fix: use consistent fallback for pickle_key derivation

Address review: _pickle_key now uses _acct_id (which has the 'hermes'
fallback) instead of raw self._user_id, so both values stay consistent
when user_id is empty.

.github/workflows/docker-publish.yml

@@ -8,6 +8,9 @@ on:
   release:
     types: [published]
 
+permissions:
+  contents: read
+
 concurrency:
   group: docker-${{ github.ref }}
   cancel-in-progress: true
@@ -17,22 +20,29 @@ jobs:
     # Only run on the upstream repository, not on forks
     if: github.repository == 'NousResearch/hermes-agent'
     runs-on: ubuntu-latest
-    timeout-minutes: 30
+    timeout-minutes: 60
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
         with:
           submodules: recursive
 
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v3
+
       - name: Set up Docker Buildx
         uses: docker/setup-buildx-action@v3
 
-      - name: Build image
+      # Build amd64 only so we can `load` the image for smoke testing.
+      # `load: true` cannot export a multi-arch manifest to the local daemon.
+      # The multi-arch build follows on push to main / release.
+      - name: Build image (amd64, smoke test)
         uses: docker/build-push-action@v6
         with:
           context: .
           file: Dockerfile
           load: true
+          platforms: linux/amd64
           tags: nousresearch/hermes-agent:test
           cache-from: type=gha
           cache-to: type=gha,mode=max
@@ -51,26 +61,28 @@ jobs:
           username: ${{ secrets.DOCKERHUB_USERNAME }}
           password: ${{ secrets.DOCKERHUB_TOKEN }}
 
-      - name: Push image (main branch)
+      - name: Push multi-arch image (main branch)
         if: github.event_name == 'push' && github.ref == 'refs/heads/main'
         uses: docker/build-push-action@v6
         with:
           context: .
           file: Dockerfile
           push: true
+          platforms: linux/amd64,linux/arm64
           tags: |
             nousresearch/hermes-agent:latest
             nousresearch/hermes-agent:${{ github.sha }}
           cache-from: type=gha
           cache-to: type=gha,mode=max
 
-      - name: Push image (release)
+      - name: Push multi-arch image (release)
         if: github.event_name == 'release'
         uses: docker/build-push-action@v6
         with:
           context: .
           file: Dockerfile
           push: true
+          platforms: linux/amd64,linux/arm64
           tags: |
             nousresearch/hermes-agent:latest
             nousresearch/hermes-agent:${{ github.event.release.tag_name }}

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

@@ -27,8 +27,8 @@ jobs:
         with:
           python-version: '3.11'
 
-      - name: Install Python dependencies
-        run: python -m pip install ascii-guard pyyaml
+      - name: Install ascii-guard
+        run: python -m pip install ascii-guard==2.3.0 pyyaml==6.0.3
 
       - name: Extract skill metadata for dashboard
         run: python3 website/scripts/extract-skills.py

.github/workflows/nix.yml

@@ -27,8 +27,8 @@ jobs:
     timeout-minutes: 30
     steps:
       - uses: actions/checkout@v4
-      - uses: DeterminateSystems/nix-installer-action@main
-      - uses: DeterminateSystems/magic-nix-cache-action@main
+      - uses: DeterminateSystems/nix-installer-action@ef8a148080ab6020fd15196c2084a2eea5ff2d25  # v22
+      - uses: DeterminateSystems/magic-nix-cache-action@565684385bcd71bad329742eefe8d12f2e765b39  # v13
       - name: Check flake
         if: runner.os == 'Linux'
         run: nix flake check --print-build-logs

Dockerfile

@@ -1,16 +1,20 @@
 FROM debian:13.4
 
+# Disable Python stdout buffering to ensure logs are printed immediately
+ENV PYTHONUNBUFFERED=1
+
 # Install system dependencies in one layer, clear APT cache
 RUN apt-get update && \
     apt-get install -y --no-install-recommends \
-        build-essential nodejs npm python3 python3-pip ripgrep ffmpeg gcc python3-dev libffi-dev && \
+        build-essential nodejs npm python3 python3-pip ripgrep ffmpeg gcc python3-dev libffi-dev procps && \
     rm -rf /var/lib/apt/lists/*
 
 COPY . /opt/hermes
 WORKDIR /opt/hermes
 
 # Install Python and Node dependencies in one layer, no cache
-RUN pip install --no-cache-dir -e ".[all]" --break-system-packages && \
+RUN pip install --no-cache-dir uv --break-system-packages && \
+    uv pip install --system --break-system-packages --no-cache -e ".[all]" && \
     npm install --prefer-offline --no-audit && \
     npx playwright install --with-deps chromium --only-shell && \
     cd /opt/hermes/scripts/whatsapp-bridge && \

