727,10 +858,13 @@ class TelegramAdapter(BasePlatformAdapter):
                         else:
                             event.text = injection
                     except UnicodeDecodeError:
-                        print(f"[Telegram] Could not decode text file as UTF-8, skipping content injection", flush=True)
+                        logger.warning(
+                            "[Telegram] Could not decode text file as UTF-8, skipping content injection",
+                            exc_info=True,
+                        )
 
             except Exception as e:
-                print(f"[Telegram] Failed to cache document: {e}", flush=True)
+                logger.warning("[Telegram] Failed to cache document: %s", e, exc_info=True)
 
         await self.handle_message(event)
     
@@ -765,7 +899,7 @@ class TelegramAdapter(BasePlatformAdapter):
             event.text = build_sticker_injection(
                 cached["description"], cached.get("emoji", emoji), cached.get("set_name", set_name)
             )
-            print(f"[Telegram] Sticker cache hit: {sticker.file_unique_id}", flush=True)
+            logger.info("[Telegram] Sticker cache hit: %s", sticker.file_unique_id)
             return
 
         # Cache miss -- download and analyze
@@ -773,7 +907,7 @@ class TelegramAdapter(BasePlatformAdapter):
             file_obj = await sticker.get_file()
             image_bytes = await file_obj.download_as_bytearray()
             cached_path = cache_image_from_bytes(bytes(image_bytes), ext=".webp")
-            print(f"[Telegram] Analyzing sticker: {cached_path}", flush=True)
+            logger.info("[Telegram] Analyzing sticker at %s", cached_path)
 
             from tools.vision_tools import vision_analyze_tool
             import json as _json
@@ -795,7 +929,7 @@ class TelegramAdapter(BasePlatformAdapter):
                     emoji, set_name,
                 )
         except Exception as e:
-            print(f"[Telegram] Sticker analysis error: {e}", flush=True)
+            logger.warning("[Telegram] Sticker analysis error: %s", e, exc_info=True)
             event.text = build_sticker_injection(
                 f"a sticker with emoji {emoji}" if emoji else "a sticker",
                 emoji, set_name,

gateway/platforms/whatsapp.py

@@ -181,8 +181,8 @@ class WhatsAppAdapter(BasePlatformAdapter):
             
             # Kill any orphaned bridge from a previous gateway run
             _kill_port_process(self._bridge_port)
-            import time
-            time.sleep(1)
+            import asyncio
+            await asyncio.sleep(1)
             
             # Start the bridge process in its own process group.
             # Route output to a log file so QR codes, errors, and reconnection
@@ -493,7 +493,7 @@ class WhatsAppAdapter(BasePlatformAdapter):
             file_name or os.path.basename(file_path),
         )
 
-    async def send_typing(self, chat_id: str) -> None:
+    async def send_typing(self, chat_id: str, metadata=None) -> None:
         """Send typing indicator via bridge."""
         if not self._running:
             return

gateway/session.py

@@ -241,6 +241,9 @@ class SessionEntry:
     output_tokens: int = 0
     total_tokens: int = 0
     
+    # Last API-reported prompt tokens (for accurate compression pre-check)
+    last_prompt_tokens: int = 0
+    
     # Set when a session was created because the previous one expired;
     # consumed once by the message handler to inject a notice into context
     was_auto_reset: bool = False
@@ -257,6 +260,7 @@ class SessionEntry:
             "input_tokens": self.input_tokens,
             "output_tokens": self.output_tokens,
             "total_tokens": self.total_tokens,
+            "last_prompt_tokens": self.last_prompt_tokens,
         }
         if self.origin:
             result["origin"] = self.origin.to_dict()
@@ -272,8 +276,8 @@ class SessionEntry:
         if data.get("platform"):
             try:
                 platform = Platform(data["platform"])
-            except ValueError:
-                pass
+            except ValueError as e:
+                logger.debug("Unknown platform value %r: %s", data["platform"], e)
         
         return cls(
             session_key=data["session_key"],
@@ -287,6 +291,7 @@ class SessionEntry:
             input_tokens=data.get("input_tokens", 0),
             output_tokens=data.get("output_tokens", 0),
             total_tokens=data.get("total_tokens", 0),
+            last_prompt_tokens=data.get("last_prompt_tokens", 0),
         )
 
 
@@ -294,13 +299,26 @@ def build_session_key(source: SessionSource) -> str:
     """Build a deterministic session key from a message source.
 
     This is the single source of truth for session key construction.
-    WhatsApp DMs include chat_id (multi-user), other DMs do not (single owner).
+
+    DM rules:
+      - WhatsApp DMs include chat_id (multi-user support).
+      - Other DMs include thread_id when present (e.g. Slack threaded DMs),
+        so each DM thread gets its own session while top-level DMs share one.
+      - Without thread_id or chat_id, all DMs share a single session.
+
+    Group/channel rules:
+      - thread_id differentiates threads within a channel.
+      - Without thread_id, all messages in a channel share one session.
     """
     platform = source.platform.value
     if source.chat_type == "dm":
+        if source.thread_id:
+            return f"agent:main:{platform}:dm:{source.thread_id}"
         if platform == "whatsapp" and source.chat_id:
             return f"agent:main:{platform}:dm:{source.chat_id}"
         return f"agent:main:{platform}:dm"
+    if source.thread_id:
+        return f"agent:main:{platform}:{source.chat_type}:{source.chat_id}:{source.thread_id}"
     return f"agent:main:{platform}:{source.chat_type}:{source.chat_id}"
 
 
@@ -353,12 +371,26 @@ class SessionStore:
     
     def _save(self) -> None:
         """Save sessions index to disk (kept for session key -> ID mapping)."""
+        import tempfile
         self.sessions_dir.mkdir(parents=True, exist_ok=True)
         sessions_file = self.sessions_dir / "sessions.json"
-        
+
         data = {key: entry.to_dict() for key, entry in self._entries.items()}
-        with open(sessions_file, "w", encoding="utf-8") as f:
-            json.dump(data, f, indent=2)
+        fd, tmp_path = tempfile.mkstemp(
+            dir=str(self.sessions_dir), suffix=".tmp", prefix=".sessions_"
+        )
+        try:
+            with os.fdopen(fd, "w", encoding="utf-8") as f:
+                json.dump(data, f, indent=2)
+                f.flush()
+                os.fsync(f.fileno())
+            os.replace(tmp_path, sessions_file)
+        except BaseException:
+            try:
+                os.unlink(tmp_path)
+            except OSError as e:
+                logger.debug("Could not remove temp file %s: %s", tmp_path, e)
+            raise
     
     def _generate_session_key(self, source: SessionSource) -> str:
         """Generate a session key from a source."""
@@ -536,7 +568,8 @@ class SessionStore:
         self, 
         session_key: str,
         input_tokens: int = 0,
-        output_tokens: int = 0
+        output_tokens: int = 0,
+        last_prompt_tokens: int = None,
     ) -> None:
         """Update a session's metadata after an interaction."""
         self._ensure_loaded()
@@ -546,6 +579,8 @@ class SessionStore:
             entry.updated_at = datetime.now()
             entry.input_tokens += input_tokens
             entry.output_tokens += output_tokens
+            if last_prompt_tokens is not None:
+                entry.last_prompt_tokens = last_prompt_tokens
             entry.total_tokens = entry.input_tokens + entry.output_tokens
             self._save()
             
@@ -663,10 +698,17 @@ class SessionStore:
         """Get the path to a session's legacy transcript file."""
         return self.sessions_dir / f"{session_id}.jsonl"
     
-    def append_to_transcript(self, session_id: str, message: Dict[str, Any]) -> None:
-        """Append a message to a session's transcript (SQLite + legacy JSONL)."""
-        # Write to SQLite
-        if self._db:
+    def append_to_transcript(self, session_id: str, message: Dict[str, Any], skip_db: bool = False) -> None:
+        """Append a message to a session's transcript (SQLite + legacy JSONL).
+
+        Args:
+            skip_db: When True, only write to JSONL and skip the SQLite write.
+                     Used when the agent already persisted messages to SQLite
+                     via its own _flush_messages_to_session_db(), preventing
+                     the duplicate-write bug (#860).
+        """
+        # Write to SQLite (unless the agent already handled it)
+        if self._db and not skip_db:
             try:
                 self._db.append_message(
                     session_id=session_id,

hermes_cli/__init__.py

@@ -11,4 +11,5 @@ Provides subcommands for:
 - hermes cron          - Manage cron jobs
 """
 
-__version__ = "v1.0.0"
+__version__ = "0.2.0"
+__release_date__ = "2026.3.12"

hermes_cli/auth.py

@@ -23,6 +23,7 @@ import stat
 import base64
 import hashlib
 import subprocess
+import threading
 import time
 import uuid
 import webbrowser
@@ -44,6 +45,10 @@ try:
     import fcntl
 except Exception:
     fcntl = None
+try:
+    import msvcrt
+except Exception:
+    msvcrt = None
 
 # =============================================================================
 # Constants
@@ -127,6 +132,13 @@ PROVIDER_REGISTRY: Dict[str, ProviderConfig] = {
         api_key_env_vars=("MINIMAX_API_KEY",),
         base_url_env_var="MINIMAX_BASE_URL",
     ),
+    "anthropic": ProviderConfig(
+        id="anthropic",
+        name="Anthropic",
+        auth_type="api_key",
+        inference_base_url="https://api.anthropic.com",
+        api_key_env_vars=("ANTHROPIC_API_KEY", "ANTHROPIC_TOKEN", "CLAUDE_CODE_OAUTH_TOKEN"),
+    ),
     "minimax-cn": ProviderConfig(
         id="minimax-cn",
         name="MiniMax (China)",
@@ -299,31 +311,64 @@ def _auth_lock_path() -> Path:
     return _auth_file_path().with_suffix(".lock")
 
 
+_auth_lock_holder = threading.local()
+
 @contextmanager
 def _auth_store_lock(timeout_seconds: float = AUTH_LOCK_TIMEOUT_SECONDS):
-    """Cross-process advisory lock for auth.json reads+writes."""
+    """Cross-process advisory lock for auth.json reads+writes.  Reentrant."""
+    # Reentrant: if this thread already holds the lock, just yield.
+    if getattr(_auth_lock_holder, "depth", 0) > 0:
+        _auth_lock_holder.depth += 1
+        try:
+            yield
+        finally:
+            _auth_lock_holder.depth -= 1
+        return
+
     lock_path = _auth_lock_path()
     lock_path.parent.mkdir(parents=True, exist_ok=True)
 
-    with lock_path.open("a+") as lock_file:
-        if fcntl is None:
+    if fcntl is None and msvcrt is None:
+        _auth_lock_holder.depth = 1
+        try:
             yield
-            return
+        finally:
+            _auth_lock_holder.depth = 0
+        return
 
+    # On Windows, msvcrt.locking needs the file to have content and the
+    # file pointer at position 0.  Ensure the lock file has at least 1 byte.
+    if msvcrt and (not lock_path.exists() or lock_path.stat().st_size == 0):
+        lock_path.write_text(" ", encoding="utf-8")
+
+    with lock_path.open("r+" if msvcrt else "a+") as lock_file:
         deadline = time.time() + max(1.0, timeout_seconds)
         while True:
             try:
-                fcntl.flock(lock_file.fileno(), fcntl.LOCK_EX | fcntl.LOCK_NB)
+                if fcntl:
+                    fcntl.flock(lock_file.fileno(), fcntl.LOCK_EX | fcntl.LOCK_NB)
+                else:
+                    lock_file.seek(0)
+                    msvcrt.locking(lock_file.fileno(), msvcrt.LK_NBLCK, 1)
                 break
-            except BlockingIOError:
+            except (BlockingIOError, OSError, PermissionError):
                 if time.time() >= deadline:
                     raise TimeoutError("Timed out waiting for auth store lock")
                 time.sleep(0.05)
 
+        _auth_lock_holder.depth = 1
         try:
             yield
         finally:
-            fcntl.flock(lock_file.fileno(), fcntl.LOCK_UN)
+            _auth_lock_holder.depth = 0
+            if fcntl:
+                fcntl.flock(lock_file.fileno(), fcntl.LOCK_UN)
+            elif msvcrt:
+                try:
+                    lock_file.seek(0)
+                    msvcrt.locking(lock_file.fileno(), msvcrt.LK_UNLCK, 1)
+                except (OSError, IOError):
+                    pass
 
 
 def _load_auth_store(auth_file: Optional[Path] = None) -> Dict[str, Any]:
@@ -478,6 +523,7 @@ def resolve_provider(
         "glm": "zai", "z-ai": "zai", "z.ai": "zai", "zhipu": "zai",
         "kimi": "kimi-coding", "moonshot": "kimi-coding",
         "minimax-china": "minimax-cn", "minimax_cn": "minimax-cn",
+        "claude": "anthropic", "claude-code": "anthropic",
     }
     normalized = _PROVIDER_ALIASES.get(normalized, normalized)
 
@@ -1056,6 +1102,19 @@ def fetch_nous_models(
                 continue
             model_ids.append(mid)
 
+    # Sort: prefer opus > pro > haiku/flash > sonnet (sonnet is cheap/fast,
+    # users who want the best model should see opus first).
+    def _model_priority(mid: str) -> tuple:
+        low = mid.lower()
+        if "opus" in low:
+            return (0, mid)
+        if "pro" in low and "sonnet" not in low:
+            return (1, mid)
+        if "sonnet" in low:
+            return (3, mid)
+        return (2, mid)
+
+    model_ids.sort(key=_model_priority)
     return list(dict.fromkeys(model_ids))
 
 
@@ -1512,7 +1571,11 @@ def _update_config_for_provider(provider_id: str, inference_base_url: str) -> Pa
         model_cfg = {}
 
     model_cfg["provider"] = provider_id
-    model_cfg["base_url"] = inference_base_url.rstrip("/")
+    if inference_base_url and inference_base_url.strip():
+        model_cfg["base_url"] = inference_base_url.rstrip("/")
+    else:
+        # Clear stale base_url to prevent contamination when switching providers
+        model_cfg.pop("base_url", None)
     config["model"] = model_cfg
 
     config_path.write_text(yaml.safe_dump(config, sort_keys=False))
@@ -1620,17 +1683,20 @@ def _prompt_model_selection(model_ids: List[str], current_model: str = "") -> Op
 
 
 def _save_model_choice(model_id: str) -> None:
-    """Save the selected model to config.yaml and .env."""
-    from hermes_cli.config import save_config, load_config, save_env_value
+    """Save the selected model to config.yaml (single source of truth).
+
+    The model is stored in config.yaml only — NOT in .env.  This avoids
+    conflicts in multi-agent setups where env vars would stomp each other.
+    """
+    from hermes_cli.config import save_config, load_config
 
     config = load_config()
-    # Handle both string and dict model formats
+    # Always use dict format so provider/base_url can be stored alongside
     if isinstance(config.get("model"), dict):
         config["model"]["default"] = model_id
     else:
-        config["model"] = model_id
+        config["model"] = {"default": model_id}
     save_config(config)
-    save_env_value("LLM_MODEL", model_id)
 
 
 def login_command(args) -> None:

hermes_cli/banner.py

@@ -36,11 +36,33 @@ def cprint(text: str):
     _pt_print(_PT_ANSI(text))
 
 
+# =========================================================================
+# Skin-aware color helpers
+# =========================================================================
+
+def _skin_color(key: str, fallback: str) -> str:
+    """Get a color from the active skin, or return fallback."""
+    try:
+        from hermes_cli.skin_engine import get_active_skin
+        return get_active_skin().get_color(key, fallback)
+    except Exception:
+        return fallback
+
+
+def _skin_branding(key: str, fallback: str) -> str:
+    """Get a branding string from the active skin, or return fallback."""
+    try:
+        from hermes_cli.skin_engine import get_active_skin
+        return get_active_skin().get_branding(key, fallback)
+    except Exception:
+        return fallback
+
+
 # =========================================================================
 # ASCII Art & Branding
 # =========================================================================
 
-from hermes_cli import __version__ as VERSION
+from hermes_cli import __version__ as VERSION, __release_date__ as RELEASE_DATE
 
 HERMES_AGENT_LOGO = """[bold #FFD700]██╗  ██╗███████╗██████╗ ███╗   ███╗███████╗███████╗       █████╗  ██████╗ ███████╗███╗   ██╗████████╗[/]
 [bold #FFD700]██║  ██║██╔════╝██╔══██╗████╗ ████║██╔════╝██╔════╝      ██╔══██╗██╔════╝ ██╔════╝████╗  ██║╚══██╔══╝[/]
@@ -217,18 +239,24 @@ def build_welcome_banner(console: Console, model: str, cwd: str,
     layout_table.add_column("left", justify="center")
     layout_table.add_column("right", justify="left")
 
+    # Resolve skin colors once for the entire banner
+    accent = _skin_color("banner_accent", "#FFBF00")
+    dim = _skin_color("banner_dim", "#B8860B")
+    text = _skin_color("banner_text", "#FFF8DC")
+    session_color = _skin_color("session_border", "#8B8682")
+
     left_lines = ["", HERMES_CADUCEUS, ""]
     model_short = model.split("/")[-1] if "/" in model else model
     if len(model_short) > 28:
         model_short = model_short[:25] + "..."
-    ctx_str = f" [dim #B8860B]·[/] [dim #B8860B]{_format_context_length(context_length)} context[/]" if context_length else ""
-    left_lines.append(f"[#FFBF00]{model_short}[/]{ctx_str} [dim #B8860B]·[/] [dim #B8860B]Nous Research[/]")
-    left_lines.append(f"[dim #B8860B]{cwd}[/]")
+    ctx_str = f" [dim {dim}]·[/] [dim {dim}]{_format_context_length(context_length)} context[/]" if context_length else ""
+    left_lines.append(f"[{accent}]{model_short}[/]{ctx_str} [dim {dim}]·[/] [dim {dim}]Nous Research[/]")
+    left_lines.append(f"[dim {dim}]{cwd}[/]")
     if session_id:
-        left_lines.append(f"[dim #8B8682]Session: {session_id}[/]")
+        left_lines.append(f"[dim {session_color}]Session: {session_id}[/]")
     left_content = "\n".join(left_lines)
 
-    right_lines = ["[bold #FFBF00]Available Tools[/]"]
+    right_lines = [f"[bold {accent}]Available Tools[/]"]
     toolsets_dict: Dict[str, list] = {}
 
     for tool in tools:
@@ -256,7 +284,7 @@ def build_welcome_banner(console: Console, model: str, cwd: str,
             if name in disabled_tools:
                 colored_names.append(f"[red]{name}[/]")
             else:
-                colored_names.append(f"[#FFF8DC]{name}[/]")
+                colored_names.append(f"[{text}]{name}[/]")
 
         tools_str = ", ".join(colored_names)
         if len(", ".join(sorted(tool_names))) > 45:
@@ -275,7 +303,7 @@ def build_welcome_banner(console: Console, model: str, cwd: str,
                 elif name in disabled_tools:
                     colored_names.append(f"[red]{name}[/]")
                 else:
-                    colored_names.append(f"[#FFF8DC]{name}[/]")
+                    colored_names.append(f"[{text}]{name}[/]")
             tools_str = ", ".join(colored_names)
 
         right_lines.append(f"[dim #B8860B]{toolset}:[/] {tools_str}")
@@ -306,7 +334,7 @@ def build_welcome_banner(console: Console, model: str, cwd: str,
                 )
 
     right_lines.append("")
-    right_lines.append("[bold #FFBF00]Available Skills[/]")
+    right_lines.append(f"[bold {accent}]Available Skills[/]")
     skills_by_category = get_available_skills()
     total_skills = sum(len(s) for s in skills_by_category.values())
 
@@ -320,9 +348,9 @@ def build_welcome_banner(console: Console, model: str, cwd: str,
                 skills_str = ", ".join(skill_names)
             if len(skills_str) > 50:
                 skills_str = skills_str[:47] + "..."
-            right_lines.append(f"[dim #B8860B]{category}:[/] [#FFF8DC]{skills_str}[/]")
+            right_lines.append(f"[dim {dim}]{category}:[/] [{text}]{skills_str}[/]")
     else:
-        right_lines.append("[dim #B8860B]No skills installed[/]")
+        right_lines.append(f"[dim {dim}]No skills installed[/]")
 
     right_lines.append("")
     mcp_connected = sum(1 for s in mcp_status if s["connected"]) if mcp_status else 0
@@ -330,7 +358,7 @@ def build_welcome_banner(console: Console, model: str, cwd: str,
     if mcp_connected:
         summary_parts.append(f"{mcp_connected} MCP servers")
     summary_parts.append("/help for commands")
-    right_lines.append(f"[dim #B8860B]{' · '.join(summary_parts)}[/]")
+    right_lines.append(f"[dim {dim}]{' · '.join(summary_parts)}[/]")
 
     # Update check — show if behind origin/main
     try:
@@ -347,10 +375,13 @@ def build_welcome_banner(console: Console, model: str, cwd: str,
     right_content = "\n".join(right_lines)
     layout_table.add_row(left_content, right_content)
 
+    agent_name = _skin_branding("agent_name", "Hermes Agent")
+    title_color = _skin_color("banner_title", "#FFD700")
+    border_color = _skin_color("banner_border", "#CD7F32")
     outer_panel = Panel(
         layout_table,
-        title=f"[bold #FFD700]Hermes Agent {VERSION}[/]",
-        border_style="#CD7F32",
+        title=f"[bold {title_color}]{agent_name} v{VERSION} ({RELEASE_DATE})[/]",
+        border_style=border_color,
         padding=(0, 2),
     )
 

hermes_cli/callbacks.py

@@ -8,8 +8,10 @@ with the TUI.
 
 import queue
 import time as _time
+import getpass
 
 from hermes_cli.banner import cprint, _DIM, _RST
+from hermes_cli.config import save_env_value_secure
 
 
 def clarify_callback(cli, question, choices):
@@ -33,7 +35,7 @@ def clarify_callback(cli, question, choices):
     cli._clarify_deadline = _time.monotonic() + timeout
     cli._clarify_freetext = is_open_ended
 
-    if hasattr(cli, '_app') and cli._app:
+    if hasattr(cli, "_app") and cli._app:
         cli._app.invalidate()
 
     while True:
@@ -45,13 +47,13 @@ def clarify_callback(cli, question, choices):
             remaining = cli._clarify_deadline - _time.monotonic()
             if remaining <= 0:
                 break
-            if hasattr(cli, '_app') and cli._app:
+            if hasattr(cli, "_app") and cli._app:
                 cli._app.invalidate()
 
     cli._clarify_state = None
     cli._clarify_freetext = False
     cli._clarify_deadline = 0
-    if hasattr(cli, '_app') and cli._app:
+    if hasattr(cli, "_app") and cli._app:
         cli._app.invalidate()
     cprint(f"\n{_DIM}(clarify timed out after {timeout}s — agent will decide){_RST}")
     return (
@@ -71,7 +73,7 @@ def sudo_password_callback(cli) -> str:
     cli._sudo_state = {"response_queue": response_queue}
     cli._sudo_deadline = _time.monotonic() + timeout
 
-    if hasattr(cli, '_app') and cli._app:
+    if hasattr(cli, "_app") and cli._app:
         cli._app.invalidate()
 
     while True:
@@ -79,7 +81,7 @@ def sudo_password_callback(cli) -> str:
             result = response_queue.get(timeout=1)
             cli._sudo_state = None
             cli._sudo_deadline = 0
-            if hasattr(cli, '_app') and cli._app:
+            if hasattr(cli, "_app") and cli._app:
                 cli._app.invalidate()
             if result:
                 cprint(f"\n{_DIM}  ✓ Password received (cached for session){_RST}")
@@ -90,25 +92,147 @@ def sudo_password_callback(cli) -> str:
             remaining = cli._sudo_deadline - _time.monotonic()
             if remaining <= 0:
                 break
-            if hasattr(cli, '_app') and cli._app:
+            if hasattr(cli, "_app") and cli._app:
                 cli._app.invalidate()
 
     cli._sudo_state = None
     cli._sudo_deadline = 0
-    if hasattr(cli, '_app') and cli._app:
+    if hasattr(cli, "_app") and cli._app:
         cli._app.invalidate()
     cprint(f"\n{_DIM}  ⏱ Timeout — continuing without sudo{_RST}")
     return ""
 
 
+def prompt_for_secret(cli, var_name: str, prompt: str, metadata=None) -> dict:
+    """Prompt for a secret value through the TUI (e.g. API keys for skills).
+
+    Returns a dict with keys: success, stored_as, validated, skipped, message.
+    The secret is stored in ~/.hermes/.env and never exposed to the model.
+    """
+    if not getattr(cli, "_app", None):
+        if not hasattr(cli, "_secret_state"):
+            cli._secret_state = None
+        if not hasattr(cli, "_secret_deadline"):
+            cli._secret_deadline = 0
+        try:
+            value = getpass.getpass(f"{prompt} (hidden, Enter to skip): ")
+        except (EOFError, KeyboardInterrupt):
+            value = ""
+
+        if not value:
+            cprint(f"\n{_DIM}  ⏭ Secret entry cancelled{_RST}")
+            return {
+                "success": True,
+                "reason": "cancelled",
+                "stored_as": var_name,
+                "validated": False,
+                "skipped": True,
+                "message": "Secret setup was skipped.",
+            }
+
+        stored = save_env_value_secure(var_name, value)
+        cprint(f"\n{_DIM}  ✓ Stored secret in ~/.hermes/.env as {var_name}{_RST}")
+        return {
+            **stored,
+            "skipped": False,
+            "message": "Secret stored securely. The secret value was not exposed to the model.",
+        }
+
+    timeout = 120
+    response_queue = queue.Queue()
+
+    cli._secret_state = {
+        "var_name": var_name,
+        "prompt": prompt,
+        "metadata": metadata or {},
+        "response_queue": response_queue,
+    }
+    cli._secret_deadline = _time.monotonic() + timeout
+    # Avoid storing stale draft input as the secret when Enter is pressed.
+    if hasattr(cli, "_clear_secret_input_buffer"):
+        try:
+            cli._clear_secret_input_buffer()
+        except Exception:
+            pass
+    elif hasattr(cli, "_app") and cli._app:
+        try:
+            cli._app.current_buffer.reset()
+        except Exception:
+            pass
+
+    if hasattr(cli, "_app") and cli._app:
+        cli._app.invalidate()
+
+    while True:
+        try:
+            value = response_queue.get(timeout=1)
+            cli._secret_state = None
+            cli._secret_deadline = 0
+            if hasattr(cli, "_app") and cli._app:
+                cli._app.invalidate()
+
+            if not value:
+                cprint(f"\n{_DIM}  ⏭ Secret entry cancelled{_RST}")
+                return {
+                    "success": True,
+                    "reason": "cancelled",
+                    "stored_as": var_name,
+                    "validated": False,
+                    "skipped": True,
+                    "message": "Secret setup was skipped.",
+                }
+
+            stored = save_env_value_secure(var_name, value)
+            cprint(f"\n{_DIM}  ✓ Stored secret in ~/.hermes/.env as {var_name}{_RST}")
+            return {
+                **stored,
+                "skipped": False,
+                "message": "Secret stored securely. The secret value was not exposed to the model.",
+            }
+        except queue.Empty:
+            remaining = cli._secret_deadline - _time.monotonic()
+            if remaining <= 0:
+                break
+            if hasattr(cli, "_app") and cli._app:
+                cli._app.invalidate()
+
+    cli._secret_state = None
+    cli._secret_deadline = 0
+    if hasattr(cli, "_clear_secret_input_buffer"):
+        try:
+            cli._clear_secret_input_buffer()
+        except Exception:
+            pass
+    elif hasattr(cli, "_app") and cli._app:
+        try:
+            cli._app.current_buffer.reset()
+        except Exception:
+            pass
+    if hasattr(cli, "_app") and cli._app:
+        cli._app.invalidate()
+    cprint(f"\n{_DIM}  ⏱ Timeout — secret capture cancelled{_RST}")
+    return {
+        "success": True,
+        "reason": "timeout",
+        "stored_as": var_name,
+        "validated": False,
+        "skipped": True,
+        "message": "Secret setup timed out and was skipped.",
+    }
+
+
 def approval_callback(cli, command: str, description: str) -> str:
     """Prompt for dangerous command approval through the TUI.
 
     Shows a selection UI with choices: once / session / always / deny.
+    When the command is longer than 70 characters, a "view" option is
+    included so the user can reveal the full text before deciding.
     """
     timeout = 60
     response_queue = queue.Queue()
     choices = ["once", "session", "always", "deny"]
+    if len(command) > 70:
+        choices.append("view")
 
     cli._approval_state = {
         "command": command,
@@ -119,7 +243,7 @@ def approval_callback(cli, command: str, description: str) -> str:
     }
     cli._approval_deadline = _time.monotonic() + timeout
 
-    if hasattr(cli, '_app') and cli._app:
+    if hasattr(cli, "_app") and cli._app:
         cli._app.invalidate()
 
     while True:
@@ -127,19 +251,19 @@ def approval_callback(cli, command: str, description: str) -> str:
             result = response_queue.get(timeout=1)
             cli._approval_state = None
             cli._approval_deadline = 0
-            if hasattr(cli, '_app') and cli._app:
+            if hasattr(cli, "_app") and cli._app:
                 cli._app.invalidate()
             return result
         except queue.Empty:
             remaining = cli._approval_deadline - _time.monotonic()
             if remaining <= 0:
                 break
-            if hasattr(cli, '_app') and cli._app:
+            if hasattr(cli, "_app") and cli._app:
                 cli._app.invalidate()
 
     cli._approval_state = None
     cli._approval_deadline = 0
-    if hasattr(cli, '_app') and cli._app:
+    if hasattr(cli, "_app") and cli._app:
         cli._app.invalidate()
     cprint(f"\n{_DIM}  ⏱ Timeout — denying command{_RST}")
     return "deny"

hermes_cli/checklist.py

@@ -0,0 +1,135 @@
+"""Shared curses-based multi-select checklist for Hermes CLI.
+
+Used by both ``hermes tools`` and ``hermes skills`` to present a
+toggleable list of items.  Falls back to a numbered text UI when
+curses is unavailable (Windows without curses, piped stdin, etc.).
+"""
+
+from typing import List, Set
+
+from hermes_cli.colors import Colors, color
+
+
+def curses_checklist(
+    title: str,
+    items: List[str],
+    pre_selected: Set[int],
+) -> Set[int]:
+    """Multi-select checklist.  Returns set of **selected** indices.
+
+    Args:
+        title: Header text shown at the top of the checklist.
+        items: Display labels for each row.
+        pre_selected: Indices that start checked.
+
+    Returns:
+        The indices the user confirmed as checked.  On cancel (ESC/q),
+        returns ``pre_selected`` unchanged.
+    """
+    try:
+        import curses
+        selected = set(pre_selected)
+        result = [None]
+
+        def _ui(stdscr):
+            curses.curs_set(0)
+            if curses.has_colors():
+                curses.start_color()
+                curses.use_default_colors()
+                curses.init_pair(1, curses.COLOR_GREEN, -1)
+                curses.init_pair(2, curses.COLOR_YELLOW, -1)
+                curses.init_pair(3, 8, -1)  # dim gray
+            cursor = 0
+            scroll_offset = 0
+
+            while True:
+                stdscr.clear()
+                max_y, max_x = stdscr.getmaxyx()
+
+                # Header
+                try:
+                    hattr = curses.A_BOLD | (curses.color_pair(2) if curses.has_colors() else 0)
+                    stdscr.addnstr(0, 0, title, max_x - 1, hattr)
+                    stdscr.addnstr(
+                        1, 0,
+                        "  ↑↓ navigate  SPACE toggle  ENTER confirm  ESC cancel",
+                        max_x - 1, curses.A_DIM,
+                    )
+                except curses.error:
+                    pass
+
+                # Scrollable item list
+                visible_rows = max_y - 3
+                if cursor < scroll_offset:
+                    scroll_offset = cursor
+                elif cursor >= scroll_offset + visible_rows:
+                    scroll_offset = cursor - visible_rows + 1
+
+                for draw_i, i in enumerate(
+                    range(scroll_offset, min(len(items), scroll_offset + visible_rows))
+                ):
+                    y = draw_i + 3
+                    if y >= max_y - 1:
+                        break
+                    check = "✓" if i in selected else " "
+                    arrow = "→" if i == cursor else " "
+                    line = f" {arrow} [{check}] {items[i]}"
+
+                    attr = curses.A_NORMAL
+                    if i == cursor:
+                        attr = curses.A_BOLD
+                        if curses.has_colors():
+                            attr |= curses.color_pair(1)
+                    try:
+                        stdscr.addnstr(y, 0, line, max_x - 1, attr)
+                    except curses.error:
+                        pass
+
+                stdscr.refresh()
+                key = stdscr.getch()
+
+                if key in (curses.KEY_UP, ord("k")):
+                    cursor = (cursor - 1) % len(items)
+                elif key in (curses.KEY_DOWN, ord("j")):
+                    cursor = (cursor + 1) % len(items)
+                elif key == ord(" "):
+                    selected.symmetric_difference_update({cursor})
+                elif key in (curses.KEY_ENTER, 10, 13):
+                    result[0] = set(selected)
+                    return
+                elif key in (27, ord("q")):
+                    result[0] = set(pre_selected)
+                    return
+
+        curses.wrapper(_ui)
+        return result[0] if result[0] is not None else set(pre_selected)
+
+    except Exception:
+        pass  # fall through to numbered fallback
+
+    # ── Numbered text fallback ────────────────────────────────────────────
+    selected = set(pre_selected)
+    print(color(f"\n  {title}", Colors.YELLOW))
+    print(color("  Toggle by number, Enter to confirm.\n", Colors.DIM))
+
+    while True:
+        for i, label in enumerate(items):
+            check = "✓" if i in selected else " "
+            print(f"    {i + 1:3}. [{check}] {label}")
+        print()
+
+        try:
+            raw = input(color("  Number to toggle, 's' to save, 'q' to cancel: ", Colors.DIM)).strip()
+        except (KeyboardInterrupt, EOFError):
+            return set(pre_selected)
+
+        if raw.lower() == "s" or raw == "":
+            return selected
+        if raw.lower() == "q":
+            return set(pre_selected)
+        try:
+            idx = int(raw) - 1
+            if 0 <= idx < len(items):
+                selected.symmetric_difference_update({idx})
+        except ValueError:
+            print(color("  Invalid input", Colors.DIM))

hermes_cli/claw.py

@@ -0,0 +1,296 @@
+"""hermes claw — OpenClaw migration commands.
+
+Usage:
+    hermes claw migrate              # Interactive migration from ~/.openclaw
+    hermes claw migrate --dry-run    # Preview what would be migrated
+    hermes claw migrate --preset full --overwrite  # Full migration, overwrite conflicts
+"""
+
+import importlib.util
+import logging
+import sys
+from pathlib import Path
+
+from hermes_cli.config import get_hermes_home, get_config_path, load_config, save_config
+from hermes_cli.setup import (
+    Colors,
+    color,
+    print_header,
+    print_info,
+    print_success,
+    print_warning,
+    print_error,
+    prompt_yes_no,
+    prompt_choice,
+)
+
+logger = logging.getLogger(__name__)
+
+PROJECT_ROOT = Path(__file__).parent.parent.resolve()
+
+_OPENCLAW_SCRIPT = (
+    PROJECT_ROOT
+    / "optional-skills"
+    / "migration"
+    / "openclaw-migration"
+    / "scripts"
+    / "openclaw_to_hermes.py"
+)
+
+# Fallback: user may have installed the skill from the Hub
+_OPENCLAW_SCRIPT_INSTALLED = (
+    get_hermes_home()
+    / "skills"
+    / "migration"
+    / "openclaw-migration"
+    / "scripts"
+    / "openclaw_to_hermes.py"
+)
+
+
+def _find_migration_script() -> Path | None:
+    """Find the openclaw_to_hermes.py script in known locations."""
+    for candidate in [_OPENCLAW_SCRIPT, _OPENCLAW_SCRIPT_INSTALLED]:
+        if candidate.exists():
+            return candidate
+    return None
+
+
+def _load_migration_module(script_path: Path):
+    """Dynamically load the migration script as a module."""
+    spec = importlib.util.spec_from_file_location("openclaw_to_hermes", script_path)
+    if spec is None or spec.loader is None:
+        return None
+    mod = importlib.util.module_from_spec(spec)
+    # Register in sys.modules so @dataclass can resolve the module
+    # (Python 3.11+ requires this for dynamically loaded modules)
+    sys.modules[spec.name] = mod
+    try:
+        spec.loader.exec_module(mod)
+    except Exception:
+        sys.modules.pop(spec.name, None)
+        raise
+    return mod
+
+
+def claw_command(args):
+    """Route hermes claw subcommands."""
+    action = getattr(args, "claw_action", None)
+
+    if action == "migrate":
+        _cmd_migrate(args)
+    else:
+        print("Usage: hermes claw migrate [options]")
+        print()
+        print("Commands:")
+        print("  migrate          Migrate settings from OpenClaw to Hermes")
+        print()
+        print("Run 'hermes claw migrate --help' for migration options.")
+
+
+def _cmd_migrate(args):
+    """Run the OpenClaw → Hermes migration."""
+    source_dir = Path(getattr(args, "source", None) or Path.home() / ".openclaw")
+    dry_run = getattr(args, "dry_run", False)
+    preset = getattr(args, "preset", "full")
+    overwrite = getattr(args, "overwrite", False)
+    migrate_secrets = getattr(args, "migrate_secrets", False)
+    workspace_target = getattr(args, "workspace_target", None)
+    skill_conflict = getattr(args, "skill_conflict", "skip")
+
+    # If using the "full" preset, secrets are included by default
+    if preset == "full":
+        migrate_secrets = True
+
+    print()
+    print(
+        color(
+            "┌─────────────────────────────────────────────────────────┐",
+            Colors.MAGENTA,
+        )
+    )
+    print(
+        color(
+            "│          ⚕ Hermes — OpenClaw Migration                 │",
+            Colors.MAGENTA,
+        )
+    )
+    print(
+        color(
+            "└─────────────────────────────────────────────────────────┘",
+            Colors.MAGENTA,
+        )
+    )
+
+    # Check source directory
+    if not source_dir.is_dir():
+        print()
+        print_error(f"OpenClaw directory not found: {source_dir}")
+        print_info("Make sure your OpenClaw installation is at the expected path.")
+        print_info(f"You can specify a custom path: hermes claw migrate --source /path/to/.openclaw")
+        return
+
+    # Find the migration script
+    script_path = _find_migration_script()
+    if not script_path:
+        print()
+        print_error("Migration script not found.")
+        print_info("Expected at one of:")
+        print_info(f"  {_OPENCLAW_SCRIPT}")
+        print_info(f"  {_OPENCLAW_SCRIPT_INSTALLED}")
+        print_info("Make sure the openclaw-migration skill is installed.")
+        return
+
+    # Show what we're doing
+    hermes_home = get_hermes_home()
+    print()
+    print_header("Migration Settings")
+    print_info(f"Source:      {source_dir}")
+    print_info(f"Target:      {hermes_home}")
+    print_info(f"Preset:      {preset}")
+    print_info(f"Mode:        {'dry run (preview only)' if dry_run else 'execute'}")
+    print_info(f"Overwrite:   {'yes' if overwrite else 'no (skip conflicts)'}")
+    print_info(f"Secrets:     {'yes (allowlisted only)' if migrate_secrets else 'no'}")
+    if skill_conflict != "skip":
+        print_info(f"Skill conflicts: {skill_conflict}")
+    if workspace_target:
+        print_info(f"Workspace:   {workspace_target}")
+    print()
+
+    # For execute mode (non-dry-run), confirm unless --yes was passed
+    if not dry_run and not getattr(args, "yes", False):
+        if not prompt_yes_no("Proceed with migration?", default=True):
+            print_info("Migration cancelled.")
+            return
+
+    # Ensure config.yaml exists before migration tries to read it
+    config_path = get_config_path()
+    if not config_path.exists():
+        save_config(load_config())
+
+    # Load and run the migration
+    try:
+        mod = _load_migration_module(script_path)
+        if mod is None:
+            print_error("Could not load migration script.")
+            return
+
+        selected = mod.resolve_selected_options(None, None, preset=preset)
+        ws_target = Path(workspace_target).resolve() if workspace_target else None
+
+        migrator = mod.Migrator(
+            source_root=source_dir.resolve(),
+            target_root=hermes_home.resolve(),
+            execute=not dry_run,
+            workspace_target=ws_target,
+            overwrite=overwrite,
+            migrate_secrets=migrate_secrets,
+            output_dir=None,
+            selected_options=selected,
+            preset_name=preset,
+            skill_conflict_mode=skill_conflict,
+        )
+        report = migrator.migrate()
+    except Exception as e:
+        print()
+        print_error(f"Migration failed: {e}")
+        logger.debug("OpenClaw migration error", exc_info=True)
+        return
+
+    # Print results
+    _print_migration_report(report, dry_run)
+
+
+def _print_migration_report(report: dict, dry_run: bool):
+    """Print a formatted migration report."""
+    summary = report.get("summary", {})
+    migrated = summary.get("migrated", 0)
+    skipped = summary.get("skipped", 0)
+    conflicts = summary.get("conflict", 0)
+    errors = summary.get("error", 0)
+    total = migrated + skipped + conflicts + errors
+
+    print()
+    if dry_run:
+        print_header("Dry Run Results")
+        print_info("No files were modified. This is a preview of what would happen.")
+    else:
+        print_header("Migration Results")
+
+    print()
+
+    # Detailed items
+    items = report.get("items", [])
+    if items:
+        # Group by status
+        migrated_items = [i for i in items if i.get("status") == "migrated"]
+        skipped_items = [i for i in items if i.get("status") == "skipped"]
+        conflict_items = [i for i in items if i.get("status") == "conflict"]
+        error_items = [i for i in items if i.get("status") == "error"]
+
+        if migrated_items:
+            label = "Would migrate" if dry_run else "Migrated"
+            print(color(f"  ✓ {label}:", Colors.GREEN))
+            for item in migrated_items:
+                kind = item.get("kind", "unknown")
+                dest = item.get("destination", "")
+                if dest:
+                    dest_short = str(dest).replace(str(Path.home()), "~")
+                    print(f"      {kind:<22s} → {dest_short}")
+                else:
+                    print(f"      {kind}")
+            print()
+
+        if conflict_items:
+            print(color(f"  ⚠ Conflicts (skipped — use --overwrite to force):", Colors.YELLOW))
+            for item in conflict_items:
+                kind = item.get("kind", "unknown")
+                reason = item.get("reason", "already exists")
+                print(f"      {kind:<22s}  {reason}")
+            print()
+
+        if skipped_items:
+            print(color(f"  ─ Skipped:", Colors.DIM))
+            for item in skipped_items:
+                kind = item.get("kind", "unknown")
+                reason = item.get("reason", "")
+                print(f"      {kind:<22s}  {reason}")
+            print()
+
+        if error_items:
+            print(color(f"  ✗ Errors:", Colors.RED))
+            for item in error_items:
+                kind = item.get("kind", "unknown")
+                reason = item.get("reason", "unknown error")
+                print(f"      {kind:<22s}  {reason}")
+            print()
+
+    # Summary line
+    parts = []
+    if migrated:
+        action = "would migrate" if dry_run else "migrated"
+        parts.append(f"{migrated} {action}")
+    if conflicts:
+        parts.append(f"{conflicts} conflict(s)")
+    if skipped:
+        parts.append(f"{skipped} skipped")
+    if errors:
+        parts.append(f"{errors} error(s)")
+
+    if parts:
+        print_info(f"Summary: {', '.join(parts)}")
+    else:
+        print_info("Nothing to migrate.")
+
+    # Output directory
+    output_dir = report.get("output_dir")
+    if output_dir:
+        print_info(f"Full report saved to: {output_dir}")
+
+    if dry_run:
+        print()
+        print_info("To execute the migration, run without --dry-run:")
+        print_info(f"  hermes claw migrate --preset {report.get('preset', 'full')}")
+    elif migrated:
+        print()
+        print_success("Migration complete!")

hermes_cli/clipboard.py

@@ -254,6 +254,7 @@ def _wayland_save(dest: Path) -> bool:
             )
 
         if not dest.exists() or dest.stat().st_size == 0:
+            dest.unlink(missing_ok=True)
             return False
 
         # BMP needs conversion to PNG (common in WSLg where only BMP
@@ -292,9 +293,12 @@ def _convert_to_png(path: Path) -> bool:
             ["convert", str(tmp), "png:" + str(path)],
             capture_output=True, timeout=5,
         )
-        tmp.unlink(missing_ok=True)
         if r.returncode == 0 and path.exists() and path.stat().st_size > 0:
+            tmp.unlink(missing_ok=True)
             return True
+        else:
+            # Convert failed — restore the original file
+            tmp.rename(path)
     except FileNotFoundError:
         logger.debug("ImageMagick not installed — cannot convert BMP to PNG")
         if tmp.exists() and not path.exists():

hermes_cli/codex_models.py

@@ -47,7 +47,7 @@ def _fetch_models_from_api(access_token: str) -> List[str]:
         if item.get("supported_in_api") is False:
             continue
         visibility = item.get("visibility", "")
-        if isinstance(visibility, str) and visibility.strip().lower() == "hidden":
+        if isinstance(visibility, str) and visibility.strip().lower() in ("hide", "hidden"):
             continue
         priority = item.get("priority")
         rank = int(priority) if isinstance(priority, (int, float)) else 10_000
@@ -97,7 +97,7 @@ def _read_cache_models(codex_home: Path) -> List[str]:
             if item.get("supported_in_api") is False:
                 continue
             visibility = item.get("visibility")
-            if isinstance(visibility, str) and visibility.strip().lower() == "hidden":
+            if isinstance(visibility, str) and visibility.strip().lower() in ("hide", "hidden"):
                 continue
             priority = item.get("priority")
             rank = int(priority) if isinstance(priority, (int, float)) else 10_000

hermes_cli/commands.py

@@ -13,35 +13,55 @@ from typing import Any
 from prompt_toolkit.completion import Completer, Completion
 
 
-COMMANDS = {
-    "/help": "Show this help message",
-    "/tools": "List available tools",
-    "/toolsets": "List available toolsets",
-    "/model": "Show or change the current model",
-    "/provider": "Show available providers and current provider",
-    "/prompt": "View/set custom system prompt",
-    "/personality": "Set a predefined personality",
-    "/clear": "Clear screen and reset conversation (fresh start)",
-    "/history": "Show conversation history",
-    "/new": "Start a new conversation (reset history)",
-    "/reset": "Reset conversation only (keep screen)",
-    "/retry": "Retry the last message (resend to agent)",
-    "/undo": "Remove the last user/assistant exchange",
-    "/save": "Save the current conversation",
-    "/config": "Show current configuration",
-    "/cron": "Manage scheduled tasks (list, add, remove)",
-    "/skills": "Search, install, inspect, or manage skills from online registries",
-    "/platforms": "Show gateway/messaging platform status",
-    "/verbose": "Cycle tool progress display: off → new → all → verbose",
-    "/compress": "Manually compress conversation context (flush memories + summarize)",
-    "/title": "Set a title for the current session (usage: /title My Session Name)",
-    "/usage": "Show token usage for the current session",
-    "/insights": "Show usage insights and analytics (last 30 days)",
-    "/paste": "Check clipboard for an image and attach it",
-    "/reload-mcp": "Reload MCP servers from config.yaml",
-    "/quit": "Exit the CLI (also: /exit, /q)",
+# Commands organized by category for better help display
+COMMANDS_BY_CATEGORY = {
+    "Session": {
+        "/new": "Start a new conversation (reset history)",
+        "/reset": "Reset conversation only (keep screen)",
+        "/clear": "Clear screen and reset conversation (fresh start)",
+        "/history": "Show conversation history",
+        "/save": "Save the current conversation",
+        "/retry": "Retry the last message (resend to agent)",
+        "/undo": "Remove the last user/assistant exchange",
+        "/title": "Set a title for the current session (usage: /title My Session Name)",
+        "/compress": "Manually compress conversation context (flush memories + summarize)",
+        "/rollback": "List or restore filesystem checkpoints (usage: /rollback [number])",
+        "/background": "Run a prompt in the background (usage: /background <prompt>)",
+    },
+    "Configuration": {
+        "/config": "Show current configuration",
+        "/model": "Show or change the current model",
+        "/provider": "Show available providers and current provider",
+        "/prompt": "View/set custom system prompt",
+        "/personality": "Set a predefined personality",
+        "/verbose": "Cycle tool progress display: off → new → all → verbose",
+        "/reasoning": "Manage reasoning effort and display (usage: /reasoning [level|show|hide])",
+        "/skin": "Show or change the display skin/theme",
+    },
+    "Tools & Skills": {
+        "/tools": "List available tools",
+        "/toolsets": "List available toolsets",
+        "/skills": "Search, install, inspect, or manage skills from online registries",
+        "/cron": "Manage scheduled tasks (list, add, remove)",
+        "/reload-mcp": "Reload MCP servers from config.yaml",
+    },
+    "Info": {
+        "/help": "Show this help message",
+        "/usage": "Show token usage for the current session",
+        "/insights": "Show usage insights and analytics (last 30 days)",
+        "/platforms": "Show gateway/messaging platform status",
+        "/paste": "Check clipboard for an image and attach it",
+    },
+    "Exit": {
+        "/quit": "Exit the CLI (also: /exit, /q)",
+    },
 }
 
+# Flat dict for backwards compatibility and autocomplete
+COMMANDS = {}
+for category_commands in COMMANDS_BY_CATEGORY.values():
+    COMMANDS.update(category_commands)
+
 
 class SlashCommandCompleter(Completer):
     """Autocomplete for built-in slash commands and optional skill commands."""

hermes_cli/config.py

@@ -14,12 +14,17 @@ This module provides:
 
 import os
 import platform
+import re
+import stat
 import sys
 import subprocess
+import sys
+import tempfile
 from pathlib import Path
 from typing import Dict, Any, Optional, List, Tuple
 
 _IS_WINDOWS = platform.system() == "Windows"
+_ENV_VAR_NAME_RE = re.compile(r"^[A-Za-z_][A-Za-z0-9_]*$")
 
 import yaml
 
@@ -46,13 +51,32 @@ def get_project_root() -> Path:
     """Get the project installation directory."""
     return Path(__file__).parent.parent.resolve()
 
+def _secure_dir(path):
+    """Set directory to owner-only access (0700). No-op on Windows."""
+    try:
+        os.chmod(path, 0o700)
+    except (OSError, NotImplementedError):
+        pass
+
+
+def _secure_file(path):
+    """Set file to owner-only read/write (0600). No-op on Windows."""
+    try:
+        if os.path.exists(str(path)):
+            os.chmod(path, 0o600)
+    except (OSError, NotImplementedError):
+        pass
+
+
 def ensure_hermes_home():
-    """Ensure ~/.hermes directory structure exists."""
+    """Ensure ~/.hermes directory structure exists with secure permissions."""
     home = get_hermes_home()
-    (home / "cron").mkdir(parents=True, exist_ok=True)
-    (home / "sessions").mkdir(parents=True, exist_ok=True)
-    (home / "logs").mkdir(parents=True, exist_ok=True)
-    (home / "memories").mkdir(parents=True, exist_ok=True)
+    home.mkdir(parents=True, exist_ok=True)
+    _secure_dir(home)
+    for subdir in ("cron", "sessions", "logs", "memories"):
+        d = home / subdir
+        d.mkdir(parents=True, exist_ok=True)
+        _secure_dir(d)
 
 
 # =============================================================================
@@ -62,7 +86,9 @@ def ensure_hermes_home():
 DEFAULT_CONFIG = {
     "model": "anthropic/claude-opus-4.6",
     "toolsets": ["hermes-cli"],
-    "max_turns": 100,
+    "agent": {
+        "max_turns": 90,
+    },
     
     "terminal": {
         "backend": "local",
@@ -87,32 +113,66 @@ DEFAULT_CONFIG = {
         "inactivity_timeout": 120,
         "record_sessions": False,  # Auto-record browser sessions as WebM videos
     },
+
+    # Filesystem checkpoints — automatic snapshots before destructive file ops.
+    # When enabled, the agent takes a snapshot of the working directory once per
+    # conversation turn (on first write_file/patch call).  Use /rollback to restore.
+    "checkpoints": {
+        "enabled": False,
+        "max_snapshots": 50,  # Max checkpoints to keep per directory
+    },
     
     "compression": {
         "enabled": True,
-        "threshold": 0.85,
+        "threshold": 0.50,
         "summary_model": "google/gemini-3-flash-preview",
         "summary_provider": "auto",
     },
     
-    # Auxiliary model overrides (advanced).  By default Hermes auto-selects
-    # the provider and model for each side task.  Set these to override.
+    # Auxiliary model config — provider:model for each side task.
+    # Format: provider is the provider name, model is the model slug.
+    # "auto" for provider = auto-detect best available provider.
+    # Empty model = use provider's default auxiliary model.
+    # All tasks fall back to openrouter:google/gemini-3-flash-preview if
+    # the configured provider is unavailable.
     "auxiliary": {
         "vision": {
-            "provider": "auto",    # auto | openrouter | nous | main
+            "provider": "auto",    # auto | openrouter | nous | codex | custom
             "model": "",           # e.g. "google/gemini-2.5-flash", "gpt-4o"
         },
         "web_extract": {
             "provider": "auto",
             "model": "",
         },
+        "compression": {
+            "provider": "auto",
+            "model": "",
+        },
+        "session_search": {
+            "provider": "auto",
+            "model": "",
+        },
+        "skills_hub": {
+            "provider": "auto",
+            "model": "",
+        },
+        "mcp": {
+            "provider": "auto",
+            "model": "",
+        },
+        "flush_memories": {
+            "provider": "auto",
+            "model": "",
+        },
     },
     
     "display": {
         "compact": False,
         "personality": "kawaii",
-        "resume_display": "full",  # "full" (show previous messages) | "minimal" (one-liner only)
-        "bell_on_complete": False,  # Play terminal bell (\a) when agent finishes a response
+        "resume_display": "full",
+        "bell_on_complete": False,
+        "show_reasoning": False,
+        "skin": "default",
     },
     
     # Text-to-speech configuration
@@ -151,7 +211,16 @@ DEFAULT_CONFIG = {
         "memory_char_limit": 2200,   # ~800 tokens at 2.75 chars/token
         "user_char_limit": 1375,     # ~500 tokens at 2.75 chars/token
     },
-    
+
+    # Subagent delegation — override the provider:model used by delegate_task
+    # so child agents can run on a different (cheaper/faster) provider and model.
+    # Uses the same runtime provider resolution as CLI/gateway startup, so all
+    # configured providers (OpenRouter, Nous, Z.ai, Kimi, etc.) are supported.
+    "delegation": {
+        "model": "",       # e.g. "google/gemini-3-flash-preview" (empty = inherit parent model)
+        "provider": "",    # e.g. "openrouter" (empty = inherit parent provider + credentials)
+    },
+
     # Ephemeral prefill messages file — JSON list of {role, content} dicts
     # injected at the start of every API call for few-shot priming.
     # Never saved to sessions, logs, or trajectories.
@@ -166,11 +235,23 @@ DEFAULT_CONFIG = {
     # Empty string means use server-local time.
     "timezone": "",
 
+    # Discord platform settings (gateway mode)
+    "discord": {
+        "require_mention": True,       # Require @mention to respond in server channels
+        "free_response_channels": "",  # Comma-separated channel IDs where bot responds without mention
+    },
+
     # Permanently allowed dangerous command patterns (added via "always" approval)
     "command_allowlist": [],
+    # User-defined quick commands that bypass the agent loop (type: exec only)
+    "quick_commands": {},
+    # Custom personalities — add your own entries here
+    # Supports string format: {"name": "system prompt"}
+    # Or dict format: {"name": {"description": "...", "system_prompt": "...", "tone": "...", "style": "..."}}
+    "personalities": {},
 
     # Config schema version - bump this when adding new required fields
-    "_config_version": 5,
+    "_config_version": 7,
 }
 
 # =============================================================================
@@ -195,6 +276,14 @@ REQUIRED_ENV_VARS = {}
 # Optional environment variables that enhance functionality
 OPTIONAL_ENV_VARS = {
     # ── Provider (handled in provider selection, not shown in checklists) ──
+    "NOUS_BASE_URL": {
+        "description": "Nous Portal base URL override",
+        "prompt": "Nous Portal base URL (leave empty for default)",
+        "url": None,
+        "password": False,
+        "category": "provider",
+        "advanced": True,
+    },
     "OPENROUTER_API_KEY": {
         "description": "OpenRouter API key (for vision, web scraping helpers, and MoA)",
         "prompt": "OpenRouter API key",
@@ -370,7 +459,7 @@ OPTIONAL_ENV_VARS = {
         "description": "Honcho API key for AI-native persistent memory",
         "prompt": "Honcho API key",
         "url": "https://app.honcho.dev",
-        "tools": ["query_user_context"],
+        "tools": ["honcho_context"],
         "password": True,
         "category": "tool",
     },
@@ -748,6 +837,23 @@ def _deep_merge(base: dict, override: dict) -> dict:
     return result
 
 
+def _normalize_max_turns_config(config: Dict[str, Any]) -> Dict[str, Any]:
+    """Normalize legacy root-level max_turns into agent.max_turns."""
+    config = dict(config)
+    agent_config = dict(config.get("agent") or {})
+
+    if "max_turns" in config and "max_turns" not in agent_config:
+        agent_config["max_turns"] = config["max_turns"]
+
+    if "max_turns" not in agent_config:
+        agent_config["max_turns"] = DEFAULT_CONFIG["agent"]["max_turns"]
+
+    config["agent"] = agent_config
+    config.pop("max_turns", None)
+    return config
+
+
+
 def load_config() -> Dict[str, Any]:
     """Load configuration from ~/.hermes/config.yaml."""
     import copy
@@ -757,14 +863,51 @@ def load_config() -> Dict[str, Any]:
     
     if config_path.exists():
         try:
-            with open(config_path) as f:
+            with open(config_path, encoding="utf-8") as f:
                 user_config = yaml.safe_load(f) or {}
-            
+
+            if "max_turns" in user_config:
+                agent_user_config = dict(user_config.get("agent") or {})
+                if agent_user_config.get("max_turns") is None:
+                    agent_user_config["max_turns"] = user_config["max_turns"]
+                user_config["agent"] = agent_user_config
+                user_config.pop("max_turns", None)
+
             config = _deep_merge(config, user_config)
         except Exception as e:
             print(f"Warning: Failed to load config: {e}")
     
-    return config
+    return _normalize_max_turns_config(config)
+
+
+_COMMENTED_SECTIONS = """
+# ── Security ──────────────────────────────────────────────────────────
+# API keys, tokens, and passwords are redacted from tool output by default.
+# Set to false to see full values (useful for debugging auth issues).
+#
+# security:
+#   redact_secrets: false
+
+# ── Fallback Model ────────────────────────────────────────────────────
+# Automatic provider failover when primary is unavailable.
+# Uncomment and configure to enable. Triggers on rate limits (429),
+# overload (529), service errors (503), or connection failures.
+#
+# Supported providers:
+#   openrouter   (OPENROUTER_API_KEY)  — routes to any model
+#   openai-codex (OAuth — hermes login) — OpenAI Codex
+#   nous         (OAuth — hermes login) — Nous Portal
+#   zai          (ZAI_API_KEY)         — Z.AI / GLM
+#   kimi-coding  (KIMI_API_KEY)        — Kimi / Moonshot
+#   minimax      (MINIMAX_API_KEY)     — MiniMax
+#   minimax-cn   (MINIMAX_CN_API_KEY)  — MiniMax (China)
+#
+# For custom OpenAI-compatible endpoints, add base_url and api_key_env.
+#
+# fallback_model:
+#   provider: openrouter
+#   model: anthropic/claude-sonnet-4
+"""
 
 
 _COMMENTED_SECTIONS = """
@@ -799,23 +942,28 @@ _COMMENTED_SECTIONS = """
 
 def save_config(config: Dict[str, Any]):
     """Save configuration to ~/.hermes/config.yaml."""
+    from utils import atomic_yaml_write
+
     ensure_hermes_home()
     config_path = get_config_path()
-    
-    with open(config_path, 'w') as f:
-        yaml.dump(config, f, default_flow_style=False, sort_keys=False)
-        # Append commented-out sections for features that are off by default
-        # or only relevant when explicitly configured. Skip sections the
-        # user has already uncommented and configured.
-        sections = []
-        sec = config.get("security", {})
-        if not sec or sec.get("redact_secrets") is None:
-            sections.append("security")
-        fb = config.get("fallback_model", {})
-        if not fb or not (fb.get("provider") and fb.get("model")):
-            sections.append("fallback")
-        if sections:
-            f.write(_COMMENTED_SECTIONS)
+    normalized = _normalize_max_turns_config(config)
+
+    # Build optional commented-out sections for features that are off by
+    # default or only relevant when explicitly configured.
+    sections = []
+    sec = normalized.get("security", {})
+    if not sec or sec.get("redact_secrets") is None:
+        sections.append("security")
+    fb = normalized.get("fallback_model", {})
+    if not fb or not (fb.get("provider") and fb.get("model")):
+        sections.append("fallback")
+
+    atomic_yaml_write(
+        config_path,
+        normalized,
+        extra_content=_COMMENTED_SECTIONS if sections else None,
+    )
+    _secure_file(config_path)
 
 
 def load_env() -> Dict[str, str]:
@@ -839,6 +987,9 @@ def load_env() -> Dict[str, str]:
 
 def save_env_value(key: str, value: str):
     """Save or update a value in ~/.hermes/.env."""
+    if not _ENV_VAR_NAME_RE.match(key):
+        raise ValueError(f"Invalid environment variable name: {key!r}")
+    value = value.replace("\n", "").replace("\r", "")
     ensure_hermes_home()
     env_path = get_env_path()
     
@@ -866,8 +1017,53 @@ def save_env_value(key: str, value: str):
             lines[-1] += "\n"
         lines.append(f"{key}={value}\n")
     
-    with open(env_path, 'w', **write_kw) as f:
-        f.writelines(lines)
+    fd, tmp_path = tempfile.mkstemp(dir=str(env_path.parent), suffix='.tmp', prefix='.env_')
+    try:
+        with os.fdopen(fd, 'w', **write_kw) as f:
+            f.writelines(lines)
+            f.flush()
+            os.fsync(f.fileno())
+        os.replace(tmp_path, env_path)
+    except BaseException:
+        try:
+            os.unlink(tmp_path)
+        except OSError:
+            pass
+        raise
+    _secure_file(env_path)
+
+    os.environ[key] = value
+
+    # Restrict .env permissions to owner-only (contains API keys)
+    if not _IS_WINDOWS:
+        try:
+            os.chmod(env_path, stat.S_IRUSR | stat.S_IWUSR)
+        except OSError:
+            pass
+
+
+def save_anthropic_oauth_token(value: str, save_fn=None):
+    """Persist an Anthropic OAuth/setup token and clear the API-key slot."""
+    writer = save_fn or save_env_value
+    writer("ANTHROPIC_TOKEN", value)
+    writer("ANTHROPIC_API_KEY", "")
+
+
+def save_anthropic_api_key(value: str, save_fn=None):
+    """Persist an Anthropic API key and clear the OAuth/setup-token slot."""
+    writer = save_fn or save_env_value
+    writer("ANTHROPIC_API_KEY", value)
+    writer("ANTHROPIC_TOKEN", "")
+
+
+def save_env_value_secure(key: str, value: str) -> Dict[str, Any]:
+    save_env_value(key, value)
+    return {
+        "success": True,
+        "stored_as": key,
+        "validated": False,
+    }
+
 
 
 def get_env_value(key: str) -> Optional[str]:
@@ -897,7 +1093,6 @@ def redact_key(key: str) -> str:
 def show_config():
     """Display current configuration."""
     config = load_config()
-    env_vars = load_env()
     
     print()
     print(color("┌─────────────────────────────────────────────────────────┐", Colors.CYAN))
@@ -917,7 +1112,6 @@ def show_config():
     
     keys = [
         ("OPENROUTER_API_KEY", "OpenRouter"),
-        ("ANTHROPIC_API_KEY", "Anthropic"),
         ("VOICE_TOOLS_OPENAI_KEY", "OpenAI (STT/TTS)"),
         ("FIRECRAWL_API_KEY", "Firecrawl"),
         ("BROWSERBASE_API_KEY", "Browserbase"),
@@ -927,14 +1121,24 @@ def show_config():
     for env_key, name in keys:
         value = get_env_value(env_key)
         print(f"  {name:<14} {redact_key(value)}")
+    anthropic_value = get_env_value("ANTHROPIC_TOKEN") or get_env_value("ANTHROPIC_API_KEY")
+    print(f"  {'Anthropic':<14} {redact_key(anthropic_value)}")
     
     # Model settings
     print()
     print(color("◆ Model", Colors.CYAN, Colors.BOLD))
     print(f"  Model:        {config.get('model', 'not set')}")
-    print(f"  Max turns:    {config.get('max_turns', 100)}")
+    print(f"  Max turns:    {config.get('agent', {}).get('max_turns', DEFAULT_CONFIG['agent']['max_turns'])}")
     print(f"  Toolsets:     {', '.join(config.get('toolsets', ['all']))}")
     
+    # Display
+    print()
+    print(color("◆ Display", Colors.CYAN, Colors.BOLD))
+    display = config.get('display', {})
+    print(f"  Personality:  {display.get('personality', 'kawaii')}")
+    print(f"  Reasoning:    {'on' if display.get('show_reasoning', False) else 'off'}")
+    print(f"  Bell:         {'on' if display.get('bell_on_complete', False) else 'off'}")
+
     # Terminal
     print()
     print(color("◆ Terminal", Colors.CYAN, Colors.BOLD))
@@ -977,7 +1181,7 @@ def show_config():
     enabled = compression.get('enabled', True)
     print(f"  Enabled:      {'yes' if enabled else 'no'}")
     if enabled:
-        print(f"  Threshold:    {compression.get('threshold', 0.85) * 100:.0f}%")
+        print(f"  Threshold:    {compression.get('threshold', 0.50) * 100:.0f}%")
         print(f"  Model:        {compression.get('summary_model', 'google/gemini-3-flash-preview')}")
         comp_provider = compression.get('summary_provider', 'auto')
         if comp_provider != 'auto':
@@ -1044,7 +1248,7 @@ def edit_config():
                 break
     
     if not editor:
-        print(f"No editor found. Config file is at:")
+        print("No editor found. Config file is at:")
         print(f"  {config_path}")
         return
     
@@ -1077,7 +1281,7 @@ def set_config_value(key: str, value: str):
     user_config = {}
     if config_path.exists():
         try:
-            with open(config_path) as f:
+            with open(config_path, encoding="utf-8") as f:
                 user_config = yaml.safe_load(f) or {}
         except Exception:
             user_config = {}
@@ -1105,7 +1309,7 @@ def set_config_value(key: str, value: str):
     
     # Write only user config back (not the full merged defaults)
     ensure_hermes_home()
-    with open(config_path, 'w') as f:
+    with open(config_path, 'w', encoding="utf-8") as f:
         yaml.dump(user_config, f, default_flow_style=False, sort_keys=False)
     
     # Keep .env in sync for keys that terminal_tool reads directly from env vars.
@@ -1249,7 +1453,7 @@ def config_command(args):
         if missing_config:
             print()
             print(color(f"  {len(missing_config)} new config option(s) available", Colors.YELLOW))
-            print(f"    Run 'hermes config migrate' to add them")
+            print("    Run 'hermes config migrate' to add them")
         
         print()
     

hermes_cli/curses_ui.py

@@ -0,0 +1,140 @@
+"""Shared curses-based UI components for Hermes CLI.
+
+Used by `hermes tools` and `hermes skills` for interactive checklists.
+Provides a curses multi-select with keyboard navigation, plus a
+text-based numbered fallback for terminals without curses support.
+"""
+from typing import List, Set
+
+from hermes_cli.colors import Colors, color
+
+
+def curses_checklist(
+    title: str,
+    items: List[str],
+    selected: Set[int],
+    *,
+    cancel_returns: Set[int] | None = None,
+) -> Set[int]:
+    """Curses multi-select checklist. Returns set of selected indices.
+
+    Args:
+        title: Header line displayed above the checklist.
+        items: Display labels for each row.
+        selected: Indices that start checked (pre-selected).
+        cancel_returns: Returned on ESC/q. Defaults to the original *selected*.
+    """
+    if cancel_returns is None:
+        cancel_returns = set(selected)
+
+    try:
+        import curses
+        chosen = set(selected)
+        result_holder: list = [None]
+
+        def _draw(stdscr):
+            curses.curs_set(0)
+            if curses.has_colors():
+                curses.start_color()
+                curses.use_default_colors()
+                curses.init_pair(1, curses.COLOR_GREEN, -1)
+                curses.init_pair(2, curses.COLOR_YELLOW, -1)
+                curses.init_pair(3, 8, -1)  # dim gray
+            cursor = 0
+            scroll_offset = 0
+
+            while True:
+                stdscr.clear()
+                max_y, max_x = stdscr.getmaxyx()
+
+                # Header
+                try:
+                    hattr = curses.A_BOLD
+                    if curses.has_colors():
+                        hattr |= curses.color_pair(2)
+                    stdscr.addnstr(0, 0, title, max_x - 1, hattr)
+                    stdscr.addnstr(
+                        1, 0,
+                        "  ↑↓ navigate  SPACE toggle  ENTER confirm  ESC cancel",
+                        max_x - 1, curses.A_DIM,
+                    )
+                except curses.error:
+                    pass
+
+                # Scrollable item list
+                visible_rows = max_y - 3
+                if cursor < scroll_offset:
+                    scroll_offset = cursor
+                elif cursor >= scroll_offset + visible_rows:
+                    scroll_offset = cursor - visible_rows + 1
+
+                for draw_i, i in enumerate(
+                    range(scroll_offset, min(len(items), scroll_offset + visible_rows))
+                ):
+                    y = draw_i + 3
+                    if y >= max_y - 1:
+                        break
+                    check = "✓" if i in chosen else " "
+                    arrow = "→" if i == cursor else " "
+                    line = f" {arrow} [{check}] {items[i]}"
+                    attr = curses.A_NORMAL
+                    if i == cursor:
+                        attr = curses.A_BOLD
+                        if curses.has_colors():
+                            attr |= curses.color_pair(1)
+                    try:
+                        stdscr.addnstr(y, 0, line, max_x - 1, attr)
+                    except curses.error:
+                        pass
+
+                stdscr.refresh()
+                key = stdscr.getch()
+
+                if key in (curses.KEY_UP, ord("k")):
+                    cursor = (cursor - 1) % len(items)
+                elif key in (curses.KEY_DOWN, ord("j")):
+                    cursor = (cursor + 1) % len(items)
+                elif key == ord(" "):
+                    chosen.symmetric_difference_update({cursor})
+                elif key in (curses.KEY_ENTER, 10, 13):
+                    result_holder[0] = set(chosen)
+                    return
+                elif key in (27, ord("q")):
+                    result_holder[0] = cancel_returns
+                    return
+
+        curses.wrapper(_draw)
+        return result_holder[0] if result_holder[0] is not None else cancel_returns
+
+    except Exception:
+        return _numbered_fallback(title, items, selected, cancel_returns)
+
+
+def _numbered_fallback(
+    title: str,
+    items: List[str],
+    selected: Set[int],
+    cancel_returns: Set[int],
+) -> Set[int]:
+    """Text-based toggle fallback for terminals without curses."""
+    chosen = set(selected)
+    print(color(f"\n  {title}", Colors.YELLOW))
+    print(color("  Toggle by number, Enter to confirm.\n", Colors.DIM))
+
+    while True:
+        for i, label in enumerate(items):
+            marker = color("[✓]", Colors.GREEN) if i in chosen else "[ ]"
+            print(f"  {marker} {i + 1:>2}. {label}")
+        print()
+        try:
+            val = input(color("  Toggle # (or Enter to confirm): ", Colors.DIM)).strip()
+            if not val:
+                break
+            idx = int(val) - 1
+            if 0 <= idx < len(items):
+                chosen.symmetric_difference_update({idx})
+        except (ValueError, KeyboardInterrupt, EOFError):
+            return cancel_returns
+        print()
+
+    return chosen

hermes_cli/doctor.py

@@ -38,6 +38,7 @@ _PROVIDER_ENV_HINTS = (
     "OPENROUTER_API_KEY",
     "OPENAI_API_KEY",
     "ANTHROPIC_API_KEY",
+    "ANTHROPIC_TOKEN",
     "OPENAI_BASE_URL",
     "GLM_API_KEY",
     "ZAI_API_KEY",
@@ -53,6 +54,33 @@ def _has_provider_env_config(content: str) -> bool:
     return any(key in content for key in _PROVIDER_ENV_HINTS)
 
 
+def _honcho_is_configured_for_doctor() -> bool:
+    """Return True when Honcho is configured, even if this process has no active session."""
+    try:
+        from honcho_integration.client import HonchoClientConfig
+
+        cfg = HonchoClientConfig.from_global_config()
+        return bool(cfg.enabled and cfg.api_key)
+    except Exception:
+        return False
+
+
+def _apply_doctor_tool_availability_overrides(available: list[str], unavailable: list[dict]) -> tuple[list[str], list[dict]]:
+    """Adjust runtime-gated tool availability for doctor diagnostics."""
+    if not _honcho_is_configured_for_doctor():
+        return available, unavailable
+
+    updated_available = list(available)
+    updated_unavailable = []
+    for item in unavailable:
+        if item.get("name") == "honcho":
+            if "honcho" not in updated_available:
+                updated_available.append("honcho")
+            continue
+        updated_unavailable.append(item)
+    return updated_available, updated_unavailable
+
+
 def check_ok(text: str, detail: str = ""):
     print(f"  {color('✓', Colors.GREEN)} {text}" + (f" {color(detail, Colors.DIM)}" if detail else ""))
 
@@ -466,17 +494,22 @@ def run_doctor(args):
     else:
         check_warn("OpenRouter API", "(not configured)")
     
-    anthropic_key = os.getenv("ANTHROPIC_API_KEY")
+    anthropic_key = os.getenv("ANTHROPIC_TOKEN") or os.getenv("ANTHROPIC_API_KEY")
     if anthropic_key:
         print("  Checking Anthropic API...", end="", flush=True)
         try:
             import httpx
+            from agent.anthropic_adapter import _is_oauth_token, _COMMON_BETAS, _OAUTH_ONLY_BETAS
+
+            headers = {"anthropic-version": "2023-06-01"}
+            if _is_oauth_token(anthropic_key):
+                headers["Authorization"] = f"Bearer {anthropic_key}"
+                headers["anthropic-beta"] = ",".join(_COMMON_BETAS + _OAUTH_ONLY_BETAS)
+            else:
+                headers["x-api-key"] = anthropic_key
             response = httpx.get(
                 "https://api.anthropic.com/v1/models",
-                headers={
-                    "x-api-key": anthropic_key,
-                    "anthropic-version": "2023-06-01"
-                },
+                headers=headers,
                 timeout=10
             )
             if response.status_code == 200:
@@ -490,13 +523,16 @@ def run_doctor(args):
             print(f"\r  {color('⚠', Colors.YELLOW)} Anthropic API {color(f'({e})', Colors.DIM)}                 ")
 
     # -- API-key providers (Z.AI/GLM, Kimi, MiniMax, MiniMax-CN) --
+    # Tuple: (name, env_vars, default_url, base_env, supports_models_endpoint)
+    # If supports_models_endpoint is False, we skip the health check and just show "configured"
     _apikey_providers = [
-        ("Z.AI / GLM",      ("GLM_API_KEY", "ZAI_API_KEY", "Z_AI_API_KEY"), "https://api.z.ai/api/paas/v4/models", "GLM_BASE_URL"),
-        ("Kimi / Moonshot",  ("KIMI_API_KEY",),                              "https://api.moonshot.ai/v1/models",   "KIMI_BASE_URL"),
-        ("MiniMax",          ("MINIMAX_API_KEY",),                            "https://api.minimax.io/v1/models",    "MINIMAX_BASE_URL"),
-        ("MiniMax (China)",  ("MINIMAX_CN_API_KEY",),                         "https://api.minimaxi.com/v1/models",  "MINIMAX_CN_BASE_URL"),
+        ("Z.AI / GLM",      ("GLM_API_KEY", "ZAI_API_KEY", "Z_AI_API_KEY"), "https://api.z.ai/api/paas/v4/models", "GLM_BASE_URL", True),
+        ("Kimi / Moonshot",  ("KIMI_API_KEY",),                              "https://api.moonshot.ai/v1/models",   "KIMI_BASE_URL", True),
+        # MiniMax APIs don't support /models endpoint — https://github.com/NousResearch/hermes-agent/issues/811
+        ("MiniMax",          ("MINIMAX_API_KEY",),                            None,                                  "MINIMAX_BASE_URL", False),
+        ("MiniMax (China)",  ("MINIMAX_CN_API_KEY",),                         None,                                  "MINIMAX_CN_BASE_URL", False),
     ]
-    for _pname, _env_vars, _default_url, _base_env in _apikey_providers:
+    for _pname, _env_vars, _default_url, _base_env, _supports_health_check in _apikey_providers:
         _key = ""
         for _ev in _env_vars:
             _key = os.getenv(_ev, "")
@@ -504,6 +540,10 @@ def run_doctor(args):
                 break
         if _key:
             _label = _pname.ljust(20)
+            # Some providers (like MiniMax) don't support /models endpoint
+            if not _supports_health_check:
+                print(f"  {color('✓', Colors.GREEN)} {_label} {color('(key configured)', Colors.DIM)}")
+                continue
             print(f"  Checking {_pname} API...", end="", flush=True)
             try:
                 import httpx
@@ -575,6 +615,7 @@ def run_doctor(args):
         from model_tools import check_tool_availability, TOOLSET_REQUIREMENTS
         
         available, unavailable = check_tool_availability()
+        available, unavailable = _apply_doctor_tool_availability_overrides(available, unavailable)
         
         for tid in available:
             info = TOOLSET_REQUIREMENTS.get(tid, {})
@@ -627,6 +668,40 @@ def run_doctor(args):
     else:
         check_warn("No GITHUB_TOKEN", "(60 req/hr rate limit — set in ~/.hermes/.env for better rates)")
 
+    # =========================================================================
+    # Honcho memory
+    # =========================================================================
+    print()
+    print(color("◆ Honcho Memory", Colors.CYAN, Colors.BOLD))
+
+    try:
+        from honcho_integration.client import HonchoClientConfig, GLOBAL_CONFIG_PATH
+        hcfg = HonchoClientConfig.from_global_config()
+
+        if not GLOBAL_CONFIG_PATH.exists():
+            check_warn("Honcho config not found", f"run: hermes honcho setup")
+        elif not hcfg.enabled:
+            check_info("Honcho disabled (set enabled: true in ~/.honcho/config.json to activate)")
+        elif not hcfg.api_key:
+            check_fail("Honcho API key not set", "run: hermes honcho setup")
+            issues.append("No Honcho API key — run 'hermes honcho setup'")
+        else:
+            from honcho_integration.client import get_honcho_client, reset_honcho_client
+            reset_honcho_client()
+            try:
+                get_honcho_client(hcfg)
+                check_ok(
+                    "Honcho connected",
+                    f"workspace={hcfg.workspace_id} mode={hcfg.memory_mode} freq={hcfg.write_frequency}",
+                )
+            except Exception as _e:
+                check_fail("Honcho connection failed", str(_e))
+                issues.append(f"Honcho unreachable: {_e}")
+    except ImportError:
+        check_warn("honcho-ai not installed", "pip install honcho-ai")
+    except Exception as _e:
+        check_warn("Honcho check failed", str(_e))
+
     # =========================================================================
     # Summary
     # =========================================================================

hermes_cli/gateway.py

@@ -518,6 +518,32 @@ _PLATFORMS = [
         "emoji": "📡",
         "token_var": "SIGNAL_HTTP_URL",
     },
+    {
+        "key": "email",
+        "label": "Email",
+        "emoji": "📧",
+        "token_var": "EMAIL_ADDRESS",
+        "setup_instructions": [
+            "1. Use a dedicated email account for your Hermes agent",
+            "2. For Gmail: enable 2FA, then create an App Password at",
+            "   https://myaccount.google.com/apppasswords",
+            "3. For other providers: use your email password or app-specific password",
+            "4. IMAP must be enabled on your email account",
+        ],
+        "vars": [
+            {"name": "EMAIL_ADDRESS", "prompt": "Email address", "password": False,
+             "help": "The email address Hermes will use (e.g., hermes@gmail.com)."},
+            {"name": "EMAIL_PASSWORD", "prompt": "Email password (or app password)", "password": True,
+             "help": "For Gmail, use an App Password (not your regular password)."},
+            {"name": "EMAIL_IMAP_HOST", "prompt": "IMAP host", "password": False,
+             "help": "e.g., imap.gmail.com for Gmail, outlook.office365.com for Outlook."},
+            {"name": "EMAIL_SMTP_HOST", "prompt": "SMTP host", "password": False,
+             "help": "e.g., smtp.gmail.com for Gmail, smtp.office365.com for Outlook."},
+            {"name": "EMAIL_ALLOWED_USERS", "prompt": "Allowed sender emails (comma-separated)", "password": False,
+             "is_allowlist": True,
+             "help": "Only emails from these addresses will be processed."},
+        ],
+    },
 ]
 
 
@@ -543,6 +569,15 @@ def _platform_status(platform: dict) -> str:
         if val or account:
             return "partially configured"
         return "not configured"
+    if platform.get("key") == "email":
+        pwd = get_env_value("EMAIL_PASSWORD")
+        imap = get_env_value("EMAIL_IMAP_HOST")
+        smtp = get_env_value("EMAIL_SMTP_HOST")
+        if all([val, pwd, imap, smtp]):
+            return "configured"
+        if any([val, pwd, imap, smtp]):
+            return "partially configured"
+        return "not configured"
     if val:
         return "configured"
     return "not configured"

hermes_cli/main.py

@@ -18,10 +18,28 @@ Usage:
     hermes cron list           # List cron jobs
     hermes cron status         # Check if cron scheduler is running
     hermes doctor              # Check configuration and dependencies
+    hermes honcho setup                    # Configure Honcho AI memory integration
+    hermes honcho status                   # Show Honcho config and connection status
+    hermes honcho sessions                 # List directory → session name mappings
+    hermes honcho map <name>               # Map current directory to a session name
+    hermes honcho peer                     # Show peer names and dialectic settings
+    hermes honcho peer --user NAME         # Set user peer name
+    hermes honcho peer --ai NAME           # Set AI peer name
+    hermes honcho peer --reasoning LEVEL   # Set dialectic reasoning level
+    hermes honcho mode                     # Show current memory mode
+    hermes honcho mode [hybrid|honcho|local]  # Set memory mode
+    hermes honcho tokens                   # Show token budget settings
+    hermes honcho tokens --context N       # Set session.context() token cap
+    hermes honcho tokens --dialectic N     # Set dialectic result char cap
+    hermes honcho identity                 # Show AI peer identity representation
+    hermes honcho identity <file>          # Seed AI peer identity from a file (SOUL.md etc.)
+    hermes honcho migrate                  # Step-by-step migration guide: OpenClaw native → Hermes + Honcho
     hermes version             # Show version
     hermes update              # Update to latest version
     hermes uninstall           # Uninstall Hermes Agent
     hermes sessions browse     # Interactive session picker with search
+    hermes claw migrate        # Migrate from OpenClaw to Hermes
+    hermes claw migrate --dry-run  # Preview migration without changes
 """
 
 import argparse
@@ -51,7 +69,7 @@ os.environ.setdefault("MSWEA_SILENT_STARTUP", "1")
 
 import logging
 
-from hermes_cli import __version__
+from hermes_cli import __version__, __release_date__
 from hermes_constants import OPENROUTER_BASE_URL
 
 logger = logging.getLogger(__name__)
@@ -68,7 +86,7 @@ def _has_any_provider_configured() -> bool:
     from hermes_cli.auth import PROVIDER_REGISTRY
 
     # Collect all provider env vars
-    provider_env_vars = {"OPENROUTER_API_KEY", "OPENAI_API_KEY", "ANTHROPIC_API_KEY", "OPENAI_BASE_URL"}
+    provider_env_vars = {"OPENROUTER_API_KEY", "OPENAI_API_KEY", "ANTHROPIC_API_KEY", "ANTHROPIC_TOKEN", "OPENAI_BASE_URL"}
     for pconfig in PROVIDER_REGISTRY.values():
         if pconfig.auth_type == "api_key":
             provider_env_vars.update(pconfig.api_key_env_vars)
@@ -477,6 +495,10 @@ def cmd_chat(args):
     except Exception:
         pass
 
+    # --yolo: bypass all dangerous command approvals
+    if getattr(args, "yolo", False):
+        os.environ["HERMES_YOLO_MODE"] = "1"
+
     # Import and run the CLI
     from cli import main as cli_main
     
@@ -486,9 +508,12 @@ def cmd_chat(args):
         "provider": getattr(args, "provider", None),
         "toolsets": args.toolsets,
         "verbose": args.verbose,
+        "quiet": getattr(args, "quiet", False),
         "query": args.query,
         "resume": getattr(args, "resume", None),
         "worktree": getattr(args, "worktree", False),
+        "checkpoints": getattr(args, "checkpoints", False),
+        "pass_session_id": getattr(args, "pass_session_id", False),
     }
     # Filter out None values
     kwargs = {k: v for k, v in kwargs.items() if v is not None}
@@ -739,6 +764,7 @@ def cmd_model(args):
         "openrouter": "OpenRouter",
         "nous": "Nous Portal",
         "openai-codex": "OpenAI Codex",
+        "anthropic": "Anthropic",
         "zai": "Z.AI / GLM",
         "kimi-coding": "Kimi / Moonshot",
         "minimax": "MiniMax",
@@ -757,6 +783,7 @@ def cmd_model(args):
         ("openrouter", "OpenRouter (100+ models, pay-per-use)"),
         ("nous", "Nous Portal (Nous Research subscription)"),
         ("openai-codex", "OpenAI Codex"),
+        ("anthropic", "Anthropic (Claude models — API key or Claude Code)"),
         ("zai", "Z.AI / GLM (Zhipu AI direct API)"),
         ("kimi-coding", "Kimi / Moonshot (Moonshot AI direct API)"),
         ("minimax", "MiniMax (global direct API)"),
@@ -825,7 +852,11 @@ def cmd_model(args):
         _model_flow_named_custom(config, _custom_provider_map[selected_provider])
     elif selected_provider == "remove-custom":
         _remove_custom_provider(config)
-    elif selected_provider in ("zai", "kimi-coding", "minimax", "minimax-cn"):
+    elif selected_provider == "anthropic":
+        _model_flow_anthropic(config, current_model)
+    elif selected_provider == "kimi-coding":
+        _model_flow_kimi(config, current_model)
+    elif selected_provider in ("zai", "minimax", "minimax-cn"):
         _model_flow_api_key_provider(config, selected_provider, current_model)
 
 
@@ -905,9 +936,11 @@ def _model_flow_openrouter(config, current_model=""):
         from hermes_cli.config import load_config, save_config
         cfg = load_config()
         model = cfg.get("model")
-        if isinstance(model, dict):
-            model["provider"] = "openrouter"
-            model["base_url"] = OPENROUTER_BASE_URL
+        if not isinstance(model, dict):
+            model = {"default": model} if model else {}
+            cfg["model"] = model
+        model["provider"] = "openrouter"
+        model["base_url"] = OPENROUTER_BASE_URL
         save_config(cfg)
         deactivate_provider()
         print(f"Default model set to: {selected} (via OpenRouter)")
@@ -1089,9 +1122,11 @@ def _model_flow_custom(config):
         # Update config and deactivate any OAuth provider
         cfg = load_config()
         model = cfg.get("model")
-        if isinstance(model, dict):
-            model["provider"] = "custom"
-            model["base_url"] = effective_url
+        if not isinstance(model, dict):
+            model = {"default": model} if model else {}
+            cfg["model"] = model
+        model["provider"] = "custom"
+        model["base_url"] = effective_url
         save_config(cfg)
         deactivate_provider()
 
@@ -1234,9 +1269,11 @@ def _model_flow_named_custom(config, provider_info):
 
         cfg = load_config()
         model = cfg.get("model")
-        if isinstance(model, dict):
-            model["provider"] = "custom"
-            model["base_url"] = base_url
+        if not isinstance(model, dict):
+            model = {"default": model} if model else {}
+            cfg["model"] = model
+        model["provider"] = "custom"
+        model["base_url"] = base_url
         save_config(cfg)
         deactivate_provider()
 
@@ -1306,9 +1343,11 @@ def _model_flow_named_custom(config, provider_info):
 
     cfg = load_config()
     model = cfg.get("model")
-    if isinstance(model, dict):
-        model["provider"] = "custom"
-        model["base_url"] = base_url
+    if not isinstance(model, dict):
+        model = {"default": model} if model else {}
+        cfg["model"] = model
+    model["provider"] = "custom"
+    model["base_url"] = base_url
     save_config(cfg)
     deactivate_provider()
 
@@ -1328,8 +1367,10 @@ _PROVIDER_MODELS = {
         "glm-4.5-flash",
     ],
     "kimi-coding": [
+        "kimi-for-coding",
         "kimi-k2.5",
         "kimi-k2-thinking",
+        "kimi-k2-thinking-turbo",
         "kimi-k2-turbo-preview",
         "kimi-k2-0905-preview",
     ],
@@ -1346,8 +1387,112 @@ _PROVIDER_MODELS = {
 }
 
 
+def _model_flow_kimi(config, current_model=""):
+    """Kimi / Moonshot model selection with automatic endpoint routing.
+
+    - sk-kimi-* keys   → api.kimi.com/coding/v1  (Kimi Coding Plan)
+    - Other keys        → api.moonshot.ai/v1      (legacy Moonshot)
+
+    No manual base URL prompt — endpoint is determined by key prefix.
+    """
+    from hermes_cli.auth import (
+        PROVIDER_REGISTRY, KIMI_CODE_BASE_URL, _prompt_model_selection,
+        _save_model_choice, deactivate_provider,
+    )
+    from hermes_cli.config import get_env_value, save_env_value, load_config, save_config
+
+    provider_id = "kimi-coding"
+    pconfig = PROVIDER_REGISTRY[provider_id]
+    key_env = pconfig.api_key_env_vars[0] if pconfig.api_key_env_vars else ""
+    base_url_env = pconfig.base_url_env_var or ""
+
+    # Step 1: Check / prompt for API key
+    existing_key = ""
+    for ev in pconfig.api_key_env_vars:
+        existing_key = get_env_value(ev) or os.getenv(ev, "")
+        if existing_key:
+            break
+
+    if not existing_key:
+        print(f"No {pconfig.name} API key configured.")
+        if key_env:
+            try:
+                new_key = input(f"{key_env} (or Enter to cancel): ").strip()
+            except (KeyboardInterrupt, EOFError):
+                print()
+                return
+            if not new_key:
+                print("Cancelled.")
+                return
+            save_env_value(key_env, new_key)
+            existing_key = new_key
+            print("API key saved.")
+            print()
+    else:
+        print(f"  {pconfig.name} API key: {existing_key[:8]}... ✓")
+        print()
+
+    # Step 2: Auto-detect endpoint from key prefix
+    is_coding_plan = existing_key.startswith("sk-kimi-")
+    if is_coding_plan:
+        effective_base = KIMI_CODE_BASE_URL
+        print(f"  Detected Kimi Coding Plan key → {effective_base}")
+    else:
+        effective_base = pconfig.inference_base_url
+        print(f"  Using Moonshot endpoint → {effective_base}")
+    # Clear any manual base URL override so auto-detection works at runtime
+    if base_url_env and get_env_value(base_url_env):
+        save_env_value(base_url_env, "")
+    print()
+
+    # Step 3: Model selection — show appropriate models for the endpoint
+    if is_coding_plan:
+        # Coding Plan models (kimi-for-coding first)
+        model_list = [
+            "kimi-for-coding",
+            "kimi-k2.5",
+            "kimi-k2-thinking",
+            "kimi-k2-thinking-turbo",
+        ]
+    else:
+        # Legacy Moonshot models
+        model_list = _PROVIDER_MODELS.get(provider_id, [])
+
+    if model_list:
+        selected = _prompt_model_selection(model_list, current_model=current_model)
+    else:
+        try:
+            selected = input("Enter model name: ").strip()
+        except (KeyboardInterrupt, EOFError):
+            selected = None
+
+    if selected:
+        # Clear custom endpoint if set (avoid confusion)
+        if get_env_value("OPENAI_BASE_URL"):
+            save_env_value("OPENAI_BASE_URL", "")
+            save_env_value("OPENAI_API_KEY", "")
+
+        _save_model_choice(selected)
+
+        # Update config with provider and base URL
+        cfg = load_config()
+        model = cfg.get("model")
+        if not isinstance(model, dict):
+            model = {"default": model} if model else {}
+            cfg["model"] = model
+        model["provider"] = provider_id
+        model["base_url"] = effective_base
+        save_config(cfg)
+        deactivate_provider()
+
+        endpoint_label = "Kimi Coding" if is_coding_plan else "Moonshot"
+        print(f"Default model set to: {selected} (via {endpoint_label})")
+    else:
+        print("No change.")
+
+
 def _model_flow_api_key_provider(config, provider_id, current_model=""):
-    """Generic flow for API-key providers (z.ai, Kimi, MiniMax)."""
+    """Generic flow for API-key providers (z.ai, MiniMax)."""
     from hermes_cli.auth import (
         PROVIDER_REGISTRY, _prompt_model_selection, _save_model_choice,
         _update_config_for_provider, deactivate_provider,
@@ -1398,8 +1543,21 @@ def _model_flow_api_key_provider(config, provider_id, current_model=""):
         save_env_value(base_url_env, override)
         effective_base = override
 
-    # Model selection
-    model_list = _PROVIDER_MODELS.get(provider_id, [])
+    # Model selection — try live /models endpoint first, fall back to defaults
+    from hermes_cli.models import fetch_api_models
+    api_key_for_probe = existing_key or (get_env_value(key_env) if key_env else "")
+    live_models = fetch_api_models(api_key_for_probe, effective_base)
+
+    if live_models:
+        model_list = live_models
+        print(f"  Found {len(model_list)} model(s) from {pconfig.name} API")
+    else:
+        model_list = _PROVIDER_MODELS.get(provider_id, [])
+        if model_list:
+            print(f"  ⚠ Could not auto-detect models from API — showing defaults.")
+            print(f"    Use \"Enter custom model name\" if you don't see your model.")
+        # else: no defaults either, will fall through to raw input
+
     if model_list:
         selected = _prompt_model_selection(model_list, current_model=current_model)
     else:
@@ -1419,9 +1577,11 @@ def _model_flow_api_key_provider(config, provider_id, current_model=""):
         # Update config with provider and base URL
         cfg = load_config()
         model = cfg.get("model")
-        if isinstance(model, dict):
-            model["provider"] = provider_id
-            model["base_url"] = effective_base
+        if not isinstance(model, dict):
+            model = {"default": model} if model else {}
+            cfg["model"] = model
+        model["provider"] = provider_id
+        model["base_url"] = effective_base
         save_config(cfg)
         deactivate_provider()
 
@@ -1430,6 +1590,199 @@ def _model_flow_api_key_provider(config, provider_id, current_model=""):
         print("No change.")
 