README.md

@@ -33,8 +33,10 @@ Use any model you want — [Nous Portal](https://portal.nousresearch.com), [Open
 curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash
 ```
 
-Works on Linux, macOS, and WSL2. The installer handles everything — Python, Node.js, dependencies, and the `hermes` command. No prerequisites except git.
+Works on Linux, macOS, WSL2, and Android via Termux. The installer handles the platform-specific setup for you.
 
+> **Android / Termux:** The tested manual path is documented in the [Termux guide](https://hermes-agent.nousresearch.com/docs/getting-started/termux). On Termux, Hermes installs a curated `.[termux]` extra because the full `.[all]` extra currently pulls Android-incompatible voice dependencies.
+>
 > **Windows:** Native Windows is not supported. Please install [WSL2](https://learn.microsoft.com/en-us/windows/wsl/install) and run the command above.
 
 After installation:

acp_adapter/server.py

@@ -36,6 +36,7 @@ from acp.schema import (
     SessionCapabilities,
     SessionForkCapabilities,
     SessionListCapabilities,
+    SessionResumeCapabilities,
     SessionInfo,
     TextContentBlock,
     UnstructuredCommandInput,
@@ -245,9 +246,11 @@ class HermesACPAgent(acp.Agent):
             protocol_version=acp.PROTOCOL_VERSION,
             agent_info=Implementation(name="hermes-agent", version=HERMES_VERSION),
             agent_capabilities=AgentCapabilities(
+                load_session=True,
                 session_capabilities=SessionCapabilities(
                     fork=SessionForkCapabilities(),
                     list=SessionListCapabilities(),
+                    resume=SessionResumeCapabilities(),
                 ),
             ),
             auth_methods=auth_methods,
@@ -451,14 +454,13 @@ class HermesACPAgent(acp.Agent):
             await conn.session_update(session_id, update)
 
         usage = None
-        usage_data = result.get("usage")
-        if usage_data and isinstance(usage_data, dict):
+        if any(result.get(key) is not None for key in ("prompt_tokens", "completion_tokens", "total_tokens")):
             usage = Usage(
-                input_tokens=usage_data.get("prompt_tokens", 0),
-                output_tokens=usage_data.get("completion_tokens", 0),
-                total_tokens=usage_data.get("total_tokens", 0),
-                thought_tokens=usage_data.get("reasoning_tokens"),
-                cached_read_tokens=usage_data.get("cached_tokens"),
+                input_tokens=result.get("prompt_tokens", 0),
+                output_tokens=result.get("completion_tokens", 0),
+                total_tokens=result.get("total_tokens", 0),
+                thought_tokens=result.get("reasoning_tokens"),
+                cached_read_tokens=result.get("cache_read_tokens"),
             )
 
         stop_reason = "cancelled" if state.cancel_event and state.cancel_event.is_set() else "end_turn"

agent/anthropic_adapter.py

@@ -60,6 +60,8 @@ _ANTHROPIC_OUTPUT_LIMITS = {
     "claude-3-opus":       4_096,
     "claude-3-sonnet":     4_096,
     "claude-3-haiku":      4_096,
+    # Third-party Anthropic-compatible providers
+    "minimax":            131_072,
 }
 
 # For any model not in the table, assume the highest current limit.
@@ -74,8 +76,11 @@ def _get_anthropic_max_output(model: str) -> int:
     model IDs (claude-sonnet-4-5-20250929) and variant suffixes (:1m, :fast)
     resolve correctly.  Longest-prefix match wins to avoid e.g. "claude-3-5"
     matching before "claude-3-5-sonnet".
+
+    Normalizes dots to hyphens so that model names like
+    ``anthropic/claude-opus-4.6`` match the ``claude-opus-4-6`` table key.
     """
-    m = model.lower()
+    m = model.lower().replace(".", "-")
     best_key = ""
     best_val = _ANTHROPIC_DEFAULT_OUTPUT_LIMIT
     for key, val in _ANTHROPIC_OUTPUT_LIMITS.items():
@@ -95,6 +100,15 @@ _COMMON_BETAS = [
     "interleaved-thinking-2025-05-14",
     "fine-grained-tool-streaming-2025-05-14",
 ]
+# MiniMax's Anthropic-compatible endpoints fail tool-use requests when
+# the fine-grained tool streaming beta is present.  Omit it so tool calls
+# fall back to the provider's default response path.
+_TOOL_STREAMING_BETA = "fine-grained-tool-streaming-2025-05-14"
+
+# Fast mode beta — enables the ``speed: "fast"`` request parameter for
+# significantly higher output token throughput on Opus 4.6 (~2.5x).
+# See https://platform.claude.com/docs/en/build-with-claude/fast-mode
+_FAST_MODE_BETA = "fast-mode-2026-02-01"
 
 # Additional beta headers required for OAuth/subscription auth.
 # Matches what Claude Code (and pi-ai / OpenCode) send.
@@ -149,18 +163,27 @@ def _get_claude_code_version() -> str:
 
 
 def _is_oauth_token(key: str) -> bool:
-    """Check if the key is an OAuth/setup token (not a regular Console API key).
+    """Check if the key is an Anthropic OAuth/setup token.
 
-    Regular API keys start with 'sk-ant-api'. Everything else (setup-tokens
-    starting with 'sk-ant-oat', managed keys, JWTs, etc.) needs Bearer auth.
+    Positively identifies Anthropic OAuth tokens by their key format:
+    - ``sk-ant-`` prefix (but NOT ``sk-ant-api``) → setup tokens, managed keys
+    - ``eyJ`` prefix → JWTs from the Anthropic OAuth flow
+
+    Non-Anthropic keys (MiniMax, Alibaba, etc.) don't match either pattern
+    and correctly return False.
     """
     if not key:
         return False
-    # Regular Console API keys use x-api-key header
+    # Regular Anthropic Console API keys — x-api-key auth, never OAuth
     if key.startswith("sk-ant-api"):
         return False
-    # Everything else (setup-tokens, managed keys, JWTs) uses Bearer auth
-    return True
+    # Anthropic-issued tokens (setup-tokens sk-ant-oat-*, managed keys)
+    if key.startswith("sk-ant-"):
+        return True
+    # JWTs from Anthropic OAuth flow
+    if key.startswith("eyJ"):
+        return True
+    return False
 
 
 def _normalize_base_url_text(base_url) -> str:
@@ -204,6 +227,19 @@ def _requires_bearer_auth(base_url: str | None) -> bool:
     return normalized.startswith(("https://api.minimax.io/anthropic", "https://api.minimaxi.com/anthropic"))
 
 
+def _common_betas_for_base_url(base_url: str | None) -> list[str]:
+    """Return the beta headers that are safe for the configured endpoint.
+
+    MiniMax's Anthropic-compatible endpoints (Bearer-auth) reject requests
+    that include Anthropic's ``fine-grained-tool-streaming`` beta — every
+    tool-use message triggers a connection error.  Strip that beta for
+    Bearer-auth endpoints while keeping all other betas intact.
+    """
+    if _requires_bearer_auth(base_url):
+        return [b for b in _COMMON_BETAS if b != _TOOL_STREAMING_BETA]
+    return _COMMON_BETAS
+
+
 def build_anthropic_client(api_key: str, base_url: str = None):
     """Create an Anthropic client, auto-detecting setup-tokens vs API keys.
 
@@ -222,6 +258,7 @@ def build_anthropic_client(api_key: str, base_url: str = None):
     }
     if normalized_base_url:
         kwargs["base_url"] = normalized_base_url
+    common_betas = _common_betas_for_base_url(normalized_base_url)
 
     if _requires_bearer_auth(normalized_base_url):
         # Some Anthropic-compatible providers (e.g. MiniMax) expect the API key in
@@ -231,21 +268,21 @@ def build_anthropic_client(api_key: str, base_url: str = None):
         # not use Anthropic's sk-ant-api prefix and would otherwise be misread as
         # Anthropic OAuth/setup tokens.
         kwargs["auth_token"] = api_key
-        if _COMMON_BETAS:
-            kwargs["default_headers"] = {"anthropic-beta": ",".join(_COMMON_BETAS)}
+        if common_betas:
+            kwargs["default_headers"] = {"anthropic-beta": ",".join(common_betas)}
     elif _is_third_party_anthropic_endpoint(base_url):
         # Third-party proxies (Azure AI Foundry, AWS Bedrock, etc.) use their
         # own API keys with x-api-key auth. Skip OAuth detection — their keys
         # don't follow Anthropic's sk-ant-* prefix convention and would be
         # misclassified as OAuth tokens.
         kwargs["api_key"] = api_key
-        if _COMMON_BETAS:
-            kwargs["default_headers"] = {"anthropic-beta": ",".join(_COMMON_BETAS)}
+        if common_betas:
+            kwargs["default_headers"] = {"anthropic-beta": ",".join(common_betas)}
     elif _is_oauth_token(api_key):
         # OAuth access token / setup-token → Bearer auth + Claude Code identity.
         # Anthropic routes OAuth requests based on user-agent and headers;
         # without Claude Code's fingerprint, requests get intermittent 500s.
-        all_betas = _COMMON_BETAS + _OAUTH_ONLY_BETAS
+        all_betas = common_betas + _OAUTH_ONLY_BETAS
         kwargs["auth_token"] = api_key
         kwargs["default_headers"] = {
             "anthropic-beta": ",".join(all_betas),
@@ -255,8 +292,8 @@ def build_anthropic_client(api_key: str, base_url: str = None):
     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)}
+        if common_betas:
+            kwargs["default_headers"] = {"anthropic-beta": ",".join(common_betas)}
 
     return _anthropic_sdk.Anthropic(**kwargs)
 
@@ -485,35 +522,6 @@ def _prefer_refreshable_claude_code_token(env_token: str, creds: Optional[Dict[s
     return None
 
 
-def get_anthropic_token_source(token: Optional[str] = None) -> str:
-    """Best-effort source classification for an Anthropic credential token."""
-    token = (token or "").strip()
-    if not token:
-        return "none"
-
-    env_token = os.getenv("ANTHROPIC_TOKEN", "").strip()
-    if env_token and env_token == token:
-        return "anthropic_token_env"
-
-    cc_env_token = os.getenv("CLAUDE_CODE_OAUTH_TOKEN", "").strip()
-    if cc_env_token and cc_env_token == token:
-        return "claude_code_oauth_token_env"
-
-    creds = read_claude_code_credentials()
-    if creds and creds.get("accessToken") == token:
-        return str(creds.get("source") or "claude_code_credentials")
-
-    managed_key = read_claude_managed_key()
-    if managed_key and managed_key == token:
-        return "claude_json_primary_api_key"
-
-    api_key = os.getenv("ANTHROPIC_API_KEY", "").strip()
-    if api_key and api_key == token:
-        return "anthropic_api_key_env"
-
-    return "unknown"
-
-
 def resolve_anthropic_token() -> Optional[str]:
     """Resolve an Anthropic token from all available sources.
 
@@ -720,21 +728,6 @@ def run_hermes_oauth_login_pure() -> Optional[Dict[str, Any]]:
     }
 
 
-def _save_hermes_oauth_credentials(access_token: str, refresh_token: str, expires_at_ms: int) -> None:
-    """Save OAuth credentials to ~/.hermes/.anthropic_oauth.json."""
-    data = {
-        "accessToken": access_token,
-        "refreshToken": refresh_token,
-        "expiresAt": expires_at_ms,
-    }
-    try:
-        _HERMES_OAUTH_FILE.parent.mkdir(parents=True, exist_ok=True)
-        _HERMES_OAUTH_FILE.write_text(json.dumps(data, indent=2), encoding="utf-8")
-        _HERMES_OAUTH_FILE.chmod(0o600)
-    except (OSError, IOError) as e:
-        logger.debug("Failed to save Hermes OAuth credentials: %s", e)
-
-
 def read_hermes_oauth_credentials() -> Optional[Dict[str, Any]]:
     """Read Hermes-managed OAuth credentials from ~/.hermes/.anthropic_oauth.json."""
     if _HERMES_OAUTH_FILE.exists():
@@ -783,39 +776,6 @@ def _sanitize_tool_id(tool_id: str) -> str:
     return sanitized or "tool_0"
 
 
-def _convert_openai_image_part_to_anthropic(part: Dict[str, Any]) -> Optional[Dict[str, Any]]:
-    """Convert an OpenAI-style image block to Anthropic's image source format."""
-    image_data = part.get("image_url", {})
-    url = image_data.get("url", "") if isinstance(image_data, dict) else str(image_data)
-    if not isinstance(url, str) or not url.strip():
-        return None
-    url = url.strip()
-
-    if url.startswith("data:"):
-        header, sep, data = url.partition(",")
-        if sep and ";base64" in header:
-            media_type = header[5:].split(";", 1)[0] or "image/png"
-            return {
-                "type": "image",
-                "source": {
-                    "type": "base64",
-                    "media_type": media_type,
-                    "data": data,
-                },
-            }
-
-    if url.startswith(("http://", "https://")):
-        return {
-            "type": "image",
-            "source": {
-                "type": "url",
-                "url": url,
-            },
-        }
-
-    return None
-
-
 def convert_tools_to_anthropic(tools: List[Dict]) -> List[Dict]:
     """Convert OpenAI tool definitions to Anthropic format."""
     if not tools:
@@ -1235,13 +1195,31 @@ def build_anthropic_kwargs(
     preserve_dots: bool = False,
     context_length: Optional[int] = None,
     base_url: str | None = None,
+    fast_mode: bool = False,
 ) -> Dict[str, Any]:
     """Build kwargs for anthropic.messages.create().
 
-    When *max_tokens* is None, the model's native output limit is used
-    (e.g. 128K for Opus 4.6, 64K for Sonnet 4.6).  If *context_length*
-    is provided, the effective limit is clamped so it doesn't exceed
-    the context window.
+    Naming note — two distinct concepts, easily confused:
+      max_tokens     = OUTPUT token cap for a single response.
+                       Anthropic's API calls this "max_tokens" but it only
+                       limits the *output*.  Anthropic's own native SDK
+                       renamed it "max_output_tokens" for clarity.
+      context_length = TOTAL context window (input tokens + output tokens).
+                       The API enforces: input_tokens + max_tokens ≤ context_length.
+                       Stored on the ContextCompressor; reduced on overflow errors.
+
+    When *max_tokens* is None the model's native output ceiling is used
+    (e.g. 128K for Opus 4.6, 64K for Sonnet 4.6).
+
+    When *context_length* is provided and the model's native output ceiling
+    exceeds it (e.g. a local endpoint with an 8K window), the output cap is
+    clamped to context_length − 1.  This only kicks in for unusually small
+    context windows; for full-size models the native output cap is always
+    smaller than the context window so no clamping happens.
+    NOTE: this clamping does not account for prompt size — if the prompt is
+    large, Anthropic may still reject the request.  The caller must detect
+    "max_tokens too large given prompt" errors and retry with a smaller cap
+    (see parse_available_output_tokens_from_error + _ephemeral_max_output_tokens).
 
     When *is_oauth* is True, applies Claude Code compatibility transforms:
     system prompt prefix, tool name prefixing, and prompt sanitization.
@@ -1251,15 +1229,23 @@ def build_anthropic_kwargs(
 
     When *base_url* points to a third-party Anthropic-compatible endpoint,
     thinking block signatures are stripped (they are Anthropic-proprietary).
+
+    When *fast_mode* is True, adds ``speed: "fast"`` and the fast-mode beta
+    header for ~2.5x faster output throughput on Opus 4.6.  Currently only
+    supported on native Anthropic endpoints (not third-party compatible ones).
     """
     system, anthropic_messages = convert_messages_to_anthropic(messages, base_url=base_url)
     anthropic_tools = convert_tools_to_anthropic(tools) if tools else []
 
     model = normalize_model_name(model, preserve_dots=preserve_dots)
+    # effective_max_tokens = output cap for this call (≠ total context window)
     effective_max_tokens = max_tokens or _get_anthropic_max_output(model)
 
-    # Clamp to context window if the user set a lower context_length
-    # (e.g. custom endpoint with limited capacity).
+    # Clamp output cap to fit inside the total context window.
+    # Only matters for small custom endpoints where context_length < native
+    # output ceiling.  For standard Anthropic models context_length (e.g.
+    # 200K) is always larger than the output ceiling (e.g. 128K), so this
+    # branch is not taken.
     if context_length and effective_max_tokens > context_length:
         effective_max_tokens = max(context_length - 1, 1)
 
@@ -1329,9 +1315,10 @@ def build_anthropic_kwargs(
     # 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 and MiniMax models do NOT support extended thinking — skip entirely.
+    # MiniMax Anthropic-compat endpoints support thinking (manual mode only,
+    # not adaptive).  Haiku does NOT support extended thinking — skip entirely.
     if reasoning_config and isinstance(reasoning_config, dict):
-        if reasoning_config.get("enabled") is not False and "haiku" not in model.lower() and "minimax" not in model.lower():
+        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):
@@ -1345,6 +1332,20 @@ def build_anthropic_kwargs(
                 kwargs["temperature"] = 1
                 kwargs["max_tokens"] = max(effective_max_tokens, budget + 4096)
 
+    # ── Fast mode (Opus 4.6 only) ────────────────────────────────────
+    # Adds speed:"fast" + the fast-mode beta header for ~2.5x output speed.
+    # Only for native Anthropic endpoints — third-party providers would
+    # reject the unknown beta header and speed parameter.
+    if fast_mode and not _is_third_party_anthropic_endpoint(base_url):
+        kwargs["speed"] = "fast"
+        # Build extra_headers with ALL applicable betas (the per-request
+        # extra_headers override the client-level anthropic-beta header).
+        betas = list(_common_betas_for_base_url(base_url))
+        if is_oauth:
+            betas.extend(_OAUTH_ONLY_BETAS)
+        betas.append(_FAST_MODE_BETA)
+        kwargs["extra_headers"] = {"anthropic-beta": ",".join(betas)}
+
     return kwargs
 
 
@@ -1406,4 +1407,4 @@ def normalize_anthropic_response(
             reasoning_details=reasoning_details or None,
         ),
         finish_reason,
-    )
+    )

agent/auxiliary_client.py

@@ -59,6 +59,9 @@ from hermes_constants import OPENROUTER_BASE_URL
 
 logger = logging.getLogger(__name__)
 
+# Module-level flag: only warn once per process about stale OPENAI_BASE_URL.
+_stale_base_url_warned = False
+
 _PROVIDER_ALIASES = {
     "google": "gemini",
     "google-gemini": "gemini",
@@ -629,11 +632,19 @@ def _nous_base_url() -> str:
 
 
 def _read_codex_access_token() -> Optional[str]:
-    """Read a valid, non-expired Codex OAuth access token from Hermes auth store."""
+    """Read a valid, non-expired Codex OAuth access token from Hermes auth store.
+
+    If a credential pool exists but currently has no selectable runtime entry
+    (for example all pool slots are marked exhausted), fall back to the
+    profile's auth.json token instead of hard-failing. This keeps explicit
+    fallback-to-Codex working when the pool state is stale but the stored OAuth
+    token is still valid.
+    """
     pool_present, entry = _select_pool_entry("openai-codex")
     if pool_present:
         token = _pool_runtime_api_key(entry)
-        return token or None
+        if token:
+            return token
 
     try:
         from hermes_cli.auth import _read_codex_tokens
@@ -679,6 +690,15 @@ def _resolve_api_key_provider() -> Tuple[Optional[OpenAI], Optional[str]]:
         if pconfig.auth_type != "api_key":
             continue
         if provider_id == "anthropic":
+            # Only try anthropic when the user has explicitly configured it.
+            # Without this gate, Claude Code credentials get silently used
+            # as auxiliary fallback when the user's primary provider fails.
+            try:
+                from hermes_cli.auth import is_provider_explicitly_configured
+                if not is_provider_explicitly_configured("anthropic"):
+                    continue
+            except ImportError:
+                pass
             return _try_anthropic()
 
         pool_present, entry = _select_pool_entry(provider_id)
@@ -690,11 +710,13 @@ def _resolve_api_key_provider() -> Tuple[Optional[OpenAI], Optional[str]]:
             base_url = _to_openai_base_url(
                 _pool_runtime_base_url(entry, pconfig.inference_base_url) or pconfig.inference_base_url
             )
-            model = _API_KEY_PROVIDER_AUX_MODELS.get(provider_id, "default")
+            model = _API_KEY_PROVIDER_AUX_MODELS.get(provider_id)
+            if model is None:
+                continue  # skip provider if we don't know a valid aux model
             logger.debug("Auxiliary text client: %s (%s) via pool", pconfig.name, model)
             extra = {}
             if "api.kimi.com" in base_url.lower():
-                extra["default_headers"] = {"User-Agent": "KimiCLI/1.0"}
+                extra["default_headers"] = {"User-Agent": "KimiCLI/1.30.0"}
             elif "api.githubcopilot.com" in base_url.lower():
                 from hermes_cli.models import copilot_default_headers
 
@@ -709,11 +731,13 @@ def _resolve_api_key_provider() -> Tuple[Optional[OpenAI], Optional[str]]:
         base_url = _to_openai_base_url(
             str(creds.get("base_url", "")).strip().rstrip("/") or pconfig.inference_base_url
         )
-        model = _API_KEY_PROVIDER_AUX_MODELS.get(provider_id, "default")
+        model = _API_KEY_PROVIDER_AUX_MODELS.get(provider_id)
+        if model is None:
+            continue  # skip provider if we don't know a valid aux model
         logger.debug("Auxiliary text client: %s (%s)", pconfig.name, model)
         extra = {}
         if "api.kimi.com" in base_url.lower():
-            extra["default_headers"] = {"User-Agent": "KimiCLI/1.0"}
+            extra["default_headers"] = {"User-Agent": "KimiCLI/1.30.0"}
         elif "api.githubcopilot.com" in base_url.lower():
             from hermes_cli.models import copilot_default_headers
 
@@ -840,7 +864,7 @@ def _read_main_provider() -> str:
     return ""
 
 
-def _resolve_custom_runtime() -> Tuple[Optional[str], Optional[str]]:
+def _resolve_custom_runtime() -> Tuple[Optional[str], Optional[str], Optional[str]]:
     """Resolve the active custom/main endpoint the same way the main CLI does.
 
     This covers both env-driven OPENAI_BASE_URL setups and config-saved custom
@@ -853,18 +877,29 @@ def _resolve_custom_runtime() -> Tuple[Optional[str], Optional[str]]:
         runtime = resolve_runtime_provider(requested="custom")
     except Exception as exc:
         logger.debug("Auxiliary client: custom runtime resolution failed: %s", exc)
-        return None, None
+        runtime = None
+
+    if not isinstance(runtime, dict):
+        openai_base = os.getenv("OPENAI_BASE_URL", "").strip().rstrip("/")
+        openai_key = os.getenv("OPENAI_API_KEY", "").strip()
+        if not openai_base:
+            return None, None, None
+        runtime = {
+            "base_url": openai_base,
+            "api_key": openai_key,
+        }
 
     custom_base = runtime.get("base_url")
     custom_key = runtime.get("api_key")
+    custom_mode = runtime.get("api_mode")
     if not isinstance(custom_base, str) or not custom_base.strip():
-        return None, None
+        return None, None, None
 
     custom_base = custom_base.strip().rstrip("/")
     if "openrouter.ai" in custom_base.lower():
         # requested='custom' falls back to OpenRouter when no custom endpoint is
         # configured. Treat that as "no custom endpoint" for auxiliary routing.
-        return None, None
+        return None, None, None
 
     # Local servers (Ollama, llama.cpp, vLLM, LM Studio) don't require auth.
     # Use a placeholder key — the OpenAI SDK requires a non-empty string but
@@ -873,20 +908,33 @@ def _resolve_custom_runtime() -> Tuple[Optional[str], Optional[str]]:
     if not isinstance(custom_key, str) or not custom_key.strip():
         custom_key = "no-key-required"
 
-    return custom_base, custom_key.strip()
+    if not isinstance(custom_mode, str) or not custom_mode.strip():
+        custom_mode = None
+
+    return custom_base, custom_key.strip(), custom_mode
 
 
 def _current_custom_base_url() -> str:
-    custom_base, _ = _resolve_custom_runtime()
+    custom_base, _, _ = _resolve_custom_runtime()
     return custom_base or ""
 
 
 def _try_custom_endpoint() -> Tuple[Optional[OpenAI], Optional[str]]:
-    custom_base, custom_key = _resolve_custom_runtime()
+    runtime = _resolve_custom_runtime()
+    if len(runtime) == 2:
+        custom_base, custom_key = runtime
+        custom_mode = None
+    else:
+        custom_base, custom_key, custom_mode = runtime
     if not custom_base or not custom_key:
         return None, None
+    if custom_base.lower().startswith(_CODEX_AUX_BASE_URL.lower()):
+        return None, None
     model = _read_main_model() or "gpt-4o-mini"
-    logger.debug("Auxiliary client: custom endpoint (%s)", model)
+    logger.debug("Auxiliary client: custom endpoint (%s, api_mode=%s)", model, custom_mode or "chat_completions")
+    if custom_mode == "codex_responses":
+        real_client = OpenAI(api_key=custom_key, base_url=custom_base)
+        return CodexAuxiliaryClient(real_client, model), model
     return OpenAI(api_key=custom_key, base_url=custom_base), model
 
 
@@ -894,9 +942,13 @@ def _try_codex() -> Tuple[Optional[Any], Optional[str]]:
     pool_present, entry = _select_pool_entry("openai-codex")
     if pool_present:
         codex_token = _pool_runtime_api_key(entry)
-        if not codex_token:
-            return None, None
-        base_url = _pool_runtime_base_url(entry, _CODEX_AUX_BASE_URL) or _CODEX_AUX_BASE_URL
+        if codex_token:
+            base_url = _pool_runtime_base_url(entry, _CODEX_AUX_BASE_URL) or _CODEX_AUX_BASE_URL
+        else:
+            codex_token = _read_codex_access_token()
+            if not codex_token:
+                return None, None
+            base_url = _CODEX_AUX_BASE_URL
     else:
         codex_token = _read_codex_access_token()
         if not codex_token:
@@ -955,40 +1007,6 @@ def _try_anthropic() -> Tuple[Optional[Any], Optional[str]]:
     return AnthropicAuxiliaryClient(real_client, model, token, base_url, is_oauth=is_oauth), model
 
 
-def _resolve_forced_provider(forced: str) -> Tuple[Optional[OpenAI], Optional[str]]:
-    """Resolve a specific forced provider.  Returns (None, None) if creds missing."""
-    if forced == "openrouter":
-        client, model = _try_openrouter()
-        if client is None:
-            logger.warning("auxiliary.provider=openrouter but OPENROUTER_API_KEY not set")
-        return client, model
-
-    if forced == "nous":
-        client, model = _try_nous()
-        if client is None:
-            logger.warning("auxiliary.provider=nous but Nous Portal not configured (run: hermes auth)")
-        return client, model
-
-    if forced == "codex":
-        client, model = _try_codex()
-        if client is None:
-            logger.warning("auxiliary.provider=codex but no Codex OAuth token found (run: hermes model)")
-        return client, model
-
-    if forced == "main":
-        # "main" = skip OpenRouter/Nous, use the main chat model's credentials.
-        for try_fn in (_try_custom_endpoint, _try_codex, _resolve_api_key_provider):
-            client, model = try_fn()
-            if client is not None:
-                return client, model
-        logger.warning("auxiliary.provider=main but no main endpoint credentials found")
-        return None, None
-
-    # Unknown provider name — fall through to auto
-    logger.warning("Unknown auxiliary.provider=%r, falling back to auto", forced)
-    return None, None
-
-
 _AUTO_PROVIDER_LABELS = {
     "_try_openrouter": "openrouter",
     "_try_nous": "nous",
@@ -1035,14 +1053,41 @@ def _is_payment_error(exc: Exception) -> bool:
     return False
 
 
+def _is_connection_error(exc: Exception) -> bool:
+    """Detect connection/network errors that warrant provider fallback.
+
+    Returns True for errors indicating the provider endpoint is unreachable
+    (DNS failure, connection refused, TLS errors, timeouts).  These are
+    distinct from API errors (4xx/5xx) which indicate the provider IS
+    reachable but returned an error.
+    """
+    from openai import APIConnectionError, APITimeoutError
+
+    if isinstance(exc, (APIConnectionError, APITimeoutError)):
+        return True
+    # urllib3 / httpx / httpcore connection errors
+    err_type = type(exc).__name__
+    if any(kw in err_type for kw in ("Connection", "Timeout", "DNS", "SSL")):
+        return True
+    err_lower = str(exc).lower()
+    if any(kw in err_lower for kw in (
+        "connection refused", "name or service not known",
+        "no route to host", "network is unreachable",
+        "timed out", "connection reset",
+    )):
+        return True
+    return False
+
+
 def _try_payment_fallback(
     failed_provider: str,
     task: str = None,
+    reason: str = "payment error",
 ) -> Tuple[Optional[Any], Optional[str], str]:
-    """Try alternative providers after a payment/credit error.
+    """Try alternative providers after a payment/credit or connection error.
 
     Iterates the standard auto-detection chain, skipping the provider that
-    returned a payment error.
+    failed.
 
     Returns:
         (client, model, provider_label) or (None, None, "") if no fallback.
@@ -1068,15 +1113,15 @@ def _try_payment_fallback(
         client, model = try_fn()
         if client is not None:
             logger.info(
-                "Auxiliary %s: payment error on %s — falling back to %s (%s)",
-                task or "call", failed_provider, label, model or "default",
+                "Auxiliary %s: %s on %s — falling back to %s (%s)",
+                task or "call", reason, failed_provider, label, model or "default",
             )
             return client, model, label
         tried.append(label)
 
     logger.warning(
-        "Auxiliary %s: payment error on %s and no fallback available (tried: %s)",
-        task or "call", failed_provider, ", ".join(tried),
+        "Auxiliary %s: %s on %s and no fallback available (tried: %s)",
+        task or "call", reason, failed_provider, ", ".join(tried),
     )
     return None, None, ""
 
@@ -1091,15 +1136,34 @@ def _resolve_auto() -> Tuple[Optional[OpenAI], Optional[str]]:
          provider they already have credentials for — no OpenRouter key needed.
       2. OpenRouter → Nous → custom → Codex → API-key providers (original chain).
     """
-    global auxiliary_is_nous
+    global auxiliary_is_nous, _stale_base_url_warned
     auxiliary_is_nous = False  # Reset — _try_nous() will set True if it wins
 
+    # ── Warn once if OPENAI_BASE_URL is set but config.yaml uses a named
+    #    provider (not 'custom').  This catches the common "env poisoning"
+    #    scenario where a user switches providers via `hermes model` but the
+    #    old OPENAI_BASE_URL lingers in ~/.hermes/.env. ──
+    if not _stale_base_url_warned:
+        _env_base = os.getenv("OPENAI_BASE_URL", "").strip()
+        _cfg_provider = _read_main_provider()
+        if (_env_base and _cfg_provider
+                and _cfg_provider != "custom"
+                and not _cfg_provider.startswith("custom:")):
+            logger.warning(
+                "OPENAI_BASE_URL is set (%s) but model.provider is '%s'. "
+                "Auxiliary clients may route to the wrong endpoint. "
+                "Run: hermes model to reconfigure, or remove "
+                "OPENAI_BASE_URL from ~/.hermes/.env",
+                _env_base, _cfg_provider,
+            )
+            _stale_base_url_warned = True
+
     # ── Step 1: non-aggregator main provider → use main model directly ──
     main_provider = _read_main_provider()
     main_model = _read_main_model()
     if (main_provider and main_model
             and main_provider not in _AGGREGATOR_PROVIDERS
-            and main_provider not in ("auto", "custom", "")):
+            and main_provider not in ("auto", "")):
         client, resolved = resolve_provider_client(main_provider, main_model)
         if client is not None:
             logger.info("Auxiliary auto-detect: using main provider %s (%s)",
@@ -1157,10 +1221,22 @@ def _to_async_client(sync_client, model: str):
 
         async_kwargs["default_headers"] = copilot_default_headers()
     elif "api.kimi.com" in base_lower:
-        async_kwargs["default_headers"] = {"User-Agent": "KimiCLI/1.0"}
+        async_kwargs["default_headers"] = {"User-Agent": "KimiCLI/1.30.0"}
     return AsyncOpenAI(**async_kwargs), model
 
 
+def _normalize_resolved_model(model_name: Optional[str], provider: str) -> Optional[str]:
+    """Normalize a resolved model for the provider that will receive it."""
+    if not model_name:
+        return model_name
+    try:
+        from hermes_cli.model_normalize import normalize_model_for_provider
+
+        return normalize_model_for_provider(model_name, provider)
+    except Exception:
+        return model_name
+
+
 def resolve_provider_client(
     provider: str,
     model: str = None,
@@ -1168,6 +1244,7 @@ def resolve_provider_client(
     raw_codex: bool = False,
     explicit_base_url: str = None,
     explicit_api_key: str = None,
+    api_mode: str = None,
 ) -> 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.
@@ -1191,6 +1268,10 @@ def resolve_provider_client(
             the main agent loop).
         explicit_base_url: Optional direct OpenAI-compatible endpoint.
         explicit_api_key: Optional API key paired with explicit_base_url.
+        api_mode: API mode override.  One of "chat_completions",
+            "codex_responses", or None (auto-detect).  When set to
+            "codex_responses", the client is wrapped in
+            CodexAuxiliaryClient to route through the Responses API.
 
     Returns:
         (client, resolved_model) or (None, None) if auth is unavailable.
@@ -1198,6 +1279,40 @@ def resolve_provider_client(
     # Normalise aliases
     provider = _normalize_aux_provider(provider)
 
+    def _needs_codex_wrap(client_obj, base_url_str: str, model_str: str) -> bool:
+        """Decide if a plain OpenAI client should be wrapped for Responses API.
+
+        Returns True when api_mode is explicitly "codex_responses", or when
+        auto-detection (api.openai.com + codex-family model) suggests it.
+        Already-wrapped clients (CodexAuxiliaryClient) are skipped.
+        """
+        if isinstance(client_obj, CodexAuxiliaryClient):
+            return False
+        if raw_codex:
+            return False
+        if api_mode == "codex_responses":
+            return True
+        # Auto-detect: api.openai.com + codex model name pattern
+        if api_mode and api_mode != "codex_responses":
+            return False  # explicit non-codex mode
+        normalized_base = (base_url_str or "").strip().lower()
+        if "api.openai.com" in normalized_base and "openrouter" not in normalized_base:
+            model_lower = (model_str or "").lower()
+            if "codex" in model_lower:
+                return True
+        return False
+
+    def _wrap_if_needed(client_obj, final_model_str: str, base_url_str: str = ""):
+        """Wrap a plain OpenAI client in CodexAuxiliaryClient if Responses API is needed."""
+        if _needs_codex_wrap(client_obj, base_url_str, final_model_str):
+            logger.debug(
+                "resolve_provider_client: wrapping client in CodexAuxiliaryClient "
+                "(api_mode=%s, model=%s, base_url=%s)",
+                api_mode or "auto-detected", final_model_str,
+                base_url_str[:60] if base_url_str else "")
+            return CodexAuxiliaryClient(client_obj, final_model_str)
+        return client_obj
+
     # ── Auto: try all providers in priority order ────────────────────
     if provider == "auto":
         client, resolved = _resolve_auto()
@@ -1223,7 +1338,7 @@ def resolve_provider_client(
             logger.warning("resolve_provider_client: openrouter requested "
                            "but OPENROUTER_API_KEY not set")
             return None, None
-        final_model = model or default
+        final_model = _normalize_resolved_model(model or default, provider)
         return (_to_async_client(client, final_model) if async_mode
                 else (client, final_model))
 
@@ -1234,7 +1349,7 @@ def resolve_provider_client(
             logger.warning("resolve_provider_client: nous requested "
                            "but Nous Portal not configured (run: hermes auth)")
             return None, None
-        final_model = model or default
+        final_model = _normalize_resolved_model(model or default, provider)
         return (_to_async_client(client, final_model) if async_mode
                 else (client, final_model))
 
@@ -1248,7 +1363,7 @@ def resolve_provider_client(
                 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
+            final_model = _normalize_resolved_model(model or _CODEX_AUX_MODEL, provider)
             raw_client = OpenAI(api_key=codex_token, base_url=_CODEX_AUX_BASE_URL)
             return (raw_client, final_model)
         # Standard path: wrap in CodexAuxiliaryClient adapter
@@ -1257,7 +1372,7 @@ def resolve_provider_client(
             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
+        final_model = _normalize_resolved_model(model or default, provider)
         return (_to_async_client(client, final_model) if async_mode
                 else (client, final_model))
 
@@ -1276,8 +1391,18 @@ def resolve_provider_client(
                     "but base_url is empty"
                 )
                 return None, None
-            final_model = model or _read_main_model() or "gpt-4o-mini"
-            client = OpenAI(api_key=custom_key, base_url=custom_base)
+            final_model = _normalize_resolved_model(
+                model or _read_main_model() or "gpt-4o-mini",
+                provider,
+            )
+            extra = {}
+            if "api.kimi.com" in custom_base.lower():
+                extra["default_headers"] = {"User-Agent": "KimiCLI/1.30.0"}
+            elif "api.githubcopilot.com" in custom_base.lower():
+                from hermes_cli.models import copilot_default_headers
+                extra["default_headers"] = copilot_default_headers()
+            client = OpenAI(api_key=custom_key, base_url=custom_base, **extra)
+            client = _wrap_if_needed(client, final_model, custom_base)
             return (_to_async_client(client, final_model) if async_mode
                     else (client, final_model))
         # Try custom first, then codex, then API-key providers
@@ -1285,7 +1410,9 @@ def resolve_provider_client(
                        _resolve_api_key_provider):
             client, default = try_fn()
             if client is not None:
-                final_model = model or default
+                final_model = _normalize_resolved_model(model or default, provider)
+                _cbase = str(getattr(client, "base_url", "") or "")
+                client = _wrap_if_needed(client, final_model, _cbase)
                 return (_to_async_client(client, final_model) if async_mode
                         else (client, final_model))
         logger.warning("resolve_provider_client: custom/main requested "
@@ -1300,8 +1427,12 @@ def resolve_provider_client(
             custom_base = custom_entry.get("base_url", "").strip()
             custom_key = custom_entry.get("api_key", "").strip() or "no-key-required"
             if custom_base:
-                final_model = model or _read_main_model() or "gpt-4o-mini"
+                final_model = _normalize_resolved_model(
+                    model or _read_main_model() or "gpt-4o-mini",
+                    provider,
+                )
                 client = OpenAI(api_key=custom_key, base_url=custom_base)
+                client = _wrap_if_needed(client, final_model, custom_base)
                 logger.debug(
                     "resolve_provider_client: named custom provider %r (%s)",
                     provider, final_model)
@@ -1332,7 +1463,7 @@ def resolve_provider_client(
             if client is None:
                 logger.warning("resolve_provider_client: anthropic requested but no Anthropic credentials found")
                 return None, None
-            final_model = model or default_model
+            final_model = _normalize_resolved_model(model or default_model, provider)
             return (_to_async_client(client, final_model) if async_mode else (client, final_model))
 
         creds = resolve_api_key_provider_credentials(provider)
@@ -1351,12 +1482,12 @@ def resolve_provider_client(
         )
 
         default_model = _API_KEY_PROVIDER_AUX_MODELS.get(provider, "")
-        final_model = model or default_model
+        final_model = _normalize_resolved_model(model or default_model, provider)
 
         # Provider-specific headers
         headers = {}
         if "api.kimi.com" in base_url.lower():
-            headers["User-Agent"] = "KimiCLI/1.0"
+            headers["User-Agent"] = "KimiCLI/1.30.0"
         elif "api.githubcopilot.com" in base_url.lower():
             from hermes_cli.models import copilot_default_headers
 
@@ -1364,6 +1495,28 @@ def resolve_provider_client(
 
         client = OpenAI(api_key=api_key, base_url=base_url,
                         **({"default_headers": headers} if headers else {}))
+
+        # Copilot GPT-5+ models (except gpt-5-mini) require the Responses
+        # API — they are not accessible via /chat/completions.  Wrap the
+        # plain client in CodexAuxiliaryClient so call_llm() transparently
+        # routes through responses.stream().
+        if provider == "copilot" and final_model and not raw_codex:
+            try:
+                from hermes_cli.models import _should_use_copilot_responses_api
+                if _should_use_copilot_responses_api(final_model):
+                    logger.debug(
+                        "resolve_provider_client: copilot model %s needs "
+                        "Responses API — wrapping with CodexAuxiliaryClient",
+                        final_model)
+                    client = CodexAuxiliaryClient(client, final_model)
+            except ImportError:
+                pass
+
+        # Honor api_mode for any API-key provider (e.g. direct OpenAI with
+        # codex-family models).  The copilot-specific wrapping above handles
+        # copilot; this covers the general case (#6800).
+        client = _wrap_if_needed(client, final_model, base_url)
+
         logger.debug("resolve_provider_client: %s (%s)", provider, final_model)
         return (_to_async_client(client, final_model) if async_mode
                 else (client, final_model))
@@ -1396,12 +1549,13 @@ def get_text_auxiliary_client(task: str = "") -> Tuple[Optional[OpenAI], Optiona
     Callers may override the returned model with a per-task env var
     (e.g. CONTEXT_COMPRESSION_MODEL, AUXILIARY_WEB_EXTRACT_MODEL).
     """
-    provider, model, base_url, api_key = _resolve_task_provider_model(task or None)
+    provider, model, base_url, api_key, api_mode = _resolve_task_provider_model(task or None)
     return resolve_provider_client(
         provider,
         model=model,
         explicit_base_url=base_url,
         explicit_api_key=api_key,
+        api_mode=api_mode,
     )
 
 
@@ -1412,13 +1566,14 @@ def get_async_text_auxiliary_client(task: str = ""):
     (AsyncCodexAuxiliaryClient, model) which wraps the Responses API.
     Returns (None, None) when no provider is available.
     """
-    provider, model, base_url, api_key = _resolve_task_provider_model(task or None)
+    provider, model, base_url, api_key, api_mode = _resolve_task_provider_model(task or None)
     return resolve_provider_client(
         provider,
         model=model,
         async_mode=True,
         explicit_base_url=base_url,
         explicit_api_key=api_key,
+        api_mode=api_mode,
     )
 
 
@@ -1451,22 +1606,6 @@ def _strict_vision_backend_available(provider: str) -> bool:
     return _resolve_strict_vision_backend(provider)[0] is not None
 
 
-def _preferred_main_vision_provider() -> Optional[str]:
-    """Return the selected main provider when it is also a supported vision backend."""
-    try:
-        from hermes_cli.config import load_config
-
-        config = load_config()
-        model_cfg = config.get("model", {})
-        if isinstance(model_cfg, dict):
-            provider = _normalize_vision_provider(model_cfg.get("provider", ""))
-            if provider in _VISION_AUTO_PROVIDER_ORDER:
-                return provider
-    except Exception:
-        pass
-    return None
-
-
 def get_available_vision_backends() -> List[str]:
     """Return the currently available vision backends in auto-selection order.
 
@@ -1507,7 +1646,7 @@ def resolve_vision_provider_client(
     backends, so users can intentionally force experimental providers. Auto mode
     stays conservative and only tries vision backends known to work today.
     """
-    requested, resolved_model, resolved_base_url, resolved_api_key = _resolve_task_provider_model(
+    requested, resolved_model, resolved_base_url, resolved_api_key, resolved_api_mode = _resolve_task_provider_model(
         "vision", provider, model, base_url, api_key
     )
     requested = _normalize_vision_provider(requested)
@@ -1580,18 +1719,6 @@ def resolve_vision_provider_client(
     return requested, client, final_model
 
 
-def get_vision_auxiliary_client() -> Tuple[Optional[OpenAI], Optional[str]]:
-    """Return (client, default_model_slug) for vision/multimodal auxiliary tasks."""
-    _, client, final_model = resolve_vision_provider_client(async_mode=False)
-    return client, final_model
-
-
-def get_async_vision_auxiliary_client():
-    """Return (async_client, model_slug) for async vision consumers."""
-    _, client, final_model = resolve_vision_provider_client(async_mode=True)
-    return client, final_model
-
-
 def get_auxiliary_extra_body() -> dict:
     """Return extra_body kwargs for auxiliary API calls.
     
@@ -1735,12 +1862,30 @@ def cleanup_stale_async_clients() -> None:
             del _client_cache[key]
 
 
+def _is_openrouter_client(client: Any) -> bool:
+    for obj in (client, getattr(client, "_client", None), getattr(client, "client", None)):
+        if obj and "openrouter" in str(getattr(obj, "base_url", "") or "").lower():
+            return True
+    return False
+
+
+def _compat_model(client: Any, model: Optional[str], cached_default: Optional[str]) -> Optional[str]:
+    """Drop OpenRouter-format model slugs (with '/') for non-OpenRouter clients.
+
+    Mirrors the guard in resolve_provider_client() which is skipped on cache hits.
+    """
+    if model and "/" in model and not _is_openrouter_client(client):
+        return cached_default
+    return model or cached_default
+
+
 def _get_cached_client(
     provider: str,
     model: str = None,
     async_mode: bool = False,
     base_url: str = None,
     api_key: str = None,
+    api_mode: str = None,
 ) -> Tuple[Optional[Any], Optional[str]]:
     """Get or create a cached client for the given provider.
 
@@ -1764,7 +1909,7 @@ def _get_cached_client(
             loop_id = id(current_loop)
         except RuntimeError:
             pass
-    cache_key = (provider, async_mode, base_url or "", api_key or "", loop_id)
+    cache_key = (provider, async_mode, base_url or "", api_key or "", api_mode or "", loop_id)
     with _client_cache_lock:
         if cache_key in _client_cache:
             cached_client, cached_default, cached_loop = _client_cache[cache_key]
@@ -1776,9 +1921,11 @@ def _get_cached_client(
                     _force_close_async_httpx(cached_client)
                     del _client_cache[cache_key]
                 else:
-                    return cached_client, model or cached_default
+                    effective = _compat_model(cached_client, model, cached_default)
+                    return cached_client, effective
             else:
-                return cached_client, model or cached_default
+                effective = _compat_model(cached_client, model, cached_default)
+                return cached_client, effective
     # Build outside the lock
     client, default_model = resolve_provider_client(
         provider,
@@ -1786,6 +1933,7 @@ def _get_cached_client(
         async_mode,
         explicit_base_url=base_url,
         explicit_api_key=api_key,
+        api_mode=api_mode,
     )
     if client is not None:
         # For async clients, remember which loop they were created on so we
@@ -1805,7 +1953,7 @@ def _resolve_task_provider_model(
     model: str = None,
     base_url: str = None,
     api_key: str = None,
-) -> Tuple[str, Optional[str], Optional[str], Optional[str]]:
+) -> Tuple[str, Optional[str], Optional[str], Optional[str], Optional[str]]:
     """Determine provider + model for a call.
 
     Priority:
@@ -1814,15 +1962,17 @@ def _resolve_task_provider_model(
       3. Config file (auxiliary.{task}.* or compression.*)
       4. "auto" (full auto-detection chain)
 
-    Returns (provider, model, base_url, api_key) where model may be None
-    (use provider default). When base_url is set, provider is forced to
-    "custom" and the task uses that direct endpoint.
+    Returns (provider, model, base_url, api_key, api_mode) where model may
+    be None (use provider default). When base_url is set, provider is forced
+    to "custom" and the task uses that direct endpoint. api_mode is one of
+    "chat_completions", "codex_responses", or None (auto-detect).
     """
     config = {}
     cfg_provider = None
     cfg_model = None
     cfg_base_url = None
     cfg_api_key = None
+    cfg_api_mode = None
 
     if task:
         try:
@@ -1839,6 +1989,7 @@ def _resolve_task_provider_model(
         cfg_model = str(task_config.get("model", "")).strip() or None
         cfg_base_url = str(task_config.get("base_url", "")).strip() or None
         cfg_api_key = str(task_config.get("api_key", "")).strip() or None
+        cfg_api_mode = str(task_config.get("api_mode", "")).strip() or None
 
         # Backwards compat: compression section has its own keys.
         # The auxiliary.compression defaults to provider="auto", so treat
@@ -1852,30 +2003,32 @@ def _resolve_task_provider_model(
                 cfg_base_url = cfg_base_url or _sbu.strip() or None
 
     env_model = _get_auxiliary_env_override(task, "MODEL") if task else None
+    env_api_mode = _get_auxiliary_env_override(task, "API_MODE") if task else None
     resolved_model = model or env_model or cfg_model
+    resolved_api_mode = env_api_mode or cfg_api_mode
 
     if base_url:
-        return "custom", resolved_model, base_url, api_key
+        return "custom", resolved_model, base_url, api_key, resolved_api_mode
     if provider:
-        return provider, resolved_model, base_url, api_key
+        return provider, resolved_model, base_url, api_key, resolved_api_mode
 
     if task:
         env_base_url = _get_auxiliary_env_override(task, "BASE_URL")
         env_api_key = _get_auxiliary_env_override(task, "API_KEY")
         if env_base_url:
-            return "custom", resolved_model, env_base_url, env_api_key or cfg_api_key
+            return "custom", resolved_model, env_base_url, env_api_key or cfg_api_key, resolved_api_mode
 
         env_provider = _get_auxiliary_provider(task)
         if env_provider != "auto":
-            return env_provider, resolved_model, None, None
+            return env_provider, resolved_model, None, None, resolved_api_mode
 
         if cfg_base_url:
-            return "custom", resolved_model, cfg_base_url, cfg_api_key
+            return "custom", resolved_model, cfg_base_url, cfg_api_key, resolved_api_mode
         if cfg_provider and cfg_provider != "auto":
-            return cfg_provider, resolved_model, None, None
-        return "auto", resolved_model, None, None
+            return cfg_provider, resolved_model, None, None, resolved_api_mode
+        return "auto", resolved_model, None, None, resolved_api_mode
 
-    return "auto", resolved_model, None, None
+    return "auto", resolved_model, None, None, resolved_api_mode
 
 
 _DEFAULT_AUX_TIMEOUT = 30.0
@@ -1947,6 +2100,37 @@ def _build_call_kwargs(
     return kwargs
 
 
+def _validate_llm_response(response: Any, task: str = None) -> Any:
+    """Validate that an LLM response has the expected .choices[0].message shape.
+
+    Fails fast with a clear error instead of letting malformed payloads
+    propagate to downstream consumers where they crash with misleading
+    AttributeError (e.g. "'str' object has no attribute 'choices'").
+
+    See #7264.
+    """
+    if response is None:
+        raise RuntimeError(
+            f"Auxiliary {task or 'call'}: LLM returned None response"
+        )
+    # Allow SimpleNamespace responses from adapters (CodexAuxiliaryClient,
+    # AnthropicAuxiliaryClient) — they have .choices[0].message.
+    try:
+        choices = response.choices
+        if not choices or not hasattr(choices[0], "message"):
+            raise AttributeError("missing choices[0].message")
+    except (AttributeError, TypeError, IndexError) as exc:
+        response_type = type(response).__name__
+        response_preview = str(response)[:120]
+        raise RuntimeError(
+            f"Auxiliary {task or 'call'}: LLM returned invalid response "
+            f"(type={response_type}): {response_preview!r}. "
+            f"Expected object with .choices[0].message — check provider "
+            f"adapter or custom endpoint compatibility."
+        ) from exc
+    return response
+
+
 def call_llm(
     task: str = None,
     *,
@@ -1985,7 +2169,7 @@ def call_llm(
     Raises:
         RuntimeError: If no provider is configured.
     """
-    resolved_provider, resolved_model, resolved_base_url, resolved_api_key = _resolve_task_provider_model(
+    resolved_provider, resolved_model, resolved_base_url, resolved_api_key, resolved_api_mode = _resolve_task_provider_model(
         task, provider, model, base_url, api_key)
 
     if task == "vision":
@@ -2018,6 +2202,7 @@ def call_llm(
             resolved_model,
             base_url=resolved_base_url,
             api_key=resolved_api_key,
+            api_mode=resolved_api_mode,
         )
         if client is None:
             # When the user explicitly chose a non-OpenRouter provider but no
@@ -2061,18 +2246,20 @@ def call_llm(
 
     # Handle max_tokens vs max_completion_tokens retry, then payment fallback.
     try:
-        return client.chat.completions.create(**kwargs)
+        return _validate_llm_response(
+            client.chat.completions.create(**kwargs), task)
     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
             try:
-                return client.chat.completions.create(**kwargs)
+                return _validate_llm_response(
+                    client.chat.completions.create(**kwargs), task)
             except Exception as retry_err:
-                # If the max_tokens retry also hits a payment error,
-                # fall through to the payment fallback below.
-                if not _is_payment_error(retry_err):
+                # If the max_tokens retry also hits a payment or connection
+                # error, fall through to the fallback chain below.
+                if not (_is_payment_error(retry_err) or _is_connection_error(retry_err)):
                     raise
                 first_err = retry_err
 
@@ -2081,16 +2268,32 @@ def call_llm(
         # try alternative providers instead of giving up.  This handles the
         # common case where a user runs out of OpenRouter credits but has
         # Codex OAuth or another provider available.
-        if _is_payment_error(first_err):
+        #
+        # ── Connection error fallback ────────────────────────────────
+        # When a provider endpoint is unreachable (DNS failure, connection
+        # refused, timeout), try alternative providers.  This handles stale
+        # Codex/OAuth tokens that authenticate but whose endpoint is down,
+        # and providers the user never configured that got picked up by
+        # the auto-detection chain.
+        should_fallback = _is_payment_error(first_err) or _is_connection_error(first_err)
+        # Only try alternative providers when the user didn't explicitly
+        # configure this task's provider.  Explicit provider = hard constraint;
+        # auto (the default) = best-effort fallback chain.  (#7559)
+        is_auto = resolved_provider in ("auto", "", None)
+        if should_fallback and is_auto:
+            reason = "payment error" if _is_payment_error(first_err) else "connection error"
+            logger.info("Auxiliary %s: %s on %s (%s), trying fallback",
+                        task or "call", reason, resolved_provider, first_err)
             fb_client, fb_model, fb_label = _try_payment_fallback(
-                resolved_provider, task)
+                resolved_provider, task, reason=reason)
             if fb_client is not None:
                 fb_kwargs = _build_call_kwargs(
                     fb_label, fb_model, messages,
                     temperature=temperature, max_tokens=max_tokens,
                     tools=tools, timeout=effective_timeout,
                     extra_body=extra_body)
-                return fb_client.chat.completions.create(**fb_kwargs)
+                return _validate_llm_response(
+                    fb_client.chat.completions.create(**fb_kwargs), task)
         raise
 
 
@@ -2168,7 +2371,7 @@ async def async_call_llm(
 
     Same as call_llm() but async. See call_llm() for full documentation.
     """
-    resolved_provider, resolved_model, resolved_base_url, resolved_api_key = _resolve_task_provider_model(
+    resolved_provider, resolved_model, resolved_base_url, resolved_api_key, resolved_api_mode = _resolve_task_provider_model(
         task, provider, model, base_url, api_key)
 
     if task == "vision":
@@ -2202,6 +2405,7 @@ async def async_call_llm(
             async_mode=True,
             base_url=resolved_base_url,
             api_key=resolved_api_key,
+            api_mode=resolved_api_mode,
         )
         if client is None:
             _explicit = (resolved_provider or "").strip().lower()
@@ -2212,11 +2416,9 @@ async def async_call_llm(
                     f"variable, or switch to a different provider with `hermes model`."
                 )
             if not resolved_base_url:
-                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)
+                logger.info("Auxiliary %s: provider %s unavailable, trying auto-detection chain",
+                            task or "call", resolved_provider)
+                client, final_model = _get_cached_client("auto", async_mode=True)
         if client is None:
             raise RuntimeError(
                 f"No LLM provider configured for task={task} provider={resolved_provider}. "
@@ -2231,11 +2433,42 @@ async def async_call_llm(
         base_url=resolved_base_url)
 
     try:
-        return await client.chat.completions.create(**kwargs)
+        return _validate_llm_response(
+            await client.chat.completions.create(**kwargs), task)
     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)
+            try:
+                return _validate_llm_response(
+                    await client.chat.completions.create(**kwargs), task)
+            except Exception as retry_err:
+                # If the max_tokens retry also hits a payment or connection
+                # error, fall through to the fallback chain below.
+                if not (_is_payment_error(retry_err) or _is_connection_error(retry_err)):
+                    raise
+                first_err = retry_err
+
+        # ── Payment / connection fallback (mirrors sync call_llm) ─────
+        should_fallback = _is_payment_error(first_err) or _is_connection_error(first_err)
+        is_auto = resolved_provider in ("auto", "", None)
+        if should_fallback and is_auto:
+            reason = "payment error" if _is_payment_error(first_err) else "connection error"
+            logger.info("Auxiliary %s (async): %s on %s (%s), trying fallback",
+                        task or "call", reason, resolved_provider, first_err)
+            fb_client, fb_model, fb_label = _try_payment_fallback(
+                resolved_provider, task, reason=reason)
+            if fb_client is not None:
+                fb_kwargs = _build_call_kwargs(
+                    fb_label, fb_model, messages,
+                    temperature=temperature, max_tokens=max_tokens,
+                    tools=tools, timeout=effective_timeout,
+                    extra_body=extra_body)
+                # Convert sync fallback client to async
+                async_fb, async_fb_model = _to_async_client(fb_client, fb_model or "")
+                if async_fb_model and async_fb_model != fb_kwargs.get("model"):
+                    fb_kwargs["model"] = async_fb_model
+                return _validate_llm_response(
+                    await async_fb.chat.completions.create(**fb_kwargs), task)
         raise

agent/builtin_memory_provider.py

@@ -1,114 +0,0 @@
-"""BuiltinMemoryProvider — wraps MEMORY.md / USER.md as a MemoryProvider.
-
-Always registered as the first provider. Cannot be disabled or removed.
-This is the existing Hermes memory system exposed through the provider
-interface for compatibility with the MemoryManager.
-
-The actual storage logic lives in tools/memory_tool.py (MemoryStore).
-This provider is a thin adapter that delegates to MemoryStore and
-exposes the memory tool schema.
-"""
-
-from __future__ import annotations
-
-import json
-import logging
-from typing import Any, Dict, List
-
-from agent.memory_provider import MemoryProvider
-from tools.registry import tool_error
-
-logger = logging.getLogger(__name__)
-
-
-class BuiltinMemoryProvider(MemoryProvider):
-    """Built-in file-backed memory (MEMORY.md + USER.md).
-
-    Always active, never disabled by other providers. The `memory` tool
-    is handled by run_agent.py's agent-level tool interception (not through
-    the normal registry), so get_tool_schemas() returns an empty list —
-    the memory tool is already wired separately.
-    """
-
-    def __init__(
-        self,
-        memory_store=None,
-        memory_enabled: bool = False,
-        user_profile_enabled: bool = False,
-    ):
-        self._store = memory_store
-        self._memory_enabled = memory_enabled
-        self._user_profile_enabled = user_profile_enabled
-
-    @property
-    def name(self) -> str:
-        return "builtin"
-
-    def is_available(self) -> bool:
-        """Built-in memory is always available."""
-        return True
-
-    def initialize(self, session_id: str, **kwargs) -> None:
-        """Load memory from disk if not already loaded."""
-        if self._store is not None:
-            self._store.load_from_disk()
-
-    def system_prompt_block(self) -> str:
-        """Return MEMORY.md and USER.md content for the system prompt.
-
-        Uses the frozen snapshot captured at load time. This ensures the
-        system prompt stays stable throughout a session (preserving the
-        prompt cache), even though the live entries may change via tool calls.
-        """
-        if not self._store:
-            return ""
-
-        parts = []
-        if self._memory_enabled:
-            mem_block = self._store.format_for_system_prompt("memory")
-            if mem_block:
-                parts.append(mem_block)
-        if self._user_profile_enabled:
-            user_block = self._store.format_for_system_prompt("user")
-            if user_block:
-                parts.append(user_block)
-
-        return "\n\n".join(parts)
-
-    def prefetch(self, query: str, *, session_id: str = "") -> str:
-        """Built-in memory doesn't do query-based recall — it's injected via system_prompt_block."""
-        return ""
-
-    def sync_turn(self, user_content: str, assistant_content: str, *, session_id: str = "") -> None:
-        """Built-in memory doesn't auto-sync turns — writes happen via the memory tool."""
-
-    def get_tool_schemas(self) -> List[Dict[str, Any]]:
-        """Return empty list.
-
-        The `memory` tool is an agent-level intercepted tool, handled
-        specially in run_agent.py before normal tool dispatch. It's not
-        part of the standard tool registry. We don't duplicate it here.
-        """
-        return []
-
-    def handle_tool_call(self, tool_name: str, args: Dict[str, Any], **kwargs) -> str:
-        """Not used — the memory tool is intercepted in run_agent.py."""
-        return tool_error("Built-in memory tool is handled by the agent loop")
-
-    def shutdown(self) -> None:
-        """No cleanup needed — files are saved on every write."""
-
-    # -- Property access for backward compatibility --------------------------
-
-    @property
-    def store(self):
-        """Access the underlying MemoryStore for legacy code paths."""
-        return self._store
-
-    @property
-    def memory_enabled(self) -> bool:
-        return self._memory_enabled
-
-    @property
-    def user_profile_enabled(self) -> bool:
-        return self._user_profile_enabled

agent/context_compressor.py

@@ -18,6 +18,7 @@ import time
 from typing import Any, Dict, List, Optional
 
 from agent.auxiliary_client import call_llm
+from agent.context_engine import ContextEngine
 from agent.model_metadata import (
     get_model_context_length,
     estimate_messages_tokens_rough,
@@ -50,8 +51,8 @@ _CHARS_PER_TOKEN = 4
 _SUMMARY_FAILURE_COOLDOWN_SECONDS = 600
 
 
-class ContextCompressor:
-    """Compresses conversation context when approaching the model's context limit.
+class ContextCompressor(ContextEngine):
+    """Default context engine — compresses conversation context via lossy summarization.
 
     Algorithm:
       1. Prune old tool results (cheap, no LLM call)
@@ -61,6 +62,33 @@ class ContextCompressor:
       5. On subsequent compactions, iteratively update the previous summary
     """
 
+    @property
+    def name(self) -> str:
+        return "compressor"
+
+    def on_session_reset(self) -> None:
+        """Reset all per-session state for /new or /reset."""
+        super().on_session_reset()
+        self._context_probed = False
+        self._context_probe_persistable = False
+        self._previous_summary = None
+
+    def update_model(
+        self,
+        model: str,
+        context_length: int,
+        base_url: str = "",
+        api_key: str = "",
+        provider: str = "",
+    ) -> None:
+        """Update model info after a model switch or fallback activation."""
+        self.model = model
+        self.base_url = base_url
+        self.api_key = api_key
+        self.provider = provider
+        self.context_length = context_length
+        self.threshold_tokens = int(context_length * self.threshold_percent)
+
     def __init__(
         self,
         model: str,
@@ -114,7 +142,6 @@ class ContextCompressor:
 
         self.last_prompt_tokens = 0
         self.last_completion_tokens = 0
-        self.last_total_tokens = 0
 
         self.summary_model = summary_model_override or ""
 
@@ -126,40 +153,27 @@ class ContextCompressor:
         """Update tracked token usage from API response."""
         self.last_prompt_tokens = usage.get("prompt_tokens", 0)
         self.last_completion_tokens = usage.get("completion_tokens", 0)
-        self.last_total_tokens = usage.get("total_tokens", 0)
 
     def should_compress(self, prompt_tokens: int = None) -> bool:
         """Check if context exceeds the compression threshold."""
         tokens = prompt_tokens if prompt_tokens is not None else self.last_prompt_tokens
         return tokens >= self.threshold_tokens
 
-    def should_compress_preflight(self, messages: List[Dict[str, Any]]) -> bool:
-        """Quick pre-flight check using rough estimate (before API call)."""
-        rough_estimate = estimate_messages_tokens_rough(messages)
-        return rough_estimate >= self.threshold_tokens
-
-    def get_status(self) -> Dict[str, Any]:
-        """Get current compression status for display/logging."""
-        return {
-            "last_prompt_tokens": self.last_prompt_tokens,
-            "threshold_tokens": self.threshold_tokens,
-            "context_length": self.context_length,
-            "usage_percent": min(100, (self.last_prompt_tokens / self.context_length * 100)) if self.context_length else 0,
-            "compression_count": self.compression_count,
-        }
-
     # ------------------------------------------------------------------
     # Tool output pruning (cheap pre-pass, no LLM call)
     # ------------------------------------------------------------------
 
     def _prune_old_tool_results(
         self, messages: List[Dict[str, Any]], protect_tail_count: int,
+        protect_tail_tokens: int | None = None,
     ) -> tuple[List[Dict[str, Any]], int]:
         """Replace old tool result contents with a short placeholder.
 
-        Walks backward from the end, protecting the most recent
-        ``protect_tail_count`` messages. Older tool results get their
-        content replaced with a placeholder string.
+        Walks backward from the end, protecting the most recent messages that
+        fall within ``protect_tail_tokens`` (when provided) OR the last
+        ``protect_tail_count`` messages (backward-compatible default).
+        When both are given, the token budget takes priority and the message
+        count acts as a hard minimum floor.
 
         Returns (pruned_messages, pruned_count).
         """
@@ -168,7 +182,29 @@ class ContextCompressor:
 
         result = [m.copy() for m in messages]
         pruned = 0
-        prune_boundary = len(result) - protect_tail_count
+
+        # Determine the prune boundary
+        if protect_tail_tokens is not None and protect_tail_tokens > 0:
+            # Token-budget approach: walk backward accumulating tokens
+            accumulated = 0
+            boundary = len(result)
+            min_protect = min(protect_tail_count, len(result) - 1)
+            for i in range(len(result) - 1, -1, -1):
+                msg = result[i]
+                content_len = len(msg.get("content") or "")
+                msg_tokens = content_len // _CHARS_PER_TOKEN + 10
+                for tc in msg.get("tool_calls") or []:
+                    if isinstance(tc, dict):
+                        args = tc.get("function", {}).get("arguments", "")
+                        msg_tokens += len(args) // _CHARS_PER_TOKEN
+                if accumulated + msg_tokens > protect_tail_tokens and (len(result) - i) >= min_protect:
+                    boundary = i
+                    break
+                accumulated += msg_tokens
+                boundary = i
+            prune_boundary = max(boundary, len(result) - min_protect)
+        else:
+            prune_boundary = len(result) - protect_tail_count
 
         for i in range(prune_boundary):
             msg = result[i]
@@ -199,30 +235,39 @@ class ContextCompressor:
         budget = int(content_tokens * _SUMMARY_RATIO)
         return max(_MIN_SUMMARY_TOKENS, min(budget, self.max_summary_tokens))
 
+    # Truncation limits for the summarizer input.  These bound how much of
+    # each message the summary model sees — the budget is the *summary*
+    # model's context window, not the main model's.
+    _CONTENT_MAX = 6000       # total chars per message body
+    _CONTENT_HEAD = 4000      # chars kept from the start
+    _CONTENT_TAIL = 1500      # chars kept from the end
+    _TOOL_ARGS_MAX = 1500     # tool call argument chars
+    _TOOL_ARGS_HEAD = 1200    # kept from the start of tool args
+
     def _serialize_for_summary(self, turns: List[Dict[str, Any]]) -> str:
         """Serialize conversation turns into labeled text for the summarizer.
 
-        Includes tool call arguments and result content (up to 3000 chars
-        per message) so the summarizer can preserve specific details like
-        file paths, commands, and outputs.
+        Includes tool call arguments and result content (up to
+        ``_CONTENT_MAX`` chars per message) so the summarizer can preserve
+        specific details like file paths, commands, and outputs.
         """
         parts = []
         for msg in turns:
             role = msg.get("role", "unknown")
             content = msg.get("content") or ""
 
-            # Tool results: keep more content than before (3000 chars)
+            # Tool results: keep enough content for the summarizer
             if role == "tool":
                 tool_id = msg.get("tool_call_id", "")
-                if len(content) > 3000:
-                    content = content[:2000] + "\n...[truncated]...\n" + content[-800:]
+                if len(content) > self._CONTENT_MAX:
+                    content = content[:self._CONTENT_HEAD] + "\n...[truncated]...\n" + content[-self._CONTENT_TAIL:]
                 parts.append(f"[TOOL RESULT {tool_id}]: {content}")
                 continue
 
             # Assistant messages: include tool call names AND arguments
             if role == "assistant":
-                if len(content) > 3000:
-                    content = content[:2000] + "\n...[truncated]...\n" + content[-800:]
+                if len(content) > self._CONTENT_MAX:
+                    content = content[:self._CONTENT_HEAD] + "\n...[truncated]...\n" + content[-self._CONTENT_TAIL:]
                 tool_calls = msg.get("tool_calls", [])
                 if tool_calls:
                     tc_parts = []
@@ -232,8 +277,8 @@ class ContextCompressor:
                             name = fn.get("name", "?")
                             args = fn.get("arguments", "")
                             # Truncate long arguments but keep enough for context
-                            if len(args) > 500:
-                                args = args[:400] + "..."
+                            if len(args) > self._TOOL_ARGS_MAX:
+                                args = args[:self._TOOL_ARGS_HEAD] + "..."
                             tc_parts.append(f"  {name}({args})")
                         else:
                             fn = getattr(tc, "function", None)
@@ -244,8 +289,8 @@ class ContextCompressor:
                 continue
 
             # User and other roles
-            if len(content) > 3000:
-                content = content[:2000] + "\n...[truncated]...\n" + content[-800:]
+            if len(content) > self._CONTENT_MAX:
+                content = content[:self._CONTENT_HEAD] + "\n...[truncated]...\n" + content[-self._CONTENT_TAIL:]
             parts.append(f"[{role.upper()}]: {content}")
 
         return "\n\n".join(parts)
@@ -310,6 +355,9 @@ Update the summary using this exact structure. PRESERVE all existing information
 ## Critical Context
 [Any specific values, error messages, configuration details, or data that would be lost without explicit preservation]
 
+## Tools & Patterns
+[Which tools were used, how they were used effectively, and any tool-specific discoveries. Accumulate across compactions.]
+
 Target ~{summary_budget} tokens. Be specific — include file paths, command outputs, error messages, and concrete values rather than vague descriptions.
 
 Write only the summary body. Do not include any preamble or prefix."""
@@ -348,6 +396,9 @@ Use this exact structure:
 ## Critical Context
 [Any specific values, error messages, configuration details, or data that would be lost without explicit preservation]
 
+## Tools & Patterns
+[Which tools were used, how they were used effectively, and any tool-specific discoveries (e.g., preferred flags, working invocations, successful command patterns)]
+
 Target ~{summary_budget} tokens. Be specific — include file paths, command outputs, error messages, and concrete values rather than vague descriptions. The goal is to prevent the next assistant from repeating work or losing important details.
 
 Write only the summary body. Do not include any preamble or prefix."""
@@ -518,13 +569,20 @@ Write only the summary body. Do not include any preamble or prefix."""
         derived from ``summary_target_ratio * context_length``, so it
         scales automatically with the model's context window.
 
-        Never cuts inside a tool_call/result group. Falls back to the old
-        ``protect_last_n`` if the budget would protect fewer messages.
+        Token budget is the primary criterion.  A hard minimum of 3 messages
+        is always protected, but the budget is allowed to exceed by up to
+        1.5x to avoid cutting inside an oversized message (tool output, file
+        read, etc.).  If even the minimum 3 messages exceed 1.5x the budget
+        the cut is placed right after the head so compression still runs.
+
+        Never cuts inside a tool_call/result group.
         """
         if token_budget is None:
             token_budget = self.tail_token_budget
         n = len(messages)
-        min_tail = self.protect_last_n
+        # Hard minimum: always keep at least 3 messages in the tail
+        min_tail = min(3, n - head_end - 1) if n - head_end > 1 else 0
+        soft_ceiling = int(token_budget * 1.5)
         accumulated = 0
         cut_idx = n  # start from beyond the end
 
@@ -537,21 +595,21 @@ Write only the summary body. Do not include any preamble or prefix."""
                 if isinstance(tc, dict):
                     args = tc.get("function", {}).get("arguments", "")
                     msg_tokens += len(args) // _CHARS_PER_TOKEN
-            if accumulated + msg_tokens > token_budget and (n - i) >= min_tail:
+            # Stop once we exceed the soft ceiling (unless we haven't hit min_tail yet)
+            if accumulated + msg_tokens > soft_ceiling and (n - i) >= min_tail:
                 break
             accumulated += msg_tokens
             cut_idx = i
 
-        # Ensure we protect at least protect_last_n messages
+        # Ensure we protect at least min_tail messages
         fallback_cut = n - min_tail
         if cut_idx > fallback_cut:
             cut_idx = fallback_cut
 
         # If the token budget would protect everything (small conversations),
-        # fall back to the fixed protect_last_n approach so compression can
-        # still remove middle turns.
+        # force a cut after the head so compression can still remove middle turns.
         if cut_idx <= head_end:
-            cut_idx = fallback_cut
+            cut_idx = max(fallback_cut, head_end + 1)
 
         # Align to avoid splitting tool groups
         cut_idx = self._align_boundary_backward(messages, cut_idx)
@@ -576,12 +634,13 @@ Write only the summary body. Do not include any preamble or prefix."""
         up so the API never receives mismatched IDs.
         """
         n_messages = len(messages)
-        if n_messages <= self.protect_first_n + self.protect_last_n + 1:
+        # Only need head + 3 tail messages minimum (token budget decides the real tail size)
+        _min_for_compress = self.protect_first_n + 3 + 1
+        if n_messages <= _min_for_compress:
             if not self.quiet_mode:
                 logger.warning(
                     "Cannot compress: only %d messages (need > %d)",
-                    n_messages,
-                    self.protect_first_n + self.protect_last_n + 1,
+                    n_messages, _min_for_compress,
                 )
             return messages
 
@@ -589,7 +648,8 @@ Write only the summary body. Do not include any preamble or prefix."""
 
         # Phase 1: Prune old tool results (cheap, no LLM call)
         messages, pruned_count = self._prune_old_tool_results(
-            messages, protect_tail_count=self.protect_last_n * 3,
+            messages, protect_tail_count=self.protect_last_n,
+            protect_tail_tokens=self.tail_token_budget,
         )
         if pruned_count and not self.quiet_mode:
             logger.info("Pre-compression: pruned %d old tool result(s)", pruned_count)
@@ -642,33 +702,43 @@ Write only the summary body. Do not include any preamble or prefix."""
                 )
             compressed.append(msg)
 
-        _merge_summary_into_tail = False
-        if summary:
-            last_head_role = messages[compress_start - 1].get("role", "user") if compress_start > 0 else "user"
-            first_tail_role = messages[compress_end].get("role", "user") if compress_end < n_messages else "user"
-            # Pick a role that avoids consecutive same-role with both neighbors.
-            # Priority: avoid colliding with head (already committed), then tail.
-            if last_head_role in ("assistant", "tool"):
-                summary_role = "user"
-            else:
-                summary_role = "assistant"
-            # If the chosen role collides with the tail AND flipping wouldn't
-            # collide with the head, flip it.
-            if summary_role == first_tail_role:
-                flipped = "assistant" if summary_role == "user" else "user"
-                if flipped != last_head_role:
-                    summary_role = flipped
-                else:
-                    # Both roles would create consecutive same-role messages
-                    # (e.g. head=assistant, tail=user — neither role works).
-                    # Merge the summary into the first tail message instead
-                    # of inserting a standalone message that breaks alternation.
-                    _merge_summary_into_tail = True
-            if not _merge_summary_into_tail:
-                compressed.append({"role": summary_role, "content": summary})
-        else:
+        # If LLM summary failed, insert a static fallback so the model
+        # knows context was lost rather than silently dropping everything.
+        if not summary:
             if not self.quiet_mode:
-                logger.debug("No summary model available — middle turns dropped without summary")
+                logger.warning("Summary generation failed — inserting static fallback context marker")
+            n_dropped = compress_end - compress_start
+            summary = (
+                f"{SUMMARY_PREFIX}\n"
+                f"Summary generation was unavailable. {n_dropped} conversation turns were "
+                f"removed to free context space but could not be summarized. The removed "
+                f"turns contained earlier work in this session. Continue based on the "
+                f"recent messages below and the current state of any files or resources."
+            )
+
+        _merge_summary_into_tail = False
+        last_head_role = messages[compress_start - 1].get("role", "user") if compress_start > 0 else "user"
+        first_tail_role = messages[compress_end].get("role", "user") if compress_end < n_messages else "user"
+        # Pick a role that avoids consecutive same-role with both neighbors.
+        # Priority: avoid colliding with head (already committed), then tail.
+        if last_head_role in ("assistant", "tool"):
+            summary_role = "user"
+        else:
+            summary_role = "assistant"
+        # If the chosen role collides with the tail AND flipping wouldn't
+        # collide with the head, flip it.
+        if summary_role == first_tail_role:
+            flipped = "assistant" if summary_role == "user" else "user"
+            if flipped != last_head_role:
+                summary_role = flipped
+            else:
+                # Both roles would create consecutive same-role messages
+                # (e.g. head=assistant, tail=user — neither role works).
+                # Merge the summary into the first tail message instead
+                # of inserting a standalone message that breaks alternation.
+                _merge_summary_into_tail = True
+        if not _merge_summary_into_tail:
+            compressed.append({"role": summary_role, "content": summary})
 
         for i in range(compress_end, n_messages):
             msg = messages[i].copy()

agent/context_engine.py

@@ -0,0 +1,184 @@
+"""Abstract base class for pluggable context engines.
+
+A context engine controls how conversation context is managed when
+approaching the model's token limit. The built-in ContextCompressor
+is the default implementation. Third-party engines (e.g. LCM) can
+replace it via the plugin system or by being placed in the
+``plugins/context_engine/<name>/`` directory.
+
+Selection is config-driven: ``context.engine`` in config.yaml.
+Default is ``"compressor"`` (the built-in). Only one engine is active.
+
+The engine is responsible for:
+  - Deciding when compaction should fire
+  - Performing compaction (summarization, DAG construction, etc.)
+  - Optionally exposing tools the agent can call (e.g. lcm_grep)
+  - Tracking token usage from API responses
+
+Lifecycle:
+  1. Engine is instantiated and registered (plugin register() or default)
+  2. on_session_start() called when a conversation begins
+  3. update_from_response() called after each API response with usage data
+  4. should_compress() checked after each turn
+  5. compress() called when should_compress() returns True
+  6. on_session_end() called at real session boundaries (CLI exit, /reset,
+     gateway session expiry) — NOT per-turn
+"""
+
+from abc import ABC, abstractmethod
+from typing import Any, Dict, List, Optional
+
+
+class ContextEngine(ABC):
+    """Base class all context engines must implement."""
+
+    # -- Identity ----------------------------------------------------------
+
+    @property
+    @abstractmethod
+    def name(self) -> str:
+        """Short identifier (e.g. 'compressor', 'lcm')."""
+
+    # -- Token state (read by run_agent.py for display/logging) ------------
+    #
+    # Engines MUST maintain these. run_agent.py reads them directly.
+
+    last_prompt_tokens: int = 0
+    last_completion_tokens: int = 0
+    last_total_tokens: int = 0
+    threshold_tokens: int = 0
+    context_length: int = 0
+    compression_count: int = 0
+
+    # -- Compaction parameters (read by run_agent.py for preflight) --------
+    #
+    # These control the preflight compression check.  Subclasses may
+    # override via __init__ or property; defaults are sensible for most
+    # engines.
+
+    threshold_percent: float = 0.75
+    protect_first_n: int = 3
+    protect_last_n: int = 6
+
+    # -- Core interface ----------------------------------------------------
+
+    @abstractmethod
+    def update_from_response(self, usage: Dict[str, Any]) -> None:
+        """Update tracked token usage from an API response.
+
+        Called after every LLM call with the usage dict from the response.
+        """
+
+    @abstractmethod
+    def should_compress(self, prompt_tokens: int = None) -> bool:
+        """Return True if compaction should fire this turn."""
+
+    @abstractmethod
+    def compress(
+        self,
+        messages: List[Dict[str, Any]],
+        current_tokens: int = None,
+    ) -> List[Dict[str, Any]]:
+        """Compact the message list and return the new message list.
+
+        This is the main entry point. The engine receives the full message
+        list and returns a (possibly shorter) list that fits within the
+        context budget. The implementation is free to summarize, build a
+        DAG, or do anything else — as long as the returned list is a valid
+        OpenAI-format message sequence.
+        """
+
+    # -- Optional: pre-flight check ----------------------------------------
+
+    def should_compress_preflight(self, messages: List[Dict[str, Any]]) -> bool:
+        """Quick rough check before the API call (no real token count yet).
+
+        Default returns False (skip pre-flight). Override if your engine
+        can do a cheap estimate.
+        """
+        return False
+
+    # -- Optional: session lifecycle ---------------------------------------
+
+    def on_session_start(self, session_id: str, **kwargs) -> None:
+        """Called when a new conversation session begins.
+
+        Use this to load persisted state (DAG, store) for the session.
+        kwargs may include hermes_home, platform, model, etc.
+        """
+
+    def on_session_end(self, session_id: str, messages: List[Dict[str, Any]]) -> None:
+        """Called at real session boundaries (CLI exit, /reset, gateway expiry).
+
+        Use this to flush state, close DB connections, etc.
+        NOT called per-turn — only when the session truly ends.
+        """
+
+    def on_session_reset(self) -> None:
+        """Called on /new or /reset. Reset per-session state.
+
+        Default resets compression_count and token tracking.
+        """
+        self.last_prompt_tokens = 0
+        self.last_completion_tokens = 0
+        self.last_total_tokens = 0
+        self.compression_count = 0
+
+    # -- Optional: tools ---------------------------------------------------
+
+    def get_tool_schemas(self) -> List[Dict[str, Any]]:
+        """Return tool schemas this engine provides to the agent.
+
+        Default returns empty list (no tools). LCM would return schemas
+        for lcm_grep, lcm_describe, lcm_expand here.
+        """
+        return []
+
+    def handle_tool_call(self, name: str, args: Dict[str, Any], **kwargs) -> str:
+        """Handle a tool call from the agent.
+
+        Only called for tool names returned by get_tool_schemas().
+        Must return a JSON string.
+
+        kwargs may include:
+          messages: the current in-memory message list (for live ingestion)
+        """
+        import json
+        return json.dumps({"error": f"Unknown context engine tool: {name}"})
+
+    # -- Optional: status / display ----------------------------------------
+
+    def get_status(self) -> Dict[str, Any]:
+        """Return status dict for display/logging.
+
+        Default returns the standard fields run_agent.py expects.
+        """
+        return {
+            "last_prompt_tokens": self.last_prompt_tokens,
+            "threshold_tokens": self.threshold_tokens,
+            "context_length": self.context_length,
+            "usage_percent": (
+                min(100, self.last_prompt_tokens / self.context_length * 100)
+                if self.context_length else 0
+            ),
+            "compression_count": self.compression_count,
+        }
+
+    # -- Optional: model switch support ------------------------------------
+
+    def update_model(
+        self,
+        model: str,
+        context_length: int,
+        base_url: str = "",
+        api_key: str = "",
+        provider: str = "",
+    ) -> None:
+        """Called when the user switches models or on fallback activation.
+
+        Default updates context_length and recalculates threshold_tokens
+        from threshold_percent. Override if your engine needs more
+        (e.g. recalculate DAG budgets, switch summary models).
+        """
+        self.context_length = context_length
+        self.threshold_tokens = int(context_length * self.threshold_percent)

agent/context_references.py

@@ -13,8 +13,9 @@ from typing import Awaitable, Callable
 
 from agent.model_metadata import estimate_tokens_rough
 
+_QUOTED_REFERENCE_VALUE = r'(?:`[^`\n]+`|"[^"\n]+"|\'[^\'\n]+\')'
 REFERENCE_PATTERN = re.compile(
-    r"(?<![\w/])@(?:(?P<simple>diff|staged)\b|(?P<kind>file|folder|git|url):(?P<value>\S+))"
+    rf"(?<![\w/])@(?:(?P<simple>diff|staged)\b|(?P<kind>file|folder|git|url):(?P<value>{_QUOTED_REFERENCE_VALUE}(?::\d+(?:-\d+)?)?|\S+))"
 )
 TRAILING_PUNCTUATION = ",.;!?"
 _SENSITIVE_HOME_DIRS = (".ssh", ".aws", ".gnupg", ".kube", ".docker", ".azure", ".config/gh")
@@ -81,14 +82,10 @@ def parse_context_references(message: str) -> list[ContextReference]:
         value = _strip_trailing_punctuation(match.group("value") or "")
         line_start = None
         line_end = None
-        target = value
+        target = _strip_reference_wrappers(value)
 
         if kind == "file":
-            range_match = re.match(r"^(?P<path>.+?):(?P<start>\d+)(?:-(?P<end>\d+))?$", value)
-            if range_match:
-                target = range_match.group("path")
-                line_start = int(range_match.group("start"))
-                line_end = int(range_match.group("end") or range_match.group("start"))
+            target, line_start, line_end = _parse_file_reference_value(value)
 
         refs.append(
             ContextReference(
@@ -375,6 +372,38 @@ def _strip_trailing_punctuation(value: str) -> str:
     return stripped
 
 
+def _strip_reference_wrappers(value: str) -> str:
+    if len(value) >= 2 and value[0] == value[-1] and value[0] in "`\"'":
+        return value[1:-1]
+    return value
+
+
+def _parse_file_reference_value(value: str) -> tuple[str, int | None, int | None]:
+    quoted_match = re.match(
+        r'^(?P<quote>`|"|\')(?P<path>.+?)(?P=quote)(?::(?P<start>\d+)(?:-(?P<end>\d+))?)?$',
+        value,
+    )
+    if quoted_match:
+        line_start = quoted_match.group("start")
+        line_end = quoted_match.group("end")
+        return (
+            quoted_match.group("path"),
+            int(line_start) if line_start is not None else None,
+            int(line_end or line_start) if line_start is not None else None,
+        )
+
+    range_match = re.match(r"^(?P<path>.+?):(?P<start>\d+)(?:-(?P<end>\d+))?$", value)
+    if range_match:
+        line_start = int(range_match.group("start"))
+        return (
+            range_match.group("path"),
+            line_start,
+            int(range_match.group("end") or range_match.group("start")),
+        )
+
+    return _strip_reference_wrappers(value), None, None
+
+
 def _remove_reference_tokens(message: str, refs: list[ContextReference]) -> str:
     pieces: list[str] = []
     cursor = 0

agent/credential_pool.py

@@ -18,13 +18,18 @@ import hermes_cli.auth as auth_mod
 from hermes_cli.auth import (
     CODEX_ACCESS_TOKEN_REFRESH_SKEW_SECONDS,
     DEFAULT_AGENT_KEY_MIN_TTL_SECONDS,
+    KIMI_CODE_BASE_URL,
     PROVIDER_REGISTRY,
+    _auth_store_lock,
     _codex_access_token_is_expiring,
     _decode_jwt_claims,
     _import_codex_cli_tokens,
     _load_auth_store,
     _load_provider_state,
+    _resolve_kimi_base_url,
     _resolve_zai_base_url,
+    _save_auth_store,
+    _save_provider_state,
     read_credential_pool,
     write_credential_pool,
 )
@@ -64,10 +69,10 @@ SUPPORTED_POOL_STRATEGIES = {
 }
 
 # Cooldown before retrying an exhausted credential.
-# 429 (rate-limited) cools down faster since quotas reset frequently.
-# 402 (billing/quota) and other codes use a longer default.
+# 429 (rate-limited) and 402 (billing/quota) both cool down after 1 hour.
+# Provider-supplied reset_at timestamps override these defaults.
 EXHAUSTED_TTL_429_SECONDS = 60 * 60          # 1 hour
-EXHAUSTED_TTL_DEFAULT_SECONDS = 24 * 60 * 60 # 24 hours
+EXHAUSTED_TTL_DEFAULT_SECONDS = 60 * 60      # 1 hour
 
 # Pool key prefix for custom OpenAI-compatible endpoints.
 # Custom endpoints all share provider='custom' but are keyed by their
@@ -477,6 +482,67 @@ class CredentialPool:
             logger.debug("Failed to sync from ~/.codex/auth.json: %s", exc)
         return entry
 
+    def _sync_device_code_entry_to_auth_store(self, entry: PooledCredential) -> None:
+        """Write refreshed pool entry tokens back to auth.json providers.
+
+        After a pool-level refresh, the pool entry has fresh tokens but
+        auth.json's ``providers.<id>`` still holds the pre-refresh state.
+        On the next ``load_pool()``, ``_seed_from_singletons()`` reads that
+        stale state and can overwrite the fresh pool entry — potentially
+        re-seeding a consumed single-use refresh token.
+
+        Applies to any OAuth provider whose singleton lives in auth.json
+        (currently Nous and OpenAI Codex).
+        """
+        if entry.source != "device_code":
+            return
+        try:
+            with _auth_store_lock():
+                auth_store = _load_auth_store()
+                if self.provider == "nous":
+                    state = _load_provider_state(auth_store, "nous")
+                    if state is None:
+                        return
+                    state["access_token"] = entry.access_token
+                    if entry.refresh_token:
+                        state["refresh_token"] = entry.refresh_token
+                    if entry.expires_at:
+                        state["expires_at"] = entry.expires_at
+                    if entry.agent_key:
+                        state["agent_key"] = entry.agent_key
+                    if entry.agent_key_expires_at:
+                        state["agent_key_expires_at"] = entry.agent_key_expires_at
+                    for extra_key in ("obtained_at", "expires_in", "agent_key_id",
+                                      "agent_key_expires_in", "agent_key_reused",
+                                      "agent_key_obtained_at"):
+                        val = entry.extra.get(extra_key)
+                        if val is not None:
+                            state[extra_key] = val
+                    if entry.inference_base_url:
+                        state["inference_base_url"] = entry.inference_base_url
+                    _save_provider_state(auth_store, "nous", state)
+
+                elif self.provider == "openai-codex":
+                    state = _load_provider_state(auth_store, "openai-codex")
+                    if not isinstance(state, dict):
+                        return
+                    tokens = state.get("tokens")
+                    if not isinstance(tokens, dict):
+                        return
+                    tokens["access_token"] = entry.access_token
+                    if entry.refresh_token:
+                        tokens["refresh_token"] = entry.refresh_token
+                    if entry.last_refresh:
+                        state["last_refresh"] = entry.last_refresh
+                    _save_provider_state(auth_store, "openai-codex", state)
+
+                else:
+                    return
+
+                _save_auth_store(auth_store)
+        except Exception as exc:
+            logger.debug("Failed to sync %s pool entry back to auth store: %s", self.provider, exc)
+
     def _refresh_entry(self, entry: PooledCredential, *, force: bool) -> Optional[PooledCredential]:
         if entry.auth_type != AUTH_TYPE_OAUTH or not entry.refresh_token:
             if force:
@@ -511,6 +577,13 @@ class CredentialPool:
                     except Exception as wexc:
                         logger.debug("Failed to write refreshed token to credentials file: %s", wexc)
             elif self.provider == "openai-codex":
+                # Proactively sync from ~/.codex/auth.json before refresh.
+                # The Codex CLI (or another Hermes profile) may have already
+                # consumed our refresh_token.  Syncing first avoids a
+                # "refresh_token_reused" error when the CLI has a newer pair.
+                synced = self._sync_codex_entry_from_cli(entry)
+                if synced is not entry:
+                    entry = synced
                 refreshed = auth_mod.refresh_codex_oauth_pure(
                     entry.access_token,
                     entry.refresh_token,
@@ -596,6 +669,37 @@ class CredentialPool:
                     # Credentials file had a valid (non-expired) token — use it directly
                     logger.debug("Credentials file has valid token, using without refresh")
                     return synced
+            # For openai-codex: the refresh_token may have been consumed by
+            # the Codex CLI between our proactive sync and the refresh call.
+            # Re-sync and retry once.
+            if self.provider == "openai-codex":
+                synced = self._sync_codex_entry_from_cli(entry)
+                if synced.refresh_token != entry.refresh_token:
+                    logger.debug("Retrying Codex refresh with synced token from ~/.codex/auth.json")
+                    try:
+                        refreshed = auth_mod.refresh_codex_oauth_pure(
+                            synced.access_token,
+                            synced.refresh_token,
+                        )
+                        updated = replace(
+                            synced,
+                            access_token=refreshed["access_token"],
+                            refresh_token=refreshed["refresh_token"],
+                            last_refresh=refreshed.get("last_refresh"),
+                            last_status=STATUS_OK,
+                            last_status_at=None,
+                            last_error_code=None,
+                        )
+                        self._replace_entry(synced, updated)
+                        self._persist()
+                        self._sync_device_code_entry_to_auth_store(updated)
+                        return updated
+                    except Exception as retry_exc:
+                        logger.debug("Codex retry refresh also failed: %s", retry_exc)
+                elif not self._entry_needs_refresh(synced):
+                    logger.debug("Codex CLI has valid token, using without refresh")
+                    self._sync_device_code_entry_to_auth_store(synced)
+                    return synced
             self._mark_exhausted(entry, None)
             return None
 
@@ -610,6 +714,10 @@ class CredentialPool:
         )
         self._replace_entry(entry, updated)
         self._persist()
+        # Sync refreshed tokens back to auth.json providers so that
+        # _seed_from_singletons() on the next load_pool() sees fresh state
+        # instead of re-seeding stale/consumed tokens.
+        self._sync_device_code_entry_to_auth_store(updated)
         return updated
 
     def _entry_needs_refresh(self, entry: PooledCredential) -> bool:
@@ -631,17 +739,6 @@ class CredentialPool:
             return False
         return False
 
-    def mark_used(self, entry_id: Optional[str] = None) -> None:
-        """Increment request_count for tracking. Used by least_used strategy."""
-        target_id = entry_id or self._current_id
-        if not target_id:
-            return
-        with self._lock:
-            for idx, entry in enumerate(self._entries):
-                if entry.id == target_id:
-                    self._entries[idx] = replace(entry, request_count=entry.request_count + 1)
-                    return
-
     def select(self) -> Optional[PooledCredential]:
         with self._lock:
             return self._select_unlocked()
@@ -803,11 +900,6 @@ class CredentialPool:
             else:
                 self._active_leases[credential_id] = count - 1
 
-    def active_lease_count(self, credential_id: str) -> int:
-        """Return the number of active leases for a credential."""
-        with self._lock:
-            return self._active_leases.get(credential_id, 0)
-
     def try_refresh_current(self) -> Optional[PooledCredential]:
         with self._lock:
             return self._try_refresh_current_unlocked()
@@ -967,6 +1059,17 @@ def _seed_from_singletons(provider: str, entries: List[PooledCredential]) -> Tup
     auth_store = _load_auth_store()
 
     if provider == "anthropic":
+        # Only auto-discover external credentials (Claude Code, Hermes PKCE)
+        # when the user has explicitly configured anthropic as their provider.
+        # Without this gate, auxiliary client fallback chains silently read
+        # ~/.claude/.credentials.json without user consent.  See PR #4210.
+        try:
+            from hermes_cli.auth import is_provider_explicitly_configured
+            if not is_provider_explicitly_configured("anthropic"):
+                return changed, active_sources
+        except ImportError:
+            pass
+
         from agent.anthropic_adapter import read_claude_code_credentials, read_hermes_oauth_credentials
 
         for source_name, creds in (
@@ -974,6 +1077,13 @@ def _seed_from_singletons(provider: str, entries: List[PooledCredential]) -> Tup
             ("claude_code", read_claude_code_credentials()),
         ):
             if creds and creds.get("accessToken"):
+                # Check if user explicitly removed this source
+                try:
+                    from hermes_cli.auth import is_source_suppressed
+                    if is_source_suppressed(provider, source_name):
+                        continue
+                except ImportError:
+                    pass
                 active_sources.add(source_name)
                 changed |= _upsert_entry(
                     entries,
@@ -1084,7 +1194,9 @@ def _seed_from_env(provider: str, entries: List[PooledCredential]) -> Tuple[bool
         active_sources.add(source)
         auth_type = AUTH_TYPE_OAUTH if provider == "anthropic" and not token.startswith("sk-ant-api") else AUTH_TYPE_API_KEY
         base_url = env_url or pconfig.inference_base_url
-        if provider == "zai":
+        if provider == "kimi-coding":
+            base_url = _resolve_kimi_base_url(token, pconfig.inference_base_url, env_url)
+        elif provider == "zai":
             base_url = _resolve_zai_base_url(token, pconfig.inference_base_url, env_url)
         changed |= _upsert_entry(
             entries,

agent/display.py

@@ -21,11 +21,73 @@ _RESET = "\033[0m"
 logger = logging.getLogger(__name__)
 
 _ANSI_RESET = "\033[0m"
-_ANSI_DIM = "\033[38;2;150;150;150m"
-_ANSI_FILE = "\033[38;2;180;160;255m"
-_ANSI_HUNK = "\033[38;2;120;120;140m"
-_ANSI_MINUS = "\033[38;2;255;255;255;48;2;120;20;20m"
-_ANSI_PLUS = "\033[38;2;255;255;255;48;2;20;90;20m"
+
+# Diff colors — resolved lazily from the skin engine so they adapt
+# to light/dark themes.  Falls back to sensible defaults on import
+# failure.  We cache after first resolution for performance.
+_diff_colors_cached: dict[str, str] | None = None
+
+
+def _diff_ansi() -> dict[str, str]:
+    """Return ANSI escapes for diff display, resolved from the active skin."""
+    global _diff_colors_cached
+    if _diff_colors_cached is not None:
+        return _diff_colors_cached
+
+    # Defaults that work on dark terminals
+    dim = "\033[38;2;150;150;150m"
+    file_c = "\033[38;2;180;160;255m"
+    hunk = "\033[38;2;120;120;140m"
+    minus = "\033[38;2;255;255;255;48;2;120;20;20m"
+    plus = "\033[38;2;255;255;255;48;2;20;90;20m"
+
+    try:
+        from hermes_cli.skin_engine import get_active_skin
+        skin = get_active_skin()
+
+        def _hex_fg(key: str, fallback_rgb: tuple[int, int, int]) -> str:
+            h = skin.get_color(key, "")
+            if h and len(h) == 7 and h[0] == "#":
+                r, g, b = int(h[1:3], 16), int(h[3:5], 16), int(h[5:7], 16)
+                return f"\033[38;2;{r};{g};{b}m"
+            r, g, b = fallback_rgb
+            return f"\033[38;2;{r};{g};{b}m"
+
+        dim = _hex_fg("banner_dim", (150, 150, 150))
+        file_c = _hex_fg("session_label", (180, 160, 255))
+        hunk = _hex_fg("session_border", (120, 120, 140))
+        # minus/plus use background colors — derive from ui_error/ui_ok
+        err_h = skin.get_color("ui_error", "#ef5350")
+        ok_h = skin.get_color("ui_ok", "#4caf50")
+        if err_h and len(err_h) == 7:
+            er, eg, eb = int(err_h[1:3], 16), int(err_h[3:5], 16), int(err_h[5:7], 16)
+            # Use a dark tinted version as background
+            minus = f"\033[38;2;255;255;255;48;2;{max(er//2,20)};{max(eg//4,10)};{max(eb//4,10)}m"
+        if ok_h and len(ok_h) == 7:
+            or_, og, ob = int(ok_h[1:3], 16), int(ok_h[3:5], 16), int(ok_h[5:7], 16)
+            plus = f"\033[38;2;255;255;255;48;2;{max(or_//4,10)};{max(og//2,20)};{max(ob//4,10)}m"
+    except Exception:
+        pass
+
+    _diff_colors_cached = {
+        "dim": dim, "file": file_c, "hunk": hunk,
+        "minus": minus, "plus": plus,
+    }
+    return _diff_colors_cached
+
+
+def reset_diff_colors() -> None:
+    """Reset cached diff colors (call after /skin switch)."""
+    global _diff_colors_cached
+    _diff_colors_cached = None
+
+
+# Module-level helpers — each call resolves from the active skin lazily.
+def _diff_dim():   return _diff_ansi()["dim"]
+def _diff_file():  return _diff_ansi()["file"]
+def _diff_hunk():  return _diff_ansi()["hunk"]
+def _diff_minus(): return _diff_ansi()["minus"]
+def _diff_plus():  return _diff_ansi()["plus"]
 _MAX_INLINE_DIFF_FILES = 6
 _MAX_INLINE_DIFF_LINES = 80
 
@@ -67,26 +129,6 @@ def _get_skin():
         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()
@@ -423,19 +465,19 @@ def _render_inline_unified_diff(diff: str) -> list[str]:
         if raw_line.startswith("+++ "):
             to_file = raw_line[4:].strip()
             if from_file or to_file:
-                rendered.append(f"{_ANSI_FILE}{from_file or 'a/?'} → {to_file or 'b/?'}{_ANSI_RESET}")
+                rendered.append(f"{_diff_file()}{from_file or 'a/?'} → {to_file or 'b/?'}{_ANSI_RESET}")
             continue
         if raw_line.startswith("@@"):
-            rendered.append(f"{_ANSI_HUNK}{raw_line}{_ANSI_RESET}")
+            rendered.append(f"{_diff_hunk()}{raw_line}{_ANSI_RESET}")
             continue
         if raw_line.startswith("-"):
-            rendered.append(f"{_ANSI_MINUS}{raw_line}{_ANSI_RESET}")
+            rendered.append(f"{_diff_minus()}{raw_line}{_ANSI_RESET}")
             continue
         if raw_line.startswith("+"):
-            rendered.append(f"{_ANSI_PLUS}{raw_line}{_ANSI_RESET}")
+            rendered.append(f"{_diff_plus()}{raw_line}{_ANSI_RESET}")
             continue
         if raw_line.startswith(" "):
-            rendered.append(f"{_ANSI_DIM}{raw_line}{_ANSI_RESET}")
+            rendered.append(f"{_diff_dim()}{raw_line}{_ANSI_RESET}")
             continue
         if raw_line:
             rendered.append(raw_line)
@@ -501,7 +543,7 @@ def _summarize_rendered_diff_sections(
         summary = f"… omitted {omitted_lines} diff line(s)"
         if omitted_files:
             summary += f" across {omitted_files} additional file(s)/section(s)"
-        rendered.append(f"{_ANSI_HUNK}{summary}{_ANSI_RESET}")
+        rendered.append(f"{_diff_hunk()}{summary}{_ANSI_RESET}")
 
     return rendered
 
@@ -723,46 +765,6 @@ class KawaiiSpinner:
         return False
 
 
-# =========================================================================
-# Kawaii face arrays (used by AIAgent._execute_tool_calls for spinner text)
-# =========================================================================
-
-KAWAII_SEARCH = [
-    "♪(´ε` )", "(｡◕‿◕｡)", "ヾ(＾∇＾)", "(◕ᴗ◕✿)", "( ˘▽˘)っ",
-    "٩(◕‿◕｡)۶", "(✿◠‿◠)", "♪～(´ε｀ )", "(ノ´ヮ`)ノ*:・゚✧", "＼(◎o◎)／",
-]
-KAWAII_READ = [
-    "φ(゜▽゜*)♪", "( ˘▽˘)っ", "(⌐■_■)", "٩(｡•́‿•̀｡)۶", "(◕‿◕✿)",
-    "ヾ(＠⌒ー⌒＠)ノ", "(✧ω✧)", "♪(๑ᴖ◡ᴖ๑)♪", "(≧◡≦)", "( ´ ▽ ` )ノ",
-]
-KAWAII_TERMINAL = [
-    "ヽ(>∀<☆)ノ", "(ノ°∀°)ノ", "٩(^ᴗ^)۶", "ヾ(⌐■_■)ノ♪", "(•̀ᴗ•́)و",
-    "┗(＾0＾)┓", "(｀・ω・´)", "＼(￣▽￣)／", "(ง •̀_•́)ง", "ヽ(´▽`)/",
-]
-KAWAII_BROWSER = [
-    "(ノ°∀°)ノ", "(☞゚ヮ゚)☞", "( ͡° ͜ʖ ͡°)", "┌( ಠ_ಠ)┘", "(⊙_⊙)？",
-    "ヾ(•ω•`)o", "(￣ω￣)", "( ˇωˇ )", "(ᵔᴥᵔ)", "＼(◎o◎)／",
-]
-KAWAII_CREATE = [
-    "✧*。٩(ˊᗜˋ*)و✧", "(ﾉ◕ヮ◕)ﾉ*:・ﾟ✧", "ヽ(>∀<☆)ノ", "٩(♡ε♡)۶", "(◕‿◕)♡",
-    "✿◕ ‿ ◕✿", "(*≧▽≦)", "ヾ(＾-＾)ノ", "(☆▽☆)", "°˖✧◝(⁰▿⁰)◜✧˖°",
-]
-KAWAII_SKILL = [
-    "ヾ(＠⌒ー⌒＠)ノ", "(๑˃ᴗ˂)ﻭ", "٩(◕‿◕｡)۶", "(✿╹◡╹)", "ヽ(・∀・)ノ",
-    "(ノ´ヮ`)ノ*:・ﾟ✧", "♪(๑ᴖ◡ᴖ๑)♪", "(◠‿◠)", "٩(ˊᗜˋ*)و", "(＾▽＾)",
-    "ヾ(＾∇＾)", "(★ω★)/", "٩(｡•́‿•̀｡)۶", "(◕ᴗ◕✿)", "＼(◎o◎)／",
-    "(✧ω✧)", "ヽ(>∀<☆)ノ", "( ˘▽˘)っ", "(≧◡≦) ♡", "ヾ(￣▽￣)",
-]
-KAWAII_THINK = [
-    "(っ°Д°;)っ", "(；′⌒`)", "(・_・ヾ", "( ´_ゝ`)", "(￣ヘ￣)",
-    "(。-`ω´-)", "( ˘︹˘ )", "(¬_¬)", "ヽ(ー_ー )ノ", "(；一_一)",
-]
-KAWAII_GENERIC = [
-    "♪(´ε` )", "(◕‿◕✿)", "ヾ(＾∇＾)", "٩(◕‿◕｡)۶", "(✿◠‿◠)",
-    "(ノ´ヮ`)ノ*:・ﾟ✧", "ヽ(>∀<☆)ノ", "(☆▽☆)", "( ˘▽˘)っ", "(≧◡≦)",
-]
-
-
 # =========================================================================
 # Cute tool message (completion line that replaces the spinner)
 # =========================================================================
@@ -970,22 +972,6 @@ _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\\"
-
-
 # =========================================================================
 # Context pressure display (CLI user-facing warnings)
 # =========================================================================

agent/error_classifier.py

@@ -0,0 +1,809 @@
+"""API error classification for smart failover and recovery.
+
+Provides a structured taxonomy of API errors and a priority-ordered
+classification pipeline that determines the correct recovery action
+(retry, rotate credential, fallback to another provider, compress
+context, or abort).
+
+Replaces scattered inline string-matching with a centralized classifier
+that the main retry loop in run_agent.py consults for every API failure.
+"""
+
+from __future__ import annotations
+
+import enum
+import logging
+import re
+from dataclasses import dataclass, field
+from typing import Any, Dict, Optional
+
+logger = logging.getLogger(__name__)
+
+
+# ── Error taxonomy ──────────────────────────────────────────────────────
+
+class FailoverReason(enum.Enum):
+    """Why an API call failed — determines recovery strategy."""
+
+    # Authentication / authorization
+    auth = "auth"                        # Transient auth (401/403) — refresh/rotate
+    auth_permanent = "auth_permanent"    # Auth failed after refresh — abort
+
+    # Billing / quota
+    billing = "billing"                  # 402 or confirmed credit exhaustion — rotate immediately
+    rate_limit = "rate_limit"            # 429 or quota-based throttling — backoff then rotate
+
+    # Server-side
+    overloaded = "overloaded"            # 503/529 — provider overloaded, backoff
+    server_error = "server_error"        # 500/502 — internal server error, retry
+
+    # Transport
+    timeout = "timeout"                  # Connection/read timeout — rebuild client + retry
+
+    # Context / payload
+    context_overflow = "context_overflow"  # Context too large — compress, not failover
+    payload_too_large = "payload_too_large"  # 413 — compress payload
+
+    # Model
+    model_not_found = "model_not_found"  # 404 or invalid model — fallback to different model
+
+    # Request format
+    format_error = "format_error"        # 400 bad request — abort or strip + retry
+
+    # Provider-specific
+    thinking_signature = "thinking_signature"  # Anthropic thinking block sig invalid
+    long_context_tier = "long_context_tier"    # Anthropic "extra usage" tier gate
+
+    # Catch-all
+    unknown = "unknown"                  # Unclassifiable — retry with backoff
+
+
+# ── Classification result ───────────────────────────────────────────────
+
+@dataclass
+class ClassifiedError:
+    """Structured classification of an API error with recovery hints."""
+
+    reason: FailoverReason
+    status_code: Optional[int] = None
+    provider: Optional[str] = None
+    model: Optional[str] = None
+    message: str = ""
+    error_context: Dict[str, Any] = field(default_factory=dict)
+
+    # Recovery action hints — the retry loop checks these instead of
+    # re-classifying the error itself.
+    retryable: bool = True
+    should_compress: bool = False
+    should_rotate_credential: bool = False
+    should_fallback: bool = False
+
+    @property
+    def is_auth(self) -> bool:
+        return self.reason in (FailoverReason.auth, FailoverReason.auth_permanent)
+
+
+
+# ── Provider-specific patterns ──────────────────────────────────────────
+
+# Patterns that indicate billing exhaustion (not transient rate limit)
+_BILLING_PATTERNS = [
+    "insufficient credits",
+    "insufficient_quota",
+    "credit balance",
+    "credits have been exhausted",
+    "top up your credits",
+    "payment required",
+    "billing hard limit",
+    "exceeded your current quota",
+    "account is deactivated",
+    "plan does not include",
+]
+
+# Patterns that indicate rate limiting (transient, will resolve)
+_RATE_LIMIT_PATTERNS = [
+    "rate limit",
+    "rate_limit",
+    "too many requests",
+    "throttled",
+    "requests per minute",
+    "tokens per minute",
+    "requests per day",
+    "try again in",
+    "please retry after",
+    "resource_exhausted",
+    "rate increased too quickly",  # Alibaba/DashScope throttling
+]
+
+# Usage-limit patterns that need disambiguation (could be billing OR rate_limit)
+_USAGE_LIMIT_PATTERNS = [
+    "usage limit",
+    "quota",
+    "limit exceeded",
+    "key limit exceeded",
+]
+
+# Patterns confirming usage limit is transient (not billing)
+_USAGE_LIMIT_TRANSIENT_SIGNALS = [
+    "try again",
+    "retry",
+    "resets at",
+    "reset in",
+    "wait",
+    "requests remaining",
+    "periodic",
+    "window",
+]
+
+# Payload-too-large patterns detected from message text (no status_code attr).
+# Proxies and some backends embed the HTTP status in the error message.
+_PAYLOAD_TOO_LARGE_PATTERNS = [
+    "request entity too large",
+    "payload too large",
+    "error code: 413",
+]
+
+# Context overflow patterns
+_CONTEXT_OVERFLOW_PATTERNS = [
+    "context length",
+    "context size",
+    "maximum context",
+    "token limit",
+    "too many tokens",
+    "reduce the length",
+    "exceeds the limit",
+    "context window",
+    "prompt is too long",
+    "prompt exceeds max length",
+    "max_tokens",
+    "maximum number of tokens",
+    # Chinese error messages (some providers return these)
+    "超过最大长度",
+    "上下文长度",
+]
+
+# Model not found patterns
+_MODEL_NOT_FOUND_PATTERNS = [
+    "is not a valid model",
+    "invalid model",
+    "model not found",
+    "model_not_found",
+    "does not exist",
+    "no such model",
+    "unknown model",
+    "unsupported model",
+]
+
+# Auth patterns (non-status-code signals)
+_AUTH_PATTERNS = [
+    "invalid api key",
+    "invalid_api_key",
+    "authentication",
+    "unauthorized",
+    "forbidden",
+    "invalid token",
+    "token expired",
+    "token revoked",
+    "access denied",
+]
+
+# Anthropic thinking block signature patterns
+_THINKING_SIG_PATTERNS = [
+    "signature",  # Combined with "thinking" check
+]
+
+# Transport error type names
+_TRANSPORT_ERROR_TYPES = frozenset({
+    "ReadTimeout", "ConnectTimeout", "PoolTimeout",
+    "ConnectError", "RemoteProtocolError",
+    "ConnectionError", "ConnectionResetError",
+    "ConnectionAbortedError", "BrokenPipeError",
+    "TimeoutError", "ReadError",
+    "ServerDisconnectedError",
+    # OpenAI SDK errors (not subclasses of Python builtins)
+    "APIConnectionError",
+    "APITimeoutError",
+})
+
+# Server disconnect patterns (no status code, but transport-level)
+_SERVER_DISCONNECT_PATTERNS = [
+    "server disconnected",
+    "peer closed connection",
+    "connection reset by peer",
+    "connection was closed",
+    "network connection lost",
+    "unexpected eof",
+    "incomplete chunked read",
+]
+
+
+# ── Classification pipeline ─────────────────────────────────────────────
+
+def classify_api_error(
+    error: Exception,
+    *,
+    provider: str = "",
+    model: str = "",
+    approx_tokens: int = 0,
+    context_length: int = 200000,
+    num_messages: int = 0,
+) -> ClassifiedError:
+    """Classify an API error into a structured recovery recommendation.
+
+    Priority-ordered pipeline:
+      1. Special-case provider-specific patterns (thinking sigs, tier gates)
+      2. HTTP status code + message-aware refinement
+      3. Error code classification (from body)
+      4. Message pattern matching (billing vs rate_limit vs context vs auth)
+      5. Transport error heuristics
+      6. Server disconnect + large session → context overflow
+      7. Fallback: unknown (retryable with backoff)
+
+    Args:
+        error: The exception from the API call.
+        provider: Current provider name (e.g. "openrouter", "anthropic").
+        model: Current model slug.
+        approx_tokens: Approximate token count of the current context.
+        context_length: Maximum context length for the current model.
+
+    Returns:
+        ClassifiedError with reason and recovery action hints.
+    """
+    status_code = _extract_status_code(error)
+    error_type = type(error).__name__
+    body = _extract_error_body(error)
+    error_code = _extract_error_code(body)
+
+    # Build a comprehensive error message string for pattern matching.
+    # str(error) alone may not include the body message (e.g. OpenAI SDK's
+    # APIStatusError.__str__ returns the first arg, not the body).  Append
+    # the body message so patterns like "try again" in 402 disambiguation
+    # are detected even when only present in the structured body.
+    #
+    # Also extract metadata.raw — OpenRouter wraps upstream provider errors
+    # inside {"error": {"message": "Provider returned error", "metadata":
+    # {"raw": "<actual error JSON>"}}} and the real error message (e.g.
+    # "context length exceeded") is only in the inner JSON.
+    _raw_msg = str(error).lower()
+    _body_msg = ""
+    _metadata_msg = ""
+    if isinstance(body, dict):
+        _err_obj = body.get("error", {})
+        if isinstance(_err_obj, dict):
+            _body_msg = (_err_obj.get("message") or "").lower()
+            # Parse metadata.raw for wrapped provider errors
+            _metadata = _err_obj.get("metadata", {})
+            if isinstance(_metadata, dict):
+                _raw_json = _metadata.get("raw") or ""
+                if isinstance(_raw_json, str) and _raw_json.strip():
+                    try:
+                        import json
+                        _inner = json.loads(_raw_json)
+                        if isinstance(_inner, dict):
+                            _inner_err = _inner.get("error", {})
+                            if isinstance(_inner_err, dict):
+                                _metadata_msg = (_inner_err.get("message") or "").lower()
+                    except (json.JSONDecodeError, TypeError):
+                        pass
+        if not _body_msg:
+            _body_msg = (body.get("message") or "").lower()
+    # Combine all message sources for pattern matching
+    parts = [_raw_msg]
+    if _body_msg and _body_msg not in _raw_msg:
+        parts.append(_body_msg)
+    if _metadata_msg and _metadata_msg not in _raw_msg and _metadata_msg not in _body_msg:
+        parts.append(_metadata_msg)
+    error_msg = " ".join(parts)
+    provider_lower = (provider or "").strip().lower()
+    model_lower = (model or "").strip().lower()
+
+    def _result(reason: FailoverReason, **overrides) -> ClassifiedError:
+        defaults = {
+            "reason": reason,
+            "status_code": status_code,
+            "provider": provider,
+            "model": model,
+            "message": _extract_message(error, body),
+        }
+        defaults.update(overrides)
+        return ClassifiedError(**defaults)
+
+    # ── 1. Provider-specific patterns (highest priority) ────────────
+
+    # Anthropic thinking block signature invalid (400).
+    # Don't gate on provider — OpenRouter proxies Anthropic errors, so the
+    # provider may be "openrouter" even though the error is Anthropic-specific.
+    # The message pattern ("signature" + "thinking") is unique enough.
+    if (
+        status_code == 400
+        and "signature" in error_msg
+        and "thinking" in error_msg
+    ):
+        return _result(
+            FailoverReason.thinking_signature,
+            retryable=True,
+            should_compress=False,
+        )
+
+    # Anthropic long-context tier gate (429 "extra usage" + "long context")
+    if (
+        status_code == 429
+        and "extra usage" in error_msg
+        and "long context" in error_msg
+    ):
+        return _result(
+            FailoverReason.long_context_tier,
+            retryable=True,
+            should_compress=True,
+        )
+
+    # ── 2. HTTP status code classification ──────────────────────────
+
+    if status_code is not None:
+        classified = _classify_by_status(
+            status_code, error_msg, error_code, body,
+            provider=provider_lower, model=model_lower,
+            approx_tokens=approx_tokens, context_length=context_length,
+            num_messages=num_messages,
+            result_fn=_result,
+        )
+        if classified is not None:
+            return classified
+
+    # ── 3. Error code classification ────────────────────────────────
+
+    if error_code:
+        classified = _classify_by_error_code(error_code, error_msg, _result)
+        if classified is not None:
+            return classified
+
+    # ── 4. Message pattern matching (no status code) ────────────────
+
+    classified = _classify_by_message(
+        error_msg, error_type,
+        approx_tokens=approx_tokens,
+        context_length=context_length,
+        result_fn=_result,
+    )
+    if classified is not None:
+        return classified
+
+    # ── 5. Server disconnect + large session → context overflow ─────
+    # Must come BEFORE generic transport error catch — a disconnect on
+    # a large session is more likely context overflow than a transient
+    # transport hiccup.  Without this ordering, RemoteProtocolError
+    # always maps to timeout regardless of session size.
+
+    is_disconnect = any(p in error_msg for p in _SERVER_DISCONNECT_PATTERNS)
+    if is_disconnect and not status_code:
+        is_large = approx_tokens > context_length * 0.6 or approx_tokens > 120000 or num_messages > 200
+        if is_large:
+            return _result(
+                FailoverReason.context_overflow,
+                retryable=True,
+                should_compress=True,
+            )
+        return _result(FailoverReason.timeout, retryable=True)
+
+    # ── 6. Transport / timeout heuristics ───────────────────────────
+
+    if error_type in _TRANSPORT_ERROR_TYPES or isinstance(error, (TimeoutError, ConnectionError, OSError)):
+        return _result(FailoverReason.timeout, retryable=True)
+
+    # ── 7. Fallback: unknown ────────────────────────────────────────
+
+    return _result(FailoverReason.unknown, retryable=True)
+
+
+# ── Status code classification ──────────────────────────────────────────
+
+def _classify_by_status(
+    status_code: int,
+    error_msg: str,
+    error_code: str,
+    body: dict,
+    *,
+    provider: str,
+    model: str,
+    approx_tokens: int,
+    context_length: int,
+    num_messages: int = 0,
+    result_fn,
+) -> Optional[ClassifiedError]:
+    """Classify based on HTTP status code with message-aware refinement."""
+
+    if status_code == 401:
+        # Not retryable on its own — credential pool rotation and
+        # provider-specific refresh (Codex, Anthropic, Nous) run before
+        # the retryability check in run_agent.py.  If those succeed, the
+        # loop `continue`s.  If they fail, retryable=False ensures we
+        # hit the client-error abort path (which tries fallback first).
+        return result_fn(
+            FailoverReason.auth,
+            retryable=False,
+            should_rotate_credential=True,
+            should_fallback=True,
+        )
+
+    if status_code == 403:
+        # OpenRouter 403 "key limit exceeded" is actually billing
+        if "key limit exceeded" in error_msg or "spending limit" in error_msg:
+            return result_fn(
+                FailoverReason.billing,
+                retryable=False,
+                should_rotate_credential=True,
+                should_fallback=True,
+            )
+        return result_fn(
+            FailoverReason.auth,
+            retryable=False,
+            should_fallback=True,
+        )
+
+    if status_code == 402:
+        return _classify_402(error_msg, result_fn)
+
+    if status_code == 404:
+        if any(p in error_msg for p in _MODEL_NOT_FOUND_PATTERNS):
+            return result_fn(
+                FailoverReason.model_not_found,
+                retryable=False,
+                should_fallback=True,
+            )
+        # Generic 404 — could be model or endpoint
+        return result_fn(
+            FailoverReason.model_not_found,
+            retryable=False,
+            should_fallback=True,
+        )
+
+    if status_code == 413:
+        return result_fn(
+            FailoverReason.payload_too_large,
+            retryable=True,
+            should_compress=True,
+        )
+
+    if status_code == 429:
+        # Already checked long_context_tier above; this is a normal rate limit
+        return result_fn(
+            FailoverReason.rate_limit,
+            retryable=True,
+            should_rotate_credential=True,
+            should_fallback=True,
+        )
+
+    if status_code == 400:
+        return _classify_400(
+            error_msg, error_code, body,
+            provider=provider, model=model,
+            approx_tokens=approx_tokens,
+            context_length=context_length,
+            num_messages=num_messages,
+            result_fn=result_fn,
+        )
+
+    if status_code in (500, 502):
+        return result_fn(FailoverReason.server_error, retryable=True)