 
+def _run_anthropic_oauth_flow(save_env_value):
+    """Run the Claude OAuth setup-token flow. Returns True if credentials were saved."""
+    from agent.anthropic_adapter import run_oauth_setup_token
+    from hermes_cli.config import save_anthropic_oauth_token
+
+    try:
+        print()
+        print("  Running 'claude setup-token' — follow the prompts below.")
+        print("  A browser window will open for you to authorize access.")
+        print()
+        token = run_oauth_setup_token()
+        if token:
+            save_anthropic_oauth_token(token, save_fn=save_env_value)
+            print("  ✓ OAuth credentials saved.")
+            return True
+
+        # Subprocess completed but no token auto-detected — ask user to paste
+        print()
+        print("  If the setup-token was displayed above, paste it here:")
+        print()
+        try:
+            manual_token = input("  Paste setup-token (or Enter to cancel): ").strip()
+        except (KeyboardInterrupt, EOFError):
+            print()
+            return False
+        if manual_token:
+            save_anthropic_oauth_token(manual_token, save_fn=save_env_value)
+            print("  ✓ Setup-token saved.")
+            return True
+
+        print("  ⚠ Could not detect saved credentials.")
+        return False
+
+    except FileNotFoundError:
+        # Claude CLI not installed — guide user through manual setup
+        print()
+        print("  The 'claude' CLI is required for OAuth login.")
+        print()
+        print("  To install and authenticate:")
+        print()
+        print("    1. Install Claude Code:  npm install -g @anthropic-ai/claude-code")
+        print("    2. Run:                  claude setup-token")
+        print("    3. Follow the browser prompts to authorize")
+        print("    4. Re-run:               hermes model")
+        print()
+        print("  Or paste an existing setup-token now (sk-ant-oat-...):")
+        print()
+        try:
+            token = input("  Setup-token (or Enter to cancel): ").strip()
+        except (KeyboardInterrupt, EOFError):
+            print()
+            return False
+        if token:
+            save_anthropic_oauth_token(token, save_fn=save_env_value)
+            print("  ✓ Setup-token saved.")
+            return True
+        print("  Cancelled — install Claude Code and try again.")
+        return False
+
+
+def _model_flow_anthropic(config, current_model=""):
+    """Flow for Anthropic provider — OAuth subscription, API key, or Claude Code creds."""
+    import os
+    from hermes_cli.auth import (
+        PROVIDER_REGISTRY, _prompt_model_selection, _save_model_choice,
+        _update_config_for_provider, deactivate_provider,
+    )
+    from hermes_cli.config import (
+        get_env_value, save_env_value, load_config, save_config,
+        save_anthropic_api_key,
+    )
+    from hermes_cli.models import _PROVIDER_MODELS
+
+    pconfig = PROVIDER_REGISTRY["anthropic"]
+
+    # Check ALL credential sources
+    existing_key = (
+        get_env_value("ANTHROPIC_TOKEN")
+        or os.getenv("ANTHROPIC_TOKEN", "")
+        or get_env_value("ANTHROPIC_API_KEY")
+        or os.getenv("ANTHROPIC_API_KEY", "")
+        or os.getenv("CLAUDE_CODE_OAUTH_TOKEN", "")
+    )
+    cc_available = False
+    try:
+        from agent.anthropic_adapter import read_claude_code_credentials, is_claude_code_token_valid
+        cc_creds = read_claude_code_credentials()
+        if cc_creds and is_claude_code_token_valid(cc_creds):
+            cc_available = True
+    except Exception:
+        pass
+
+    has_creds = bool(existing_key) or cc_available
+    needs_auth = not has_creds
+
+    if has_creds:
+        # Show what we found
+        if existing_key:
+            print(f"  Anthropic credentials: {existing_key[:12]}... ✓")
+        elif cc_available:
+            print("  Claude Code credentials: ✓ (auto-detected)")
+        print()
+        print("    1. Use existing credentials")
+        print("    2. Reauthenticate (new OAuth login)")
+        print("    3. Cancel")
+        print()
+        try:
+            choice = input("  Choice [1/2/3]: ").strip()
+        except (KeyboardInterrupt, EOFError):
+            choice = "1"
+
+        if choice == "2":
+            needs_auth = True
+        elif choice == "3":
+            return
+        # choice == "1" or default: use existing, proceed to model selection
+
+    if needs_auth:
+        # Show auth method choice
+        print()
+        print("  Choose authentication method:")
+        print()
+        print("    1. Claude Pro/Max subscription (OAuth login)")
+        print("    2. Anthropic API key (pay-per-token)")
+        print("    3. Cancel")
+        print()
+        try:
+            choice = input("  Choice [1/2/3]: ").strip()
+        except (KeyboardInterrupt, EOFError):
+            print()
+            return
+
+        if choice == "1":
+            if not _run_anthropic_oauth_flow(save_env_value):
+                return
+
+        elif choice == "2":
+            print()
+            print("  Get an API key at: https://console.anthropic.com/settings/keys")
+            print()
+            try:
+                api_key = input("  API key (sk-ant-...): ").strip()
+            except (KeyboardInterrupt, EOFError):
+                print()
+                return
+            if not api_key:
+                print("  Cancelled.")
+                return
+            save_anthropic_api_key(api_key, save_fn=save_env_value)
+            print("  ✓ API key saved.")
+
+        else:
+            print("  No change.")
+            return
+    print()
+
+    # Model selection
+    model_list = _PROVIDER_MODELS.get("anthropic", [])
+    if model_list:
+        selected = _prompt_model_selection(model_list, current_model=current_model)
+    else:
+        try:
+            selected = input("Model name (e.g., claude-sonnet-4-20250514): ").strip()
+        except (KeyboardInterrupt, EOFError):
+            selected = None
+
+    if selected:
+        # Clear custom endpoint if set
+        if get_env_value("OPENAI_BASE_URL"):
+            save_env_value("OPENAI_BASE_URL", "")
+            save_env_value("OPENAI_API_KEY", "")
+
+        _save_model_choice(selected)
+
+        # Update config with provider — clear base_url since
+        # resolve_runtime_provider() always hardcodes Anthropic's URL.
+        # Leaving a stale base_url in config can contaminate other
+        # providers if the user switches without running 'hermes model'.
+        cfg = load_config()
+        model = cfg.get("model")
+        if not isinstance(model, dict):
+            model = {"default": model} if model else {}
+            cfg["model"] = model
+        model["provider"] = "anthropic"
+        model.pop("base_url", None)
+        save_config(cfg)
+        deactivate_provider()
+
+        print(f"Default model set to: {selected} (via Anthropic)")
+    else:
+        print("No change.")
+
+
 def cmd_login(args):
     """Authenticate Hermes CLI with a provider."""
     from hermes_cli.auth import login_command
@@ -1468,7 +1821,7 @@ def cmd_config(args):
 
 def cmd_version(args):
     """Show version."""
-    print(f"Hermes Agent v{__version__}")
+    print(f"Hermes Agent v{__version__} ({__release_date__})")
     print(f"Project: {PROJECT_ROOT}")
     
     # Show Python version
@@ -1777,6 +2130,44 @@ def cmd_update(args):
             sys.exit(1)
 
 
+def _coalesce_session_name_args(argv: list) -> list:
+    """Join unquoted multi-word session names after -c/--continue and -r/--resume.
+
+    When a user types ``hermes -c Pokemon Agent Dev`` without quoting the
+    session name, argparse sees three separate tokens.  This function merges
+    them into a single argument so argparse receives
+    ``['-c', 'Pokemon Agent Dev']`` instead.
+
+    Tokens are collected after the flag until we hit another flag (``-*``)
+    or a known top-level subcommand.
+    """
+    _SUBCOMMANDS = {
+        "chat", "model", "gateway", "setup", "whatsapp", "login", "logout",
+        "status", "cron", "doctor", "config", "pairing", "skills", "tools",
+        "sessions", "insights", "version", "update", "uninstall",
+    }
+    _SESSION_FLAGS = {"-c", "--continue", "-r", "--resume"}
+
+    result = []
+    i = 0
+    while i < len(argv):
+        token = argv[i]
+        if token in _SESSION_FLAGS:
+            result.append(token)
+            i += 1
+            # Collect subsequent non-flag, non-subcommand tokens as one name
+            parts: list = []
+            while i < len(argv) and not argv[i].startswith("-") and argv[i] not in _SUBCOMMANDS:
+                parts.append(argv[i])
+                i += 1
+            if parts:
+                result.append(" ".join(parts))
+        else:
+            result.append(token)
+            i += 1
+    return result
+
+
 def main():
     """Main entry point for hermes CLI."""
     parser = argparse.ArgumentParser(
@@ -1835,6 +2226,18 @@ For more help on a command:
         default=False,
         help="Run in an isolated git worktree (for parallel agents)"
     )
+    parser.add_argument(
+        "--yolo",
+        action="store_true",
+        default=False,
+        help="Bypass all dangerous command approval prompts (use at your own risk)"
+    )
+    parser.add_argument(
+        "--pass-session-id",
+        action="store_true",
+        default=False,
+        help="Include the session ID in the agent's system prompt"
+    )
     
     subparsers = parser.add_subparsers(dest="command", help="Command to run")
     
@@ -1860,7 +2263,7 @@ For more help on a command:
     )
     chat_parser.add_argument(
         "--provider",
-        choices=["auto", "openrouter", "nous", "openai-codex", "zai", "kimi-coding", "minimax", "minimax-cn"],
+        choices=["auto", "openrouter", "nous", "openai-codex", "anthropic", "zai", "kimi-coding", "minimax", "minimax-cn"],
         default=None,
         help="Inference provider (default: auto)"
     )
@@ -1869,6 +2272,11 @@ For more help on a command:
         action="store_true",
         help="Verbose output"
     )
+    chat_parser.add_argument(
+        "-Q", "--quiet",
+        action="store_true",
+        help="Quiet mode for programmatic use: suppress banner, spinner, and tool previews. Only output the final response and session info."
+    )
     chat_parser.add_argument(
         "--resume", "-r",
         metavar="SESSION_ID",
@@ -1889,6 +2297,24 @@ For more help on a command:
         default=False,
         help="Run in an isolated git worktree (for parallel agents on the same repo)"
     )
+    chat_parser.add_argument(
+        "--checkpoints",
+        action="store_true",
+        default=False,
+        help="Enable filesystem checkpoints before destructive file operations (use /rollback to restore)"
+    )
+    chat_parser.add_argument(
+        "--yolo",
+        action="store_true",
+        default=False,
+        help="Bypass all dangerous command approval prompts (use at your own risk)"
+    )
+    chat_parser.add_argument(
+        "--pass-session-id",
+        action="store_true",
+        default=False,
+        help="Include the session ID in the agent's system prompt"
+    )
     chat_parser.set_defaults(func=cmd_chat)
 
     # =========================================================================
@@ -2175,8 +2601,8 @@ For more help on a command:
     # =========================================================================
     skills_parser = subparsers.add_parser(
         "skills",
-        help="Skills Hub — search, install, and manage skills from online registries",
-        description="Search, install, inspect, audit, and manage skills from GitHub, ClawHub, and other registries."
+        help="Search, install, configure, and manage skills",
+        description="Search, install, inspect, audit, configure, and manage skills from GitHub, ClawHub, and other registries."
     )
     skills_subparsers = skills_parser.add_subparsers(dest="skills_action")
 
@@ -2201,7 +2627,7 @@ For more help on a command:
     skills_inspect.add_argument("identifier", help="Skill identifier")
 
     skills_list = skills_subparsers.add_parser("list", help="List installed skills")
-    skills_list.add_argument("--source", default="all", choices=["all", "hub", "builtin"])
+    skills_list.add_argument("--source", default="all", choices=["all", "hub", "builtin", "local"])
 
     skills_audit = skills_subparsers.add_parser("audit", help="Re-scan installed hub skills")
     skills_audit.add_argument("name", nargs="?", help="Specific skill to audit (default: all)")
@@ -2230,12 +2656,108 @@ For more help on a command:
     tap_rm = tap_subparsers.add_parser("remove", help="Remove a tap")
     tap_rm.add_argument("name", help="Tap name to remove")
 
+    # config sub-action: interactive enable/disable
+    skills_subparsers.add_parser("config", help="Interactive skill configuration — enable/disable individual skills")
+
     def cmd_skills(args):
-        from hermes_cli.skills_hub import skills_command
-        skills_command(args)
+        # Route 'config' action to skills_config module
+        if getattr(args, 'skills_action', None) == 'config':
+            from hermes_cli.skills_config import skills_command as skills_config_command
+            skills_config_command(args)
+        else:
+            from hermes_cli.skills_hub import skills_command
+            skills_command(args)
 
     skills_parser.set_defaults(func=cmd_skills)
 
+    # =========================================================================
+    # honcho command
+    # =========================================================================
+    honcho_parser = subparsers.add_parser(
+        "honcho",
+        help="Manage Honcho AI memory integration",
+        description=(
+            "Honcho is a memory layer that persists across sessions.\n\n"
+            "Each conversation is stored as a peer interaction in a workspace. "
+            "Honcho builds a representation of the user over time — conclusions, "
+            "patterns, context — and surfaces the relevant slice at the start of "
+            "each turn so Hermes knows who you are without you having to repeat yourself.\n\n"
+            "Modes: hybrid (Honcho + local MEMORY.md), honcho (Honcho only), "
+            "local (MEMORY.md only). Write frequency is configurable so memory "
+            "writes never block the response."
+        ),
+        formatter_class=__import__("argparse").RawDescriptionHelpFormatter,
+    )
+    honcho_subparsers = honcho_parser.add_subparsers(dest="honcho_command")
+
+    honcho_subparsers.add_parser("setup", help="Interactive setup wizard for Honcho integration")
+    honcho_subparsers.add_parser("status", help="Show current Honcho config and connection status")
+    honcho_subparsers.add_parser("sessions", help="List known Honcho session mappings")
+
+    honcho_map = honcho_subparsers.add_parser(
+        "map", help="Map current directory to a Honcho session name (no arg = list mappings)"
+    )
+    honcho_map.add_argument(
+        "session_name", nargs="?", default=None,
+        help="Session name to associate with this directory. Omit to list current mappings.",
+    )
+
+    honcho_peer = honcho_subparsers.add_parser(
+        "peer", help="Show or update peer names and dialectic reasoning level"
+    )
+    honcho_peer.add_argument("--user", metavar="NAME", help="Set user peer name")
+    honcho_peer.add_argument("--ai", metavar="NAME", help="Set AI peer name")
+    honcho_peer.add_argument(
+        "--reasoning",
+        metavar="LEVEL",
+        choices=("minimal", "low", "medium", "high", "max"),
+        help="Set default dialectic reasoning level (minimal/low/medium/high/max)",
+    )
+
+    honcho_mode = honcho_subparsers.add_parser(
+        "mode", help="Show or set memory mode (hybrid/honcho/local)"
+    )
+    honcho_mode.add_argument(
+        "mode", nargs="?", metavar="MODE",
+        choices=("hybrid", "honcho", "local"),
+        help="Memory mode to set (hybrid/honcho/local). Omit to show current.",
+    )
+
+    honcho_tokens = honcho_subparsers.add_parser(
+        "tokens", help="Show or set token budget for context and dialectic"
+    )
+    honcho_tokens.add_argument(
+        "--context", type=int, metavar="N",
+        help="Max tokens Honcho returns from session.context() per turn",
+    )
+    honcho_tokens.add_argument(
+        "--dialectic", type=int, metavar="N",
+        help="Max chars of dialectic result to inject into system prompt",
+    )
+
+    honcho_identity = honcho_subparsers.add_parser(
+        "identity", help="Seed or show the AI peer's Honcho identity representation"
+    )
+    honcho_identity.add_argument(
+        "file", nargs="?", default=None,
+        help="Path to file to seed from (e.g. SOUL.md). Omit to show usage.",
+    )
+    honcho_identity.add_argument(
+        "--show", action="store_true",
+        help="Show current AI peer representation from Honcho",
+    )
+
+    honcho_subparsers.add_parser(
+        "migrate",
+        help="Step-by-step migration guide from openclaw-honcho to Hermes Honcho",
+    )
+
+    def cmd_honcho(args):
+        from honcho_integration.cli import honcho_command
+        honcho_command(args)
+
+    honcho_parser.set_defaults(func=cmd_honcho)
+
     # =========================================================================
     # tools command
     # =========================================================================
@@ -2244,13 +2766,17 @@ For more help on a command:
         help="Configure which tools are enabled per platform",
         description="Interactive tool configuration — enable/disable tools for CLI, Telegram, Discord, etc."
     )
+    tools_parser.add_argument(
+        "--summary",
+        action="store_true",
+        help="Print a summary of enabled tools per platform and exit"
+    )
 
     def cmd_tools(args):
         from hermes_cli.tools_config import tools_command
         tools_command(args)
 
     tools_parser.set_defaults(func=cmd_tools)
-
     # =========================================================================
     # sessions command
     # =========================================================================
@@ -2356,12 +2882,12 @@ For more help on a command:
                 if not data:
                     print(f"Session '{args.session_id}' not found.")
                     return
-                with open(args.output, "w") as f:
+                with open(args.output, "w", encoding="utf-8") as f:
                     f.write(_json.dumps(data, ensure_ascii=False) + "\n")
                 print(f"Exported 1 session to {args.output}")
             else:
                 sessions = db.export_all(source=args.source)
-                with open(args.output, "w") as f:
+                with open(args.output, "w", encoding="utf-8") as f:
                     for s in sessions:
                         f.write(_json.dumps(s, ensure_ascii=False) + "\n")
                 print(f"Exported {len(sessions)} sessions to {args.output}")
@@ -2473,6 +2999,69 @@ For more help on a command:
 
     insights_parser.set_defaults(func=cmd_insights)
 
+    # =========================================================================
+    # claw command (OpenClaw migration)
+    # =========================================================================
+    claw_parser = subparsers.add_parser(
+        "claw",
+        help="OpenClaw migration tools",
+        description="Migrate settings, memories, skills, and API keys from OpenClaw to Hermes"
+    )
+    claw_subparsers = claw_parser.add_subparsers(dest="claw_action")
+
+    # claw migrate
+    claw_migrate = claw_subparsers.add_parser(
+        "migrate",
+        help="Migrate from OpenClaw to Hermes",
+        description="Import settings, memories, skills, and API keys from an OpenClaw installation"
+    )
+    claw_migrate.add_argument(
+        "--source",
+        help="Path to OpenClaw directory (default: ~/.openclaw)"
+    )
+    claw_migrate.add_argument(
+        "--dry-run",
+        action="store_true",
+        help="Preview what would be migrated without making changes"
+    )
+    claw_migrate.add_argument(
+        "--preset",
+        choices=["user-data", "full"],
+        default="full",
+        help="Migration preset (default: full). 'user-data' excludes secrets"
+    )
+    claw_migrate.add_argument(
+        "--overwrite",
+        action="store_true",
+        help="Overwrite existing files (default: skip conflicts)"
+    )
+    claw_migrate.add_argument(
+        "--migrate-secrets",
+        action="store_true",
+        help="Include allowlisted secrets (TELEGRAM_BOT_TOKEN, API keys, etc.)"
+    )
+    claw_migrate.add_argument(
+        "--workspace-target",
+        help="Absolute path to copy workspace instructions into"
+    )
+    claw_migrate.add_argument(
+        "--skill-conflict",
+        choices=["skip", "overwrite", "rename"],
+        default="skip",
+        help="How to handle skill name conflicts (default: skip)"
+    )
+    claw_migrate.add_argument(
+        "--yes", "-y",
+        action="store_true",
+        help="Skip confirmation prompts"
+    )
+
+    def cmd_claw(args):
+        from hermes_cli.claw import claw_command
+        claw_command(args)
+
+    claw_parser.set_defaults(func=cmd_claw)
+
     # =========================================================================
     # version command
     # =========================================================================
@@ -2515,7 +3104,11 @@ For more help on a command:
     # =========================================================================
     # Parse and execute
     # =========================================================================
-    args = parser.parse_args()
+    # Pre-process argv so unquoted multi-word session names after -c / -r
+    # are merged into a single token before argparse sees them.
+    # e.g. ``hermes -c Pokemon Agent Dev`` → ``hermes -c 'Pokemon Agent Dev'``
+    _processed_argv = _coalesce_session_name_args(sys.argv[1:])
+    args = parser.parse_args(_processed_argv)
     
     # Handle --version flag
     if args.version:

hermes_cli/models.py

@@ -31,6 +31,19 @@ OPENROUTER_MODELS: list[tuple[str, str]] = [
 ]
 
 _PROVIDER_MODELS: dict[str, list[str]] = {
+    "nous": [
+        "claude-opus-4-6",
+        "claude-sonnet-4-6",
+        "gpt-5.4",
+        "gemini-3-flash",
+        "gemini-3.0-pro-preview",
+        "deepseek-v3.2",
+    ],
+    "openai-codex": [
+        "gpt-5.2-codex",
+        "gpt-5.1-codex-mini",
+        "gpt-5.1-codex-max",
+    ],
     "zai": [
         "glm-5",
         "glm-4.7",
@@ -38,8 +51,10 @@ _PROVIDER_MODELS: dict[str, list[str]] = {
         "glm-4.5-flash",
     ],
     "kimi-coding": [
+        "kimi-for-coding",
         "kimi-k2.5",
         "kimi-k2-thinking",
+        "kimi-k2-thinking-turbo",
         "kimi-k2-turbo-preview",
         "kimi-k2-0905-preview",
     ],
@@ -53,6 +68,15 @@ _PROVIDER_MODELS: dict[str, list[str]] = {
         "MiniMax-M2.5-highspeed",
         "MiniMax-M2.1",
     ],
+    "anthropic": [
+        "claude-opus-4-6",
+        "claude-sonnet-4-6",
+        "claude-opus-4-5-20251101",
+        "claude-sonnet-4-5-20250929",
+        "claude-opus-4-20250514",
+        "claude-sonnet-4-20250514",
+        "claude-haiku-4-5-20251001",
+    ],
 }
 
 _PROVIDER_LABELS = {
@@ -63,6 +87,7 @@ _PROVIDER_LABELS = {
     "kimi-coding": "Kimi / Moonshot",
     "minimax": "MiniMax",
     "minimax-cn": "MiniMax (China)",
+    "anthropic": "Anthropic",
     "custom": "Custom endpoint",
 }
 
@@ -75,6 +100,8 @@ _PROVIDER_ALIASES = {
     "moonshot": "kimi-coding",
     "minimax-china": "minimax-cn",
     "minimax_cn": "minimax-cn",
+    "claude": "anthropic",
+    "claude-code": "anthropic",
 }
 
 
@@ -108,7 +135,7 @@ def list_available_providers() -> list[dict[str, str]]:
     # Canonical providers in display order
     _PROVIDER_ORDER = [
         "openrouter", "nous", "openai-codex",
-        "zai", "kimi-coding", "minimax", "minimax-cn",
+        "zai", "kimi-coding", "minimax", "minimax-cn", "anthropic",
     ]
     # Build reverse alias map
     aliases_for: dict[str, list[str]] = {}
@@ -164,10 +191,22 @@ def parse_model_input(raw: str, current_provider: str) -> tuple[str, str]:
 
 
 def curated_models_for_provider(provider: Optional[str]) -> list[tuple[str, str]]:
-    """Return ``(model_id, description)`` tuples for a provider's curated list."""
+    """Return ``(model_id, description)`` tuples for a provider's model list.
+
+    Tries to fetch the live model list from the provider's API first,
+    falling back to the static ``_PROVIDER_MODELS`` catalog if the API
+    is unreachable.
+    """
     normalized = normalize_provider(provider)
     if normalized == "openrouter":
         return list(OPENROUTER_MODELS)
+
+    # Try live API first (Codex, Nous, etc. all support /models)
+    live = provider_model_ids(normalized)
+    if live:
+        return [(m, "") for m in live]
+
+    # Fallback to static catalog
     models = _PROVIDER_MODELS.get(normalized, [])
     return [(m, "") for m in models]
 
@@ -184,7 +223,11 @@ def normalize_provider(provider: Optional[str]) -> str:
 
 
 def provider_model_ids(provider: Optional[str]) -> list[str]:
-    """Return the best known model catalog for a provider."""
+    """Return the best known model catalog for a provider.
+
+    Tries live API endpoints for providers that support them (Codex, Nous),
+    falling back to static lists.
+    """
     normalized = normalize_provider(provider)
     if normalized == "openrouter":
         return model_ids()
@@ -192,9 +235,68 @@ def provider_model_ids(provider: Optional[str]) -> list[str]:
         from hermes_cli.codex_models import get_codex_model_ids
 
         return get_codex_model_ids()
+    if normalized == "nous":
+        # Try live Nous Portal /models endpoint
+        try:
+            from hermes_cli.auth import fetch_nous_models, resolve_nous_runtime_credentials
+            creds = resolve_nous_runtime_credentials()
+            if creds:
+                live = fetch_nous_models(creds.get("api_key", ""), creds.get("base_url", ""))
+                if live:
+                    return live
+        except Exception:
+            pass
+    if normalized == "anthropic":
+        live = _fetch_anthropic_models()
+        if live:
+            return live
     return list(_PROVIDER_MODELS.get(normalized, []))
 
 
+def _fetch_anthropic_models(timeout: float = 5.0) -> Optional[list[str]]:
+    """Fetch available models from the Anthropic /v1/models endpoint.
+
+    Uses resolve_anthropic_token() to find credentials (env vars or
+    Claude Code auto-discovery).  Returns sorted model IDs or None.
+    """
+    try:
+        from agent.anthropic_adapter import resolve_anthropic_token, _is_oauth_token
+    except ImportError:
+        return None
+
+    token = resolve_anthropic_token()
+    if not token:
+        return None
+
+    headers: dict[str, str] = {"anthropic-version": "2023-06-01"}
+    if _is_oauth_token(token):
+        headers["Authorization"] = f"Bearer {token}"
+        from agent.anthropic_adapter import _COMMON_BETAS, _OAUTH_ONLY_BETAS
+        headers["anthropic-beta"] = ",".join(_COMMON_BETAS + _OAUTH_ONLY_BETAS)
+    else:
+        headers["x-api-key"] = token
+
+    req = urllib.request.Request(
+        "https://api.anthropic.com/v1/models",
+        headers=headers,
+    )
+    try:
+        with urllib.request.urlopen(req, timeout=timeout) as resp:
+            data = json.loads(resp.read().decode())
+            models = [m["id"] for m in data.get("data", []) if m.get("id")]
+            # Sort: latest/largest first (opus > sonnet > haiku, higher version first)
+            return sorted(models, key=lambda m: (
+                "opus" not in m,      # opus first
+                "sonnet" not in m,    # then sonnet
+                "haiku" not in m,     # then haiku
+                m,                    # alphabetical within tier
+            ))
+    except Exception as e:
+        import logging
+        logging.getLogger(__name__).debug("Failed to fetch Anthropic models: %s", e)
+        return None
+
+
 def fetch_api_models(
     api_key: Optional[str],
     base_url: Optional[str],
@@ -263,6 +365,15 @@ def validate_requested_model(
             "message": "Model names cannot contain spaces.",
         }
 
+    # Custom endpoints can serve any model — skip validation
+    if normalized == "custom":
+        return {
+            "accepted": True,
+            "persist": True,
+            "recognized": False,
+            "message": None,
+        }
+
     # Probe the live API to check if the model actually exists
     api_models = fetch_api_models(api_key, base_url)
 
@@ -276,44 +387,35 @@ def validate_requested_model(
                 "message": None,
             }
         else:
-            # API responded but model is not listed
+            # API responded but model is not listed.  Accept anyway —
+            # the user may have access to models not shown in the public
+            # listing (e.g. Z.AI Pro/Max plans can use glm-5 on coding
+            # endpoints even though it's not in /models).  Warn but allow.
             suggestions = get_close_matches(requested, api_models, n=3, cutoff=0.5)
             suggestion_text = ""
             if suggestions:
-                suggestion_text = "\n  Did you mean: " + ", ".join(f"`{s}`" for s in suggestions)
+                suggestion_text = "\n  Similar models: " + ", ".join(f"`{s}`" for s in suggestions)
 
             return {
-                "accepted": False,
-                "persist": False,
+                "accepted": True,
+                "persist": True,
                 "recognized": False,
                 "message": (
-                    f"Error: `{requested}` is not a valid model for this provider."
+                    f"Note: `{requested}` was not found in this provider's model listing. "
+                    f"It may still work if your plan supports it."
                     f"{suggestion_text}"
                 ),
             }
 
-    # api_models is None — couldn't reach API, fall back to catalog check
+    # api_models is None — couldn't reach API.  Accept and persist,
+    # but warn so typos don't silently break things.
     provider_label = _PROVIDER_LABELS.get(normalized, normalized)
-    known_models = provider_model_ids(normalized)
-
-    if requested in known_models:
-        return {
-            "accepted": True,
-            "persist": True,
-            "recognized": True,
-            "message": None,
-        }
-
-    # Can't validate — accept for session only
-    suggestion = get_close_matches(requested, known_models, n=1, cutoff=0.6)
-    suggestion_text = f" Did you mean `{suggestion[0]}`?" if suggestion else ""
     return {
         "accepted": True,
-        "persist": False,
+        "persist": True,
         "recognized": False,
         "message": (
-            f"Could not validate `{requested}` against the live {provider_label} API. "
-            "Using it for this session only; config unchanged."
-            f"{suggestion_text}"
+            f"Could not reach the {provider_label} API to validate `{requested}`. "
+            f"If the service isn't down, this model may not be valid."
         ),
     }

hermes_cli/runtime_provider.py

@@ -66,9 +66,14 @@ def _resolve_openrouter_runtime(
             if not cfg_provider or cfg_provider == "auto":
                 use_config_base_url = True
 
+    # When the user explicitly requested the openrouter provider, skip
+    # OPENAI_BASE_URL — it typically points to a custom / non-OpenRouter
+    # endpoint and would prevent switching back to OpenRouter (#874).
+    skip_openai_base = requested_norm == "openrouter"
+
     base_url = (
         (explicit_base_url or "").strip()
-        or env_openai_base_url
+        or ("" if skip_openai_base else env_openai_base_url)
         or (cfg_base_url.strip() if use_config_base_url else "")
         or env_openrouter_base_url
         or OPENROUTER_BASE_URL
@@ -148,6 +153,24 @@ def resolve_runtime_provider(
             "requested_provider": requested_provider,
         }
 
+    # Anthropic (native Messages API)
+    if provider == "anthropic":
+        from agent.anthropic_adapter import resolve_anthropic_token
+        token = resolve_anthropic_token()
+        if not token:
+            raise AuthError(
+                "No Anthropic credentials found. Set ANTHROPIC_TOKEN or ANTHROPIC_API_KEY, "
+                "run 'claude setup-token', or authenticate with 'claude /login'."
+            )
+        return {
+            "provider": "anthropic",
+            "api_mode": "anthropic_messages",
+            "base_url": "https://api.anthropic.com",
+            "api_key": token,
+            "source": "env",
+            "requested_provider": requested_provider,
+        }
+
     # API-key providers (z.ai/GLM, Kimi, MiniMax, MiniMax-CN)
     pconfig = PROVIDER_REGISTRY.get(provider)
     if pconfig and pconfig.auth_type == "api_key":

hermes_cli/skills_config.py

@@ -0,0 +1,181 @@
+"""
+Skills configuration for Hermes Agent.
+`hermes skills` enters this module.
+
+Toggle individual skills or categories on/off, globally or per-platform.
+Config stored in ~/.hermes/config.yaml under:
+
+  skills:
+    disabled: [skill-a, skill-b]          # global disabled list
+    platform_disabled:                    # per-platform overrides
+      telegram: [skill-c]
+      cli: []
+"""
+from typing import Dict, List, Optional, Set
+
+from hermes_cli.config import load_config, save_config
+from hermes_cli.colors import Colors, color
+
+PLATFORMS = {
+    "cli":      "🖥️  CLI",
+    "telegram": "📱 Telegram",
+    "discord":  "💬 Discord",
+    "slack":    "💼 Slack",
+    "whatsapp": "📱 WhatsApp",
+    "signal":   "📡 Signal",
+    "email":    "📧 Email",
+}
+
+# ─── Config Helpers ───────────────────────────────────────────────────────────
+
+def get_disabled_skills(config: dict, platform: Optional[str] = None) -> Set[str]:
+    """Return disabled skill names. Platform-specific list falls back to global."""
+    skills_cfg = config.get("skills", {})
+    global_disabled = set(skills_cfg.get("disabled", []))
+    if platform is None:
+        return global_disabled
+    platform_disabled = skills_cfg.get("platform_disabled", {}).get(platform)
+    if platform_disabled is None:
+        return global_disabled
+    return set(platform_disabled)
+
+
+def save_disabled_skills(config: dict, disabled: Set[str], platform: Optional[str] = None):
+    """Persist disabled skill names to config."""
+    config.setdefault("skills", {})
+    if platform is None:
+        config["skills"]["disabled"] = sorted(disabled)
+    else:
+        config["skills"].setdefault("platform_disabled", {})
+        config["skills"]["platform_disabled"][platform] = sorted(disabled)
+    save_config(config)
+
+
+# ─── Skill Discovery ─────────────────────────────────────────────────────────
+
+def _list_all_skills() -> List[dict]:
+    """Return all installed skills (ignoring disabled state)."""
+    try:
+        from tools.skills_tool import _find_all_skills
+        return _find_all_skills(skip_disabled=True)
+    except Exception:
+        return []
+
+
+def _get_categories(skills: List[dict]) -> List[str]:
+    """Return sorted unique category names (None -> 'uncategorized')."""
+    return sorted({s["category"] or "uncategorized" for s in skills})
+
+
+# ─── Platform Selection ──────────────────────────────────────────────────────
+
+def _select_platform() -> Optional[str]:
+    """Ask user which platform to configure, or global."""
+    options = [("global", "All platforms (global default)")] + list(PLATFORMS.items())
+    print()
+    print(color("  Configure skills for:", Colors.BOLD))
+    for i, (key, label) in enumerate(options, 1):
+        print(f"  {i}. {label}")
+    print()
+    try:
+        raw = input(color("  Select [1]: ", Colors.YELLOW)).strip()
+    except (KeyboardInterrupt, EOFError):
+        return None
+    if not raw:
+        return None  # global
+    try:
+        idx = int(raw) - 1
+        if 0 <= idx < len(options):
+            key = options[idx][0]
+            return None if key == "global" else key
+    except ValueError:
+        pass
+    return None
+
+
+# ─── Category Toggle ─────────────────────────────────────────────────────────
+
+def _toggle_by_category(skills: List[dict], disabled: Set[str]) -> Set[str]:
+    """Toggle all skills in a category at once."""
+    from hermes_cli.curses_ui import curses_checklist
+
+    categories = _get_categories(skills)
+    cat_labels = []
+    # A category is "enabled" (checked) when NOT all its skills are disabled
+    pre_selected = set()
+    for i, cat in enumerate(categories):
+        cat_skills = [s["name"] for s in skills if (s["category"] or "uncategorized") == cat]
+        cat_labels.append(f"{cat} ({len(cat_skills)} skills)")
+        if not all(s in disabled for s in cat_skills):
+            pre_selected.add(i)
+
+    chosen = curses_checklist(
+        "Categories — toggle entire categories",
+        cat_labels, pre_selected, cancel_returns=pre_selected,
+    )
+
+    new_disabled = set(disabled)
+    for i, cat in enumerate(categories):
+        cat_skills = {s["name"] for s in skills if (s["category"] or "uncategorized") == cat}
+        if i in chosen:
+            new_disabled -= cat_skills  # category enabled → remove from disabled
+        else:
+            new_disabled |= cat_skills  # category disabled → add to disabled
+    return new_disabled
+
+
+# ─── Entry Point ──────────────────────────────────────────────────────────────
+
+def skills_command(args=None):
+    """Entry point for `hermes skills`."""
+    from hermes_cli.curses_ui import curses_checklist
+
+    config = load_config()
+    skills = _list_all_skills()
+
+    if not skills:
+        print(color("  No skills installed.", Colors.DIM))
+        return
+
+    # Step 1: Select platform
+    platform = _select_platform()
+    platform_label = PLATFORMS.get(platform, "All platforms") if platform else "All platforms"
+
+    # Step 2: Select mode — individual or by category
+    print()
+    print(color(f"  Configure for: {platform_label}", Colors.DIM))
+    print()
+    print("  1. Toggle individual skills")
+    print("  2. Toggle by category")
+    print()
+    try:
+        mode = input(color("  Select [1]: ", Colors.YELLOW)).strip() or "1"
+    except (KeyboardInterrupt, EOFError):
+        return
+
+    disabled = get_disabled_skills(config, platform)
+
+    if mode == "2":
+        new_disabled = _toggle_by_category(skills, disabled)
+    else:
+        # Build labels and map indices → skill names
+        labels = [
+            f"{s['name']}  ({s['category'] or 'uncategorized'})  —  {s['description'][:55]}"
+            for s in skills
+        ]
+        # "selected" = enabled (not disabled) — matches the [✓] convention
+        pre_selected = {i for i, s in enumerate(skills) if s["name"] not in disabled}
+        chosen = curses_checklist(
+            f"Skills for {platform_label}",
+            labels, pre_selected, cancel_returns=pre_selected,
+        )
+        # Anything NOT chosen is disabled
+        new_disabled = {skills[i]["name"] for i in range(len(skills)) if i not in chosen}
+
+    if new_disabled == disabled:
+        print(color("  No changes.", Colors.DIM))
+        return
+
+    save_disabled_skills(config, new_disabled, platform)
+    enabled_count = len(skills) - len(new_disabled)
+    print(color(f"✓ Saved: {enabled_count} enabled, {len(new_disabled)} disabled ({platform_label}).", Colors.GREEN))

hermes_cli/skills_hub.py

@@ -407,14 +407,16 @@ def do_inspect(identifier: str, console: Optional[Console] = None) -> None:
 
 
 def do_list(source_filter: str = "all", console: Optional[Console] = None) -> None:
-    """List installed skills, distinguishing builtins from hub-installed."""
+    """List installed skills, distinguishing hub, builtin, and local skills."""
     from tools.skills_hub import HubLockFile, ensure_hub_dirs
+    from tools.skills_sync import _read_manifest
     from tools.skills_tool import _find_all_skills
 
     c = console or _console
     ensure_hub_dirs()
     lock = HubLockFile()
     hub_installed = {e["name"]: e for e in lock.list_installed()}
+    builtin_names = set(_read_manifest())
 
     all_skills = _find_all_skills()
 
@@ -424,30 +426,42 @@ def do_list(source_filter: str = "all", console: Optional[Console] = None) -> No
     table.add_column("Source", style="dim")
     table.add_column("Trust", style="dim")
 
+    hub_count = 0
+    builtin_count = 0
+    local_count = 0
+
     for skill in sorted(all_skills, key=lambda s: (s.get("category") or "", s["name"])):
         name = skill["name"]
         category = skill.get("category", "")
         hub_entry = hub_installed.get(name)
 
         if hub_entry:
+            source_type = "hub"
             source_display = hub_entry.get("source", "hub")
             trust = hub_entry.get("trust_level", "community")
-        else:
+            hub_count += 1
+        elif name in builtin_names:
+            source_type = "builtin"
             source_display = "builtin"
             trust = "builtin"
+            builtin_count += 1
+        else:
+            source_type = "local"
+            source_display = "local"
+            trust = "local"
+            local_count += 1
 
-        if source_filter == "hub" and not hub_entry:
-            continue
-        if source_filter == "builtin" and hub_entry:
+        if source_filter != "all" and source_filter != source_type:
             continue
 