+
+    if status_code in (503, 529):
+        return result_fn(FailoverReason.overloaded, retryable=True)
+
+    # Other 4xx — non-retryable
+    if 400 <= status_code < 500:
+        return result_fn(
+            FailoverReason.format_error,
+            retryable=False,
+            should_fallback=True,
+        )
+
+    # Other 5xx — retryable
+    if 500 <= status_code < 600:
+        return result_fn(FailoverReason.server_error, retryable=True)
+
+    return None
+
+
+def _classify_402(error_msg: str, result_fn) -> ClassifiedError:
+    """Disambiguate 402: billing exhaustion vs transient usage limit.
+
+    The key insight from OpenClaw: some 402s are transient rate limits
+    disguised as payment errors.  "Usage limit, try again in 5 minutes"
+    is NOT a billing problem — it's a periodic quota that resets.
+    """
+    # Check for transient usage-limit signals first
+    has_usage_limit = any(p in error_msg for p in _USAGE_LIMIT_PATTERNS)
+    has_transient_signal = any(p in error_msg for p in _USAGE_LIMIT_TRANSIENT_SIGNALS)
+
+    if has_usage_limit and has_transient_signal:
+        # Transient quota — treat as rate limit, not billing
+        return result_fn(
+            FailoverReason.rate_limit,
+            retryable=True,
+            should_rotate_credential=True,
+            should_fallback=True,
+        )
+
+    # Confirmed billing exhaustion
+    return result_fn(
+        FailoverReason.billing,
+        retryable=False,
+        should_rotate_credential=True,
+        should_fallback=True,
+    )
+
+
+def _classify_400(
+    error_msg: str,
+    error_code: str,
+    body: dict,
+    *,
+    provider: str,
+    model: str,
+    approx_tokens: int,
+    context_length: int,
+    num_messages: int = 0,
+    result_fn,
+) -> ClassifiedError:
+    """Classify 400 Bad Request — context overflow, format error, or generic."""
+
+    # Context overflow from 400
+    if any(p in error_msg for p in _CONTEXT_OVERFLOW_PATTERNS):
+        return result_fn(
+            FailoverReason.context_overflow,
+            retryable=True,
+            should_compress=True,
+        )
+
+    # Some providers return model-not-found as 400 instead of 404 (e.g. OpenRouter).
+    if any(p in error_msg for p in _MODEL_NOT_FOUND_PATTERNS):
+        return result_fn(
+            FailoverReason.model_not_found,
+            retryable=False,
+            should_fallback=True,
+        )
+
+    # Some providers return rate limit / billing errors as 400 instead of 429/402.
+    # Check these patterns before falling through to format_error.
+    if any(p in error_msg for p in _RATE_LIMIT_PATTERNS):
+        return result_fn(
+            FailoverReason.rate_limit,
+            retryable=True,
+            should_rotate_credential=True,
+            should_fallback=True,
+        )
+    if any(p in error_msg for p in _BILLING_PATTERNS):
+        return result_fn(
+            FailoverReason.billing,
+            retryable=False,
+            should_rotate_credential=True,
+            should_fallback=True,
+        )
+
+    # Generic 400 + large session → probable context overflow
+    # Anthropic sometimes returns a bare "Error" message when context is too large
+    err_body_msg = ""
+    if isinstance(body, dict):
+        err_obj = body.get("error", {})
+        if isinstance(err_obj, dict):
+            err_body_msg = (err_obj.get("message") or "").strip().lower()
+        # Responses API (and some providers) use flat body: {"message": "..."}
+        if not err_body_msg:
+            err_body_msg = (body.get("message") or "").strip().lower()
+    is_generic = len(err_body_msg) < 30 or err_body_msg in ("error", "")
+    is_large = approx_tokens > context_length * 0.4 or approx_tokens > 80000 or num_messages > 80
+
+    if is_generic and is_large:
+        return result_fn(
+            FailoverReason.context_overflow,
+            retryable=True,
+            should_compress=True,
+        )
+
+    # Non-retryable format error
+    return result_fn(
+        FailoverReason.format_error,
+        retryable=False,
+        should_fallback=True,
+    )
+
+
+# ── Error code classification ───────────────────────────────────────────
+
+def _classify_by_error_code(
+    error_code: str, error_msg: str, result_fn,
+) -> Optional[ClassifiedError]:
+    """Classify by structured error codes from the response body."""
+    code_lower = error_code.lower()
+
+    if code_lower in ("resource_exhausted", "throttled", "rate_limit_exceeded"):
+        return result_fn(
+            FailoverReason.rate_limit,
+            retryable=True,
+            should_rotate_credential=True,
+        )
+
+    if code_lower in ("insufficient_quota", "billing_not_active", "payment_required"):
+        return result_fn(
+            FailoverReason.billing,
+            retryable=False,
+            should_rotate_credential=True,
+            should_fallback=True,
+        )
+
+    if code_lower in ("model_not_found", "model_not_available", "invalid_model"):
+        return result_fn(
+            FailoverReason.model_not_found,
+            retryable=False,
+            should_fallback=True,
+        )
+
+    if code_lower in ("context_length_exceeded", "max_tokens_exceeded"):
+        return result_fn(
+            FailoverReason.context_overflow,
+            retryable=True,
+            should_compress=True,
+        )
+
+    return None
+
+
+# ── Message pattern classification ──────────────────────────────────────
+
+def _classify_by_message(
+    error_msg: str,
+    error_type: str,
+    *,
+    approx_tokens: int,
+    context_length: int,
+    result_fn,
+) -> Optional[ClassifiedError]:
+    """Classify based on error message patterns when no status code is available."""
+
+    # Payload-too-large patterns (from message text when no status_code)
+    if any(p in error_msg for p in _PAYLOAD_TOO_LARGE_PATTERNS):
+        return result_fn(
+            FailoverReason.payload_too_large,
+            retryable=True,
+            should_compress=True,
+        )
+
+    # Usage-limit patterns need the same disambiguation as 402: some providers
+    # surface "usage limit" errors without an HTTP status code.  A transient
+    # signal ("try again", "resets at", …) means it's a periodic quota, not
+    # billing exhaustion.
+    has_usage_limit = any(p in error_msg for p in _USAGE_LIMIT_PATTERNS)
+    if has_usage_limit:
+        has_transient_signal = any(p in error_msg for p in _USAGE_LIMIT_TRANSIENT_SIGNALS)
+        if has_transient_signal:
+            return result_fn(
+                FailoverReason.rate_limit,
+                retryable=True,
+                should_rotate_credential=True,
+                should_fallback=True,
+            )
+        return result_fn(
+            FailoverReason.billing,
+            retryable=False,
+            should_rotate_credential=True,
+            should_fallback=True,
+        )
+
+    # Billing patterns
+    if any(p in error_msg for p in _BILLING_PATTERNS):
+        return result_fn(
+            FailoverReason.billing,
+            retryable=False,
+            should_rotate_credential=True,
+            should_fallback=True,
+        )
+
+    # Rate limit patterns
+    if any(p in error_msg for p in _RATE_LIMIT_PATTERNS):
+        return result_fn(
+            FailoverReason.rate_limit,
+            retryable=True,
+            should_rotate_credential=True,
+            should_fallback=True,
+        )
+
+    # Context overflow patterns
+    if any(p in error_msg for p in _CONTEXT_OVERFLOW_PATTERNS):
+        return result_fn(
+            FailoverReason.context_overflow,
+            retryable=True,
+            should_compress=True,
+        )
+
+    # Auth patterns
+    # Auth errors should NOT be retried directly — the credential is invalid and
+    # retrying with the same key will always fail.  Set retryable=False so the
+    # caller triggers credential rotation (should_rotate_credential=True) or
+    # provider fallback rather than an immediate retry loop.
+    if any(p in error_msg for p in _AUTH_PATTERNS):
+        return result_fn(
+            FailoverReason.auth,
+            retryable=False,
+            should_rotate_credential=True,
+            should_fallback=True,
+        )
+
+    # Model not found patterns
+    if any(p in error_msg for p in _MODEL_NOT_FOUND_PATTERNS):
+        return result_fn(
+            FailoverReason.model_not_found,
+            retryable=False,
+            should_fallback=True,
+        )
+
+    return None
+
+
+# ── Helpers ─────────────────────────────────────────────────────────────
+
+def _extract_status_code(error: Exception) -> Optional[int]:
+    """Walk the error and its cause chain to find an HTTP status code."""
+    current = error
+    for _ in range(5):  # Max depth to prevent infinite loops
+        code = getattr(current, "status_code", None)
+        if isinstance(code, int):
+            return code
+        # Some SDKs use .status instead of .status_code
+        code = getattr(current, "status", None)
+        if isinstance(code, int) and 100 <= code < 600:
+            return code
+        # Walk cause chain
+        cause = getattr(current, "__cause__", None) or getattr(current, "__context__", None)
+        if cause is None or cause is current:
+            break
+        current = cause
+    return None
+
+
+def _extract_error_body(error: Exception) -> dict:
+    """Extract the structured error body from an SDK exception."""
+    body = getattr(error, "body", None)
+    if isinstance(body, dict):
+        return body
+    # Some errors have .response.json()
+    response = getattr(error, "response", None)
+    if response is not None:
+        try:
+            json_body = response.json()
+            if isinstance(json_body, dict):
+                return json_body
+        except Exception:
+            pass
+    return {}
+
+
+def _extract_error_code(body: dict) -> str:
+    """Extract an error code string from the response body."""
+    if not body:
+        return ""
+    error_obj = body.get("error", {})
+    if isinstance(error_obj, dict):
+        code = error_obj.get("code") or error_obj.get("type") or ""
+        if isinstance(code, str) and code.strip():
+            return code.strip()
+    # Top-level code
+    code = body.get("code") or body.get("error_code") or ""
+    if isinstance(code, (str, int)):
+        return str(code).strip()
+    return ""
+
+
+def _extract_message(error: Exception, body: dict) -> str:
+    """Extract the most informative error message."""
+    # Try structured body first
+    if body:
+        error_obj = body.get("error", {})
+        if isinstance(error_obj, dict):
+            msg = error_obj.get("message", "")
+            if isinstance(msg, str) and msg.strip():
+                return msg.strip()[:500]
+        msg = body.get("message", "")
+        if isinstance(msg, str) and msg.strip():
+            return msg.strip()[:500]
+    # Fallback to str(error)
+    return str(error)[:500]

agent/insights.py

@@ -39,15 +39,6 @@ def _has_known_pricing(model_name: str, provider: str = None, base_url: str = No
     return has_known_pricing(model_name, provider=provider, base_url=base_url)
 
 
-def _get_pricing(model_name: str) -> Dict[str, float]:
-    """Look up pricing for a model. Uses fuzzy matching on model name.
-
-    Returns _DEFAULT_PRICING (zero cost) for unknown/custom models —
-    we can't assume costs for self-hosted endpoints, local inference, etc.
-    """
-    return get_pricing(model_name)
-
-
 def _estimate_cost(
     session_or_model: Dict[str, Any] | str,
     input_tokens: int = 0,

agent/manual_compression_feedback.py

@@ -0,0 +1,49 @@
+"""User-facing summaries for manual compression commands."""
+
+from __future__ import annotations
+
+from typing import Any, Sequence
+
+
+def summarize_manual_compression(
+    before_messages: Sequence[dict[str, Any]],
+    after_messages: Sequence[dict[str, Any]],
+    before_tokens: int,
+    after_tokens: int,
+) -> dict[str, Any]:
+    """Return consistent user-facing feedback for manual compression."""
+    before_count = len(before_messages)
+    after_count = len(after_messages)
+    noop = list(after_messages) == list(before_messages)
+
+    if noop:
+        headline = f"No changes from compression: {before_count} messages"
+        if after_tokens == before_tokens:
+            token_line = (
+                f"Rough transcript estimate: ~{before_tokens:,} tokens (unchanged)"
+            )
+        else:
+            token_line = (
+                f"Rough transcript estimate: ~{before_tokens:,} → "
+                f"~{after_tokens:,} tokens"
+            )
+    else:
+        headline = f"Compressed: {before_count} → {after_count} messages"
+        token_line = (
+            f"Rough transcript estimate: ~{before_tokens:,} → "
+            f"~{after_tokens:,} tokens"
+        )
+
+    note = None
+    if not noop and after_count < before_count and after_tokens > before_tokens:
+        note = (
+            "Note: fewer messages can still raise this rough transcript estimate "
+            "when compression rewrites the transcript into denser summaries."
+        )
+
+    return {
+        "noop": noop,
+        "headline": headline,
+        "token_line": token_line,
+        "note": note,
+    }

agent/memory_manager.py

@@ -134,11 +134,6 @@ class MemoryManager:
         """All registered providers in order."""
         return list(self._providers)
 
-    @property
-    def provider_names(self) -> List[str]:
-        """Names of all registered providers."""
-        return [p.name for p in self._providers]
-
     def get_provider(self, name: str) -> Optional[MemoryProvider]:
         """Get a provider by name, or None if not registered."""
         for p in self._providers:

agent/model_metadata.py

@@ -113,19 +113,31 @@ DEFAULT_CONTEXT_LENGTHS = {
     "deepseek": 128000,
     # Meta
     "llama": 131072,
-    # Qwen
+    # Qwen — specific model families before the catch-all.
+    # Official docs: https://help.aliyun.com/zh/model-studio/developer-reference/
+    "qwen3-coder-plus": 1000000,  # 1M context
+    "qwen3-coder": 262144,        # 256K context
     "qwen": 131072,
-    # MiniMax (lowercase — lookup lowercases model names at line 973)
-    "minimax-m1-256k": 1000000,
-    "minimax-m1-128k": 1000000,
-    "minimax-m1-80k": 1000000,
-    "minimax-m1-40k": 1000000,
-    "minimax-m1": 1000000,
-    "minimax-m2.5": 1048576,
-    "minimax-m2.7": 1048576,
-    "minimax": 1048576,
+    # MiniMax — official docs: 204,800 context for all models
+    # https://platform.minimax.io/docs/api-reference/text-anthropic-api
+    "minimax": 204800,
     # GLM
     "glm": 202752,
+    # xAI Grok — xAI /v1/models does not return context_length metadata,
+    # so these hardcoded fallbacks prevent Hermes from probing-down to
+    # the default 128k when the user points at https://api.x.ai/v1
+    # via a custom provider. Values sourced from models.dev (2026-04).
+    # Keys use substring matching (longest-first), so e.g. "grok-4.20"
+    # matches "grok-4.20-0309-reasoning" / "-non-reasoning" / "-multi-agent-0309".
+    "grok-code-fast": 256000,   # grok-code-fast-1
+    "grok-4-1-fast": 2000000,   # grok-4-1-fast-(non-)reasoning
+    "grok-2-vision": 8192,      # grok-2-vision, -1212, -latest
+    "grok-4-fast": 2000000,     # grok-4-fast-(non-)reasoning
+    "grok-4.20": 2000000,       # grok-4.20-0309-(non-)reasoning, -multi-agent-0309
+    "grok-4": 256000,           # grok-4, grok-4-0709
+    "grok-3": 131072,           # grok-3, grok-3-mini, grok-3-fast, grok-3-mini-fast
+    "grok-2": 131072,           # grok-2, grok-2-1212, grok-2-latest
+    "grok": 131072,             # catch-all (grok-beta, unknown grok-*)
     # Kimi
     "kimi": 262144,
     # Arcee
@@ -136,7 +148,7 @@ DEFAULT_CONTEXT_LENGTHS = {
     "deepseek-ai/DeepSeek-V3.2": 65536,
     "moonshotai/Kimi-K2.5": 262144,
     "moonshotai/Kimi-K2-Thinking": 262144,
-    "MiniMaxAI/MiniMax-M2.5": 1048576,
+    "MiniMaxAI/MiniMax-M2.5": 204800,
     "XiaomiMiMo/MiMo-V2-Flash": 32768,
     "mimo-v2-pro": 1048576,
     "mimo-v2-omni": 1048576,
@@ -197,6 +209,8 @@ _URL_TO_PROVIDER: Dict[str, str] = {
     "api.githubcopilot.com": "copilot",
     "models.github.ai": "copilot",
     "api.fireworks.ai": "fireworks",
+    "opencode.ai": "opencode-go",
+    "api.x.ai": "xai",
 }
 
 
@@ -602,6 +616,49 @@ def parse_context_limit_from_error(error_msg: str) -> Optional[int]:
     return None
 
 
+def parse_available_output_tokens_from_error(error_msg: str) -> Optional[int]:
+    """Detect an "output cap too large" error and return how many output tokens are available.
+
+    Background — two distinct context errors exist:
+      1. "Prompt too long"  — the INPUT itself exceeds the context window.
+           Fix: compress history and/or halve context_length.
+      2. "max_tokens too large" — input is fine, but input + requested_output > window.
+           Fix: reduce max_tokens (the output cap) for this call.
+           Do NOT touch context_length — the window hasn't shrunk.
+
+    Anthropic's API returns errors like:
+      "max_tokens: 32768 > context_window: 200000 - input_tokens: 190000 = available_tokens: 10000"
+
+    Returns the number of output tokens that would fit (e.g. 10000 above), or None if
+    the error does not look like a max_tokens-too-large error.
+    """
+    error_lower = error_msg.lower()
+
+    # Must look like an output-cap error, not a prompt-length error.
+    is_output_cap_error = (
+        "max_tokens" in error_lower
+        and ("available_tokens" in error_lower or "available tokens" in error_lower)
+    )
+    if not is_output_cap_error:
+        return None
+
+    # Extract the available_tokens figure.
+    # Anthropic format: "… = available_tokens: 10000"
+    patterns = [
+        r'available_tokens[:\s]+(\d+)',
+        r'available\s+tokens[:\s]+(\d+)',
+        # fallback: last number after "=" in expressions like "200000 - 190000 = 10000"
+        r'=\s*(\d+)\s*$',
+    ]
+    for pattern in patterns:
+        match = re.search(pattern, error_lower)
+        if match:
+            tokens = int(match.group(1))
+            if tokens >= 1:
+                return tokens
+    return None
+
+
 def _model_id_matches(candidate_id: str, lookup_model: str) -> bool:
     """Return True if *candidate_id* (from server) matches *lookup_model* (configured).
 

agent/models_dev.py

@@ -135,9 +135,6 @@ class ProviderInfo:
     doc: str = ""                   # documentation URL
     model_count: int = 0
 
-    def has_api_url(self) -> bool:
-        return bool(self.api)
-
 
 # ---------------------------------------------------------------------------
 # Provider ID mapping: Hermes ↔ models.dev
@@ -634,43 +631,6 @@ def get_provider_info(provider_id: str) -> Optional[ProviderInfo]:
     return _parse_provider_info(mdev_id, raw)
 
 
-def list_all_providers() -> Dict[str, ProviderInfo]:
-    """Return all providers from models.dev as {provider_id: ProviderInfo}.
-
-    Returns the full catalog — 109+ providers.  For providers that have
-    a Hermes alias, both the models.dev ID and the Hermes ID are included.
-    """
-    data = fetch_models_dev()
-    result: Dict[str, ProviderInfo] = {}
-
-    for pid, pdata in data.items():
-        if isinstance(pdata, dict):
-            info = _parse_provider_info(pid, pdata)
-            result[pid] = info
-
-    return result
-
-
-def get_providers_for_env_var(env_var: str) -> List[str]:
-    """Reverse lookup: find all providers that use a given env var.
-
-    Useful for auto-detection: "user has ANTHROPIC_API_KEY set, which
-    providers does that enable?"
-
-    Returns list of models.dev provider IDs.
-    """
-    data = fetch_models_dev()
-    matches: List[str] = []
-
-    for pid, pdata in data.items():
-        if isinstance(pdata, dict):
-            env = pdata.get("env", [])
-            if isinstance(env, list) and env_var in env:
-                matches.append(pid)
-
-    return matches
-
-
 # ---------------------------------------------------------------------------
 # Model-level queries (rich ModelInfo)
 # ---------------------------------------------------------------------------
@@ -708,74 +668,3 @@ def get_model_info(
     return None
 
 
-def get_model_info_any_provider(model_id: str) -> Optional[ModelInfo]:
-    """Search all providers for a model by ID.
-
-    Useful when you have a full slug like "anthropic/claude-sonnet-4.6" or
-    a bare name and want to find it anywhere.  Checks Hermes-mapped providers
-    first, then falls back to all models.dev providers.
-    """
-    data = fetch_models_dev()
-
-    # Try Hermes-mapped providers first (more likely what the user wants)
-    for hermes_id, mdev_id in PROVIDER_TO_MODELS_DEV.items():
-        pdata = data.get(mdev_id)
-        if not isinstance(pdata, dict):
-            continue
-        models = pdata.get("models", {})
-        if not isinstance(models, dict):
-            continue
-
-        raw = models.get(model_id)
-        if isinstance(raw, dict):
-            return _parse_model_info(model_id, raw, mdev_id)
-
-        # Case-insensitive
-        model_lower = model_id.lower()
-        for mid, mdata in models.items():
-            if mid.lower() == model_lower and isinstance(mdata, dict):
-                return _parse_model_info(mid, mdata, mdev_id)
-
-    # Fall back to ALL providers
-    for pid, pdata in data.items():
-        if pid in _get_reverse_mapping():
-            continue  # already checked
-        if not isinstance(pdata, dict):
-            continue
-        models = pdata.get("models", {})
-        if not isinstance(models, dict):
-            continue
-
-        raw = models.get(model_id)
-        if isinstance(raw, dict):
-            return _parse_model_info(model_id, raw, pid)
-
-    return None
-
-
-def list_provider_model_infos(provider_id: str) -> List[ModelInfo]:
-    """Return all models for a provider as ModelInfo objects.
-
-    Filters out deprecated models by default.
-    """
-    mdev_id = PROVIDER_TO_MODELS_DEV.get(provider_id, provider_id)
-
-    data = fetch_models_dev()
-    pdata = data.get(mdev_id)
-    if not isinstance(pdata, dict):
-        return []
-
-    models = pdata.get("models", {})
-    if not isinstance(models, dict):
-        return []
-
-    result: List[ModelInfo] = []
-    for mid, mdata in models.items():
-        if not isinstance(mdata, dict):
-            continue
-        status = mdata.get("status", "")
-        if status == "deprecated":
-            continue
-        result.append(_parse_model_info(mid, mdata, mdev_id))
-
-    return result

agent/prompt_builder.py

@@ -40,7 +40,7 @@ _CONTEXT_THREAT_PATTERNS = [
     (r'disregard\s+(your|all|any)\s+(instructions|rules|guidelines)', "disregard_rules"),
     (r'act\s+as\s+(if|though)\s+you\s+(have\s+no|don\'t\s+have)\s+(restrictions|limits|rules)', "bypass_restrictions"),
     (r'<!--[^>]*(?:ignore|override|system|secret|hidden)[^>]*-->', "html_comment_injection"),
-    (r'<\s*div\s+style\s*=\s*["\'].*display\s*:\s*none', "hidden_div"),
+    (r'<\s*div\s+style\s*=\s*["\'][\s\S]*?display\s*:\s*none', "hidden_div"),
     (r'translate\s+.*\s+into\s+.*\s+and\s+(execute|run|eval)', "translate_execute"),
     (r'curl\s+[^\n]*\$\{?\w*(KEY|TOKEN|SECRET|PASSWORD|CREDENTIAL|API)', "exfil_curl"),
     (r'cat\s+[^\n]*(\.env|credentials|\.netrc|\.pgpass)', "read_secrets"),
@@ -349,6 +349,21 @@ PLATFORM_HINTS = {
         "only — no markdown, no formatting. SMS messages are limited to ~1600 "
         "characters, so be brief and direct."
     ),
+    "bluebubbles": (
+        "You are chatting via iMessage (BlueBubbles). iMessage does not render "
+        "markdown formatting — use plain text. Keep responses concise as they "
+        "appear as text messages. You can send media files natively: include "
+        "MEDIA:/absolute/path/to/file in your response. Images (.jpg, .png, "
+        ".heic) appear as photos and other files arrive as attachments."
+    ),
+    "weixin": (
+        "You are on Weixin/WeChat. Markdown formatting is supported, so you may use it when "
+        "it improves readability, but keep the message compact and chat-friendly. You can send media files natively: "
+        "include MEDIA:/absolute/path/to/file in your response. Images are sent as native "
+        "photos, videos play inline when supported, and other files arrive as downloadable "
+        "documents. You can also include image URLs in markdown format ![alt](url) and they "
+        "will be downloaded and sent as native media when possible."
+    ),
 }
 
 CONTEXT_FILE_MAX_CHARS = 20_000
@@ -472,7 +487,7 @@ def _parse_skill_file(skill_file: Path) -> tuple[bool, dict, str]:
     (True, {}, "") to err on the side of showing the skill.
     """
     try:
-        raw = skill_file.read_text(encoding="utf-8")[:2000]
+        raw = skill_file.read_text(encoding="utf-8")
         frontmatter, _ = parse_frontmatter(raw)
 
         if not skill_matches_platform(frontmatter):
@@ -480,21 +495,10 @@ def _parse_skill_file(skill_file: Path) -> tuple[bool, dict, str]:
 
         return True, frontmatter, extract_skill_description(frontmatter)
     except Exception as e:
-        logger.debug("Failed to parse skill file %s: %s", skill_file, e)
+        logger.warning("Failed to parse skill file %s: %s", skill_file, e)
         return True, {}, ""
 
 
-def _read_skill_conditions(skill_file: Path) -> dict:
-    """Extract conditional activation fields from SKILL.md frontmatter."""
-    try:
-        raw = skill_file.read_text(encoding="utf-8")[:2000]
-        frontmatter, _ = parse_frontmatter(raw)
-        return extract_skill_conditions(frontmatter)
-    except Exception as e:
-        logger.debug("Failed to read skill conditions from %s: %s", skill_file, e)
-        return {}
-
-
 def _skill_should_show(
     conditions: dict,
     available_tools: "set[str] | None",
@@ -554,9 +558,10 @@ def build_skills_system_prompt(
     # ── Layer 1: in-process LRU cache ─────────────────────────────────
     # Include the resolved platform so per-platform disabled-skill lists
     # produce distinct cache entries (gateway serves multiple platforms).
+    from gateway.session_context import get_session_env
     _platform_hint = (
         os.environ.get("HERMES_PLATFORM")
-        or os.environ.get("HERMES_SESSION_PLATFORM")
+        or get_session_env("HERMES_SESSION_PLATFORM")
         or ""
     )
     cache_key = (

agent/rate_limit_tracker.py

@@ -0,0 +1,246 @@
+"""Rate limit tracking for inference API responses.
+
+Captures x-ratelimit-* headers from provider responses and provides
+formatted display for the /usage slash command.  Currently supports
+the Nous Portal header format (also used by OpenRouter and OpenAI-compatible
+APIs that follow the same convention).
+
+Header schema (12 headers total):
+    x-ratelimit-limit-requests          RPM cap
+    x-ratelimit-limit-requests-1h       RPH cap
+    x-ratelimit-limit-tokens            TPM cap
+    x-ratelimit-limit-tokens-1h         TPH cap
+    x-ratelimit-remaining-requests      requests left in minute window
+    x-ratelimit-remaining-requests-1h   requests left in hour window
+    x-ratelimit-remaining-tokens        tokens left in minute window
+    x-ratelimit-remaining-tokens-1h     tokens left in hour window
+    x-ratelimit-reset-requests          seconds until minute request window resets
+    x-ratelimit-reset-requests-1h       seconds until hour request window resets
+    x-ratelimit-reset-tokens            seconds until minute token window resets
+    x-ratelimit-reset-tokens-1h         seconds until hour token window resets
+"""
+
+from __future__ import annotations
+
+import time
+from dataclasses import dataclass, field
+from typing import Any, Dict, Mapping, Optional
+
+
+@dataclass
+class RateLimitBucket:
+    """One rate-limit window (e.g. requests per minute)."""
+
+    limit: int = 0
+    remaining: int = 0
+    reset_seconds: float = 0.0
+    captured_at: float = 0.0  # time.time() when this was captured
+
+    @property
+    def used(self) -> int:
+        return max(0, self.limit - self.remaining)
+
+    @property
+    def usage_pct(self) -> float:
+        if self.limit <= 0:
+            return 0.0
+        return (self.used / self.limit) * 100.0
+
+    @property
+    def remaining_seconds_now(self) -> float:
+        """Estimated seconds remaining until reset, adjusted for elapsed time."""
+        elapsed = time.time() - self.captured_at
+        return max(0.0, self.reset_seconds - elapsed)
+
+
+@dataclass
+class RateLimitState:
+    """Full rate-limit state parsed from response headers."""
+
+    requests_min: RateLimitBucket = field(default_factory=RateLimitBucket)
+    requests_hour: RateLimitBucket = field(default_factory=RateLimitBucket)
+    tokens_min: RateLimitBucket = field(default_factory=RateLimitBucket)
+    tokens_hour: RateLimitBucket = field(default_factory=RateLimitBucket)
+    captured_at: float = 0.0  # when the headers were captured
+    provider: str = ""
+
+    @property
+    def has_data(self) -> bool:
+        return self.captured_at > 0
+
+    @property
+    def age_seconds(self) -> float:
+        if not self.has_data:
+            return float("inf")
+        return time.time() - self.captured_at
+
+
+def _safe_int(value: Any, default: int = 0) -> int:
+    try:
+        return int(float(value))
+    except (TypeError, ValueError):
+        return default
+
+
+def _safe_float(value: Any, default: float = 0.0) -> float:
+    try:
+        return float(value)
+    except (TypeError, ValueError):
+        return default
+
+
+def parse_rate_limit_headers(
+    headers: Mapping[str, str],
+    provider: str = "",
+) -> Optional[RateLimitState]:
+    """Parse x-ratelimit-* headers into a RateLimitState.
+
+    Returns None if no rate limit headers are present.
+    """
+    # Normalize to lowercase so lookups work regardless of how the server
+    # capitalises headers (HTTP header names are case-insensitive per RFC 7230).
+    lowered = {k.lower(): v for k, v in headers.items()}
+
+    # Quick check: at least one rate limit header must exist
+    has_any = any(k.startswith("x-ratelimit-") for k in lowered)
+    if not has_any:
+        return None
+
+    now = time.time()
+
+    def _bucket(resource: str, suffix: str = "") -> RateLimitBucket:
+        # e.g. resource="requests", suffix="" -> per-minute
+        #      resource="tokens", suffix="-1h" -> per-hour
+        tag = f"{resource}{suffix}"
+        return RateLimitBucket(
+            limit=_safe_int(lowered.get(f"x-ratelimit-limit-{tag}")),
+            remaining=_safe_int(lowered.get(f"x-ratelimit-remaining-{tag}")),
+            reset_seconds=_safe_float(lowered.get(f"x-ratelimit-reset-{tag}")),
+            captured_at=now,
+        )
+
+    return RateLimitState(
+        requests_min=_bucket("requests"),
+        requests_hour=_bucket("requests", "-1h"),
+        tokens_min=_bucket("tokens"),
+        tokens_hour=_bucket("tokens", "-1h"),
+        captured_at=now,
+        provider=provider,
+    )
+
+
+# ── Formatting ──────────────────────────────────────────────────────────
+
+
+def _fmt_count(n: int) -> str:
+    """Human-friendly number: 7999856 -> '8.0M', 33599 -> '33.6K', 799 -> '799'."""
+    if n >= 1_000_000:
+        return f"{n / 1_000_000:.1f}M"
+    if n >= 10_000:
+        return f"{n / 1_000:.1f}K"
+    if n >= 1_000:
+        return f"{n / 1_000:.1f}K"
+    return str(n)
+
+
+def _fmt_seconds(seconds: float) -> str:
+    """Seconds -> human-friendly duration: '58s', '2m 14s', '58m 57s', '1h 2m'."""
+    s = max(0, int(seconds))
+    if s < 60:
+        return f"{s}s"
+    if s < 3600:
+        m, sec = divmod(s, 60)
+        return f"{m}m {sec}s" if sec else f"{m}m"
+    h, remainder = divmod(s, 3600)
+    m = remainder // 60
+    return f"{h}h {m}m" if m else f"{h}h"
+
+
+def _bar(pct: float, width: int = 20) -> str:
+    """ASCII progress bar: [████████░░░░░░░░░░░░] 40%."""
+    filled = int(pct / 100.0 * width)
+    filled = max(0, min(width, filled))
+    empty = width - filled
+    return f"[{'█' * filled}{'░' * empty}]"
+
+
+def _bucket_line(label: str, bucket: RateLimitBucket, label_width: int = 14) -> str:
+    """Format one bucket as a single line."""
+    if bucket.limit <= 0:
+        return f"  {label:<{label_width}}  (no data)"
+
+    pct = bucket.usage_pct
+    used = _fmt_count(bucket.used)
+    limit = _fmt_count(bucket.limit)
+    remaining = _fmt_count(bucket.remaining)
+    reset = _fmt_seconds(bucket.remaining_seconds_now)
+
+    bar = _bar(pct)
+    return f"  {label:<{label_width}} {bar} {pct:5.1f}%  {used}/{limit} used  ({remaining} left, resets in {reset})"
+
+
+def format_rate_limit_display(state: RateLimitState) -> str:
+    """Format rate limit state for terminal/chat display."""
+    if not state.has_data:
+        return "No rate limit data yet — make an API request first."
+
+    age = state.age_seconds
+    if age < 5:
+        freshness = "just now"
+    elif age < 60:
+        freshness = f"{int(age)}s ago"
+    else:
+        freshness = f"{_fmt_seconds(age)} ago"
+
+    provider_label = state.provider.title() if state.provider else "Provider"
+
+    lines = [
+        f"{provider_label} Rate Limits (captured {freshness}):",
+        "",
+        _bucket_line("Requests/min", state.requests_min),
+        _bucket_line("Requests/hr", state.requests_hour),
+        "",
+        _bucket_line("Tokens/min", state.tokens_min),
+        _bucket_line("Tokens/hr", state.tokens_hour),
+    ]
+
+    # Add warnings if any bucket is getting hot
+    warnings = []
+    for label, bucket in [
+        ("requests/min", state.requests_min),
+        ("requests/hr", state.requests_hour),
+        ("tokens/min", state.tokens_min),
+        ("tokens/hr", state.tokens_hour),
+    ]:
+        if bucket.limit > 0 and bucket.usage_pct >= 80:
+            reset = _fmt_seconds(bucket.remaining_seconds_now)
+            warnings.append(f"  ⚠ {label} at {bucket.usage_pct:.0f}% — resets in {reset}")
+
+    if warnings:
+        lines.append("")
+        lines.extend(warnings)
+
+    return "\n".join(lines)
+
+
+def format_rate_limit_compact(state: RateLimitState) -> str:
+    """One-line compact summary for status bars / gateway messages."""
+    if not state.has_data:
+        return "No rate limit data."
+
+    rm = state.requests_min
+    tm = state.tokens_min
+    rh = state.requests_hour
+    th = state.tokens_hour
+
+    parts = []
+    if rm.limit > 0:
+        parts.append(f"RPM: {rm.remaining}/{rm.limit}")
+    if rh.limit > 0:
+        parts.append(f"RPH: {_fmt_count(rh.remaining)}/{_fmt_count(rh.limit)} (resets {_fmt_seconds(rh.remaining_seconds_now)})")
+    if tm.limit > 0:
+        parts.append(f"TPM: {_fmt_count(tm.remaining)}/{_fmt_count(tm.limit)}")
+    if th.limit > 0:
+        parts.append(f"TPH: {_fmt_count(th.remaining)}/{_fmt_count(th.limit)} (resets {_fmt_seconds(th.remaining_seconds_now)})")
+
+    return " | ".join(parts)

agent/skill_commands.py

@@ -168,7 +168,7 @@ def _build_skill_message(
             subdir_path = skill_dir / subdir
             if subdir_path.exists():
                 for f in sorted(subdir_path.rglob("*")):
-                    if f.is_file():
+                    if f.is_file() and not f.is_symlink():
                         rel = str(f.relative_to(skill_dir))
                         supporting.append(rel)
 

agent/skill_utils.py

@@ -145,10 +145,11 @@ def get_disabled_skill_names(platform: str | None = None) -> Set[str]:
     if not isinstance(skills_cfg, dict):
         return set()
 
+    from gateway.session_context import get_session_env
     resolved_platform = (
         platform
         or os.getenv("HERMES_PLATFORM")
-        or os.getenv("HERMES_SESSION_PLATFORM")
+        or get_session_env("HERMES_SESSION_PLATFORM")
     )
     if resolved_platform:
         platform_disabled = (skills_cfg.get("platform_disabled") or {}).get(

agent/smart_model_routing.py

@@ -181,6 +181,7 @@ def resolve_turn_route(user_message: str, routing_config: Optional[Dict[str, Any
             "api_mode": runtime.get("api_mode"),
             "command": runtime.get("command"),
             "args": list(runtime.get("args") or []),
+            "credential_pool": runtime.get("credential_pool"),
         },
         "label": f"smart route → {route.get('model')} ({runtime.get('provider')})",
         "signature": (

agent/subdirectory_hints.py

@@ -159,7 +159,10 @@ class SubdirectoryHintTracker:
 
     def _is_valid_subdir(self, path: Path) -> bool:
         """Check if path is a valid directory to scan for hints."""
-        if not path.is_dir():
+        try:
+            if not path.is_dir():
+                return False
+        except OSError:
             return False
         if path in self._loaded_dirs:
             return False
@@ -172,7 +175,10 @@ class SubdirectoryHintTracker:
         found_hints = []
         for filename in _HINT_FILENAMES:
             hint_path = directory / filename
-            if not hint_path.is_file():
+            try:
+                if not hint_path.is_file():
+                    continue
+            except OSError:
                 continue
             try:
                 content = hint_path.read_text(encoding="utf-8").strip()

agent/usage_pricing.py

@@ -595,30 +595,6 @@ def get_pricing(
     }
 
 
-def estimate_cost_usd(
-    model: str,
-    input_tokens: int,
-    output_tokens: int,
-    *,
-    provider: Optional[str] = None,
-    base_url: Optional[str] = None,
-    api_key: Optional[str] = None,
-) -> float:
-    """Backward-compatible helper for legacy callers.
-
-    This uses non-cached input/output only. New code should call
-    `estimate_usage_cost()` with canonical usage buckets.
-    """
-    result = estimate_usage_cost(
-        model,
-        CanonicalUsage(input_tokens=input_tokens, output_tokens=output_tokens),
-        provider=provider,
-        base_url=base_url,
-        api_key=api_key,
-    )
-    return float(result.amount_usd or _ZERO)
-
-
 def format_duration_compact(seconds: float) -> str:
     if seconds < 60:
         return f"{seconds:.0f}s"

batch_runner.py

@@ -1158,7 +1158,7 @@ def main(
         providers_order (str): Comma-separated list of OpenRouter providers to try in order (e.g. "anthropic,openai,google")
         provider_sort (str): Sort providers by "price", "throughput", or "latency" (OpenRouter only)
         max_tokens (int): Maximum tokens for model responses (optional, uses model default if not set)
-        reasoning_effort (str): OpenRouter reasoning effort level: "xhigh", "high", "medium", "low", "minimal", "none" (default: "medium")
+        reasoning_effort (str): OpenRouter reasoning effort level: "none", "minimal", "low", "medium", "high", "xhigh" (default: "medium")
         reasoning_disabled (bool): Completely disable reasoning/thinking tokens (default: False)
         prefill_messages_file (str): Path to JSON file containing prefill messages (list of {role, content} dicts)
         max_samples (int): Only process the first N samples from the dataset (optional, processes all if not set)
@@ -1227,7 +1227,7 @@ def main(
         print("🧠 Reasoning: DISABLED (effort=none)")
     elif reasoning_effort:
         # Use specified effort level
-        valid_efforts = ["xhigh", "high", "medium", "low", "minimal", "none"]
+        valid_efforts = ["none", "minimal", "low", "medium", "high", "xhigh"]
         if reasoning_effort not in valid_efforts:
             print(f"❌ Error: --reasoning_effort must be one of: {', '.join(valid_efforts)}")
             return

cli-config.yaml.example

@@ -48,6 +48,25 @@ model:
   # api_key: "your-key-here"  # Uncomment to set here instead of .env
   base_url: "https://openrouter.ai/api/v1"
 
+  # ── Token limits — two settings, easy to confuse ──────────────────────────
+  #
+  # context_length: TOTAL context window (input + output tokens combined).
+  #   Controls when Hermes compresses history and validates requests.
+  #   Leave unset — Hermes auto-detects the correct value from the provider.
+  #   Set manually only when auto-detection is wrong (e.g. a local server with
+  #   a custom num_ctx, or a proxy that doesn't expose /v1/models).
+  #
+  # context_length: 131072
+  #
+  # max_tokens: OUTPUT cap — maximum tokens the model may generate per response.
+  #   Unrelated to how long your conversation history can be.
+  #   The OpenAI-standard name "max_tokens" is a misnomer; Anthropic's native
+  #   API has since renamed it "max_output_tokens" for clarity.
+  #   Leave unset to use the model's native output ceiling (recommended).
+  #   Set only if you want to deliberately limit individual response length.
+  #
+  # max_tokens: 8192
+
 # =============================================================================
 # OpenRouter Provider Routing (only applies when using OpenRouter)
 # =============================================================================
@@ -117,7 +136,8 @@ terminal:
   timeout: 180
   docker_mount_cwd_to_workspace: false  # SECURITY: off by default. Opt in to mount the launch cwd into Docker /workspace.
   lifetime_seconds: 300
-  # sudo_password: ""  # Enable sudo commands (pipes via sudo -S) - SECURITY WARNING: plaintext!
+  # sudo_password: "hunter2"  # Optional: pipe a sudo password via sudo -S. SECURITY WARNING: plaintext.
+  # sudo_password: ""         # Explicit empty password: try empty and never open the interactive sudo prompt.
 
 # -----------------------------------------------------------------------------
 # OPTION 2: SSH remote execution
@@ -208,13 +228,18 @@ terminal:
 #
 # SECURITY WARNING: Password stored in plaintext!
 #
-# INTERACTIVE PROMPT: If no sudo_password is set and the CLI is running,
+# INTERACTIVE PROMPT: If sudo_password is unset and the CLI is running,
 # you'll be prompted to enter your password when sudo is needed:
 # - 45-second timeout (auto-skips if no input)
 # - Press Enter to skip (command fails gracefully)
 # - Password is hidden while typing
 # - Password is cached for the session
 #
+# EMPTY PASSWORDS: Setting sudo_password to an explicit empty string is different
+# from leaving it unset. Hermes will try an empty password via `sudo -S` and
+# will not open the interactive prompt. This is useful for passwordless sudo,
+# Touch ID sudo setups, and environments where prompting is just noise.
+#
 # ALTERNATIVES:
 # - SSH backend: Configure passwordless sudo on the remote server
 # - Containers: Run as root inside the container (no sudo needed)
@@ -445,6 +470,22 @@ agent:
   # Higher = more room for complex tasks, but costs more tokens
   # Recommended: 20-30 for focused tasks, 50-100 for open exploration
   max_turns: 60
+
+  # Inactivity timeout for gateway agent runs (seconds, 0 = unlimited).
+  # The agent can run indefinitely when actively calling tools or receiving
+  # API responses.  Only fires after the agent has been idle for this duration.
+  # gateway_timeout: 1800
+
+  # Staged warning: send a warning before escalating to full timeout.
+  # Fires once per run when inactivity reaches this threshold (seconds).
+  # Set to 0 to disable the warning.
+  # gateway_timeout_warning: 900
+
+  # Graceful drain timeout for gateway stop/restart (seconds).
+  # The gateway stops accepting new work, waits for in-flight agents to
+  # finish, then interrupts anything still running after this timeout.
+  # 0 = no drain, interrupt immediately.
+  # restart_drain_timeout: 60
   
   # Enable verbose logging
   verbose: false
@@ -547,7 +588,7 @@ platform_toolsets:
 #   skills_hub   - skill_hub (search/install/manage from online registries — user-driven only)
 #   moa          - mixture_of_agents  (requires OPENROUTER_API_KEY)
 #   todo         - todo (in-memory task planning, no deps)
-#   tts          - text_to_speech  (Edge TTS free, or ELEVENLABS/OPENAI/MINIMAX key)
+#   tts          - text_to_speech  (Edge TTS free, or ELEVENLABS/OPENAI/MINIMAX/MISTRAL key)
 #   cronjob      - cronjob (create/list/update/pause/resume/run/remove scheduled tasks)
 #   rl           - rl_list_environments, rl_start_training, etc. (requires TINKER_API_KEY)
 #
@@ -576,7 +617,7 @@ platform_toolsets:
 #   todo         - Task planning and tracking for multi-step work
 #   memory       - Persistent memory across sessions (personal notes + user profile)
 #   session_search - Search and recall past conversations (FTS5 + Gemini Flash summarization)
-#   tts          - Text-to-speech (Edge TTS free, ElevenLabs, OpenAI, MiniMax)
+#   tts          - Text-to-speech (Edge TTS free, ElevenLabs, OpenAI, MiniMax, Mistral)
 #   cronjob      - Schedule and manage automated tasks (CLI-only)
 #   rl           - RL training tools (Tinker-Atropos)
 #
@@ -649,7 +690,11 @@ platform_toolsets:
 stt:
   enabled: true
   # provider: "local"          # auto-detected if omitted
-  model: "whisper-1"  # whisper-1 (cheapest) | gpt-4o-mini-transcribe | gpt-4o-transcribe
+  local:
+    model: "base"              # tiny | base | small | medium | large-v3 | turbo
+    # language: ""             # auto-detect; set to "en", "es", "fr", etc. to force
+  openai:
+    model: "whisper-1"         # whisper-1 | gpt-4o-mini-transcribe | gpt-4o-transcribe
   # mistral:
   #   model: "voxtral-mini-latest"  # voxtral-mini-latest | voxtral-mini-2602
 

constraints-termux.txt

@@ -0,0 +1,15 @@
+# Termux / Android dependency constraints for Hermes Agent.
+#
+# Usage:
+#   python -m pip install -e '.[termux]' -c constraints-termux.txt
+#
+# These pins keep the tested Android install path stable when upstream packages
+# move faster than Termux-compatible wheels / sdists.
+
+ipython<10
+jedi>=0.18.1,<0.20
+parso>=0.8.4,<0.9
+stack-data>=0.6,<0.7
+pexpect>4.3,<5
+matplotlib-inline>=0.1.7,<0.2
+asttokens>=2.1,<3

cron/jobs.py

@@ -31,7 +31,7 @@ except ImportError:
 # Configuration
 # =============================================================================
 
-HERMES_DIR = get_hermes_home()
+HERMES_DIR = get_hermes_home().resolve()
 CRON_DIR = HERMES_DIR / "cron"
 JOBS_FILE = CRON_DIR / "jobs.json"
 OUTPUT_DIR = CRON_DIR / "output"
@@ -338,10 +338,12 @@ def load_jobs() -> List[Dict[str, Any]]:
                     save_jobs(jobs)
                     logger.warning("Auto-repaired jobs.json (had invalid control characters)")
                 return jobs
-        except Exception:
-            return []
-    except IOError:
-        return []
+        except Exception as e:
+            logger.error("Failed to auto-repair jobs.json: %s", e)
+            raise RuntimeError(f"Cron database corrupted and unrepairable: {e}") from e
+    except IOError as e:
+        logger.error("IOError reading jobs.json: %s", e)
+        raise RuntimeError(f"Failed to read cron database: {e}") from e
 
 
 def save_jobs(jobs: List[Dict[str, Any]]):
@@ -452,6 +454,7 @@ def create_job(
         "last_run_at": None,
         "last_status": None,
         "last_error": None,
+        "last_delivery_error": None,
         # Delivery configuration
         "deliver": deliver,
         "origin": origin,  # Tracks where job was created for "origin" delivery
@@ -620,8 +623,8 @@ def mark_job_run(job_id: str, success: bool, error: Optional[str] = None,
 
             save_jobs(jobs)
             return
-    
-    save_jobs(jobs)
+
+    logger.warning("mark_job_run: job_id %s not found, skipping save", job_id)
 
 
 def advance_next_run(job_id: str) -> bool:

cron/scheduler.py

@@ -44,7 +44,7 @@ logger = logging.getLogger(__name__)
 _KNOWN_DELIVERY_PLATFORMS = frozenset({
     "telegram", "discord", "slack", "whatsapp", "signal",
     "matrix", "mattermost", "homeassistant", "dingtalk", "feishu",
-    "wecom", "sms", "email", "webhook",
+    "wecom", "weixin", "sms", "email", "webhook", "bluebubbles",
 })
 
 from cron.jobs import get_due_jobs, mark_job_run, save_job_output, advance_next_run
@@ -91,7 +91,7 @@ def _resolve_delivery_target(job: dict) -> Optional[dict]:
             }
         # Origin missing (e.g. job created via API/script) — try each
         # platform's home channel as a fallback instead of silently dropping.
-        for platform_name in ("matrix", "telegram", "discord", "slack"):
+        for platform_name in ("matrix", "telegram", "discord", "slack", "bluebubbles"):
             chat_id = os.getenv(f"{platform_name.upper()}_HOME_CHANNEL", "")
             if chat_id:
                 logger.info(
@@ -234,8 +234,10 @@ def _deliver_result(job: dict, content: str, adapters=None, loop=None) -> Option
         "dingtalk": Platform.DINGTALK,
         "feishu": Platform.FEISHU,
         "wecom": Platform.WECOM,
+        "weixin": Platform.WEIXIN,
         "email": Platform.EMAIL,
         "sms": Platform.SMS,
+        "bluebubbles": Platform.BLUEBUBBLES,
     }
     platform = platform_map.get(platform_name.lower())
     if not platform:
@@ -345,7 +347,42 @@ def _deliver_result(job: dict, content: str, adapters=None, loop=None) -> Option
     return None
 
 
-_SCRIPT_TIMEOUT = 120  # seconds
+_DEFAULT_SCRIPT_TIMEOUT = 120  # seconds
+# Backward-compatible module override used by tests and emergency monkeypatches.
+_SCRIPT_TIMEOUT = _DEFAULT_SCRIPT_TIMEOUT
+
+
+def _get_script_timeout() -> int:
+    """Resolve cron pre-run script timeout from module/env/config with a safe default."""
+    if _SCRIPT_TIMEOUT != _DEFAULT_SCRIPT_TIMEOUT:
+        try:
+            timeout = int(float(_SCRIPT_TIMEOUT))
+            if timeout > 0:
+                return timeout
+        except Exception:
+            logger.warning("Invalid patched _SCRIPT_TIMEOUT=%r; using env/config/default", _SCRIPT_TIMEOUT)
+
+    env_value = os.getenv("HERMES_CRON_SCRIPT_TIMEOUT", "").strip()
+    if env_value:
+        try:
+            timeout = int(float(env_value))
+            if timeout > 0:
+                return timeout
+        except Exception:
+            logger.warning("Invalid HERMES_CRON_SCRIPT_TIMEOUT=%r; using config/default", env_value)
+
+    try:
+        cfg = load_config() or {}
+        cron_cfg = cfg.get("cron", {}) if isinstance(cfg, dict) else {}
+        configured = cron_cfg.get("script_timeout_seconds")
+        if configured is not None:
+            timeout = int(float(configured))
+            if timeout > 0:
+                return timeout
+    except Exception as exc:
+        logger.debug("Failed to load cron script timeout from config: %s", exc)
+
+    return _DEFAULT_SCRIPT_TIMEOUT
 
 
 def _run_job_script(script_path: str) -> tuple[bool, str]:
@@ -392,17 +429,27 @@ def _run_job_script(script_path: str) -> tuple[bool, str]:
     if not path.is_file():
         return False, f"Script path is not a file: {path}"
 
+    script_timeout = _get_script_timeout()
+
     try:
         result = subprocess.run(
             [sys.executable, str(path)],
             capture_output=True,
             text=True,
-            timeout=_SCRIPT_TIMEOUT,
+            timeout=script_timeout,
             cwd=str(path.parent),
         )
         stdout = (result.stdout or "").strip()
         stderr = (result.stderr or "").strip()
 
+        # Redact secrets from both stdout and stderr before any return path.
+        try:
+            from agent.redact import redact_sensitive_text
+            stdout = redact_sensitive_text(stdout)
+            stderr = redact_sensitive_text(stderr)
+        except Exception:
+            pass
+
         if result.returncode != 0:
             parts = [f"Script exited with code {result.returncode}"]
             if stderr:
@@ -411,17 +458,10 @@ def _run_job_script(script_path: str) -> tuple[bool, str]:
                 parts.append(f"stdout:\n{stdout}")
             return False, "\n".join(parts)
 
-        # Redact any secrets that may appear in script output before
-        # they are injected into the LLM prompt context.
-        try:
-            from agent.redact import redact_sensitive_text
-            stdout = redact_sensitive_text(stdout)
-        except Exception:
-            pass
         return True, stdout
 
     except subprocess.TimeoutExpired:
-        return False, f"Script timed out after {_SCRIPT_TIMEOUT}s: {path}"
+        return False, f"Script timed out after {script_timeout}s: {path}"
     except Exception as exc:
         return False, f"Script execution failed: {exc}"
 
@@ -645,6 +685,24 @@ def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:
             },
         )
 
+        fallback_model = _cfg.get("fallback_providers") or _cfg.get("fallback_model") or None
+        credential_pool = None
+        runtime_provider = str(turn_route["runtime"].get("provider") or "").strip().lower()
+        if runtime_provider:
+            try:
+                from agent.credential_pool import load_pool
+                pool = load_pool(runtime_provider)
+                if pool.has_credentials():
+                    credential_pool = pool
+                    logger.info(
+                        "Job '%s': loaded credential pool for provider %s with %d entries",
+                        job_id,
+                        runtime_provider,
+                        len(pool.entries()),
+                    )
+            except Exception as e:
+                logger.debug("Job '%s': failed to load credential pool for %s: %s", job_id, runtime_provider, e)
+
         agent = AIAgent(
             model=turn_route["model"],
             api_key=turn_route["runtime"].get("api_key"),
@@ -656,6 +714,8 @@ def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:
             max_iterations=max_iterations,
             reasoning_config=reasoning_config,
             prefill_messages=prefill_messages,
+            fallback_model=fallback_model,
+            credential_pool=credential_pool,
             providers_allowed=pr.get("only"),
             providers_ignored=pr.get("ignore"),
             providers_order=pr.get("order"),
@@ -710,7 +770,7 @@ def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:
             _cron_pool.shutdown(wait=False, cancel_futures=True)
             raise
         finally:
-            _cron_pool.shutdown(wait=False)
+            _cron_pool.shutdown(wait=False, cancel_futures=True)
 
         if _inactivity_timeout:
             # Build diagnostic summary from the agent's activity tracker.

docker/entrypoint.sh

@@ -9,7 +9,10 @@ INSTALL_DIR="/opt/hermes"
 # (cache/images, cache/audio, platforms/whatsapp, etc.) are created on
 # demand by the application — don't pre-create them here so new installs
 # get the consolidated layout from get_hermes_dir().
-mkdir -p "$HERMES_HOME"/{cron,sessions,logs,hooks,memories,skills}
+# The "home/" subdirectory is a per-profile HOME for subprocesses (git,
+# ssh, gh, npm …).  Without it those tools write to /root which is
+# ephemeral and shared across profiles.  See issue #4426.
+mkdir -p "$HERMES_HOME"/{cron,sessions,logs,hooks,memories,skills,skins,plans,workspace,home}
 
 # .env
 if [ ! -f "$HERMES_HOME/.env" ]; then

environments/tool_call_parsers/hermes_parser.py

@@ -49,6 +49,8 @@ class HermesToolCallParser(ToolCallParser):
                     continue
 
                 tc_data = json.loads(raw_json)
+                if "name" not in tc_data:
+                    continue
                 tool_calls.append(
                     ChatCompletionMessageToolCall(
                         id=f"call_{uuid.uuid4().hex[:8]}",

environments/tool_call_parsers/mistral_parser.py

@@ -89,6 +89,8 @@ class MistralToolCallParser(ToolCallParser):
                         parsed = [parsed]
 
                     for tc in parsed:
+                        if "name" not in tc:
+                            continue
                         args = tc.get("arguments", {})
                         if isinstance(args, dict):
                             args = json.dumps(args, ensure_ascii=False)

flake.lock

@@ -22,16 +22,16 @@
     },
     "nixpkgs": {
       "locked": {
-        "lastModified": 1751274312,
-        "narHash": "sha256-/bVBlRpECLVzjV19t5KMdMFWSwKLtb5RyXdjz3LJT+g=",
+        "lastModified": 1775036866,
+        "narHash": "sha256-ZojAnPuCdy657PbTq5V0Y+AHKhZAIwSIT2cb8UgAz/U=",
         "owner": "NixOS",
         "repo": "nixpkgs",
-        "rev": "50ab793786d9de88ee30ec4e4c24fb4236fc2674",
+        "rev": "6201e203d09599479a3b3450ed24fa81537ebc4e",
         "type": "github"
       },
       "original": {
         "owner": "NixOS",
-        "ref": "nixos-24.11",
+        "ref": "nixos-unstable",
         "repo": "nixpkgs",
         "type": "github"
       }

flake.nix

@@ -2,7 +2,7 @@
   description = "Hermes Agent - AI agent framework by Nous Research";
 
   inputs = {
-    nixpkgs.url = "github:NixOS/nixpkgs/nixos-24.11";
+    nixpkgs.url = "github:NixOS/nixpkgs/nixos-unstable";
     flake-parts = {
       url = "github:hercules-ci/flake-parts";
       inputs.nixpkgs-lib.follows = "nixpkgs";

gateway/channel_directory.py

@@ -76,10 +76,15 @@ def build_channel_directory(adapters: Dict[Any, Any]) -> Dict[str, Any]:
         except Exception as e:
             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", "email", "sms"):
-        if plat_name not in platforms:
-            platforms[plat_name] = _build_from_sessions(plat_name)
+    # Platforms that don't support direct channel enumeration get session-based
+    # discovery automatically.  Skip infrastructure entries that aren't messaging
+    # platforms — everything else falls through to _build_from_sessions().
+    _SKIP_SESSION_DISCOVERY = frozenset({"local", "api_server", "webhook"})
+    for plat in Platform:
+        plat_name = plat.value
+        if plat_name in _SKIP_SESSION_DISCOVERY or plat_name in platforms:
+            continue
+        platforms[plat_name] = _build_from_sessions(plat_name)
 
     directory = {
         "updated_at": datetime.now().isoformat(),

gateway/config.py

@@ -63,6 +63,8 @@ class Platform(Enum):
     WEBHOOK = "webhook"
     FEISHU = "feishu"
     WECOM = "wecom"
+    WEIXIN = "weixin"
+    BLUEBUBBLES = "bluebubbles"
 
 
 @dataclass
@@ -260,6 +262,11 @@ class GatewayConfig:
         for platform, config in self.platforms.items():
             if not config.enabled:
                 continue
+            # Weixin requires both a token and an account_id
+            if platform == Platform.WEIXIN:
+                if config.extra.get("account_id") and (config.token or config.extra.get("token")):
+                    connected.append(platform)
+                continue
             # Platforms that use token/api_key auth
             if config.token or config.api_key:
                 connected.append(platform)
@@ -287,6 +294,9 @@ class GatewayConfig:
             # WeCom uses extra dict for bot credentials
             elif platform == Platform.WECOM and config.extra.get("bot_id"):
                 connected.append(platform)
+            # BlueBubbles uses extra dict for local server config
+            elif platform == Platform.BLUEBUBBLES and config.extra.get("server_url") and config.extra.get("password"):
+                connected.append(platform)
         return connected
     
     def get_home_channel(self, platform: Platform) -> Optional[HomeChannel]:
@@ -528,8 +538,12 @@ def load_gateway_config() -> GatewayConfig:
                     bridged["reply_prefix"] = platform_cfg["reply_prefix"]
                 if "require_mention" in platform_cfg:
                     bridged["require_mention"] = platform_cfg["require_mention"]
+                if "free_response_channels" in platform_cfg:
+                    bridged["free_response_channels"] = platform_cfg["free_response_channels"]
                 if "mention_patterns" in platform_cfg:
                     bridged["mention_patterns"] = platform_cfg["mention_patterns"]
+                if plat == Platform.DISCORD and "channel_skill_bindings" in platform_cfg:
+                    bridged["channel_skill_bindings"] = platform_cfg["channel_skill_bindings"]
                 if not bridged:
                     continue
                 plat_data = platforms_data.setdefault(plat.value, {})
@@ -542,6 +556,19 @@ def load_gateway_config() -> GatewayConfig:
                     plat_data["extra"] = extra
                 extra.update(bridged)
 
+            # Slack settings → env vars (env vars take precedence)
+            slack_cfg = yaml_cfg.get("slack", {})
+            if isinstance(slack_cfg, dict):
+                if "require_mention" in slack_cfg and not os.getenv("SLACK_REQUIRE_MENTION"):
+                    os.environ["SLACK_REQUIRE_MENTION"] = str(slack_cfg["require_mention"]).lower()
+                if "allow_bots" in slack_cfg and not os.getenv("SLACK_ALLOW_BOTS"):
+                    os.environ["SLACK_ALLOW_BOTS"] = str(slack_cfg["allow_bots"]).lower()
+                frc = slack_cfg.get("free_response_channels")
+                if frc is not None and not os.getenv("SLACK_FREE_RESPONSE_CHANNELS"):
+                    if isinstance(frc, list):
+                        frc = ",".join(str(v) for v in frc)
+                    os.environ["SLACK_FREE_RESPONSE_CHANNELS"] = str(frc)
+
             # Discord settings → env vars (env vars take precedence)
             discord_cfg = yaml_cfg.get("discord", {})
             if isinstance(discord_cfg, dict):
@@ -562,6 +589,12 @@ def load_gateway_config() -> GatewayConfig:
                     if isinstance(ic, list):
                         ic = ",".join(str(v) for v in ic)
                     os.environ["DISCORD_IGNORED_CHANNELS"] = str(ic)
+                # allowed_channels: if set, bot ONLY responds in these channels (whitelist)
+                ac = discord_cfg.get("allowed_channels")
+                if ac is not None and not os.getenv("DISCORD_ALLOWED_CHANNELS"):
+                    if isinstance(ac, list):
+                        ac = ",".join(str(v) for v in ac)
+                    os.environ["DISCORD_ALLOWED_CHANNELS"] = str(ac)
                 # no_thread_channels: channels where bot responds directly without creating thread
                 ntc = discord_cfg.get("no_thread_channels")
                 if ntc is not None and not os.getenv("DISCORD_NO_THREAD_CHANNELS"):
@@ -609,6 +642,8 @@ def load_gateway_config() -> GatewayConfig:
                     os.environ["MATRIX_FREE_RESPONSE_ROOMS"] = str(frc)
                 if "auto_thread" in matrix_cfg and not os.getenv("MATRIX_AUTO_THREAD"):
                     os.environ["MATRIX_AUTO_THREAD"] = str(matrix_cfg["auto_thread"]).lower()
+                if "dm_mention_threads" in matrix_cfg and not os.getenv("MATRIX_DM_MENTION_THREADS"):
+                    os.environ["MATRIX_DM_MENTION_THREADS"] = str(matrix_cfg["dm_mention_threads"]).lower()
 
     except Exception as e:
         logger.warning(
@@ -647,6 +682,7 @@ def load_gateway_config() -> GatewayConfig:
         Platform.SLACK: "SLACK_BOT_TOKEN",
         Platform.MATTERMOST: "MATTERMOST_TOKEN",
         Platform.MATRIX: "MATRIX_ACCESS_TOKEN",
+        Platform.WEIXIN: "WEIXIN_TOKEN",
     }
     for platform, pconfig in config.platforms.items():
         if not pconfig.enabled:
@@ -882,6 +918,9 @@ def _apply_env_overrides(config: GatewayConfig) -> None:
                 pass
         if api_server_host:
             config.platforms[Platform.API_SERVER].extra["host"] = api_server_host
+        api_server_model_name = os.getenv("API_SERVER_MODEL_NAME", "")
+        if api_server_model_name:
+            config.platforms[Platform.API_SERVER].extra["model_name"] = api_server_model_name
 
     # Webhook platform
     webhook_enabled = os.getenv("WEBHOOK_ENABLED", "").lower() in ("true", "1", "yes")
@@ -948,6 +987,67 @@ def _apply_env_overrides(config: GatewayConfig) -> None:
                 name=os.getenv("WECOM_HOME_CHANNEL_NAME", "Home"),
             )
 
+    # Weixin (personal WeChat via iLink Bot API)
+    weixin_token = os.getenv("WEIXIN_TOKEN")
+    weixin_account_id = os.getenv("WEIXIN_ACCOUNT_ID")
+    if weixin_token or weixin_account_id:
+        if Platform.WEIXIN not in config.platforms:
+            config.platforms[Platform.WEIXIN] = PlatformConfig()
+        config.platforms[Platform.WEIXIN].enabled = True
+        if weixin_token:
+            config.platforms[Platform.WEIXIN].token = weixin_token
+        extra = config.platforms[Platform.WEIXIN].extra
+        if weixin_account_id:
+            extra["account_id"] = weixin_account_id
+        weixin_base_url = os.getenv("WEIXIN_BASE_URL", "").strip()
+        if weixin_base_url:
+            extra["base_url"] = weixin_base_url.rstrip("/")
+        weixin_cdn_base_url = os.getenv("WEIXIN_CDN_BASE_URL", "").strip()
+        if weixin_cdn_base_url:
+            extra["cdn_base_url"] = weixin_cdn_base_url.rstrip("/")
+        weixin_dm_policy = os.getenv("WEIXIN_DM_POLICY", "").strip().lower()
+        if weixin_dm_policy:
+            extra["dm_policy"] = weixin_dm_policy
+        weixin_group_policy = os.getenv("WEIXIN_GROUP_POLICY", "").strip().lower()
+        if weixin_group_policy:
+            extra["group_policy"] = weixin_group_policy
+        weixin_allowed_users = os.getenv("WEIXIN_ALLOWED_USERS", "").strip()
+        if weixin_allowed_users:
+            extra["allow_from"] = weixin_allowed_users
+        weixin_group_allowed_users = os.getenv("WEIXIN_GROUP_ALLOWED_USERS", "").strip()
+        if weixin_group_allowed_users:
+            extra["group_allow_from"] = weixin_group_allowed_users
+        weixin_home = os.getenv("WEIXIN_HOME_CHANNEL", "").strip()
+        if weixin_home:
+            config.platforms[Platform.WEIXIN].home_channel = HomeChannel(
+                platform=Platform.WEIXIN,
+                chat_id=weixin_home,
+                name=os.getenv("WEIXIN_HOME_CHANNEL_NAME", "Home"),
+            )
+
+    # BlueBubbles (iMessage)
+    bluebubbles_server_url = os.getenv("BLUEBUBBLES_SERVER_URL")
+    bluebubbles_password = os.getenv("BLUEBUBBLES_PASSWORD")
+    if bluebubbles_server_url and bluebubbles_password:
+        if Platform.BLUEBUBBLES not in config.platforms:
+            config.platforms[Platform.BLUEBUBBLES] = PlatformConfig()
+        config.platforms[Platform.BLUEBUBBLES].enabled = True
+        config.platforms[Platform.BLUEBUBBLES].extra.update({
+            "server_url": bluebubbles_server_url.rstrip("/"),
+            "password": bluebubbles_password,
+            "webhook_host": os.getenv("BLUEBUBBLES_WEBHOOK_HOST", "127.0.0.1"),
+            "webhook_port": int(os.getenv("BLUEBUBBLES_WEBHOOK_PORT", "8645")),
+            "webhook_path": os.getenv("BLUEBUBBLES_WEBHOOK_PATH", "/bluebubbles-webhook"),
+            "send_read_receipts": os.getenv("BLUEBUBBLES_SEND_READ_RECEIPTS", "true").lower() in ("true", "1", "yes"),
+        })
+    bluebubbles_home = os.getenv("BLUEBUBBLES_HOME_CHANNEL")
+    if bluebubbles_home and Platform.BLUEBUBBLES in config.platforms:
+        config.platforms[Platform.BLUEBUBBLES].home_channel = HomeChannel(
+            platform=Platform.BLUEBUBBLES,
+            chat_id=bluebubbles_home,
+            name=os.getenv("BLUEBUBBLES_HOME_CHANNEL_NAME", "Home"),
+        )
+
     # Session settings
     idle_minutes = os.getenv("SESSION_IDLE_MINUTES")
     if idle_minutes:

gateway/delivery.py

@@ -124,53 +124,6 @@ class DeliveryRouter:
         self.adapters = adapters or {}
         self.output_dir = get_hermes_home() / "cron" / "output"
     
-    def resolve_targets(
-        self,
-        deliver: Union[str, List[str]],
-        origin: Optional[SessionSource] = None
-    ) -> List[DeliveryTarget]:
-        """
-        Resolve delivery specification to concrete targets.
-        
-        Args:
-            deliver: Delivery spec - "origin", "telegram", ["local", "discord"], etc.
-            origin: The source where the request originated (for "origin" target)
-        
-        Returns:
-            List of resolved delivery targets
-        """
-        if isinstance(deliver, str):
-            deliver = [deliver]
-        
-        targets = []
-        seen_platforms = set()
-        
-        for target_str in deliver:
-            target = DeliveryTarget.parse(target_str, origin)
-            
-            # Resolve home channel if needed
-            if target.chat_id is None and target.platform != Platform.LOCAL:
-                home = self.config.get_home_channel(target.platform)
-                if home:
-                    target.chat_id = home.chat_id
-                else:
-                    # No home channel configured, skip this platform
-                    continue
-            
-            # Deduplicate
-            key = (target.platform, target.chat_id, target.thread_id)
-            if key not in seen_platforms:
-                seen_platforms.add(key)
-                targets.append(target)
-        
-        # Always include local if configured
-        if self.config.always_log_local:
-            local_key = (Platform.LOCAL, None, None)
-            if local_key not in seen_platforms:
-                targets.append(DeliveryTarget(platform=Platform.LOCAL))
-        
-        return targets
-    
     async def deliver(
         self,
         content: str,
@@ -299,19 +252,5 @@ class DeliveryRouter:
         return await adapter.send(target.chat_id, content, metadata=send_metadata or None)
 
 
-def parse_deliver_spec(
-    deliver: Optional[Union[str, List[str]]],
-    origin: Optional[SessionSource] = None,
-    default: str = "origin"
-) -> Union[str, List[str]]:
-    """
-    Normalize a delivery specification.
-    
-    If None or empty, returns the default.
-    """
-    if not deliver:
-        return default
-    return deliver
-
 
 

gateway/platforms/api_server.py

@@ -20,10 +20,13 @@ Requires:
 """
 
 import asyncio
+import hashlib
 import hmac
 import json
 import logging
 import os
+import socket as _socket
+import re
 import sqlite3
 import time
 import uuid
@@ -40,6 +43,7 @@ from gateway.config import Platform, PlatformConfig
 from gateway.platforms.base import (
     BasePlatformAdapter,
     SendResult,
+    is_network_accessible,
 )
 
 logger = logging.getLogger(__name__)
@@ -282,6 +286,24 @@ def _make_request_fingerprint(body: Dict[str, Any], keys: List[str]) -> str:
     return sha256(repr(subset).encode("utf-8")).hexdigest()
 
 
+def _derive_chat_session_id(
+    system_prompt: Optional[str],
+    first_user_message: str,
+) -> str:
+    """Derive a stable session ID from the conversation's first user message.
+
+    OpenAI-compatible frontends (Open WebUI, LibreChat, etc.) send the full
+    conversation history with every request.  The system prompt and first user
+    message are constant across all turns of the same conversation, so hashing
+    them produces a deterministic session ID that lets the API server reuse
+    the same Hermes session (and therefore the same Docker container sandbox
+    directory) across turns.
+    """
+    seed = f"{system_prompt or ''}\n{first_user_message}"
+    digest = hashlib.sha256(seed.encode("utf-8")).hexdigest()[:16]
+    return f"api-{digest}"
+
+
 class APIServerAdapter(BasePlatformAdapter):
     """
     OpenAI-compatible HTTP API server adapter.
@@ -299,6 +321,9 @@ class APIServerAdapter(BasePlatformAdapter):
         self._cors_origins: tuple[str, ...] = self._parse_cors_origins(
             extra.get("cors_origins", os.getenv("API_SERVER_CORS_ORIGINS", "")),
         )
+        self._model_name: str = self._resolve_model_name(
+            extra.get("model_name", os.getenv("API_SERVER_MODEL_NAME", "")),
+        )
         self._app: Optional["web.Application"] = None
         self._runner: Optional["web.AppRunner"] = None
         self._site: Optional["web.TCPSite"] = None
@@ -324,6 +349,26 @@ class APIServerAdapter(BasePlatformAdapter):
 
         return tuple(str(item).strip() for item in items if str(item).strip())
 
+    @staticmethod
+    def _resolve_model_name(explicit: str) -> str:
+        """Derive the advertised model name for /v1/models.
+
+        Priority:
+        1. Explicit override (config extra or API_SERVER_MODEL_NAME env var)
+        2. Active profile name (so each profile advertises a distinct model)
+        3. Fallback: "hermes-agent"
+        """
+        if explicit and explicit.strip():
+            return explicit.strip()
+        try:
+            from hermes_cli.profiles import get_active_profile_name
+            profile = get_active_profile_name()
+            if profile and profile not in ("default", "custom"):
+                return profile
+        except Exception:
+            pass
+        return "hermes-agent"
+
     def _cors_headers_for_origin(self, origin: str) -> Optional[Dict[str, str]]:
         """Return CORS headers for an allowed browser origin."""
         if not origin or not self._cors_origins:
@@ -363,7 +408,8 @@ class APIServerAdapter(BasePlatformAdapter):
         Validate Bearer token from Authorization header.
 
         Returns None if auth is OK, or a 401 web.Response on failure.
-        If no API key is configured, all requests are allowed.
+        If no API key is configured, all requests are allowed (only when API
+        server is local).
         """
         if not self._api_key:
             return None  # No key configured — allow all (local-only use)
@@ -468,12 +514,12 @@ class APIServerAdapter(BasePlatformAdapter):
             "object": "list",
             "data": [
                 {
-                    "id": "hermes-agent",
+                    "id": self._model_name,
                     "object": "model",
                     "created": int(time.time()),
                     "owned_by": "hermes",
                     "permission": [],
-                    "root": "hermes-agent",
+                    "root": self._model_name,
                     "parent": None,
                 }
             ],
@@ -531,8 +577,32 @@ class APIServerAdapter(BasePlatformAdapter):
 
         # Allow caller to continue an existing session by passing X-Hermes-Session-Id.
         # When provided, history is loaded from state.db instead of from the request body.
+        #
+        # Security: session continuation exposes conversation history, so it is
+        # only allowed when the API key is configured and the request is
+        # authenticated.  Without this gate, any unauthenticated client could
+        # read arbitrary session history by guessing/enumerating session IDs.
         provided_session_id = request.headers.get("X-Hermes-Session-Id", "").strip()
         if provided_session_id:
+            if not self._api_key:
+                logger.warning(
+                    "Session continuation via X-Hermes-Session-Id rejected: "
+                    "no API key configured.  Set API_SERVER_KEY to enable "
+                    "session continuity."
+                )
+                return web.json_response(
+                    _openai_error(
+                        "Session continuation requires API key authentication. "
+                        "Configure API_SERVER_KEY to enable this feature."
+                    ),
+                    status=403,
+                )
+            # Sanitize: reject control characters that could enable header injection.
+            if re.search(r'[\r\n\x00]', provided_session_id):
+                return web.json_response(
+                    {"error": {"message": "Invalid session ID", "type": "invalid_request_error"}},
+                    status=400,
+                )
             session_id = provided_session_id
             try:
                 db = self._ensure_session_db()
@@ -542,11 +612,20 @@ class APIServerAdapter(BasePlatformAdapter):
                 logger.warning("Failed to load session history for %s: %s", session_id, e)
                 history = []
         else:
-            session_id = str(uuid.uuid4())
+            # Derive a stable session ID from the conversation fingerprint so
+            # that consecutive messages from the same Open WebUI (or similar)
+            # conversation map to the same Hermes session.  The first user
+            # message + system prompt are constant across all turns.
+            first_user = ""
+            for cm in conversation_messages:
+                if cm.get("role") == "user":
+                    first_user = cm.get("content", "")
+                    break
+            session_id = _derive_chat_session_id(system_prompt, first_user)
             # history already set from request body above
 
         completion_id = f"chatcmpl-{uuid.uuid4().hex[:29]}"
-        model_name = body.get("model", "hermes-agent")
+        model_name = body.get("model", self._model_name)
         created = int(time.time())
 
         if stream:
@@ -565,15 +644,35 @@ class APIServerAdapter(BasePlatformAdapter):
                     _stream_q.put(delta)
 
             def _on_tool_progress(event_type, name, preview, args, **kwargs):
-                """Inject tool progress into the SSE stream for Open WebUI."""
+                """Send tool progress as a separate SSE event.
+
+                Previously, progress markers like ``⏰ list`` were injected
+                directly into ``delta.content``.  OpenAI-compatible frontends
+                (Open WebUI, LobeChat, …) store ``delta.content`` verbatim as
+                the assistant message and send it back on subsequent requests.
+                After enough turns the model learns to *emit* the markers as
+                plain text instead of issuing real tool calls — silently
+                hallucinating tool results.  See #6972.
+
+                The fix: push a tagged tuple ``("__tool_progress__", payload)``
+                onto the stream queue.  The SSE writer emits it as a custom
+                ``event: hermes.tool.progress`` line that compliant frontends
+                can render for UX but will *not* persist into conversation
+                history.  Clients that don't understand the custom event type
+                silently ignore it per the SSE specification.
+                """
                 if event_type != "tool.started":
-                    return  # Only show tool start events in chat stream
+                    return
                 if name.startswith("_"):
-                    return  # Skip internal events (_thinking)
+                    return
                 from agent.display import get_tool_emoji
                 emoji = get_tool_emoji(name)
                 label = preview or name
-                _stream_q.put(f"\n`{emoji} {label}`\n")
+                _stream_q.put(("__tool_progress__", {
+                    "tool": name,
+                    "emoji": emoji,
+                    "label": label,
+                }))
 
             # Start agent in background.  agent_ref is a mutable container
             # so the SSE writer can interrupt the agent on client disconnect.
@@ -684,6 +783,29 @@ class APIServerAdapter(BasePlatformAdapter):
             }
             await response.write(f"data: {json.dumps(role_chunk)}\n\n".encode())
 
+            # Helper — route a queue item to the correct SSE event.
+            async def _emit(item):
+                """Write a single queue item to the SSE stream.
+
+                Plain strings are sent as normal ``delta.content`` chunks.
+                Tagged tuples ``("__tool_progress__", payload)`` are sent
+                as a custom ``event: hermes.tool.progress`` SSE event so
+                frontends can display them without storing the markers in
+                conversation history.  See #6972.
+                """
+                if isinstance(item, tuple) and len(item) == 2 and item[0] == "__tool_progress__":
+                    event_data = json.dumps(item[1])
+                    await response.write(
+                        f"event: hermes.tool.progress\ndata: {event_data}\n\n".encode()
+                    )
+                else:
+                    content_chunk = {
+                        "id": completion_id, "object": "chat.completion.chunk",
+                        "created": created, "model": model,
+                        "choices": [{"index": 0, "delta": {"content": item}, "finish_reason": None}],
+                    }
+                    await response.write(f"data: {json.dumps(content_chunk)}\n\n".encode())
+
             # Stream content chunks as they arrive from the agent
             loop = asyncio.get_event_loop()
             while True:
@@ -697,12 +819,7 @@ class APIServerAdapter(BasePlatformAdapter):
                                 delta = stream_q.get_nowait()
                                 if delta is None:
                                     break
-                                content_chunk = {
-                                    "id": completion_id, "object": "chat.completion.chunk",
-                                    "created": created, "model": model,
-                                    "choices": [{"index": 0, "delta": {"content": delta}, "finish_reason": None}],
-                                }
-                                await response.write(f"data: {json.dumps(content_chunk)}\n\n".encode())
+                                await _emit(delta)
                             except _q.Empty:
                                 break
                         break
@@ -711,12 +828,7 @@ class APIServerAdapter(BasePlatformAdapter):
                 if delta is None:  # End of stream sentinel
                     break
 
-                content_chunk = {
-                    "id": completion_id, "object": "chat.completion.chunk",
-                    "created": created, "model": model,
-                    "choices": [{"index": 0, "delta": {"content": delta}, "finish_reason": None}],
-                }
-                await response.write(f"data: {json.dumps(content_chunk)}\n\n".encode())
+                await _emit(delta)
 
             # Get usage from completed agent
             usage = {"input_tokens": 0, "output_tokens": 0, "total_tokens": 0}
@@ -923,7 +1035,7 @@ class APIServerAdapter(BasePlatformAdapter):
             "object": "response",
             "status": "completed",
             "created_at": created_at,
-            "model": body.get("model", "hermes-agent"),
+            "model": body.get("model", self._model_name),
             "output": output_items,
             "usage": {
                 "input_tokens": usage.get("input_tokens", 0),
@@ -1318,6 +1430,7 @@ class APIServerAdapter(BasePlatformAdapter):
             result = agent.run_conversation(
                 user_message=user_message,
                 conversation_history=conversation_history,
+                task_id="default",
             )
             usage = {
                 "input_tokens": getattr(agent, "session_prompt_tokens", 0) or 0,
@@ -1484,6 +1597,7 @@ class APIServerAdapter(BasePlatformAdapter):
                     r = agent.run_conversation(
                         user_message=user_message,
                         conversation_history=conversation_history,
+                        task_id="default",
                     )
                     u = {
                         "input_tokens": getattr(agent, "session_prompt_tokens", 0) or 0,
@@ -1635,8 +1749,16 @@ class APIServerAdapter(BasePlatformAdapter):
             if hasattr(sweep_task, "add_done_callback"):
                 sweep_task.add_done_callback(self._background_tasks.discard)
 
+            # Refuse to start network-accessible without authentication
+            if is_network_accessible(self._host) and not self._api_key:
+                logger.error(
+                    "[%s] Refusing to start: binding to %s requires API_SERVER_KEY. "
+                    "Set API_SERVER_KEY or use the default 127.0.0.1.",
+                    self.name, self._host,
+                )
+                return False
+
             # Port conflict detection — fail fast if port is already in use
-            import socket as _socket
             try:
                 with _socket.socket(_socket.AF_INET, _socket.SOCK_STREAM) as _s:
                     _s.settimeout(1)
@@ -1652,9 +1774,17 @@ class APIServerAdapter(BasePlatformAdapter):
             await self._site.start()
 
             self._mark_connected()
+            if not self._api_key:
+                logger.warning(
+                    "[%s] ⚠️  No API key configured (API_SERVER_KEY / platforms.api_server.key). "
+                    "All requests will be accepted without authentication. "
+                    "Set an API key for production deployments to prevent "
+                    "unauthorized access to sessions, responses, and cron jobs.",
+                    self.name,
+                )
             logger.info(
-                "[%s] API server listening on http://%s:%d",
-                self.name, self._host, self._port,
+                "[%s] API server listening on http://%s:%d (model: %s)",
+                self.name, self._host, self._port, self._model_name,
             )
             return True
 

gateway/platforms/base.py

@@ -6,22 +6,183 @@ and implement the required methods.
 """
 
 import asyncio
+import ipaddress
 import logging
 import os
 import random
 import re
+import socket as _socket
+import subprocess
+import sys
 import uuid
 from abc import ABC, abstractmethod
 from urllib.parse import urlsplit
 
 logger = logging.getLogger(__name__)
+
+
+def is_network_accessible(host: str) -> bool:
+    """Return True if *host* would expose the server beyond loopback.
+
+    Loopback addresses (127.0.0.1, ::1, IPv4-mapped ::ffff:127.0.0.1)
+    are local-only.  Unspecified addresses (0.0.0.0, ::) bind all
+    interfaces.  Hostnames are resolved; DNS failure fails closed.
+    """
+    try:
+        addr = ipaddress.ip_address(host)
+        if addr.is_loopback:
+            return False
+        # ::ffff:127.0.0.1 — Python reports is_loopback=False for mapped
+        # addresses, so check the underlying IPv4 explicitly.
+        if getattr(addr, "ipv4_mapped", None) and addr.ipv4_mapped.is_loopback:
+            return False
+        return True
+    except ValueError:
+        # when host variable is a hostname, we should try to resolve below
+        pass
+
+    try:
+        resolved = _socket.getaddrinfo(
+            host, None, _socket.AF_UNSPEC, _socket.SOCK_STREAM,
+        )
+        # if the hostname resolves into at least one non-loopback address,
+        # then we consider it to be network accessible
+        for _family, _type, _proto, _canonname, sockaddr in resolved:
+            addr = ipaddress.ip_address(sockaddr[0])
+            if not addr.is_loopback:
+                return True
+        return False
+    except (_socket.gaierror, OSError):
+        return True
+
+
+def _detect_macos_system_proxy() -> str | None:
+    """Read the macOS system HTTP(S) proxy via ``scutil --proxy``.
+
+    Returns an ``http://host:port`` URL string if an HTTP or HTTPS proxy is
+    enabled, otherwise *None*.  Falls back silently on non-macOS or on any
+    subprocess error.
+    """
+    if sys.platform != "darwin":
+        return None
+    try:
+        out = subprocess.check_output(
+            ["scutil", "--proxy"], timeout=3, text=True, stderr=subprocess.DEVNULL,
+        )
+    except Exception:
+        return None
+
+    props: dict[str, str] = {}
+    for line in out.splitlines():
+        line = line.strip()
+        if " : " in line:
+            key, _, val = line.partition(" : ")
+            props[key.strip()] = val.strip()
+
+    # Prefer HTTPS, fall back to HTTP
+    for enable_key, host_key, port_key in (
+        ("HTTPSEnable", "HTTPSProxy", "HTTPSPort"),
+        ("HTTPEnable", "HTTPProxy", "HTTPPort"),
+    ):
+        if props.get(enable_key) == "1":
+            host = props.get(host_key)
+            port = props.get(port_key)
+            if host and port:
+                return f"http://{host}:{port}"
+    return None
+
+
+def resolve_proxy_url(platform_env_var: str | None = None) -> str | None:
+    """Return a proxy URL from env vars, or macOS system proxy.
+
+    Check order:
+      0. *platform_env_var* (e.g. ``DISCORD_PROXY``) — highest priority
+      1. HTTPS_PROXY / HTTP_PROXY / ALL_PROXY (and lowercase variants)
+      2. macOS system proxy via ``scutil --proxy`` (auto-detect)
+
+    Returns *None* if no proxy is found.
+    """
+    if platform_env_var:
+        value = (os.environ.get(platform_env_var) or "").strip()
+        if value:
+            return value
+    for key in ("HTTPS_PROXY", "HTTP_PROXY", "ALL_PROXY",
+                "https_proxy", "http_proxy", "all_proxy"):
+        value = (os.environ.get(key) or "").strip()
+        if value:
+            return value
+    return _detect_macos_system_proxy()
+
+
+def proxy_kwargs_for_bot(proxy_url: str | None) -> dict:
+    """Build kwargs for ``commands.Bot()`` / ``discord.Client()`` with proxy.
+
+    Returns:
+      - SOCKS URL  → ``{"connector": ProxyConnector(..., rdns=True)}``
+      - HTTP URL   → ``{"proxy": url}``
+      - *None*     → ``{}``
+
+    ``rdns=True`` forces remote DNS resolution through the proxy — required
+    by many SOCKS implementations (Shadowrocket, Clash) and essential for
+    bypassing DNS pollution behind the GFW.
+    """
+    if not proxy_url:
+        return {}
+    if proxy_url.lower().startswith("socks"):
+        try:
+            from aiohttp_socks import ProxyConnector
+
+            connector = ProxyConnector.from_url(proxy_url, rdns=True)
+            return {"connector": connector}
+        except ImportError:
+            logger.warning(
+                "aiohttp_socks not installed — SOCKS proxy %s ignored. "
+                "Run: pip install aiohttp-socks",
+                proxy_url,
+            )
+            return {}
+    return {"proxy": proxy_url}
+
+
+def proxy_kwargs_for_aiohttp(proxy_url: str | None) -> tuple[dict, dict]:
+    """Build kwargs for standalone ``aiohttp.ClientSession`` with proxy.
+
+    Returns ``(session_kwargs, request_kwargs)`` where:
+      - SOCKS → ``({"connector": ProxyConnector(...)}, {})``
+      - HTTP  → ``({}, {"proxy": url})``
+      - None  → ``({}, {})``
+
+    Usage::
+
+        sess_kw, req_kw = proxy_kwargs_for_aiohttp(proxy_url)
+        async with aiohttp.ClientSession(**sess_kw) as session:
+            async with session.get(url, **req_kw) as resp:
+                ...
+    """
+    if not proxy_url:
+        return {}, {}
+    if proxy_url.lower().startswith("socks"):
+        try:
+            from aiohttp_socks import ProxyConnector
+
+            connector = ProxyConnector.from_url(proxy_url, rdns=True)
+            return {"connector": connector}, {}
+        except ImportError:
+            logger.warning(
+                "aiohttp_socks not installed — SOCKS proxy %s ignored. "
+                "Run: pip install aiohttp-socks",
+                proxy_url,
+            )
+            return {}, {}
+    return {}, {"proxy": proxy_url}
+
+
 from dataclasses import dataclass, field
 from datetime import datetime
 from pathlib import Path
 from typing import Dict, List, Optional, Any, Callable, Awaitable, Tuple
 from enum import Enum
 
-import sys
 from pathlib import Path as _Path
 sys.path.insert(0, str(_Path(__file__).resolve().parents[2]))
 
@@ -36,7 +197,7 @@ GATEWAY_SECRET_CAPTURE_UNSUPPORTED_MESSAGE = (
 )
 
 
-def _safe_url_for_log(url: str, max_len: int = 80) -> str:
+def safe_url_for_log(url: str, max_len: int = 80) -> str:
     """Return a URL string safe for logs (no query/fragment/userinfo)."""
     if max_len <= 0:
         return ""
@@ -73,6 +234,23 @@ def _safe_url_for_log(url: str, max_len: int = 80) -> str:
     return f"{safe[:max_len - 3]}..."
 
 
+async def _ssrf_redirect_guard(response):
+    """Re-validate each redirect target to prevent redirect-based SSRF.
+
+    Without this, an attacker can host a public URL that 302-redirects to
+    http://169.254.169.254/ and bypass the pre-flight is_safe_url() check.
+
+    Must be async because httpx.AsyncClient awaits response event hooks.
+    """
+    if response.is_redirect and response.next_request:
+        redirect_url = str(response.next_request.url)
+        from tools.url_safety import is_safe_url
+        if not is_safe_url(redirect_url):
+            raise ValueError(
+                f"Blocked redirect to private/internal address: {safe_url_for_log(redirect_url)}"
+            )
+
+
 # ---------------------------------------------------------------------------
 # Image cache utilities
 #
@@ -92,6 +270,23 @@ def get_image_cache_dir() -> Path:
     return IMAGE_CACHE_DIR
 
 
+def _looks_like_image(data: bytes) -> bool:
+    """Return True if *data* starts with a known image magic-byte sequence."""
+    if len(data) < 4:
+        return False
+    if data[:8] == b"\x89PNG\r\n\x1a\n":
+        return True
+    if data[:3] == b"\xff\xd8\xff":
+        return True
+    if data[:6] in (b"GIF87a", b"GIF89a"):
+        return True
+    if data[:2] == b"BM":
+        return True
+    if data[:4] == b"RIFF" and len(data) >= 12 and data[8:12] == b"WEBP":
+        return True
+    return False
+
+
 def cache_image_from_bytes(data: bytes, ext: str = ".jpg") -> str:
     """
     Save raw image bytes to the cache and return the absolute file path.
@@ -102,7 +297,17 @@ def cache_image_from_bytes(data: bytes, ext: str = ".jpg") -> str:
 
     Returns:
         Absolute path to the cached image file as a string.
+
+    Raises:
+        ValueError: If *data* does not look like a valid image (e.g. an HTML
+            error page returned by the upstream server).
     """
+    if not _looks_like_image(data):
+        snippet = data[:80].decode("utf-8", errors="replace")
+        raise ValueError(
+            f"Refusing to cache non-image data as {ext} "
+            f"(starts with: {snippet!r})"
+        )
     cache_dir = get_image_cache_dir()
     filename = f"img_{uuid.uuid4().hex[:12]}{ext}"
     filepath = cache_dir / filename
@@ -130,7 +335,7 @@ async def cache_image_from_url(url: str, ext: str = ".jpg", retries: int = 2) ->
     """
     from tools.url_safety import is_safe_url
     if not is_safe_url(url):
-        raise ValueError(f"Blocked unsafe URL (SSRF protection): {_safe_url_for_log(url)}")
+        raise ValueError(f"Blocked unsafe URL (SSRF protection): {safe_url_for_log(url)}")
 
     import asyncio
     import httpx
@@ -138,7 +343,11 @@ async def cache_image_from_url(url: str, ext: str = ".jpg", retries: int = 2) ->
     _log = _logging.getLogger(__name__)
 
     last_exc = None
-    async with httpx.AsyncClient(timeout=30.0, follow_redirects=True) as client:
+    async with httpx.AsyncClient(
+        timeout=30.0,
+        follow_redirects=True,
+        event_hooks={"response": [_ssrf_redirect_guard]},
+    ) as client:
         for attempt in range(retries + 1):
             try:
                 response = await client.get(
@@ -160,7 +369,7 @@ async def cache_image_from_url(url: str, ext: str = ".jpg", retries: int = 2) ->
                         "Media cache retry %d/%d for %s (%.1fs): %s",
                         attempt + 1,
                         retries,
-                        _safe_url_for_log(url),
+                        safe_url_for_log(url),
                         wait,
                         exc,
                     )
@@ -245,7 +454,7 @@ async def cache_audio_from_url(url: str, ext: str = ".ogg", retries: int = 2) ->
     """
     from tools.url_safety import is_safe_url
     if not is_safe_url(url):
-        raise ValueError(f"Blocked unsafe URL (SSRF protection): {_safe_url_for_log(url)}")
+        raise ValueError(f"Blocked unsafe URL (SSRF protection): {safe_url_for_log(url)}")
 
     import asyncio
     import httpx
@@ -253,7 +462,11 @@ async def cache_audio_from_url(url: str, ext: str = ".ogg", retries: int = 2) ->
     _log = _logging.getLogger(__name__)
 
     last_exc = None
-    async with httpx.AsyncClient(timeout=30.0, follow_redirects=True) as client:
+    async with httpx.AsyncClient(
+        timeout=30.0,
+        follow_redirects=True,
+        event_hooks={"response": [_ssrf_redirect_guard]},
+    ) as client:
         for attempt in range(retries + 1):
             try:
                 response = await client.get(
@@ -275,7 +488,7 @@ async def cache_audio_from_url(url: str, ext: str = ".ogg", retries: int = 2) ->
                         "Audio cache retry %d/%d for %s (%.1fs): %s",
                         attempt + 1,
                         retries,
-                        _safe_url_for_log(url),
+                        safe_url_for_log(url),
                         wait,
                         exc,
                     )
@@ -298,6 +511,7 @@ SUPPORTED_DOCUMENT_TYPES = {
     ".pdf": "application/pdf",
     ".md": "text/markdown",
     ".txt": "text/plain",
+    ".log": "text/plain",
     ".zip": "application/zip",
     ".docx": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
     ".xlsx": "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
@@ -377,6 +591,14 @@ class MessageType(Enum):
     COMMAND = "command"  # /command style
 
 
+class ProcessingOutcome(Enum):
+    """Result classification for message-processing lifecycle hooks."""
+
+    SUCCESS = "success"
+    FAILURE = "failure"
+    CANCELLED = "cancelled"
+
+
 @dataclass
 class MessageEvent:
     """
@@ -404,9 +626,14 @@ class MessageEvent:
     reply_to_message_id: Optional[str] = None
     reply_to_text: Optional[str] = None  # Text of the replied-to message (for context injection)
     
-    # Auto-loaded skill for topic/channel bindings (e.g., Telegram DM Topics)
-    auto_skill: Optional[str] = None
+    # Auto-loaded skill(s) for topic/channel bindings (e.g., Telegram DM Topics,
+    # Discord channel_skill_bindings).  A single name or ordered list.
+    auto_skill: Optional[str | list[str]] = None
     
+    # Internal flag — set for synthetic events (e.g. background process
+    # completion notifications) that must bypass user authorization checks.
+    internal: bool = False
+
     # Timestamps
     timestamp: datetime = field(default_factory=datetime.now)
     
@@ -423,6 +650,9 @@ class MessageEvent:
         raw = parts[0][1:].lower() if parts else None
         if raw and "@" in raw:
             raw = raw.split("@", 1)[0]
+        # Reject file paths: valid command names never contain /
+        if raw and "/" in raw:
+            return None
         return raw
     
     def get_command_args(self) -> str:
@@ -443,6 +673,32 @@ class SendResult:
     retryable: bool = False  # True for transient connection errors — base will retry automatically
 
 
+def merge_pending_message_event(
+    pending_messages: Dict[str, MessageEvent],
+    session_key: str,
+    event: MessageEvent,
+) -> None:
+    """Store or merge a pending event for a session.
+
+    Photo bursts/albums often arrive as multiple near-simultaneous PHOTO
+    events. Merge those into the existing queued event so the next turn sees
+    the whole burst, while non-photo follow-ups still replace the pending
+    event normally.
+    """
+    existing = pending_messages.get(session_key)
+    if (
+        existing
+        and getattr(existing, "message_type", None) == MessageType.PHOTO
+        and event.message_type == MessageType.PHOTO
+    ):
+        existing.media_urls.extend(event.media_urls)
+        existing.media_types.extend(event.media_types)
+        if event.text:
+            existing.text = BasePlatformAdapter._merge_caption(existing.text, event.text)
+        return
+    pending_messages[session_key] = event
+
+
 # Error substrings that indicate a transient *connection* failure worth retrying.
 # "timeout" / "timed out" / "readtimeout" / "writetimeout" are intentionally
 # excluded: a read/write timeout on a non-idempotent call (e.g. send_message)
@@ -496,6 +752,8 @@ class BasePlatformAdapter(ABC):
         # Gateway shutdown cancels these so an old gateway instance doesn't keep
         # working on a task after --replace or manual restarts.
         self._background_tasks: set[asyncio.Task] = set()
+        self._expected_cancelled_tasks: set[asyncio.Task] = set()
+        self._busy_session_handler: Optional[Callable[[MessageEvent, str], Awaitable[bool]]] = None
         # Chats where auto-TTS on voice input is disabled (set by /voice off)
         self._auto_tts_disabled_chats: set = set()
         # Chats where typing indicator is paused (e.g. during approval waits).
@@ -584,6 +842,10 @@ class BasePlatformAdapter(ABC):
         an optional response string.
         """
         self._message_handler = handler
+
+    def set_busy_session_handler(self, handler: Optional[Callable[[MessageEvent, str], Awaitable[bool]]]) -> None:
+        """Set an optional handler for messages arriving during active sessions."""
+        self._busy_session_handler = handler
     
     def set_session_store(self, session_store: Any) -> None:
         """
@@ -1004,7 +1266,7 @@ class BasePlatformAdapter(ABC):
     async def on_processing_start(self, event: MessageEvent) -> None:
         """Hook called when background processing begins."""
 
-    async def on_processing_complete(self, event: MessageEvent, success: bool) -> None:
+    async def on_processing_complete(self, event: MessageEvent, outcome: ProcessingOutcome) -> None:
         """Hook called when background processing completes."""
 
     async def _run_processing_hook(self, hook_name: str, *args: Any, **kwargs: Any) -> None:
@@ -1165,7 +1427,7 @@ class BasePlatformAdapter(ABC):
             # session lifecycle and its cleanup races with the running task
             # (see PR #4926).
             cmd = event.get_command()
-            if cmd in ("approve", "deny", "status", "stop", "new", "reset"):
+            if cmd in ("approve", "deny", "status", "stop", "new", "reset", "background", "restart"):
                 logger.debug(
                     "[%s] Command '/%s' bypassing active-session guard for %s",
                     self.name, cmd, session_key,
@@ -1184,19 +1446,19 @@ class BasePlatformAdapter(ABC):
                     logger.error("[%s] Command '/%s' dispatch failed: %s", self.name, cmd, e, exc_info=True)
                 return
 
+            if self._busy_session_handler is not None:
+                try:
+                    if await self._busy_session_handler(event, session_key):
+                        return
+                except Exception as e:
+                    logger.error("[%s] Busy-session handler failed: %s", self.name, e, exc_info=True)
+
             # Special case: photo bursts/albums frequently arrive as multiple near-
             # simultaneous messages. Queue them without interrupting the active run,
             # then process them immediately after the current task finishes.
             if event.message_type == MessageType.PHOTO:
                 logger.debug("[%s] Queuing photo follow-up for session %s without interrupt", self.name, session_key)
-                existing = self._pending_messages.get(session_key)
-                if existing and existing.message_type == MessageType.PHOTO:
-                    existing.media_urls.extend(event.media_urls)
-                    existing.media_types.extend(event.media_types)
-                    if event.text:
-                        existing.text = self._merge_caption(existing.text, event.text)
-                else:
-                    self._pending_messages[session_key] = event
+                merge_pending_message_event(self._pending_messages, session_key, event)
                 return  # Don't interrupt now - will run after current task completes
 
             # Default behavior for non-photo follow-ups: interrupt the running agent
@@ -1223,6 +1485,7 @@ class BasePlatformAdapter(ABC):
             return
         if hasattr(task, "add_done_callback"):
             task.add_done_callback(self._background_tasks.discard)
+            task.add_done_callback(self._expected_cancelled_tasks.discard)
     
     @staticmethod
     def _get_human_delay() -> float:
@@ -1359,7 +1622,7 @@ class BasePlatformAdapter(ABC):
                         logger.info(
                             "[%s] Sending image: %s (alt=%s)",
                             self.name,
-                            _safe_url_for_log(image_url),
+                            safe_url_for_log(image_url),
                             alt_text[:30] if alt_text else "",
                         )
                         # Route animated GIFs through send_animation for proper playback
@@ -1451,7 +1714,11 @@ class BasePlatformAdapter(ABC):
 
             # Determine overall success for the processing hook
             processing_ok = delivery_succeeded if delivery_attempted else not bool(response)
-            await self._run_processing_hook("on_processing_complete", event, processing_ok)
+            await self._run_processing_hook(
+                "on_processing_complete",
+                event,
+                ProcessingOutcome.SUCCESS if processing_ok else ProcessingOutcome.FAILURE,
+            )
 
             # Check if there's a pending message that was queued during our processing
             if session_key in self._pending_messages:
@@ -1470,10 +1737,14 @@ class BasePlatformAdapter(ABC):
                 return  # Already cleaned up
                 
         except asyncio.CancelledError:
-            await self._run_processing_hook("on_processing_complete", event, False)
+            current_task = asyncio.current_task()
+            outcome = ProcessingOutcome.CANCELLED
+            if current_task is None or current_task not in self._expected_cancelled_tasks:
+                outcome = ProcessingOutcome.FAILURE
+            await self._run_processing_hook("on_processing_complete", event, outcome)
             raise
         except Exception as e:
-            await self._run_processing_hook("on_processing_complete", event, False)
+            await self._run_processing_hook("on_processing_complete", event, ProcessingOutcome.FAILURE)
             logger.error("[%s] Error handling message: %s", self.name, e, exc_info=True)
             # Send the error to the user so they aren't left with radio silence
             try:
@@ -1517,10 +1788,12 @@ class BasePlatformAdapter(ABC):
         """
         tasks = [task for task in self._background_tasks if not task.done()]
         for task in tasks:
+            self._expected_cancelled_tasks.add(task)
             task.cancel()
         if tasks:
             await asyncio.gather(*tasks, return_exceptions=True)
         self._background_tasks.clear()
+        self._expected_cancelled_tasks.clear()
         self._pending_messages.clear()
         self._active_sessions.clear()
 

gateway/platforms/bluebubbles.py

@@ -0,0 +1,936 @@
+"""BlueBubbles iMessage platform adapter.
+
+Uses the local BlueBubbles macOS server for outbound REST sends and inbound
+webhooks.  Supports text messaging, media attachments (images, voice, video,
+documents), tapback reactions, typing indicators, and read receipts.
+
+Architecture based on PR #5869 (benjaminsehl) with inbound attachment
+downloading from PR #4588 (YuhangLin).
+"""
+
+import asyncio
+import json
+import logging
+import os
+import re
+import uuid
+from datetime import datetime
+from typing import Any, Dict, List, Optional
+from urllib.parse import quote
+
+import httpx
+
+from gateway.config import Platform, PlatformConfig
+from gateway.platforms.base import (
+    BasePlatformAdapter,
+    MessageEvent,
+    MessageType,
+    SendResult,
+    cache_image_from_bytes,
+    cache_audio_from_bytes,
+    cache_document_from_bytes,
+)
+
+logger = logging.getLogger(__name__)
+
+# ---------------------------------------------------------------------------
+# Constants
+# ---------------------------------------------------------------------------
+
+DEFAULT_WEBHOOK_HOST = "127.0.0.1"
+DEFAULT_WEBHOOK_PORT = 8645
+DEFAULT_WEBHOOK_PATH = "/bluebubbles-webhook"
+MAX_TEXT_LENGTH = 4000
+
+# Tapback reaction codes (BlueBubbles associatedMessageType values)
+_TAPBACK_ADDED = {
+    2000: "love", 2001: "like", 2002: "dislike",
+    2003: "laugh", 2004: "emphasize", 2005: "question",
+}
+_TAPBACK_REMOVED = {
+    3000: "love", 3001: "like", 3002: "dislike",
+    3003: "laugh", 3004: "emphasize", 3005: "question",
+}
+
+# Webhook event types that carry user messages
+_MESSAGE_EVENTS = {"new-message", "message", "updated-message"}
+
+# Log redaction patterns
+_PHONE_RE = re.compile(r"\+?\d{7,15}")
+_EMAIL_RE = re.compile(r"[\w.+-]+@[\w-]+\.[\w.]+")
+
+
+def _redact(text: str) -> str:
+    """Redact phone numbers and emails from log output."""
+    text = _PHONE_RE.sub("[REDACTED]", text)
+    text = _EMAIL_RE.sub("[REDACTED]", text)
+    return text
+
+
+# ---------------------------------------------------------------------------
+# Helpers
+# ---------------------------------------------------------------------------
+
+def check_bluebubbles_requirements() -> bool:
+    try:
+        import aiohttp  # noqa: F401
+        import httpx as _httpx  # noqa: F401
+    except ImportError:
+        return False
+    return True
+
+
+def _normalize_server_url(raw: str) -> str:
+    value = (raw or "").strip()
+    if not value:
+        return ""
+    if not re.match(r"^https?://", value, flags=re.I):
+        value = f"http://{value}"
+    return value.rstrip("/")
+
+
+def _strip_markdown(text: str) -> str:
+    """Strip common markdown formatting for iMessage plain-text delivery."""
+    text = re.sub(r"\*\*(.+?)\*\*", r"\1", text, flags=re.DOTALL)
+    text = re.sub(r"\*(.+?)\*", r"\1", text, flags=re.DOTALL)
+    text = re.sub(r"__(.+?)__", r"\1", text, flags=re.DOTALL)
+    text = re.sub(r"_(.+?)_", r"\1", text, flags=re.DOTALL)
+    text = re.sub(r"```[a-zA-Z0-9_+-]*\n?", "", text)
+    text = re.sub(r"`(.+?)`", r"\1", text)
+    text = re.sub(r"^#{1,6}\s+", "", text, flags=re.MULTILINE)
+    text = re.sub(r"\[([^\]]+)\]\(([^\)]+)\)", r"\1", text)
+    text = re.sub(r"\n{3,}", "\n\n", text)
+    return text.strip()
+
+
+# ---------------------------------------------------------------------------
+# Adapter
+# ---------------------------------------------------------------------------
+
+class BlueBubblesAdapter(BasePlatformAdapter):
+    platform = Platform.BLUEBUBBLES
+    MAX_MESSAGE_LENGTH = MAX_TEXT_LENGTH
+
+    def __init__(self, config: PlatformConfig):
+        super().__init__(config, Platform.BLUEBUBBLES)
+        extra = config.extra or {}
+        self.server_url = _normalize_server_url(
+            extra.get("server_url") or os.getenv("BLUEBUBBLES_SERVER_URL", "")
+        )
+        self.password = extra.get("password") or os.getenv("BLUEBUBBLES_PASSWORD", "")
+        self.webhook_host = (
+            extra.get("webhook_host")
+            or os.getenv("BLUEBUBBLES_WEBHOOK_HOST", DEFAULT_WEBHOOK_HOST)
+        )
+        self.webhook_port = int(
+            extra.get("webhook_port")
+            or os.getenv("BLUEBUBBLES_WEBHOOK_PORT", str(DEFAULT_WEBHOOK_PORT))
+        )
+        self.webhook_path = (
+            extra.get("webhook_path")
+            or os.getenv("BLUEBUBBLES_WEBHOOK_PATH", DEFAULT_WEBHOOK_PATH)
+        )
+        if not str(self.webhook_path).startswith("/"):
+            self.webhook_path = f"/{self.webhook_path}"
+        self.send_read_receipts = bool(extra.get("send_read_receipts", True))
+        self.client: Optional[httpx.AsyncClient] = None
+        self._runner = None
+        self._private_api_enabled: Optional[bool] = None
+        self._helper_connected: bool = False
+        self._guid_cache: Dict[str, str] = {}
+
+    # ------------------------------------------------------------------
+    # API helpers
+    # ------------------------------------------------------------------
+
+    def _api_url(self, path: str) -> str:
+        sep = "&" if "?" in path else "?"
+        return f"{self.server_url}{path}{sep}password={quote(self.password, safe='')}"
+
+    async def _api_get(self, path: str) -> Dict[str, Any]:
+        assert self.client is not None
+        res = await self.client.get(self._api_url(path))
+        res.raise_for_status()
+        return res.json()
+
+    async def _api_post(self, path: str, payload: Dict[str, Any]) -> Dict[str, Any]:
+        assert self.client is not None
+        res = await self.client.post(self._api_url(path), json=payload)
+        res.raise_for_status()
+        return res.json()
+
+    # ------------------------------------------------------------------
+    # Lifecycle
+    # ------------------------------------------------------------------
+
+    async def connect(self) -> bool:
+        if not self.server_url or not self.password:
+            logger.error(
+                "[bluebubbles] BLUEBUBBLES_SERVER_URL and BLUEBUBBLES_PASSWORD are required"
+            )
+            return False
+        from aiohttp import web
+
+        self.client = httpx.AsyncClient(timeout=30.0)
+        try:
+            await self._api_get("/api/v1/ping")
+            info = await self._api_get("/api/v1/server/info")
+            server_data = (info or {}).get("data", {})
+            self._private_api_enabled = bool(server_data.get("private_api"))
+            self._helper_connected = bool(server_data.get("helper_connected"))
+            logger.info(
+                "[bluebubbles] connected to %s (private_api=%s, helper=%s)",
+                self.server_url,
+                self._private_api_enabled,
+                self._helper_connected,
+            )
+        except Exception as exc:
+            logger.error(
+                "[bluebubbles] cannot reach server at %s: %s", self.server_url, exc
+            )
+            if self.client:
+                await self.client.aclose()
+                self.client = None
+            return False
+
+        app = web.Application()
+        app.router.add_get("/health", lambda _: web.Response(text="ok"))
+        app.router.add_post(self.webhook_path, self._handle_webhook)
+        self._runner = web.AppRunner(app)
+        await self._runner.setup()
+        site = web.TCPSite(self._runner, self.webhook_host, self.webhook_port)
+        await site.start()
+        self._mark_connected()
+        logger.info(
+            "[bluebubbles] webhook listening on http://%s:%s%s",
+            self.webhook_host,
+            self.webhook_port,
+            self.webhook_path,
+        )
+
+        # Register webhook with BlueBubbles server
+        # This is required for the server to know where to send events
+        await self._register_webhook()
+
+        return True
+
+    async def disconnect(self) -> None:
+        # Unregister webhook before cleaning up
+        await self._unregister_webhook()
+
+        if self.client:
+            await self.client.aclose()
+            self.client = None
+        if self._runner:
+            await self._runner.cleanup()
+            self._runner = None
+        self._mark_disconnected()
+
+    @property
+    def _webhook_url(self) -> str:
+        """Compute the external webhook URL for BlueBubbles registration."""
+        host = self.webhook_host
+        if host in ("0.0.0.0", "127.0.0.1", "localhost", "::"):
+            host = "localhost"
+        return f"http://{host}:{self.webhook_port}{self.webhook_path}"
+
+    async def _find_registered_webhooks(self, url: str) -> list:
+        """Return list of BB webhook entries matching *url*."""
+        try:
+            res = await self._api_get("/api/v1/webhook")
+            data = res.get("data")
+            if isinstance(data, list):
+                return [wh for wh in data if wh.get("url") == url]
+        except Exception:
+            pass
+        return []
+
+    async def _register_webhook(self) -> bool:
+        """Register this webhook URL with the BlueBubbles server.
+
+        BlueBubbles requires webhooks to be registered via API before
+        it will send events.  Checks for an existing registration first
+        to avoid duplicates (e.g. after a crash without clean shutdown).
+        """
+        if not self.client:
+            return False
+
+        webhook_url = self._webhook_url
+
+        # Crash resilience — reuse an existing registration if present
+        existing = await self._find_registered_webhooks(webhook_url)
+        if existing:
+            logger.info(
+                "[bluebubbles] webhook already registered: %s", webhook_url
+            )
+            return True
+
+        payload = {
+            "url": webhook_url,
+            "events": ["new-message", "updated-message", "message"],
+        }
+
+        try:
+            res = await self._api_post("/api/v1/webhook", payload)
+            status = res.get("status", 0)
+            if 200 <= status < 300:
+                logger.info(
+                    "[bluebubbles] webhook registered with server: %s",
+                    webhook_url,
+                )
+                return True
+            else:
+                logger.warning(
+                    "[bluebubbles] webhook registration returned status %s: %s",
+                    status,
+                    res.get("message"),
+                )
+                return False
+        except Exception as exc:
+            logger.warning(
+                "[bluebubbles] failed to register webhook with server: %s",
+                exc,
+            )
+            return False
+
+    async def _unregister_webhook(self) -> bool:
+        """Unregister this webhook URL from the BlueBubbles server.
+
+        Removes *all* matching registrations to clean up any duplicates
+        left by prior crashes.
+        """
+        if not self.client:
+            return False
+
+        webhook_url = self._webhook_url
+        removed = False
+
+        try:
+            for wh in await self._find_registered_webhooks(webhook_url):
+                wh_id = wh.get("id")
+                if wh_id:
+                    res = await self.client.delete(
+                        self._api_url(f"/api/v1/webhook/{wh_id}")
+                    )
+                    res.raise_for_status()
+                    removed = True
+            if removed:
+                logger.info(
+                    "[bluebubbles] webhook unregistered: %s", webhook_url
+                )
+        except Exception as exc:
+            logger.debug(
+                "[bluebubbles] failed to unregister webhook (non-critical): %s",
+                exc,
+            )
+        return removed
+
+    # ------------------------------------------------------------------
+    # Chat GUID resolution
+    # ------------------------------------------------------------------
+
+    async def _resolve_chat_guid(self, target: str) -> Optional[str]:
+        """Resolve an email/phone to a BlueBubbles chat GUID.
+
+        If *target* already contains a semicolon (raw GUID format like
+        ``iMessage;-;user@example.com``), it is returned as-is.  Otherwise
+        the adapter queries the BlueBubbles chat list and matches on
+        ``chatIdentifier`` or participant address.
+        """
+        target = (target or "").strip()
+        if not target:
+            return None
+        # Already a raw GUID
+        if ";" in target:
+            return target
+        if target in self._guid_cache:
+            return self._guid_cache[target]
+        try:
+            payload = await self._api_post(
+                "/api/v1/chat/query",
+                {"limit": 100, "offset": 0, "with": ["participants"]},
+            )
+            for chat in payload.get("data", []) or []:
+                guid = chat.get("guid") or chat.get("chatGuid")
+                identifier = chat.get("chatIdentifier") or chat.get("identifier")
+                if identifier == target:
+                    if guid:
+                        self._guid_cache[target] = guid
+                    return guid
+                for part in chat.get("participants", []) or []:
+                    if (part.get("address") or "").strip() == target and guid:
+                        self._guid_cache[target] = guid
+                        return guid
+        except Exception:
+            pass
+        return None
+
+    async def _create_chat_for_handle(
+        self, address: str, message: str
+    ) -> SendResult:
+        """Create a new chat by sending the first message to *address*."""
+        payload = {
+            "addresses": [address],
+            "message": message,
+            "tempGuid": f"temp-{datetime.utcnow().timestamp()}",
+        }
+        try:
+            res = await self._api_post("/api/v1/chat/new", payload)
+            data = res.get("data") or {}
+            msg_id = data.get("guid") or data.get("messageGuid") or "ok"
+            return SendResult(success=True, message_id=str(msg_id), raw_response=res)
+        except Exception as exc:
+            return SendResult(success=False, error=str(exc))
+
+    # ------------------------------------------------------------------
+    # Text sending
+    # ------------------------------------------------------------------
+
+    async def send(
+        self,
+        chat_id: str,
+        content: str,
+        reply_to: Optional[str] = None,
+        metadata: Optional[Dict[str, Any]] = None,
+    ) -> SendResult:
+        text = _strip_markdown(content or "")
+        if not text:
+            return SendResult(success=False, error="BlueBubbles send requires text")
+        chunks = self.truncate_message(text, max_length=self.MAX_MESSAGE_LENGTH)
+        last = SendResult(success=True)
+        for chunk in chunks:
+            guid = await self._resolve_chat_guid(chat_id)
+            if not guid:
+                # If the target looks like an address, try creating a new chat
+                if self._private_api_enabled and (
+                    "@" in chat_id or re.match(r"^\+\d+", chat_id)
+                ):
+                    return await self._create_chat_for_handle(chat_id, chunk)
+                return SendResult(
+                    success=False,
+                    error=f"BlueBubbles chat not found for target: {chat_id}",
+                )
+            payload: Dict[str, Any] = {
+                "chatGuid": guid,
+                "tempGuid": f"temp-{datetime.utcnow().timestamp()}",
+                "message": chunk,
+            }
+            if reply_to and self._private_api_enabled and self._helper_connected:
+                payload["method"] = "private-api"
+                payload["selectedMessageGuid"] = reply_to
+                payload["partIndex"] = 0
+            try:
+                res = await self._api_post("/api/v1/message/text", payload)
+                data = res.get("data") or {}
+                msg_id = data.get("guid") or data.get("messageGuid") or "ok"
+                last = SendResult(
+                    success=True, message_id=str(msg_id), raw_response=res
+                )
+            except Exception as exc:
+                return SendResult(success=False, error=str(exc))
+        return last
+
+    # ------------------------------------------------------------------
+    # Media sending (outbound)
+    # ------------------------------------------------------------------
+
+    async def _send_attachment(
+        self,
+        chat_id: str,
+        file_path: str,
+        filename: Optional[str] = None,
+        caption: Optional[str] = None,
+        is_audio_message: bool = False,
+    ) -> SendResult:
+        """Send a file attachment via BlueBubbles multipart upload."""
+        if not self.client:
+            return SendResult(success=False, error="Not connected")
+        if not os.path.isfile(file_path):
+            return SendResult(success=False, error=f"File not found: {file_path}")
+
+        guid = await self._resolve_chat_guid(chat_id)
+        if not guid:
+            return SendResult(success=False, error=f"Chat not found: {chat_id}")
+
+        fname = filename or os.path.basename(file_path)
+        try:
+            with open(file_path, "rb") as f:
+                files = {"attachment": (fname, f, "application/octet-stream")}
+                data: Dict[str, str] = {
+                    "chatGuid": guid,
+                    "name": fname,
+                    "tempGuid": uuid.uuid4().hex,
+                }
+                if is_audio_message:
+                    data["isAudioMessage"] = "true"
+                res = await self.client.post(
+                    self._api_url("/api/v1/message/attachment"),
+                    files=files,
+                    data=data,
+                    timeout=120,
+                )
+                res.raise_for_status()
+                result = res.json()
+
+            if caption:
+                await self.send(chat_id, caption)
+
+            if result.get("status") == 200:
+                rdata = result.get("data") or {}
+                msg_id = rdata.get("guid") if isinstance(rdata, dict) else None
+                return SendResult(
+                    success=True, message_id=msg_id, raw_response=result
+                )
+            return SendResult(
+                success=False,
+                error=result.get("message", "Attachment upload failed"),
+            )
+        except Exception as e:
+            return SendResult(success=False, error=str(e))
+
+    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:
+        try:
+            from gateway.platforms.base import cache_image_from_url
+
+            local_path = await cache_image_from_url(image_url)
+            return await self._send_attachment(chat_id, local_path, caption=caption)
+        except Exception:
+            return await super().send_image(chat_id, image_url, caption, reply_to)
+
+    async def send_image_file(
+        self,
+        chat_id: str,
+        image_path: str,
+        caption: Optional[str] = None,
+        reply_to: Optional[str] = None,
+        **kwargs,
+    ) -> SendResult:
+        return await self._send_attachment(chat_id, image_path, caption=caption)
+
+    async def send_voice(
+        self,
+        chat_id: str,
+        audio_path: str,
+        caption: Optional[str] = None,
+        reply_to: Optional[str] = None,
+        **kwargs,
+    ) -> SendResult:
+        return await self._send_attachment(
+            chat_id, audio_path, caption=caption, is_audio_message=True
+        )
+
+    async def send_video(
+        self,
+        chat_id: str,
+        video_path: str,
+        caption: Optional[str] = None,
+        reply_to: Optional[str] = None,
+        **kwargs,
+    ) -> SendResult:
+        return await self._send_attachment(chat_id, video_path, caption=caption)
+
+    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:
+        return await self._send_attachment(
+            chat_id, file_path, filename=file_name, caption=caption
+        )
+
+    async def send_animation(
+        self,
+        chat_id: str,
+        animation_url: str,
+        caption: Optional[str] = None,
+        reply_to: Optional[str] = None,
+        metadata: Optional[Dict[str, Any]] = None,
+    ) -> SendResult:
+        return await self.send_image(
+            chat_id, animation_url, caption, reply_to, metadata
+        )
+
+    # ------------------------------------------------------------------
+    # Typing indicators
+    # ------------------------------------------------------------------
+
+    async def send_typing(self, chat_id: str, metadata=None) -> None:
+        if not self._private_api_enabled or not self._helper_connected or not self.client:
+            return
+        try:
+            guid = await self._resolve_chat_guid(chat_id)
+            if guid:
+                encoded = quote(guid, safe="")
+                await self.client.post(
+                    self._api_url(f"/api/v1/chat/{encoded}/typing"), timeout=5
+                )
+        except Exception:
+            pass
+
+    async def stop_typing(self, chat_id: str) -> None:
+        if not self._private_api_enabled or not self._helper_connected or not self.client:
+            return
+        try:
+            guid = await self._resolve_chat_guid(chat_id)
+            if guid:
+                encoded = quote(guid, safe="")
+                await self.client.delete(
+                    self._api_url(f"/api/v1/chat/{encoded}/typing"), timeout=5
+                )
+        except Exception:
+            pass
+
+    # ------------------------------------------------------------------
+    # Read receipts
+    # ------------------------------------------------------------------
+
+    async def mark_read(self, chat_id: str) -> bool:
+        if not self._private_api_enabled or not self._helper_connected or not self.client:
+            return False
+        try:
+            guid = await self._resolve_chat_guid(chat_id)
+            if guid:
+                encoded = quote(guid, safe="")
+                await self.client.post(
+                    self._api_url(f"/api/v1/chat/{encoded}/read"), timeout=5
+                )
+                return True
+        except Exception:
+            pass
+        return False
+
+    # ------------------------------------------------------------------
+    # Tapback reactions
+    # ------------------------------------------------------------------
+
+    async def send_reaction(
+        self,
+        chat_id: str,
+        message_guid: str,
+        reaction: str,
+        part_index: int = 0,
+    ) -> SendResult:
+        """Send a tapback reaction (requires Private API helper)."""
+        if not self._private_api_enabled or not self._helper_connected:
+            return SendResult(
+                success=False, error="Private API helper not connected"
+            )
+        guid = await self._resolve_chat_guid(chat_id)
+        if not guid:
+            return SendResult(success=False, error=f"Chat not found: {chat_id}")
+        try:
+            res = await self._api_post(
+                "/api/v1/message/react",
+                {
+                    "chatGuid": guid,
+                    "selectedMessageGuid": message_guid,
+                    "reaction": reaction,
+                    "partIndex": part_index,
+                },
+            )
+            return SendResult(success=True, raw_response=res)
+        except Exception as exc:
+            return SendResult(success=False, error=str(exc))
+
+    # ------------------------------------------------------------------
+    # Chat info
+    # ------------------------------------------------------------------
+
+    async def get_chat_info(self, chat_id: str) -> Dict[str, Any]:
+        is_group = ";+;" in (chat_id or "")
+        info: Dict[str, Any] = {
+            "name": chat_id,
+            "type": "group" if is_group else "dm",
+        }
+        try:
+            guid = await self._resolve_chat_guid(chat_id)
+            if guid:
+                encoded = quote(guid, safe="")
+                res = await self._api_get(
+                    f"/api/v1/chat/{encoded}?with=participants"
+                )
+                data = (res or {}).get("data", {})
+                display_name = (
+                    data.get("displayName")
+                    or data.get("chatIdentifier")
+                    or chat_id
+                )
+                participants = []
+                for p in data.get("participants", []) or []:
+                    addr = (p.get("address") or "").strip()
+                    if addr:
+                        participants.append(addr)
+                info["name"] = display_name
+                if participants:
+                    info["participants"] = participants
+        except Exception:
+            pass
+        return info
+
+    def format_message(self, content: str) -> str:
+        return _strip_markdown(content)
+
+    # ------------------------------------------------------------------
+    # Inbound attachment downloading (from #4588)
+    # ------------------------------------------------------------------
+
+    async def _download_attachment(
+        self, att_guid: str, att_meta: Dict[str, Any]
+    ) -> Optional[str]:
+        """Download an attachment from BlueBubbles and cache it locally.
+
+        Returns the local file path on success, None on failure.
+        """
+        if not self.client:
+            return None
+        try:
+            encoded = quote(att_guid, safe="")
+            resp = await self.client.get(
+                self._api_url(f"/api/v1/attachment/{encoded}/download"),
+                timeout=60,
+                follow_redirects=True,
+            )
+            resp.raise_for_status()
+            data = resp.content
+
+            mime = (att_meta.get("mimeType") or "").lower()
+            transfer_name = att_meta.get("transferName", "")
+
+            if mime.startswith("image/"):
+                ext_map = {
+                    "image/jpeg": ".jpg",
+                    "image/png": ".png",
+                    "image/gif": ".gif",
+                    "image/webp": ".webp",
+                    "image/heic": ".jpg",
+                    "image/heif": ".jpg",
+                    "image/tiff": ".jpg",
+                }
+                ext = ext_map.get(mime, ".jpg")
+                return cache_image_from_bytes(data, ext)
+
+            if mime.startswith("audio/"):
+                ext_map = {
+                    "audio/mp3": ".mp3",
+                    "audio/mpeg": ".mp3",
+                    "audio/ogg": ".ogg",
+                    "audio/wav": ".wav",
+                    "audio/x-caf": ".mp3",
+                    "audio/mp4": ".m4a",
+                    "audio/aac": ".m4a",
+                }
+                ext = ext_map.get(mime, ".mp3")
+                return cache_audio_from_bytes(data, ext)
+
+            # Videos, documents, and everything else
+            filename = transfer_name or f"file_{uuid.uuid4().hex[:8]}"
+            return cache_document_from_bytes(data, filename)
+
+        except Exception as exc:
+            logger.warning(
+                "[bluebubbles] failed to download attachment %s: %s",
+                _redact(att_guid),
+                exc,
+            )
+            return None
+
+    # ------------------------------------------------------------------
+    # Webhook handling
+    # ------------------------------------------------------------------
+
+    def _extract_payload_record(
+        self, payload: Dict[str, Any]
+    ) -> Optional[Dict[str, Any]]:
+        data = payload.get("data")
+        if isinstance(data, dict):
+            return data
+        if isinstance(data, list):
+            for item in data:
+                if isinstance(item, dict):
+                    return item
+        if isinstance(payload.get("message"), dict):
+            return payload.get("message")
+        return payload if isinstance(payload, dict) else None
+
+    @staticmethod
+    def _value(*candidates: Any) -> Optional[str]:
+        for candidate in candidates:
+            if isinstance(candidate, str) and candidate.strip():
+                return candidate.strip()
+        return None
+
+    async def _handle_webhook(self, request):
+        from aiohttp import web
+
+        token = (
+            request.query.get("password")
+            or request.query.get("guid")
+            or request.headers.get("x-password")
+            or request.headers.get("x-guid")
+            or request.headers.get("x-bluebubbles-guid")
+        )
+        if token != self.password:
+            return web.json_response({"error": "unauthorized"}, status=401)
+        try:
+            raw = await request.read()
+            body = raw.decode("utf-8", errors="replace")
+            try:
+                payload = json.loads(body)
+            except Exception:
+                from urllib.parse import parse_qs
+
+                form = parse_qs(body)
+                payload_str = (
+                    form.get("payload")
+                    or form.get("data")
+                    or form.get("message")
+                    or [""]
+                )[0]
+                payload = json.loads(payload_str) if payload_str else {}
+        except Exception as exc:
+            logger.error("[bluebubbles] webhook parse error: %s", exc)
+            return web.json_response({"error": "invalid payload"}, status=400)
+
+        event_type = self._value(payload.get("type"), payload.get("event")) or ""
+        # Only process message events; silently acknowledge everything else
+        if event_type and event_type not in _MESSAGE_EVENTS:
+            return web.Response(text="ok")
+
+        record = self._extract_payload_record(payload) or {}
+        is_from_me = bool(
+            record.get("isFromMe")
+            or record.get("fromMe")
+            or record.get("is_from_me")
+        )
+        if is_from_me:
+            return web.Response(text="ok")
+
+        # Skip tapback reactions delivered as messages
+        assoc_type = record.get("associatedMessageType")
+        if isinstance(assoc_type, int) and assoc_type in {
+            **_TAPBACK_ADDED,
+            **_TAPBACK_REMOVED,
+        }:
+            return web.Response(text="ok")
+
+        text = (
+            self._value(
+                record.get("text"), record.get("message"), record.get("body")
+            )
+            or ""
+        )
+
+        # --- Inbound attachment handling ---
+        attachments = record.get("attachments") or []
+        media_urls: List[str] = []
+        media_types: List[str] = []
+        msg_type = MessageType.TEXT
+
+        for att in attachments:
+            att_guid = att.get("guid", "")
+            if not att_guid:
+                continue
+            cached = await self._download_attachment(att_guid, att)
+            if cached:
+                mime = (att.get("mimeType") or "").lower()
+                media_urls.append(cached)
+                media_types.append(mime)
+                if mime.startswith("image/"):
+                    msg_type = MessageType.PHOTO
+                elif mime.startswith("audio/") or (att.get("uti") or "").endswith(
+                    "caf"
+                ):
+                    msg_type = MessageType.VOICE
+                elif mime.startswith("video/"):
+                    msg_type = MessageType.VIDEO
+                else:
+                    msg_type = MessageType.DOCUMENT
+
+        # With multiple attachments, prefer PHOTO if any images present
+        if len(media_urls) > 1:
+            mime_prefixes = {(m or "").split("/")[0] for m in media_types}
+            if "image" in mime_prefixes:
+                msg_type = MessageType.PHOTO
+
+        if not text and media_urls:
+            text = "(attachment)"
+        # --- End attachment handling ---
+
+        chat_guid = self._value(
+            record.get("chatGuid"),
+            payload.get("chatGuid"),
+            record.get("chat_guid"),
+            payload.get("chat_guid"),
+            payload.get("guid"),
+        )
+        chat_identifier = self._value(
+            record.get("chatIdentifier"),
+            record.get("identifier"),
+            payload.get("chatIdentifier"),
+            payload.get("identifier"),
+        )
+        sender = (
+            self._value(
+                record.get("handle", {}).get("address")
+                if isinstance(record.get("handle"), dict)
+                else None,
+                record.get("sender"),
+                record.get("from"),
+                record.get("address"),
+            )
+            or chat_identifier
+            or chat_guid
+        )
+        if not (chat_guid or chat_identifier) and sender:
+            chat_identifier = sender
+        if not sender or not (chat_guid or chat_identifier) or not text:
+            return web.json_response({"error": "missing message fields"}, status=400)
+
+        session_chat_id = chat_guid or chat_identifier
+        is_group = bool(record.get("isGroup")) or (";+;" in (chat_guid or ""))
+        source = self.build_source(
+            chat_id=session_chat_id,
+            chat_name=chat_identifier or sender,
+            chat_type="group" if is_group else "dm",
+            user_id=sender,
+            user_name=sender,
+            chat_id_alt=chat_identifier,
+        )
+        event = MessageEvent(
+            text=text,
+            message_type=msg_type,
+            source=source,
+            raw_message=payload,
+            message_id=self._value(
+                record.get("guid"),
+                record.get("messageGuid"),
+                record.get("id"),
+            ),
+            reply_to_message_id=self._value(
+                record.get("threadOriginatorGuid"),
+                record.get("associatedMessageGuid"),
+            ),
+            media_urls=media_urls,
+            media_types=media_types,
+        )
+        task = asyncio.create_task(self.handle_message(event))
+        self._background_tasks.add(task)
+        task.add_done_callback(self._background_tasks.discard)
+
+        # Fire-and-forget read receipt
+        if self.send_read_receipts and session_chat_id:
+            asyncio.create_task(self.mark_read(session_chat_id))
+
+        return web.Response(text="ok")
+

gateway/platforms/dingtalk.py

@@ -20,6 +20,7 @@ Configuration in config.yaml:
 import asyncio
 import logging
 import os
+import re
 import time
 import uuid
 from datetime import datetime, timezone
@@ -54,6 +55,8 @@ MAX_MESSAGE_LENGTH = 20000
 DEDUP_WINDOW_SECONDS = 300
 DEDUP_MAX_SIZE = 1000
 RECONNECT_BACKOFF = [2, 5, 10, 30, 60]
+_SESSION_WEBHOOKS_MAX = 500
+_DINGTALK_WEBHOOK_RE = re.compile(r'^https://api\.dingtalk\.com/')
 
 
 def check_dingtalk_requirements() -> bool:
@@ -195,9 +198,15 @@ class DingTalkAdapter(BasePlatformAdapter):
         chat_id = conversation_id or sender_id
         chat_type = "group" if is_group else "dm"
 
-        # Store session webhook for reply routing
+        # Store session webhook for reply routing (validate origin to prevent SSRF)
         session_webhook = getattr(message, "session_webhook", None) or ""
-        if session_webhook and chat_id:
+        if session_webhook and chat_id and _DINGTALK_WEBHOOK_RE.match(session_webhook):
+            if len(self._session_webhooks) >= _SESSION_WEBHOOKS_MAX:
+                # Evict oldest entry to cap memory growth
+                try:
+                    self._session_webhooks.pop(next(iter(self._session_webhooks)))
+                except StopIteration:
+                    pass
             self._session_webhooks[chat_id] = session_webhook
 
         source = self.build_source(

gateway/platforms/discord.py

@@ -49,6 +49,7 @@ from gateway.platforms.base import (
     BasePlatformAdapter,
     MessageEvent,
     MessageType,
+    ProcessingOutcome,
     SendResult,
     cache_image_from_url,
     cache_audio_from_url,
@@ -422,6 +423,7 @@ class DiscordAdapter(BasePlatformAdapter):
 
     # Discord message limits
     MAX_MESSAGE_LENGTH = 2000
+    _SPLIT_THRESHOLD = 1900  # near the 2000-char split point
 
     # Auto-disconnect from voice channel after this many seconds of inactivity
     VOICE_TIMEOUT = 300
@@ -433,6 +435,11 @@ class DiscordAdapter(BasePlatformAdapter):
         self._allowed_user_ids: set = set()  # For button approval authorization
         # Voice channel state (per-guild)
         self._voice_clients: Dict[int, Any] = {}  # guild_id -> VoiceClient
+        # Text batching: merge rapid successive messages (Telegram-style)
+        self._text_batch_delay_seconds = float(os.getenv("HERMES_DISCORD_TEXT_BATCH_DELAY_SECONDS", "0.6"))
+        self._text_batch_split_delay_seconds = float(os.getenv("HERMES_DISCORD_TEXT_BATCH_SPLIT_DELAY_SECONDS", "2.0"))
+        self._pending_text_batches: Dict[str, MessageEvent] = {}
+        self._pending_text_batch_tasks: Dict[str, asyncio.Task] = {}
         self._voice_text_channels: Dict[int, int] = {}  # guild_id -> text_channel_id
         self._voice_timeout_tasks: Dict[int, asyncio.Task] = {}  # guild_id -> timeout task
         # Phase 2: voice listening
@@ -529,10 +536,17 @@ class DiscordAdapter(BasePlatformAdapter):
             intents.members = any(not entry.isdigit() for entry in self._allowed_user_ids)
             intents.voice_states = True
 
-            # Create bot
+            # Resolve proxy (DISCORD_PROXY > generic env vars > macOS system proxy)
+            from gateway.platforms.base import resolve_proxy_url, proxy_kwargs_for_bot
+            proxy_url = resolve_proxy_url(platform_env_var="DISCORD_PROXY")
+            if proxy_url:
+                logger.info("[%s] Using proxy for Discord: %s", self.name, proxy_url)
+
+            # Create bot — proxy= for HTTP, connector= for SOCKS
             self._client = commands.Bot(
                 command_prefix="!",  # Not really used, we handle raw messages
                 intents=intents,
+                **proxy_kwargs_for_bot(proxy_url),
             )
             adapter_self = self  # capture for closure
 
@@ -592,22 +606,35 @@ class DiscordAdapter(BasePlatformAdapter):
                         if not self._client.user or self._client.user not in message.mentions:
                             return
                     # "all" falls through to handle_message
-
-                # If the message @mentions other users but NOT the bot, the
-                # sender is talking to someone else — stay silent.  Only
-                # applies in server channels; in DMs the user is always
-                # talking to the bot (mentions are just references).
-                # Controlled by DISCORD_IGNORE_NO_MENTION (default: true).
-                _ignore_no_mention = os.getenv(
-                    "DISCORD_IGNORE_NO_MENTION", "true"
-                ).lower() in ("true", "1", "yes")
-                if _ignore_no_mention and message.mentions and not isinstance(message.channel, discord.DMChannel):
-                    _bot_mentioned = (
+                
+                # Multi-agent filtering: if the message mentions specific bots
+                # but NOT this bot, the sender is talking to another agent —
+                # stay silent.  Messages with no bot mentions (general chat)
+                # still fall through to _handle_message for the existing
+                # DISCORD_REQUIRE_MENTION check.
+                #
+                # This replaces the older DISCORD_IGNORE_NO_MENTION logic
+                # with bot-aware filtering that works correctly when multiple
+                # agents share a channel.
+                if not isinstance(message.channel, discord.DMChannel) and message.mentions:
+                    _self_mentioned = (
                         self._client.user is not None
                         and self._client.user in message.mentions
                     )
-                    if not _bot_mentioned:
-                        return  # Talking to someone else, don't interrupt
+                    _other_bots_mentioned = any(
+                        m.bot and m != self._client.user
+                        for m in message.mentions
+                    )
+                    # If other bots are mentioned but we're not → not for us
+                    if _other_bots_mentioned and not _self_mentioned:
+                        return
+                    # If humans are mentioned but we're not → not for us
+                    # (preserves old DISCORD_IGNORE_NO_MENTION=true behavior)
+                    _ignore_no_mention = os.getenv(
+                        "DISCORD_IGNORE_NO_MENTION", "true"
+                    ).lower() in ("true", "1", "yes")
+                    if _ignore_no_mention and not _self_mentioned and not _other_bots_mentioned:
+                        return
 
                 await self._handle_message(message)
 
@@ -741,14 +768,17 @@ class DiscordAdapter(BasePlatformAdapter):
         if hasattr(message, "add_reaction"):
             await self._add_reaction(message, "👀")
 
-    async def on_processing_complete(self, event: MessageEvent, success: bool) -> None:
+    async def on_processing_complete(self, event: MessageEvent, outcome: ProcessingOutcome) -> None:
         """Swap the in-progress reaction for a final success/failure reaction."""
         if not self._reactions_enabled():
             return
         message = event.raw_message
         if hasattr(message, "add_reaction"):
             await self._remove_reaction(message, "👀")
-            await self._add_reaction(message, "✅" if success else "❌")
+            if outcome == ProcessingOutcome.SUCCESS:
+                await self._add_reaction(message, "✅")
+            elif outcome == ProcessingOutcome.FAILURE:
+                await self._add_reaction(message, "❌")
 
     async def send(
         self,
@@ -757,18 +787,34 @@ class DiscordAdapter(BasePlatformAdapter):
         reply_to: Optional[str] = None,
         metadata: Optional[Dict[str, Any]] = None
     ) -> SendResult:
-        """Send a message to a Discord channel."""
+        """Send a message to a Discord channel or thread.
+
+        When metadata contains a thread_id, the message is sent to that
+        thread instead of the parent channel identified by chat_id.
+        """
         if not self._client:
             return SendResult(success=False, error="Not connected")
 
         try:
-            # Get the channel
-            channel = self._client.get_channel(int(chat_id))
-            if not channel:
-                channel = await self._client.fetch_channel(int(chat_id))
+            # Determine target channel: thread_id in metadata takes precedence.
+            thread_id = None
+            if metadata and metadata.get("thread_id"):
+                thread_id = metadata["thread_id"]
 
-            if not channel:
-                return SendResult(success=False, error=f"Channel {chat_id} not found")
+            if thread_id:
+                # Fetch the thread directly — threads are addressed by their own ID.
+                channel = self._client.get_channel(int(thread_id))
+                if not channel:
+                    channel = await self._client.fetch_channel(int(thread_id))
+                if not channel:
+                    return SendResult(success=False, error=f"Thread {thread_id} not found")
+            else:
+                # Get the parent channel
+                channel = self._client.get_channel(int(chat_id))
+                if not channel:
+                    channel = await self._client.fetch_channel(int(chat_id))
+                if not channel:
+                    return SendResult(success=False, error=f"Channel {chat_id} not found")
 
             # Format and split message if needed
             formatted = self.format_message(content)
@@ -1231,9 +1277,8 @@ class DiscordAdapter(BasePlatformAdapter):
         try:
             await asyncio.to_thread(VoiceReceiver.pcm_to_wav, pcm_data, wav_path)
 
-            from tools.transcription_tools import transcribe_audio, get_stt_model_from_config
-            stt_model = get_stt_model_from_config()
-            result = await asyncio.to_thread(transcribe_audio, wav_path, model=stt_model)
+            from tools.transcription_tools import transcribe_audio
+            result = await asyncio.to_thread(transcribe_audio, wav_path)
 
             if not result.get("success"):
                 return
@@ -1307,8 +1352,11 @@ class DiscordAdapter(BasePlatformAdapter):
 
             # Download the image and send as a Discord file attachment
             # (Discord renders attachments inline, unlike plain URLs)
-            async with aiohttp.ClientSession() as session:
-                async with session.get(image_url, timeout=aiohttp.ClientTimeout(total=30)) as resp:
+            from gateway.platforms.base import resolve_proxy_url, proxy_kwargs_for_aiohttp
+            _proxy = resolve_proxy_url(platform_env_var="DISCORD_PROXY")
+            _sess_kw, _req_kw = proxy_kwargs_for_aiohttp(_proxy)
+            async with aiohttp.ClientSession(**_sess_kw) as session:
+                async with session.get(image_url, timeout=aiohttp.ClientTimeout(total=30), **_req_kw) as resp:
                     if resp.status != 200:
                         raise Exception(f"Failed to download image: HTTP {resp.status}")
 
@@ -1585,7 +1633,7 @@ class DiscordAdapter(BasePlatformAdapter):
             await self._run_simple_slash(interaction, f"/model {name}".strip())
 
         @tree.command(name="reasoning", description="Show or change reasoning effort")
-        @discord.app_commands.describe(effort="Reasoning effort: xhigh, high, medium, low, minimal, or none.")
+        @discord.app_commands.describe(effort="Reasoning effort: none, minimal, low, medium, high, or xhigh.")
         async def slash_reasoning(interaction: discord.Interaction, effort: str = ""):
             await self._run_simple_slash(interaction, f"/reasoning {effort}".strip())
 
@@ -1767,8 +1815,9 @@ class DiscordAdapter(BasePlatformAdapter):
             if hasattr(interaction.channel, "guild") and interaction.channel.guild:
                 chat_name = f"{interaction.channel.guild.name} / #{chat_name}"
 
-        # Get channel topic (if available)
-        chat_topic = getattr(interaction.channel, "topic", None)
+        # Get channel topic (if available).
+        # For forum threads, inherit the parent forum's topic.
+        chat_topic = self._get_effective_topic(interaction.channel, is_thread=is_thread)
 
         source = self.build_source(
             chat_id=str(interaction.channel_id),
@@ -1842,6 +1891,10 @@ class DiscordAdapter(BasePlatformAdapter):
 
         chat_name = f"{guild_name} / {thread_name}" if guild_name else thread_name
 
+        # Inherit forum topic when the thread was created inside a forum channel.
+        _chan = getattr(interaction, "channel", None)
+        chat_topic = self._get_effective_topic(_chan, is_thread=True) if _chan else None
+
         source = self.build_source(
             chat_id=thread_id,
             chat_name=chat_name,
@@ -1849,16 +1902,45 @@ class DiscordAdapter(BasePlatformAdapter):
             user_id=str(interaction.user.id),
             user_name=interaction.user.display_name,
             thread_id=thread_id,
+            chat_topic=chat_topic,
         )
 
+        _parent_id = str(getattr(getattr(interaction, "channel", None), "parent_id", "") or "")
+        _skills = self._resolve_channel_skills(thread_id, _parent_id or None)
         event = MessageEvent(
             text=text,
             message_type=MessageType.TEXT,
             source=source,
             raw_message=interaction,
+            auto_skill=_skills,
         )
         await self.handle_message(event)
 
+    def _resolve_channel_skills(self, channel_id: str, parent_id: str | None = None) -> list[str] | None:
+        """Look up auto-skill bindings for a Discord channel/forum thread.
+
+        Config format (in platform extra):
+            channel_skill_bindings:
+              - id: "123456"
+                skills: ["skill-a", "skill-b"]
+        Also checks parent_id so forum threads inherit the forum's bindings.
+        """
+        bindings = self.config.extra.get("channel_skill_bindings", [])
+        if not bindings:
+            return None
+        ids_to_check = {channel_id}
+        if parent_id:
+            ids_to_check.add(parent_id)
+        for entry in bindings:
+            entry_id = str(entry.get("id", ""))
+            if entry_id in ids_to_check:
+                skills = entry.get("skills") or entry.get("skill")
+                if isinstance(skills, str):
+                    return [skills]
+                if isinstance(skills, list) and skills:
+                    return list(dict.fromkeys(skills))  # dedup, preserve order
+        return None
+
     def _thread_parent_channel(self, channel: Any) -> Any:
         """Return the parent text channel when invoked from a thread."""
         return getattr(channel, "parent", None) or channel
@@ -2134,6 +2216,15 @@ class DiscordAdapter(BasePlatformAdapter):
                 return True
         return False
 
+    def _get_effective_topic(self, channel: Any, is_thread: bool = False) -> Optional[str]:
+        """Return the channel topic, falling back to the parent forum's topic for forum threads."""
+        topic = getattr(channel, "topic", None)
+        if not topic and is_thread:
+            parent = getattr(channel, "parent", None)
+            if parent and self._is_forum_parent(parent):
+                topic = getattr(parent, "topic", None)
+        return topic
+
     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"))
@@ -2203,6 +2294,7 @@ class DiscordAdapter(BasePlatformAdapter):
         #   discord.require_mention: Require @mention in server channels (default: true)
         #   discord.free_response_channels: Channel IDs where bot responds without mention
         #   discord.ignored_channels: Channel IDs where bot NEVER responds (even when mentioned)
+        #   discord.allowed_channels: If set, bot ONLY responds in these channels (whitelist)
         #   discord.no_thread_channels: Channel IDs where bot responds directly without creating thread
         #   discord.auto_thread: Auto-create thread on @mention in channels (default: true)
 
@@ -2214,12 +2306,21 @@ class DiscordAdapter(BasePlatformAdapter):
             parent_channel_id = self._get_parent_channel_id(message.channel)
 
         if not isinstance(message.channel, discord.DMChannel):
-            # Check ignored channels first - never respond even when mentioned
-            ignored_channels_raw = os.getenv("DISCORD_IGNORED_CHANNELS", "")
-            ignored_channels = {ch.strip() for ch in ignored_channels_raw.split(",") if ch.strip()}
             channel_ids = {str(message.channel.id)}
             if parent_channel_id:
                 channel_ids.add(parent_channel_id)
+
+            # Check allowed channels - if set, only respond in these channels
+            allowed_channels_raw = os.getenv("DISCORD_ALLOWED_CHANNELS", "")
+            if allowed_channels_raw:
+                allowed_channels = {ch.strip() for ch in allowed_channels_raw.split(",") if ch.strip()}
+                if not (channel_ids & allowed_channels):
+                    logger.debug("[%s] Ignoring message in non-allowed channel: %s", self.name, channel_ids)
+                    return
+
+            # Check ignored channels - never respond even when mentioned
+            ignored_channels_raw = os.getenv("DISCORD_IGNORED_CHANNELS", "")
+            ignored_channels = {ch.strip() for ch in ignored_channels_raw.split(",") if ch.strip()}
             if channel_ids & ignored_channels:
                 logger.debug("[%s] Ignoring message in ignored channel: %s", self.name, channel_ids)
                 return
@@ -2301,8 +2402,10 @@ class DiscordAdapter(BasePlatformAdapter):
             if hasattr(message.channel, "guild") and message.channel.guild:
                 chat_name = f"{message.channel.guild.name} / #{chat_name}"
 
-        # Get channel topic (if available - TextChannels have topics, DMs/threads don't)
-        chat_topic = getattr(message.channel, "topic", None)
+        # Get channel topic (if available - TextChannels have topics, DMs/threads don't).
+        # For threads whose parent is a forum channel, inherit the parent's topic
+        # so forum descriptions (e.g. project instructions) appear in the session context.
+        chat_topic = self._get_effective_topic(message.channel, is_thread=is_thread)
 
         # Build source
         source = self.build_source(
@@ -2365,7 +2468,7 @@ class DiscordAdapter(BasePlatformAdapter):
                         ext or "unknown", content_type,
                     )
                 else:
-                    MAX_DOC_BYTES = 20 * 1024 * 1024
+                    MAX_DOC_BYTES = 32 * 1024 * 1024
                     if att.size and att.size > MAX_DOC_BYTES:
                         logger.warning(
                             "[Discord] Document too large (%s bytes), skipping: %s",
@@ -2374,10 +2477,14 @@ class DiscordAdapter(BasePlatformAdapter):
                     else:
                         try:
                             import aiohttp
-                            async with aiohttp.ClientSession() as session:
+                            from gateway.platforms.base import resolve_proxy_url, proxy_kwargs_for_aiohttp
+                            _proxy = resolve_proxy_url(platform_env_var="DISCORD_PROXY")
+                            _sess_kw, _req_kw = proxy_kwargs_for_aiohttp(_proxy)
+                            async with aiohttp.ClientSession(**_sess_kw) as session:
                                 async with session.get(
                                     att.url,
                                     timeout=aiohttp.ClientTimeout(total=30),
+                                    **_req_kw,
                                 ) as resp:
                                     if resp.status != 200:
                                         raise Exception(f"HTTP {resp.status}")
@@ -2389,9 +2496,9 @@ class DiscordAdapter(BasePlatformAdapter):
                             media_urls.append(cached_path)
                             media_types.append(doc_mime)
                             logger.info("[Discord] Cached user document: %s", cached_path)
-                            # Inject text content for .txt/.md files (capped at 100 KB)
+                            # Inject text content for plain-text documents (capped at 100 KB)
                             MAX_TEXT_INJECT_BYTES = 100 * 1024
-                            if ext in (".md", ".txt") and len(raw_bytes) <= MAX_TEXT_INJECT_BYTES:
+                            if ext in (".md", ".txt", ".log") and len(raw_bytes) <= MAX_TEXT_INJECT_BYTES:
                                 try:
                                     text_content = raw_bytes.decode("utf-8")
                                     display_name = att.filename or f"document{ext}"
@@ -2418,6 +2525,10 @@ class DiscordAdapter(BasePlatformAdapter):
         if not event_text or not event_text.strip():
             event_text = "(The user sent a message with no text content)"
 
+        _chan = message.channel
+        _parent_id = str(getattr(_chan, "parent_id", "") or "")
+        _chan_id = str(getattr(_chan, "id", ""))
+        _skills = self._resolve_channel_skills(_chan_id, _parent_id or None)
         event = MessageEvent(
             text=event_text,
             message_type=msg_type,
@@ -2428,6 +2539,7 @@ class DiscordAdapter(BasePlatformAdapter):
             media_types=media_types,
             reply_to_message_id=str(message.reference.message_id) if message.reference else None,
             timestamp=message.created_at,
+            auto_skill=_skills,
         )
 
         # Track thread participation so the bot won't require @mention for
@@ -2435,7 +2547,80 @@ class DiscordAdapter(BasePlatformAdapter):
         if thread_id:
             self._track_thread(thread_id)
 
-        await self.handle_message(event)
+        # Only batch plain text messages — commands, media, etc. dispatch
+        # immediately since they won't be split by the Discord client.
+        if msg_type == MessageType.TEXT and self._text_batch_delay_seconds > 0:
+            self._enqueue_text_event(event)
+        else:
+            await self.handle_message(event)
+
+    # ------------------------------------------------------------------
+    # Text message aggregation (handles Discord client-side splits)
+    # ------------------------------------------------------------------
+
+    def _text_batch_key(self, event: MessageEvent) -> str:
+        """Session-scoped key for text message batching."""
+        from gateway.session import build_session_key
+        return build_session_key(
+            event.source,
+            group_sessions_per_user=self.config.extra.get("group_sessions_per_user", True),
+            thread_sessions_per_user=self.config.extra.get("thread_sessions_per_user", False),
+        )
+
+    def _enqueue_text_event(self, event: MessageEvent) -> None:
+        """Buffer a text event and reset the flush timer.
+
+        When Discord splits a long user message at 2000 chars, the chunks
+        arrive within a few hundred milliseconds.  This merges them into
+        a single event before dispatching.
+        """
+        key = self._text_batch_key(event)
+        existing = self._pending_text_batches.get(key)
+        chunk_len = len(event.text or "")
+        if existing is None:
+            event._last_chunk_len = chunk_len  # type: ignore[attr-defined]
+            self._pending_text_batches[key] = event
+        else:
+            if event.text:
+                existing.text = f"{existing.text}\n{event.text}" if existing.text else event.text
+            existing._last_chunk_len = chunk_len  # type: ignore[attr-defined]
+            if event.media_urls:
+                existing.media_urls.extend(event.media_urls)
+                existing.media_types.extend(event.media_types)
+
+        prior_task = self._pending_text_batch_tasks.get(key)
+        if prior_task and not prior_task.done():
+            prior_task.cancel()
+        self._pending_text_batch_tasks[key] = asyncio.create_task(
+            self._flush_text_batch(key)
+        )
+
+    async def _flush_text_batch(self, key: str) -> None:
+        """Wait for the quiet period then dispatch the aggregated text.
+
+        Uses a longer delay when the latest chunk is near Discord's 2000-char
+        split point, since a continuation chunk is almost certain.
+        """
+        current_task = asyncio.current_task()
+        try:
+            pending = self._pending_text_batches.get(key)
+            last_len = getattr(pending, "_last_chunk_len", 0) if pending else 0
+            if last_len >= self._SPLIT_THRESHOLD:
+                delay = self._text_batch_split_delay_seconds
+            else:
+                delay = self._text_batch_delay_seconds
+            await asyncio.sleep(delay)
+            event = self._pending_text_batches.pop(key, None)
+            if not event:
+                return
+            logger.info(
+                "[Discord] Flushing text batch %s (%d chars)",
+                key, len(event.text or ""),
+            )
+            await self.handle_message(event)
+        finally:
+            if self._pending_text_batch_tasks.get(key) is current_task:
+                self._pending_text_batch_tasks.pop(key, None)
 
 
 # ---------------------------------------------------------------------------

gateway/platforms/email.py

@@ -195,7 +195,11 @@ def _extract_attachments(
 
         ext = Path(filename).suffix.lower()
         if ext in _IMAGE_EXTS:
-            cached_path = cache_image_from_bytes(payload, ext)
+            try:
+                cached_path = cache_image_from_bytes(payload, ext)
+            except ValueError:
+                logger.debug("Skipping non-image attachment %s (invalid magic bytes)", filename)
+                continue
             attachments.append({
                 "path": cached_path,
                 "filename": filename,

gateway/platforms/feishu.py

@@ -264,6 +264,7 @@ class FeishuAdapterSettings:
     bot_name: str
     dedup_cache_size: int
     text_batch_delay_seconds: float
+    text_batch_split_delay_seconds: float
     text_batch_max_messages: int
     text_batch_max_chars: int
     media_batch_delay_seconds: float
@@ -972,7 +973,8 @@ def _run_official_feishu_ws_client(ws_client: Any, adapter: Any) -> None:
         return await original_connect(*args, **kwargs)
 
     def _configure_with_overrides(conf: Any) -> Any:
-        assert original_configure is not None
+        if original_configure is None:
+            raise RuntimeError("Feishu _configure_with_overrides called but original_configure is None")
         result = original_configure(conf)
         _apply_runtime_ws_overrides()
         return result
@@ -1014,6 +1016,10 @@ class FeishuAdapter(BasePlatformAdapter):
     """Feishu/Lark bot adapter."""
 
     MAX_MESSAGE_LENGTH = 8000
+    # Threshold for detecting Feishu client-side message splits.
+    # When a chunk is near the ~4096-char practical limit, a continuation
+    # is almost certain.
+    _SPLIT_THRESHOLD = 4000
 
     # =========================================================================
     # Lifecycle — init / settings / connect / disconnect
@@ -1105,6 +1111,9 @@ class FeishuAdapter(BasePlatformAdapter):
             text_batch_delay_seconds=float(
                 os.getenv("HERMES_FEISHU_TEXT_BATCH_DELAY_SECONDS", str(_DEFAULT_TEXT_BATCH_DELAY_SECONDS))
             ),
+            text_batch_split_delay_seconds=float(
+                os.getenv("HERMES_FEISHU_TEXT_BATCH_SPLIT_DELAY_SECONDS", "2.0")
+            ),
             text_batch_max_messages=max(
                 1,
                 int(os.getenv("HERMES_FEISHU_TEXT_BATCH_MAX_MESSAGES", str(_DEFAULT_TEXT_BATCH_MAX_MESSAGES))),
@@ -1152,6 +1161,7 @@ class FeishuAdapter(BasePlatformAdapter):
         self._bot_name = settings.bot_name
         self._dedup_cache_size = settings.dedup_cache_size
         self._text_batch_delay_seconds = settings.text_batch_delay_seconds
+        self._text_batch_split_delay_seconds = settings.text_batch_split_delay_seconds
         self._text_batch_max_messages = settings.text_batch_max_messages
         self._text_batch_max_chars = settings.text_batch_max_chars
         self._media_batch_delay_seconds = settings.media_batch_delay_seconds
@@ -1180,6 +1190,8 @@ class FeishuAdapter(BasePlatformAdapter):
                 lambda data: self._on_reaction_event("im.message.reaction.deleted_v1", data)
             )
             .register_p2_card_action_trigger(self._on_card_action_trigger)
+            .register_p2_im_chat_member_bot_added_v1(self._on_bot_added_to_chat)
+            .register_p2_im_chat_member_bot_deleted_v1(self._on_bot_removed_from_chat)
             .build()
         )
 
@@ -1570,13 +1582,18 @@ class FeishuAdapter(BasePlatformAdapter):
             return SendResult(success=False, error=f"Image file not found: {image_path}")
 
         try:
-            with open(image_path, "rb") as image_file:
-                body = self._build_image_upload_body(
-                    image_type=_FEISHU_IMAGE_UPLOAD_TYPE,
-                    image=image_file,
-                )
-                request = self._build_image_upload_request(body)
-                upload_response = await asyncio.to_thread(self._client.im.v1.image.create, request)
+            import io as _io
+            with open(image_path, "rb") as f:
+                image_bytes = f.read()
+            # Wrap in BytesIO so lark SDK's MultipartEncoder can read .name and .tell()
+            image_file = _io.BytesIO(image_bytes)
+            image_file.name = os.path.basename(image_path)
+            body = self._build_image_upload_body(
+                image_type=_FEISHU_IMAGE_UPLOAD_TYPE,
+                image=image_file,
+            )
+            request = self._build_image_upload_request(body)
+            upload_response = await asyncio.to_thread(self._client.im.v1.image.create, request)
             image_key = self._extract_response_field(upload_response, "image_key")
             if not image_key:
                 return self._response_error_result(
@@ -2478,8 +2495,10 @@ class FeishuAdapter(BasePlatformAdapter):
     async def _enqueue_text_event(self, event: MessageEvent) -> None:
         """Debounce rapid Feishu text bursts into a single MessageEvent."""
         key = self._text_batch_key(event)
+        chunk_len = len(event.text or "")
         existing = self._pending_text_batches.get(key)
         if existing is None:
+            event._last_chunk_len = chunk_len  # type: ignore[attr-defined]
             self._pending_text_batches[key] = event
             self._pending_text_batch_counts[key] = 1
             self._schedule_text_batch_flush(key)
@@ -2504,6 +2523,7 @@ class FeishuAdapter(BasePlatformAdapter):
             return
 
         existing.text = next_text
+        existing._last_chunk_len = chunk_len  # type: ignore[attr-defined]
         existing.timestamp = event.timestamp
         if event.message_id:
             existing.message_id = event.message_id
@@ -2530,10 +2550,22 @@ class FeishuAdapter(BasePlatformAdapter):
         task_map[key] = asyncio.create_task(flush_fn(key))
 
     async def _flush_text_batch(self, key: str) -> None:
-        """Flush a pending text batch after the quiet period."""
+        """Flush a pending text batch after the quiet period.
+
+        Uses a longer delay when the latest chunk is near Feishu's ~4096-char
+        split point, since a continuation chunk is almost certain.
+        """
         current_task = asyncio.current_task()
         try:
-            await asyncio.sleep(self._text_batch_delay_seconds)
+            # Adaptive delay: if the latest chunk is near the split threshold,
+            # a continuation is almost certain — wait longer.
+            pending = self._pending_text_batches.get(key)
+            last_len = getattr(pending, "_last_chunk_len", 0) if pending else 0
+            if last_len >= self._SPLIT_THRESHOLD:
+                delay = self._text_batch_split_delay_seconds
+            else:
+                delay = self._text_batch_delay_seconds
+            await asyncio.sleep(delay)
             await self._flush_text_batch_now(key)
         finally:
             if self._pending_text_batch_tasks.get(key) is current_task:

gateway/platforms/slack.py

@@ -14,7 +14,8 @@ import logging
 import os
 import re
 import time
-from typing import Dict, Optional, Any
+from dataclasses import dataclass, field
+from typing import Dict, Optional, Any, Tuple
 
 try:
     from slack_bolt.async_app import AsyncApp
@@ -38,6 +39,7 @@ from gateway.platforms.base import (
     MessageType,
     SendResult,
     SUPPORTED_DOCUMENT_TYPES,
+    safe_url_for_log,
     cache_document_from_bytes,
 )
 
@@ -45,6 +47,14 @@ from gateway.platforms.base import (
 logger = logging.getLogger(__name__)
 
 
+@dataclass
+class _ThreadContextCache:
+    """Cache entry for fetched thread context."""
+    content: str
+    fetched_at: float = field(default_factory=time.monotonic)
+    message_count: int = 0
+
+
 def check_slack_requirements() -> bool:
     """Check if Slack dependencies are available."""
     return SLACK_AVAILABLE
@@ -95,6 +105,15 @@ class SlackAdapter(BasePlatformAdapter):
         # respond to ALL subsequent messages in that thread automatically.
         self._mentioned_threads: set = set()
         self._MENTIONED_THREADS_MAX = 5000
+        # Assistant thread metadata keyed by (channel_id, thread_ts). Slack's
+        # AI Assistant lifecycle events can arrive before/alongside message
+        # events, and they carry the user/thread identity needed for stable
+        # session + memory scoping.
+        self._assistant_threads: Dict[Tuple[str, str], Dict[str, str]] = {}
+        self._ASSISTANT_THREADS_MAX = 5000
+        # Cache for _fetch_thread_context results: cache_key → _ThreadContextCache
+        self._thread_context_cache: Dict[str, _ThreadContextCache] = {}
+        self._THREAD_CACHE_TTL = 60.0
 
     async def connect(self) -> bool:
         """Connect to Slack via Socket Mode."""
@@ -181,6 +200,14 @@ class SlackAdapter(BasePlatformAdapter):
             async def handle_app_mention(event, say):
                 pass
 
+            @self._app.event("assistant_thread_started")
+            async def handle_assistant_thread_started(event, say):
+                await self._handle_assistant_thread_lifecycle_event(event)
+
+            @self._app.event("assistant_thread_context_changed")
+            async def handle_assistant_thread_context_changed(event, say):
+                await self._handle_assistant_thread_lifecycle_event(event)
+
             # Register slash command handler
             @self._app.command("/hermes")
             async def handle_hermes_command(ack, command):
@@ -267,6 +294,7 @@ class SlackAdapter(BasePlatformAdapter):
                 kwargs = {
                     "channel": chat_id,
                     "text": chunk,
+                    "mrkdwn": True,
                 }
                 if thread_ts:
                     kwargs["thread_ts"] = thread_ts
@@ -309,9 +337,7 @@ class SlackAdapter(BasePlatformAdapter):
         if not self._app:
             return SendResult(success=False, error="Not connected")
         try:
-            # Convert standard markdown → Slack mrkdwn
             formatted = self.format_message(content)
-
             await self._get_client(chat_id).chat_update(
                 channel=chat_id,
                 ts=message_id,
@@ -443,13 +469,36 @@ class SlackAdapter(BasePlatformAdapter):
         text = re.sub(r'(`[^`]+`)', lambda m: _ph(m.group(0)), text)
 
         # 3) Convert markdown links [text](url) → <url|text>
+        def _convert_markdown_link(m):
+            label = m.group(1)
+            url = m.group(2).strip()
+            if url.startswith('<') and url.endswith('>'):
+                url = url[1:-1].strip()
+            return _ph(f'<{url}|{label}>')
+
         text = re.sub(
-            r'\[([^\]]+)\]\(([^)]+)\)',
-            lambda m: _ph(f'<{m.group(2)}|{m.group(1)}>'),
+            r'\[([^\]]+)\]\(([^()]*(?:\([^()]*\)[^()]*)*)\)',
+            _convert_markdown_link,
             text,
         )
 
-        # 4) Convert headers (## Title) → *Title* (bold)
+        # 4) Protect existing Slack entities/manual links so escaping and later
+        #    formatting passes don't break them.
+        text = re.sub(
+            r'(<(?:[@#!]|(?:https?|mailto|tel):)[^>\n]+>)',
+            lambda m: _ph(m.group(1)),
+            text,
+        )
+
+        # 5) Protect blockquote markers before escaping
+        text = re.sub(r'^(>+\s)', lambda m: _ph(m.group(0)), text, flags=re.MULTILINE)
+
+        # 6) Escape Slack control characters in remaining plain text.
+        # Unescape first so already-escaped input doesn't get double-escaped.
+        text = text.replace('&amp;', '&').replace('&lt;', '<').replace('&gt;', '>')
+        text = text.replace('&', '&amp;').replace('<', '&lt;').replace('>', '&gt;')
+
+        # 7) Convert headers (## Title) → *Title* (bold)
         def _convert_header(m):
             inner = m.group(1).strip()
             # Strip redundant bold markers inside a header
@@ -460,34 +509,39 @@ class SlackAdapter(BasePlatformAdapter):
             r'^#{1,6}\s+(.+)$', _convert_header, text, flags=re.MULTILINE
         )
 
-        # 5) Convert bold: **text** → *text* (Slack bold)
+        # 8) Convert bold+italic: ***text*** → *_text_* (Slack bold wrapping italic)
+        text = re.sub(
+            r'\*\*\*(.+?)\*\*\*',
+            lambda m: _ph(f'*_{m.group(1)}_*'),
+            text,
+        )
+
+        # 9) 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)
+        # 10) 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~
+        # 11) 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.
+        # 12) Blockquotes: > prefix is already protected by step 5 above.
 
-        # 9) Restore placeholders in reverse order
-        for key in reversed(list(placeholders.keys())):
+        # 13) Restore placeholders in reverse order
+        for key in reversed(placeholders):
             text = text.replace(key, placeholders[key])
 
         return text
@@ -603,8 +657,19 @@ class SlackAdapter(BasePlatformAdapter):
         try:
             import httpx
 
+            async def _ssrf_redirect_guard(response):
+                """Re-check redirect targets so public URLs cannot bounce into private IPs."""
+                if response.is_redirect and response.next_request:
+                    redirect_url = str(response.next_request.url)
+                    if not is_safe_url(redirect_url):
+                        raise ValueError("Blocked redirect to private/internal address")
+
             # Download the image first
-            async with httpx.AsyncClient(timeout=30.0, follow_redirects=True) as client:
+            async with httpx.AsyncClient(
+                timeout=30.0,
+                follow_redirects=True,
+                event_hooks={"response": [_ssrf_redirect_guard]},
+            ) as client:
                 response = await client.get(image_url)
                 response.raise_for_status()
 
@@ -621,7 +686,7 @@ class SlackAdapter(BasePlatformAdapter):
         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,
+                safe_url_for_log(image_url),
                 e,
                 exc_info=True,
             )
@@ -755,6 +820,135 @@ class SlackAdapter(BasePlatformAdapter):
 
     # ----- Internal handlers -----
 
+    def _assistant_thread_key(self, channel_id: str, thread_ts: str) -> Optional[Tuple[str, str]]:
+        """Return a stable cache key for Slack assistant thread metadata."""
+        if not channel_id or not thread_ts:
+            return None
+        return (str(channel_id), str(thread_ts))
+
+    def _extract_assistant_thread_metadata(self, event: dict) -> Dict[str, str]:
+        """Extract Slack Assistant thread identity data from an event payload."""
+        assistant_thread = event.get("assistant_thread") or {}
+        context = assistant_thread.get("context") or event.get("context") or {}
+
+        channel_id = (
+            assistant_thread.get("channel_id")
+            or event.get("channel")
+            or context.get("channel_id")
+            or ""
+        )
+        thread_ts = (
+            assistant_thread.get("thread_ts")
+            or event.get("thread_ts")
+            or event.get("message_ts")
+            or ""
+        )
+        user_id = (
+            assistant_thread.get("user_id")
+            or event.get("user")
+            or context.get("user_id")
+            or ""
+        )
+        team_id = (
+            event.get("team")
+            or event.get("team_id")
+            or assistant_thread.get("team_id")
+            or ""
+        )
+        context_channel_id = context.get("channel_id") or ""
+
+        return {
+            "channel_id": str(channel_id) if channel_id else "",
+            "thread_ts": str(thread_ts) if thread_ts else "",
+            "user_id": str(user_id) if user_id else "",
+            "team_id": str(team_id) if team_id else "",
+            "context_channel_id": str(context_channel_id) if context_channel_id else "",
+        }
+
+    def _cache_assistant_thread_metadata(self, metadata: Dict[str, str]) -> None:
+        """Remember assistant thread identity data for later message events."""
+        channel_id = metadata.get("channel_id", "")
+        thread_ts = metadata.get("thread_ts", "")
+        key = self._assistant_thread_key(channel_id, thread_ts)
+        if not key:
+            return
+
+        existing = self._assistant_threads.get(key, {})
+        merged = dict(existing)
+        merged.update({k: v for k, v in metadata.items() if v})
+        self._assistant_threads[key] = merged
+
+        # Evict oldest entries when the cache exceeds the limit
+        if len(self._assistant_threads) > self._ASSISTANT_THREADS_MAX:
+            excess = len(self._assistant_threads) - self._ASSISTANT_THREADS_MAX // 2
+            for old_key in list(self._assistant_threads)[:excess]:
+                del self._assistant_threads[old_key]
+
+        team_id = merged.get("team_id", "")
+        if team_id and channel_id:
+            self._channel_team[channel_id] = team_id
+
+    def _lookup_assistant_thread_metadata(
+        self,
+        event: dict,
+        channel_id: str = "",
+        thread_ts: str = "",
+    ) -> Dict[str, str]:
+        """Load cached assistant-thread metadata that matches the current event."""
+        metadata = self._extract_assistant_thread_metadata(event)
+        if channel_id and not metadata.get("channel_id"):
+            metadata["channel_id"] = channel_id
+        if thread_ts and not metadata.get("thread_ts"):
+            metadata["thread_ts"] = thread_ts
+
+        key = self._assistant_thread_key(
+            metadata.get("channel_id", ""),
+            metadata.get("thread_ts", ""),
+        )
+        cached = self._assistant_threads.get(key, {}) if key else {}
+        if cached:
+            merged = dict(cached)
+            merged.update({k: v for k, v in metadata.items() if v})
+            return merged
+        return metadata
+
+    def _seed_assistant_thread_session(self, metadata: Dict[str, str]) -> None:
+        """Prime the session store so assistant threads get stable user scoping."""
+        session_store = getattr(self, "_session_store", None)
+        if not session_store:
+            return
+
+        channel_id = metadata.get("channel_id", "")
+        thread_ts = metadata.get("thread_ts", "")
+        user_id = metadata.get("user_id", "")
+        if not channel_id or not thread_ts or not user_id:
+            return
+
+        source = self.build_source(
+            chat_id=channel_id,
+            chat_name=channel_id,
+            chat_type="dm",
+            user_id=user_id,
+            thread_id=thread_ts,
+            chat_topic=metadata.get("context_channel_id") or None,
+        )
+
+        try:
+            session_store.get_or_create_session(source)
+        except Exception:
+            logger.debug(
+                "[Slack] Failed to seed assistant thread session for %s/%s",
+                channel_id,
+                thread_ts,
+                exc_info=True,
+            )
+
+    async def _handle_assistant_thread_lifecycle_event(self, event: dict) -> None:
+        """Handle Slack Assistant lifecycle events that carry user/thread identity."""
+        metadata = self._extract_assistant_thread_metadata(event)
+        self._cache_assistant_thread_metadata(metadata)
+        self._seed_assistant_thread_session(metadata)
+
     async def _handle_slack_message(self, event: dict) -> None:
         """Handle an incoming Slack message event."""
         # Dedup: Slack Socket Mode can redeliver events after reconnects (#4777)
@@ -771,9 +965,26 @@ class SlackAdapter(BasePlatformAdapter):
                     if v > cutoff
                 }
 
-        # Ignore bot messages (including our own)
+        # Bot message filtering (SLACK_ALLOW_BOTS / config allow_bots):
+        #   "none"     — ignore all bot messages (default, backward-compatible)
+        #   "mentions" — accept bot messages only when they @mention us
+        #   "all"      — accept all bot messages (except our own)
         if event.get("bot_id") or event.get("subtype") == "bot_message":
-            return
+            allow_bots = self.config.extra.get("allow_bots", "")
+            if not allow_bots:
+                allow_bots = os.getenv("SLACK_ALLOW_BOTS", "none")
+            allow_bots = str(allow_bots).lower().strip()
+            if allow_bots == "none":
+                return
+            elif allow_bots == "mentions":
+                text_check = event.get("text", "")
+                if self._bot_user_id and f"<@{self._bot_user_id}>" not in text_check:
+                    return
+            # "all" falls through to process the message
+            # Always ignore our own messages to prevent echo loops
+            msg_user = event.get("user", "")
+            if msg_user and self._bot_user_id and msg_user == self._bot_user_id:
+                return
 
         # Ignore message edits and deletions
         subtype = event.get("subtype")
@@ -781,10 +992,21 @@ class SlackAdapter(BasePlatformAdapter):
             return
 
         text = event.get("text", "")
-        user_id = event.get("user", "")
         channel_id = event.get("channel", "")
         ts = event.get("ts", "")
-        team_id = event.get("team", "")
+        assistant_meta = self._lookup_assistant_thread_metadata(
+            event,
+            channel_id=channel_id,
+            thread_ts=event.get("thread_ts", ""),
+        )
+        user_id = event.get("user") or assistant_meta.get("user_id", "")
+        if not channel_id:
+            channel_id = assistant_meta.get("channel_id", "")
+        team_id = (
+            event.get("team")
+            or event.get("team_id")
+            or assistant_meta.get("team_id", "")
+        )
 
         # Track which workspace owns this channel
         if team_id and channel_id:
@@ -792,7 +1014,9 @@ class SlackAdapter(BasePlatformAdapter):
 
         # Determine if this is a DM or channel message
         channel_type = event.get("channel_type", "")
-        is_dm = channel_type == "im"
+        if not channel_type and channel_id.startswith("D"):
+            channel_type = "im"
+        is_dm = channel_type in ("im", "mpim")  # Both 1:1 and group DMs
 
         # Build thread_ts for session keying.
         # In channels: fall back to ts so each top-level @mention starts a
@@ -800,11 +1024,13 @@ class SlackAdapter(BasePlatformAdapter):
         # 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
+            thread_ts = event.get("thread_ts") or assistant_meta.get("thread_ts")  # None for top-level DMs
         else:
             thread_ts = event.get("thread_ts") or ts  # ts fallback for channels
 
         # In channels, respond if:
+        #   0. Channel is in free_response_channels, OR require_mention is
+        #      disabled — always process regardless of mention.
         #   1. The bot is @mentioned in this message, OR
         #   2. The message is a reply in a thread the bot started/participated in, OR
         #   3. The message is in a thread where the bot was previously @mentioned, OR
@@ -814,24 +1040,29 @@ class SlackAdapter(BasePlatformAdapter):
         event_thread_ts = event.get("thread_ts")
         is_thread_reply = bool(event_thread_ts and event_thread_ts != ts)
 
-        if not is_dm and bot_uid and not is_mentioned:
-            reply_to_bot_thread = (
-                is_thread_reply and event_thread_ts in self._bot_message_ts
-            )
-            in_mentioned_thread = (
-                event_thread_ts is not None
-                and event_thread_ts in self._mentioned_threads
-            )
-            has_session = (
-                is_thread_reply
-                and self._has_active_session_for_thread(
-                    channel_id=channel_id,
-                    thread_ts=event_thread_ts,
-                    user_id=user_id,
+        if not is_dm and bot_uid:
+            if channel_id in self._slack_free_response_channels():
+                pass  # Free-response channel — always process
+            elif not self._slack_require_mention():
+                pass  # Mention requirement disabled globally for Slack
+            elif not is_mentioned:
+                reply_to_bot_thread = (
+                    is_thread_reply and event_thread_ts in self._bot_message_ts
                 )
-            )
-            if not reply_to_bot_thread and not in_mentioned_thread and not has_session:
-                return
+                in_mentioned_thread = (
+                    event_thread_ts is not None
+                    and event_thread_ts in self._mentioned_threads
+                )
+                has_session = (
+                    is_thread_reply
+                    and self._has_active_session_for_thread(
+                        channel_id=channel_id,
+                        thread_ts=event_thread_ts,
+                        user_id=user_id,
+                    )
+                )
+                if not reply_to_bot_thread and not in_mentioned_thread and not has_session:
+                    return
 
         if is_mentioned:
             # Strip the bot mention from the text
@@ -972,14 +1203,19 @@ 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")
+        # Only react when bot is directly addressed (DM or @mention).
+        # In listen-all channels (require_mention=false), reacting to every
+        # casual message would be noisy.
+        _should_react = is_dm or is_mentioned
+
+        if _should_react:
+            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")
+        if _should_react:
+            await self._remove_reaction(channel_id, ts, "eyes")
+            await self._add_reaction(channel_id, ts, "white_check_mark")
 
     # ----- Approval button support (Block Kit) -----
 
@@ -1073,6 +1309,20 @@ class SlackAdapter(BasePlatformAdapter):
         msg_ts = message.get("ts", "")
         channel_id = body.get("channel", {}).get("id", "")
         user_name = body.get("user", {}).get("name", "unknown")
+        user_id = body.get("user", {}).get("id", "")
+
+        # Only authorized users may click approval buttons.  Button clicks
+        # bypass the normal message auth flow in gateway/run.py, so we must
+        # check here as well.
+        allowed_csv = os.getenv("SLACK_ALLOWED_USERS", "").strip()
+        if allowed_csv:
+            allowed_ids = {uid.strip() for uid in allowed_csv.split(",") if uid.strip()}
+            if "*" not in allowed_ids and user_id not in allowed_ids:
+                logger.warning(
+                    "[Slack] Unauthorized approval click by %s (%s) — ignoring",
+                    user_name, user_id,
+                )
+                return
 
         # Map action_id to approval choice
         choice_map = {
@@ -1083,10 +1333,9 @@ class SlackAdapter(BasePlatformAdapter):
         }
         choice = choice_map.get(action_id, "deny")
 
-        # Prevent double-clicks
-        if self._approval_resolved.get(msg_ts, False):
+        # Prevent double-clicks — atomic pop; first caller gets False, others get True (default)
+        if self._approval_resolved.pop(msg_ts, True):
             return
-        self._approval_resolved[msg_ts] = True
 
         # Update the message to show the decision and remove buttons
         label_map = {
@@ -1141,8 +1390,7 @@ class SlackAdapter(BasePlatformAdapter):
         except Exception as exc:
             logger.error("Failed to resolve gateway approval from Slack button: %s", exc)
 
-        # Clean up stale approval state
-        self._approval_resolved.pop(msg_ts, None)
+        # (approval state already consumed by atomic pop above)
 
     # ----- Thread context fetching -----
 
@@ -1153,57 +1401,104 @@ class SlackAdapter(BasePlatformAdapter):
         """Fetch recent thread messages to provide context when the bot is
         mentioned mid-thread for the first time.
 
-        Returns a formatted string with thread history, or empty string on
-        failure or if the thread is empty (just the parent message).
+        This method is only called when there is NO active session for the
+        thread (guarded at the call site by _has_active_session_for_thread).
+        That guard ensures thread messages are prepended only on the very
+        first turn — after that the session history already holds them, so
+        there is no duplication across subsequent turns.
+
+        Results are cached for _THREAD_CACHE_TTL seconds per thread to avoid
+        hammering conversations.replies (Tier 3, ~50 req/min).
+
+        Returns a formatted string with prior thread history, or empty string
+        on failure or if the thread has no prior messages.
         """
+        cache_key = f"{channel_id}:{thread_ts}"
+        now = time.monotonic()
+        cached = self._thread_context_cache.get(cache_key)
+        if cached and (now - cached.fetched_at) < self._THREAD_CACHE_TTL:
+            return cached.content
+
         try:
             client = self._get_client(channel_id)
-            result = await client.conversations_replies(
-                channel=channel_id,
-                ts=thread_ts,
-                limit=limit + 1,  # +1 because it includes the current message
-                inclusive=True,
-            )
+
+            # Retry with exponential backoff for Tier-3 rate limits (429).
+            result = None
+            for attempt in range(3):
+                try:
+                    result = await client.conversations_replies(
+                        channel=channel_id,
+                        ts=thread_ts,
+                        limit=limit + 1,  # +1 because it includes the current message
+                        inclusive=True,
+                    )
+                    break
+                except Exception as exc:
+                    # Check for rate-limit error from slack_sdk
+                    err_str = str(exc).lower()
+                    is_rate_limit = (
+                        "ratelimited" in err_str
+                        or "429" in err_str
+                        or "rate_limited" in err_str
+                    )
+                    if is_rate_limit and attempt < 2:
+                        retry_after = 1.0 * (2 ** attempt)  # 1s, 2s
+                        logger.warning(
+                            "[Slack] conversations.replies rate limited; retrying in %.1fs (attempt %d/3)",
+                            retry_after, attempt + 1,
+                        )
+                        await asyncio.sleep(retry_after)
+                        continue
+                    raise
+
+            if result is None:
+                return ""
+
             messages = result.get("messages", [])
             if not messages:
                 return ""
 
+            bot_uid = self._team_bot_user_ids.get(team_id, self._bot_user_id)
             context_parts = []
             for msg in messages:
                 msg_ts = msg.get("ts", "")
-                # Skip the current message (the one that triggered this fetch)
+                # Exclude the current triggering message — it will be delivered
+                # as the user message itself, so including it here would duplicate it.
                 if msg_ts == current_ts:
                     continue
-                # Skip bot messages from ourselves
+                # Exclude our own bot messages to avoid circular context.
                 if msg.get("bot_id") or msg.get("subtype") == "bot_message":
                     continue
 
-                msg_user = msg.get("user", "unknown")
                 msg_text = msg.get("text", "").strip()
                 if not msg_text:
                     continue
 
                 # Strip bot mentions from context messages
-                bot_uid = self._team_bot_user_ids.get(team_id, self._bot_user_id)
                 if bot_uid:
                     msg_text = msg_text.replace(f"<@{bot_uid}>", "").strip()
 
-                # Mark the thread parent
+                msg_user = msg.get("user", "unknown")
                 is_parent = msg_ts == thread_ts
                 prefix = "[thread parent] " if is_parent else ""
-
-                # Resolve user name (cached)
                 name = await self._resolve_user_name(msg_user, chat_id=channel_id)
                 context_parts.append(f"{prefix}{name}: {msg_text}")
 
-            if not context_parts:
-                return ""
+            content = ""
+            if context_parts:
+                content = (
+                    "[Thread context — prior messages in this thread (not yet in conversation history):]\n"
+                    + "\n".join(context_parts)
+                    + "\n[End of thread context]\n\n"
+                )
 
-            return (
-                "[Thread context — previous messages in this thread:]\n"
-                + "\n".join(context_parts)
-                + "\n[End of thread context]\n\n"
+            self._thread_context_cache[cache_key] = _ThreadContextCache(
+                content=content,
+                fetched_at=now,
+                message_count=len(context_parts),
             )
+            return content
+
         except Exception as e:
             logger.warning("[Slack] Failed to fetch thread context: %s", e)
             return ""
@@ -1313,6 +1608,18 @@ class SlackAdapter(BasePlatformAdapter):
                     )
                     response.raise_for_status()
 
+                    # Slack may return an HTML sign-in/redirect page
+                    # instead of actual media bytes (e.g. expired token,
+                    # restricted file access).  Detect this early so we
+                    # don't cache bogus data and confuse downstream tools.
+                    ct = response.headers.get("content-type", "")
+                    if "text/html" in ct:
+                        raise ValueError(
+                            "Slack returned HTML instead of media "
+                            f"(content-type: {ct}); "
+                            "check bot token scopes and file permissions"
+                        )
+
                     if audio:
                         from gateway.platforms.base import cache_audio_from_bytes
                         return cache_audio_from_bytes(response.content, ext)
@@ -1359,3 +1666,30 @@ class SlackAdapter(BasePlatformAdapter):
                         continue
                     raise
         raise last_exc
+
+    # ── Channel mention gating ─────────────────────────────────────────────
+
+    def _slack_require_mention(self) -> bool:
+        """Return whether channel messages require an explicit bot mention.
+
+        Uses explicit-false parsing (like Discord/Matrix) rather than
+        truthy parsing, since the safe default is True (gating on).
+        Unrecognised or empty values keep gating enabled.
+        """
+        configured = self.config.extra.get("require_mention")
+        if configured is not None:
+            if isinstance(configured, str):
+                return configured.lower() not in ("false", "0", "no", "off")
+            return bool(configured)
+        return os.getenv("SLACK_REQUIRE_MENTION", "true").lower() not in ("false", "0", "no", "off")
+
+    def _slack_free_response_channels(self) -> set:
+        """Return channel IDs where no @mention is required."""
+        raw = self.config.extra.get("free_response_channels")
+        if raw is None:
+            raw = os.getenv("SLACK_FREE_RESPONSE_CHANNELS", "")
+        if isinstance(raw, list):
+            return {str(part).strip() for part in raw if str(part).strip()}
+        if isinstance(raw, str) and raw.strip():
+            return {part.strip() for part in raw.split(",") if part.strip()}
+        return set()

gateway/platforms/telegram.py

@@ -60,6 +60,7 @@ from gateway.platforms.base import (
     BasePlatformAdapter,
     MessageEvent,
     MessageType,
+    ProcessingOutcome,
     SendResult,
     cache_image_from_bytes,
     cache_audio_from_bytes,
@@ -121,6 +122,9 @@ class TelegramAdapter(BasePlatformAdapter):
     
     # Telegram message limits
     MAX_MESSAGE_LENGTH = 4096
+    # Threshold for detecting Telegram client-side message splits.
+    # When a chunk is near this limit, a continuation is almost certain.
+    _SPLIT_THRESHOLD = 4000
     MEDIA_GROUP_WAIT_SECONDS = 0.8
     
     def __init__(self, config: PlatformConfig):
@@ -140,6 +144,7 @@ class TelegramAdapter(BasePlatformAdapter):
         # Buffer rapid text messages so Telegram client-side splits of long
         # messages are aggregated into a single MessageEvent.
         self._text_batch_delay_seconds = float(os.getenv("HERMES_TELEGRAM_TEXT_BATCH_DELAY_SECONDS", "0.6"))
+        self._text_batch_split_delay_seconds = float(os.getenv("HERMES_TELEGRAM_TEXT_BATCH_SPLIT_DELAY_SECONDS", "2.0"))
         self._pending_text_batches: Dict[str, MessageEvent] = {}
         self._pending_text_batch_tasks: Dict[str, asyncio.Task] = {}
         self._token_lock_identity: Optional[str] = None
@@ -513,6 +518,45 @@ class TelegramAdapter(BasePlatformAdapter):
 
             # Build the application
             builder = Application.builder().token(self.config.token)
+            custom_base_url = self.config.extra.get("base_url")
+            if custom_base_url:
+                builder = builder.base_url(custom_base_url)
+                builder = builder.base_file_url(
+                    self.config.extra.get("base_file_url", custom_base_url)
+                )
+                logger.info(
+                    "[%s] Using custom Telegram base_url: %s",
+                    self.name, custom_base_url,
+                )
+
+            # PTB defaults (pool_timeout=1s) are too aggressive on flaky networks and
+            # can trigger "Pool timeout: All connections in the connection pool are occupied"
+            # during reconnect/bootstrap. Use safer defaults and allow env overrides.
+            def _env_int(name: str, default: int) -> int:
+                try:
+                    return int(os.getenv(name, str(default)))
+                except (TypeError, ValueError):
+                    return default
+
+            def _env_float(name: str, default: float) -> float:
+                try:
+                    return float(os.getenv(name, str(default)))
+                except (TypeError, ValueError):
+                    return default
+
+            request_kwargs = {
+                "connection_pool_size": _env_int("HERMES_TELEGRAM_HTTP_POOL_SIZE", 512),
+                "pool_timeout": _env_float("HERMES_TELEGRAM_HTTP_POOL_TIMEOUT", 8.0),
+                "connect_timeout": _env_float("HERMES_TELEGRAM_HTTP_CONNECT_TIMEOUT", 10.0),
+                "read_timeout": _env_float("HERMES_TELEGRAM_HTTP_READ_TIMEOUT", 20.0),
+                "write_timeout": _env_float("HERMES_TELEGRAM_HTTP_WRITE_TIMEOUT", 20.0),
+            }
+
+            proxy_configured = any(
+                (os.getenv(k) or "").strip()
+                for k in ("HTTPS_PROXY", "HTTP_PROXY", "ALL_PROXY", "https_proxy", "http_proxy", "all_proxy")
+            )
+            disable_fallback = (os.getenv("HERMES_TELEGRAM_DISABLE_FALLBACK_IPS", "").strip().lower() in ("1", "true", "yes", "on"))
             fallback_ips = self._fallback_ips()
             if not fallback_ips:
                 fallback_ips = await discover_fallback_ips()
@@ -521,16 +565,32 @@ class TelegramAdapter(BasePlatformAdapter):
                     self.name,
                     ", ".join(fallback_ips),
                 )
-            if fallback_ips:
+
+            if fallback_ips and not proxy_configured and not disable_fallback:
                 logger.info(
                     "[%s] Telegram fallback IPs active: %s",
                     self.name,
                     ", ".join(fallback_ips),
                 )
-                transport = TelegramFallbackTransport(fallback_ips)
-                request = HTTPXRequest(httpx_kwargs={"transport": transport})
-                get_updates_request = HTTPXRequest(httpx_kwargs={"transport": transport})
-                builder = builder.request(request).get_updates_request(get_updates_request)
+                # Keep request/update pools separate to reduce contention during
+                # polling reconnect + bot API bootstrap/delete_webhook calls.
+                request = HTTPXRequest(
+                    **request_kwargs,
+                    httpx_kwargs={"transport": TelegramFallbackTransport(fallback_ips)},
+                )
+                get_updates_request = HTTPXRequest(
+                    **request_kwargs,
+                    httpx_kwargs={"transport": TelegramFallbackTransport(fallback_ips)},
+                )
+            else:
+                if proxy_configured:
+                    logger.info("[%s] Proxy configured; skipping Telegram fallback-IP transport", self.name)
+                elif disable_fallback:
+                    logger.info("[%s] Telegram fallback-IP transport disabled via env", self.name)
+                request = HTTPXRequest(**request_kwargs)
+                get_updates_request = HTTPXRequest(**request_kwargs)
+
+            builder = builder.request(request).get_updates_request(get_updates_request)
             self._app = builder.build()
             self._bot = self._app.bot
             
@@ -1398,6 +1458,15 @@ class TelegramAdapter(BasePlatformAdapter):
                     await query.answer(text="Invalid approval data.")
                     return
 
+                # Only authorized users may click approval buttons.
+                caller_id = str(getattr(query.from_user, "id", ""))
+                allowed_csv = os.getenv("TELEGRAM_ALLOWED_USERS", "").strip()
+                if allowed_csv:
+                    allowed_ids = {uid.strip() for uid in allowed_csv.split(",") if uid.strip()}
+                    if "*" not in allowed_ids and caller_id not in allowed_ids:
+                        await query.answer(text="⛔ You are not authorized to approve commands.")
+                        return
+
                 session_key = self._approval_state.pop(approval_id, None)
                 if not session_key:
                     await query.answer(text="This approval has already been resolved.")
@@ -2151,12 +2220,15 @@ class TelegramAdapter(BasePlatformAdapter):
         """
         key = self._text_batch_key(event)
         existing = self._pending_text_batches.get(key)
+        chunk_len = len(event.text or "")
         if existing is None:
+            event._last_chunk_len = chunk_len  # type: ignore[attr-defined]
             self._pending_text_batches[key] = event
         else:
             # Append text from the follow-up chunk
             if event.text:
                 existing.text = f"{existing.text}\n{event.text}" if existing.text else event.text
+            existing._last_chunk_len = chunk_len  # type: ignore[attr-defined]
             # Merge any media that might be attached
             if event.media_urls:
                 existing.media_urls.extend(event.media_urls)
@@ -2171,10 +2243,22 @@ class TelegramAdapter(BasePlatformAdapter):
         )
 
     async def _flush_text_batch(self, key: str) -> None:
-        """Wait for the quiet period then dispatch the aggregated text."""
+        """Wait for the quiet period then dispatch the aggregated text.
+
+        Uses a longer delay when the latest chunk is near Telegram's 4096-char
+        split point, since a continuation chunk is almost certain.
+        """
         current_task = asyncio.current_task()
         try:
-            await asyncio.sleep(self._text_batch_delay_seconds)
+            # Adaptive delay: if the latest chunk is near Telegram's 4096-char
+            # split point, a continuation is almost certain — wait longer.
+            pending = self._pending_text_batches.get(key)
+            last_len = getattr(pending, "_last_chunk_len", 0) if pending else 0
+            if last_len >= self._SPLIT_THRESHOLD:
+                delay = self._text_batch_split_delay_seconds
+            else:
+                delay = self._text_batch_delay_seconds
+            await asyncio.sleep(delay)
             event = self._pending_text_batches.pop(key, None)
             if not event:
                 return
@@ -2704,7 +2788,7 @@ class TelegramAdapter(BasePlatformAdapter):
         if chat_id and message_id:
             await self._set_reaction(chat_id, message_id, "\U0001f440")
 
-    async def on_processing_complete(self, event: MessageEvent, success: bool) -> None:
+    async def on_processing_complete(self, event: MessageEvent, outcome: ProcessingOutcome) -> None:
         """Swap the in-progress reaction for a final success/failure reaction.
 
         Unlike Discord (additive reactions), Telegram's set_message_reaction
@@ -2714,5 +2798,9 @@ class TelegramAdapter(BasePlatformAdapter):
             return
         chat_id = getattr(event.source, "chat_id", None)
         message_id = getattr(event, "message_id", None)
-        if chat_id and message_id:
-            await self._set_reaction(chat_id, message_id, "\u2705" if success else "\u274c")
+        if chat_id and message_id and outcome != ProcessingOutcome.CANCELLED:
+            await self._set_reaction(
+                chat_id,
+                message_id,
+                "\U0001f44d" if outcome == ProcessingOutcome.SUCCESS else "\U0001f44e",
+            )

gateway/platforms/telegram_network.py

@@ -45,11 +45,9 @@ _SEED_FALLBACK_IPS: list[str] = ["149.154.167.220"]
 
 
 def _resolve_proxy_url() -> str | None:
-    for key in ("HTTPS_PROXY", "HTTP_PROXY", "ALL_PROXY", "https_proxy", "http_proxy", "all_proxy"):
-        value = (os.environ.get(key) or "").strip()
-        if value:
-            return value
-    return None
+    # Delegate to shared implementation (env vars + macOS system proxy detection)
+    from gateway.platforms.base import resolve_proxy_url
+    return resolve_proxy_url()
 
 
 class TelegramFallbackTransport(httpx.AsyncBaseTransport):
@@ -112,7 +110,8 @@ class TelegramFallbackTransport(httpx.AsyncBaseTransport):
                 logger.warning("[Telegram] Fallback IP %s failed: %s", ip, exc)
                 continue
 
-        assert last_error is not None
+        if last_error is None:
+            raise RuntimeError("All Telegram fallback IPs exhausted but no error was recorded")
         raise last_error
 
     async def aclose(self) -> None:

gateway/platforms/webhook.py

@@ -186,13 +186,23 @@ class WebhookAdapter(BasePlatformAdapter):
         if deliver_type == "github_comment":
             return await self._deliver_github_comment(content, delivery)
 
-        # Cross-platform delivery (telegram, discord, etc.)
+        # Cross-platform delivery — any platform with a gateway adapter
         if self.gateway_runner and deliver_type in (
             "telegram",
             "discord",
             "slack",
             "signal",
             "sms",
+            "whatsapp",
+            "matrix",
+            "mattermost",
+            "homeassistant",
+            "email",
+            "dingtalk",
+            "feishu",
+            "wecom",
+            "weixin",
+            "bluebubbles",
         ):
             return await self._deliver_cross_platform(
                 deliver_type, content, delivery
@@ -262,7 +272,7 @@ class WebhookAdapter(BasePlatformAdapter):
                 ", ".join(self._dynamic_routes.keys()) or "(none)",
             )
         except Exception as e:
-            logger.warning("[webhook] Failed to reload dynamic routes: %s", e)
+            logger.error("[webhook] Failed to reload dynamic routes: %s", e)
 
     async def _handle_webhook(self, request: "web.Request") -> "web.Response":
         """POST /webhooks/{route_name} — receive and process a webhook event."""

gateway/platforms/wecom.py

@@ -143,6 +143,9 @@ class WeComAdapter(BasePlatformAdapter):
     """WeCom AI Bot adapter backed by a persistent WebSocket connection."""
 
     MAX_MESSAGE_LENGTH = MAX_MESSAGE_LENGTH
+    # Threshold for detecting WeCom client-side message splits.
+    # When a chunk is near the 4000-char limit, a continuation is almost certain.
+    _SPLIT_THRESHOLD = 3900
 
     def __init__(self, config: PlatformConfig):
         super().__init__(config, Platform.WECOM)
@@ -172,6 +175,13 @@ class WeComAdapter(BasePlatformAdapter):
         self._seen_messages: Dict[str, float] = {}
         self._reply_req_ids: Dict[str, str] = {}
 
+        # Text batching: merge rapid successive messages (Telegram-style).
+        # WeCom clients split long messages around 4000 chars.
+        self._text_batch_delay_seconds = float(os.getenv("HERMES_WECOM_TEXT_BATCH_DELAY_SECONDS", "0.6"))
+        self._text_batch_split_delay_seconds = float(os.getenv("HERMES_WECOM_TEXT_BATCH_SPLIT_DELAY_SECONDS", "2.0"))
+        self._pending_text_batches: Dict[str, MessageEvent] = {}
+        self._pending_text_batch_tasks: Dict[str, asyncio.Task] = {}
+
     # ------------------------------------------------------------------
     # Connection lifecycle
     # ------------------------------------------------------------------
@@ -519,7 +529,82 @@ class WeComAdapter(BasePlatformAdapter):
             timestamp=datetime.now(tz=timezone.utc),
         )
 
-        await self.handle_message(event)
+        # Only batch plain text messages — commands, media, etc. dispatch
+        # immediately since they won't be split by the WeCom client.
+        if message_type == MessageType.TEXT and self._text_batch_delay_seconds > 0:
+            self._enqueue_text_event(event)
+        else:
+            await self.handle_message(event)
+
+    # ------------------------------------------------------------------
+    # Text message aggregation (handles WeCom client-side splits)
+    # ------------------------------------------------------------------
+
+    def _text_batch_key(self, event: MessageEvent) -> str:
+        """Session-scoped key for text message batching."""
+        from gateway.session import build_session_key
+        return build_session_key(
+            event.source,
+            group_sessions_per_user=self.config.extra.get("group_sessions_per_user", True),
+            thread_sessions_per_user=self.config.extra.get("thread_sessions_per_user", False),
+        )
+
+    def _enqueue_text_event(self, event: MessageEvent) -> None:
+        """Buffer a text event and reset the flush timer.
+
+        When WeCom splits a long user message at 4000 chars, the chunks
+        arrive within a few hundred milliseconds.  This merges them into
+        a single event before dispatching.
+        """
+        key = self._text_batch_key(event)
+        existing = self._pending_text_batches.get(key)
+        chunk_len = len(event.text or "")
+        if existing is None:
+            event._last_chunk_len = chunk_len  # type: ignore[attr-defined]
+            self._pending_text_batches[key] = event
+        else:
+            if event.text:
+                existing.text = f"{existing.text}\n{event.text}" if existing.text else event.text
+            existing._last_chunk_len = chunk_len  # type: ignore[attr-defined]
+            # Merge any media that might be attached
+            if event.media_urls:
+                existing.media_urls.extend(event.media_urls)
+                existing.media_types.extend(event.media_types)
+
+        # Cancel any pending flush and restart the timer
+        prior_task = self._pending_text_batch_tasks.get(key)
+        if prior_task and not prior_task.done():
+            prior_task.cancel()
+        self._pending_text_batch_tasks[key] = asyncio.create_task(
+            self._flush_text_batch(key)
+        )
+
+    async def _flush_text_batch(self, key: str) -> None:
+        """Wait for the quiet period then dispatch the aggregated text.
+
+        Uses a longer delay when the latest chunk is near WeCom's 4000-char
+        split point, since a continuation chunk is almost certain.
+        """
+        current_task = asyncio.current_task()
+        try:
+            pending = self._pending_text_batches.get(key)
+            last_len = getattr(pending, "_last_chunk_len", 0) if pending else 0
+            if last_len >= self._SPLIT_THRESHOLD:
+                delay = self._text_batch_split_delay_seconds
+            else:
+                delay = self._text_batch_delay_seconds
+            await asyncio.sleep(delay)
+            event = self._pending_text_batches.pop(key, None)
+            if not event:
+                return
+            logger.info(
+                "[WeCom] Flushing text batch %s (%d chars)",
+                key, len(event.text or ""),
+            )
+            await self.handle_message(event)
+        finally:
+            if self._pending_text_batch_tasks.get(key) is current_task:
+                self._pending_text_batch_tasks.pop(key, None)
 
     @staticmethod
     def _extract_text(body: Dict[str, Any]) -> Tuple[str, Optional[str]]:
@@ -611,7 +696,11 @@ class WeComAdapter(BasePlatformAdapter):
 
             if kind == "image":
                 ext = self._detect_image_ext(raw)
-                return cache_image_from_bytes(raw, ext), self._mime_for_ext(ext, fallback="image/jpeg")
+                try:
+                    return cache_image_from_bytes(raw, ext), self._mime_for_ext(ext, fallback="image/jpeg")
+                except ValueError as exc:
+                    logger.warning("[%s] Rejected non-image bytes: %s", self.name, exc)
+                    return None
 
             filename = str(media.get("filename") or media.get("name") or "wecom_file")
             return cache_document_from_bytes(raw, filename), mimetypes.guess_type(filename)[0] or "application/octet-stream"
@@ -637,7 +726,11 @@ class WeComAdapter(BasePlatformAdapter):
         content_type = str(headers.get("content-type") or "").split(";", 1)[0].strip() or "application/octet-stream"
         if kind == "image":
             ext = self._guess_extension(url, content_type, fallback=self._detect_image_ext(raw))
-            return cache_image_from_bytes(raw, ext), content_type or self._mime_for_ext(ext, fallback="image/jpeg")
+            try:
+                return cache_image_from_bytes(raw, ext), content_type or self._mime_for_ext(ext, fallback="image/jpeg")
+            except ValueError as exc:
+                logger.warning("[%s] Rejected non-image bytes from %s: %s", self.name, url, exc)
+                return None
 
         filename = self._guess_filename(url, headers.get("content-disposition"), content_type)
         return cache_document_from_bytes(raw, filename), content_type

gateway/restart.py

@@ -0,0 +1,20 @@
+"""Shared gateway restart constants and parsing helpers."""
+
+from hermes_cli.config import DEFAULT_CONFIG
+
+# EX_TEMPFAIL from sysexits.h — used to ask the service manager to restart
+# the gateway after a graceful drain/reload path completes.
+GATEWAY_SERVICE_RESTART_EXIT_CODE = 75
+
+DEFAULT_GATEWAY_RESTART_DRAIN_TIMEOUT = float(
+    DEFAULT_CONFIG["agent"]["restart_drain_timeout"]
+)
+
+
+def parse_restart_drain_timeout(raw: object) -> float:
+    """Parse a configured drain timeout, falling back to the shared default."""
+    try:
+        value = float(raw) if str(raw or "").strip() else DEFAULT_GATEWAY_RESTART_DRAIN_TIMEOUT
+    except (TypeError, ValueError):
+        return DEFAULT_GATEWAY_RESTART_DRAIN_TIMEOUT
+    return max(0.0, value)

gateway/session.py

@@ -32,9 +32,6 @@ def _now() -> datetime:
 # PII redaction helpers
 # ---------------------------------------------------------------------------
 
-_PHONE_RE = re.compile(r"^\+?\d[\d\-\s]{6,}$")
-
-
 def _hash_id(value: str) -> str:
     """Deterministic 12-char hex hash of an identifier."""
     return hashlib.sha256(value.encode("utf-8")).hexdigest()[:12]
@@ -58,10 +55,6 @@ def _hash_chat_id(value: str) -> str:
     return _hash_id(value)
 
 
-def _looks_like_phone(value: str) -> bool:
-    """Return True if *value* looks like a phone number (E.164 or similar)."""
-    return bool(_PHONE_RE.match(value.strip()))
-
 from .config import (
     Platform,
     GatewayConfig,
@@ -144,15 +137,6 @@ class SessionSource:
             chat_id_alt=data.get("chat_id_alt"),
         )
     
-    @classmethod
-    def local_cli(cls) -> "SessionSource":
-        """Create a source representing the local CLI."""
-        return cls(
-            platform=Platform.LOCAL,
-            chat_id="cli",
-            chat_name="CLI terminal",
-            chat_type="dm",
-        )
 
 
 @dataclass
@@ -193,6 +177,7 @@ _PII_SAFE_PLATFORMS = frozenset({
     Platform.WHATSAPP,
     Platform.SIGNAL,
     Platform.TELEGRAM,
+    Platform.BLUEBUBBLES,
 })
 """Platforms where user IDs can be safely redacted (no in-message mention system
 that requires raw IDs).  Discord is excluded because mentions use ``<@user_id>``
@@ -509,8 +494,7 @@ class SessionStore:
     """
     
     def __init__(self, sessions_dir: Path, config: GatewayConfig,
-                 has_active_processes_fn=None,
-                 on_auto_reset=None):
+                 has_active_processes_fn=None):
         self.sessions_dir = sessions_dir
         self.config = config
         self._entries: Dict[str, SessionEntry] = {}
@@ -769,41 +753,6 @@ class SessionStore:
             except Exception as e:
                 print(f"[gateway] Warning: Failed to create SQLite session: {e}")
 
-        # Seed new DM thread sessions with parent DM session history.
-        # When a bot reply creates a Slack thread and the user responds in it,
-        # the thread gets a new session (keyed by thread_ts).  Without seeding,
-        # the thread session starts with zero context — the user's original
-        # question and the bot's answer are invisible.  Fix: copy the parent
-        # DM session's transcript into the new thread session so context carries
-        # over while still keeping threads isolated from each other.
-        if (
-            source.chat_type == "dm"
-            and source.thread_id
-            and entry.created_at == entry.updated_at  # brand-new session
-            and not was_auto_reset
-        ):
-            parent_source = SessionSource(
-                platform=source.platform,
-                chat_id=source.chat_id,
-                chat_type="dm",
-                user_id=source.user_id,
-                # no thread_id — this is the parent DM session
-            )
-            parent_key = self._generate_session_key(parent_source)
-            with self._lock:
-                parent_entry = self._entries.get(parent_key)
-            if parent_entry and parent_entry.session_id != entry.session_id:
-                try:
-                    parent_history = self.load_transcript(parent_entry.session_id)
-                    if parent_history:
-                        self.rewrite_transcript(entry.session_id, parent_history)
-                        logger.info(
-                            "[Session] Seeded DM thread session %s with %d messages from parent %s",
-                            entry.session_id, len(parent_history), parent_entry.session_id,
-                        )
-                except Exception as e:
-                    logger.warning("[Session] Failed to seed thread session: %s", e)
-
         return entry
 
     def update_session(

gateway/session_context.py

@@ -0,0 +1,113 @@
+"""
+Session-scoped context variables for the Hermes gateway.
+
+Replaces the previous ``os.environ``-based session state
+(``HERMES_SESSION_PLATFORM``, ``HERMES_SESSION_CHAT_ID``, etc.) with
+Python's ``contextvars.ContextVar``.
+
+**Why this matters**
+
+The gateway processes messages concurrently via ``asyncio``.  When two
+messages arrive at the same time the old code did:
+
+    os.environ["HERMES_SESSION_THREAD_ID"] = str(context.source.thread_id)
+
+Because ``os.environ`` is *process-global*, Message A's value was
+silently overwritten by Message B before Message A's agent finished
+running.  Background-task notifications and tool calls therefore routed
+to the wrong thread.
+
+``contextvars.ContextVar`` values are *task-local*: each ``asyncio``
+task (and any ``run_in_executor`` thread it spawns) gets its own copy,
+so concurrent messages never interfere.
+
+**Backward compatibility**
+
+The public helper ``get_session_env(name, default="")`` mirrors the old
+``os.getenv("HERMES_SESSION_*", ...)`` calls.  Existing tool code only
+needs to replace the import + call site:
+
+    # before
+    import os
+    platform = os.getenv("HERMES_SESSION_PLATFORM", "")
+
+    # after
+    from gateway.session_context import get_session_env
+    platform = get_session_env("HERMES_SESSION_PLATFORM", "")
+"""
+
+from contextvars import ContextVar
+
+# ---------------------------------------------------------------------------
+# Per-task session variables
+# ---------------------------------------------------------------------------
+
+_SESSION_PLATFORM: ContextVar[str] = ContextVar("HERMES_SESSION_PLATFORM", default="")
+_SESSION_CHAT_ID: ContextVar[str] = ContextVar("HERMES_SESSION_CHAT_ID", default="")
+_SESSION_CHAT_NAME: ContextVar[str] = ContextVar("HERMES_SESSION_CHAT_NAME", default="")
+_SESSION_THREAD_ID: ContextVar[str] = ContextVar("HERMES_SESSION_THREAD_ID", default="")
+
+_VAR_MAP = {
+    "HERMES_SESSION_PLATFORM": _SESSION_PLATFORM,
+    "HERMES_SESSION_CHAT_ID": _SESSION_CHAT_ID,
+    "HERMES_SESSION_CHAT_NAME": _SESSION_CHAT_NAME,
+    "HERMES_SESSION_THREAD_ID": _SESSION_THREAD_ID,
+}
+
+
+def set_session_vars(
+    platform: str = "",
+    chat_id: str = "",
+    chat_name: str = "",
+    thread_id: str = "",
+) -> list:
+    """Set all session context variables and return reset tokens.
+
+    Call ``clear_session_vars(tokens)`` in a ``finally`` block to restore
+    the previous values when the handler exits.
+
+    Returns a list of ``Token`` objects (one per variable) that can be
+    passed to ``clear_session_vars``.
+    """
+    tokens = [
+        _SESSION_PLATFORM.set(platform),
+        _SESSION_CHAT_ID.set(chat_id),
+        _SESSION_CHAT_NAME.set(chat_name),
+        _SESSION_THREAD_ID.set(thread_id),
+    ]
+    return tokens
+
+
+def clear_session_vars(tokens: list) -> None:
+    """Restore session context variables to their pre-handler values."""
+    if not tokens:
+        return
+    vars_in_order = [
+        _SESSION_PLATFORM,
+        _SESSION_CHAT_ID,
+        _SESSION_CHAT_NAME,
+        _SESSION_THREAD_ID,
+    ]
+    for var, token in zip(vars_in_order, tokens):
+        var.reset(token)
+
+
+def get_session_env(name: str, default: str = "") -> str:
+    """Read a session context variable by its legacy ``HERMES_SESSION_*`` name.
+
+    Drop-in replacement for ``os.getenv("HERMES_SESSION_*", default)``.
+
+    Resolution order:
+    1. Context variable (set by the gateway for concurrency-safe access)
+    2. ``os.environ`` (used by CLI, cron scheduler, and tests)
+    3. *default*
+    """
+    import os
+
+    var = _VAR_MAP.get(name)
+    if var is not None:
+        value = var.get()
+        if value:
+            return value
+    # Fall back to os.environ for CLI, cron, and test compatibility
+    return os.getenv(name, default)

gateway/status.py

@@ -14,6 +14,8 @@ concurrently under distinct configurations).
 import hashlib
 import json
 import os
+import signal
+import subprocess
 import sys
 from datetime import datetime, timezone
 from pathlib import Path
@@ -23,6 +25,7 @@ from typing import Any, Optional
 _GATEWAY_KIND = "hermes-gateway"
 _RUNTIME_STATUS_FILE = "gateway_state.json"
 _LOCKS_DIRNAME = "gateway-locks"
+_IS_WINDOWS = sys.platform == "win32"
 
 
 def _get_pid_path() -> Path:
@@ -49,6 +52,33 @@ def _utc_now_iso() -> str:
     return datetime.now(timezone.utc).isoformat()
 
 
+def terminate_pid(pid: int, *, force: bool = False) -> None:
+    """Terminate a PID with platform-appropriate force semantics.
+
+    POSIX uses SIGTERM/SIGKILL. Windows uses taskkill /T /F for true force-kill
+    because os.kill(..., SIGTERM) is not equivalent to a tree-killing hard stop.
+    """
+    if force and _IS_WINDOWS:
+        try:
+            result = subprocess.run(
+                ["taskkill", "/PID", str(pid), "/T", "/F"],
+                capture_output=True,
+                text=True,
+                timeout=10,
+            )
+        except FileNotFoundError:
+            os.kill(pid, signal.SIGTERM)
+            return
+
+        if result.returncode != 0:
+            details = (result.stderr or result.stdout or "").strip()
+            raise OSError(details or f"taskkill failed for PID {pid}")
+        return
+
+    sig = signal.SIGTERM if not force else getattr(signal, "SIGKILL", signal.SIGTERM)
+    os.kill(pid, sig)
+
+
 def _scope_hash(identity: str) -> str:
     return hashlib.sha256(identity.encode("utf-8")).hexdigest()[:16]
 
@@ -128,6 +158,8 @@ def _build_runtime_status_record() -> dict[str, Any]:
     payload.update({
         "gateway_state": "starting",
         "exit_reason": None,
+        "restart_requested": False,
+        "active_agents": 0,
         "platforms": {},
         "updated_at": _utc_now_iso(),
     })
@@ -188,6 +220,8 @@ def write_runtime_status(
     *,
     gateway_state: Optional[str] = None,
     exit_reason: Optional[str] = None,
+    restart_requested: Optional[bool] = None,
+    active_agents: Optional[int] = None,
     platform: Optional[str] = None,
     platform_state: Optional[str] = None,
     error_code: Optional[str] = None,
@@ -206,6 +240,10 @@ def write_runtime_status(
         payload["gateway_state"] = gateway_state
     if exit_reason is not None:
         payload["exit_reason"] = exit_reason
+    if restart_requested is not None:
+        payload["restart_requested"] = bool(restart_requested)
+    if active_agents is not None:
+        payload["active_agents"] = max(0, int(active_agents))
 
     if platform is not None:
         platform_payload = payload["platforms"].get(platform, {})

gateway/stream_consumer.py

@@ -136,7 +136,34 @@ class GatewayStreamConsumer:
 
                 if should_edit and self._accumulated:
                     # Split overflow: if accumulated text exceeds the platform
-                    # limit, finalize the current message and start a new one.
+                    # limit, split into properly sized chunks.
+                    if (
+                        len(self._accumulated) > _safe_limit
+                        and self._message_id is None
+                    ):
+                        # No existing message to edit (first message or after a
+                        # segment break).  Use truncate_message — the same
+                        # helper the non-streaming path uses — to split with
+                        # proper word/code-fence boundaries and chunk
+                        # indicators like "(1/2)".
+                        chunks = self.adapter.truncate_message(
+                            self._accumulated, _safe_limit
+                        )
+                        for chunk in chunks:
+                            await self._send_new_chunk(chunk, self._message_id)
+                        self._accumulated = ""
+                        self._last_sent_text = ""
+                        self._last_edit_time = time.monotonic()
+                        if got_done:
+                            return
+                        if got_segment_break:
+                            self._message_id = None
+                            self._fallback_final_send = False
+                            self._fallback_prefix = ""
+                        continue
+
+                    # Existing message: edit it with the first chunk, then
+                    # start a new message for the overflow remainder.
                     while (
                         len(self._accumulated) > _safe_limit
                         and self._message_id is not None
@@ -178,11 +205,20 @@ class GatewayStreamConsumer:
                             await self._send_or_edit(self._accumulated)
                     return
 
-                # Tool boundary: the should_edit block above already flushed
-                # accumulated text without a cursor.  Reset state so the next
-                # text chunk creates a fresh message below any tool-progress
-                # messages the gateway sent in between.
-                if got_segment_break:
+                # Tool boundary: reset message state so the next text chunk
+                # creates a fresh message below any tool-progress messages.
+                #
+                # Exception: when _message_id is "__no_edit__" the platform
+                # never returned a real message ID (e.g. Signal, webhook with
+                # github_comment delivery).  Resetting to None would re-enter
+                # the "first send" path on every tool boundary and post one
+                # platform message per tool call — that is what caused 155
+                # comments under a single PR.  Instead, keep all state so the
+                # full continuation is delivered once via _send_fallback_final.
+                # (When editing fails mid-stream due to flood control the id is
+                # a real string like "msg_1", not "__no_edit__", so that case
+                # still resets and creates a fresh segment as intended.)
+                if got_segment_break and self._message_id != "__no_edit__":
                     self._message_id = None
                     self._accumulated = ""
                     self._last_sent_text = ""
@@ -226,6 +262,34 @@ class GatewayStreamConsumer:
         # Strip trailing whitespace/newlines but preserve leading content
         return cleaned.rstrip()
 
+    async def _send_new_chunk(self, text: str, reply_to_id: Optional[str]) -> Optional[str]:
+        """Send a new message chunk, optionally threaded to a previous message.
+
+        Returns the message_id so callers can thread subsequent chunks.
+        """
+        text = self._clean_for_display(text)
+        if not text.strip():
+            return reply_to_id
+        try:
+            meta = dict(self.metadata) if self.metadata else {}
+            result = await self.adapter.send(
+                chat_id=self.chat_id,
+                content=text,
+                reply_to=reply_to_id,
+                metadata=meta,
+            )
+            if result.success and result.message_id:
+                self._message_id = str(result.message_id)
+                self._already_sent = True
+                self._last_sent_text = text
+                return str(result.message_id)
+            else:
+                self._edit_supported = False
+                return reply_to_id
+        except Exception as e:
+            logger.error("Stream send chunk error: %s", e)
+            return reply_to_id
+
     def _visible_prefix(self) -> str:
         """Return the visible text already shown in the streamed message."""
         prefix = self._last_sent_text or ""

hermes_cli/auth.py

@@ -70,7 +70,6 @@ DEFAULT_CODEX_BASE_URL = "https://chatgpt.com/backend-api/codex"
 DEFAULT_QWEN_BASE_URL = "https://portal.qwen.ai/v1"
 DEFAULT_GITHUB_MODELS_BASE_URL = "https://api.githubcopilot.com"
 DEFAULT_COPILOT_ACP_BASE_URL = "acp://copilot"
-DEFAULT_GEMINI_BASE_URL = "https://generativelanguage.googleapis.com/v1beta/openai"
 CODEX_OAUTH_CLIENT_ID = "app_EMoamEEZ73f0CkXaXp7hrann"
 CODEX_OAUTH_TOKEN_URL = "https://auth.openai.com/oauth/token"
 CODEX_ACCESS_TOKEN_REFRESH_SKEW_SECONDS = 120
@@ -199,6 +198,14 @@ PROVIDER_REGISTRY: Dict[str, ProviderConfig] = {
         api_key_env_vars=("DEEPSEEK_API_KEY",),
         base_url_env_var="DEEPSEEK_BASE_URL",
     ),
+    "xai": ProviderConfig(
+        id="xai",
+        name="xAI",
+        auth_type="api_key",
+        inference_base_url="https://api.x.ai/v1",
+        api_key_env_vars=("XAI_API_KEY",),
+        base_url_env_var="XAI_BASE_URL",
+    ),
     "ai-gateway": ProviderConfig(
         id="ai-gateway",
         name="AI Gateway",
@@ -250,7 +257,7 @@ PROVIDER_REGISTRY: Dict[str, ProviderConfig] = {
 # Kimi Code Endpoint Detection
 # =============================================================================
 
-# Kimi Code (platform.kimi.ai) issues keys prefixed "sk-kimi-" that only work
+# Kimi Code (kimi.com/code) issues keys prefixed "sk-kimi-" that only work
 # on api.kimi.com/coding/v1.  Legacy keys from platform.moonshot.ai work on
 # api.moonshot.ai/v1 (the default).  Auto-detect when user hasn't set
 # KIMI_BASE_URL explicitly.
@@ -705,6 +712,27 @@ def write_credential_pool(provider_id: str, entries: List[Dict[str, Any]]) -> Pa
         return _save_auth_store(auth_store)
 
 
+def suppress_credential_source(provider_id: str, source: str) -> None:
+    """Mark a credential source as suppressed so it won't be re-seeded."""
+    with _auth_store_lock():
+        auth_store = _load_auth_store()
+        suppressed = auth_store.setdefault("suppressed_sources", {})
+        provider_list = suppressed.setdefault(provider_id, [])
+        if source not in provider_list:
+            provider_list.append(source)
+        _save_auth_store(auth_store)
+
+
+def is_source_suppressed(provider_id: str, source: str) -> bool:
+    """Check if a credential source has been suppressed by the user."""
+    try:
+        auth_store = _load_auth_store()
+        suppressed = auth_store.get("suppressed_sources", {})
+        return source in suppressed.get(provider_id, [])
+    except Exception:
+        return False
+
+
 def get_provider_auth_state(provider_id: str) -> Optional[Dict[str, Any]]:
     """Return persisted auth state for a provider, or None."""
     auth_store = _load_auth_store()
@@ -717,6 +745,57 @@ def get_active_provider() -> Optional[str]:
     return auth_store.get("active_provider")
 
 
+def is_provider_explicitly_configured(provider_id: str) -> bool:
+    """Return True only if the user has explicitly configured this provider.
+
+    Checks:
+      1. active_provider in auth.json matches
+      2. model.provider in config.yaml matches
+      3. Provider-specific env vars are set (e.g. ANTHROPIC_API_KEY)
+
+    This is used to gate auto-discovery of external credentials (e.g.
+    Claude Code's ~/.claude/.credentials.json) so they are never used
+    without the user's explicit choice.  See PR #4210 for the same
+    pattern applied to the setup wizard gate.
+    """
+    normalized = (provider_id or "").strip().lower()
+
+    # 1. Check auth.json active_provider
+    try:
+        auth_store = _load_auth_store()
+        active = (auth_store.get("active_provider") or "").strip().lower()
+        if active and active == normalized:
+            return True
+    except Exception:
+        pass
+
+    # 2. Check config.yaml model.provider
+    try:
+        from hermes_cli.config import load_config
+        cfg = load_config()
+        model_cfg = cfg.get("model")
+        if isinstance(model_cfg, dict):
+            cfg_provider = (model_cfg.get("provider") or "").strip().lower()
+            if cfg_provider == normalized:
+                return True
+    except Exception:
+        pass
+
+    # 3. Check provider-specific env vars
+    # Exclude CLAUDE_CODE_OAUTH_TOKEN — it's set by Claude Code itself,
+    # not by the user explicitly configuring anthropic in Hermes.
+    _IMPLICIT_ENV_VARS = {"CLAUDE_CODE_OAUTH_TOKEN"}
+    pconfig = PROVIDER_REGISTRY.get(normalized)
+    if pconfig and pconfig.auth_type == "api_key":
+        for env_var in pconfig.api_key_env_vars:
+            if env_var in _IMPLICIT_ENV_VARS:
+                continue
+            if has_usable_secret(os.getenv(env_var, "")):
+                return True
+
+    return False
+
+
 def clear_provider_auth(provider_id: Optional[str] = None) -> bool:
     """
     Clear auth state for a provider. Used by `hermes logout`.
@@ -819,7 +898,7 @@ def resolve_provider(
     _PROVIDER_ALIASES = {
         "glm": "zai", "z-ai": "zai", "z.ai": "zai", "zhipu": "zai",
         "google": "gemini", "google-gemini": "gemini", "google-ai-studio": "gemini",
-        "kimi": "kimi-coding", "moonshot": "kimi-coding",
+        "kimi": "kimi-coding", "kimi-for-coding": "kimi-coding", "moonshot": "kimi-coding",
         "minimax-china": "minimax-cn", "minimax_cn": "minimax-cn",
         "claude": "anthropic", "claude-code": "anthropic",
         "github": "copilot", "github-copilot": "copilot",
@@ -1442,7 +1521,15 @@ def _resolve_verify(
     if effective_insecure:
         return False
     if effective_ca:
-        return str(effective_ca)
+        ca_path = str(effective_ca)
+        if not os.path.isfile(ca_path):
+            import logging
+            logging.getLogger("hermes.auth").warning(
+                "CA bundle path does not exist: %s — falling back to default certificates",
+                ca_path,
+            )
+            return True
+        return ca_path
     return True
 
 
@@ -2342,33 +2429,6 @@ def resolve_external_process_provider_credentials(provider_id: str) -> Dict[str,
     }
 
 
-# =============================================================================
-# External credential detection
-# =============================================================================
-
-def detect_external_credentials() -> List[Dict[str, Any]]:
-    """Scan for credentials from other CLI tools that Hermes can reuse.
-
-    Returns a list of dicts, each with:
-      - provider: str   -- Hermes provider id (e.g. "openai-codex")
-      - path: str       -- filesystem path where creds were found
-      - label: str      -- human-friendly description for the setup UI
-    """
-    found: List[Dict[str, Any]] = []
-
-    # Codex CLI: ~/.codex/auth.json (importable, not shared)
-    cli_tokens = _import_codex_cli_tokens()
-    if cli_tokens:
-        codex_path = Path.home() / ".codex" / "auth.json"
-        found.append({
-            "provider": "openai-codex",
-            "path": str(codex_path),
-            "label": f"Codex CLI credentials found ({codex_path}) — run `hermes auth` to create a separate session",
-        })
-
-    return found
-
-
 # =============================================================================
 # CLI Commands — login / logout
 # =============================================================================
@@ -2572,6 +2632,8 @@ def _prompt_model_selection(
             title=effective_title,
         )
         idx = menu.show()
+        from hermes_cli.curses_ui import flush_stdin
+        flush_stdin()
         if idx is None:
             return None
         print()
@@ -2581,7 +2643,7 @@ def _prompt_model_selection(
             custom = input("Enter model name: ").strip()
             return custom if custom else None
         return None
-    except (ImportError, NotImplementedError):
+    except (ImportError, NotImplementedError, OSError, subprocess.SubprocessError):
         pass
 
     # Fallback: numbered list
@@ -3017,12 +3079,15 @@ def _login_nous(args, pconfig: ProviderConfig) -> None:
             _save_provider_state(auth_store, "nous", auth_state)
             saved_to = _save_auth_store(auth_store)
 
-        config_path = _update_config_for_provider("nous", inference_base_url)
         print()
         print("Login successful!")
         print(f"  Auth state: {saved_to}")
-        print(f"  Config updated: {config_path} (model.provider=nous)")
 
+        # Resolve model BEFORE writing provider to config.yaml so we never
+        # leave the config in a half-updated state (provider=nous but model
+        # still set to the previous provider's model, e.g. opus from
+        # OpenRouter).  The auth.json active_provider was already set above.
+        selected_model = None
         try:
             runtime_key = auth_state.get("agent_key") or auth_state.get("access_token")
             if not isinstance(runtime_key, str) or not runtime_key:
@@ -3056,9 +3121,6 @@ def _login_nous(args, pconfig: ProviderConfig) -> None:
                     unavailable_models=unavailable_models,
                     portal_url=_portal,
                 )
-                if selected_model:
-                    _save_model_choice(selected_model)
-                    print(f"Default model set to: {selected_model}")
             elif unavailable_models:
                 _url = (_portal or DEFAULT_NOUS_PORTAL_URL).rstrip("/")
                 print("No free models currently available.")
@@ -3070,6 +3132,15 @@ def _login_nous(args, pconfig: ProviderConfig) -> None:
             print()
             print(f"Login succeeded, but could not fetch available models. Reason: {message}")
 
+        # Write provider + model atomically so config is never mismatched.
+        config_path = _update_config_for_provider(
+            "nous", inference_base_url, default_model=selected_model,
+        )
+        if selected_model:
+            _save_model_choice(selected_model)
+            print(f"Default model set to: {selected_model}")
+        print(f"  Config updated: {config_path} (model.provider=nous)")
+
     except KeyboardInterrupt:
         print("\nLogin cancelled.")
         raise SystemExit(130)

hermes_cli/auth_commands.py

@@ -347,8 +347,11 @@ def auth_remove_command(args) -> None:
             print("Cleared Hermes Anthropic OAuth credentials")
 
     elif removed.source == "claude_code" and provider == "anthropic":
-        print("Note: Claude Code credentials live in ~/.claude/.credentials.json")
-        print("      Remove them manually if you want to deauthorize Claude Code.")
+        from hermes_cli.auth import suppress_credential_source
+        suppress_credential_source(provider, "claude_code")
+        print("Suppressed claude_code credential — it will not be re-seeded.")
+        print("Note: Claude Code credentials still live in ~/.claude/.credentials.json")
+        print("Run `hermes auth add anthropic` to re-enable if needed.")
 
 
 def auth_reset_command(args) -> None:

hermes_cli/banner.py

@@ -90,12 +90,6 @@ HERMES_CADUCEUS = """[#CD7F32]⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⢀⣀⡀⠀⣀⣀
 [#B8860B]⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠈⠳⠈⣡⠞⠁⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀[/]
 [#B8860B]⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠈⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀[/]"""
 
-COMPACT_BANNER = """
-[bold #FFD700]╔══════════════════════════════════════════════════════════════╗[/]
-[bold #FFD700]║[/]  [#FFBF00]⚕ NOUS HERMES[/] [dim #B8860B]- AI Agent Framework[/]              [bold #FFD700]║[/]
-[bold #FFD700]║[/]  [#CD7F32]Messenger of the Digital Gods[/]    [dim #B8860B]Nous Research[/]   [bold #FFD700]║[/]
-[bold #FFD700]╚══════════════════════════════════════════════════════════════╝[/]
-"""
 
 
 # =========================================================================
@@ -295,10 +289,16 @@ def _format_context_length(tokens: int) -> str:
     """Format a token count for display (e.g. 128000 → '128K', 1048576 → '1M')."""
     if tokens >= 1_000_000:
         val = tokens / 1_000_000
-        return f"{val:g}M"
+        rounded = round(val)
+        if abs(val - rounded) < 0.05:
+            return f"{rounded}M"
+        return f"{val:.1f}M"
     elif tokens >= 1_000:
         val = tokens / 1_000
-        return f"{val:g}K"
+        rounded = round(val)
+        if abs(val - rounded) < 0.05:
+            return f"{rounded}K"
+        return f"{val:.1f}K"
     return str(tokens)
 
 

hermes_cli/checklist.py

@@ -1,140 +0,0 @@
-"""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.).
-"""
-
-import sys
-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.
-    """
-    # Safety: return defaults when stdin is not a terminal.
-    if not sys.stdin.isatty():
-        return set(pre_selected)
-
-    try:
-        import curses
-        selected = set(pre_selected)
-        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/clipboard.py

@@ -19,10 +19,9 @@ import subprocess
 import sys
 from pathlib import Path
 
-logger = logging.getLogger(__name__)
+from hermes_constants import is_wsl as _is_wsl
 
-# Cache WSL detection (checked once per process)
-_wsl_detected: bool | None = None
+logger = logging.getLogger(__name__)
 
 
 def save_clipboard_image(dest: Path) -> bool:
@@ -217,19 +216,6 @@ def _windows_save(dest: Path) -> bool:
 
 # ── Linux ────────────────────────────────────────────────────────────────
 
-def _is_wsl() -> bool:
-    """Detect if running inside WSL (1 or 2)."""
-    global _wsl_detected
-    if _wsl_detected is not None:
-        return _wsl_detected
-    try:
-        with open("/proc/version", "r") as f:
-            _wsl_detected = "microsoft" in f.read().lower()
-    except Exception:
-        _wsl_detected = False
-    return _wsl_detected
-
-
 def _linux_save(dest: Path) -> bool:
     """Try clipboard backends in priority order: WSL → Wayland → X11."""
     if _is_wsl():

hermes_cli/commands.py

@@ -16,8 +16,18 @@ from collections.abc import Callable, Mapping
 from dataclasses import dataclass
 from typing import Any
 
-from prompt_toolkit.auto_suggest import AutoSuggest, Suggestion
-from prompt_toolkit.completion import Completer, Completion
+# prompt_toolkit is an optional CLI dependency — only needed for
+# SlashCommandCompleter and SlashCommandAutoSuggest.  Gateway and test
+# environments that lack it must still be able to import this module
+# for resolve_command, gateway_help_lines, and COMMAND_REGISTRY.
+try:
+    from prompt_toolkit.auto_suggest import AutoSuggest, Suggestion
+    from prompt_toolkit.completion import Completer, Completion
+except ImportError:  # pragma: no cover
+    AutoSuggest = object  # type: ignore[assignment,misc]
+    Completer = object    # type: ignore[assignment,misc]
+    Suggestion = None     # type: ignore[assignment]
+    Completion = None     # type: ignore[assignment]
 
 
 # ---------------------------------------------------------------------------
@@ -73,8 +83,7 @@ COMMAND_REGISTRY: list[CommandDef] = [
                args_hint="<question>"),
     CommandDef("queue", "Queue a prompt for the next turn (doesn't interrupt)", "Session",
                aliases=("q",), args_hint="<prompt>"),
-    CommandDef("status", "Show session info", "Session",
-               gateway_only=True),
+    CommandDef("status", "Show session info", "Session"),
     CommandDef("profile", "Show active profile name and home directory", "Info"),
     CommandDef("sethome", "Set this chat as the home channel", "Session",
                gateway_only=True, aliases=("set-home",)),
@@ -87,8 +96,7 @@ COMMAND_REGISTRY: list[CommandDef] = [
     CommandDef("model", "Switch model for this session", "Configuration", args_hint="[model] [--global]"),
     CommandDef("provider", "Show available providers and current provider",
                "Configuration"),
-    CommandDef("prompt", "View/set custom system prompt", "Configuration",
-               cli_only=True, args_hint="[text]", subcommands=("clear",)),
+
     CommandDef("personality", "Set a predefined personality", "Configuration",
                args_hint="[name]"),
     CommandDef("statusbar", "Toggle the context/model status bar", "Configuration",
@@ -100,7 +108,10 @@ COMMAND_REGISTRY: list[CommandDef] = [
                "Configuration"),
     CommandDef("reasoning", "Manage reasoning effort and display", "Configuration",
                args_hint="[level|show|hide]",
-               subcommands=("none", "low", "minimal", "medium", "high", "xhigh", "show", "hide", "on", "off")),
+               subcommands=("none", "minimal", "low", "medium", "high", "xhigh", "show", "hide", "on", "off")),
+    CommandDef("fast", "Toggle fast mode — OpenAI Priority Processing / Anthropic Fast Mode (Normal/Fast)", "Configuration",
+               args_hint="[normal|fast|status]",
+               subcommands=("normal", "fast", "status", "on", "off")),
     CommandDef("skin", "Show or change the display skin/theme", "Configuration",
                cli_only=True, args_hint="[name]"),
     CommandDef("voice", "Toggle voice mode", "Configuration",
@@ -129,13 +140,17 @@ COMMAND_REGISTRY: list[CommandDef] = [
     CommandDef("commands", "Browse all commands and skills (paginated)", "Info",
                gateway_only=True, args_hint="[page]"),
     CommandDef("help", "Show available commands", "Info"),
-    CommandDef("usage", "Show token usage for the current session", "Info"),
+    CommandDef("restart", "Gracefully restart the gateway after draining active runs", "Session",
+               gateway_only=True),
+    CommandDef("usage", "Show token usage and rate limits for the current session", "Info"),
     CommandDef("insights", "Show usage insights and analytics", "Info",
                args_hint="[days]"),
     CommandDef("platforms", "Show gateway/messaging platform status", "Info",
                cli_only=True, aliases=("gateway",)),
     CommandDef("paste", "Check clipboard for an image and attach it", "Info",
                cli_only=True),
+    CommandDef("image", "Attach a local image file for your next prompt", "Info",
+               cli_only=True, args_hint="<path>"),
     CommandDef("update", "Update Hermes Agent to the latest version", "Info",
                gateway_only=True),
 
@@ -170,12 +185,6 @@ def resolve_command(name: str) -> CommandDef | None:
     return _COMMAND_LOOKUP.get(name.lower().lstrip("/"))
 
 
-def register_plugin_command(cmd: CommandDef) -> None:
-    """Append a plugin-defined command to the registry and refresh lookups."""
-    COMMAND_REGISTRY.append(cmd)
-    rebuild_lookups()
-
-
 def rebuild_lookups() -> None:
     """Rebuild all derived lookup dicts from the current COMMAND_REGISTRY.
 
@@ -638,8 +647,18 @@ class SlashCommandCompleter(Completer):
     def __init__(
         self,
         skill_commands_provider: Callable[[], Mapping[str, dict[str, Any]]] | None = None,
+        command_filter: Callable[[str], bool] | None = None,
     ) -> None:
         self._skill_commands_provider = skill_commands_provider
+        self._command_filter = command_filter
+
+    def _command_allowed(self, slash_command: str) -> bool:
+        if self._command_filter is None:
+            return True
+        try:
+            return bool(self._command_filter(slash_command))
+        except Exception:
+            return True
 
     def _iter_skill_commands(self) -> Mapping[str, dict[str, Any]]:
         if self._skill_commands_provider is None:
@@ -917,7 +936,7 @@ class SlashCommandCompleter(Completer):
                 return
 
             # Static subcommand completions
-            if " " not in sub_text and base_cmd in SUBCOMMANDS:
+            if " " not in sub_text and base_cmd in SUBCOMMANDS and self._command_allowed(base_cmd):
                 for sub in SUBCOMMANDS[base_cmd]:
                     if sub.startswith(sub_lower) and sub != sub_lower:
                         yield Completion(