-        trust_style = {"builtin": "bright_cyan", "trusted": "green", "community": "yellow"}.get(trust, "dim")
+        trust_style = {"builtin": "bright_cyan", "trusted": "green", "community": "yellow", "local": "dim"}.get(trust, "dim")
         trust_label = "official" if source_display == "official" else trust
         table.add_row(name, category, source_display, f"[{trust_style}]{trust_label}[/]")
 
     c.print(table)
-    c.print(f"[dim]{len(hub_installed)} hub-installed, "
-            f"{len(all_skills) - len(hub_installed)} builtin[/]\n")
+    c.print(
+        f"[dim]{hub_count} hub-installed, {builtin_count} builtin, {local_count} local[/]\n"
+    )
 
 
 def do_audit(name: Optional[str] = None, console: Optional[Console] = None) -> None:
@@ -1014,7 +1028,7 @@ def _print_skills_help(console: Console) -> None:
         "  [cyan]search[/] <query>              Search registries for skills\n"
         "  [cyan]install[/] <identifier>        Install a skill (with security scan)\n"
         "  [cyan]inspect[/] <identifier>        Preview a skill without installing\n"
-        "  [cyan]list[/] [--source hub|builtin] List installed skills\n"
+        "  [cyan]list[/] [--source hub|builtin|local] List installed skills\n"
         "  [cyan]audit[/] [name]                Re-scan hub skills for security\n"
         "  [cyan]uninstall[/] <name>            Remove a hub-installed skill\n"
         "  [cyan]publish[/] <path> --repo <r>   Publish a skill to GitHub via PR\n"

hermes_cli/skin_engine.py

@@ -0,0 +1,630 @@
+"""Hermes CLI skin/theme engine.
+
+A data-driven skin system that lets users customize the CLI's visual appearance.
+Skins are defined as YAML files in ~/.hermes/skins/ or as built-in presets.
+No code changes are needed to add a new skin.
+
+SKIN YAML SCHEMA
+================
+
+All fields are optional. Missing values inherit from the ``default`` skin.
+
+.. code-block:: yaml
+
+    # Required: skin identity
+    name: mytheme                         # Unique skin name (lowercase, hyphens ok)
+    description: Short description        # Shown in /skin listing
+
+    # Colors: hex values for Rich markup (banner, UI, response box)
+    colors:
+      banner_border: "#CD7F32"            # Panel border color
+      banner_title: "#FFD700"             # Panel title text color
+      banner_accent: "#FFBF00"            # Section headers (Available Tools, etc.)
+      banner_dim: "#B8860B"               # Dim/muted text (separators, labels)
+      banner_text: "#FFF8DC"              # Body text (tool names, skill names)
+      ui_accent: "#FFBF00"               # General UI accent
+      ui_label: "#4dd0e1"                # UI labels
+      ui_ok: "#4caf50"                   # Success indicators
+      ui_error: "#ef5350"                # Error indicators
+      ui_warn: "#ffa726"                 # Warning indicators
+      prompt: "#FFF8DC"                  # Prompt text color
+      input_rule: "#CD7F32"              # Input area horizontal rule
+      response_border: "#FFD700"         # Response box border (ANSI)
+      session_label: "#DAA520"           # Session label color
+      session_border: "#8B8682"          # Session ID dim color
+
+    # Spinner: customize the animated spinner during API calls
+    spinner:
+      waiting_faces:                      # Faces shown while waiting for API
+        - "(⚔)"
+        - "(⛨)"
+      thinking_faces:                     # Faces shown during reasoning
+        - "(⌁)"
+        - "(<>)"
+      thinking_verbs:                     # Verbs for spinner messages
+        - "forging"
+        - "plotting"
+      wings:                              # Optional left/right spinner decorations
+        - ["⟪⚔", "⚔⟫"]                  # Each entry is [left, right] pair
+        - ["⟪▲", "▲⟫"]
+
+    # Branding: text strings used throughout the CLI
+    branding:
+      agent_name: "Hermes Agent"          # Banner title, status display
+      welcome: "Welcome message"          # Shown at CLI startup
+      goodbye: "Goodbye! ⚕"              # Shown on exit
+      response_label: " ⚕ Hermes "       # Response box header label
+      prompt_symbol: "❯ "                # Input prompt symbol
+      help_header: "(^_^)? Commands"      # /help header text
+
+    # Tool prefix: character for tool output lines (default: ┊)
+    tool_prefix: "┊"
+
+USAGE
+=====
+
+.. code-block:: python
+
+    from hermes_cli.skin_engine import get_active_skin, list_skins, set_active_skin
+
+    skin = get_active_skin()
+    print(skin.colors["banner_title"])    # "#FFD700"
+    print(skin.get_branding("agent_name"))  # "Hermes Agent"
+
+    set_active_skin("ares")               # Switch to built-in ares skin
+    set_active_skin("mytheme")            # Switch to user skin from ~/.hermes/skins/
+
+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
+
+USER SKINS
+==========
+
+Drop a YAML file in ``~/.hermes/skins/<name>.yaml`` following the schema above.
+Activate with ``/skin <name>`` in the CLI or ``display.skin: <name>`` in config.yaml.
+"""
+
+import logging
+import os
+from dataclasses import dataclass, field
+from pathlib import Path
+from typing import Any, Dict, List, Optional, Tuple
+
+logger = logging.getLogger(__name__)
+
+
+# =============================================================================
+# Skin data structure
+# =============================================================================
+
+@dataclass
+class SkinConfig:
+    """Complete skin configuration."""
+    name: str
+    description: str = ""
+    colors: Dict[str, str] = field(default_factory=dict)
+    spinner: Dict[str, Any] = field(default_factory=dict)
+    branding: Dict[str, str] = field(default_factory=dict)
+    tool_prefix: str = "┊"
+    banner_logo: str = ""    # Rich-markup ASCII art logo (replaces HERMES_AGENT_LOGO)
+    banner_hero: str = ""    # Rich-markup hero art (replaces HERMES_CADUCEUS)
+
+    def get_color(self, key: str, fallback: str = "") -> str:
+        """Get a color value with fallback."""
+        return self.colors.get(key, fallback)
+
+    def get_spinner_list(self, key: str) -> List[str]:
+        """Get a spinner list (faces, verbs, etc.)."""
+        return self.spinner.get(key, [])
+
+    def get_spinner_wings(self) -> List[Tuple[str, str]]:
+        """Get spinner wing pairs, or empty list if none."""
+        raw = self.spinner.get("wings", [])
+        result = []
+        for pair in raw:
+            if isinstance(pair, (list, tuple)) and len(pair) == 2:
+                result.append((str(pair[0]), str(pair[1])))
+        return result
+
+    def get_branding(self, key: str, fallback: str = "") -> str:
+        """Get a branding value with fallback."""
+        return self.branding.get(key, fallback)
+
+
+# =============================================================================
+# Built-in skin definitions
+# =============================================================================
+
+_BUILTIN_SKINS: Dict[str, Dict[str, Any]] = {
+    "default": {
+        "name": "default",
+        "description": "Classic Hermes — gold and kawaii",
+        "colors": {
+            "banner_border": "#CD7F32",
+            "banner_title": "#FFD700",
+            "banner_accent": "#FFBF00",
+            "banner_dim": "#B8860B",
+            "banner_text": "#FFF8DC",
+            "ui_accent": "#FFBF00",
+            "ui_label": "#4dd0e1",
+            "ui_ok": "#4caf50",
+            "ui_error": "#ef5350",
+            "ui_warn": "#ffa726",
+            "prompt": "#FFF8DC",
+            "input_rule": "#CD7F32",
+            "response_border": "#FFD700",
+            "session_label": "#DAA520",
+            "session_border": "#8B8682",
+        },
+        "spinner": {
+            # Empty = use hardcoded defaults in display.py
+        },
+        "branding": {
+            "agent_name": "Hermes Agent",
+            "welcome": "Welcome to Hermes Agent! Type your message or /help for commands.",
+            "goodbye": "Goodbye! ⚕",
+            "response_label": " ⚕ Hermes ",
+            "prompt_symbol": "❯ ",
+            "help_header": "(^_^)? Available Commands",
+        },
+        "tool_prefix": "┊",
+    },
+    "ares": {
+        "name": "ares",
+        "description": "War-god theme — crimson and bronze",
+        "colors": {
+            "banner_border": "#9F1C1C",
+            "banner_title": "#C7A96B",
+            "banner_accent": "#DD4A3A",
+            "banner_dim": "#6B1717",
+            "banner_text": "#F1E6CF",
+            "ui_accent": "#DD4A3A",
+            "ui_label": "#C7A96B",
+            "ui_ok": "#4caf50",
+            "ui_error": "#ef5350",
+            "ui_warn": "#ffa726",
+            "prompt": "#F1E6CF",
+            "input_rule": "#9F1C1C",
+            "response_border": "#C7A96B",
+            "session_label": "#C7A96B",
+            "session_border": "#6E584B",
+        },
+        "spinner": {
+            "waiting_faces": ["(⚔)", "(⛨)", "(▲)", "(<>)", "(/)"],
+            "thinking_faces": ["(⚔)", "(⛨)", "(▲)", "(⌁)", "(<>)"],
+            "thinking_verbs": [
+                "forging", "marching", "sizing the field", "holding the line",
+                "hammering plans", "tempering steel", "plotting impact", "raising the shield",
+            ],
+            "wings": [
+                ["⟪⚔", "⚔⟫"],
+                ["⟪▲", "▲⟫"],
+                ["⟪╸", "╺⟫"],
+                ["⟪⛨", "⛨⟫"],
+            ],
+        },
+        "branding": {
+            "agent_name": "Ares Agent",
+            "welcome": "Welcome to Ares Agent! Type your message or /help for commands.",
+            "goodbye": "Farewell, warrior! ⚔",
+            "response_label": " ⚔ Ares ",
+            "prompt_symbol": "⚔ ❯ ",
+            "help_header": "(⚔) Available Commands",
+        },
+        "tool_prefix": "╎",
+        "banner_logo": """[bold #A3261F] █████╗ ██████╗ ███████╗███████╗       █████╗  ██████╗ ███████╗███╗   ██╗████████╗[/]
+[bold #B73122]██╔══██╗██╔══██╗██╔════╝██╔════╝      ██╔══██╗██╔════╝ ██╔════╝████╗  ██║╚══██╔══╝[/]
+[#C93C24]███████║██████╔╝█████╗  ███████╗█████╗███████║██║  ███╗█████╗  ██╔██╗ ██║   ██║[/]
+[#D84A28]██╔══██║██╔══██╗██╔══╝  ╚════██║╚════╝██╔══██║██║   ██║██╔══╝  ██║╚██╗██║   ██║[/]
+[#E15A2D]██║  ██║██║  ██║███████╗███████║      ██║  ██║╚██████╔╝███████╗██║ ╚████║   ██║[/]
+[#EB6C32]╚═╝  ╚═╝╚═╝  ╚═╝╚══════╝╚══════╝      ╚═╝  ╚═╝ ╚═════╝ ╚══════╝╚═╝  ╚═══╝   ╚═╝[/]""",
+        "banner_hero": """[#9F1C1C]⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⣤⣤⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀[/]
+[#9F1C1C]⠀⠀⠀⠀⠀⠀⠀⠀⠀⢀⣴⣿⠟⠻⣿⣦⡀⠀⠀⠀⠀⠀⠀⠀⠀⠀[/]
+[#C7A96B]⠀⠀⠀⠀⠀⠀⠀⣠⣾⡿⠋⠀⠀⠀⠙⢿⣷⣄⠀⠀⠀⠀⠀⠀⠀[/]
+[#C7A96B]⠀⠀⠀⠀⠀⢀⣾⡿⠋⠀⠀⢠⡄⠀⠀⠙⢿⣷⡀⠀⠀⠀⠀⠀[/]
+[#DD4A3A]⠀⠀⠀⠀⣰⣿⠟⠀⠀⠀⣰⣿⣿⣆⠀⠀⠀⠻⣿⣆⠀⠀⠀⠀[/]
+[#DD4A3A]⠀⠀⠀⢰⣿⠏⠀⠀⢀⣾⡿⠉⢿⣷⡀⠀⠀⠹⣿⡆⠀⠀⠀[/]
+[#9F1C1C]⠀⠀⠀⣿⡟⠀⠀⣠⣿⠟⠀⠀⠀⠻⣿⣄⠀⠀⢻⣿⠀⠀⠀[/]
+[#9F1C1C]⠀⠀⠀⣿⡇⠀⠀⠙⠋⠀⠀⚔⠀⠀⠙⠋⠀⠀⢸⣿⠀⠀⠀[/]
+[#6B1717]⠀⠀⠀⢿⣧⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⣼⡿⠀⠀⠀[/]
+[#6B1717]⠀⠀⠀⠘⢿⣷⣄⠀⠀⠀⠀⠀⠀⠀⠀⠀⣠⣾⡿⠃⠀⠀⠀[/]
+[#C7A96B]⠀⠀⠀⠀⠈⠻⣿⣷⣦⣤⣀⣀⣤⣤⣶⣿⠿⠋⠀⠀⠀⠀[/]
+[#C7A96B]⠀⠀⠀⠀⠀⠀⠀⠉⠛⠿⠿⠿⠿⠛⠉⠀⠀⠀⠀⠀⠀⠀[/]
+[#DD4A3A]⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⚔⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀[/]
+[dim #6B1717]⠀⠀⠀⠀⠀⠀⠀⠀war god online⠀⠀⠀⠀⠀⠀⠀⠀[/]""",
+    },
+    "mono": {
+        "name": "mono",
+        "description": "Monochrome — clean grayscale",
+        "colors": {
+            "banner_border": "#555555",
+            "banner_title": "#e6edf3",
+            "banner_accent": "#aaaaaa",
+            "banner_dim": "#444444",
+            "banner_text": "#c9d1d9",
+            "ui_accent": "#aaaaaa",
+            "ui_label": "#888888",
+            "ui_ok": "#888888",
+            "ui_error": "#cccccc",
+            "ui_warn": "#999999",
+            "prompt": "#c9d1d9",
+            "input_rule": "#444444",
+            "response_border": "#aaaaaa",
+            "session_label": "#888888",
+            "session_border": "#555555",
+        },
+        "spinner": {},
+        "branding": {
+            "agent_name": "Hermes Agent",
+            "welcome": "Welcome to Hermes Agent! Type your message or /help for commands.",
+            "goodbye": "Goodbye! ⚕",
+            "response_label": " ⚕ Hermes ",
+            "prompt_symbol": "❯ ",
+            "help_header": "[?] Available Commands",
+        },
+        "tool_prefix": "┊",
+    },
+    "slate": {
+        "name": "slate",
+        "description": "Cool blue — developer-focused",
+        "colors": {
+            "banner_border": "#4169e1",
+            "banner_title": "#7eb8f6",
+            "banner_accent": "#8EA8FF",
+            "banner_dim": "#4b5563",
+            "banner_text": "#c9d1d9",
+            "ui_accent": "#7eb8f6",
+            "ui_label": "#8EA8FF",
+            "ui_ok": "#63D0A6",
+            "ui_error": "#F7A072",
+            "ui_warn": "#e6a855",
+            "prompt": "#c9d1d9",
+            "input_rule": "#4169e1",
+            "response_border": "#7eb8f6",
+            "session_label": "#7eb8f6",
+            "session_border": "#4b5563",
+        },
+        "spinner": {},
+        "branding": {
+            "agent_name": "Hermes Agent",
+            "welcome": "Welcome to Hermes Agent! Type your message or /help for commands.",
+            "goodbye": "Goodbye! ⚕",
+            "response_label": " ⚕ Hermes ",
+            "prompt_symbol": "❯ ",
+            "help_header": "(^_^)? Available Commands",
+        },
+        "tool_prefix": "┊",
+    },
+    "poseidon": {
+        "name": "poseidon",
+        "description": "Ocean-god theme — deep blue and seafoam",
+        "colors": {
+            "banner_border": "#2A6FB9",
+            "banner_title": "#A9DFFF",
+            "banner_accent": "#5DB8F5",
+            "banner_dim": "#153C73",
+            "banner_text": "#EAF7FF",
+            "ui_accent": "#5DB8F5",
+            "ui_label": "#A9DFFF",
+            "ui_ok": "#4caf50",
+            "ui_error": "#ef5350",
+            "ui_warn": "#ffa726",
+            "prompt": "#EAF7FF",
+            "input_rule": "#2A6FB9",
+            "response_border": "#5DB8F5",
+            "session_label": "#A9DFFF",
+            "session_border": "#496884",
+        },
+        "spinner": {
+            "waiting_faces": ["(≈)", "(Ψ)", "(∿)", "(◌)", "(◠)"],
+            "thinking_faces": ["(Ψ)", "(∿)", "(≈)", "(⌁)", "(◌)"],
+            "thinking_verbs": [
+                "charting currents", "sounding the depth", "reading foam lines",
+                "steering the trident", "tracking undertow", "plotting sea lanes",
+                "calling the swell", "measuring pressure",
+            ],
+            "wings": [
+                ["⟪≈", "≈⟫"],
+                ["⟪Ψ", "Ψ⟫"],
+                ["⟪∿", "∿⟫"],
+                ["⟪◌", "◌⟫"],
+            ],
+        },
+        "branding": {
+            "agent_name": "Poseidon Agent",
+            "welcome": "Welcome to Poseidon Agent! Type your message or /help for commands.",
+            "goodbye": "Fair winds! Ψ",
+            "response_label": " Ψ Poseidon ",
+            "prompt_symbol": "Ψ ❯ ",
+            "help_header": "(Ψ) Available Commands",
+        },
+        "tool_prefix": "│",
+        "banner_logo": """[bold #B8E8FF]██████╗  ██████╗ ███████╗██╗██████╗ ███████╗ ██████╗ ███╗   ██╗       █████╗  ██████╗ ███████╗███╗   ██╗████████╗[/]
+[bold #97D6FF]██╔══██╗██╔═══██╗██╔════╝██║██╔══██╗██╔════╝██╔═══██╗████╗  ██║      ██╔══██╗██╔════╝ ██╔════╝████╗  ██║╚══██╔══╝[/]
+[#75C1F6]██████╔╝██║   ██║███████╗██║██║  ██║█████╗  ██║   ██║██╔██╗ ██║█████╗███████║██║  ███╗█████╗  ██╔██╗ ██║   ██║[/]
+[#4FA2E0]██╔═══╝ ██║   ██║╚════██║██║██║  ██║██╔══╝  ██║   ██║██║╚██╗██║╚════╝██╔══██║██║   ██║██╔══╝  ██║╚██╗██║   ██║[/]
+[#2E7CC7]██║     ╚██████╔╝███████║██║██████╔╝███████╗╚██████╔╝██║ ╚████║      ██║  ██║╚██████╔╝███████╗██║ ╚████║   ██║[/]
+[#1B4F95]╚═╝      ╚═════╝ ╚══════╝╚═╝╚═════╝ ╚══════╝ ╚═════╝ ╚═╝  ╚═══╝      ╚═╝  ╚═╝ ╚═════╝ ╚══════╝╚═╝  ╚═══╝   ╚═╝[/]""",
+        "banner_hero": """[#2A6FB9]⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⢀⣀⡀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀[/]
+[#5DB8F5]⠀⠀⠀⠀⠀⠀⠀⠀⠀⣠⣾⣿⣷⣄⠀⠀⠀⠀⠀⠀⠀⠀⠀[/]
+[#5DB8F5]⠀⠀⠀⠀⠀⠀⠀⢠⣿⠏⠀Ψ⠀⠹⣿⡄⠀⠀⠀⠀⠀⠀⠀[/]
+[#A9DFFF]⠀⠀⠀⠀⠀⠀⠀⣿⡟⠀⠀⠀⠀⠀⢻⣿⠀⠀⠀⠀⠀⠀⠀[/]
+[#A9DFFF]⠀⠀⠀≈≈≈≈≈⣿⡇⠀⠀⠀⠀⠀⢸⣿≈≈≈≈≈⠀⠀⠀[/]
+[#5DB8F5]⠀⠀⠀⠀⠀⠀⠀⣿⡇⠀⠀⠀⠀⠀⢸⣿⠀⠀⠀⠀⠀⠀⠀[/]
+[#2A6FB9]⠀⠀⠀⠀⠀⠀⠀⢿⣧⠀⠀⠀⠀⠀⣼⡿⠀⠀⠀⠀⠀⠀⠀[/]
+[#2A6FB9]⠀⠀⠀⠀⠀⠀⠀⠘⢿⣷⣄⣀⣠⣾⡿⠃⠀⠀⠀⠀⠀⠀⠀[/]
+[#153C73]⠀⠀⠀⠀⠀⠀⠀⠀⠈⠻⣿⣿⡿⠟⠁⠀⠀⠀⠀⠀⠀⠀⠀[/]
+[#153C73]⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠈⠁⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀[/]
+[#5DB8F5]⠀⠀⠀⠀⠀≈≈≈≈≈≈≈≈≈≈≈≈≈≈≈⠀⠀⠀⠀⠀[/]
+[#A9DFFF]⠀⠀⠀⠀⠀⠀≈≈≈≈≈≈≈≈≈≈≈≈≈⠀⠀⠀⠀⠀⠀[/]
+[dim #153C73]⠀⠀⠀⠀⠀⠀⠀deep waters hold⠀⠀⠀⠀⠀⠀⠀[/]""",
+    },
+    "sisyphus": {
+        "name": "sisyphus",
+        "description": "Sisyphean theme — austere grayscale with persistence",
+        "colors": {
+            "banner_border": "#B7B7B7",
+            "banner_title": "#F5F5F5",
+            "banner_accent": "#E7E7E7",
+            "banner_dim": "#4A4A4A",
+            "banner_text": "#D3D3D3",
+            "ui_accent": "#E7E7E7",
+            "ui_label": "#D3D3D3",
+            "ui_ok": "#919191",
+            "ui_error": "#E7E7E7",
+            "ui_warn": "#B7B7B7",
+            "prompt": "#F5F5F5",
+            "input_rule": "#656565",
+            "response_border": "#B7B7B7",
+            "session_label": "#919191",
+            "session_border": "#656565",
+        },
+        "spinner": {
+            "waiting_faces": ["(◉)", "(◌)", "(◬)", "(⬤)", "(::)"],
+            "thinking_faces": ["(◉)", "(◬)", "(◌)", "(○)", "(●)"],
+            "thinking_verbs": [
+                "finding traction", "measuring the grade", "resetting the boulder",
+                "counting the ascent", "testing leverage", "setting the shoulder",
+                "pushing uphill", "enduring the loop",
+            ],
+            "wings": [
+                ["⟪◉", "◉⟫"],
+                ["⟪◬", "◬⟫"],
+                ["⟪◌", "◌⟫"],
+                ["⟪⬤", "⬤⟫"],
+            ],
+        },
+        "branding": {
+            "agent_name": "Sisyphus Agent",
+            "welcome": "Welcome to Sisyphus Agent! Type your message or /help for commands.",
+            "goodbye": "The boulder waits. ◉",
+            "response_label": " ◉ Sisyphus ",
+            "prompt_symbol": "◉ ❯ ",
+            "help_header": "(◉) Available Commands",
+        },
+        "tool_prefix": "│",
+        "banner_logo": """[bold #F5F5F5]███████╗██╗███████╗██╗   ██╗██████╗ ██╗  ██╗██╗   ██╗███████╗       █████╗  ██████╗ ███████╗███╗   ██╗████████╗[/]
+[bold #E7E7E7]██╔════╝██║██╔════╝╚██╗ ██╔╝██╔══██╗██║  ██║██║   ██║██╔════╝      ██╔══██╗██╔════╝ ██╔════╝████╗  ██║╚══██╔══╝[/]
+[#D7D7D7]███████╗██║███████╗ ╚████╔╝ ██████╔╝███████║██║   ██║███████╗█████╗███████║██║  ███╗█████╗  ██╔██╗ ██║   ██║[/]
+[#BFBFBF]╚════██║██║╚════██║  ╚██╔╝  ██╔═══╝ ██╔══██║██║   ██║╚════██║╚════╝██╔══██║██║   ██║██╔══╝  ██║╚██╗██║   ██║[/]
+[#8F8F8F]███████║██║███████║   ██║   ██║     ██║  ██║╚██████╔╝███████║      ██║  ██║╚██████╔╝███████╗██║ ╚████║   ██║[/]
+[#626262]╚══════╝╚═╝╚══════╝   ╚═╝   ╚═╝     ╚═╝  ╚═╝ ╚═════╝ ╚══════╝      ╚═╝  ╚═╝ ╚═════╝ ╚══════╝╚═╝  ╚═══╝   ╚═╝[/]""",
+        "banner_hero": """[#B7B7B7]⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⢀⣀⣀⣀⡀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀[/]
+[#D3D3D3]⠀⠀⠀⠀⠀⠀⠀⣠⣾⣿⣿⣿⣿⣷⣄⠀⠀⠀⠀⠀⠀⠀⠀[/]
+[#E7E7E7]⠀⠀⠀⠀⠀⠀⣾⣿⣿⣿⣿⣿⣿⣿⣷⠀⠀⠀⠀⠀⠀⠀[/]
+[#F5F5F5]⠀⠀⠀⠀⠀⢸⣿⣿⣿⣿⣿⣿⣿⣿⣿⡇⠀⠀⠀⠀⠀⠀[/]
+[#E7E7E7]⠀⠀⠀⠀⠀⠀⣿⣿⣿⣿⣿⣿⣿⣿⣿⠀⠀⠀⠀⠀⠀⠀[/]
+[#D3D3D3]⠀⠀⠀⠀⠀⠀⠘⢿⣿⣿⣿⣿⣿⡿⠃⠀⠀⠀⠀⠀⠀⠀[/]
+[#B7B7B7]⠀⠀⠀⠀⠀⠀⠀⠀⠙⠿⣿⠿⠋⠀⠀⠀⠀⠀⠀⠀⠀⠀[/]
+[#919191]⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀[/]
+[#656565]⠀⠀⠀⠀⠀⠀⠀⠀⠀⣰⡄⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀[/]
+[#656565]⠀⠀⠀⠀⠀⠀⠀⠀⣰⣿⣿⣆⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀[/]
+[#4A4A4A]⠀⠀⠀⠀⠀⠀⠀⣰⣿⣿⣿⣿⣆⠀⠀⠀⠀⠀⠀⠀⠀⠀[/]
+[#4A4A4A]⠀⠀⠀⠀⠀⣀⣴⣿⣿⣿⣿⣿⣿⣦⣀⠀⠀⠀⠀⠀⠀[/]
+[#656565]⠀⠀⠀━━━━━━━━━━━━━━━━━━━━━━━⠀⠀⠀[/]
+[dim #4A4A4A]⠀⠀⠀⠀⠀⠀⠀⠀⠀the boulder⠀⠀⠀⠀⠀⠀⠀⠀⠀[/]""",
+    },
+    "charizard": {
+        "name": "charizard",
+        "description": "Volcanic theme — burnt orange and ember",
+        "colors": {
+            "banner_border": "#C75B1D",
+            "banner_title": "#FFD39A",
+            "banner_accent": "#F29C38",
+            "banner_dim": "#7A3511",
+            "banner_text": "#FFF0D4",
+            "ui_accent": "#F29C38",
+            "ui_label": "#FFD39A",
+            "ui_ok": "#4caf50",
+            "ui_error": "#ef5350",
+            "ui_warn": "#ffa726",
+            "prompt": "#FFF0D4",
+            "input_rule": "#C75B1D",
+            "response_border": "#F29C38",
+            "session_label": "#FFD39A",
+            "session_border": "#6C4724",
+        },
+        "spinner": {
+            "waiting_faces": ["(✦)", "(▲)", "(◇)", "(<>)", "(🔥)"],
+            "thinking_faces": ["(✦)", "(▲)", "(◇)", "(⌁)", "(🔥)"],
+            "thinking_verbs": [
+                "banking into the draft", "measuring burn", "reading the updraft",
+                "tracking ember fall", "setting wing angle", "holding the flame core",
+                "plotting a hot landing", "coiling for lift",
+            ],
+            "wings": [
+                ["⟪✦", "✦⟫"],
+                ["⟪▲", "▲⟫"],
+                ["⟪◌", "◌⟫"],
+                ["⟪◇", "◇⟫"],
+            ],
+        },
+        "branding": {
+            "agent_name": "Charizard Agent",
+            "welcome": "Welcome to Charizard Agent! Type your message or /help for commands.",
+            "goodbye": "Flame out! ✦",
+            "response_label": " ✦ Charizard ",
+            "prompt_symbol": "✦ ❯ ",
+            "help_header": "(✦) Available Commands",
+        },
+        "tool_prefix": "│",
+        "banner_logo": """[bold #FFF0D4] ██████╗██╗  ██╗ █████╗ ██████╗ ██╗███████╗ █████╗ ██████╗ ██████╗        █████╗  ██████╗ ███████╗███╗   ██╗████████╗[/]
+[bold #FFD39A]██╔════╝██║  ██║██╔══██╗██╔══██╗██║╚══███╔╝██╔══██╗██╔══██╗██╔══██╗      ██╔══██╗██╔════╝ ██╔════╝████╗  ██║╚══██╔══╝[/]
+[#F29C38]██║     ███████║███████║██████╔╝██║  ███╔╝ ███████║██████╔╝██║  ██║█████╗███████║██║  ███╗█████╗  ██╔██╗ ██║   ██║[/]
+[#E2832B]██║     ██╔══██║██╔══██║██╔══██╗██║ ███╔╝  ██╔══██║██╔══██╗██║  ██║╚════╝██╔══██║██║   ██║██╔══╝  ██║╚██╗██║   ██║[/]
+[#C75B1D]╚██████╗██║  ██║██║  ██║██║  ██║██║███████╗██║  ██║██║  ██║██████╔╝      ██║  ██║╚██████╔╝███████╗██║ ╚████║   ██║[/]
+[#7A3511] ╚═════╝╚═╝  ╚═╝╚═╝  ╚═╝╚═╝  ╚═╝╚═╝╚══════╝╚═╝  ╚═╝╚═╝  ╚═╝╚═════╝       ╚═╝  ╚═╝ ╚═════╝ ╚══════╝╚═╝  ╚═══╝   ╚═╝[/]""",
+        "banner_hero": """[#FFD39A]⠀⠀⠀⠀⠀⠀⠀⠀⣀⣤⠶⠶⠶⣤⣀⠀⠀⠀⠀⠀⠀⠀⠀[/]
+[#F29C38]⠀⠀⠀⠀⠀⠀⣴⠟⠁⠀⠀⠀⠀⠈⠻⣦⠀⠀⠀⠀⠀⠀[/]
+[#F29C38]⠀⠀⠀⠀⠀⣼⠏⠀⠀⠀✦⠀⠀⠀⠀⠹⣧⠀⠀⠀⠀⠀[/]
+[#E2832B]⠀⠀⠀⠀⢰⡟⠀⠀⣀⣤⣤⣤⣀⠀⠀⠀⢻⡆⠀⠀⠀⠀[/]
+[#E2832B]⠀⠀⣠⡾⠛⠁⣠⣾⠟⠉⠀⠉⠻⣷⣄⠀⠈⠛⢷⣄⠀⠀[/]
+[#C75B1D]⠀⣼⠟⠀⢀⣾⠟⠁⠀⠀⠀⠀⠀⠈⠻⣷⡀⠀⠻⣧⠀[/]
+[#C75B1D]⢸⡟⠀⠀⣿⡟⠀⠀⠀🔥⠀⠀⠀⠀⢻⣿⠀⠀⢻⡇[/]
+[#7A3511]⠀⠻⣦⡀⠘⢿⣧⡀⠀⠀⠀⠀⠀⢀⣼⡿⠃⢀⣴⠟⠀[/]
+[#7A3511]⠀⠀⠈⠻⣦⣀⠙⢿⣷⣤⣤⣤⣾⡿⠋⣀⣴⠟⠁⠀⠀[/]
+[#C75B1D]⠀⠀⠀⠀⠈⠙⠛⠶⠤⠭⠭⠤⠶⠛⠋⠁⠀⠀⠀⠀[/]
+[#F29C38]⠀⠀⠀⠀⠀⠀⠀⠀⣰⡿⢿⣆⠀⠀⠀⠀⠀⠀⠀⠀⠀[/]
+[#F29C38]⠀⠀⠀⠀⠀⠀⠀⣼⡟⠀⠀⢻⣧⠀⠀⠀⠀⠀⠀⠀⠀[/]
+[dim #7A3511]⠀⠀⠀⠀⠀⠀⠀tail flame lit⠀⠀⠀⠀⠀⠀⠀⠀[/]""",
+    },
+}
+
+
+# =============================================================================
+# Skin loading and management
+# =============================================================================
+
+_active_skin: Optional[SkinConfig] = None
+_active_skin_name: str = "default"
+
+
+def _skins_dir() -> Path:
+    """User skins directory."""
+    home = Path(os.getenv("HERMES_HOME", Path.home() / ".hermes"))
+    return home / "skins"
+
+
+def _load_skin_from_yaml(path: Path) -> Optional[Dict[str, Any]]:
+    """Load a skin definition from a YAML file."""
+    try:
+        import yaml
+        with open(path, "r", encoding="utf-8") as f:
+            data = yaml.safe_load(f)
+        if isinstance(data, dict) and "name" in data:
+            return data
+    except Exception as e:
+        logger.debug("Failed to load skin from %s: %s", path, e)
+    return None
+
+
+def _build_skin_config(data: Dict[str, Any]) -> SkinConfig:
+    """Build a SkinConfig from a raw dict (built-in or loaded from YAML)."""
+    # Start with default values as base for missing keys
+    default = _BUILTIN_SKINS["default"]
+    colors = dict(default.get("colors", {}))
+    colors.update(data.get("colors", {}))
+    spinner = dict(default.get("spinner", {}))
+    spinner.update(data.get("spinner", {}))
+    branding = dict(default.get("branding", {}))
+    branding.update(data.get("branding", {}))
+
+    return SkinConfig(
+        name=data.get("name", "unknown"),
+        description=data.get("description", ""),
+        colors=colors,
+        spinner=spinner,
+        branding=branding,
+        tool_prefix=data.get("tool_prefix", default.get("tool_prefix", "┊")),
+        banner_logo=data.get("banner_logo", ""),
+        banner_hero=data.get("banner_hero", ""),
+    )
+
+
+def list_skins() -> List[Dict[str, str]]:
+    """List all available skins (built-in + user-installed).
+
+    Returns list of {"name": ..., "description": ..., "source": "builtin"|"user"}.
+    """
+    result = []
+    for name, data in _BUILTIN_SKINS.items():
+        result.append({
+            "name": name,
+            "description": data.get("description", ""),
+            "source": "builtin",
+        })
+
+    skins_path = _skins_dir()
+    if skins_path.is_dir():
+        for f in sorted(skins_path.glob("*.yaml")):
+            data = _load_skin_from_yaml(f)
+            if data:
+                skin_name = data.get("name", f.stem)
+                # Skip if it shadows a built-in
+                if any(s["name"] == skin_name for s in result):
+                    continue
+                result.append({
+                    "name": skin_name,
+                    "description": data.get("description", ""),
+                    "source": "user",
+                })
+
+    return result
+
+
+def load_skin(name: str) -> SkinConfig:
+    """Load a skin by name. Checks user skins first, then built-in."""
+    # Check user skins directory
+    skins_path = _skins_dir()
+    user_file = skins_path / f"{name}.yaml"
+    if user_file.is_file():
+        data = _load_skin_from_yaml(user_file)
+        if data:
+            return _build_skin_config(data)
+
+    # Check built-in skins
+    if name in _BUILTIN_SKINS:
+        return _build_skin_config(_BUILTIN_SKINS[name])
+
+    # Fallback to default
+    logger.warning("Skin '%s' not found, using default", name)
+    return _build_skin_config(_BUILTIN_SKINS["default"])
+
+
+def get_active_skin() -> SkinConfig:
+    """Get the currently active skin config (cached)."""
+    global _active_skin
+    if _active_skin is None:
+        _active_skin = load_skin(_active_skin_name)
+    return _active_skin
+
+
+def set_active_skin(name: str) -> SkinConfig:
+    """Switch the active skin. Returns the new SkinConfig."""
+    global _active_skin, _active_skin_name
+    _active_skin_name = name
+    _active_skin = load_skin(name)
+    return _active_skin
+
+
+def get_active_skin_name() -> str:
+    """Get the name of the currently active skin."""
+    return _active_skin_name
+
+
+def init_skin_from_config(config: dict) -> None:
+    """Initialize the active skin from CLI config at startup.
+
+    Call this once during CLI init with the loaded config dict.
+    """
+    display = config.get("display", {})
+    skin_name = display.get("skin", "default")
+    if isinstance(skin_name, str) and skin_name.strip():
+        set_active_skin(skin_name.strip())
+    else:
+        set_active_skin("default")

hermes_cli/status.py

@@ -77,7 +77,6 @@ def show_status(args):
     
     keys = {
         "OpenRouter": "OPENROUTER_API_KEY",
-        "Anthropic": "ANTHROPIC_API_KEY", 
         "OpenAI": "OPENAI_API_KEY",
         "Z.AI/GLM": "GLM_API_KEY",
         "Kimi": "KIMI_API_KEY",
@@ -98,6 +97,14 @@ def show_status(args):
         display = redact_key(value) if not show_all else value
         print(f"  {name:<12}  {check_mark(has_key)} {display}")
 
+    anthropic_value = (
+        get_env_value("ANTHROPIC_TOKEN")
+        or get_env_value("ANTHROPIC_API_KEY")
+        or ""
+    )
+    anthropic_display = redact_key(anthropic_value) if not show_all else anthropic_value
+    print(f"  {'Anthropic':<12}  {check_mark(bool(anthropic_value))} {anthropic_display}")
+
     # =========================================================================
     # Auth Providers (OAuth)
     # =========================================================================
@@ -208,6 +215,7 @@ def show_status(args):
         "WhatsApp": ("WHATSAPP_ENABLED", None),
         "Signal": ("SIGNAL_HTTP_URL", "SIGNAL_HOME_CHANNEL"),
         "Slack": ("SLACK_BOT_TOKEN", None),
+        "Email": ("EMAIL_ADDRESS", "EMAIL_HOME_ADDRESS"),
     }
     
     for name, (token_var, home_var) in platforms.items():
@@ -263,7 +271,7 @@ def show_status(args):
     if jobs_file.exists():
         import json
         try:
-            with open(jobs_file) as f:
+            with open(jobs_file, encoding="utf-8") as f:
                 data = json.load(f)
                 jobs = data.get("jobs", [])
                 enabled_jobs = [j for j in jobs if j.get("enabled", True)]
@@ -283,7 +291,7 @@ def show_status(args):
     if sessions_file.exists():
         import json
         try:
-            with open(sessions_file) as f:
+            with open(sessions_file, encoding="utf-8") as f:
                 data = json.load(f)
                 print(f"  Active:       {len(data)} session(s)")
         except Exception:

hermes_cli/tools_config.py

@@ -11,7 +11,7 @@ the `platform_toolsets` key.
 
 import sys
 from pathlib import Path
-from typing import Dict, List, Set
+from typing import Dict, List, Optional, Set
 
 import os
 
@@ -108,6 +108,8 @@ PLATFORMS = {
     "discord":  {"label": "💬 Discord",    "default_toolset": "hermes-discord"},
     "slack":    {"label": "💼 Slack",      "default_toolset": "hermes-slack"},
     "whatsapp": {"label": "📱 WhatsApp",   "default_toolset": "hermes-whatsapp"},
+    "signal":   {"label": "📡 Signal",     "default_toolset": "hermes-signal"},
+    "email":    {"label": "📧 Email",      "default_toolset": "hermes-email"},
 }
 
 
@@ -308,6 +310,22 @@ def _get_enabled_platforms() -> List[str]:
     return enabled
 
 
+def _platform_toolset_summary(config: dict, platforms: Optional[List[str]] = None) -> Dict[str, Set[str]]:
+    """Return a summary of enabled toolsets per platform.
+
+    When ``platforms`` is None, this uses ``_get_enabled_platforms`` to
+    auto-detect platforms. Tests can pass an explicit list to avoid relying
+    on environment variables.
+    """
+    if platforms is None:
+        platforms = _get_enabled_platforms()
+
+    summary: Dict[str, Set[str]] = {}
+    for pkey in platforms:
+        summary[pkey] = _get_platform_tools(config, pkey)
+    return summary
+
+
 def _get_platform_tools(config: dict, platform: str) -> Set[str]:
     """Resolve which individual toolset names are enabled for a platform."""
     from toolsets import resolve_toolset, TOOLSETS
@@ -447,6 +465,7 @@ def _prompt_choice(question: str, choices: list, default: int = 0) -> int:
 
 def _prompt_toolset_checklist(platform_label: str, enabled: Set[str]) -> Set[str]:
     """Multi-select checklist of toolsets. Returns set of selected toolset keys."""
+    from hermes_cli.curses_ui import curses_checklist
 
     labels = []
     for ts_key, ts_label, ts_desc in CONFIGURABLE_TOOLSETS:
@@ -455,112 +474,18 @@ def _prompt_toolset_checklist(platform_label: str, enabled: Set[str]) -> Set[str
             suffix = "  [no API key]"
         labels.append(f"{ts_label}  ({ts_desc}){suffix}")
 
-    pre_selected_indices = [
+    pre_selected = {
         i for i, (ts_key, _, _) in enumerate(CONFIGURABLE_TOOLSETS)
         if ts_key in enabled
-    ]
+    }
 
-    # Curses-based multi-select — arrow keys + space to toggle + enter to confirm.
-    # simple_term_menu has rendering bugs in tmux, iTerm, and other terminals.
-    try:
-        import curses
-        selected = set(pre_selected_indices)
-        result_holder = [None]
-
-        def _curses_checklist(stdscr):
-            curses.curs_set(0)
-            if curses.has_colors():
-                curses.start_color()
-                curses.use_default_colors()
-                curses.init_pair(1, curses.COLOR_GREEN, -1)
-                curses.init_pair(2, curses.COLOR_YELLOW, -1)
-                curses.init_pair(3, 8, -1)  # dim gray
-            cursor = 0
-            scroll_offset = 0
-
-            while True:
-                stdscr.clear()
-                max_y, max_x = stdscr.getmaxyx()
-                header = f"Tools for {platform_label}  —  ↑↓ navigate, SPACE toggle, ENTER confirm"
-                try:
-                    stdscr.addnstr(0, 0, header, max_x - 1, curses.A_BOLD | curses.color_pair(2) if curses.has_colors() else curses.A_BOLD)
-                except curses.error:
-                    pass
-
-                visible_rows = max_y - 3
-                if cursor < scroll_offset:
-                    scroll_offset = cursor
-                elif cursor >= scroll_offset + visible_rows:
-                    scroll_offset = cursor - visible_rows + 1
-
-                for draw_i, i in enumerate(range(scroll_offset, min(len(labels), scroll_offset + visible_rows))):
-                    y = draw_i + 2
-                    if y >= max_y - 1:
-                        break
-                    check = "✓" if i in selected else " "
-                    arrow = "→" if i == cursor else " "
-                    line = f" {arrow} [{check}] {labels[i]}"
-
-                    attr = curses.A_NORMAL
-                    if i == cursor:
-                        attr = curses.A_BOLD
-                        if curses.has_colors():
-                            attr |= curses.color_pair(1)
-                    try:
-                        stdscr.addnstr(y, 0, line, max_x - 1, attr)
-                    except curses.error:
-                        pass
-
-                stdscr.refresh()
-                key = stdscr.getch()
-
-                if key in (curses.KEY_UP, ord('k')):
-                    cursor = (cursor - 1) % len(labels)
-                elif key in (curses.KEY_DOWN, ord('j')):
-                    cursor = (cursor + 1) % len(labels)
-                elif key == ord(' '):
-                    if cursor in selected:
-                        selected.discard(cursor)
-                    else:
-                        selected.add(cursor)
-                elif key in (curses.KEY_ENTER, 10, 13):
-                    result_holder[0] = {CONFIGURABLE_TOOLSETS[i][0] for i in selected}
-                    return
-                elif key in (27, ord('q')):  # ESC or q
-                    result_holder[0] = enabled
-                    return
-
-        curses.wrapper(_curses_checklist)
-        return result_holder[0] if result_holder[0] is not None else enabled
-
-    except Exception:
-        pass  # fall through to numbered toggle
-
-    # Final fallback: numbered toggle (Windows without curses, etc.)
-    selected = set(pre_selected_indices)
-    print(color(f"\n  Tools for {platform_label}", Colors.YELLOW))
-    print(color("  Toggle by number, Enter to confirm.\n", Colors.DIM))
-
-    while True:
-        for i, label in enumerate(labels):
-            marker = color("[✓]", Colors.GREEN) if i in selected else "[ ]"
-            print(f"  {marker} {i + 1:>2}. {label}")
-        print()
-        try:
-            val = input(color("  Toggle # (or Enter to confirm): ", Colors.DIM)).strip()
-            if not val:
-                break
-            idx = int(val) - 1
-            if 0 <= idx < len(labels):
-                if idx in selected:
-                    selected.discard(idx)
-                else:
-                    selected.add(idx)
-        except (ValueError, KeyboardInterrupt, EOFError):
-            return enabled
-        print()
-
-    return {CONFIGURABLE_TOOLSETS[i][0] for i in selected}
+    chosen = curses_checklist(
+        f"Tools for {platform_label}",
+        labels,
+        pre_selected,
+        cancel_returns=pre_selected,
+    )
+    return {CONFIGURABLE_TOOLSETS[i][0] for i in chosen}
 
 
 # ─── Provider-Aware Configuration ────────────────────────────────────────────
@@ -874,6 +799,26 @@ def tools_command(args=None, first_install: bool = False, config: dict = None):
     enabled_platforms = _get_enabled_platforms()
 
     print()
+
+    # Non-interactive summary mode for CLI usage
+    if getattr(args, "summary", False):
+        total = len(CONFIGURABLE_TOOLSETS)
+        print(color("⚕ Tool Summary", Colors.CYAN, Colors.BOLD))
+        print()
+        summary = _platform_toolset_summary(config, enabled_platforms)
+        for pkey in enabled_platforms:
+            pinfo = PLATFORMS[pkey]
+            enabled = summary.get(pkey, set())
+            count = len(enabled)
+            print(color(f"  {pinfo['label']}", Colors.BOLD) + color(f"  ({count}/{total})", Colors.DIM))
+            if enabled:
+                for ts_key in sorted(enabled):
+                    label = next((l for k, l, _ in CONFIGURABLE_TOOLSETS if k == ts_key), ts_key)
+                    print(color(f"    ✓ {label}", Colors.GREEN))
+            else:
+                print(color("    (none enabled)", Colors.DIM))
+        print()
+        return
     print(color("⚕ Hermes Tool Configuration", Colors.CYAN, Colors.BOLD))
     print(color("  Enable or disable tools per platform.", Colors.DIM))
     print(color("  Tools that need API keys will be configured when enabled.", Colors.DIM))
@@ -941,22 +886,68 @@ def tools_command(args=None, first_install: bool = False, config: dict = None):
         platform_choices.append(f"Configure {pinfo['label']}  ({count}/{total} enabled)")
         platform_keys.append(pkey)
 
+    if len(platform_keys) > 1:
+        platform_choices.append("Configure all platforms (global)")
     platform_choices.append("Reconfigure an existing tool's provider or API key")
     platform_choices.append("Done")
 
+    # Index offsets for the extra options after per-platform entries
+    _global_idx = len(platform_keys) if len(platform_keys) > 1 else -1
+    _reconfig_idx = len(platform_keys) + (1 if len(platform_keys) > 1 else 0)
+    _done_idx = _reconfig_idx + 1
+
     while True:
         idx = _prompt_choice("Select an option:", platform_choices, default=0)
 
         # "Done" selected
-        if idx == len(platform_keys) + 1:
+        if idx == _done_idx:
             break
 
         # "Reconfigure" selected
-        if idx == len(platform_keys):
+        if idx == _reconfig_idx:
             _reconfigure_tool(config)
             print()
             continue
 
+        # "Configure all platforms (global)" selected
+        if idx == _global_idx:
+            # Use the union of all platforms' current tools as the starting state
+            all_current = set()
+            for pk in platform_keys:
+                all_current |= _get_platform_tools(config, pk)
+            new_enabled = _prompt_toolset_checklist("All platforms", all_current)
+            if new_enabled != all_current:
+                for pk in platform_keys:
+                    prev = _get_platform_tools(config, pk)
+                    added = new_enabled - prev
+                    removed = prev - new_enabled
+                    pinfo_inner = PLATFORMS[pk]
+                    if added or removed:
+                        print(color(f"  {pinfo_inner['label']}:", Colors.DIM))
+                        for ts in sorted(added):
+                            label = next((l for k, l, _ in CONFIGURABLE_TOOLSETS if k == ts), ts)
+                            print(color(f"    + {label}", Colors.GREEN))
+                        for ts in sorted(removed):
+                            label = next((l for k, l, _ in CONFIGURABLE_TOOLSETS if k == ts), ts)
+                            print(color(f"    - {label}", Colors.RED))
+                    # Configure API keys for newly enabled tools
+                    for ts_key in sorted(added):
+                        if (TOOL_CATEGORIES.get(ts_key) or TOOLSET_ENV_REQUIREMENTS.get(ts_key)):
+                            if not _toolset_has_keys(ts_key):
+                                _configure_toolset(ts_key, config)
+                    _save_platform_tools(config, pk, new_enabled)
+                save_config(config)
+                print(color("  ✓ Saved configuration for all platforms", Colors.GREEN))
+                # Update choice labels
+                for ci, pk in enumerate(platform_keys):
+                    new_count = len(_get_platform_tools(config, pk))
+                    total = len(CONFIGURABLE_TOOLSETS)
+                    platform_choices[ci] = f"Configure {PLATFORMS[pk]['label']}  ({new_count}/{total} enabled)"
+            else:
+                print(color("  No changes", Colors.DIM))
+            print()
+            continue
+
         pkey = platform_keys[idx]
         pinfo = PLATFORMS[pkey]
 

hermes_constants.py

@@ -7,3 +7,6 @@ without risk of circular imports.
 OPENROUTER_BASE_URL = "https://openrouter.ai/api/v1"
 OPENROUTER_MODELS_URL = f"{OPENROUTER_BASE_URL}/models"
 OPENROUTER_CHAT_URL = f"{OPENROUTER_BASE_URL}/chat/completions"
+
+NOUS_API_BASE_URL = "https://inference-api.nousresearch.com/v1"
+NOUS_API_CHAT_URL = f"{NOUS_API_BASE_URL}/chat/completions"

hermes_state.py

@@ -16,6 +16,7 @@ Key design decisions:
 
 import json
 import os
+import re
 import sqlite3
 import time
 from pathlib import Path
@@ -490,12 +491,16 @@ class SessionDB:
         msg_id = cursor.lastrowid
 
         # Update counters
-        is_tool_related = role == "tool" or tool_calls is not None
-        if is_tool_related:
+        # Count actual tool calls from the tool_calls list (not from tool responses).
+        # A single assistant message can contain multiple parallel tool calls.
+        num_tool_calls = 0
+        if tool_calls is not None:
+            num_tool_calls = len(tool_calls) if isinstance(tool_calls, list) else 1
+        if num_tool_calls > 0:
             self._conn.execute(
                 """UPDATE sessions SET message_count = message_count + 1,
-                   tool_call_count = tool_call_count + 1 WHERE id = ?""",
-                (session_id,),
+                   tool_call_count = tool_call_count + ? WHERE id = ?""",
+                (num_tool_calls, session_id),
             )
         else:
             self._conn.execute(
@@ -553,6 +558,32 @@ class SessionDB:
     # Search
     # =========================================================================
 
+    @staticmethod
+    def _sanitize_fts5_query(query: str) -> str:
+        """Sanitize user input for safe use in FTS5 MATCH queries.
+
+        FTS5 has its own query syntax where characters like ``"``, ``(``, ``)``,
+        ``+``, ``*``, ``{``, ``}`` and bare boolean operators (``AND``, ``OR``,
+        ``NOT``) have special meaning.  Passing raw user input directly to
+        MATCH can cause ``sqlite3.OperationalError``.
+
+        Strategy: strip characters that are only meaningful as FTS5 operators
+        and would otherwise cause syntax errors.  This preserves normal keyword
+        search while preventing crashes on inputs like ``C++``, ``"unterminated``,
+        or ``hello AND``.
+        """
+        # Remove FTS5-special characters that are not useful in keyword search
+        sanitized = re.sub(r'[+{}()"^]', " ", query)
+        # Collapse repeated * (e.g. "***") into a single one, and remove
+        # leading * (prefix-only matching requires at least one char before *)
+        sanitized = re.sub(r"\*+", "*", sanitized)
+        sanitized = re.sub(r"(^|\s)\*", r"\1", sanitized)
+        # Remove dangling boolean operators at start/end that would cause
+        # syntax errors (e.g. "hello AND" or "OR world")
+        sanitized = re.sub(r"(?i)^(AND|OR|NOT)\b\s*", "", sanitized.strip())
+        sanitized = re.sub(r"(?i)\s+(AND|OR|NOT)\s*$", "", sanitized.strip())
+        return sanitized.strip()
+
     def search_messages(
         self,
         query: str,
@@ -576,6 +607,10 @@ class SessionDB:
         if not query or not query.strip():
             return []
 
+        query = self._sanitize_fts5_query(query)
+        if not query:
+            return []
+
         if source_filter is None:
             source_filter = ["cli", "telegram", "discord", "whatsapp", "slack"]
 
@@ -615,7 +650,11 @@ class SessionDB:
             LIMIT ? OFFSET ?
         """
 
-        cursor = self._conn.execute(sql, params)
+        try:
+            cursor = self._conn.execute(sql, params)
+        except sqlite3.OperationalError:
+            # FTS5 query syntax error despite sanitization — return empty
+            return []
         matches = [dict(row) for row in cursor.fetchall()]
 
         # Add surrounding context (1 message before + after each match)

honcho_integration/cli.py

@@ -0,0 +1,765 @@
+"""CLI commands for Honcho integration management.
+
+Handles: hermes honcho setup | status | sessions | map | peer
+"""
+
+from __future__ import annotations
+
+import json
+import os
+import sys
+from pathlib import Path
+
+GLOBAL_CONFIG_PATH = Path.home() / ".honcho" / "config.json"
+HOST = "hermes"
+
+
+def _read_config() -> dict:
+    if GLOBAL_CONFIG_PATH.exists():
+        try:
+            return json.loads(GLOBAL_CONFIG_PATH.read_text(encoding="utf-8"))
+        except Exception:
+            pass
+    return {}
+
+
+def _write_config(cfg: dict) -> None:
+    GLOBAL_CONFIG_PATH.parent.mkdir(parents=True, exist_ok=True)
+    GLOBAL_CONFIG_PATH.write_text(
+        json.dumps(cfg, indent=2, ensure_ascii=False) + "\n",
+        encoding="utf-8",
+    )
+
+
+def _resolve_api_key(cfg: dict) -> str:
+    """Resolve API key with host -> root -> env fallback."""
+    host_key = ((cfg.get("hosts") or {}).get(HOST) or {}).get("apiKey")
+    return host_key or cfg.get("apiKey", "") or os.environ.get("HONCHO_API_KEY", "")
+
+
+def _prompt(label: str, default: str | None = None, secret: bool = False) -> str:
+    suffix = f" [{default}]" if default else ""
+    sys.stdout.write(f"  {label}{suffix}: ")
+    sys.stdout.flush()
+    if secret:
+        if sys.stdin.isatty():
+            import getpass
+            val = getpass.getpass(prompt="")
+        else:
+            # Non-TTY (piped input, test runners) — read plaintext
+            val = sys.stdin.readline().strip()
+    else:
+        val = sys.stdin.readline().strip()
+    return val or (default or "")
+
+
+def _ensure_sdk_installed() -> bool:
+    """Check honcho-ai is importable; offer to install if not. Returns True if ready."""
+    try:
+        import honcho  # noqa: F401
+        return True
+    except ImportError:
+        pass
+
+    print("  honcho-ai is not installed.")
+    answer = _prompt("Install it now? (honcho-ai>=2.0.1)", default="y")
+    if answer.lower() not in ("y", "yes"):
+        print("  Skipping install. Run: pip install 'honcho-ai>=2.0.1'\n")
+        return False
+
+    import subprocess
+    print("  Installing honcho-ai...", flush=True)
+    result = subprocess.run(
+        [sys.executable, "-m", "pip", "install", "honcho-ai>=2.0.1"],
+        capture_output=True,
+        text=True,
+    )
+    if result.returncode == 0:
+        print("  Installed.\n")
+        return True
+    else:
+        print(f"  Install failed:\n{result.stderr.strip()}")
+        print("  Run manually: pip install 'honcho-ai>=2.0.1'\n")
+        return False
+
+
+def cmd_setup(args) -> None:
+    """Interactive Honcho setup wizard."""
+    cfg = _read_config()
+
+    print("\nHoncho memory setup\n" + "─" * 40)
+    print("  Honcho gives Hermes persistent cross-session memory.")
+    print("  Config is shared with other hosts at ~/.honcho/config.json\n")
+
+    if not _ensure_sdk_installed():
+        return
+
+    # All writes go to hosts.hermes — root keys are managed by the user
+    # or the honcho CLI only.
+    hosts = cfg.setdefault("hosts", {})
+    hermes_host = hosts.setdefault(HOST, {})
+
+    # API key — shared credential, lives at root so all hosts can read it
+    current_key = cfg.get("apiKey", "")
+    masked = f"...{current_key[-8:]}" if len(current_key) > 8 else ("set" if current_key else "not set")
+    print(f"  Current API key: {masked}")
+    new_key = _prompt("Honcho API key (leave blank to keep current)", secret=True)
+    if new_key:
+        cfg["apiKey"] = new_key
+
+    effective_key = cfg.get("apiKey", "")
+    if not effective_key:
+        print("\n  No API key configured. Get your API key at https://app.honcho.dev")
+        print("  Run 'hermes honcho setup' again once you have a key.\n")
+        return
+
+    # Peer name
+    current_peer = hermes_host.get("peerName") or cfg.get("peerName", "")
+    new_peer = _prompt("Your name (user peer)", default=current_peer or os.getenv("USER", "user"))
+    if new_peer:
+        hermes_host["peerName"] = new_peer
+
+    current_workspace = hermes_host.get("workspace") or cfg.get("workspace", "hermes")
+    new_workspace = _prompt("Workspace ID", default=current_workspace)
+    if new_workspace:
+        hermes_host["workspace"] = new_workspace
+
+    hermes_host.setdefault("aiPeer", HOST)
+
+    # Memory mode
+    current_mode = hermes_host.get("memoryMode") or cfg.get("memoryMode", "hybrid")
+    print(f"\n  Memory mode options:")
+    print("    hybrid  — write to both Honcho and local MEMORY.md (default)")
+    print("    honcho  — Honcho only, skip MEMORY.md writes")
+    new_mode = _prompt("Memory mode", default=current_mode)
+    if new_mode in ("hybrid", "honcho"):
+        hermes_host["memoryMode"] = new_mode
+    else:
+        hermes_host["memoryMode"] = "hybrid"
+
+    # Write frequency
+    current_wf = str(hermes_host.get("writeFrequency") or cfg.get("writeFrequency", "async"))
+    print(f"\n  Write frequency options:")
+    print("    async   — background thread, no token cost (recommended)")
+    print("    turn    — sync write after every turn")
+    print("    session — batch write at session end only")
+    print("    N       — write every N turns (e.g. 5)")
+    new_wf = _prompt("Write frequency", default=current_wf)
+    try:
+        hermes_host["writeFrequency"] = int(new_wf)
+    except (ValueError, TypeError):
+        hermes_host["writeFrequency"] = new_wf if new_wf in ("async", "turn", "session") else "async"
+
+    # Recall mode
+    _raw_recall = hermes_host.get("recallMode") or cfg.get("recallMode", "hybrid")
+    current_recall = "hybrid" if _raw_recall not in ("hybrid", "context", "tools") else _raw_recall
+    print(f"\n  Recall mode options:")
+    print("    hybrid  — auto-injected context + Honcho tools available (default)")
+    print("    context — auto-injected context only, Honcho tools hidden")
+    print("    tools   — Honcho tools only, no auto-injected context")
+    new_recall = _prompt("Recall mode", default=current_recall)
+    if new_recall in ("hybrid", "context", "tools"):
+        hermes_host["recallMode"] = new_recall
+
+    # Session strategy
+    current_strat = hermes_host.get("sessionStrategy") or cfg.get("sessionStrategy", "per-session")
+    print(f"\n  Session strategy options:")
+    print("    per-session   — new Honcho session each run, named by Hermes session ID (default)")
+    print("    per-directory — one session per working directory")
+    print("    per-repo      — one session per git repository (uses repo root name)")
+    print("    global        — single session across all directories")
+    new_strat = _prompt("Session strategy", default=current_strat)
+    if new_strat in ("per-session", "per-repo", "per-directory", "global"):
+        hermes_host["sessionStrategy"] = new_strat
+
+    hermes_host.setdefault("enabled", True)
+    hermes_host.setdefault("saveMessages", True)
+
+    _write_config(cfg)
+    print(f"\n  Config written to {GLOBAL_CONFIG_PATH}")
+
+    # Test connection
+    print("  Testing connection... ", end="", flush=True)
+    try:
+        from honcho_integration.client import HonchoClientConfig, get_honcho_client, reset_honcho_client
+        reset_honcho_client()
+        hcfg = HonchoClientConfig.from_global_config()
+        get_honcho_client(hcfg)
+        print("OK")
+    except Exception as e:
+        print(f"FAILED\n  Error: {e}")
+        return
+
+    print(f"\n  Honcho is ready.")
+    print(f"  Session:   {hcfg.resolve_session_name()}")
+    print(f"  Workspace: {hcfg.workspace_id}")
+    print(f"  Peer:      {hcfg.peer_name}")
+    _mode_str = hcfg.memory_mode
+    if hcfg.peer_memory_modes:
+        overrides = ", ".join(f"{k}={v}" for k, v in hcfg.peer_memory_modes.items())
+        _mode_str = f"{hcfg.memory_mode}  (peers: {overrides})"
+    print(f"  Mode:      {_mode_str}")
+    print(f"  Frequency: {hcfg.write_frequency}")
+    print(f"\n  Honcho tools available in chat:")
+    print(f"    honcho_context  — ask Honcho a question about you (LLM-synthesized)")
+    print(f"    honcho_search       — semantic search over your history (no LLM)")
+    print(f"    honcho_profile      — your peer card, key facts (no LLM)")
+    print(f"    honcho_conclude     — persist a user fact to Honcho memory (no LLM)")
+    print(f"\n  Other commands:")
+    print(f"    hermes honcho status     — show full config")
+    print(f"    hermes honcho mode       — show or change memory mode")
+    print(f"    hermes honcho tokens     — show or set token budgets")
+    print(f"    hermes honcho identity   — seed or show AI peer identity")
+    print(f"    hermes honcho map <name> — map this directory to a session name\n")
+
+
+def cmd_status(args) -> None:
+    """Show current Honcho config and connection status."""
+    try:
+        import honcho  # noqa: F401
+    except ImportError:
+        print("  honcho-ai is not installed. Run: hermes honcho setup\n")
+        return
+
+    cfg = _read_config()
+
+    if not cfg:
+        print("  No Honcho config found at ~/.honcho/config.json")
+        print("  Run 'hermes honcho setup' to configure.\n")
+        return
+
+    try:
+        from honcho_integration.client import HonchoClientConfig, get_honcho_client
+        hcfg = HonchoClientConfig.from_global_config()
+    except Exception as e:
+        print(f"  Config error: {e}\n")
+        return
+
+    api_key = hcfg.api_key or ""
+    masked = f"...{api_key[-8:]}" if len(api_key) > 8 else ("set" if api_key else "not set")
+
+    print(f"\nHoncho status\n" + "─" * 40)
+    print(f"  Enabled:        {hcfg.enabled}")
+    print(f"  API key:        {masked}")
+    print(f"  Workspace:      {hcfg.workspace_id}")
+    print(f"  Host:           {hcfg.host}")
+    print(f"  Config path:    {GLOBAL_CONFIG_PATH}")
+    print(f"  AI peer:        {hcfg.ai_peer}")
+    print(f"  User peer:      {hcfg.peer_name or 'not set'}")
+    print(f"  Session key:    {hcfg.resolve_session_name()}")
+    print(f"  Recall mode:    {hcfg.recall_mode}")
+    print(f"  Memory mode:    {hcfg.memory_mode}")
+    if hcfg.peer_memory_modes:
+        print(f"  Per-peer modes:")
+        for peer, mode in hcfg.peer_memory_modes.items():
+            print(f"    {peer}: {mode}")
+    print(f"  Write freq:     {hcfg.write_frequency}")
+
+    if hcfg.enabled and hcfg.api_key:
+        print("\n  Connection... ", end="", flush=True)
+        try:
+            get_honcho_client(hcfg)
+            print("OK\n")
+        except Exception as e:
+            print(f"FAILED ({e})\n")
+    else:
+        reason = "disabled" if not hcfg.enabled else "no API key"
+        print(f"\n  Not connected ({reason})\n")
+
+
+def cmd_sessions(args) -> None:
+    """List known directory → session name mappings."""
+    cfg = _read_config()
+    sessions = cfg.get("sessions", {})
+
+    if not sessions:
+        print("  No session mappings configured.\n")
+        print("  Add one with: hermes honcho map <session-name>")
+        print("  Or edit ~/.honcho/config.json directly.\n")
+        return
+
+    cwd = os.getcwd()
+    print(f"\nHoncho session mappings ({len(sessions)})\n" + "─" * 40)
+    for path, name in sorted(sessions.items()):
+        marker = " ←" if path == cwd else ""
+        print(f"  {name:<30} {path}{marker}")
+    print()
+
+
+def cmd_map(args) -> None:
+    """Map current directory to a Honcho session name."""
+    if not args.session_name:
+        cmd_sessions(args)
+        return
+
+    cwd = os.getcwd()
+    session_name = args.session_name.strip()
+
+    if not session_name:
+        print("  Session name cannot be empty.\n")
+        return
+
+    import re
+    sanitized = re.sub(r'[^a-zA-Z0-9_-]', '-', session_name).strip('-')
+    if sanitized != session_name:
+        print(f"  Session name sanitized to: {sanitized}")
+        session_name = sanitized
+
+    cfg = _read_config()
+    cfg.setdefault("sessions", {})[cwd] = session_name
+    _write_config(cfg)
+    print(f"  Mapped {cwd}\n     → {session_name}\n")
+
+
+def cmd_peer(args) -> None:
+    """Show or update peer names and dialectic reasoning level."""
+    cfg = _read_config()
+    changed = False
+
+    user_name = getattr(args, "user", None)
+    ai_name = getattr(args, "ai", None)
+    reasoning = getattr(args, "reasoning", None)
+
+    REASONING_LEVELS = ("minimal", "low", "medium", "high", "max")
+
+    if user_name is None and ai_name is None and reasoning is None:
+        # Show current values
+        hosts = cfg.get("hosts", {})
+        hermes = hosts.get(HOST, {})
+        user = hermes.get('peerName') or cfg.get('peerName') or '(not set)'
+        ai = hermes.get('aiPeer') or cfg.get('aiPeer') or HOST
+        lvl = hermes.get("dialecticReasoningLevel") or cfg.get("dialecticReasoningLevel") or "low"
+        max_chars = hermes.get("dialecticMaxChars") or cfg.get("dialecticMaxChars") or 600
+        print(f"\nHoncho peers\n" + "─" * 40)
+        print(f"  User peer:   {user}")
+        print(f"    Your identity in Honcho. Messages you send build this peer's card.")
+        print(f"  AI peer:     {ai}")
+        print(f"    Hermes' identity in Honcho. Seed with 'hermes honcho identity <file>'.")
+        print(f"    Dialectic calls ask this peer questions to warm session context.")
+        print()
+        print(f"  Dialectic reasoning:  {lvl}  ({', '.join(REASONING_LEVELS)})")
+        print(f"  Dialectic cap:        {max_chars} chars\n")
+        return
+
+    if user_name is not None:
+        cfg.setdefault("hosts", {}).setdefault(HOST, {})["peerName"] = user_name.strip()
+        changed = True
+        print(f"  User peer → {user_name.strip()}")
+
+    if ai_name is not None:
+        cfg.setdefault("hosts", {}).setdefault(HOST, {})["aiPeer"] = ai_name.strip()
+        changed = True
+        print(f"  AI peer   → {ai_name.strip()}")
+
+    if reasoning is not None:
+        if reasoning not in REASONING_LEVELS:
+            print(f"  Invalid reasoning level '{reasoning}'. Options: {', '.join(REASONING_LEVELS)}")
+            return
+        cfg.setdefault("hosts", {}).setdefault(HOST, {})["dialecticReasoningLevel"] = reasoning
+        changed = True
+        print(f"  Dialectic reasoning level → {reasoning}")
+
+    if changed:
+        _write_config(cfg)
+        print(f"  Saved to {GLOBAL_CONFIG_PATH}\n")
+
+
+def cmd_mode(args) -> None:
+    """Show or set the memory mode."""
+    MODES = {
+        "hybrid": "write to both Honcho and local MEMORY.md (default)",
+        "honcho": "Honcho only — MEMORY.md writes disabled",
+    }
+    cfg = _read_config()
+    mode_arg = getattr(args, "mode", None)
+
+    if mode_arg is None:
+        current = (
+            (cfg.get("hosts") or {}).get(HOST, {}).get("memoryMode")
+            or cfg.get("memoryMode")
+            or "hybrid"
+        )
+        print(f"\nHoncho memory mode\n" + "─" * 40)
+        for m, desc in MODES.items():
+            marker = " ←" if m == current else ""
+            print(f"  {m:<8}  {desc}{marker}")
+        print(f"\n  Set with: hermes honcho mode [hybrid|honcho]\n")
+        return
+
+    if mode_arg not in MODES:
+        print(f"  Invalid mode '{mode_arg}'. Options: {', '.join(MODES)}\n")
+        return
+
+    cfg.setdefault("hosts", {}).setdefault(HOST, {})["memoryMode"] = mode_arg
+    _write_config(cfg)
+    print(f"  Memory mode → {mode_arg}  ({MODES[mode_arg]})\n")
+
+
+def cmd_tokens(args) -> None:
+    """Show or set token budget settings."""
+    cfg = _read_config()
+    hosts = cfg.get("hosts", {})
+    hermes = hosts.get(HOST, {})
+
+    context = getattr(args, "context", None)
+    dialectic = getattr(args, "dialectic", None)
+
+    if context is None and dialectic is None:
+        ctx_tokens = hermes.get("contextTokens") or cfg.get("contextTokens") or "(Honcho default)"
+        d_chars = hermes.get("dialecticMaxChars") or cfg.get("dialecticMaxChars") or 600
+        d_level = hermes.get("dialecticReasoningLevel") or cfg.get("dialecticReasoningLevel") or "low"
+        print(f"\nHoncho budgets\n" + "─" * 40)
+        print()
+        print(f"  Context     {ctx_tokens} tokens")
+        print(f"    Raw memory retrieval. Honcho returns stored facts/history about")
+        print(f"    the user and session, injected directly into the system prompt.")
+        print()
+        print(f"  Dialectic   {d_chars} chars, reasoning: {d_level}")
+        print(f"    AI-to-AI inference. Hermes asks Honcho's AI peer a question")
+        print(f"    (e.g. \"what were we working on?\") and Honcho runs its own model")
+        print(f"    to synthesize an answer. Used for first-turn session continuity.")
+        print(f"    Level controls how much reasoning Honcho spends on the answer.")
+        print(f"\n  Set with: hermes honcho tokens [--context N] [--dialectic N]\n")
+        return
+
+    changed = False
+    if context is not None:
+        cfg.setdefault("hosts", {}).setdefault(HOST, {})["contextTokens"] = context
+        print(f"  context tokens → {context}")
+        changed = True
+    if dialectic is not None:
+        cfg.setdefault("hosts", {}).setdefault(HOST, {})["dialecticMaxChars"] = dialectic
+        print(f"  dialectic cap  → {dialectic} chars")
+        changed = True
+
+    if changed:
+        _write_config(cfg)
+        print(f"  Saved to {GLOBAL_CONFIG_PATH}\n")
+
+
+def cmd_identity(args) -> None:
+    """Seed AI peer identity or show both peer representations."""
+    cfg = _read_config()
+    if not _resolve_api_key(cfg):
+        print("  No API key configured. Run 'hermes honcho setup' first.\n")
+        return
+
+    file_path = getattr(args, "file", None)
+    show = getattr(args, "show", False)
+
+    try:
+        from honcho_integration.client import HonchoClientConfig, get_honcho_client
+        from honcho_integration.session import HonchoSessionManager
+        hcfg = HonchoClientConfig.from_global_config()
+        client = get_honcho_client(hcfg)
+        mgr = HonchoSessionManager(honcho=client, config=hcfg)
+        session_key = hcfg.resolve_session_name()
+        mgr.get_or_create(session_key)
+    except Exception as e:
+        print(f"  Honcho connection failed: {e}\n")
+        return
+
+    if show:
+        # ── User peer ────────────────────────────────────────────────────────
+        user_card = mgr.get_peer_card(session_key)
+        print(f"\nUser peer ({hcfg.peer_name or 'not set'})\n" + "─" * 40)
+        if user_card:
+            for fact in user_card:
+                print(f"  {fact}")
+        else:
+            print("  No user peer card yet. Send a few messages to build one.")
+
+        # ── AI peer ──────────────────────────────────────────────────────────
+        ai_rep = mgr.get_ai_representation(session_key)
+        print(f"\nAI peer ({hcfg.ai_peer})\n" + "─" * 40)
+        if ai_rep.get("representation"):
+            print(ai_rep["representation"])
+        elif ai_rep.get("card"):
+            print(ai_rep["card"])
+        else:
+            print("  No representation built yet.")
+            print("  Run 'hermes honcho identity <file>' to seed one.")
+        print()
+        return
+
+    if not file_path:
+        print("\nHoncho identity management\n" + "─" * 40)
+        print(f"  User peer: {hcfg.peer_name or 'not set'}")
+        print(f"  AI peer:   {hcfg.ai_peer}")
+        print()
+        print("    hermes honcho identity --show        — show both peer representations")
+        print("    hermes honcho identity <file>        — seed AI peer from SOUL.md or any .md/.txt\n")
+        return
+
+    from pathlib import Path
+    p = Path(file_path).expanduser()
+    if not p.exists():
+        print(f"  File not found: {p}\n")
+        return
+
+    content = p.read_text(encoding="utf-8").strip()
+    if not content:
+        print(f"  File is empty: {p}\n")
+        return
+
+    source = p.name
+    ok = mgr.seed_ai_identity(session_key, content, source=source)
+    if ok:
+        print(f"  Seeded AI peer identity from {p.name} into session '{session_key}'")
+        print(f"  Honcho will incorporate this into {hcfg.ai_peer}'s representation over time.\n")
+    else:
+        print(f"  Failed to seed identity. Check logs for details.\n")
+
+
+def cmd_migrate(args) -> None:
+    """Step-by-step migration guide: OpenClaw native memory → Hermes + Honcho."""
+    from pathlib import Path
+
+    # ── Detect OpenClaw native memory files ──────────────────────────────────
+    cwd = Path(os.getcwd())
+    openclaw_home = Path.home() / ".openclaw"
+
+    # User peer: facts about the user
+    user_file_names = ["USER.md", "MEMORY.md"]
+    # AI peer: agent identity / configuration
+    agent_file_names = ["SOUL.md", "IDENTITY.md", "AGENTS.md", "TOOLS.md", "BOOTSTRAP.md"]
+
+    user_files: list[Path] = []
+    agent_files: list[Path] = []
+    for name in user_file_names:
+        for d in [cwd, openclaw_home]:
+            p = d / name
+            if p.exists() and p not in user_files:
+                user_files.append(p)
+    for name in agent_file_names:
+        for d in [cwd, openclaw_home]:
+            p = d / name
+            if p.exists() and p not in agent_files:
+                agent_files.append(p)
+
+    cfg = _read_config()
+    has_key = bool(_resolve_api_key(cfg))
+
+    print("\nHoncho migration: OpenClaw native memory → Hermes\n" + "─" * 50)
+    print()
+    print("  OpenClaw's native memory stores context in local markdown files")
+    print("  (USER.md, MEMORY.md, SOUL.md, ...) and injects them via QMD search.")
+    print("  Honcho replaces that with a cloud-backed, LLM-observable memory layer:")
+    print("  context is retrieved semantically, injected automatically each turn,")
+    print("  and enriched by a dialectic reasoning layer that builds over time.")
+    print()
+
+    # ── Step 1: Honcho account ────────────────────────────────────────────────
+    print("Step 1  Create a Honcho account")
+    print()
+    if has_key:
+        masked = f"...{cfg['apiKey'][-8:]}" if len(cfg["apiKey"]) > 8 else "set"
+        print(f"  Honcho API key already configured: {masked}")
+        print("  Skip to Step 2.")
+    else:
+        print("  Honcho is a cloud memory service that gives Hermes persistent memory")
+        print("  across sessions. You need an API key to use it.")
+        print()
+        print("  1. Get your API key at https://app.honcho.dev")
+        print("  2. Run:  hermes honcho setup")
+        print("     Paste the key when prompted.")
+        print()
+        answer = _prompt("  Run 'hermes honcho setup' now?", default="y")
+        if answer.lower() in ("y", "yes"):
+            cmd_setup(args)
+            cfg = _read_config()
+            has_key = bool(cfg.get("apiKey", ""))
+        else:
+            print()
+            print("  Run 'hermes honcho setup' when ready, then re-run this walkthrough.")
+
+    # ── Step 2: Detected files ────────────────────────────────────────────────
+    print()
+    print("Step 2  Detected OpenClaw memory files")
+    print()
+    if user_files or agent_files:
+        if user_files:
+            print(f"  User memory ({len(user_files)} file(s)) — will go to Honcho user peer:")
+            for f in user_files:
+                print(f"    {f}")
+        if agent_files:
+            print(f"  Agent identity ({len(agent_files)} file(s)) — will go to Honcho AI peer:")
+            for f in agent_files:
+                print(f"    {f}")
+    else:
+        print("  No OpenClaw native memory files found in cwd or ~/.openclaw/.")
+        print("  If your files are elsewhere, copy them here before continuing,")
+        print("  or seed them manually:  hermes honcho identity <path/to/file>")
+
+    # ── Step 3: Migrate user memory ───────────────────────────────────────────
+    print()
+    print("Step 3  Migrate user memory files → Honcho user peer")
+    print()
+    print("  USER.md and MEMORY.md contain facts about you that the agent should")
+    print("  remember across sessions. Honcho will store these under your user peer")
+    print("  and inject relevant excerpts into the system prompt automatically.")
+    print()
+    if user_files:
+        print(f"  Found: {', '.join(f.name for f in user_files)}")
+        print()
+        print("  These are picked up automatically the first time you run 'hermes'")
+        print("  with Honcho configured and no prior session history.")
+        print("  (Hermes calls migrate_memory_files() on first session init.)")
+        print()
+        print("  If you want to migrate them now without starting a session:")
+        for f in user_files:
+            print(f"    hermes honcho migrate  — this step handles it interactively")
+        if has_key:
+            answer = _prompt("  Upload user memory files to Honcho now?", default="y")
+            if answer.lower() in ("y", "yes"):
+                try:
+                    from honcho_integration.client import (
+                        HonchoClientConfig,
+                        get_honcho_client,
+                        reset_honcho_client,
+                    )
+                    from honcho_integration.session import HonchoSessionManager
+
+                    reset_honcho_client()
+                    hcfg = HonchoClientConfig.from_global_config()
+                    client = get_honcho_client(hcfg)
+                    mgr = HonchoSessionManager(honcho=client, config=hcfg)
+                    session_key = hcfg.resolve_session_name()
+                    mgr.get_or_create(session_key)
+                    # Upload from each directory that had user files
+                    dirs_with_files = set(str(f.parent) for f in user_files)
+                    any_uploaded = False
+                    for d in dirs_with_files:
+                        if mgr.migrate_memory_files(session_key, d):
+                            any_uploaded = True
+                    if any_uploaded:
+                        print(f"  Uploaded user memory files from: {', '.join(dirs_with_files)}")
+                    else:
+                        print("  Nothing uploaded (files may already be migrated or empty).")
+                except Exception as e:
+                    print(f"  Failed: {e}")
+        else:
+            print("  Run 'hermes honcho setup' first, then re-run this step.")
+    else:
+        print("  No user memory files detected. Nothing to migrate here.")
+
+    # ── Step 4: Seed AI identity ──────────────────────────────────────────────
+    print()
+    print("Step 4  Seed AI identity files → Honcho AI peer")
+    print()
+    print("  SOUL.md, IDENTITY.md, AGENTS.md, TOOLS.md, BOOTSTRAP.md define the")
+    print("  agent's character, capabilities, and behavioral rules. In OpenClaw")
+    print("  these are injected via file search at prompt-build time.")
+    print()
+    print("  In Hermes, they are seeded once into Honcho's AI peer through the")
+    print("  observation pipeline. Honcho builds a representation from them and")
+    print("  from every subsequent assistant message (observe_me=True). Over time")
+    print("  the representation reflects actual behavior, not just declaration.")
+    print()
+    if agent_files:
+        print(f"  Found: {', '.join(f.name for f in agent_files)}")
+        print()
+        if has_key:
+            answer = _prompt("  Seed AI identity from all detected files now?", default="y")
+            if answer.lower() in ("y", "yes"):
+                try:
+                    from honcho_integration.client import (
+                        HonchoClientConfig,
+                        get_honcho_client,
+                        reset_honcho_client,
+                    )
+                    from honcho_integration.session import HonchoSessionManager
+
+                    reset_honcho_client()
+                    hcfg = HonchoClientConfig.from_global_config()
+                    client = get_honcho_client(hcfg)
+                    mgr = HonchoSessionManager(honcho=client, config=hcfg)
+                    session_key = hcfg.resolve_session_name()
+                    mgr.get_or_create(session_key)
+                    for f in agent_files:
+                        content = f.read_text(encoding="utf-8").strip()
+                        if content:
+                            ok = mgr.seed_ai_identity(session_key, content, source=f.name)
+                            status = "seeded" if ok else "failed"
+                            print(f"    {f.name}: {status}")
+                except Exception as e:
+                    print(f"  Failed: {e}")
+        else:
+            print("  Run 'hermes honcho setup' first, then seed manually:")
+            for f in agent_files:
+                print(f"    hermes honcho identity {f}")
+    else:
+        print("  No agent identity files detected.")
+        print("  To seed manually:  hermes honcho identity <path/to/SOUL.md>")
+
+    # ── Step 5: What changes ──────────────────────────────────────────────────
+    print()
+    print("Step 5  What changes vs. OpenClaw native memory")
+    print()
+    print("  Storage")
+    print("    OpenClaw: markdown files on disk, searched via QMD at prompt-build time.")
+    print("    Hermes:   cloud-backed Honcho peers. Files can stay on disk as source")
+    print("              of truth; Honcho holds the live representation.")
+    print()
+    print("  Context injection")
+    print("    OpenClaw: file excerpts injected synchronously before each LLM call.")
+    print("    Hermes:   Honcho context fetched async at turn end, injected next turn.")
+    print("              First turn has no Honcho context; subsequent turns are loaded.")
+    print()
+    print("  Memory growth")
+    print("    OpenClaw: you edit files manually to update memory.")
+    print("    Hermes:   Honcho observes every message and updates representations")
+    print("              automatically. Files become the seed, not the live store.")
+    print()
+    print("  Honcho tools (available to the agent during conversation)")
+    print("    honcho_context   — ask Honcho a question, get a synthesized answer (LLM)")
+    print("    honcho_search        — semantic search over stored context (no LLM)")
+    print("    honcho_profile       — fast peer card snapshot (no LLM)")
+    print("    honcho_conclude      — write a conclusion/fact back to memory (no LLM)")
+    print()
+    print("  Session naming")
+    print("    OpenClaw: no persistent session concept — files are global.")
+    print("    Hermes:   per-session by default — each run gets its own session")
+    print("              Map a custom name:  hermes honcho map <session-name>")
+
+    # ── Step 6: Next steps ────────────────────────────────────────────────────
+    print()
+    print("Step 6  Next steps")
+    print()
+    if not has_key:
+        print("  1. hermes honcho setup              — configure API key (required)")
+        print("  2. hermes honcho migrate            — re-run this walkthrough")
+    else:
+        print("  1. hermes honcho status             — verify Honcho connection")
+        print("  2. hermes                           — start a session")
+        print("     (user memory files auto-uploaded on first turn if not done above)")
+        print("  3. hermes honcho identity --show    — verify AI peer representation")
+        print("  4. hermes honcho tokens             — tune context and dialectic budgets")
+        print("  5. hermes honcho mode               — view or change memory mode")
+    print()
+
+
+def honcho_command(args) -> None:
+    """Route honcho subcommands."""
+    sub = getattr(args, "honcho_command", None)
+    if sub == "setup" or sub is None:
+        cmd_setup(args)
+    elif sub == "status":
+        cmd_status(args)
+    elif sub == "sessions":
+        cmd_sessions(args)
+    elif sub == "map":
+        cmd_map(args)
+    elif sub == "peer":
+        cmd_peer(args)
+    elif sub == "mode":
+        cmd_mode(args)
+    elif sub == "tokens":
+        cmd_tokens(args)
+    elif sub == "identity":
+        cmd_identity(args)
+    elif sub == "migrate":
+        cmd_migrate(args)
+    else:
+        print(f"  Unknown honcho command: {sub}")
+        print("  Available: setup, status, sessions, map, peer, mode, tokens, identity, migrate\n")

honcho_integration/client.py

@@ -27,6 +27,40 @@ GLOBAL_CONFIG_PATH = Path.home() / ".honcho" / "config.json"
 HOST = "hermes"
 
 
+_RECALL_MODE_ALIASES = {"auto": "hybrid"}
+_VALID_RECALL_MODES = {"hybrid", "context", "tools"}
+
+
+def _normalize_recall_mode(val: str) -> str:
+    """Normalize legacy recall mode values (e.g. 'auto' → 'hybrid')."""
+    val = _RECALL_MODE_ALIASES.get(val, val)
+    return val if val in _VALID_RECALL_MODES else "hybrid"
+
+
+def _resolve_memory_mode(
+    global_val: str | dict,
+    host_val: str | dict | None,
+) -> dict:
+    """Parse memoryMode (string or object) into memory_mode + peer_memory_modes.
+
+    Resolution order: host-level wins over global.
+    String form:  applies as the default for all peers.
+    Object form:  { "default": "hybrid", "hermes": "honcho", ... }
+                  "default" key sets the fallback; other keys are per-peer overrides.
+    """
+    # Pick the winning value (host beats global)
+    val = host_val if host_val is not None else global_val
+
+    if isinstance(val, dict):
+        default = val.get("default", "hybrid")
+        overrides = {k: v for k, v in val.items() if k != "default"}
+    else:
+        default = str(val) if val else "hybrid"
+        overrides = {}
+
+    return {"memory_mode": default, "peer_memory_modes": overrides}
+
+
 @dataclass
 class HonchoClientConfig:
     """Configuration for Honcho client, resolved for a specific host."""
@@ -42,10 +76,36 @@ class HonchoClientConfig:
     # Toggles
     enabled: bool = False
     save_messages: bool = True
+    # memoryMode: default for all peers. "hybrid" / "honcho"
+    memory_mode: str = "hybrid"
+    # Per-peer overrides — any named Honcho peer. Override memory_mode when set.
+    # Config object form: "memoryMode": { "default": "hybrid", "hermes": "honcho" }
+    peer_memory_modes: dict[str, str] = field(default_factory=dict)
+
+    def peer_memory_mode(self, peer_name: str) -> str:
+        """Return the effective memory mode for a named peer.
+
+        Resolution: per-peer override → global memory_mode default.
+        """
+        return self.peer_memory_modes.get(peer_name, self.memory_mode)
+    # Write frequency: "async" (background thread), "turn" (sync per turn),
+    # "session" (flush on session end), or int (every N turns)
+    write_frequency: str | int = "async"
     # Prefetch budget
     context_tokens: int | None = None
+    # Dialectic (peer.chat) settings
+    # reasoning_level: "minimal" | "low" | "medium" | "high" | "max"
+    # Used as the default; prefetch_dialectic may bump it dynamically.
+    dialectic_reasoning_level: str = "low"
+    # Max chars of dialectic result to inject into Hermes system prompt
+    dialectic_max_chars: int = 600
+    # Recall mode: how memory retrieval works when Honcho is active.
+    # "hybrid"  — auto-injected context + Honcho tools available (model decides)
+    # "context" — auto-injected context only, Honcho tools removed
+    # "tools"   — Honcho tools only, no auto-injected context
+    recall_mode: str = "hybrid"
     # Session resolution
-    session_strategy: str = "per-directory"
+    session_strategy: str = "per-session"
     session_peer_prefix: bool = False
     sessions: dict[str, str] = field(default_factory=dict)
     # Raw global config for anything else consumers need
@@ -97,53 +157,164 @@ class HonchoClientConfig:
         )
         linked_hosts = host_block.get("linkedHosts", [])
 
-        api_key = raw.get("apiKey") or os.environ.get("HONCHO_API_KEY")
+        api_key = (
+            host_block.get("apiKey")
+            or raw.get("apiKey")
+            or os.environ.get("HONCHO_API_KEY")
+        )
+
+        environment = (
+            host_block.get("environment")
+            or raw.get("environment", "production")
+        )
 
         # Auto-enable when API key is present (unless explicitly disabled)
-        # This matches user expectations: setting an API key should activate the feature.
-        explicit_enabled = raw.get("enabled")
-        if explicit_enabled is None:
-            # Not explicitly set in config -> auto-enable if API key exists
-            enabled = bool(api_key)
+        # Host-level enabled wins, then root-level, then auto-enable if key exists.
+        host_enabled = host_block.get("enabled")
+        root_enabled = raw.get("enabled")
+        if host_enabled is not None:
+            enabled = host_enabled
+        elif root_enabled is not None:
+            enabled = root_enabled
         else:
-            # Respect explicit setting
-            enabled = explicit_enabled
+            # Not explicitly set anywhere -> auto-enable if API key exists
+            enabled = bool(api_key)
+
+        # write_frequency: accept int or string
+        raw_wf = (
+            host_block.get("writeFrequency")
+            or raw.get("writeFrequency")
+            or "async"
+        )
+        try:
+            write_frequency: str | int = int(raw_wf)
+        except (TypeError, ValueError):
+            write_frequency = str(raw_wf)
+
+        # saveMessages: host wins (None-aware since False is valid)
+        host_save = host_block.get("saveMessages")
+        save_messages = host_save if host_save is not None else raw.get("saveMessages", True)
+
+        # sessionStrategy / sessionPeerPrefix: host first, root fallback
+        session_strategy = (
+            host_block.get("sessionStrategy")
+            or raw.get("sessionStrategy", "per-session")
+        )
+        host_prefix = host_block.get("sessionPeerPrefix")
+        session_peer_prefix = (
+            host_prefix if host_prefix is not None
+            else raw.get("sessionPeerPrefix", False)
+        )
 
         return cls(
             host=host,
             workspace_id=workspace,
             api_key=api_key,
-            environment=raw.get("environment", "production"),
-            peer_name=raw.get("peerName"),
+            environment=environment,
+            peer_name=host_block.get("peerName") or raw.get("peerName"),
             ai_peer=ai_peer,
             linked_hosts=linked_hosts,
             enabled=enabled,
-            save_messages=raw.get("saveMessages", True),
-            context_tokens=raw.get("contextTokens") or host_block.get("contextTokens"),
-            session_strategy=raw.get("sessionStrategy", "per-directory"),
-            session_peer_prefix=raw.get("sessionPeerPrefix", False),
+            save_messages=save_messages,
+            **_resolve_memory_mode(
+                raw.get("memoryMode", "hybrid"),
+                host_block.get("memoryMode"),
+            ),
+            write_frequency=write_frequency,
+            context_tokens=host_block.get("contextTokens") or raw.get("contextTokens"),
+            dialectic_reasoning_level=(
+                host_block.get("dialecticReasoningLevel")
+                or raw.get("dialecticReasoningLevel")
+                or "low"
+            ),
+            dialectic_max_chars=int(
+                host_block.get("dialecticMaxChars")
+                or raw.get("dialecticMaxChars")
+                or 600
+            ),
+            recall_mode=_normalize_recall_mode(
+                host_block.get("recallMode")
+                or raw.get("recallMode")
+                or "hybrid"
+            ),
+            session_strategy=session_strategy,
+            session_peer_prefix=session_peer_prefix,
             sessions=raw.get("sessions", {}),
             raw=raw,
         )
 
-    def resolve_session_name(self, cwd: str | None = None) -> str | None:
-        """Resolve session name for a directory.
+    @staticmethod
+    def _git_repo_name(cwd: str) -> str | None:
+        """Return the git repo root directory name, or None if not in a repo."""
+        import subprocess
 
-        Checks manual overrides first, then derives from directory name.
+        try:
+            root = subprocess.run(
+                ["git", "rev-parse", "--show-toplevel"],
+                capture_output=True, text=True, cwd=cwd, timeout=5,
+            )
+            if root.returncode == 0:
+                return Path(root.stdout.strip()).name
+        except (OSError, subprocess.TimeoutExpired):
+            pass
+        return None
+
+    def resolve_session_name(
+        self,
+        cwd: str | None = None,
+        session_title: str | None = None,
+        session_id: str | None = None,
+    ) -> str | None:
+        """Resolve Honcho session name.
+
+        Resolution order:
+          1. Manual directory override from sessions map
+          2. Hermes session title (from /title command)
+          3. per-session strategy — Hermes session_id ({timestamp}_{hex})
+          4. per-repo strategy — git repo root directory name
+          5. per-directory strategy — directory basename
+          6. global strategy — workspace name
         """
+        import re
+
         if not cwd:
             cwd = os.getcwd()
 
-        # Manual override
+        # Manual override always wins
         manual = self.sessions.get(cwd)
         if manual:
             return manual
 
-        # Derive from directory basename
-        base = Path(cwd).name
-        if self.session_peer_prefix and self.peer_name:
-            return f"{self.peer_name}-{base}"
-        return base
+        # /title mid-session remap
+        if session_title:
+            sanitized = re.sub(r'[^a-zA-Z0-9_-]', '-', session_title).strip('-')
+            if sanitized:
+                if self.session_peer_prefix and self.peer_name:
+                    return f"{self.peer_name}-{sanitized}"
+                return sanitized
+
+        # per-session: inherit Hermes session_id (new Honcho session each run)
+        if self.session_strategy == "per-session" and session_id:
+            if self.session_peer_prefix and self.peer_name:
+                return f"{self.peer_name}-{session_id}"
+            return session_id
+
+        # per-repo: one Honcho session per git repository
+        if self.session_strategy == "per-repo":
+            base = self._git_repo_name(cwd) or Path(cwd).name
+            if self.session_peer_prefix and self.peer_name:
+                return f"{self.peer_name}-{base}"
+            return base
+
+        # per-directory: one Honcho session per working directory
+        if self.session_strategy in ("per-directory", "per-session"):
+            base = Path(cwd).name
+            if self.session_peer_prefix and self.peer_name:
+                return f"{self.peer_name}-{base}"
+            return base
+
+        # global: single session across all directories
+        return self.workspace_id
 
     def get_linked_workspaces(self) -> list[str]:
         """Resolve linked host keys to workspace names."""
@@ -176,9 +347,9 @@ def get_honcho_client(config: HonchoClientConfig | None = None) -> Honcho:
 
     if not config.api_key:
         raise ValueError(
-            "Honcho API key not found. Set it in ~/.honcho/config.json "
-            "or the HONCHO_API_KEY environment variable. "
-            "Get an API key from https://app.honcho.dev"
+            "Honcho API key not found. "
+            "Get your API key at https://app.honcho.dev, "
+            "then run 'hermes honcho setup' or set HONCHO_API_KEY."
         )
 
     try:

honcho_integration/session.py

@@ -2,8 +2,10 @@
 
 from __future__ import annotations
 
+import queue
 import re
 import logging
+import threading
 from dataclasses import dataclass, field
 from datetime import datetime
 from typing import Any, TYPE_CHECKING
@@ -15,6 +17,9 @@ if TYPE_CHECKING:
 
 logger = logging.getLogger(__name__)
 
+# Sentinel to signal the async writer thread to shut down
+_ASYNC_SHUTDOWN = object()
+
 
 @dataclass
 class HonchoSession:
@@ -80,7 +85,8 @@ class HonchoSessionManager:
         Args:
             honcho: Optional Honcho client. If not provided, uses the singleton.
             context_tokens: Max tokens for context() calls (None = Honcho default).
-            config: HonchoClientConfig from global config (provides peer_name, ai_peer, etc.).
+            config: HonchoClientConfig from global config (provides peer_name, ai_peer,
+                    write_frequency, memory_mode, etc.).
         """
         self._honcho = honcho
         self._context_tokens = context_tokens
@@ -89,6 +95,34 @@ class HonchoSessionManager:
         self._peers_cache: dict[str, Any] = {}
         self._sessions_cache: dict[str, Any] = {}
 
+        # Write frequency state
+        write_frequency = (config.write_frequency if config else "async")
+        self._write_frequency = write_frequency
+        self._turn_counter: int = 0
+
+        # Prefetch caches: session_key → last result (consumed once per turn)
+        self._context_cache: dict[str, dict] = {}
+        self._dialectic_cache: dict[str, str] = {}
+        self._prefetch_cache_lock = threading.Lock()
+        self._dialectic_reasoning_level: str = (
+            config.dialectic_reasoning_level if config else "low"
+        )
+        self._dialectic_max_chars: int = (
+            config.dialectic_max_chars if config else 600
+        )
+
+        # Async write queue — started lazily on first enqueue
+        self._async_queue: queue.Queue | None = None
+        self._async_thread: threading.Thread | None = None
+        if write_frequency == "async":
+            self._async_queue = queue.Queue()
+            self._async_thread = threading.Thread(
+                target=self._async_writer_loop,
+                name="honcho-async-writer",
+                daemon=True,
+            )
+            self._async_thread.start()
+
     @property
     def honcho(self) -> Honcho:
         """Get the Honcho client, initializing if needed."""
@@ -125,10 +159,12 @@ class HonchoSessionManager:
 
         session = self.honcho.session(session_id)
 
-        # Configure peer observation settings
+        # Configure peer observation settings.
+        # observe_me=True for AI peer so Honcho watches what the agent says
+        # and builds its representation over time — enabling identity formation.
         from honcho.session import SessionPeerConfig
         user_config = SessionPeerConfig(observe_me=True, observe_others=True)
-        ai_config = SessionPeerConfig(observe_me=False, observe_others=True)
+        ai_config = SessionPeerConfig(observe_me=True, observe_others=True)
 
         session.add_peers([(user_peer, user_config), (assistant_peer, ai_config)])
 
@@ -234,16 +270,11 @@ class HonchoSessionManager:
         self._cache[key] = session
         return session
 
-    def save(self, session: HonchoSession) -> None:
-        """
-        Save messages to Honcho.
-
-        Syncs only new (unsynced) messages from the local cache.
-        """
+    def _flush_session(self, session: HonchoSession) -> bool:
+        """Internal: write unsynced messages to Honcho synchronously."""
         if not session.messages:
-            return
+            return True
 
-        # Get the Honcho session and peers
         user_peer = self._get_or_create_peer(session.user_peer_id)
         assistant_peer = self._get_or_create_peer(session.assistant_peer_id)
         honcho_session = self._sessions_cache.get(session.honcho_session_id)
@@ -253,11 +284,9 @@ class HonchoSessionManager:
                 session.honcho_session_id, user_peer, assistant_peer
             )
 
-        # Only send new messages (those without a '_synced' flag)
         new_messages = [m for m in session.messages if not m.get("_synced")]
-
         if not new_messages:
-            return
+            return True
 
         honcho_messages = []
         for msg in new_messages:
@@ -269,13 +298,106 @@ class HonchoSessionManager:
             for msg in new_messages:
                 msg["_synced"] = True
             logger.debug("Synced %d messages to Honcho for %s", len(honcho_messages), session.key)
+            self._cache[session.key] = session
+            return True
         except Exception as e:
             for msg in new_messages:
                 msg["_synced"] = False
             logger.error("Failed to sync messages to Honcho: %s", e)
+            self._cache[session.key] = session
+            return False
 
-        # Update cache
-        self._cache[session.key] = session
+    def _async_writer_loop(self) -> None:
+        """Background daemon thread: drains the async write queue."""
+        while True:
+            try:
+                item = self._async_queue.get(timeout=5)
+                if item is _ASYNC_SHUTDOWN:
+                    break
+
+                first_error: Exception | None = None
+                try:
+                    success = self._flush_session(item)
+                except Exception as e:
+                    success = False
+                    first_error = e
+
+                if success:
+                    continue
+
+                if first_error is not None:
+                    logger.warning("Honcho async write failed, retrying once: %s", first_error)
+                else:
+                    logger.warning("Honcho async write failed, retrying once")
+
+                import time as _time
+                _time.sleep(2)
+
+                try:
+                    retry_success = self._flush_session(item)
+                except Exception as e2:
+                    logger.error("Honcho async write retry failed, dropping batch: %s", e2)
+                    continue
+
+                if not retry_success:
+                    logger.error("Honcho async write retry failed, dropping batch")
+            except queue.Empty:
+                continue
+            except Exception as e:
+                logger.error("Honcho async writer error: %s", e)
+
+    def save(self, session: HonchoSession) -> None:
+        """Save messages to Honcho, respecting write_frequency.
+
+        write_frequency modes:
+          "async"   — enqueue for background thread (zero blocking, zero token cost)
+          "turn"    — flush synchronously every turn
+          "session" — defer until flush_session() is called explicitly
+          N (int)   — flush every N turns
+        """
+        self._turn_counter += 1
+        wf = self._write_frequency
+
+        if wf == "async":
+            if self._async_queue is not None:
+                self._async_queue.put(session)
+        elif wf == "turn":
+            self._flush_session(session)
+        elif wf == "session":
+            # Accumulate; caller must call flush_all() at session end
+            pass
+        elif isinstance(wf, int) and wf > 0:
+            if self._turn_counter % wf == 0:
+                self._flush_session(session)
+
+    def flush_all(self) -> None:
+        """Flush all pending unsynced messages for all cached sessions.
+
+        Called at session end for "session" write_frequency, or to force
+        a sync before process exit regardless of mode.
+        """
+        for session in list(self._cache.values()):
+            try:
+                self._flush_session(session)
+            except Exception as e:
+                logger.error("Honcho flush_all error for %s: %s", session.key, e)
+
+        # Drain async queue synchronously if it exists
+        if self._async_queue is not None:
+            while not self._async_queue.empty():
+                try:
+                    item = self._async_queue.get_nowait()
+                    if item is not _ASYNC_SHUTDOWN:
+                        self._flush_session(item)
+                except queue.Empty:
+                    break
+
+    def shutdown(self) -> None:
+        """Gracefully shut down the async writer thread."""
+        if self._async_queue is not None and self._async_thread is not None:
+            self.flush_all()
+            self._async_queue.put(_ASYNC_SHUTDOWN)
+            self._async_thread.join(timeout=10)
 
     def delete(self, key: str) -> bool:
         """Delete a session from local cache."""
@@ -305,49 +427,163 @@ class HonchoSessionManager:
         # get_or_create will create a fresh session
         session = self.get_or_create(new_key)
 
-        # Cache under both original key and timestamped key
+        # Cache under the original key so callers find it by the expected name
         self._cache[key] = session
-        self._cache[new_key] = session
 
         logger.info("Created new session for %s (honcho: %s)", key, session.honcho_session_id)
         return session
 
-    def get_user_context(self, session_key: str, query: str) -> str:
+    _REASONING_LEVELS = ("minimal", "low", "medium", "high", "max")
+
+    def _dynamic_reasoning_level(self, query: str) -> str:
         """
-        Query Honcho's dialectic chat for user context.
+        Pick a reasoning level based on message complexity.
+
+        Uses the configured default as a floor; bumps up for longer or
+        more complex messages so Honcho applies more inference where it matters.
+
+          < 120 chars  → default (typically "low")
+          120–400 chars → one level above default (cap at "high")
+          > 400 chars  → two levels above default (cap at "high")
+
+        "max" is never selected automatically — reserve it for explicit config.
+        """
+        levels = self._REASONING_LEVELS
+        default_idx = levels.index(self._dialectic_reasoning_level) if self._dialectic_reasoning_level in levels else 1
+        n = len(query)
+        if n < 120:
+            bump = 0
+        elif n < 400:
+            bump = 1
+        else:
+            bump = 2
+        # Cap at "high" (index 3) for auto-selection
+        idx = min(default_idx + bump, 3)
+        return levels[idx]
+
+    def dialectic_query(
+        self, session_key: str, query: str,
+        reasoning_level: str | None = None,
+        peer: str = "user",
+    ) -> str:
+        """
+        Query Honcho's dialectic endpoint about a peer.
+
+        Runs an LLM on Honcho's backend against the target peer's full
+        representation. Higher latency than context() — call async via
+        prefetch_dialectic() to avoid blocking the response.
 
         Args:
-            session_key: The session key to get context for.
-            query: Natural language question about the user.
+            session_key: The session key to query against.
+            query: Natural language question.
+            reasoning_level: Override the config default. If None, uses
+                             _dynamic_reasoning_level(query).
+            peer: Which peer to query — "user" (default) or "ai".
 
         Returns:
-            Honcho's response about the user.
+            Honcho's synthesized answer, or empty string on failure.
         """
         session = self._cache.get(session_key)
         if not session:
-            return "No session found for this context."
+            return ""
 
-        user_peer = self._get_or_create_peer(session.user_peer_id)
+        peer_id = session.assistant_peer_id if peer == "ai" else session.user_peer_id
+        target_peer = self._get_or_create_peer(peer_id)
+        level = reasoning_level or self._dynamic_reasoning_level(query)
 
         try:
-            return user_peer.chat(query)
+            result = target_peer.chat(query, reasoning_level=level) or ""
+            # Apply Hermes-side char cap before caching
+            if result and self._dialectic_max_chars and len(result) > self._dialectic_max_chars:
+                result = result[:self._dialectic_max_chars].rsplit(" ", 1)[0] + " …"
+            return result
         except Exception as e:
-            logger.error("Failed to get user context from Honcho: %s", e)
-            return f"Unable to retrieve user context: {e}"
+            logger.warning("Honcho dialectic query failed: %s", e)
+            return ""
+
+    def prefetch_dialectic(self, session_key: str, query: str) -> None:
+        """
+        Fire a dialectic_query in a background thread, caching the result.
+
+        Non-blocking. The result is available via pop_dialectic_result()
+        on the next call (typically the following turn). Reasoning level
+        is selected dynamically based on query complexity.
+
+        Args:
+            session_key: The session key to query against.
+            query: The user's current message, used as the query.
+        """
+        def _run():
+            result = self.dialectic_query(session_key, query)
+            if result:
+                self.set_dialectic_result(session_key, result)
+
+        t = threading.Thread(target=_run, name="honcho-dialectic-prefetch", daemon=True)
+        t.start()
+
+    def set_dialectic_result(self, session_key: str, result: str) -> None:
+        """Store a prefetched dialectic result in a thread-safe way."""
+        if not result:
+            return
+        with self._prefetch_cache_lock:
+            self._dialectic_cache[session_key] = result
+
+    def pop_dialectic_result(self, session_key: str) -> str:
+        """
+        Return and clear the cached dialectic result for this session.
+
+        Returns empty string if no result is ready yet.
+        """
+        with self._prefetch_cache_lock:
+            return self._dialectic_cache.pop(session_key, "")
+
+    def prefetch_context(self, session_key: str, user_message: str | None = None) -> None:
+        """
+        Fire get_prefetch_context in a background thread, caching the result.
+
+        Non-blocking. Consumed next turn via pop_context_result(). This avoids
+        a synchronous HTTP round-trip blocking every response.
+        """
+        def _run():
+            result = self.get_prefetch_context(session_key, user_message)
+            if result:
+                self.set_context_result(session_key, result)
+
+        t = threading.Thread(target=_run, name="honcho-context-prefetch", daemon=True)
+        t.start()
+
+    def set_context_result(self, session_key: str, result: dict[str, str]) -> None:
+        """Store a prefetched context result in a thread-safe way."""
+        if not result:
+            return
+        with self._prefetch_cache_lock:
+            self._context_cache[session_key] = result
+
+    def pop_context_result(self, session_key: str) -> dict[str, str]:
+        """
+        Return and clear the cached context result for this session.
+
+        Returns empty dict if no result is ready yet (first turn).
+        """
+        with self._prefetch_cache_lock:
+            return self._context_cache.pop(session_key, {})
 
     def get_prefetch_context(self, session_key: str, user_message: str | None = None) -> dict[str, str]:
         """
-        Pre-fetch user context using Honcho's context() method.
+        Pre-fetch user and AI peer context from Honcho.
 
-        Single API call that returns the user's representation
-        and peer card, using semantic search based on the user's message.
+        Fetches peer_representation and peer_card for both peers. search_query
+        is intentionally omitted — it would only affect additional excerpts
+        that this code does not consume, and passing the raw message exposes
+        conversation content in server access logs.
 
         Args:
             session_key: The session key to get context for.
-            user_message: The user's message for semantic search.
+            user_message: Unused; kept for call-site compatibility.
 
         Returns:
-            Dictionary with 'representation' and 'card' keys.
+            Dictionary with 'representation', 'card', 'ai_representation',
+            and 'ai_card' keys.
         """
         session = self._cache.get(session_key)
         if not session:
@@ -357,23 +593,35 @@ class HonchoSessionManager:
         if not honcho_session:
             return {}
 
+        result: dict[str, str] = {}
         try:
             ctx = honcho_session.context(
                 summary=False,
                 tokens=self._context_tokens,
                 peer_target=session.user_peer_id,
-                search_query=user_message,
+                peer_perspective=session.assistant_peer_id,
             )
-            # peer_card is list[str] in SDK v2, join for prompt injection
             card = ctx.peer_card or []
-            card_str = "\n".join(card) if isinstance(card, list) else str(card)
-            return {
-                "representation": ctx.peer_representation or "",
-                "card": card_str,
-            }
+            result["representation"] = ctx.peer_representation or ""
+            result["card"] = "\n".join(card) if isinstance(card, list) else str(card)
         except Exception as e:
-            logger.warning("Failed to fetch context from Honcho: %s", e)
-            return {}
+            logger.warning("Failed to fetch user context from Honcho: %s", e)
+
+        # Also fetch AI peer's own representation so Hermes knows itself.
+        try:
+            ai_ctx = honcho_session.context(
+                summary=False,
+                tokens=self._context_tokens,
+                peer_target=session.assistant_peer_id,
+                peer_perspective=session.user_peer_id,
+            )
+            ai_card = ai_ctx.peer_card or []
+            result["ai_representation"] = ai_ctx.peer_representation or ""
+            result["ai_card"] = "\n".join(ai_card) if isinstance(ai_card, list) else str(ai_card)
+        except Exception as e:
+            logger.debug("Failed to fetch AI peer context from Honcho: %s", e)
+
+        return result
 
     def migrate_local_history(self, session_key: str, messages: list[dict[str, Any]]) -> bool:
         """
@@ -388,21 +636,17 @@ class HonchoSessionManager:
         Returns:
             True if upload succeeded, False otherwise.
         """
-        sanitized = self._sanitize_id(session_key)
-        honcho_session = self._sessions_cache.get(sanitized)
+        session = self._cache.get(session_key)
+        if not session:
+            logger.warning("No local session cached for '%s', skipping migration", session_key)
+            return False
+
+        honcho_session = self._sessions_cache.get(session.honcho_session_id)
         if not honcho_session:
             logger.warning("No Honcho session cached for '%s', skipping migration", session_key)
             return False
 
-        # Resolve user peer for attribution
-        parts = session_key.split(":", 1)
-        channel = parts[0] if len(parts) > 1 else "default"
-        chat_id = parts[1] if len(parts) > 1 else session_key
-        user_peer_id = self._sanitize_id(f"user-{channel}-{chat_id}")
-        user_peer = self._peers_cache.get(user_peer_id)
-        if not user_peer:
-            logger.warning("No user peer cached for '%s', skipping migration", user_peer_id)
-            return False
+        user_peer = self._get_or_create_peer(session.user_peer_id)
 
         content_bytes = self._format_migration_transcript(session_key, messages)
         first_ts = messages[0].get("timestamp") if messages else None
@@ -471,29 +715,45 @@ class HonchoSessionManager:
         if not memory_path.exists():
             return False
 
-        sanitized = self._sanitize_id(session_key)
-        honcho_session = self._sessions_cache.get(sanitized)
+        session = self._cache.get(session_key)
+        if not session:
+            logger.warning("No local session cached for '%s', skipping memory migration", session_key)
+            return False
+
+        honcho_session = self._sessions_cache.get(session.honcho_session_id)
         if not honcho_session:
             logger.warning("No Honcho session cached for '%s', skipping memory migration", session_key)
             return False
 
-        # Resolve user peer for attribution
-        parts = session_key.split(":", 1)
-        channel = parts[0] if len(parts) > 1 else "default"
-        chat_id = parts[1] if len(parts) > 1 else session_key
-        user_peer_id = self._sanitize_id(f"user-{channel}-{chat_id}")
-        user_peer = self._peers_cache.get(user_peer_id)
-        if not user_peer:
-            logger.warning("No user peer cached for '%s', skipping memory migration", user_peer_id)
-            return False
+        user_peer = self._get_or_create_peer(session.user_peer_id)
+        assistant_peer = self._get_or_create_peer(session.assistant_peer_id)
 
         uploaded = False
         files = [
-            ("MEMORY.md", "consolidated_memory.md", "Long-term agent notes and preferences"),
-            ("USER.md", "user_profile.md", "User profile and preferences"),
+            (
+                "MEMORY.md",
+                "consolidated_memory.md",
+                "Long-term agent notes and preferences",
+                user_peer,
+                "user",
+            ),
+            (
+                "USER.md",
+                "user_profile.md",
+                "User profile and preferences",
+                user_peer,
+                "user",
+            ),
+            (
+                "SOUL.md",
+                "agent_soul.md",
+                "Agent persona and identity configuration",
+                assistant_peer,
+                "ai",
+            ),
         ]
 
-        for filename, upload_name, description in files:
+        for filename, upload_name, description, target_peer, target_kind in files:
             filepath = memory_path / filename
             if not filepath.exists():
                 continue
@@ -515,16 +775,204 @@ class HonchoSessionManager:
             try:
                 honcho_session.upload_file(
                     file=(upload_name, wrapped.encode("utf-8"), "text/plain"),
-                    peer=user_peer,
-                    metadata={"source": "local_memory", "original_file": filename},
+                    peer=target_peer,
+                    metadata={
+                        "source": "local_memory",
+                        "original_file": filename,
+                        "target_peer": target_kind,
+                    },
+                )
+                logger.info(
+                    "Uploaded %s to Honcho for %s (%s peer)",
+                    filename,
+                    session_key,
+                    target_kind,
                 )
-                logger.info("Uploaded %s to Honcho for %s", filename, session_key)
                 uploaded = True
             except Exception as e:
                 logger.error("Failed to upload %s to Honcho: %s", filename, e)
 
         return uploaded
 
+    def get_peer_card(self, session_key: str) -> list[str]:
+        """
+        Fetch the user peer's card — a curated list of key facts.
+
+        Fast, no LLM reasoning. Returns raw structured facts Honcho has
+        inferred about the user (name, role, preferences, patterns).
+        Empty list if unavailable.
+        """
+        session = self._cache.get(session_key)
+        if not session:
+            return []
+
+        honcho_session = self._sessions_cache.get(session.honcho_session_id)
+        if not honcho_session:
+            return []
+
+        try:
+            ctx = honcho_session.context(
+                summary=False,
+                tokens=200,
+                peer_target=session.user_peer_id,
+                peer_perspective=session.assistant_peer_id,
+            )
+            card = ctx.peer_card or []
+            return card if isinstance(card, list) else [str(card)]
+        except Exception as e:
+            logger.debug("Failed to fetch peer card from Honcho: %s", e)
+            return []
+
+    def search_context(self, session_key: str, query: str, max_tokens: int = 800) -> str:
+        """
+        Semantic search over Honcho session context.
+
+        Returns raw excerpts ranked by relevance to the query. No LLM
+        reasoning — cheaper and faster than dialectic_query. Good for
+        factual lookups where the model will do its own synthesis.
+
+        Args:
+            session_key: Session to search against.
+            query: Search query for semantic matching.
+            max_tokens: Token budget for returned content.
+
+        Returns:
+            Relevant context excerpts as a string, or empty string if none.
+        """
+        session = self._cache.get(session_key)
+        if not session:
+            return ""
+
+        honcho_session = self._sessions_cache.get(session.honcho_session_id)
+        if not honcho_session:
+            return ""
+
+        try:
+            ctx = honcho_session.context(
+                summary=False,
+                tokens=max_tokens,
+                peer_target=session.user_peer_id,
+                peer_perspective=session.assistant_peer_id,
+                search_query=query,
+            )
+            parts = []
+            if ctx.peer_representation:
+                parts.append(ctx.peer_representation)
+            card = ctx.peer_card or []
+            if card:
+                facts = card if isinstance(card, list) else [str(card)]
+                parts.append("\n".join(f"- {f}" for f in facts))
+            return "\n\n".join(parts)
+        except Exception as e:
+            logger.debug("Honcho search_context failed: %s", e)
+            return ""
+
+    def create_conclusion(self, session_key: str, content: str) -> bool:
+        """Write a conclusion about the user back to Honcho.
+
+        Conclusions are facts the AI peer observes about the user —
+        preferences, corrections, clarifications, project context.
+        They feed into the user's peer card and representation.
+
+        Args:
+            session_key: Session to associate the conclusion with.
+            content: The conclusion text (e.g. "User prefers dark mode").
+
+        Returns:
+            True on success, False on failure.
+        """
+        if not content or not content.strip():
+            return False
+
+        session = self._cache.get(session_key)
+        if not session:
+            logger.warning("No session cached for '%s', skipping conclusion", session_key)
+            return False
+
+        assistant_peer = self._get_or_create_peer(session.assistant_peer_id)
+        try:
+            conclusions_scope = assistant_peer.conclusions_of(session.user_peer_id)
+            conclusions_scope.create([{
+                "content": content.strip(),
+                "session_id": session.honcho_session_id,
+            }])
+            logger.info("Created conclusion for %s: %s", session_key, content[:80])
+            return True
+        except Exception as e:
+            logger.error("Failed to create conclusion: %s", e)
+            return False
+
+    def seed_ai_identity(self, session_key: str, content: str, source: str = "manual") -> bool:
+        """
+        Seed the AI peer's Honcho representation from text content.
+
+        Useful for priming AI identity from SOUL.md, exported chats, or
+        any structured description. The content is sent as an assistant
+        peer message so Honcho's reasoning model can incorporate it.
+
+        Args:
+            session_key: The session key to associate with.
+            content: The identity/persona content to seed.
+            source: Metadata tag for the source (e.g. "soul_md", "export").
+
+        Returns:
+            True on success, False on failure.
+        """
+        if not content or not content.strip():
+            return False
+
+        session = self._cache.get(session_key)
+        if not session:
+            logger.warning("No session cached for '%s', skipping AI seed", session_key)
+            return False
+
+        assistant_peer = self._get_or_create_peer(session.assistant_peer_id)
+        try:
+            wrapped = (
+                f"<ai_identity_seed>\n"
+                f"<source>{source}</source>\n"
+                f"\n"
+                f"{content.strip()}\n"
+                f"</ai_identity_seed>"
+            )
+            assistant_peer.add_message("assistant", wrapped)
+            logger.info("Seeded AI identity from '%s' into %s", source, session_key)
+            return True
+        except Exception as e:
+            logger.error("Failed to seed AI identity: %s", e)
+            return False
+
+    def get_ai_representation(self, session_key: str) -> dict[str, str]:
+        """
+        Fetch the AI peer's current Honcho representation.
+
+        Returns:
+            Dict with 'representation' and 'card' keys, empty strings if unavailable.
+        """
+        session = self._cache.get(session_key)
+        if not session:
+            return {"representation": "", "card": ""}
+
+        honcho_session = self._sessions_cache.get(session.honcho_session_id)
+        if not honcho_session:
+            return {"representation": "", "card": ""}
+
+        try:
+            ctx = honcho_session.context(
+                summary=False,
+                tokens=self._context_tokens,
+                peer_target=session.assistant_peer_id,
+                peer_perspective=session.user_peer_id,
+            )
+            ai_card = ctx.peer_card or []
+            return {
+                "representation": ctx.peer_representation or "",
+                "card": "\n".join(ai_card) if isinstance(ai_card, list) else str(ai_card),
+            }
+        except Exception as e:
+            logger.debug("Failed to fetch AI representation: %s", e)
+            return {"representation": "", "card": ""}
+
     def list_sessions(self) -> list[dict[str, Any]]:
         """List all cached sessions."""
         return [

landingpage/index.html

@@ -19,7 +19,10 @@
     <link href="https://fonts.googleapis.com/css2?family=Inter:wght@300;400;500;600;700&family=JetBrains+Mono:wght@400;500&display=swap" rel="stylesheet">
     
     <link rel="stylesheet" href="style.css">
-    <link rel="icon" href="data:image/svg+xml,<svg xmlns='http://www.w3.org/2000/svg' viewBox='0 0 100 100'><text y='.9em' font-size='90'>⚕</text></svg>">
+    <link rel="icon" type="image/x-icon" href="favicon.ico">
+    <link rel="icon" type="image/png" sizes="32x32" href="favicon-32x32.png">
+    <link rel="icon" type="image/png" sizes="16x16" href="favicon-16x16.png">
+    <link rel="apple-touch-icon" sizes="180x180" href="apple-touch-icon.png">
 </head>
 <body>
     <!-- Ambient glow effects -->

mini_swe_runner.py

@@ -189,29 +189,30 @@ class MiniSWERunner:
         )
         self.logger = logging.getLogger(__name__)
         
-        # Initialize OpenAI client - defaults to OpenRouter
-        from openai import OpenAI
-        
-        client_kwargs = {}
-        
-        # Default to OpenRouter if no base_url provided
-        if base_url:
-            client_kwargs["base_url"] = base_url
+        # Initialize LLM client via centralized provider router.
+        # If explicit api_key/base_url are provided (e.g. from CLI args),
+        # construct directly.  Otherwise use the router for OpenRouter.
+        if api_key or base_url:
+            from openai import OpenAI
+            client_kwargs = {
+                "base_url": base_url or "https://openrouter.ai/api/v1",
+                "api_key": api_key or os.getenv(
+                    "OPENROUTER_API_KEY",
+                    os.getenv("ANTHROPIC_API_KEY",
+                              os.getenv("OPENAI_API_KEY", ""))),
+            }
+            self.client = OpenAI(**client_kwargs)
         else:
-            client_kwargs["base_url"] = "https://openrouter.ai/api/v1"
-
-
-        
-        # Handle API key - OpenRouter is the primary provider
-        if api_key:
-            client_kwargs["api_key"] = api_key
-        else:
-            client_kwargs["api_key"] = os.getenv(
-                "OPENROUTER_API_KEY",
-                os.getenv("ANTHROPIC_API_KEY", os.getenv("OPENAI_API_KEY", ""))
-            )
-        
-        self.client = OpenAI(**client_kwargs)
+            from agent.auxiliary_client import resolve_provider_client
+            self.client, _ = resolve_provider_client("openrouter", model=model)
+            if self.client is None:
+                # Fallback: try auto-detection
+                self.client, _ = resolve_provider_client("auto", model=model)
+            if self.client is None:
+                from openai import OpenAI
+                self.client = OpenAI(
+                    base_url="https://openrouter.ai/api/v1",
+                    api_key=os.getenv("OPENROUTER_API_KEY", ""))
         
         # Environment will be created per-task
         self.env = None

model_tools.py

@@ -266,6 +266,7 @@ def handle_function_call(
     function_args: Dict[str, Any],
     task_id: Optional[str] = None,
     user_task: Optional[str] = None,
+    enabled_tools: Optional[List[str]] = None,
 ) -> str:
     """
     Main function call dispatcher that routes calls to the tool registry.
@@ -275,19 +276,36 @@ def handle_function_call(
         function_args: Arguments for the function.
         task_id: Unique identifier for terminal/browser session isolation.
         user_task: The user's original task (for browser_snapshot context).
+        enabled_tools: Tool names enabled for this session.  When provided,
+                       execute_code uses this list to determine which sandbox
+                       tools to generate.  Falls back to the process-global
+                       ``_last_resolved_tool_names`` for backward compat.
 
     Returns:
         Function result as a JSON string.
     """
+    # Notify the read-loop tracker when a non-read/search tool runs,
+    # so the *consecutive* counter resets (reads after other work are fine).
+    _READ_SEARCH_TOOLS = {"read_file", "search_files"}
+    if function_name not in _READ_SEARCH_TOOLS:
+        try:
+            from tools.file_tools import notify_other_tool_call
+            notify_other_tool_call(task_id or "default")
+        except Exception:
+            pass  # file_tools may not be loaded yet
+
     try:
         if function_name in _AGENT_LOOP_TOOLS:
             return json.dumps({"error": f"{function_name} must be handled by the agent loop"})
 
         if function_name == "execute_code":
+            # Prefer the caller-provided list so subagents can't overwrite
+            # the parent's tool set via the process-global.
+            sandbox_enabled = enabled_tools if enabled_tools is not None else _last_resolved_tool_names
             return registry.dispatch(
                 function_name, function_args,
                 task_id=task_id,
-                enabled_tools=_last_resolved_tool_names,
+                enabled_tools=sandbox_enabled,
             )
 
         return registry.dispatch(

optional-skills/health/DESCRIPTION.md

@@ -0,0 +1 @@
+Health, wellness, and biometric integration skills — BCI wearables, neurofeedback, sleep tracking, and cognitive state monitoring.

optional-skills/health/neuroskill-bci/SKILL.md

@@ -0,0 +1,458 @@
+---
+name: neuroskill-bci
+description: >
+  Connect to a running NeuroSkill instance and incorporate the user's real-time
+  cognitive and emotional state (focus, relaxation, mood, cognitive load, drowsiness,
+  heart rate, HRV, sleep staging, and 40+ derived EXG scores) into responses.
+  Requires a BCI wearable (Muse 2/S or OpenBCI) and the NeuroSkill desktop app
+  running locally.
+version: 1.0.0
+author: Hermes Agent + Nous Research
+license: MIT
+metadata:
+  hermes:
+    tags: [BCI, neurofeedback, health, focus, EEG, cognitive-state, biometrics, neuroskill]
+    category: health
+    related_skills: []
+---
+
+# NeuroSkill BCI Integration
+
+Connect Hermes to a running [NeuroSkill](https://neuroskill.com/) instance to read
+real-time brain and body metrics from a BCI wearable. Use this to give
+cognitively-aware responses, suggest interventions, and track mental performance
+over time.
+
+> **⚠️ Research Use Only** — NeuroSkill is an open-source research tool. It is
+> NOT a medical device and has NOT been cleared by the FDA, CE, or any regulatory
+> body. Never use these metrics for clinical diagnosis or treatment.
+
+See `references/metrics.md` for the full metric reference, `references/protocols.md`
+for intervention protocols, and `references/api.md` for the WebSocket/HTTP API.
+
+---
+
+## Prerequisites
+
+- **Node.js 20+** installed (`node --version`)
+- **NeuroSkill desktop app** running with a connected BCI device
+- **BCI hardware**: Muse 2, Muse S, or OpenBCI (4-channel EEG + PPG + IMU via BLE)
+- `npx neuroskill status` returns data without errors
+
+### Verify Setup
+```bash
+node --version                    # Must be 20+
+npx neuroskill status             # Full system snapshot
+npx neuroskill status --json      # Machine-parseable JSON
+```
+
+If `npx neuroskill status` returns an error, tell the user:
+- Make sure the NeuroSkill desktop app is open
+- Ensure the BCI device is powered on and connected via Bluetooth
+- Check signal quality — green indicators in NeuroSkill (≥0.7 per electrode)
+- If `command not found`, install Node.js 20+
+
+---
+
+## CLI Reference: `npx neuroskill <command>`
+
+All commands support `--json` (raw JSON, pipe-safe) and `--full` (human summary + JSON).
+
+| Command | Description |
+|---------|-------------|
+| `status` | Full system snapshot: device, scores, bands, ratios, sleep, history |
+| `session [N]` | Single session breakdown with first/second half trends (0=most recent) |
+| `sessions` | List all recorded sessions across all days |
+| `search` | ANN similarity search for neurally similar historical moments |
+| `compare` | A/B session comparison with metric deltas and trend analysis |
+| `sleep [N]` | Sleep stage classification (Wake/N1/N2/N3/REM) with analysis |
+| `label "text"` | Create a timestamped annotation at the current moment |
+| `search-labels "query"` | Semantic vector search over past labels |
+| `interactive "query"` | Cross-modal 4-layer graph search (text → EXG → labels) |
+| `listen` | Real-time event streaming (default 5s, set `--seconds N`) |
+| `umap` | 3D UMAP projection of session embeddings |
+| `calibrate` | Open calibration window and start a profile |
+| `timer` | Launch focus timer (Pomodoro/Deep Work/Short Focus presets) |
+| `notify "title" "body"` | Send an OS notification via the NeuroSkill app |
+| `raw '{json}'` | Raw JSON passthrough to the server |
+
+### Global Flags
+| Flag | Description |
+|------|-------------|
+| `--json` | Raw JSON output (no ANSI, pipe-safe) |
+| `--full` | Human summary + colorized JSON |
+| `--port <N>` | Override server port (default: auto-discover, usually 8375) |
+| `--ws` | Force WebSocket transport |
+| `--http` | Force HTTP transport |
+| `--k <N>` | Nearest neighbors count (search, search-labels) |
+| `--seconds <N>` | Duration for listen (default: 5) |
+| `--trends` | Show per-session metric trends (sessions) |
+| `--dot` | Graphviz DOT output (interactive) |
+
+---
+
+## 1. Checking Current State
+
+### Get Live Metrics
+```bash
+npx neuroskill status --json
+```
+
+**Always use `--json`** for reliable parsing. The default output is colorized
+human-readable text.
+
+### Key Fields in the Response
+
+The `scores` object contains all live metrics (0–1 scale unless noted):
+
+```jsonc
+{
+  "scores": {
+    "focus": 0.70,           // β / (α + θ) — sustained attention
+    "relaxation": 0.40,      // α / (β + θ) — calm wakefulness
+    "engagement": 0.60,      // active mental investment
+    "meditation": 0.52,      // alpha + stillness + HRV coherence
+    "mood": 0.55,            // composite from FAA, TAR, BAR
+    "cognitive_load": 0.33,  // frontal θ / temporal α · f(FAA, TBR)
+    "drowsiness": 0.10,      // TAR + TBR + falling spectral centroid
+    "hr": 68.2,              // heart rate in bpm (from PPG)
+    "snr": 14.3,             // signal-to-noise ratio in dB
+    "stillness": 0.88,       // 0–1; 1 = perfectly still
+    "faa": 0.042,            // Frontal Alpha Asymmetry (+ = approach)
+    "tar": 0.56,             // Theta/Alpha Ratio
+    "bar": 0.53,             // Beta/Alpha Ratio
+    "tbr": 1.06,             // Theta/Beta Ratio (ADHD proxy)
+    "apf": 10.1,             // Alpha Peak Frequency in Hz
+    "coherence": 0.614,      // inter-hemispheric coherence
+    "bands": {
+      "rel_delta": 0.28, "rel_theta": 0.18,
+      "rel_alpha": 0.32, "rel_beta": 0.17, "rel_gamma": 0.05
+    }
+  }
+}
+```
+
+Also includes: `device` (state, battery, firmware), `signal_quality` (per-electrode 0–1),
+`session` (duration, epochs), `embeddings`, `labels`, `sleep` summary, and `history`.
+
+### Interpreting the Output
+
+Parse the JSON and translate metrics into natural language. Never report raw
+numbers alone — always give them meaning:
+
+**DO:**
+> "Your focus is solid right now at 0.70 — that's flow state territory. Heart
+> rate is steady at 68 bpm and your FAA is positive, which suggests good
+> approach motivation. Great time to tackle something complex."
+
+**DON'T:**
+> "Focus: 0.70, Relaxation: 0.40, HR: 68"
+
+Key interpretation thresholds (see `references/metrics.md` for the full guide):
+- **Focus > 0.70** → flow state territory, protect it
+- **Focus < 0.40** → suggest a break or protocol
+- **Drowsiness > 0.60** → fatigue warning, micro-sleep risk
+- **Relaxation < 0.30** → stress intervention needed
+- **Cognitive Load > 0.70 sustained** → mind dump or break
+- **TBR > 1.5** → theta-dominant, reduced executive control
+- **FAA < 0** → withdrawal/negative affect — consider FAA rebalancing
+- **SNR < 3 dB** → unreliable signal, suggest electrode repositioning
+
+---
+
+## 2. Session Analysis
+
+### Single Session Breakdown
+```bash
+npx neuroskill session --json         # most recent session
+npx neuroskill session 1 --json       # previous session
+npx neuroskill session 0 --json | jq '{focus: .metrics.focus, trend: .trends.focus}'
+```
+
+Returns full metrics with **first-half vs second-half trends** (`"up"`, `"down"`, `"flat"`).
+Use this to describe how a session evolved:
+
+> "Your focus started at 0.64 and climbed to 0.76 by the end — a clear upward trend.
+> Cognitive load dropped from 0.38 to 0.28, suggesting the task became more automatic
+> as you settled in."
+
+### List All Sessions
+```bash
+npx neuroskill sessions --json
+npx neuroskill sessions --trends      # show per-session metric trends
+```
+
+---
+
+## 3. Historical Search
+
+### Neural Similarity Search
+```bash
+npx neuroskill search --json                    # auto: last session, k=5
+npx neuroskill search --k 10 --json             # 10 nearest neighbors
+npx neuroskill search --start <UTC> --end <UTC> --json
+```
+
+Finds moments in history that are neurally similar using HNSW approximate
+nearest-neighbor search over 128-D ZUNA embeddings. Returns distance statistics,
+temporal distribution (hour of day), and top matching days.
+
+Use this when the user asks:
+- "When was I last in a state like this?"
+- "Find my best focus sessions"
+- "When do I usually crash in the afternoon?"
+
+### Semantic Label Search
+```bash
+npx neuroskill search-labels "deep focus" --k 10 --json
+npx neuroskill search-labels "stress" --json | jq '[.results[].EXG_metrics.tbr]'
+```
+
+Searches label text using vector embeddings (Xenova/bge-small-en-v1.5). Returns
+matching labels with their associated EXG metrics at the time of labeling.
+
+### Cross-Modal Graph Search
+```bash
+npx neuroskill interactive "deep focus" --json
+npx neuroskill interactive "deep focus" --dot | dot -Tsvg > graph.svg
+```
+
+4-layer graph: query → text labels → EXG points → nearby labels. Use `--k-text`,
+`--k-EXG`, `--reach <minutes>` to tune.
+
+---
+
+## 4. Session Comparison
+```bash
+npx neuroskill compare --json                   # auto: last 2 sessions
+npx neuroskill compare --a-start <UTC> --a-end <UTC> --b-start <UTC> --b-end <UTC> --json
+```
+
+Returns metric deltas with absolute change, percentage change, and direction for
+~50 metrics. Also includes `insights.improved[]` and `insights.declined[]` arrays,
+sleep staging for both sessions, and a UMAP job ID.
+
+Interpret comparisons with context — mention trends, not just deltas:
+> "Yesterday you had two strong focus blocks (10am and 2pm). Today you've had one
+> starting around 11am that's still going. Your overall engagement is higher today
+> but there have been more stress spikes — your stress index jumped 15% and
+> FAA dipped negative more often."
+
+```bash
+# Sort metrics by improvement percentage
+npx neuroskill compare --json | jq '.insights.deltas | to_entries | sort_by(.value.pct) | reverse'
+```
+
+---
+
+## 5. Sleep Data
+```bash
+npx neuroskill sleep --json                     # last 24 hours
+npx neuroskill sleep 0 --json                   # most recent sleep session
+npx neuroskill sleep --start <UTC> --end <UTC> --json
+```
+
+Returns epoch-by-epoch sleep staging (5-second windows) with analysis:
+- **Stage codes**: 0=Wake, 1=N1, 2=N2, 3=N3 (deep), 4=REM
+- **Analysis**: efficiency_pct, onset_latency_min, rem_latency_min, bout counts
+- **Healthy targets**: N3 15–25%, REM 20–25%, efficiency >85%, onset <20 min
+
+```bash
+npx neuroskill sleep --json | jq '.summary | {n3: .n3_epochs, rem: .rem_epochs}'
+npx neuroskill sleep --json | jq '.analysis.efficiency_pct'
+```
+
+Use this when the user mentions sleep, tiredness, or recovery.
+
+---
+
+## 6. Labeling Moments
+```bash
+npx neuroskill label "breakthrough"
+npx neuroskill label "studying algorithms"
+npx neuroskill label "post-meditation"
+npx neuroskill label --json "focus block start"   # returns label_id
+```
+
+Auto-label moments when:
+- User reports a breakthrough or insight
+- User starts a new task type (e.g., "switching to code review")
+- User completes a significant protocol
+- User asks you to mark the current moment
+- A notable state transition occurs (entering/leaving flow)
+
+Labels are stored in a database and indexed for later retrieval via `search-labels`
+and `interactive` commands.
+
+---
+
+## 7. Real-Time Streaming
+```bash
+npx neuroskill listen --seconds 30 --json
+npx neuroskill listen --seconds 5 --json | jq '[.[] | select(.event == "scores")]'
+```
+
+Streams live WebSocket events (EXG, PPG, IMU, scores, labels) for the specified
+duration. Requires WebSocket connection (not available with `--http`).
+
+Use this for continuous monitoring scenarios or to observe metric changes in real-time
+during a protocol.
+
+---
+
+## 8. UMAP Visualization
+```bash
+npx neuroskill umap --json                      # auto: last 2 sessions
+npx neuroskill umap --a-start <UTC> --a-end <UTC> --b-start <UTC> --b-end <UTC> --json
+```
+
+GPU-accelerated 3D UMAP projection of ZUNA embeddings. The `separation_score`
+indicates how neurally distinct two sessions are:
+- **> 1.5** → Sessions are neurally distinct (different brain states)
+- **< 0.5** → Similar brain states across both sessions
+
+---
+
+## 9. Proactive State Awareness
+
+### Session Start Check
+At the beginning of a session, optionally run a status check if the user mentions
+they're wearing their device or asks about their state:
+```bash
+npx neuroskill status --json
+```
+
+Inject a brief state summary:
+> "Quick check-in: focus is building at 0.62, relaxation is good at 0.55, and your
+> FAA is positive — approach motivation is engaged. Looks like a solid start."
+
+### When to Proactively Mention State
+
+Mention cognitive state **only** when:
+- User explicitly asks ("How am I doing?", "Check my focus")
+- User reports difficulty concentrating, stress, or fatigue
+- A critical threshold is crossed (drowsiness > 0.70, focus < 0.30 sustained)
+- User is about to do something cognitively demanding and asks for readiness
+
+**Do NOT** interrupt flow state to report metrics. If focus > 0.75, protect the
+session — silence is the correct response.
+
+---
+
+## 10. Suggesting Protocols
+
+When metrics indicate a need, suggest a protocol from `references/protocols.md`.
+Always ask before starting — never interrupt flow state:
+
+> "Your focus has been declining for the past 15 minutes and TBR is climbing past
+> 1.5 — signs of theta dominance and mental fatigue. Want me to walk you through
+> a Theta-Beta Neurofeedback Anchor? It's a 90-second exercise that uses rhythmic
+> counting and breath to suppress theta and lift beta."
+
+Key triggers:
+- **Focus < 0.40, TBR > 1.5** → Theta-Beta Neurofeedback Anchor or Box Breathing
+- **Relaxation < 0.30, stress_index high** → Cardiac Coherence or 4-7-8 Breathing
+- **Cognitive Load > 0.70 sustained** → Cognitive Load Offload (mind dump)
+- **Drowsiness > 0.60** → Ultradian Reset or Wake Reset
+- **FAA < 0 (negative)** → FAA Rebalancing
+- **Flow State (focus > 0.75, engagement > 0.70)** → Do NOT interrupt
+- **High stillness + headache_index** → Neck Release Sequence
+- **Low RMSSD (< 25ms)** → Vagal Toning
+
+---
+
+## 11. Additional Tools
+
+### Focus Timer
+```bash
+npx neuroskill timer --json
+```
+Launches the Focus Timer window with Pomodoro (25/5), Deep Work (50/10), or
+Short Focus (15/5) presets.
+
+### Calibration
+```bash
+npx neuroskill calibrate
+npx neuroskill calibrate --profile "Eyes Open"
+```
+Opens the calibration window. Useful when signal quality is poor or the user
+wants to establish a personalized baseline.
+
+### OS Notifications
+```bash
+npx neuroskill notify "Break Time" "Your focus has been declining for 20 minutes"
+```
+
+### Raw JSON Passthrough
+```bash
+npx neuroskill raw '{"command":"status"}' --json
+```
+For any server command not yet mapped to a CLI subcommand.
+
+---
+
+## Error Handling
+
+| Error | Likely Cause | Fix |
+|-------|-------------|-----|
+| `npx neuroskill status` hangs | NeuroSkill app not running | Open NeuroSkill desktop app |
+| `device.state: "disconnected"` | BCI device not connected | Check Bluetooth, device battery |
+| All scores return 0 | Poor electrode contact | Reposition headband, moisten electrodes |
+| `signal_quality` values < 0.7 | Loose electrodes | Adjust fit, clean electrode contacts |
+| SNR < 3 dB | Noisy signal | Minimize head movement, check environment |
+| `command not found: npx` | Node.js not installed | Install Node.js 20+ |
+
+---
+
+## Example Interactions
+
+**"How am I doing right now?"**
+```bash
+npx neuroskill status --json
+```
+→ Interpret scores naturally, mentioning focus, relaxation, mood, and any notable
+  ratios (FAA, TBR). Suggest an action only if metrics indicate a need.
+
+**"I can't concentrate"**
+```bash
+npx neuroskill status --json
+```
+→ Check if metrics confirm it (high theta, low beta, rising TBR, high drowsiness).
+→ If confirmed, suggest an appropriate protocol from `references/protocols.md`.
+→ If metrics look fine, the issue may be motivational rather than neurological.
+
+**"Compare my focus today vs yesterday"**
+```bash
+npx neuroskill compare --json
+```
+→ Interpret trends, not just numbers. Mention what improved, what declined, and
+  possible causes.
+
+**"When was I last in a flow state?"**
+```bash
+npx neuroskill search-labels "flow" --json
+npx neuroskill search --json
+```
+→ Report timestamps, associated metrics, and what the user was doing (from labels).
+
+**"How did I sleep?"**
+```bash
+npx neuroskill sleep --json
+```
+→ Report sleep architecture (N3%, REM%, efficiency), compare to healthy targets,
+  and note any issues (high wake epochs, low REM).
+
+**"Mark this moment — I just had a breakthrough"**
+```bash
+npx neuroskill label "breakthrough"
+```
+→ Confirm label saved. Optionally note the current metrics to remember the state.
+
+---
+
+## References
+
+- [NeuroSkill Paper — arXiv:2603.03212](https://arxiv.org/abs/2603.03212) (Kosmyna & Hauptmann, MIT Media Lab)
+- [NeuroSkill Desktop App](https://github.com/NeuroSkill-com/skill) (GPLv3)
+- [NeuroLoop CLI Companion](https://github.com/NeuroSkill-com/neuroloop) (GPLv3)
+- [MIT Media Lab Project](https://www.media.mit.edu/projects/neuroskill/overview/)

optional-skills/health/neuroskill-bci/references/api.md

@@ -0,0 +1,286 @@
+# NeuroSkill WebSocket & HTTP API Reference
+
+NeuroSkill runs a local server (default port **8375**) discoverable via mDNS
+(`_skill._tcp`). It exposes both WebSocket and HTTP endpoints.
+
+---
+
+## Server Discovery
+
+```bash
+# Auto-discovery (built into the CLI — usually just works)
+npx neuroskill status --json
+
+# Manual port discovery
+NEURO_PORT=$(lsof -i -n -P | grep neuroskill | grep LISTEN | awk '{print $9}' | cut -d: -f2 | head -1)
+echo "NeuroSkill on port: $NEURO_PORT"
+```
+
+The CLI auto-discovers the port. Use `--port <N>` to override.
+
+---
+
+## HTTP REST Endpoints
+
+### Universal Command Tunnel
+```bash
+# POST / — accepts any command as JSON
+curl -s -X POST http://127.0.0.1:8375/ \
+  -H "Content-Type: application/json" \
+  -d '{"command":"status"}'
+```
+
+### Convenience Endpoints
+| Method | Endpoint | Description |
+|--------|----------|-------------|
+| GET | `/v1/status` | System status |
+| GET | `/v1/sessions` | List sessions |
+| POST | `/v1/label` | Create label |
+| POST | `/v1/search` | ANN search |
+| POST | `/v1/compare` | A/B comparison |
+| POST | `/v1/sleep` | Sleep staging |
+| POST | `/v1/notify` | OS notification |
+| POST | `/v1/say` | Text-to-speech |
+| POST | `/v1/calibrate` | Open calibration |
+| POST | `/v1/timer` | Open focus timer |
+| GET | `/v1/dnd` | Get DND status |
+| POST | `/v1/dnd` | Force DND on/off |
+| GET | `/v1/calibrations` | List calibration profiles |
+| POST | `/v1/calibrations` | Create profile |
+| GET | `/v1/calibrations/{id}` | Get profile |
+| PATCH | `/v1/calibrations/{id}` | Update profile |
+| DELETE | `/v1/calibrations/{id}` | Delete profile |
+
+---
+
+## WebSocket Events (Broadcast)
+
+Connect to `ws://127.0.0.1:8375/` to receive real-time events:
+
+### EXG (Raw EEG Samples)
+```json
+{"event": "EXG", "electrode": 0, "samples": [12.3, -4.1, ...], "timestamp": 1740412800.512}
+```
+
+### PPG (Photoplethysmography)
+```json
+{"event": "PPG", "channel": 0, "samples": [...], "timestamp": 1740412800.512}
+```
+
+### IMU (Inertial Measurement Unit)
+```json
+{"event": "IMU", "ax": 0.01, "ay": -0.02, "az": 9.81, "gx": 0.1, "gy": -0.05, "gz": 0.02}
+```
+
+### Scores (Computed Metrics)
+```json
+{
+  "event": "scores",
+  "focus": 0.70, "relaxation": 0.40, "engagement": 0.60,
+  "rel_delta": 0.28, "rel_theta": 0.18, "rel_alpha": 0.32,
+  "rel_beta": 0.17, "hr": 68.2, "snr": 14.3
+}
+```
+
+### EXG Bands (Spectral Analysis)
+```json
+{"event": "EXG-bands", "channels": [...], "faa": 0.12}
+```
+
+### Labels
+```json
+{"event": "label", "label_id": 42, "text": "meditation start", "created_at": 1740413100}
+```
+
+### Device Status
+```json
+{"event": "muse-status", "state": "connected"}
+```
+
+---
+
+## JSON Response Formats
+
+### `status`
+```jsonc
+{
+  "command": "status", "ok": true,
+  "device": {
+    "state": "connected",     // "connected" | "connecting" | "disconnected"
+    "name": "Muse-A1B2",
+    "battery": 73,
+    "firmware": "1.3.4",
+    "EXG_samples": 195840,
+    "ppg_samples": 30600,
+    "imu_samples": 122400
+  },
+  "session": {
+    "start_utc": 1740412800,
+    "duration_secs": 1847,
+    "n_epochs": 369
+  },
+  "signal_quality": {
+    "tp9": 0.95, "af7": 0.88, "af8": 0.91, "tp10": 0.97
+  },
+  "scores": {
+    "focus": 0.70, "relaxation": 0.40, "engagement": 0.60,
+    "meditation": 0.52, "mood": 0.55, "cognitive_load": 0.33,
+    "drowsiness": 0.10, "hr": 68.2, "snr": 14.3, "stillness": 0.88,
+    "bands": { "rel_delta": 0.28, "rel_theta": 0.18, "rel_alpha": 0.32, "rel_beta": 0.17, "rel_gamma": 0.05 },
+    "faa": 0.042, "tar": 0.56, "bar": 0.53, "tbr": 1.06,
+    "apf": 10.1, "coherence": 0.614, "mu_suppression": 0.031
+  },
+  "embeddings": { "today": 342, "total": 14820, "recording_days": 31 },
+  "labels": { "total": 58, "recent": [{"id": 42, "text": "meditation start", "created_at": 1740413100}] },
+  "sleep": { "total_epochs": 1054, "wake_epochs": 134, "n1_epochs": 89, "n2_epochs": 421, "n3_epochs": 298, "rem_epochs": 112, "epoch_secs": 5 },
+  "history": { "total_sessions": 63, "recording_days": 31, "current_streak_days": 7, "total_recording_hours": 94.2, "longest_session_min": 187, "avg_session_min": 89 }
+}
+```
+
+### `sessions`
+```jsonc
+{
+  "command": "sessions", "ok": true,
+  "sessions": [
+    { "day": "20260224", "start_utc": 1740412800, "end_utc": 1740415510, "n_epochs": 541 },
+    { "day": "20260223", "start_utc": 1740380100, "end_utc": 1740382665, "n_epochs": 513 }
+  ]
+}
+```
+
+### `session` (single session breakdown)
+```jsonc
+{
+  "ok": true,
+  "metrics": { "focus": 0.70, "relaxation": 0.40, "n_epochs": 541 /* ... ~50 metrics */ },
+  "first":   { "focus": 0.64 /* first-half averages */ },
+  "second":  { "focus": 0.76 /* second-half averages */ },
+  "trends":  { "focus": "up", "relaxation": "down" /* "up" | "down" | "flat" */ }
+}
+```
+
+### `compare` (A/B comparison)
+```jsonc
+{
+  "command": "compare", "ok": true,
+  "insights": {
+    "deltas": {
+      "focus": { "a": 0.62, "b": 0.71, "abs": 0.09, "pct": 14.5, "direction": "up" },
+      "relaxation": { "a": 0.45, "b": 0.38, "abs": -0.07, "pct": -15.6, "direction": "down" }
+    },
+    "improved": ["focus", "engagement"],
+    "declined": ["relaxation"]
+  },
+  "sleep_a": { /* sleep summary for session A */ },
+  "sleep_b": { /* sleep summary for session B */ },
+  "umap": { "job_id": "abc123" }
+}
+```
+
+### `search` (ANN similarity)
+```jsonc
+{
+  "command": "search", "ok": true,
+  "result": {
+    "results": [{
+      "neighbors": [{ "distance": 0.12, "metadata": {"device": "Muse-A1B2", "date": "20260223"} }]
+    }],
+    "analysis": {
+      "distance_stats": { "mean": 0.15, "min": 0.08, "max": 0.42 },
+      "temporal_distribution": { /* hour-of-day distribution */ },
+      "top_days": [["20260223", 5], ["20260222", 3]]
+    }
+  }
+}
+```
+
+### `sleep` (sleep staging)
+```jsonc
+{
+  "command": "sleep", "ok": true,
+  "summary": { "total_epochs": 1054, "wake_epochs": 134, "n1_epochs": 89, "n2_epochs": 421, "n3_epochs": 298, "rem_epochs": 112, "epoch_secs": 5 },
+  "analysis": { "efficiency_pct": 87.3, "onset_latency_min": 12.5, "rem_latency_min": 65.0, "bouts": { /* wake/n3/rem bout counts and durations */ } },
+  "epochs": [{ "utc": 1740380100, "stage": 0, "rel_delta": 0.15, "rel_theta": 0.22, "rel_alpha": 0.38, "rel_beta": 0.20 }]
+}
+```
+
+### `label`
+```json
+{"command": "label", "ok": true, "label_id": 42}
+```
+
+### `search-labels` (semantic search)
+```jsonc
+{
+  "command": "search-labels", "ok": true,
+  "results": [{
+    "text": "deep focus block",
+    "EXG_metrics": { "focus": 0.82, "relaxation": 0.35, "engagement": 0.75, "hr": 65.0, "mood": 0.60 },
+    "EXG_start": 1740412800, "EXG_end": 1740412805,
+    "created_at": 1740412802,
+    "similarity": 0.92
+  }]
+}
+```
+
+### `umap` (3D projection)
+```jsonc
+{
+  "command": "umap", "ok": true,
+  "result": {
+    "points": [{ "x": 1.23, "y": -0.45, "z": 2.01, "session": "a", "utc": 1740412800 }],
+    "analysis": {
+      "separation_score": 1.84,
+      "inter_cluster_distance": 2.31,
+      "intra_spread_a": 0.82, "intra_spread_b": 0.94,
+      "centroid_a": [1.23, -0.45, 2.01],
+      "centroid_b": [-0.87, 1.34, -1.22]
+    }
+  }
+}
+```
+
+---
+
+## Useful `jq` Snippets
+
+```bash
+# Get just focus score
+npx neuroskill status --json | jq '.scores.focus'
+
+# Get all band powers
+npx neuroskill status --json | jq '.scores.bands'
+
+# Check device battery
+npx neuroskill status --json | jq '.device.battery'
+
+# Get signal quality
+npx neuroskill status --json | jq '.signal_quality'
+
+# Find improving metrics after a session
+npx neuroskill session 0 --json | jq '[.trends | to_entries[] | select(.value == "up") | .key]'
+
+# Sort comparison deltas by improvement
+npx neuroskill compare --json | jq '.insights.deltas | to_entries | sort_by(.value.pct) | reverse'
+
+# Get sleep efficiency
+npx neuroskill sleep --json | jq '.analysis.efficiency_pct'
+
+# Find closest neural match
+npx neuroskill search --json | jq '[.result.results[].neighbors[]] | sort_by(.distance) | .[0]'
+
+# Extract TBR from labeled stress moments
+npx neuroskill search-labels "stress" --json | jq '[.results[].EXG_metrics.tbr]'
+
+# Get session timestamps for manual compare
+npx neuroskill sessions --json | jq '{start: .sessions[0].start_utc, end: .sessions[0].end_utc}'
+```
+
+---
+
+## Data Storage
+
+- **Local database**: `~/.skill/YYYYMMDD/` (SQLite + HNSW index)
+- **ZUNA embeddings**: 128-D vectors, 5-second epochs
+- **Labels**: Stored in SQLite, indexed with bge-small-en-v1.5 embeddings
+- **All data is local** — nothing is sent to external servers

optional-skills/health/neuroskill-bci/references/metrics.md

@@ -0,0 +1,220 @@
+# NeuroSkill Metric Definitions & Interpretation Guide
+
+> **⚠️ Research Use Only:** All metrics are experimental and derived from
+> consumer-grade hardware (Muse 2/S). They are not FDA/CE-cleared and must not
+> be used for medical diagnosis or treatment.
+
+---
+
+## Hardware & Signal Acquisition
+
+NeuroSkill is validated for **Muse 2** and **Muse S** headbands (with OpenBCI
+support in the desktop app), streaming at **256 Hz** (EEG) and **64 Hz** (PPG).
+
+### Electrode Positions (International 10-20 System)
+| Channel | Electrode | Position | Primary Signals |
+|---------|-----------|----------|-----------------|
+| CH1 | TP9 | Left Mastoid | Auditory cortex, verbal memory, jaw-clench artifact |
+| CH2 | AF7 | Left Prefrontal | Executive function, approach motivation, eye blinks |
+| CH3 | AF8 | Right Prefrontal | Emotional regulation, vigilance, eye blinks |
+| CH4 | TP10 | Right Mastoid | Prosody, spatial hearing, non-verbal cognition |
+
+### Preprocessing Pipeline
+1. **Filtering**: High-pass (0.5 Hz), Low-pass (50/60 Hz), Notch filter
+2. **Spectral Analysis**: Hann-windowed FFT (512-sample window), Welch periodogram
+3. **GPU acceleration**: ~125ms latency via `gpu_fft`
+
+---
+
+## EEG Frequency Bands
+
+Relative power values (sum ≈ 1.0 across all bands):
+
+| Band | Range (Hz) | High Means | Low Means |
+|------|-----------|------------|-----------|
+| **Delta (δ)** | 1–4 | Deep sleep (N3), high-amplitude artifacts | Awake, alert |
+| **Theta (θ)** | 4–8 | Drowsiness, REM onset, creative ideation, cognitive load | Alert, focused |
+| **Alpha (α)** | 8–13 | Relaxed wakefulness, "alpha blocking" during effort | Active thinking, anxiety |
+| **Beta (β)** | 13–30 | Active concentration, problem-solving, alertness | Relaxed, unfocused |
+| **Gamma (γ)** | 30–50 | Higher-order processing, perceptual binding, memory | Baseline |
+
+### JSON Field Names
+```json
+"bands": {
+  "rel_delta": 0.28, "rel_theta": 0.18, "rel_alpha": 0.32,
+  "rel_beta": 0.17, "rel_gamma": 0.05
+}
+```
+
+---
+
+## Core Composite Scores (0–1 Scale)
+
+### Focus
+- **Formula**: σ(β / (α + θ)) — beta dominance over slow waves, sigmoid-mapped
+- **> 0.70**: Deep concentration, flow state, task absorption
+- **0.40–0.69**: Moderate attention, some mind-wandering
+- **< 0.40**: Distracted, fatigued, difficulty concentrating
+
+### Relaxation
+- **Formula**: σ(α / (β + θ)) — alpha dominance, sigmoid-mapped
+- **> 0.70**: Calm, stress-free, parasympathetic dominant
+- **0.40–0.69**: Mild tension present
+- **< 0.30**: Stressed, anxious, sympathetic dominant
+
+### Engagement
+- **0–1 scale**: Active mental investment and motivation
+- **> 0.70**: Mentally invested, motivated, active processing
+- **0.40–0.69**: Passive participation
+- **< 0.30**: Bored, disengaged, autopilot mode
+
+### Meditation
+- **Composite**: Combines alpha elevation, physical stillness (IMU), and HRV coherence
+- **> 0.70**: Deep meditative state
+- **< 0.30**: Active, non-meditative
+
+### Mood
+- **Composite**: Derived from FAA, TAR, and BAR
+- **> 0.60**: Positive affect, approach motivation
+- **< 0.40**: Low mood, withdrawal tendency
+
+### Cognitive Load
+- **Formula**: (P_θ_frontal / P_α_temporal) · f(FAA, TBR) — working memory usage
+- **> 0.70**: Working memory near capacity, complex processing
+- **0.40–0.69**: Moderate mental effort
+- **< 0.40**: Task is easy or automatic
+- **Interpretation**: High load + high focus = productive struggle. High load + low focus = overwhelmed.
+
+### Drowsiness
+- **Composite**: Weighted TAR + TBR + falling Spectral Centroid
+- **> 0.60**: Sleep pressure building, micro-sleep risk
+- **0.30–0.59**: Mild fatigue
+- **< 0.30**: Alert
+
+---
+
+## EEG Ratios & Spectral Indices
+
+| Metric | Formula | Interpretation |
+|--------|---------|----------------|
+| **FAA** | ln(P_α_AF8) − ln(P_α_AF7) | Frontal Alpha Asymmetry. Positive = approach/positive affect. Negative = withdrawal/depression. |
+| **TAR** | P_θ / P_α | Theta/Alpha Ratio. > 1.5 = drowsiness or mind-wandering. |
+| **BAR** | P_β / P_α | Beta/Alpha Ratio. > 1.5 = alert, engaged cognition. Can also indicate anxiety. |
+| **TBR** | P_θ / P_β | Theta/Beta Ratio. ADHD biomarker. Healthy ≈ 1.0, elevated > 1.5, clinical > 3.0. |
+| **APF** | argmax_f PSD(f) in [7.5, 12.5] Hz | Alpha Peak Frequency. Typical 8–12 Hz. Higher = faster cognitive processing. Slows with age/fatigue. |
+| **SNR** | 10 · log₁₀(P_signal / P_noise) | Signal-to-Noise Ratio. > 10 dB = clean, 3–10 dB = usable, < 3 dB = unreliable. |
+| **Coherence** | Inter-hemispheric coherence (0–1) | Cortical connectivity between hemispheres. |
+| **Mu Suppression** | Motor cortex suppression index | Low values during movement or motor imagery. |
+
+---
+
+## Complexity & Nonlinear Metrics
+
+| Metric | Description | Healthy Range |
+|--------|-------------|---------------|
+| **Permutation Entropy (PE)** | Temporal complexity. Near 1 = maximally irregular. | Consciousness marker |
+| **Higuchi Fractal Dimension (HFD)** | Waveform self-similarity. | Waking: 1.3–1.8; higher = complex |
+| **DFA Exponent** | Long-range correlations. | Healthy: 0.6–0.9 |
+| **PSE** | Power Spectral Entropy. Near 1.0 = white noise. | Lower = organized brain state |
+| **PAC θ-γ** | Phase-Amplitude Coupling, theta-gamma. | Working memory mechanism |
+| **BPS** | Band-Power Slope (1/f spectral exponent). | Steeper = inhibition-dominated |
+
+---
+
+## Consciousness Metrics
+
+Derived from the nonlinear metrics above:
+
+| Metric | Scale | Interpretation |
+|--------|-------|----------------|
+| **LZC** | 0–100 | Lempel-Ziv Complexity proxy (PE + HFD). > 60 = wakefulness. |
+| **Wakefulness** | 0–100 | Inverse drowsiness composite. |
+| **Integration** | 0–100 | Cortical integration (Coherence × PAC × Spectral Entropy). |
+
+Status thresholds: ≥ 50 Green, 25–50 Yellow, < 25 Red.
+
+---
+
+## Cardiac & Autonomic Metrics (from PPG)
+
+| Metric | Description | Normal / Green Range |
+|--------|-------------|---------------------|
+| **HR** | Heart rate (bpm) | 55–90 (green), 45–110 (yellow), else red |
+| **RMSSD** | Primary vagal tone marker (ms) | > 50 ms healthy, < 20 ms stress |
+| **SDNN** | HRV time-domain variability (ms) | Higher = better |
+| **pNN50** | Parasympathetic indicator (%) | Higher = more parasympathetic activity |
+| **LF/HF Ratio** | Sympatho-vagal balance | > 2.0 = stress, < 0.5 = relaxation |
+| **Stress Index** | Baevsky SI: AMo / (2 × MxDMn × Mo) | 0–100 composite. > 200 raw = strong stress |
+| **SpO₂ Estimate** | Blood oxygen saturation (uncalibrated) | 95–100% normal (research only) |
+| **Respiratory Rate** | Breaths per minute | 12–20 normal |
+
+---
+
+## Motion & Artifact Detection
+
+| Metric | Description |
+|--------|-------------|
+| **Stillness** | 0–1 (1 = perfectly still). From IMU accelerometer/gyroscope. |
+| **Blink Count** | Eye blinks detected (large spikes in AF7/AF8). Normal: 15–20/min. |
+| **Jaw Clench Count** | High-frequency EMG bursts (> 30 Hz) at TP9/TP10. |
+| **Nod Count** | Head nods detected via IMU. |
+| **Shake Count** | Head shakes detected via IMU. |
+| **Head Pitch/Roll** | Head orientation from IMU. |
+
+---
+
+## Signal Quality (Per Electrode)
+
+| Electrode | Range | Interpretation |
+|-----------|-------|----------------|
+| **TP9** | 0–1 | ≥ 0.9 = good, ≥ 0.7 = acceptable, < 0.7 = poor |
+| **AF7** | 0–1 | Same thresholds |
+| **AF8** | 0–1 | Same thresholds |
+| **TP10** | 0–1 | Same thresholds |
+
+If any electrode is below 0.7, recommend the user adjust the headband fit or
+moisten the electrode contacts.
+
+---
+
+## Sleep Staging
+
+Based on 5-second epochs using relative band-power ratios and AASM heuristics:
+
+| Stage | Code | EEG Signature | Function |
+|-------|------|---------------|----------|
+| Wake | 0 | Alpha-dominant, BAR > 0.8 | Conscious awareness |
+| N1 | 1 | Alpha → Theta transition | Light sleep onset |
+| N2 | 2 | Sleep spindles, K-complexes | Memory consolidation |
+| N3 (Deep) | 3 | Delta > 20% of epoch, DTR > 2 | Deep restorative sleep |
+| REM | 4 | Active EEG, high Theta, low Delta | Emotional processing, dreaming |
+
+### Healthy Adult Targets (~8h Sleep)
+- **N3 (Deep)**: 15–25% of total sleep
+- **REM**: 20–25%
+- **Sleep Efficiency**: > 85%
+- **Sleep Onset Latency**: < 20 min
+
+---
+
+## Composite State Patterns
+
+| Pattern | Key Metrics | Interpretation |
+|---------|-------------|----------------|
+| **Flow State** | Focus > 0.75, Engagement > 0.70, Cognitive Load 0.50–0.70, HR steady | Optimal performance zone — protect it |
+| **Mental Fatigue** | Focus < 0.40, Drowsiness > 0.60, TBR > 1.5, Theta elevated | Rest or break needed |
+| **Anxiety** | Relaxation < 0.30, HR elevated, high Beta, high BAR, stress_index high | Calming intervention helpful |
+| **Peak Alert** | Focus > 0.80, Engagement > 0.70, Drowsiness < 0.20 | Best time for hard tasks |
+| **Recovery** | Relaxation > 0.70, HRV (RMSSD) rising, Alpha dominant | Integration, light tasks only |
+| **Creative Mode** | High Theta, high Alpha, low Beta, moderate focus | Ideation — don't force structure |
+| **Withdrawal** | FAA < 0, low Mood, low Engagement | Approach motivation needed |
+
+---
+
+## ZUNA Embeddings
+
+NeuroSkill uses the **ZUNA Neural Encoder** to convert 5-second EEG epochs into
+**128-dimensional vectors** stored in an HNSW index:
+- **Search**: Sub-millisecond approximate nearest-neighbor queries
+- **UMAP**: GPU-accelerated 3D projection for visual comparison
+- **Storage**: Local SQLite + HNSW index in `~/.skill/YYYYMMDD/`

optional-skills/health/neuroskill-bci/references/protocols.md

@@ -0,0 +1,452 @@
+# NeuroSkill Guided Protocols
+
+Over 70 mind-body practices triggered by specific biometric (EXG) signals. These
+are sourced from NeuroLoop's protocol repertoire and are designed to be suggested
+when the system detects specific cognitive or physiological states.
+
+> **⚠️ Contraindication**: Wim Hof and hyperventilation-style breathwork are
+> unsuitable for epilepsy_risk > 30, known cardiac conditions, or pregnancy.
+
+---
+
+## When to Suggest Protocols
+
+**Always ask before starting.** Match ONE protocol to the single most salient
+metric signal. Explain the metric connection to the user.
+
+| User State | Recommended Protocol |
+|------------|---------------------|
+| Focus < 0.40, TBR > 1.5 | Theta-Beta Neurofeedback Anchor or Box Breathing |
+| Low engagement, session start | WOOP or Pre-Task Priming |
+| Relaxation < 0.30, stress_index high | Cardiac Coherence or 4-7-8 Breathing |
+| Cognitive Load > 0.70 sustained | Cognitive Load Offload (Mind Dump) |
+| Engagement < 0.30 for > 20 min | Novel Stimulation Burst or Environment Change |
+| Flow State (focus > 0.75, engagement > 0.70) | **Do NOT interrupt — protect the session** |
+| Drowsiness > 0.60, post-lunch | Ultradian Reset or Power Nap |
+| FAA < 0, depression_index elevated | FAA Rebalancing |
+| Low RMSSD (< 25ms) | Vagal Toning |
+| High stillness + headache signals | Neck Release Sequence |
+| Pre-sleep, HRV low | Sleep Wind-Down |
+| Post-social-media, low mood | Envy & Comparison Alchemy |
+
+---
+
+## Attention & Focus Protocols
+
+### Theta-Beta Neurofeedback Anchor
+**Duration**: ~90 seconds
+**Trigger**: High TBR (> 1.5) and low focus
+**Instructions**:
+1. Close your eyes
+2. Breathe slowly — 4s inhale, 6s exhale
+3. Count rhythmically from 1 to 10, matching your breath
+4. Focus on the counting — if you lose count, restart from 1
+5. Open your eyes after 4–5 full cycles
+**Effect**: Suppresses theta dominance and lifts beta activity
+
+### Focus Reset
+**Duration**: 90 seconds
+**Trigger**: Scattered engagement, difficulty settling into task
+**Instructions**:
+1. Close your eyes completely
+2. Take 5 slow, deep breaths
+3. Mentally state your intention for the next work block
+4. Open your eyes and begin immediately
+**Effect**: Resets attentional baseline
+
+### Working Memory Primer
+**Duration**: 3 minutes
+**Trigger**: Low PAC θ-γ (theta-gamma coupling), low sample entropy
+**Instructions**:
+1. Breathe at theta pace: 4s inhale, 6s exhale, 2s hold
+2. While breathing, do a verbal 3-back task: listen to or read a sequence
+   of numbers, say which number appeared 3 positions back
+3. Continue for 3 minutes
+**Effect**: Lifts theta-gamma coupling and working memory engagement
+
+### Creativity Unlock
+**Duration**: 5 minutes
+**Trigger**: High beta, low rel_alpha — system is too analytically locked
+**Instructions**:
+1. Stop all structured work
+2. Let your mind wander without a goal
+3. Doodle, look out the window, or listen to ambient sound
+4. Don't force any outcome — just observe what arises
+5. After 5 minutes, jot down any ideas that surfaced
+**Effect**: Promotes alpha and theta activity for creative ideation
+
+### Dual-N-Back Warm-Up
+**Duration**: 3 minutes
+**Trigger**: Low PAC θ-γ, low sample entropy
+**Instructions**:
+1. Read or listen to a sequence of spoken numbers
+2. Track which number appeared 2 positions back (2-back)
+3. If comfortable, increase to 3-back
+**Effect**: Activates prefrontal cortex, lifts executive function
+
+### Novel Stimulation Burst
+**Duration**: 2–3 minutes
+**Trigger**: Low APF (< 9 Hz), dementia_index > 30
+**Instructions**:
+1. Pick up an unusual object nearby and describe it in detail
+2. Name 5 things you can see, 4 you can touch, 3 you can hear
+3. Try a quick riddle or lateral thinking puzzle
+**Effect**: Counters cortical slowing, raises alpha peak frequency
+
+---
+
+## Autonomic & Stress Regulation Protocols
+
+### Box Breathing (4-4-4-4)
+**Duration**: 2–4 minutes
+**Trigger**: High BAR, high anxiety_index, acute stress
+**Instructions**:
+1. Inhale for 4 counts
+2. Hold for 4 counts
+3. Exhale for 4 counts
+4. Hold for 4 counts
+5. Repeat 4–8 cycles
+**Effect**: Engages parasympathetic nervous system, reduces beta activity
+
+### Extended Exhale (4-7-8)
+**Duration**: 3–5 minutes
+**Trigger**: Acute stress spikes, racing thoughts, high sympathetic activation
+**Instructions**:
+1. Exhale completely through mouth
+2. Inhale through nose for 4 counts
+3. Hold for 7 counts
+4. Exhale through mouth for 8 counts
+5. Repeat 4 cycles
+**Effect**: Fastest parasympathetic trigger for acute stress
+
+### Cardiac Coherence
+**Duration**: 5 minutes
+**Trigger**: Low RMSSD (< 30 ms), high stress_index
+**Instructions**:
+1. Breathe evenly: 5-second inhale, 5-second exhale
+2. Focus on the area around your heart
+3. Recall a positive memory or feeling of appreciation
+4. Maintain for 5 minutes
+**Effect**: Maximizes HRV, creates coherent heart rhythm pattern
+
+### Physiological Sigh
+**Duration**: 30 seconds (1–3 cycles)
+**Trigger**: Rapid overwhelm, acute panic
+**Instructions**:
+1. Take a quick double inhale through the nose (sniff-sniff)
+2. Follow with a long, slow exhale through the mouth
+3. Repeat 1–3 times
+**Effect**: Rapid parasympathetic activation, immediate calming
+
+### Alpha Induction (Open Focus)
+**Duration**: 5 minutes
+**Trigger**: High beta, low relaxation — cannot relax
+**Instructions**:
+1. Soften your gaze — don't focus on any single object
+2. Notice the space between and around objects
+3. Expand your awareness to peripheral vision
+4. Maintain this "open focus" for 5 minutes
+**Effect**: Promotes alpha wave production, reduces beta dominance
+
+### Open Monitoring
+**Duration**: 5–10 minutes
+**Trigger**: Low LZC (< 40 on 0-100 scale) — neural complexity too low
+**Instructions**:
+1. Sit comfortably with eyes closed or softly focused
+2. Don't direct attention to anything specific
+3. Simply notice whatever arises — thoughts, sounds, sensations
+4. Let each observation pass without engagement
+**Effect**: Raises neural complexity and consciousness metrics
+
+### Vagal Toning
+**Duration**: 3 minutes
+**Trigger**: Low RMSSD (< 25 ms) — weak vagal tone
+**Instructions**:
+1. Hum a long, steady note on each exhale for 30 seconds
+2. Alternatively: gargle cold water for 30 seconds
+3. Repeat 3–5 times
+**Effect**: Directly stimulates the vagus nerve, increases parasympathetic tone
+
+---
+
+## Emotional Regulation Protocols
+
+### FAA Rebalancing
+**Duration**: 5 minutes
+**Trigger**: Negative FAA (right-hemisphere dominant), high depression_index
+**Instructions**:
+1. Think of something you're genuinely looking forward to (approach motivation)
+2. Visualize yourself successfully completing a meaningful goal
+3. Squeeze your left hand into a fist for 10 seconds, release
+4. Repeat the visualization + left-hand squeeze 3–4 times
+**Effect**: Activates left prefrontal cortex, shifts FAA positive
+
+### Loving-Kindness (Metta)
+**Duration**: 5–10 minutes
+**Trigger**: Loneliness signals, shame, low mood
+**Instructions**:
+1. Close your eyes and think of someone you care about
+2. Silently repeat: "May you be happy. May you be healthy. May you be safe."
+3. Extend the same wishes to yourself
+4. Extend to a neutral person, then gradually to someone difficult
+**Effect**: Reduces withdrawal motivation, increases positive affect
+
+### Emotional Discharge
+**Duration**: 2 minutes
+**Trigger**: High bipolar_index or extreme FAA swings
+**Instructions**:
+1. Take 30 seconds of vigorous, fast breathing (safely)
+2. Stop and take 3 slow, deep breaths
+3. Do a 60-second body scan — notice where tension is held
+4. Shake out your hands and arms for 15 seconds
+**Effect**: Releases trapped sympathetic energy, recalibrates
+
+### Havening Touch
+**Duration**: 3–5 minutes
+**Trigger**: Acute distress, trauma activation, overwhelming anxiety
+**Instructions**:
+1. Gently stroke your arms from shoulder to elbow, palms down
+2. Rub your palms together slowly
+3. Gently touch your forehead, temples
+4. Continue for 3–5 minutes while breathing slowly
+**Effect**: Disrupts amygdala-cortex encoding loop, reduces distress
+
+### Anxiety Surfing
+**Duration**: ~8 minutes
+**Trigger**: Rising anxiety without clear cause
+**Instructions**:
+1. Notice where anxiety lives in your body — chest? stomach? throat?
+2. Describe the sensation without judging it (tight? hot? buzzing?)
+3. Breathe into that area for 3 breaths
+4. Notice: is it getting bigger, smaller, or changing shape?
+5. Continue observing for 5–8 minutes — anxiety typically peaks then subsides
+
+### Anger: Palm-Press Discharge
+**Duration**: 2 minutes
+**Trigger**: Anger signals, high BAR + elevated HR
+**Instructions**:
+1. Press your palms together firmly for 10 seconds
+2. Release and take 3 extended exhales (4s in, 8s out)
+3. Repeat 3–4 times
+
+### Envy & Comparison Alchemy
+**Duration**: 3 minutes
+**Trigger**: Post-social-media, envy signals
+**Instructions**:
+1. Name the envy: "I feel envious of ___"
+2. Ask: "What does this envy tell me I actually want?"
+3. Convert: "My next step toward that is ___"
+**Effect**: Converts envy into a desire-signal that identifies personal values
+
+### Awe Induction
+**Duration**: 3–5 minutes
+**Trigger**: Existential flatness, low engagement, loss of meaning
+**Instructions**:
+1. Imagine standing at the edge of the Grand Canyon, or beneath a starry sky
+2. Let yourself feel the scale — you are small, and that's beautiful
+3. Recall a moment of genuine wonder from your past
+4. Notice what changes in your body
+**Effect**: Counters hedonic adaptation, restores sense of meaning
+
+---
+
+## Sleep & Recovery Protocols
+
+### Ultradian Reset
+**Duration**: 20 minutes
+**Trigger**: End of a 90-minute focus block, drowsiness rising
+**Instructions**:
+1. Set a timer for 20 minutes
+2. No agenda — just rest (don't force sleep)
+3. Dim lights if possible, close eyes
+4. Let mind wander without structure
+**Effect**: Aligns with 90-minute ultradian rhythm, restores cognitive resources
+
+### Wake Reset
+**Duration**: 5 minutes
+**Trigger**: narcolepsy_index > 40, severe drowsiness
+**Instructions**:
+1. Splash cold water on your face and wrists
+2. Do 20 seconds of Kapalabhati breath (sharp nasal exhales)
+3. Expose yourself to bright light for 2–3 minutes
+**Effect**: Acute arousal response, suppresses drowsiness
+
+### NSDR (Non-Sleep Deep Rest / Yoga Nidra)
+**Duration**: 20–30 minutes
+**Trigger**: Accumulated fatigue, need deep recovery without sleeping
+**Instructions**:
+1. Lie on your back, palms up
+2. Close your eyes and do a slow body scan from toes to crown
+3. At each body part, notice sensation without changing anything
+4. If you fall asleep, that's fine — set an alarm
+**Effect**: Restores dopamine and cognitive resources without sleep inertia
+
+### Power Nap
+**Duration**: 10–20 minutes (set alarm!)
+**Trigger**: Drowsiness > 0.70, post-lunch slump, Theta dominant
+**Instructions**:
+1. Set alarm for 20 minutes maximum (avoids N3 sleep inertia)
+2. Lie down or recline
+3. Even if you don't fully sleep, rest with eyes closed
+4. On waking: 30 seconds of stretching before resuming work
+**Effect**: Restores focus and alertness for 2–3 hours
+
+### Sleep Wind-Down
+**Duration**: 60 minutes before bed
+**Trigger**: Evening session, rising drowsiness, pre-sleep
+**Instructions**:
+1. Dim all screens to night mode
+2. Stop new learning or complex tasks
+3. Do a mind dump of tomorrow's tasks
+4. 10 minutes of progressive relaxation or 4-7-8 breathing
+5. Keep room cool (65–68°F / 18–20°C)
+
+---
+
+## Somatic & Physical Protocols
+
+### Progressive Muscle Relaxation (PMR)
+**Duration**: 10 minutes
+**Trigger**: Relaxation < 0.25, HRV declining over session
+**Instructions**:
+1. Start with feet — tense for 5 seconds, release for 8–10 seconds
+2. Move upward: calves → thighs → abdomen → hands → arms → shoulders → face
+3. Hold each tension 5 seconds, release 8–10 seconds
+4. End with 3 deep breaths
+
+### Grounding (5-4-3-2-1)
+**Duration**: 3 minutes
+**Trigger**: Panic, dissociation, acute anxiety spike
+**Instructions**:
+1. Name 5 things you can see
+2. Name 4 things you can touch
+3. Name 3 things you can hear
+4. Name 2 things you can smell
+5. Name 1 thing you can taste
+
+### 20-20-20 Vision Reset
+**Duration**: 20 seconds
+**Trigger**: Extended screen time, eye strain
+**Instructions**:
+1. Every 20 minutes of screen time
+2. Look at something 20 feet away
+3. For 20 seconds
+
+### Neck Release Sequence
+**Duration**: 3 minutes
+**Trigger**: High stillness (> 0.85) + headache_index elevated
+**Instructions**:
+1. Ear-to-shoulder tilt — hold 15 seconds each side
+2. Chin tucks — 10 reps (pull chin straight back)
+3. Gentle neck circles — 5 each direction
+4. Shoulder shrugs — 10 reps (squeeze up, release)
+
+### Motor Cortex Activation
+**Duration**: 2 minutes
+**Trigger**: Very high stillness, prolonged static sitting
+**Instructions**:
+1. Cross-body movements: touch right hand to left knee, alternate 10 times
+2. Shake out hands and feet for 15 seconds
+3. Roll ankles and wrists 5 times each direction
+**Effect**: Resets proprioception, activates motor cortex
+
+### Cognitive Load Offload (Mind Dump)
+**Duration**: 5 minutes
+**Trigger**: Cognitive load > 0.70 sustained, racing thoughts, high beta
+**Instructions**:
+1. Open a blank document or grab paper
+2. Write everything on your mind without filtering or organizing
+3. Brain-dump worries, tasks, ideas — anything occupying working memory
+4. Close the document (review later if needed)
+**Effect**: Externalizing working memory can reduce cognitive load by 20–40%
+
+---
+
+## Digital & Lifestyle Protocols
+
+### Craving Surf
+**Duration**: 90 seconds
+**Trigger**: Phone addiction signals, urge to check social media
+**Instructions**:
+1. Notice the urge to check your phone
+2. Don't act on it — just observe for 90 seconds
+3. Notice: does the urge peak and then fade?
+4. Resume what you were doing
+**Effect**: Breaks automatic dopamine-seeking loop
+
+### Dopamine Palette Reset
+**Duration**: Ongoing
+**Trigger**: Flatness from short-form content spikes
+**Instructions**:
+1. Identify activities that provide sustained reward (reading, cooking, walking)
+2. Replace 15 minutes of scrolling with one sustained-reward activity
+3. Track mood before/after for 3 days
+
+### Digital Sunset
+**Duration**: 60–90 minutes before bed
+**Trigger**: Evening, pre-sleep routine
+**Instructions**:
+1. Hard stop on all screens 60–90 minutes before bed
+2. Switch to non-screen activities: reading, conversation, stretching
+3. If screens are necessary, use night mode at minimum brightness
+
+---
+
+## Dietary Protocols
+
+### Caffeine Timing
+**Trigger**: Morning routine, anxiety_index
+**Guidelines**:
+- Consume caffeine 90–120 minutes after waking (cortisol has already peaked)
+- None after 2 PM (half-life ~6 hours)
+- If anxiety_index > 50, stack with L-theanine (200mg) to smooth the curve
+
+### Post-Meal Energy Crash
+**Trigger**: Post-lunch drowsiness spike
+**Instructions**:
+1. 5-minute brisk walk immediately after eating
+2. 10 minutes of sunlight exposure
+**Effect**: Counters post-prandial drowsiness
+
+---
+
+## Motivation & Planning Protocols
+
+### WOOP (Wish, Outcome, Obstacle, Plan)
+**Duration**: 5 minutes
+**Trigger**: Low engagement before a task
+**Instructions**:
+1. **Wish**: What do you want to accomplish in this session?
+2. **Outcome**: What's the best possible result? Visualize it.
+3. **Obstacle**: What internal obstacle might get in the way?
+4. **Plan**: "If [obstacle], then I will [action]."
+**Effect**: Mental contrasting improves follow-through by 2–3x
+
+### Pre-Task Priming
+**Duration**: 3 minutes
+**Trigger**: Low engagement at session start, drowsiness < 0.50
+**Instructions**:
+1. Set a clear intention for the next work block
+2. Write down the single most important task
+3. Do 10 jumping jacks or 20 deep breaths
+4. Start with the easiest sub-task to build momentum
+
+---
+
+## Protocol Execution Guidelines
+
+When guiding the user through a protocol:
+1. **Match one protocol** to the single most salient metric signal
+2. **Explain the metric connection** — why this protocol for this state
+3. **Ask permission** — never start without the user's consent
+4. **Announce each step** clearly with timing
+5. **Check in after** — run `npx neuroskill status --json` to see if metrics improved
+6. **Label the moment** — `npx neuroskill label "post-protocol: [name]"` for tracking
+
+### Timing Guidelines for Step-by-Step Guidance
+- Breath inhale: 3–5 seconds
+- Breath hold: 2–4 seconds
+- Breath exhale: 4–8 seconds
+- Muscle tense: 5 seconds
+- Muscle release: 8–10 seconds
+- Body-scan region: 10–15 seconds

optional-skills/migration/DESCRIPTION.md

@@ -0,0 +1,2 @@
+Optional migration workflows for importing user state and customizations from
+other agent systems into Hermes Agent.

optional-skills/migration/openclaw-migration/SKILL.md

@@ -0,0 +1,297 @@
+---
+name: openclaw-migration
+description: Migrate a user's OpenClaw customization footprint into Hermes Agent. Imports Hermes-compatible memories, SOUL.md, command allowlists, user skills, and selected workspace assets from ~/.openclaw, then reports exactly what could not be migrated and why.
+version: 1.0.0
+author: Hermes Agent (Nous Research)
+license: MIT
+metadata:
+  hermes:
+    tags: [Migration, OpenClaw, Hermes, Memory, Persona, Import]
+    related_skills: [hermes-agent]
+---
+
+# OpenClaw -> Hermes Migration
+
+Use this skill when a user wants to move their OpenClaw setup into Hermes Agent with minimal manual cleanup.
+
+## CLI Command
+
+For a quick, non-interactive migration, use the built-in CLI command:
+
+```bash
+hermes claw migrate              # Full interactive migration
+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
+hermes claw migrate --source /custom/path/.openclaw  # Custom source
+```
+
+The CLI command runs the same migration script described below. Use this skill (via the agent) when you want an interactive, guided migration with dry-run previews and per-item conflict resolution.
+
+**First-time setup:** The `hermes setup` wizard automatically detects `~/.openclaw` and offers migration before configuration begins.
+
+## What this skill does
+
+It uses `scripts/openclaw_to_hermes.py` to:
+
+- import `SOUL.md` into the Hermes home directory as `SOUL.md`
+- transform OpenClaw `MEMORY.md` and `USER.md` into Hermes memory entries
+- merge OpenClaw command approval patterns into Hermes `command_allowlist`
+- migrate Hermes-compatible messaging settings such as `TELEGRAM_ALLOWED_USERS` and `MESSAGING_CWD`
+- copy OpenClaw skills into `~/.hermes/skills/openclaw-imports/`
+- optionally copy the OpenClaw workspace instructions file into a chosen Hermes workspace
+- mirror compatible workspace assets such as `workspace/tts/` into `~/.hermes/tts/`
+- archive non-secret docs that do not have a direct Hermes destination
+- produce a structured report listing migrated items, conflicts, skipped items, and reasons
+
+## Path resolution
+
+The helper script lives in this skill directory at:
+
+- `scripts/openclaw_to_hermes.py`
+
+When this skill is installed from the Skills Hub, the normal location is:
+
+- `~/.hermes/skills/migration/openclaw-migration/scripts/openclaw_to_hermes.py`
+
+Do not guess a shorter path like `~/.hermes/skills/openclaw-migration/...`.
+
+Before running the helper:
+
+1. Prefer the installed path under `~/.hermes/skills/migration/openclaw-migration/`.
+2. If that path fails, inspect the installed skill directory and resolve the script relative to the installed `SKILL.md`.
+3. Only use `find` as a fallback if the installed location is missing or the skill was moved manually.
+4. When calling the terminal tool, do not pass `workdir: "~"`. Use an absolute directory such as the user's home directory, or omit `workdir` entirely.
+
+With `--migrate-secrets`, it will also import a small allowlisted set of Hermes-compatible secrets, currently:
+
+- `TELEGRAM_BOT_TOKEN`
+
+## Default workflow
+
+1. Inspect first with a dry run.
+2. Present a simple summary of what can be migrated, what cannot be migrated, and what would be archived.
+3. If the `clarify` tool is available, use it for user decisions instead of asking for a free-form prose reply.
+4. If the dry run finds imported skill directory conflicts, ask how those should be handled before executing.
+5. Ask the user to choose between the two supported migration modes before executing.
+6. Ask for a target workspace path only if the user wants the workspace instructions file brought over.
+7. Execute the migration with the matching preset and flags.
+8. Summarize the results, especially:
+   - what was migrated
+   - what was archived for manual review
+   - what was skipped and why
+
+## User interaction protocol
+
+Hermes CLI supports the `clarify` tool for interactive prompts, but it is limited to:
+
+- one choice at a time
+- up to 4 predefined choices
+- an automatic `Other` free-text option
+
+It does **not** support true multi-select checkboxes in a single prompt.
+
+For every `clarify` call:
+
+- always include a non-empty `question`
+- include `choices` only for real selectable prompts
+- keep `choices` to 2-4 plain string options
+- never emit placeholder or truncated options such as `...`
+- never pad or stylize choices with extra whitespace
+- never include fake form fields in the question such as `enter directory here`, blank lines to fill in, or underscores like `_____`
+- for open-ended path questions, ask only the plain sentence; the user types in the normal CLI prompt below the panel
+
+If a `clarify` call returns an error, inspect the error text, correct the payload, and retry once with a valid `question` and clean choices.
+
+When `clarify` is available and the dry run reveals any required user decision, your **next action must be a `clarify` tool call**.
+Do not end the turn with a normal assistant message such as:
+
+- "Let me present the choices"
+- "What would you like to do?"
+- "Here are the options"
+
+If a user decision is required, collect it via `clarify` before producing more prose.
+If multiple unresolved decisions remain, do not insert an explanatory assistant message between them. After one `clarify` response is received, your next action should usually be the next required `clarify` call.
+
+Treat `workspace-agents` as an unresolved decision whenever the dry run reports:
+
+- `kind="workspace-agents"`
+- `status="skipped"`
+- reason containing `No workspace target was provided`
+
+In that case, you must ask about workspace instructions before execution. Do not silently treat that as a decision to skip.
+
+Because of that limitation, use this simplified decision flow:
+
+1. For `SOUL.md` conflicts, use `clarify` with choices such as:
+   - `keep existing`
+   - `overwrite with backup`
+   - `review first`
+2. If the dry run shows one or more `kind="skill"` items with `status="conflict"`, use `clarify` with choices such as:
+   - `keep existing skills`
+   - `overwrite conflicting skills with backup`
+   - `import conflicting skills under renamed folders`
+3. For workspace instructions, use `clarify` with choices such as:
+   - `skip workspace instructions`
+   - `copy to a workspace path`
+   - `decide later`
+4. If the user chooses to copy workspace instructions, ask a follow-up open-ended `clarify` question requesting an **absolute path**.
+5. If the user chooses `skip workspace instructions` or `decide later`, proceed without `--workspace-target`.
+5. For migration mode, use `clarify` with these 3 choices:
+   - `user-data only`
+   - `full compatible migration`
+   - `cancel`
+6. `user-data only` means: migrate user data and compatible config, but do **not** import allowlisted secrets.
+7. `full compatible migration` means: migrate the same compatible user data plus the allowlisted secrets when present.
+8. If `clarify` is not available, ask the same question in normal text, but still constrain the answer to `user-data only`, `full compatible migration`, or `cancel`.
+
+Execution gate:
+
+- Do not execute while a `workspace-agents` skip caused by `No workspace target was provided` remains unresolved.
+- The only valid ways to resolve it are:
+  - user explicitly chooses `skip workspace instructions`
+  - user explicitly chooses `decide later`
+  - user provides a workspace path after choosing `copy to a workspace path`
+- Absence of a workspace target in the dry run is not itself permission to execute.
+- Do not execute while any required `clarify` decision remains unresolved.
+
+Use these exact `clarify` payload shapes as the default pattern:
+
+- `{"question":"Your existing SOUL.md conflicts with the imported one. What should I do?","choices":["keep existing","overwrite with backup","review first"]}`
+- `{"question":"One or more imported OpenClaw skills already exist in Hermes. How should I handle those skill conflicts?","choices":["keep existing skills","overwrite conflicting skills with backup","import conflicting skills under renamed folders"]}`
+- `{"question":"Choose migration mode: migrate only user data, or run the full compatible migration including allowlisted secrets?","choices":["user-data only","full compatible migration","cancel"]}`
+- `{"question":"Do you want to copy the OpenClaw workspace instructions file into a Hermes workspace?","choices":["skip workspace instructions","copy to a workspace path","decide later"]}`
+- `{"question":"Please provide an absolute path where the workspace instructions should be copied."}`
+
+## Decision-to-command mapping
+
+Map user decisions to command flags exactly:
+
+- If the user chooses `keep existing` for `SOUL.md`, do **not** add `--overwrite`.
+- If the user chooses `overwrite with backup`, add `--overwrite`.
+- If the user chooses `review first`, stop before execution and review the relevant files.
+- If the user chooses `keep existing skills`, add `--skill-conflict skip`.
+- If the user chooses `overwrite conflicting skills with backup`, add `--skill-conflict overwrite`.
+- If the user chooses `import conflicting skills under renamed folders`, add `--skill-conflict rename`.
+- If the user chooses `user-data only`, execute with `--preset user-data` and do **not** add `--migrate-secrets`.
+- If the user chooses `full compatible migration`, execute with `--preset full --migrate-secrets`.
+- Only add `--workspace-target` if the user explicitly provided an absolute workspace path.
+- If the user chooses `skip workspace instructions` or `decide later`, do not add `--workspace-target`.
+
+Before executing, restate the exact command plan in plain language and make sure it matches the user's choices.
+
+## Post-run reporting rules
+
+After execution, treat the script's JSON output as the source of truth.
+
+1. Base all counts on `report.summary`.
+2. Only list an item under "Successfully Migrated" if its `status` is exactly `migrated`.
+3. Do not claim a conflict was resolved unless the report shows that item as `migrated`.
+4. Do not say `SOUL.md` was overwritten unless the report item for `kind="soul"` has `status="migrated"`.
+5. If `report.summary.conflict > 0`, include a conflict section instead of silently implying success.
+6. If counts and listed items disagree, fix the list to match the report before responding.
+7. Include the `output_dir` path from the report when available so the user can inspect `report.json`, `summary.md`, backups, and archived files.
+8. For memory or user-profile overflow, do not say the entries were archived unless the report explicitly shows an archive path. If `details.overflow_file` exists, say the full overflow list was exported there.
+9. If a skill was imported under a renamed folder, report the final destination and mention `details.renamed_from`.
+10. If `report.skill_conflict_mode` is present, use it as the source of truth for the selected imported-skill conflict policy.
+11. If an item has `status="skipped"`, do not describe it as overwritten, backed up, migrated, or resolved.
+12. If `kind="soul"` has `status="skipped"` with reason `Target already matches source`, say it was left unchanged and do not mention a backup.
+13. If a renamed imported skill has an empty `details.backup`, do not imply the existing Hermes skill was renamed or backed up. Say only that the imported copy was placed in the new destination and reference `details.renamed_from` as the pre-existing folder that remained in place.
+
+## Migration presets
+
+Prefer these two presets in normal use:
+
+- `user-data`
+- `full`
+
+`user-data` includes:
+
+- `soul`
+- `workspace-agents`
+- `memory`
+- `user-profile`
+- `messaging-settings`
+- `command-allowlist`
+- `skills`
+- `tts-assets`
+- `archive`
+
+`full` includes everything in `user-data` plus:
+
+- `secret-settings`
+
+The helper script still supports category-level `--include` / `--exclude`, but treat that as an advanced fallback rather than the default UX.
+
+## Commands
+
+Dry run with full discovery:
+
+```bash
+python3 ~/.hermes/skills/migration/openclaw-migration/scripts/openclaw_to_hermes.py
+```
+
+When using the terminal tool, prefer an absolute invocation pattern such as:
+
+```json
+{"command":"python3 /home/USER/.hermes/skills/migration/openclaw-migration/scripts/openclaw_to_hermes.py","workdir":"/home/USER"}
+```
+
+Dry run with the user-data preset:
+
+```bash
+python3 ~/.hermes/skills/migration/openclaw-migration/scripts/openclaw_to_hermes.py --preset user-data
+```
+
+Execute a user-data migration:
+
+```bash
+python3 ~/.hermes/skills/migration/openclaw-migration/scripts/openclaw_to_hermes.py --execute --preset user-data --skill-conflict skip
+```
+
+Execute a full compatible migration:
+
+```bash
+python3 ~/.hermes/skills/migration/openclaw-migration/scripts/openclaw_to_hermes.py --execute --preset full --migrate-secrets --skill-conflict skip
+```
+
+Execute with workspace instructions included:
+
+```bash
+python3 ~/.hermes/skills/migration/openclaw-migration/scripts/openclaw_to_hermes.py --execute --preset user-data --skill-conflict rename --workspace-target "/absolute/workspace/path"
+```
+
+Do not use `$PWD` or the home directory as the workspace target by default. Ask for an explicit workspace path first.
+
+## Important rules
+
+1. Run a dry run before writing unless the user explicitly says to proceed immediately.
+2. Do not migrate secrets by default. Tokens, auth blobs, device credentials, and raw gateway config should stay out of Hermes unless the user explicitly asks for secret migration.
+3. Do not silently overwrite non-empty Hermes targets unless the user explicitly wants that. The helper script will preserve backups when overwriting is enabled.
+4. Always give the user the skipped-items report. That report is part of the migration, not an optional extra.
+5. Prefer the primary OpenClaw workspace (`~/.openclaw/workspace/`) over `workspace.default/`. Only use the default workspace as fallback when the primary files are missing.
+6. Even in secret-migration mode, only migrate secrets with a clean Hermes destination. Unsupported auth blobs must still be reported as skipped.
+7. If the dry run shows a large asset copy, a conflicting `SOUL.md`, or overflowed memory entries, call those out separately before execution.
+8. Default to `user-data only` if the user is unsure.
+9. Only include `workspace-agents` when the user has explicitly provided a destination workspace path.
+10. Treat category-level `--include` / `--exclude` as an advanced escape hatch, not the normal flow.
+11. Do not end the dry-run summary with a vague “What would you like to do?” if `clarify` is available. Use structured follow-up prompts instead.
+12. Do not use an open-ended `clarify` prompt when a real choice prompt would work. Prefer selectable choices first, then free text only for absolute paths or file review requests.
+13. After a dry run, never stop after summarizing if there is still an unresolved decision. Use `clarify` immediately for the highest-priority blocking decision.
+14. Priority order for follow-up questions:
+    - `SOUL.md` conflict
+    - imported skill conflicts
+    - migration mode
+    - workspace instructions destination
+15. Do not promise to present choices later in the same message. Present them by actually calling `clarify`.
+16. After the migration-mode answer, explicitly check whether `workspace-agents` is still unresolved. If it is, your next action must be the workspace-instructions `clarify` call.
+17. After any `clarify` answer, if another required decision remains, do not narrate what was just decided. Ask the next required question immediately.
+
+## Expected result
+
+After a successful run, the user should have:
+
+- Hermes persona state imported
+- Hermes memory files populated with converted OpenClaw knowledge
+- OpenClaw skills available under `~/.hermes/skills/openclaw-imports/`
+- a migration report showing any conflicts, omissions, or unsupported data

plans/checkpoint-rollback.md

@@ -0,0 +1,218 @@
+# Checkpoint & Rollback — Implementation Plan
+
+## Goal
+
+Automatic filesystem snapshots before destructive file operations, with user-facing rollback. The agent never sees or interacts with this — it's transparent infrastructure.
+
+## Design Principles
+
+1. **Not a tool** — the LLM never knows about it. Zero prompt tokens, zero tool schema overhead.
+2. **Once per turn** — checkpoint at most once per conversation turn (user message → agent response cycle), triggered lazily on the first file-mutating operation. Not on every write.
+3. **Opt-in via config** — disabled by default, enabled with `checkpoints: true` in config.yaml.
+4. **Works on any directory** — uses a shadow git repo completely separate from the user's project git. Works on git repos, non-git directories, anything.
+5. **User-facing rollback** — `/rollback` slash command (CLI + gateway) to list and restore checkpoints. Also `hermes rollback` CLI subcommand.
+
+## Architecture
+
+```
+~/.hermes/checkpoints/
+  {sha256(abs_dir)[:16]}/       # Shadow git repo per working directory
+    HEAD, refs/, objects/...    # Standard git internals
+    HERMES_WORKDIR              # Original dir path (for display)
+    info/exclude                # Default excludes (node_modules, .env, etc.)
+```
+
+### Core: CheckpointManager (new file: tools/checkpoint_manager.py)
+
+Adapted from PR #559's CheckpointStore. Key changes from the PR:
+
+- **Not a tool** — no schema, no registry entry, no handler
+- **Turn-scoped deduplication** — tracks `_checkpointed_dirs: Set[str]` per turn
+- **Configurable** — reads `checkpoints` config key
+- **Pruning** — keeps last N snapshots per directory (default 50), prunes on take
+
+```python
+class CheckpointManager:
+    def __init__(self, enabled: bool = False, max_snapshots: int = 50):
+        self.enabled = enabled
+        self.max_snapshots = max_snapshots
+        self._checkpointed_dirs: Set[str] = set()  # reset each turn
+
+    def new_turn(self):
+        """Call at start of each conversation turn to reset dedup."""
+        self._checkpointed_dirs.clear()
+
+    def ensure_checkpoint(self, working_dir: str, reason: str = "auto") -> None:
+        """Take a checkpoint if enabled and not already done this turn."""
+        if not self.enabled:
+            return
+        abs_dir = str(Path(working_dir).resolve())
+        if abs_dir in self._checkpointed_dirs:
+            return
+        self._checkpointed_dirs.add(abs_dir)
+        try:
+            self._take(abs_dir, reason)
+        except Exception as e:
+            logger.debug("Checkpoint failed (non-fatal): %s", e)
+
+    def list_checkpoints(self, working_dir: str) -> List[dict]:
+        """List available checkpoints for a directory."""
+        ...
+
+    def restore(self, working_dir: str, commit_hash: str) -> dict:
+        """Restore files to a checkpoint state."""
+        ...
+
+    def _take(self, working_dir: str, reason: str):
+        """Shadow git: add -A + commit. Prune if over max_snapshots."""
+        ...
+
+    def _prune(self, shadow_repo: Path):
+        """Keep only last max_snapshots commits."""
+        ...
+```
+
+### Integration Point: run_agent.py
+
+The AIAgent already owns the conversation loop. Add CheckpointManager as an instance attribute:
+
+```python
+class AIAgent:
+    def __init__(self, ...):
+        ...
+        # Checkpoint manager — reads config to determine if enabled
+        self._checkpoint_mgr = CheckpointManager(
+            enabled=config.get("checkpoints", False),
+            max_snapshots=config.get("checkpoint_max_snapshots", 50),
+        )
+```
+
+**Turn boundary** — in `run_conversation()`, call `new_turn()` at the start of each agent iteration (before processing tool calls):
+
+```python
+# Inside the main loop, before _execute_tool_calls():
+self._checkpoint_mgr.new_turn()
+```
+
+**Trigger point** — in `_execute_tool_calls()`, before dispatching file-mutating tools:
+
+```python
+# Before the handle_function_call dispatch:
+if function_name in ("write_file", "patch"):
+    # Determine working dir from the file path in the args
+    file_path = function_args.get("path", "") or function_args.get("old_string", "")
+    if file_path:
+        work_dir = str(Path(file_path).parent.resolve())
+        self._checkpoint_mgr.ensure_checkpoint(work_dir, f"before {function_name}")
+```
+
+This means:
+- First `write_file` in a turn → checkpoint (fast, one `git add -A && git commit`)
+- Subsequent writes in the same turn → no-op (already checkpointed)
+- Next turn (new user message) → fresh checkpoint eligibility
+
+### Config
+
+Add to `DEFAULT_CONFIG` in `hermes_cli/config.py`:
+
+```python
+"checkpoints": False,          # Enable filesystem checkpoints before destructive ops
+"checkpoint_max_snapshots": 50, # Max snapshots to keep per directory
+```
+
+User enables with:
+```yaml
+# ~/.hermes/config.yaml
+checkpoints: true
+```
+
+### User-Facing Rollback
+
+**CLI slash command** — add `/rollback` to `process_command()` in `cli.py`:
+
+```
+/rollback         — List recent checkpoints for the current directory
+/rollback <hash>  — Restore files to that checkpoint
+```
+
+Shows a numbered list:
+```
+📸 Checkpoints for /home/user/project:
+  1. abc1234  2026-03-09 21:15  before write_file (3 files changed)
+  2. def5678  2026-03-09 20:42  before patch (1 file changed)
+  3. ghi9012  2026-03-09 20:30  before write_file (2 files changed)
+
+Use /rollback <number> to restore, e.g. /rollback 1
+```
+
+**Gateway slash command** — add `/rollback` to gateway/run.py with the same behavior.
+
+**CLI subcommand** — `hermes rollback` (optional, lower priority).
+
+### What Gets Excluded (not checkpointed)
+
+Same as the PR's defaults — written to the shadow repo's `info/exclude`:
+
+```
+node_modules/
+dist/
+build/
+.env
+.env.*
+__pycache__/
+*.pyc
+.DS_Store
+*.log
+.cache/
+.venv/
+.git/
+```
+
+Also respects the project's `.gitignore` if present (shadow repo can read it via `core.excludesFile`).
+
+### Safety
+
+- `ensure_checkpoint()` wraps everything in try/except — a checkpoint failure never blocks the actual file operation
+- Shadow repo is completely isolated — GIT_DIR + GIT_WORK_TREE env vars, never touches user's .git
+- If git isn't installed, checkpoints silently disable
+- Large directories: add a file count check — skip checkpoint if >50K files to avoid slowdowns
+
+## Files to Create/Modify
+
+| File | Change |
+|------|--------|
+| `tools/checkpoint_manager.py` | **NEW** — CheckpointManager class (adapted from PR #559) |
+| `run_agent.py` | Add CheckpointManager init + trigger in `_execute_tool_calls()` |
+| `hermes_cli/config.py` | Add `checkpoints` + `checkpoint_max_snapshots` to DEFAULT_CONFIG |
+| `cli.py` | Add `/rollback` slash command handler |
+| `gateway/run.py` | Add `/rollback` slash command handler |
+| `tests/tools/test_checkpoint_manager.py` | **NEW** — tests (adapted from PR #559's tests) |
+
+## What We Take From PR #559
+
+- `_shadow_repo_path()` — deterministic path hashing ✅
+- `_git_env()` — GIT_DIR/GIT_WORK_TREE isolation ✅
+- `_run_git()` — subprocess wrapper with timeout ✅
+- `_init_shadow_repo()` — shadow repo initialization ✅
+- `DEFAULT_EXCLUDES` list ✅
+- Test structure and patterns ✅
+
+## What We Change From PR #559
+
+- **Remove tool schema/registry** — not a tool
+- **Remove injection into file_operations.py and patch_parser.py** — trigger from run_agent.py instead
+- **Add turn-scoped deduplication** — one checkpoint per turn, not per operation
+- **Add pruning** — keep last N snapshots
+- **Add config flag** — opt-in, not mandatory
+- **Add /rollback command** — user-facing restore UI
+- **Add file count guard** — skip huge directories
+
+## Implementation Order
+
+1. `tools/checkpoint_manager.py` — core class with take/list/restore/prune
+2. `tests/tools/test_checkpoint_manager.py` — tests
+3. `hermes_cli/config.py` — config keys
+4. `run_agent.py` — integration (init + trigger)
+5. `cli.py` — `/rollback` slash command
+6. `gateway/run.py` — `/rollback` slash command
+7. Full test suite run + manual smoke test

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "hermes-agent"
-version = "0.1.0"
+version = "0.2.0"
 description = "The self-improving AI agent — creates skills from experience, improves them during use, and runs anywhere"
 readme = "README.md"
 requires-python = ">=3.11"
@@ -13,6 +13,7 @@ license = { text = "MIT" }
 dependencies = [
   # Core
   "openai",
+  "anthropic>=0.39.0",
   "python-dotenv",
   "fire",
   "httpx",
@@ -46,10 +47,20 @@ cron = ["croniter"]
 slack = ["slack-bolt>=1.18.0", "slack-sdk>=3.27.0"]
 cli = ["simple-term-menu"]
 tts-premium = ["elevenlabs"]
-pty = ["ptyprocess>=0.7.0"]
+pty = [
+  "ptyprocess>=0.7.0; sys_platform != 'win32'",
+  "pywinpty>=2.0.0; sys_platform == 'win32'",
+]
 honcho = ["honcho-ai>=2.0.1"]
 mcp = ["mcp>=1.2.0"]
 homeassistant = ["aiohttp>=3.9.0"]
+rl = [
+  "atroposlib @ git+https://github.com/NousResearch/atropos.git",
+  "tinker @ git+https://github.com/thinking-machines-lab/tinker.git",
+  "fastapi>=0.104.0",
+  "uvicorn[standard]>=0.24.0",
+  "wandb>=0.15.0",
+]
 yc-bench = ["yc-bench @ git+https://github.com/collinear-ai/yc-bench.git"]
 all = [
   "hermes-agent[modal]",
@@ -71,10 +82,10 @@ hermes = "hermes_cli.main:main"
 hermes-agent = "run_agent:main"
 
 [tool.setuptools]
-py-modules = ["run_agent", "model_tools", "toolsets", "batch_runner", "trajectory_compressor", "toolset_distributions", "cli", "hermes_constants"]
+py-modules = ["run_agent", "model_tools", "toolsets", "batch_runner", "trajectory_compressor", "toolset_distributions", "cli", "hermes_constants", "hermes_state", "hermes_time", "mini_swe_runner", "rl_cli", "utils"]
 
 [tool.setuptools.packages.find]
-include = ["tools", "hermes_cli", "gateway", "cron", "honcho_integration"]
+include = ["agent", "tools", "tools.*", "hermes_cli", "gateway", "gateway.*", "cron", "honcho_integration"]
 
 [tool.pytest.ini_options]
 testpaths = ["tests"]

scripts/install.sh

@@ -572,17 +572,16 @@ clone_repo() {
         fi
     else
         # Try SSH first (for private repo access), fall back to HTTPS
-        # Use --recurse-submodules to also clone mini-swe-agent and tinker-atropos
         # GIT_SSH_COMMAND disables interactive prompts and sets a short timeout
         # so SSH fails fast instead of hanging when no key is configured.
         log_info "Trying SSH clone..."
         if GIT_SSH_COMMAND="ssh -o BatchMode=yes -o ConnectTimeout=5" \
-           git clone --branch "$BRANCH" --recurse-submodules "$REPO_URL_SSH" "$INSTALL_DIR" 2>/dev/null; then
+           git clone --branch "$BRANCH" "$REPO_URL_SSH" "$INSTALL_DIR" 2>/dev/null; then
             log_success "Cloned via SSH"
         else
             rm -rf "$INSTALL_DIR" 2>/dev/null  # Clean up partial SSH clone
             log_info "SSH failed, trying HTTPS..."
-            if git clone --branch "$BRANCH" --recurse-submodules "$REPO_URL_HTTPS" "$INSTALL_DIR"; then
+            if git clone --branch "$BRANCH" "$REPO_URL_HTTPS" "$INSTALL_DIR"; then
                 log_success "Cloned via HTTPS"
             else
                 log_error "Failed to clone repository"
@@ -593,10 +592,12 @@ clone_repo() {
 
     cd "$INSTALL_DIR"
 
-    # Ensure submodules are initialized and updated (for existing installs or if --recurse failed)
-    log_info "Initializing submodules (mini-swe-agent, tinker-atropos)..."
-    git submodule update --init --recursive
-    log_success "Submodules ready"
+    # Only init mini-swe-agent (terminal tool backend — required).
+    # tinker-atropos (RL training) is optional and heavy — users can opt in later
+    # with: git submodule update --init tinker-atropos && uv pip install -e ./tinker-atropos
+    log_info "Initializing mini-swe-agent submodule (terminal backend)..."
+    git submodule update --init mini-swe-agent
+    log_success "Submodule ready"
 
     log_success "Repository ready"
 }
@@ -679,12 +680,11 @@ install_deps() {
         log_warn "mini-swe-agent not found (run: git submodule update --init)"
     fi
 
-    log_info "Installing tinker-atropos (RL training backend)..."
+    # tinker-atropos (RL training) is optional — skip by default.
+    # To enable RL tools: git submodule update --init tinker-atropos && uv pip install -e "./tinker-atropos"
     if [ -d "tinker-atropos" ] && [ -f "tinker-atropos/pyproject.toml" ]; then
-        $UV_CMD pip install -e "./tinker-atropos" || log_warn "tinker-atropos install failed (RL tools may not work)"
-        log_success "tinker-atropos installed"
-    else
-        log_warn "tinker-atropos not found (run: git submodule update --init)"
+        log_info "tinker-atropos submodule found — skipping install (optional, for RL training)"
+        log_info "  To install: $UV_CMD pip install -e \"./tinker-atropos\""
     fi
 
     log_success "All dependencies installed"

scripts/release.py

@@ -0,0 +1,540 @@
+#!/usr/bin/env python3
+"""Hermes Agent Release Script
+
+Generates changelogs and creates GitHub releases with CalVer tags.
+
+Usage:
+    # Preview changelog (dry run)
+    python scripts/release.py
+
+    # Preview with semver bump
+    python scripts/release.py --bump minor
+
+    # Create the release
+    python scripts/release.py --bump minor --publish
+
+    # First release (no previous tag)
+    python scripts/release.py --bump minor --publish --first-release
+
+    # Override CalVer date (e.g. for a belated release)
+    python scripts/release.py --bump minor --publish --date 2026.3.15
+"""
+
+import argparse
+import json
+import os
+import re
+import subprocess
+import sys
+from collections import defaultdict
+from datetime import datetime
+from pathlib import Path
+
+REPO_ROOT = Path(__file__).resolve().parent.parent
+VERSION_FILE = REPO_ROOT / "hermes_cli" / "__init__.py"
+PYPROJECT_FILE = REPO_ROOT / "pyproject.toml"
+
+# ──────────────────────────────────────────────────────────────────────
+# Git email → GitHub username mapping
+# ──────────────────────────────────────────────────────────────────────
+
+# Auto-extracted from noreply emails + manual overrides
+AUTHOR_MAP = {
+    # teknium (multiple emails)
+    "teknium1@gmail.com": "teknium1",
+    "teknium@nousresearch.com": "teknium1",
+    "127238744+teknium1@users.noreply.github.com": "teknium1",
+    # contributors (from noreply pattern)
+    "35742124+0xbyt4@users.noreply.github.com": "0xbyt4",
+    "82637225+kshitijk4poor@users.noreply.github.com": "kshitijk4poor",
+    "16443023+stablegenius49@users.noreply.github.com": "stablegenius49",
+    "185121704+stablegenius49@users.noreply.github.com": "stablegenius49",
+    "101283333+batuhankocyigit@users.noreply.github.com": "batuhankocyigit",
+    "126368201+vilkasdev@users.noreply.github.com": "vilkasdev",
+    "137614867+cutepawss@users.noreply.github.com": "cutepawss",
+    "96793918+memosr@users.noreply.github.com": "memosr",
+    "131039422+SHL0MS@users.noreply.github.com": "SHL0MS",
+    "77628552+raulvidis@users.noreply.github.com": "raulvidis",
+    "145567217+Aum08Desai@users.noreply.github.com": "Aum08Desai",
+    "256820943+kshitij-eliza@users.noreply.github.com": "kshitij-eliza",
+    "44278268+shitcoinsherpa@users.noreply.github.com": "shitcoinsherpa",
+    "104278804+Sertug17@users.noreply.github.com": "Sertug17",
+    "112503481+caentzminger@users.noreply.github.com": "caentzminger",
+    "258577966+voidborne-d@users.noreply.github.com": "voidborne-d",
+    "70424851+insecurejezza@users.noreply.github.com": "insecurejezza",
+    "259807879+Bartok9@users.noreply.github.com": "Bartok9",
+    # contributors (manual mapping from git names)
+    "dmayhem93@gmail.com": "dmahan93",
+    "samherring99@gmail.com": "samherring99",
+    "desaiaum08@gmail.com": "Aum08Desai",
+    "shannon.sands.1979@gmail.com": "shannonsands",
+    "shannon@nousresearch.com": "shannonsands",
+    "eri@plasticlabs.ai": "Erosika",
+    "hjcpuro@gmail.com": "hjc-puro",
+    "xaydinoktay@gmail.com": "aydnOktay",
+    "abdullahfarukozden@gmail.com": "Farukest",
+    "lovre.pesut@gmail.com": "rovle",
+    "hakanerten02@hotmail.com": "teyrebaz33",
+    "alireza78.crypto@gmail.com": "alireza78a",
+    "brooklyn.bb.nicholson@gmail.com": "brooklynnicholson",
+    "gpickett00@gmail.com": "gpickett00",
+    "mcosma@gmail.com": "wakamex",
+    "clawdia.nash@proton.me": "clawdia-nash",
+    "pickett.austin@gmail.com": "austinpickett",
+    "jaisehgal11299@gmail.com": "jaisup",
+    "percydikec@gmail.com": "PercyDikec",
+    "dean.kerr@gmail.com": "deankerr",
+    "socrates1024@gmail.com": "socrates1024",
+    "satelerd@gmail.com": "satelerd",
+    "numman.ali@gmail.com": "nummanali",
+    "0xNyk@users.noreply.github.com": "0xNyk",
+    "0xnykcd@googlemail.com": "0xNyk",
+    "buraysandro9@gmail.com": "buray",
+    "contact@jomar.fr": "joshmartinelle",
+    "camilo@tekelala.com": "tekelala",
+    "vincentcharlebois@gmail.com": "vincentcharlebois",
+    "aryan@synvoid.com": "aryansingh",
+    "johnsonblake1@gmail.com": "blakejohnson",
+    "bryan@intertwinesys.com": "bryanyoung",
+    "christo.mitov@gmail.com": "christomitov",
+    "hermes@nousresearch.com": "NousResearch",
+    "openclaw@sparklab.ai": "openclaw",
+    "semihcvlk53@gmail.com": "Himess",
+    "erenkar950@gmail.com": "erenkarakus",
+    "adavyasharma@gmail.com": "adavyas",
+    "acaayush1111@gmail.com": "aayushchaudhary",
+    "jason@outland.art": "jasonoutland",
+    "mrflu1918@proton.me": "SPANISHFLU",
+    "morganemoss@gmai.com": "mormio",
+    "kopjop926@gmail.com": "cesareth",
+    "fuleinist@gmail.com": "fuleinist",
+    "jack.47@gmail.com": "JackTheGit",
+    "dalvidjr2022@gmail.com": "Jr-kenny",
+    "m@statecraft.systems": "mbierling",
+    "balyan.sid@gmail.com": "balyansid",
+}
+
+
+def git(*args, cwd=None):
+    """Run a git command and return stdout."""
+    result = subprocess.run(
+        ["git"] + list(args),
+        capture_output=True, text=True,
+        cwd=cwd or str(REPO_ROOT),
+    )
+    if result.returncode != 0:
+        print(f"git {' '.join(args)} failed: {result.stderr}", file=sys.stderr)
+        return ""
+    return result.stdout.strip()
+
+
+def get_last_tag():
+    """Get the most recent CalVer tag."""
+    tags = git("tag", "--list", "v20*", "--sort=-v:refname")
+    if tags:
+        return tags.split("\n")[0]
+    return None
+
+
+def get_current_version():
+    """Read current semver from __init__.py."""
+    content = VERSION_FILE.read_text()
+    match = re.search(r'__version__\s*=\s*"([^"]+)"', content)
+    return match.group(1) if match else "0.0.0"
+
+
+def bump_version(current: str, part: str) -> str:
+    """Bump a semver version string."""
+    parts = current.split(".")
+    if len(parts) != 3:
+        parts = ["0", "0", "0"]
+    major, minor, patch = int(parts[0]), int(parts[1]), int(parts[2])
+
+    if part == "major":
+        major += 1
+        minor = 0
+        patch = 0
+    elif part == "minor":
+        minor += 1
+        patch = 0
+    elif part == "patch":
+        patch += 1
+    else:
+        raise ValueError(f"Unknown bump part: {part}")
+
+    return f"{major}.{minor}.{patch}"
+
+
+def update_version_files(semver: str, calver_date: str):
+    """Update version strings in source files."""
+    # Update __init__.py
+    content = VERSION_FILE.read_text()
+    content = re.sub(
+        r'__version__\s*=\s*"[^"]+"',
+        f'__version__ = "{semver}"',
+        content,
+    )
+    content = re.sub(
+        r'__release_date__\s*=\s*"[^"]+"',
+        f'__release_date__ = "{calver_date}"',
+        content,
+    )
+    VERSION_FILE.write_text(content)
+
+    # Update pyproject.toml
+    pyproject = PYPROJECT_FILE.read_text()
+    pyproject = re.sub(
+        r'^version\s*=\s*"[^"]+"',
+        f'version = "{semver}"',
+        pyproject,
+        flags=re.MULTILINE,
+    )
+    PYPROJECT_FILE.write_text(pyproject)
+
+
+def resolve_author(name: str, email: str) -> str:
+    """Resolve a git author to a GitHub @mention."""
+    # Try email lookup first
+    gh_user = AUTHOR_MAP.get(email)
+    if gh_user:
+        return f"@{gh_user}"
+
+    # Try noreply pattern
+    noreply_match = re.match(r"(\d+)\+(.+)@users\.noreply\.github\.com", email)
+    if noreply_match:
+        return f"@{noreply_match.group(2)}"
+
+    # Try username@users.noreply.github.com
+    noreply_match2 = re.match(r"(.+)@users\.noreply\.github\.com", email)
+    if noreply_match2:
+        return f"@{noreply_match2.group(1)}"
+
+    # Fallback to git name
+    return name
+
+
+def categorize_commit(subject: str) -> str:
+    """Categorize a commit by its conventional commit prefix."""
+    subject_lower = subject.lower()
+
+    # Match conventional commit patterns
+    patterns = {
+        "breaking": [r"^breaking[\s:(]", r"^!:", r"BREAKING CHANGE"],
+        "features": [r"^feat[\s:(]", r"^feature[\s:(]", r"^add[\s:(]"],
+        "fixes": [r"^fix[\s:(]", r"^bugfix[\s:(]", r"^bug[\s:(]", r"^hotfix[\s:(]"],
+        "improvements": [r"^improve[\s:(]", r"^perf[\s:(]", r"^enhance[\s:(]",
+                         r"^refactor[\s:(]", r"^cleanup[\s:(]", r"^clean[\s:(]",
+                         r"^update[\s:(]", r"^optimize[\s:(]"],
+        "docs": [r"^doc[\s:(]", r"^docs[\s:(]"],
+        "tests": [r"^test[\s:(]", r"^tests[\s:(]"],
+        "chore": [r"^chore[\s:(]", r"^ci[\s:(]", r"^build[\s:(]",
+                  r"^deps[\s:(]", r"^bump[\s:(]"],
+    }
+
+    for category, regexes in patterns.items():
+        for regex in regexes:
+            if re.match(regex, subject_lower):
+                return category
+
+    # Heuristic fallbacks
+    if any(w in subject_lower for w in ["add ", "new ", "implement", "support "]):
+        return "features"
+    if any(w in subject_lower for w in ["fix ", "fixed ", "resolve", "patch "]):
+        return "fixes"
+    if any(w in subject_lower for w in ["refactor", "cleanup", "improve", "update "]):
+        return "improvements"
+
+    return "other"
+
+
+def clean_subject(subject: str) -> str:
+    """Clean up a commit subject for display."""
+    # Remove conventional commit prefix
+    cleaned = re.sub(r"^(feat|fix|docs|chore|refactor|test|perf|ci|build|improve|add|update|cleanup|hotfix|breaking|enhance|optimize|bugfix|bug|feature|tests|deps|bump)[\s:(!]+\s*", "", subject, flags=re.IGNORECASE)
+    # Remove trailing issue refs that are redundant with PR links
+    cleaned = cleaned.strip()
+    # Capitalize first letter
+    if cleaned:
+        cleaned = cleaned[0].upper() + cleaned[1:]
+    return cleaned
+
+
+def get_commits(since_tag=None):
+    """Get commits since a tag (or all commits if None)."""
+    if since_tag:
+        range_spec = f"{since_tag}..HEAD"
+    else:
+        range_spec = "HEAD"
+
+    # Format: hash|author_name|author_email|subject
+    log = git(
+        "log", range_spec,
+        "--format=%H|%an|%ae|%s",
+        "--no-merges",
+    )
+
+    if not log:
+        return []
+
+    commits = []
+    for line in log.split("\n"):
+        if not line.strip():
+            continue
+        parts = line.split("|", 3)
+        if len(parts) != 4:
+            continue
+        sha, name, email, subject = parts
+        commits.append({
+            "sha": sha,
+            "short_sha": sha[:8],
+            "author_name": name,
+            "author_email": email,
+            "subject": subject,
+            "category": categorize_commit(subject),
+            "github_author": resolve_author(name, email),
+        })
+
+    return commits
+
+
+def get_pr_number(subject: str) -> str:
+    """Extract PR number from commit subject if present."""
+    match = re.search(r"#(\d+)", subject)
+    if match:
+        return match.group(1)
+    return None
+
+
+def generate_changelog(commits, tag_name, semver, repo_url="https://github.com/NousResearch/hermes-agent",
+                       prev_tag=None, first_release=False):
+    """Generate markdown changelog from categorized commits."""
+    lines = []
+
+    # Header
+    now = datetime.now()
+    date_str = now.strftime("%B %d, %Y")
+    lines.append(f"# Hermes Agent v{semver} ({tag_name})")
+    lines.append("")
+    lines.append(f"**Release Date:** {date_str}")
+    lines.append("")
+
+    if first_release:
+        lines.append("> 🎉 **First official release!** This marks the beginning of regular weekly releases")
+        lines.append("> for Hermes Agent. See below for everything included in this initial release.")
+        lines.append("")
+
+    # Group commits by category
+    categories = defaultdict(list)
+    all_authors = set()
+    teknium_aliases = {"@teknium1"}
+
+    for commit in commits:
+        categories[commit["category"]].append(commit)
+        author = commit["github_author"]
+        if author not in teknium_aliases:
+            all_authors.add(author)
+
+    # Category display order and emoji
+    category_order = [
+        ("breaking", "⚠️ Breaking Changes"),
+        ("features", "✨ Features"),
+        ("improvements", "🔧 Improvements"),
+        ("fixes", "🐛 Bug Fixes"),
+        ("docs", "📚 Documentation"),
+        ("tests", "🧪 Tests"),
+        ("chore", "🏗️ Infrastructure"),
+        ("other", "📦 Other Changes"),
+    ]
+
+    for cat_key, cat_title in category_order:
+        cat_commits = categories.get(cat_key, [])
+        if not cat_commits:
+            continue
+
+        lines.append(f"## {cat_title}")
+        lines.append("")
+
+        for commit in cat_commits:
+            subject = clean_subject(commit["subject"])
+            pr_num = get_pr_number(commit["subject"])
+            author = commit["github_author"]
+
+            # Build the line
+            parts = [f"- {subject}"]
+            if pr_num:
+                parts.append(f"([#{pr_num}]({repo_url}/pull/{pr_num}))")
+            else:
+                parts.append(f"([`{commit['short_sha']}`]({repo_url}/commit/{commit['sha']}))")
+
+            if author not in teknium_aliases:
+                parts.append(f"— {author}")
+
+            lines.append(" ".join(parts))
+
+        lines.append("")
+
+    # Contributors section
+    if all_authors:
+        # Sort contributors by commit count
+        author_counts = defaultdict(int)
+        for commit in commits:
+            author = commit["github_author"]
+            if author not in teknium_aliases:
+                author_counts[author] += 1
+
+        sorted_authors = sorted(author_counts.items(), key=lambda x: -x[1])
+
+        lines.append("## 👥 Contributors")
+        lines.append("")
+        lines.append("Thank you to everyone who contributed to this release!")
+        lines.append("")
+        for author, count in sorted_authors:
+            commit_word = "commit" if count == 1 else "commits"
+            lines.append(f"- {author} ({count} {commit_word})")
+        lines.append("")
+
+    # Full changelog link
+    if prev_tag:
+        lines.append(f"**Full Changelog**: [{prev_tag}...{tag_name}]({repo_url}/compare/{prev_tag}...{tag_name})")
+    else:
+        lines.append(f"**Full Changelog**: [{tag_name}]({repo_url}/commits/{tag_name})")
+    lines.append("")
+
+    return "\n".join(lines)
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Hermes Agent Release Tool")
+    parser.add_argument("--bump", choices=["major", "minor", "patch"],
+                        help="Which semver component to bump")
+    parser.add_argument("--publish", action="store_true",
+                        help="Actually create the tag and GitHub release (otherwise dry run)")
+    parser.add_argument("--date", type=str,
+                        help="Override CalVer date (format: YYYY.M.D)")
+    parser.add_argument("--first-release", action="store_true",
+                        help="Mark as first release (no previous tag expected)")
+    parser.add_argument("--output", type=str,
+                        help="Write changelog to file instead of stdout")
+    args = parser.parse_args()
+
+    # Determine CalVer date
+    if args.date:
+        calver_date = args.date
+    else:
+        now = datetime.now()
+        calver_date = f"{now.year}.{now.month}.{now.day}"
+
+    tag_name = f"v{calver_date}"
+
+    # Check for existing tag with same date
+    existing = git("tag", "--list", tag_name)
+    if existing and not args.publish:
+        # Append a suffix for same-day releases
+        suffix = 2
+        while git("tag", "--list", f"{tag_name}.{suffix}"):
+            suffix += 1
+        tag_name = f"{tag_name}.{suffix}"
+        calver_date = f"{calver_date}.{suffix}"
+        print(f"Note: Tag {tag_name[:-2]} already exists, using {tag_name}")
+
+    # Determine semver
+    current_version = get_current_version()
+    if args.bump:
+        new_version = bump_version(current_version, args.bump)
+    else:
+        new_version = current_version
+
+    # Get previous tag
+    prev_tag = get_last_tag()
+    if not prev_tag and not args.first_release:
+        print("No previous tags found. Use --first-release for the initial release.")
+        print(f"Would create tag: {tag_name}")
+        print(f"Would set version: {new_version}")
+
+    # Get commits
+    commits = get_commits(since_tag=prev_tag)
+    if not commits:
+        print("No new commits since last tag.")
+        if not args.first_release:
+            return
+
+    print(f"{'='*60}")
+    print(f"  Hermes Agent Release Preview")
+    print(f"{'='*60}")
+    print(f"  CalVer tag:      {tag_name}")
+    print(f"  SemVer:          v{current_version} → v{new_version}")
+    print(f"  Previous tag:    {prev_tag or '(none — first release)'}")
+    print(f"  Commits:         {len(commits)}")
+    print(f"  Unique authors:  {len(set(c['github_author'] for c in commits))}")
+    print(f"  Mode:            {'PUBLISH' if args.publish else 'DRY RUN'}")
+    print(f"{'='*60}")
+    print()
+
+    # Generate changelog
+    changelog = generate_changelog(
+        commits, tag_name, new_version,
+        prev_tag=prev_tag,
+        first_release=args.first_release,
+    )
+
+    if args.output:
+        Path(args.output).write_text(changelog)
+        print(f"Changelog written to {args.output}")
+    else:
+        print(changelog)
+
+    if args.publish:
+        print(f"\n{'='*60}")
+        print("  Publishing release...")
+        print(f"{'='*60}")
+
+        # Update version files
+        if args.bump:
+            update_version_files(new_version, calver_date)
+            print(f"  ✓ Updated version files to v{new_version} ({calver_date})")
+
+            # Commit version bump
+            git("add", str(VERSION_FILE), str(PYPROJECT_FILE))
+            git("commit", "-m", f"chore: bump version to v{new_version} ({calver_date})")
+            print(f"  ✓ Committed version bump")
+
+        # Create annotated tag
+        git("tag", "-a", tag_name, "-m",
+            f"Hermes Agent v{new_version} ({calver_date})\n\nWeekly release")
+        print(f"  ✓ Created tag {tag_name}")
+
+        # Push
+        push_result = git("push", "origin", "HEAD", "--tags")
+        print(f"  ✓ Pushed to origin")
+
+        # Create GitHub release
+        changelog_file = REPO_ROOT / ".release_notes.md"
+        changelog_file.write_text(changelog)
+
+        result = subprocess.run(
+            ["gh", "release", "create", tag_name,
+             "--title", f"Hermes Agent v{new_version} ({calver_date})",
+             "--notes-file", str(changelog_file)],
+            capture_output=True, text=True,
+            cwd=str(REPO_ROOT),
+        )
+
+        changelog_file.unlink(missing_ok=True)
+
+        if result.returncode == 0:
+            print(f"  ✓ GitHub release created: {result.stdout.strip()}")
+        else:
+            print(f"  ✗ GitHub release failed: {result.stderr}")
+            print(f"    Tag was created. Create the release manually:")
+            print(f"    gh release create {tag_name} --title 'Hermes Agent v{new_version} ({calver_date})'")
+
+        print(f"\n  🎉 Release v{new_version} ({tag_name}) published!")
+    else:
+        print(f"\n{'='*60}")
+        print(f"  Dry run complete. To publish, add --publish")
+        print(f"  Example: python scripts/release.py --bump minor --publish")
+        print(f"{'='*60}")
+
+
+if __name__ == "__main__":
+    main()

skills/apple/apple-notes/SKILL.md

@@ -9,6 +9,8 @@ metadata:
   hermes:
     tags: [Notes, Apple, macOS, note-taking]
     related_skills: [obsidian]
+prerequisites:
+  commands: [memo]
 ---
 
 # Apple Notes

skills/apple/apple-reminders/SKILL.md

@@ -8,6 +8,8 @@ platforms: [macos]
 metadata:
   hermes:
     tags: [Reminders, tasks, todo, macOS, Apple]
+prerequisites:
+  commands: [remindctl]
 ---
 
 # Apple Reminders