@@ -930,6 +949,8 @@ class SlashCommandCompleter(Completer):
         word = text[1:]
 
         for cmd, desc in COMMANDS.items():
+            if not self._command_allowed(cmd):
+                continue
             cmd_name = cmd[1:]
             if cmd_name.startswith(word):
                 yield Completion(
@@ -988,6 +1009,8 @@ class SlashCommandAutoSuggest(AutoSuggest):
             # Still typing the command name: /upd → suggest "ate"
             word = text[1:].lower()
             for cmd in COMMANDS:
+                if self._completer is not None and not self._completer._command_allowed(cmd):
+                    continue
                 cmd_name = cmd[1:]  # strip leading /
                 if cmd_name.startswith(word) and cmd_name != word:
                     return Suggestion(cmd_name[len(word):])
@@ -998,6 +1021,8 @@ class SlashCommandAutoSuggest(AutoSuggest):
         sub_lower = sub_text.lower()
 
         # Static subcommands
+        if self._completer is not None and not self._completer._command_allowed(base_cmd):
+            return None
         if base_cmd in SUBCOMMANDS and SUBCOMMANDS[base_cmd]:
             if " " not in sub_text:
                 for sub in SUBCOMMANDS[base_cmd]:

hermes_cli/config.py

@@ -39,6 +39,10 @@ _EXTRA_ENV_KEYS = frozenset({
     "DINGTALK_CLIENT_ID", "DINGTALK_CLIENT_SECRET",
     "FEISHU_APP_ID", "FEISHU_APP_SECRET", "FEISHU_ENCRYPT_KEY", "FEISHU_VERIFICATION_TOKEN",
     "WECOM_BOT_ID", "WECOM_SECRET",
+    "WEIXIN_ACCOUNT_ID", "WEIXIN_TOKEN", "WEIXIN_BASE_URL", "WEIXIN_CDN_BASE_URL",
+    "WEIXIN_HOME_CHANNEL", "WEIXIN_HOME_CHANNEL_NAME", "WEIXIN_DM_POLICY", "WEIXIN_GROUP_POLICY",
+    "WEIXIN_ALLOWED_USERS", "WEIXIN_GROUP_ALLOWED_USERS", "WEIXIN_ALLOW_ALL_USERS",
+    "BLUEBUBBLES_SERVER_URL", "BLUEBUBBLES_PASSWORD",
     "TERMINAL_ENV", "TERMINAL_SSH_KEY", "TERMINAL_SSH_PORT",
     "WHATSAPP_MODE", "WHATSAPP_ENABLED",
     "MATTERMOST_HOME_CHANNEL", "MATTERMOST_REPLY_MODE",
@@ -157,16 +161,27 @@ def get_project_root() -> Path:
     return Path(__file__).parent.parent.resolve()
 
 def _secure_dir(path):
-    """Set directory to owner-only access (0700). No-op on Windows.
+    """Set directory to owner-only access (0700 by default). No-op on Windows.
 
     Skipped in managed mode — the NixOS module sets group-readable
     permissions (0750) so interactive users in the hermes group can
     share state with the gateway service.
+
+    The mode can be overridden via the HERMES_HOME_MODE environment variable
+    (e.g. HERMES_HOME_MODE=0701) for deployments where a web server (nginx,
+    caddy, etc.) needs to traverse HERMES_HOME to reach a served subdirectory.
+    The execute-only bit on a directory permits cd-through without exposing
+    directory listings.
     """
     if is_managed():
         return
     try:
-        os.chmod(path, 0o700)
+        mode_str = os.environ.get("HERMES_HOME_MODE", "").strip()
+        mode = int(mode_str, 8) if mode_str else 0o700
+    except ValueError:
+        mode = 0o700
+    try:
+        os.chmod(path, mode)
     except (OSError, NotImplementedError):
         pass
 
@@ -196,14 +211,44 @@ def _ensure_default_soul_md(home: Path) -> None:
 
 
 def ensure_hermes_home():
-    """Ensure ~/.hermes directory structure exists with secure permissions."""
+    """Ensure ~/.hermes directory structure exists with secure permissions.
+
+    In managed mode (NixOS), dirs are created by the activation script with
+    setgid + group-writable (2770). We skip mkdir and set umask(0o007) so
+    any files created (e.g. SOUL.md) are group-writable (0660).
+    """
     home = get_hermes_home()
-    home.mkdir(parents=True, exist_ok=True)
-    _secure_dir(home)
+    if is_managed():
+        old_umask = os.umask(0o007)
+        try:
+            _ensure_hermes_home_managed(home)
+        finally:
+            os.umask(old_umask)
+    else:
+        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)
+        _ensure_default_soul_md(home)
+
+
+def _ensure_hermes_home_managed(home: Path):
+    """Managed-mode variant: verify dirs exist (activation creates them), seed SOUL.md."""
+    if not home.is_dir():
+        raise RuntimeError(
+            f"HERMES_HOME {home} does not exist. "
+            "Run 'sudo nixos-rebuild switch' first."
+        )
     for subdir in ("cron", "sessions", "logs", "memories"):
         d = home / subdir
-        d.mkdir(parents=True, exist_ok=True)
-        _secure_dir(d)
+        if not d.is_dir():
+            raise RuntimeError(
+                f"{d} does not exist. "
+                "Run 'sudo nixos-rebuild switch' first."
+            )
+    # Inside umask(0o007) scope — SOUL.md will be created as 0660
     _ensure_default_soul_md(home)
 
 
@@ -224,12 +269,22 @@ DEFAULT_CONFIG = {
         # tools or receiving API responses.  Only fires when the agent has
         # been completely idle for this duration.  0 = unlimited.
         "gateway_timeout": 1800,
+        # Graceful drain timeout for gateway stop/restart (seconds).
+        # The gateway stops accepting new work, waits for running agents
+        # to finish, then interrupts any remaining runs after the timeout.
+        # 0 = no drain, interrupt immediately.
+        "restart_drain_timeout": 60,
+        "service_tier": "",
         # Tool-use enforcement: injects system prompt guidance that tells the
         # model to actually call tools instead of describing intended actions.
         # Values: "auto" (default — applies to gpt/codex models), true/false
         # (force on/off for all models), or a list of model-name substrings
         # to match (e.g. ["gpt", "codex", "gemini", "qwen"]).
         "tool_use_enforcement": "auto",
+        # Staged inactivity warning: send a warning to the user at this
+        # threshold before escalating to a full timeout.  The warning fires
+        # once per run and does not interrupt the agent.  0 = disable warning.
+        "gateway_timeout_warning": 900,
     },
     
     "terminal": {
@@ -403,7 +458,7 @@ DEFAULT_CONFIG = {
     
     # Text-to-speech configuration
     "tts": {
-        "provider": "edge",  # "edge" (free) | "elevenlabs" (premium) | "openai" | "neutts" (local)
+        "provider": "edge",  # "edge" (free) | "elevenlabs" (premium) | "openai" | "minimax" | "mistral" | "neutts" (local)
         "edge": {
             "voice": "en-US-AriaNeural",
             # Popular: AriaNeural, JennyNeural, AndrewNeural, BrianNeural, SoniaNeural
@@ -417,6 +472,10 @@ DEFAULT_CONFIG = {
             "voice": "alloy",
             # Voices: alloy, echo, fable, onyx, nova, shimmer
         },
+        "mistral": {
+            "model": "voxtral-mini-tts-2603",
+            "voice_id": "c69964a6-ab8b-4f8a-9465-ec0925096ec8",  # Paul - Neutral
+        },
         "neutts": {
             "ref_audio": "",  # Path to reference voice audio (empty = bundled default)
             "ref_text": "",   # Path to reference voice transcript (empty = bundled default)
@@ -454,6 +513,16 @@ DEFAULT_CONFIG = {
         "max_ms": 2500,
     },
     
+    # Context engine -- controls how the context window is managed when
+    # approaching the model's token limit.
+    # "compressor" = built-in lossy summarization (default).
+    # Set to a plugin name to activate an alternative engine (e.g. "lcm"
+    # for Lossless Context Management).  The engine must be installed as
+    # a plugin in plugins/context_engine/<name>/ or ~/.hermes/plugins/.
+    "context": {
+        "engine": "compressor",
+    },
+
     # Persistent memory -- bounded curated memory injected into system prompt
     "memory": {
         "memory_enabled": True,
@@ -478,6 +547,8 @@ DEFAULT_CONFIG = {
         "api_key": "",     # API key for delegation.base_url (falls back to OPENAI_API_KEY)
         "max_iterations": 50,  # per-subagent iteration cap (each subagent gets its own budget,
                                # independent of the parent's max_iterations)
+        "reasoning_effort": "",  # reasoning effort for subagents: "xhigh", "high", "medium",
+                                 # "low", "minimal", "none" (empty = inherit parent's level)
     },
 
     # Ephemeral prefill messages file — JSON list of {role, content} dicts
@@ -505,6 +576,7 @@ DEFAULT_CONFIG = {
     "discord": {
         "require_mention": True,       # Require @mention to respond in server channels
         "free_response_channels": "",  # Comma-separated channel IDs where bot responds without mention
+        "allowed_channels": "",        # If set, bot ONLY responds in these channel IDs (whitelist)
         "auto_thread": True,           # Auto-create threads on @mention in channels (like Slack)
         "reactions": True,             # Add 👀/✅/❌ reactions to messages during processing
     },
@@ -564,7 +636,7 @@ DEFAULT_CONFIG = {
     },
 
     # Config schema version - bump this when adding new required fields
-    "_config_version": 12,
+    "_config_version": 14,
 }
 
 # =============================================================================
@@ -948,6 +1020,13 @@ OPTIONAL_ENV_VARS = {
         "password": True,
         "category": "tool",
     },
+    "MISTRAL_API_KEY": {
+        "description": "Mistral API key for Voxtral TTS and transcription (STT)",
+        "prompt": "Mistral API key",
+        "url": "https://console.mistral.ai/",
+        "password": True,
+        "category": "tool",
+    },
     "GITHUB_TOKEN": {
         "description": "GitHub token for Skills Hub (higher API rate limits, skill publish)",
         "prompt": "GitHub Token",
@@ -1120,6 +1199,27 @@ OPTIONAL_ENV_VARS = {
         "category": "messaging",
         "advanced": True,
     },
+    "BLUEBUBBLES_SERVER_URL": {
+        "description": "BlueBubbles server URL for iMessage integration (e.g. http://192.168.1.10:1234)",
+        "prompt": "BlueBubbles server URL",
+        "url": "https://bluebubbles.app/",
+        "password": False,
+        "category": "messaging",
+    },
+    "BLUEBUBBLES_PASSWORD": {
+        "description": "BlueBubbles server password (from BlueBubbles Server → Settings → API)",
+        "prompt": "BlueBubbles server password",
+        "url": None,
+        "password": True,
+        "category": "messaging",
+    },
+    "BLUEBUBBLES_ALLOWED_USERS": {
+        "description": "Comma-separated iMessage addresses (email or phone) allowed to use the bot",
+        "prompt": "Allowed iMessage addresses (comma-separated)",
+        "url": None,
+        "password": False,
+        "category": "messaging",
+    },
     "GATEWAY_ALLOW_ALL_USERS": {
         "description": "Allow all users to interact with messaging bots (true/false). Default: false.",
         "prompt": "Allow all users (true/false)",
@@ -1137,8 +1237,8 @@ OPTIONAL_ENV_VARS = {
         "advanced": True,
     },
     "API_SERVER_KEY": {
-        "description": "Bearer token for API server authentication. If empty, all requests are allowed (local use only).",
-        "prompt": "API server auth key (optional)",
+        "description": "Bearer token for API server authentication. Required for non-loopback binding; server refuses to start without it. On loopback (127.0.0.1), all requests are allowed if empty.",
+        "prompt": "API server auth key (required for network access)",
         "url": None,
         "password": True,
         "category": "messaging",
@@ -1153,13 +1253,21 @@ OPTIONAL_ENV_VARS = {
         "advanced": True,
     },
     "API_SERVER_HOST": {
-        "description": "Host/bind address for the API server (default: 127.0.0.1). Use 0.0.0.0 for network access — requires API_SERVER_KEY for security.",
+        "description": "Host/bind address for the API server (default: 127.0.0.1). Use 0.0.0.0 for network access — server refuses to start without API_SERVER_KEY.",
         "prompt": "API server host",
         "url": None,
         "password": False,
         "category": "messaging",
         "advanced": True,
     },
+    "API_SERVER_MODEL_NAME": {
+        "description": "Model name advertised on /v1/models. Defaults to the profile name (or 'hermes-agent' for the default profile). Useful for multi-user setups with OpenWebUI.",
+        "prompt": "API server model name",
+        "url": None,
+        "password": False,
+        "category": "messaging",
+        "advanced": True,
+    },
     "WEBHOOK_ENABLED": {
         "description": "Enable the webhook platform adapter for receiving events from GitHub, GitLab, etc.",
         "prompt": "Enable webhooks (true/false)",
@@ -1191,7 +1299,7 @@ OPTIONAL_ENV_VARS = {
         "category": "setting",
     },
     "SUDO_PASSWORD": {
-        "description": "Sudo password for terminal commands requiring root access",
+        "description": "Sudo password for terminal commands requiring root access; set to an explicit empty string to try empty without prompting",
         "prompt": "Sudo password",
         "url": None,
         "password": True,
@@ -1370,7 +1478,7 @@ _KNOWN_ROOT_KEYS = {
     "_config_version", "model", "providers", "fallback_model",
     "fallback_providers", "credential_pool_strategies", "toolsets",
     "agent", "terminal", "display", "compression", "delegation",
-    "auxiliary", "custom_providers", "memory", "gateway",
+    "auxiliary", "custom_providers", "context", "memory", "gateway",
 }
 
 # Valid fields inside a custom_providers list entry
@@ -1675,6 +1783,71 @@ def migrate_config(interactive: bool = True, quiet: bool = False) -> Dict[str, A
                         ep = providers_dict[key]
                         print(f"    → {key}: {ep.get('api', '')}")
 
+    # ── Version 12 → 13: clear dead LLM_MODEL / OPENAI_MODEL from .env ──
+    # These env vars were written by the old setup wizard but nothing reads
+    # them anymore (config.yaml is the sole source of truth since March 2026).
+    # Stale entries cause user confusion — see issue report.
+    if current_ver < 13:
+        for dead_var in ("LLM_MODEL", "OPENAI_MODEL"):
+            try:
+                old_val = get_env_value(dead_var)
+                if old_val:
+                    save_env_value(dead_var, "")
+                    if not quiet:
+                        print(f"  ✓ Cleared {dead_var} from .env (no longer used — config.yaml is source of truth)")
+            except Exception:
+                pass
+
+    # ── Version 13 → 14: migrate legacy flat stt.model to provider section ──
+    # Old configs (and cli-config.yaml.example) had a flat `stt.model` key
+    # that was provider-agnostic.  When the provider was "local" this caused
+    # OpenAI model names (e.g. "whisper-1") to be fed to faster-whisper,
+    # crashing with "Invalid model size".  Move the value into the correct
+    # provider-specific section and remove the flat key.
+    if current_ver < 14:
+        # Read raw config (no defaults merged) to check what the user actually
+        # wrote, then apply changes to the merged config for saving.
+        raw = read_raw_config()
+        raw_stt = raw.get("stt", {})
+        if isinstance(raw_stt, dict) and "model" in raw_stt:
+            legacy_model = raw_stt["model"]
+            provider = raw_stt.get("provider", "local")
+            config = load_config()
+            stt = config.get("stt", {})
+            # Remove the legacy flat key
+            stt.pop("model", None)
+            # Place it in the appropriate provider section only if the
+            # user didn't already set a model there
+            if provider in ("local", "local_command"):
+                # Don't migrate an OpenAI model name into the local section
+                _local_models = {
+                    "tiny.en", "tiny", "base.en", "base", "small.en", "small",
+                    "medium.en", "medium", "large-v1", "large-v2", "large-v3",
+                    "large", "distil-large-v2", "distil-medium.en",
+                    "distil-small.en", "distil-large-v3", "distil-large-v3.5",
+                    "large-v3-turbo", "turbo",
+                }
+                if legacy_model in _local_models:
+                    # Check raw config — only set if user didn't already
+                    # have a nested local.model
+                    raw_local = raw_stt.get("local", {})
+                    if not isinstance(raw_local, dict) or "model" not in raw_local:
+                        local_cfg = stt.setdefault("local", {})
+                        local_cfg["model"] = legacy_model
+                # else: drop it — it was an OpenAI model name, local section
+                # already defaults to "base" via DEFAULT_CONFIG
+            else:
+                # Cloud provider — put it in that provider's section only
+                # if user didn't already set a nested model
+                raw_provider = raw_stt.get(provider, {})
+                if not isinstance(raw_provider, dict) or "model" not in raw_provider:
+                    provider_cfg = stt.setdefault(provider, {})
+                    provider_cfg["model"] = legacy_model
+            config["stt"] = stt
+            save_config(config)
+            if not quiet:
+                print(f"  ✓ Migrated legacy stt.model to provider-specific config")
+
     if current_ver < latest_ver and not quiet:
         print(f"Config version: {current_ver} → {latest_ver}")
     
@@ -2628,6 +2801,10 @@ def set_config_value(key: str, value: str):
         "terminal.timeout": "TERMINAL_TIMEOUT",
         "terminal.sandbox_dir": "TERMINAL_SANDBOX_DIR",
         "terminal.persistent_shell": "TERMINAL_PERSISTENT_SHELL",
+        "terminal.container_cpu": "TERMINAL_CONTAINER_CPU",
+        "terminal.container_memory": "TERMINAL_CONTAINER_MEMORY",
+        "terminal.container_disk": "TERMINAL_CONTAINER_DISK",
+        "terminal.container_persistent": "TERMINAL_CONTAINER_PERSISTENT",
     }
     if key in _config_to_env_sync:
         save_env_value(_config_to_env_sync[key], str(value))

hermes_cli/copilot_auth.py

@@ -31,13 +31,6 @@ logger = logging.getLogger(__name__)
 
 # OAuth device code flow constants (same client ID as opencode/Copilot CLI)
 COPILOT_OAUTH_CLIENT_ID = "Ov23li8tweQw6odWQebz"
-COPILOT_DEVICE_CODE_URL = "https://github.com/login/device/code"
-COPILOT_ACCESS_TOKEN_URL = "https://github.com/login/oauth/access_token"
-
-# Copilot API constants
-COPILOT_TOKEN_EXCHANGE_URL = "https://api.github.com/copilot_internal/v2/token"
-COPILOT_API_BASE_URL = "https://api.githubcopilot.com"
-
 # Token type prefixes
 _CLASSIC_PAT_PREFIX = "ghp_"
 _SUPPORTED_PREFIXES = ("gho_", "github_pat_", "ghu_")
@@ -50,11 +43,6 @@ _DEVICE_CODE_POLL_INTERVAL = 5  # seconds
 _DEVICE_CODE_POLL_SAFETY_MARGIN = 3  # seconds
 
 
-def is_classic_pat(token: str) -> bool:
-    """Check if a token is a classic PAT (ghp_*), which Copilot doesn't support."""
-    return token.strip().startswith(_CLASSIC_PAT_PREFIX)
-
-
 def validate_copilot_token(token: str) -> tuple[bool, str]:
     """Validate that a token is usable with the Copilot API.
 
@@ -285,6 +273,7 @@ def copilot_request_headers(
     headers: dict[str, str] = {
         "Editor-Version": "vscode/1.104.1",
         "User-Agent": "HermesAgent/1.0",
+        "Copilot-Integration-Id": "vscode-chat",
         "Openai-Intent": "conversation-edits",
         "x-initiator": "agent" if is_agent_turn else "user",
     }

hermes_cli/curses_ui.py

@@ -10,6 +10,28 @@ from typing import Callable, List, Optional, Set
 from hermes_cli.colors import Colors, color
 
 
+def flush_stdin() -> None:
+    """Flush any stray bytes from the stdin input buffer.
+
+    Must be called after ``curses.wrapper()`` (or any terminal-mode library
+    like simple_term_menu) returns, **before** the next ``input()`` /
+    ``getpass.getpass()`` call.  ``curses.endwin()`` restores the terminal
+    but does NOT drain the OS input buffer — leftover escape-sequence bytes
+    (from arrow keys, terminal mode-switch responses, or rapid keypresses)
+    remain buffered and silently get consumed by the next ``input()`` call,
+    corrupting user data (e.g. writing ``^[^[`` into .env files).
+
+    On non-TTY stdin (piped, redirected) or Windows, this is a no-op.
+    """
+    try:
+        if not sys.stdin.isatty():
+            return
+        import termios
+        termios.tcflush(sys.stdin, termios.TCIFLUSH)
+    except Exception:
+        pass
+
+
 def curses_checklist(
     title: str,
     items: List[str],
@@ -131,12 +153,140 @@ def curses_checklist(
                     return
 
         curses.wrapper(_draw)
+        flush_stdin()
         return result_holder[0] if result_holder[0] is not None else cancel_returns
 
     except Exception:
         return _numbered_fallback(title, items, selected, cancel_returns, status_fn)
 
 
+def curses_radiolist(
+    title: str,
+    items: List[str],
+    selected: int = 0,
+    *,
+    cancel_returns: int | None = None,
+) -> int:
+    """Curses single-select radio list. Returns the selected index.
+
+    Args:
+        title: Header line displayed above the list.
+        items: Display labels for each row.
+        selected: Index that starts selected (pre-selected).
+        cancel_returns: Returned on ESC/q. Defaults to the original *selected*.
+    """
+    if cancel_returns is None:
+        cancel_returns = selected
+
+    if not sys.stdin.isatty():
+        return cancel_returns
+
+    try:
+        import curses
+        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)
+            cursor = selected
+            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,
+                        "  \u2191\u2193 navigate  ENTER/SPACE select  ESC cancel",
+                        max_x - 1, curses.A_DIM,
+                    )
+                except curses.error:
+                    pass
+
+                # Scrollable item list
+                visible_rows = max_y - 4
+                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
+                    radio = "\u25cf" if i == selected else "\u25cb"
+                    arrow = "\u2192" if i == cursor else " "
+                    line = f" {arrow} ({radio}) {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 in (ord(" "), curses.KEY_ENTER, 10, 13):
+                    result_holder[0] = cursor
+                    return
+                elif key in (27, ord("q")):
+                    result_holder[0] = cancel_returns
+                    return
+
+        curses.wrapper(_draw)
+        flush_stdin()
+        return result_holder[0] if result_holder[0] is not None else cancel_returns
+
+    except Exception:
+        return _radio_numbered_fallback(title, items, selected, cancel_returns)
+
+
+def _radio_numbered_fallback(
+    title: str,
+    items: List[str],
+    selected: int,
+    cancel_returns: int,
+) -> int:
+    """Text-based numbered fallback for radio selection."""
+    print(color(f"\n  {title}", Colors.YELLOW))
+    print(color("  Select by number, Enter to confirm.\n", Colors.DIM))
+
+    for i, label in enumerate(items):
+        marker = color("(\u25cf)", Colors.GREEN) if i == selected else "(\u25cb)"
+        print(f"  {marker} {i + 1:>2}. {label}")
+    print()
+    try:
+        val = input(color(f"  Choice [default {selected + 1}]: ", Colors.DIM)).strip()
+        if not val:
+            return selected
+        idx = int(val) - 1
+        if 0 <= idx < len(items):
+            return idx
+        return selected
+    except (ValueError, KeyboardInterrupt, EOFError):
+        return cancel_returns
+
+
 def _numbered_fallback(
     title: str,
     items: List[str],

hermes_cli/doctor.py

@@ -54,6 +54,32 @@ _PROVIDER_ENV_HINTS = (
 )
 
 
+from hermes_constants import is_termux as _is_termux
+
+
+def _python_install_cmd() -> str:
+    return "python -m pip install" if _is_termux() else "uv pip install"
+
+
+def _system_package_install_cmd(pkg: str) -> str:
+    if _is_termux():
+        return f"pkg install {pkg}"
+    if sys.platform == "darwin":
+        return f"brew install {pkg}"
+    return f"sudo apt install {pkg}"
+
+
+def _termux_browser_setup_steps(node_installed: bool) -> list[str]:
+    steps: list[str] = []
+    step = 1
+    if not node_installed:
+        steps.append(f"{step}) pkg install nodejs")
+        step += 1
+    steps.append(f"{step}) npm install -g agent-browser")
+    steps.append(f"{step + 1}) agent-browser install")
+    return steps
+
+
 def _has_provider_env_config(content: str) -> bool:
     """Return True when ~/.hermes/.env contains provider auth/base URL settings."""
     return any(key in content for key in _PROVIDER_ENV_HINTS)
@@ -200,7 +226,7 @@ def run_doctor(args):
             check_ok(name)
         except ImportError:
             check_fail(name, "(missing)")
-            issues.append(f"Install {name}: uv pip install {module}")
+            issues.append(f"Install {name}: {_python_install_cmd()} {module}")
     
     for module, name in optional_packages:
         try:
@@ -503,7 +529,7 @@ def run_doctor(args):
         check_ok("ripgrep (rg)", "(faster file search)")
     else:
         check_warn("ripgrep (rg) not found", "(file search uses grep fallback)")
-        check_info("Install for faster search: sudo apt install ripgrep")
+        check_info(f"Install for faster search: {_system_package_install_cmd('ripgrep')}")
     
     # Docker (optional)
     terminal_env = os.getenv("TERMINAL_ENV", "local")
@@ -526,7 +552,10 @@ def run_doctor(args):
         if shutil.which("docker"):
             check_ok("docker", "(optional)")
         else:
-            check_warn("docker not found", "(optional)")
+            if _is_termux():
+                check_info("Docker backend is not available inside Termux (expected on Android)")
+            else:
+                check_warn("docker not found", "(optional)")
     
     # SSH (if using ssh backend)
     if terminal_env == "ssh":
@@ -574,9 +603,23 @@ def run_doctor(args):
         if agent_browser_path.exists():
             check_ok("agent-browser (Node.js)", "(browser automation)")
         else:
-            check_warn("agent-browser not installed", "(run: npm install)")
+            if _is_termux():
+                check_info("agent-browser is not installed (expected in the tested Termux path)")
+                check_info("Install it manually later with: npm install -g agent-browser && agent-browser install")
+                check_info("Termux browser setup:")
+                for step in _termux_browser_setup_steps(node_installed=True):
+                    check_info(step)
+            else:
+                check_warn("agent-browser not installed", "(run: npm install)")
     else:
-        check_warn("Node.js not found", "(optional, needed for browser tools)")
+        if _is_termux():
+            check_info("Node.js not found (browser tools are optional in the tested Termux path)")
+            check_info("Install Node.js on Termux with: pkg install nodejs")
+            check_info("Termux browser setup:")
+            for step in _termux_browser_setup_steps(node_installed=False):
+                check_info(step)
+        else:
+            check_warn("Node.js not found", "(optional, needed for browser tools)")
     
     # npm audit for all Node.js packages
     if shutil.which("npm"):
@@ -679,9 +722,9 @@ def run_doctor(args):
         ("DeepSeek",         ("DEEPSEEK_API_KEY",),                           "https://api.deepseek.com/v1/models",  "DEEPSEEK_BASE_URL", True),
         ("Hugging Face",     ("HF_TOKEN",),                                   "https://router.huggingface.co/v1/models", "HF_BASE_URL", True),
         ("Alibaba/DashScope", ("DASHSCOPE_API_KEY",),                         "https://dashscope-intl.aliyuncs.com/compatible-mode/v1/models", "DASHSCOPE_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),
+        # MiniMax: the /anthropic endpoint doesn't support /models, but the /v1 endpoint does.
+        ("MiniMax",          ("MINIMAX_API_KEY",),                            "https://api.minimax.io/v1/models",    "MINIMAX_BASE_URL", True),
+        ("MiniMax (China)",  ("MINIMAX_CN_API_KEY",),                         "https://api.minimaxi.com/v1/models",  "MINIMAX_CN_BASE_URL", True),
         ("AI Gateway",       ("AI_GATEWAY_API_KEY",),                          "https://ai-gateway.vercel.sh/v1/models", "AI_GATEWAY_BASE_URL", True),
         ("Kilo Code",        ("KILOCODE_API_KEY",),                            "https://api.kilo.ai/api/gateway/models",  "KILOCODE_BASE_URL", True),
         ("OpenCode Zen",     ("OPENCODE_ZEN_API_KEY",),                        "https://opencode.ai/zen/v1/models",  "OPENCODE_ZEN_BASE_URL", True),
@@ -706,10 +749,15 @@ def run_doctor(args):
                 # Auto-detect Kimi Code keys (sk-kimi-) → api.kimi.com
                 if not _base and _key.startswith("sk-kimi-"):
                     _base = "https://api.kimi.com/coding/v1"
+                # Anthropic-compat endpoints (/anthropic) don't support /models.
+                # Rewrite to the OpenAI-compat /v1 surface for health checks.
+                if _base and _base.rstrip("/").endswith("/anthropic"):
+                    from agent.auxiliary_client import _to_openai_base_url
+                    _base = _to_openai_base_url(_base)
                 _url = (_base.rstrip("/") + "/models") if _base else _default_url
                 _headers = {"Authorization": f"Bearer {_key}"}
                 if "api.kimi.com" in _url.lower():
-                    _headers["User-Agent"] = "KimiCLI/1.0"
+                    _headers["User-Agent"] = "KimiCLI/1.30.0"
                 _resp = httpx.get(
                     _url,
                     headers=_headers,
@@ -739,8 +787,9 @@ def run_doctor(args):
                 __import__("tinker_atropos")
                 check_ok("tinker-atropos", "(RL training backend)")
             except ImportError:
-                check_warn("tinker-atropos found but not installed", "(run: uv pip install -e ./tinker-atropos)")
-                issues.append("Install tinker-atropos: uv pip install -e ./tinker-atropos")
+                install_cmd = f"{_python_install_cmd()} -e ./tinker-atropos"
+                check_warn("tinker-atropos found but not installed", f"(run: {install_cmd})")
+                issues.append(f"Install tinker-atropos: {install_cmd}")
         else:
             check_warn("tinker-atropos requires Python 3.11+", f"(current: {py_version.major}.{py_version.minor})")
     else:

hermes_cli/dump.py

@@ -0,0 +1,333 @@
+"""
+Dump command for hermes CLI.
+
+Outputs a compact, plain-text summary of the user's Hermes setup
+that can be copy-pasted into Discord/GitHub/Telegram for support context.
+No ANSI colors, no checkmarks — just data.
+"""
+
+import json
+import os
+import platform
+import subprocess
+import sys
+from pathlib import Path
+
+from hermes_cli.config import get_hermes_home, get_env_path, get_project_root, load_config
+from hermes_constants import display_hermes_home
+
+
+def _get_git_commit(project_root: Path) -> str:
+    """Return short git commit hash, or '(unknown)'."""
+    try:
+        result = subprocess.run(
+            ["git", "rev-parse", "--short=8", "HEAD"],
+            capture_output=True, text=True, timeout=5,
+            cwd=str(project_root),
+        )
+        if result.returncode == 0:
+            return result.stdout.strip()
+    except Exception:
+        pass
+    return "(unknown)"
+
+
+def _redact(value: str) -> str:
+    """Redact all but first 4 and last 4 chars."""
+    if not value:
+        return ""
+    if len(value) < 12:
+        return "***"
+    return value[:4] + "..." + value[-4:]
+
+
+def _gateway_status() -> str:
+    """Return a short gateway status string."""
+    if sys.platform.startswith("linux"):
+        try:
+            from hermes_cli.gateway import get_service_name
+            svc = get_service_name()
+        except Exception:
+            svc = "hermes-gateway"
+        try:
+            r = subprocess.run(
+                ["systemctl", "--user", "is-active", svc],
+                capture_output=True, text=True, timeout=5,
+            )
+            return "running (systemd)" if r.stdout.strip() == "active" else "stopped"
+        except Exception:
+            return "unknown"
+    elif sys.platform == "darwin":
+        try:
+            from hermes_cli.gateway import get_launchd_label
+            r = subprocess.run(
+                ["launchctl", "list", get_launchd_label()],
+                capture_output=True, text=True, timeout=5,
+            )
+            return "loaded (launchd)" if r.returncode == 0 else "not loaded"
+        except Exception:
+            return "unknown"
+    return "N/A"
+
+
+def _count_skills(hermes_home: Path) -> int:
+    """Count installed skills."""
+    skills_dir = hermes_home / "skills"
+    if not skills_dir.is_dir():
+        return 0
+    count = 0
+    for item in skills_dir.rglob("SKILL.md"):
+        count += 1
+    return count
+
+
+def _count_mcp_servers(config: dict) -> int:
+    """Count configured MCP servers."""
+    mcp = config.get("mcp", {})
+    servers = mcp.get("servers", {})
+    return len(servers)
+
+
+def _cron_summary(hermes_home: Path) -> str:
+    """Return cron jobs summary."""
+    jobs_file = hermes_home / "cron" / "jobs.json"
+    if not jobs_file.exists():
+        return "0"
+    try:
+        with open(jobs_file, encoding="utf-8") as f:
+            data = json.load(f)
+        jobs = data.get("jobs", [])
+        active = sum(1 for j in jobs if j.get("enabled", True))
+        return f"{active} active / {len(jobs)} total"
+    except Exception:
+        return "(error reading)"
+
+
+def _configured_platforms() -> list[str]:
+    """Return list of configured messaging platform names."""
+    checks = {
+        "telegram": "TELEGRAM_BOT_TOKEN",
+        "discord": "DISCORD_BOT_TOKEN",
+        "slack": "SLACK_BOT_TOKEN",
+        "whatsapp": "WHATSAPP_ENABLED",
+        "signal": "SIGNAL_HTTP_URL",
+        "email": "EMAIL_ADDRESS",
+        "sms": "TWILIO_ACCOUNT_SID",
+        "matrix": "MATRIX_HOMESERVER_URL",
+        "mattermost": "MATTERMOST_URL",
+        "homeassistant": "HASS_TOKEN",
+        "dingtalk": "DINGTALK_CLIENT_ID",
+        "feishu": "FEISHU_APP_ID",
+        "wecom": "WECOM_BOT_ID",
+        "weixin": "WEIXIN_ACCOUNT_ID",
+    }
+    return [name for name, env in checks.items() if os.getenv(env)]
+
+
+def _memory_provider(config: dict) -> str:
+    """Return the active memory provider name."""
+    mem = config.get("memory", {})
+    provider = mem.get("provider", "")
+    return provider if provider else "built-in"
+
+
+def _get_model_and_provider(config: dict) -> tuple[str, str]:
+    """Extract model and provider from config."""
+    model_cfg = config.get("model", "")
+    if isinstance(model_cfg, dict):
+        model = model_cfg.get("default") or model_cfg.get("model") or model_cfg.get("name") or "(not set)"
+        provider = model_cfg.get("provider") or "(auto)"
+    elif isinstance(model_cfg, str):
+        model = model_cfg or "(not set)"
+        provider = "(auto)"
+    else:
+        model = "(not set)"
+        provider = "(auto)"
+    return model, provider
+
+
+def _config_overrides(config: dict) -> dict[str, str]:
+    """Find non-default config values worth reporting.
+    
+    Returns a flat dict of dotpath -> value for interesting overrides.
+    """
+    from hermes_cli.config import DEFAULT_CONFIG
+
+    overrides = {}
+
+    # Sections with interesting user-facing overrides
+    interesting_paths = [
+        ("agent", "max_turns"),
+        ("agent", "gateway_timeout"),
+        ("agent", "tool_use_enforcement"),
+        ("terminal", "backend"),
+        ("terminal", "docker_image"),
+        ("terminal", "persistent_shell"),
+        ("browser", "allow_private_urls"),
+        ("compression", "enabled"),
+        ("compression", "threshold"),
+        ("display", "streaming"),
+        ("display", "skin"),
+        ("display", "show_reasoning"),
+        ("smart_model_routing", "enabled"),
+        ("privacy", "redact_pii"),
+        ("tts", "provider"),
+    ]
+
+    for section, key in interesting_paths:
+        default_section = DEFAULT_CONFIG.get(section, {})
+        user_section = config.get(section, {})
+        if not isinstance(default_section, dict) or not isinstance(user_section, dict):
+            continue
+        default_val = default_section.get(key)
+        user_val = user_section.get(key)
+        if user_val is not None and user_val != default_val:
+            overrides[f"{section}.{key}"] = str(user_val)
+
+    # Toolsets (if different from default)
+    default_toolsets = DEFAULT_CONFIG.get("toolsets", [])
+    user_toolsets = config.get("toolsets", [])
+    if user_toolsets != default_toolsets:
+        overrides["toolsets"] = str(user_toolsets)
+
+    # Fallback providers
+    fallbacks = config.get("fallback_providers", [])
+    if fallbacks:
+        overrides["fallback_providers"] = str(fallbacks)
+
+    return overrides
+
+
+def run_dump(args):
+    """Output a compact, copy-pasteable setup summary."""
+    show_keys = getattr(args, "show_keys", False)
+
+    # Load env from .env file so key checks work
+    from dotenv import load_dotenv
+    env_path = get_env_path()
+    if env_path.exists():
+        try:
+            load_dotenv(env_path, encoding="utf-8")
+        except UnicodeDecodeError:
+            load_dotenv(env_path, encoding="latin-1")
+    # Also try project .env as dev fallback
+    load_dotenv(get_project_root() / ".env", override=False, encoding="utf-8")
+
+    project_root = get_project_root()
+    hermes_home = get_hermes_home()
+
+    try:
+        from hermes_cli import __version__, __release_date__
+    except ImportError:
+        __version__ = "(unknown)"
+        __release_date__ = ""
+
+    commit = _get_git_commit(project_root)
+
+    try:
+        config = load_config()
+    except Exception:
+        config = {}
+
+    model, provider = _get_model_and_provider(config)
+
+    # Profile
+    try:
+        from hermes_cli.profiles import get_active_profile_name
+        profile = get_active_profile_name() or "(default)"
+    except Exception:
+        profile = "(default)"
+
+    # Terminal backend
+    terminal_cfg = config.get("terminal", {})
+    backend = terminal_cfg.get("backend", "local")
+
+    # OpenAI SDK version
+    try:
+        import openai
+        openai_ver = openai.__version__
+    except ImportError:
+        openai_ver = "not installed"
+
+    # OS info
+    os_info = f"{platform.system()} {platform.release()} {platform.machine()}"
+
+    lines = []
+    lines.append("--- hermes dump ---")
+    ver_str = f"{__version__}"
+    if __release_date__:
+        ver_str += f" ({__release_date__})"
+    ver_str += f" [{commit}]"
+    lines.append(f"version:          {ver_str}")
+    lines.append(f"os:               {os_info}")
+    lines.append(f"python:           {sys.version.split()[0]}")
+    lines.append(f"openai_sdk:       {openai_ver}")
+    lines.append(f"profile:          {profile}")
+    lines.append(f"hermes_home:      {display_hermes_home()}")
+    lines.append(f"model:            {model}")
+    lines.append(f"provider:         {provider}")
+    lines.append(f"terminal:         {backend}")
+
+    # API keys
+    lines.append("")
+    lines.append("api_keys:")
+    api_keys = [
+        ("OPENROUTER_API_KEY", "openrouter"),
+        ("OPENAI_API_KEY", "openai"),
+        ("ANTHROPIC_API_KEY", "anthropic"),
+        ("ANTHROPIC_TOKEN", "anthropic_token"),
+        ("NOUS_API_KEY", "nous"),
+        ("GLM_API_KEY", "glm/zai"),
+        ("ZAI_API_KEY", "zai"),
+        ("KIMI_API_KEY", "kimi"),
+        ("MINIMAX_API_KEY", "minimax"),
+        ("DEEPSEEK_API_KEY", "deepseek"),
+        ("DASHSCOPE_API_KEY", "dashscope"),
+        ("HF_TOKEN", "huggingface"),
+        ("AI_GATEWAY_API_KEY", "ai_gateway"),
+        ("OPENCODE_ZEN_API_KEY", "opencode_zen"),
+        ("OPENCODE_GO_API_KEY", "opencode_go"),
+        ("KILOCODE_API_KEY", "kilocode"),
+        ("FIRECRAWL_API_KEY", "firecrawl"),
+        ("TAVILY_API_KEY", "tavily"),
+        ("BROWSERBASE_API_KEY", "browserbase"),
+        ("FAL_KEY", "fal"),
+        ("ELEVENLABS_API_KEY", "elevenlabs"),
+        ("GITHUB_TOKEN", "github"),
+    ]
+
+    for env_var, label in api_keys:
+        val = os.getenv(env_var, "")
+        if show_keys and val:
+            display = _redact(val)
+        else:
+            display = "set" if val else "not set"
+        lines.append(f"  {label:<20} {display}")
+
+    # Features summary
+    lines.append("")
+    lines.append("features:")
+
+    toolsets = config.get("toolsets", ["hermes-cli"])
+    lines.append(f"  toolsets:           {', '.join(toolsets) if toolsets else '(default)'}")
+    lines.append(f"  mcp_servers:        {_count_mcp_servers(config)}")
+    lines.append(f"  memory_provider:    {_memory_provider(config)}")
+    lines.append(f"  gateway:            {_gateway_status()}")
+
+    platforms = _configured_platforms()
+    lines.append(f"  platforms:          {', '.join(platforms) if platforms else 'none'}")
+    lines.append(f"  cron_jobs:          {_cron_summary(hermes_home)}")
+    lines.append(f"  skills:             {_count_skills(hermes_home)}")
+
+    # Config overrides (non-default values)
+    overrides = _config_overrides(config)
+    if overrides:
+        lines.append("")
+        lines.append("config_overrides:")
+        for key, val in overrides.items():
+            lines.append(f"  {key}: {val}")
+
+    lines.append("--- end dump ---")
+
+    output = "\n".join(lines)
+    print(output)

hermes_cli/gateway.py

@@ -14,7 +14,20 @@ from pathlib import Path
 
 PROJECT_ROOT = Path(__file__).parent.parent.resolve()
 
-from hermes_cli.config import get_env_value, get_hermes_home, save_env_value, is_managed, managed_error
+from gateway.status import terminate_pid
+from gateway.restart import (
+    DEFAULT_GATEWAY_RESTART_DRAIN_TIMEOUT,
+    GATEWAY_SERVICE_RESTART_EXIT_CODE,
+    parse_restart_drain_timeout,
+)
+from hermes_cli.config import (
+    get_env_value,
+    get_hermes_home,
+    is_managed,
+    managed_error,
+    read_raw_config,
+    save_env_value,
+)
 # display_hermes_home is imported lazily at call sites to avoid ImportError
 # when hermes_constants is cached from a pre-update version during `hermes update`.
 from hermes_cli.setup import (
@@ -39,7 +52,7 @@ def _get_service_pids() -> set:
     pids: set = set()
 
     # --- systemd (Linux): user and system scopes ---
-    if is_linux():
+    if supports_systemd_services():
         for scope_args in [["systemctl", "--user"], ["systemctl"]]:
             try:
                 result = subprocess.run(
@@ -91,6 +104,59 @@ def _get_service_pids() -> set:
     return pids
 
 
+def _get_parent_pid(pid: int) -> int | None:
+    """Return the parent PID for ``pid``, or ``None`` when unavailable."""
+    if pid <= 1:
+        return None
+    try:
+        result = subprocess.run(
+            ["ps", "-o", "ppid=", "-p", str(pid)],
+            capture_output=True,
+            text=True,
+            timeout=5,
+        )
+    except (FileNotFoundError, subprocess.TimeoutExpired):
+        return None
+    if result.returncode != 0:
+        return None
+    raw = result.stdout.strip()
+    if not raw:
+        return None
+    try:
+        parent_pid = int(raw.splitlines()[-1].strip())
+    except ValueError:
+        return None
+    return parent_pid if parent_pid > 0 else None
+
+
+def _is_pid_ancestor_of_current_process(target_pid: int) -> bool:
+    """Return True when ``target_pid`` is this process or one of its ancestors."""
+    if target_pid <= 0:
+        return False
+
+    pid = os.getpid()
+    seen: set[int] = set()
+    while pid and pid not in seen:
+        if pid == target_pid:
+            return True
+        seen.add(pid)
+        pid = _get_parent_pid(pid) or 0
+    return False
+
+
+def _request_gateway_self_restart(pid: int) -> bool:
+    """Ask a running gateway ancestor to restart itself asynchronously."""
+    if not hasattr(signal, "SIGUSR1"):
+        return False
+    if not _is_pid_ancestor_of_current_process(pid):
+        return False
+    try:
+        os.kill(pid, signal.SIGUSR1)
+    except (ProcessLookupError, PermissionError, OSError):
+        return False
+    return True
+
+
 def find_gateway_pids(exclude_pids: set | None = None) -> list:
     """Find PIDs of running gateway processes.
 
@@ -162,7 +228,7 @@ def kill_gateway_processes(force: bool = False, exclude_pids: set | None = None)
     """Kill any running gateway processes. Returns count killed.
 
     Args:
-        force: Use SIGKILL instead of SIGTERM.
+        force: Use the platform's force-kill mechanism instead of graceful terminate.
         exclude_pids: PIDs to skip (e.g. service-managed PIDs that were just
             restarted and should not be killed).
     """
@@ -171,10 +237,7 @@ def kill_gateway_processes(force: bool = False, exclude_pids: set | None = None)
     
     for pid in pids:
         try:
-            if force and not is_windows():
-                os.kill(pid, signal.SIGKILL)
-            else:
-                os.kill(pid, signal.SIGTERM)
+            terminate_pid(pid, force=force)
             killed += 1
         except ProcessLookupError:
             # Process already gone
@@ -182,6 +245,8 @@ def kill_gateway_processes(force: bool = False, exclude_pids: set | None = None)
         except PermissionError:
             print(f"⚠ Permission denied to kill PID {pid}")
     
+        except OSError as exc:
+            print(f"Failed to kill PID {pid}: {exc}")
     return killed
 
 
@@ -225,6 +290,36 @@ def stop_profile_gateway() -> bool:
 def is_linux() -> bool:
     return sys.platform.startswith('linux')
 
+
+from hermes_constants import is_termux, is_wsl
+
+
+def _wsl_systemd_operational() -> bool:
+    """Check if systemd is actually running as PID 1 on WSL.
+
+    WSL2 with ``systemd=true`` in wsl.conf has working systemd.
+    WSL2 without it (or WSL1) does not — systemctl commands fail.
+    """
+    try:
+        result = subprocess.run(
+            ["systemctl", "is-system-running"],
+            capture_output=True, text=True, timeout=5,
+        )
+        # "running", "degraded", "starting" all mean systemd is PID 1
+        status = result.stdout.strip().lower()
+        return status in ("running", "degraded", "starting", "initializing")
+    except (FileNotFoundError, subprocess.TimeoutExpired, OSError):
+        return False
+
+
+def supports_systemd_services() -> bool:
+    if not is_linux() or is_termux():
+        return False
+    if is_wsl():
+        return _wsl_systemd_operational()
+    return True
+
+
 def is_macos() -> bool:
     return sys.platform == 'darwin'
 
@@ -243,18 +338,18 @@ SERVICE_DESCRIPTION = "Hermes Agent Gateway - Messaging Platform Integration"
 def _profile_suffix() -> str:
     """Derive a service-name suffix from the current HERMES_HOME.
 
-    Returns ``""`` for the default ``~/.hermes``, the profile name for
-    ``~/.hermes/profiles/<name>``, or a short hash for any other custom
-    HERMES_HOME path.
+    Returns ``""`` for the default root, the profile name for
+    ``<root>/profiles/<name>``, or a short hash for any other path.
+    Works correctly in Docker (HERMES_HOME=/opt/data) and standard deployments.
     """
     import hashlib
     import re
-    from pathlib import Path as _Path
+    from hermes_constants import get_default_hermes_root
     home = get_hermes_home().resolve()
-    default = (_Path.home() / ".hermes").resolve()
+    default = get_default_hermes_root().resolve()
     if home == default:
         return ""
-    # Detect ~/.hermes/profiles/<name> pattern → use the profile name
+    # Detect <root>/profiles/<name> pattern → use the profile name
     profiles_root = (default / "profiles").resolve()
     try:
         rel = home.relative_to(profiles_root)
@@ -279,9 +374,9 @@ def _profile_arg(hermes_home: str | None = None) -> str:
             service definition for a different user (e.g. system service).
     """
     import re
-    from pathlib import Path as _Path
+    from hermes_constants import get_default_hermes_root
     home = Path(hermes_home or str(get_hermes_home())).resolve()
-    default = (_Path.home() / ".hermes").resolve()
+    default = get_default_hermes_root().resolve()
     if home == default:
         return ""
     profiles_root = (default / "profiles").resolve()
@@ -308,8 +403,6 @@ def get_service_name() -> str:
     return f"{_SERVICE_BASE}-{suffix}"
 
 
-SERVICE_NAME = _SERVICE_BASE  # backward-compat for external importers; prefer get_service_name()
-
 
 def get_systemd_unit_path(system: bool = False) -> Path:
     name = get_service_name()
@@ -477,13 +570,15 @@ def install_linux_gateway_from_setup(force: bool = False) -> tuple[str | None, b
 
 
 def get_systemd_linger_status() -> tuple[bool | None, str]:
-    """Return whether systemd user lingering is enabled for the current user.
+    """Return systemd linger status for the current user.
 
     Returns:
         (True, "") when linger is enabled.
         (False, "") when linger is disabled.
         (None, detail) when the status could not be determined.
     """
+    if is_termux():
+        return None, "not supported in Termux"
     if not is_linux():
         return None, "not supported on this platform"
 
@@ -581,17 +676,6 @@ def get_python_path() -> str:
             return str(venv_python)
     return sys.executable
 
-def get_hermes_cli_path() -> str:
-    """Get the path to the hermes CLI."""
-    # Check if installed via pip
-    import shutil
-    hermes_bin = shutil.which("hermes")
-    if hermes_bin:
-        return hermes_bin
-    
-    # Fallback to direct module execution
-    return f"{get_python_path()} -m hermes_cli.main"
-
 
 # =============================================================================
 # Systemd (Linux)
@@ -608,6 +692,24 @@ def _build_user_local_paths(home: Path, path_entries: list[str]) -> list[str]:
     return [p for p in candidates if p not in path_entries and Path(p).exists()]
 
 
+def _remap_path_for_user(path: str, target_home_dir: str) -> str:
+    """Remap *path* from the current user's home to *target_home_dir*.
+
+    If *path* lives under ``Path.home()`` the corresponding prefix is swapped
+    to *target_home_dir*; otherwise the path is returned unchanged.
+
+      /root/.hermes/hermes-agent  -> /home/alice/.hermes/hermes-agent
+      /opt/hermes                 -> /opt/hermes  (kept as-is)
+    """
+    current_home = Path.home().resolve()
+    resolved = Path(path).resolve()
+    try:
+        relative = resolved.relative_to(current_home)
+        return str(Path(target_home_dir) / relative)
+    except ValueError:
+        return str(resolved)
+
+
 def _hermes_home_for_target_user(target_home_dir: str) -> str:
     """Remap the current HERMES_HOME to the equivalent under a target user's home.
 
@@ -650,11 +752,21 @@ def generate_systemd_unit(system: bool = False, run_as_user: str | None = None)
             path_entries.append(resolved_node_dir)
 
     common_bin_paths = ["/usr/local/sbin", "/usr/local/bin", "/usr/sbin", "/usr/bin", "/sbin", "/bin"]
+    restart_timeout = max(60, int(_get_restart_drain_timeout() or 0))
 
     if system:
         username, group_name, home_dir = _system_service_identity(run_as_user)
         hermes_home = _hermes_home_for_target_user(home_dir)
         profile_arg = _profile_arg(hermes_home)
+        # Remap all paths that may resolve under the calling user's home
+        # (e.g. /root/) to the target user's home so the service can
+        # actually access them.
+        python_path = _remap_path_for_user(python_path, home_dir)
+        working_dir = _remap_path_for_user(working_dir, home_dir)
+        venv_dir = _remap_path_for_user(venv_dir, home_dir)
+        venv_bin = _remap_path_for_user(venv_bin, home_dir)
+        node_bin = _remap_path_for_user(node_bin, home_dir)
+        path_entries = [_remap_path_for_user(p, home_dir) for p in path_entries]
         path_entries.extend(_build_user_local_paths(Path(home_dir), path_entries))
         path_entries.extend(common_bin_paths)
         sane_path = ":".join(path_entries)
@@ -679,9 +791,11 @@ Environment="VIRTUAL_ENV={venv_dir}"
 Environment="HERMES_HOME={hermes_home}"
 Restart=on-failure
 RestartSec=30
+RestartForceExitStatus={GATEWAY_SERVICE_RESTART_EXIT_CODE}
 KillMode=mixed
 KillSignal=SIGTERM
-TimeoutStopSec=60
+ExecReload=/bin/kill -USR1 $MAINPID
+TimeoutStopSec={restart_timeout}
 StandardOutput=journal
 StandardError=journal
 
@@ -709,9 +823,11 @@ Environment="VIRTUAL_ENV={venv_dir}"
 Environment="HERMES_HOME={hermes_home}"
 Restart=on-failure
 RestartSec=30
+RestartForceExitStatus={GATEWAY_SERVICE_RESTART_EXIT_CODE}
 KillMode=mixed
 KillSignal=SIGTERM
-TimeoutStopSec=60
+ExecReload=/bin/kill -USR1 $MAINPID
+TimeoutStopSec={restart_timeout}
 StandardOutput=journal
 StandardError=journal
 
@@ -766,7 +882,7 @@ def _print_linger_enable_warning(username: str, detail: str | None = None) -> No
 
 def _ensure_linger_enabled() -> None:
     """Enable linger when possible so the user gateway survives logout."""
-    if not is_linux():
+    if is_termux() or not is_linux():
         return
 
     import getpass
@@ -814,6 +930,20 @@ def _select_systemd_scope(system: bool = False) -> bool:
     return get_systemd_unit_path(system=True).exists() and not get_systemd_unit_path(system=False).exists()
 
 
+def _get_restart_drain_timeout() -> float:
+    """Return the configured gateway restart drain timeout in seconds."""
+    raw = os.getenv("HERMES_RESTART_DRAIN_TIMEOUT", "").strip()
+    if not raw:
+        cfg = read_raw_config()
+        agent_cfg = cfg.get("agent", {}) if isinstance(cfg, dict) else {}
+        raw = str(
+            agent_cfg.get(
+                "restart_drain_timeout", DEFAULT_GATEWAY_RESTART_DRAIN_TIMEOUT
+            )
+        )
+    return parse_restart_drain_timeout(raw)
+
+
 def systemd_install(force: bool = False, system: bool = False, run_as_user: str | None = None):
     if system:
         _require_root_for_system_service("install")
@@ -899,7 +1029,13 @@ def systemd_restart(system: bool = False):
     if system:
         _require_root_for_system_service("restart")
     refresh_systemd_unit_if_needed(system=system)
-    subprocess.run(_systemctl_cmd(system) + ["restart", get_service_name()], check=True, timeout=90)
+    from gateway.status import get_running_pid
+
+    pid = get_running_pid()
+    if pid is not None and _request_gateway_self_restart(pid):
+        print(f"✓ {_service_scope_label(system).capitalize()} service restart requested")
+        return
+    subprocess.run(_systemctl_cmd(system) + ["reload-or-restart", get_service_name()], check=True, timeout=90)
     print(f"✓ {_service_scope_label(system).capitalize()} service restarted")
 
 
@@ -1172,10 +1308,22 @@ def launchd_start():
 
 def launchd_stop():
     label = get_launchd_label()
-    subprocess.run(["launchctl", "kill", "SIGTERM", f"{_launchd_domain()}/{label}"], check=True, timeout=30)
+    target = f"{_launchd_domain()}/{label}"
+    # bootout unloads the service definition so KeepAlive doesn't respawn
+    # the process.  A plain `kill SIGTERM` only signals the process — launchd
+    # immediately restarts it because KeepAlive.SuccessfulExit = false.
+    # `hermes gateway start` re-bootstraps when it detects the job is unloaded.
+    try:
+        subprocess.run(["launchctl", "bootout", target], check=True, timeout=90)
+    except subprocess.CalledProcessError as e:
+        if e.returncode in (3, 113):
+            pass  # Already unloaded — nothing to stop.
+        else:
+            raise
+    _wait_for_gateway_exit(timeout=10.0, force_after=5.0)
     print("✓ Service stopped")
 
-def _wait_for_gateway_exit(timeout: float = 10.0, force_after: float = 5.0):
+def _wait_for_gateway_exit(timeout: float = 10.0, force_after: float | None = 5.0) -> bool:
     """Wait for the gateway process (by saved PID) to exit.
 
     Uses the PID from the gateway.pid file — not launchd labels — so this
@@ -1184,44 +1332,59 @@ def _wait_for_gateway_exit(timeout: float = 10.0, force_after: float = 5.0):
 
     Args:
         timeout: Total seconds to wait before giving up.
-        force_after: Seconds of graceful waiting before sending SIGKILL.
+        force_after: Seconds of graceful waiting before escalating to force-kill.
     """
     import time
     from gateway.status import get_running_pid
 
     deadline = time.monotonic() + timeout
-    force_deadline = time.monotonic() + force_after
+    force_deadline = (time.monotonic() + force_after) if force_after is not None else None
     force_sent = False
 
     while time.monotonic() < deadline:
         pid = get_running_pid()
         if pid is None:
-            return  # Process exited cleanly.
+            return True  # Process exited cleanly.
 
-        if not force_sent and time.monotonic() >= force_deadline:
+        if force_after is not None and not force_sent and time.monotonic() >= force_deadline:
             # Grace period expired — force-kill the specific PID.
             try:
-                os.kill(pid, signal.SIGKILL)
+                terminate_pid(pid, force=True)
                 print(f"⚠ Gateway PID {pid} did not exit gracefully; sent SIGKILL")
-            except (ProcessLookupError, PermissionError):
-                return  # Already gone or we can't touch it.
+            except (ProcessLookupError, PermissionError, OSError):
+                return True  # Already gone or we can't touch it.
             force_sent = True
 
         time.sleep(0.3)
 
-    # Timed out even after SIGKILL.
+    # Timed out even after force-kill.
     remaining_pid = get_running_pid()
     if remaining_pid is not None:
         print(f"⚠ Gateway PID {remaining_pid} still running after {timeout}s — restart may fail")
+        return False
+    return True
 
 
 def launchd_restart():
     label = get_launchd_label()
     target = f"{_launchd_domain()}/{label}"
-    # Use kickstart -k so launchd performs an atomic kill+restart.
-    # A two-step stop/start from inside the gateway's own process tree
-    # would kill the shell before the start command is reached.
+    drain_timeout = _get_restart_drain_timeout()
+    from gateway.status import get_running_pid
+
     try:
+        pid = get_running_pid()
+        if pid is not None and _request_gateway_self_restart(pid):
+            print("✓ Service restart requested")
+            return
+        if pid is not None:
+            try:
+                terminate_pid(pid, force=False)
+            except (ProcessLookupError, PermissionError, OSError):
+                pid = None
+            if pid is not None:
+                exited = _wait_for_gateway_exit(timeout=drain_timeout, force_after=None)
+                if not exited:
+                    print(f"⚠ Gateway drain timed out after {drain_timeout:.0f}s — forcing launchd restart")
         subprocess.run(["launchctl", "kickstart", "-k", target], check=True, timeout=90)
         print("✓ Service restarted")
     except subprocess.CalledProcessError as e:
@@ -1406,7 +1569,7 @@ _PLATFORMS = [
             "   Or via API: curl -X POST https://your-server/_matrix/client/v3/login \\",
             "     -d '{\"type\":\"m.login.password\",\"user\":\"@bot:server\",\"password\":\"...\"}'",
             "4. Alternatively, provide user ID + password and Hermes will log in directly",
-            "5. For E2EE: set MATRIX_ENCRYPTION=true (requires pip install 'matrix-nio[e2e]')",
+            "5. For E2EE: set MATRIX_ENCRYPTION=true (requires pip install 'mautrix[encryption]')",
             "6. To find your user ID: it's @username:your-server (shown in Element profile)",
         ],
         "vars": [
@@ -1588,6 +1751,40 @@ _PLATFORMS = [
              "help": "Chat ID for scheduled results and notifications."},
         ],
     },
+    {
+        "key": "weixin",
+        "label": "Weixin / WeChat",
+        "emoji": "💬",
+        "token_var": "WEIXIN_ACCOUNT_ID",
+    },
+    {
+        "key": "bluebubbles",
+        "label": "BlueBubbles (iMessage)",
+        "emoji": "💬",
+        "token_var": "BLUEBUBBLES_SERVER_URL",
+        "setup_instructions": [
+            "1. Install BlueBubbles on a Mac that will act as your iMessage server:",
+            "   https://bluebubbles.app/",
+            "2. Complete the BlueBubbles setup wizard — sign in with your Apple ID",
+            "3. In BlueBubbles Settings → API, note the Server URL and password",
+            "4. The server URL is typically http://<your-mac-ip>:1234",
+            "5. Hermes connects via the BlueBubbles REST API and receives",
+            "   incoming messages via a local webhook",
+            "6. To authorize users, use DM pairing: hermes pairing generate bluebubbles",
+            "   Share the code — the user sends it via iMessage to get approved",
+        ],
+        "vars": [
+            {"name": "BLUEBUBBLES_SERVER_URL", "prompt": "BlueBubbles server URL (e.g. http://192.168.1.10:1234)", "password": False,
+             "help": "The URL shown in BlueBubbles Settings → API."},
+            {"name": "BLUEBUBBLES_PASSWORD", "prompt": "BlueBubbles server password", "password": True,
+             "help": "The password shown in BlueBubbles Settings → API."},
+            {"name": "BLUEBUBBLES_ALLOWED_USERS", "prompt": "Pre-authorized phone numbers or iMessage IDs (comma-separated, or leave empty for DM pairing)", "password": False,
+             "is_allowlist": True,
+             "help": "Optional — pre-authorize specific users. Leave empty to use DM pairing instead (recommended)."},
+            {"name": "BLUEBUBBLES_HOME_CHANNEL", "prompt": "Home channel (phone number or iMessage ID for cron/notifications, or empty)", "password": False,
+             "help": "Phone number or Apple ID to deliver cron results and notifications to."},
+        ],
+    },
 ]
 
 
@@ -1632,6 +1829,13 @@ def _platform_status(platform: dict) -> str:
         if val or password or homeserver:
             return "partially configured"
         return "not configured"
+    if platform.get("key") == "weixin":
+        token = get_env_value("WEIXIN_TOKEN")
+        if val and token:
+            return "configured"
+        if val or token:
+            return "partially configured"
+        return "not configured"
     if val:
         return "configured"
     return "not configured"
@@ -1651,6 +1855,8 @@ def _runtime_health_lines() -> list[str]:
     lines: list[str] = []
     gateway_state = state.get("gateway_state")
     exit_reason = state.get("exit_reason")
+    active_agents = state.get("active_agents")
+    restart_requested = state.get("restart_requested")
     platforms = state.get("platforms", {}) or {}
 
     for platform, pdata in platforms.items():
@@ -1660,6 +1866,10 @@ def _runtime_health_lines() -> list[str]:
 
     if gateway_state == "startup_failed" and exit_reason:
         lines.append(f"⚠ Last startup issue: {exit_reason}")
+    elif gateway_state == "draining":
+        action = "restart" if restart_requested else "shutdown"
+        count = int(active_agents or 0)
+        lines.append(f"⏳ Gateway draining for {action} ({count} active agent(s))")
     elif gateway_state == "stopped" and exit_reason:
         lines.append(f"⚠ Last shutdown reason: {exit_reason}")
 
@@ -1735,7 +1945,7 @@ def _setup_standard_platform(platform: dict):
                     print_warning("  Open access enabled — anyone can use your bot!")
                 elif access_idx == 1:
                     print_success("  DM pairing mode — users will receive a code to request access.")
-                    print_info("  Approve with: hermes pairing approve {platform} {code}")
+                    print_info("  Approve with: hermes pairing approve <platform> <code>")
                 else:
                     print_info("  Skipped — configure later with 'hermes gateway setup'")
             continue
@@ -1773,7 +1983,7 @@ def _setup_whatsapp():
 
 def _is_service_installed() -> bool:
     """Check if the gateway is installed as a system service."""
-    if is_linux():
+    if supports_systemd_services():
         return get_systemd_unit_path(system=False).exists() or get_systemd_unit_path(system=True).exists()
     elif is_macos():
         return get_launchd_plist_path().exists()
@@ -1782,7 +1992,7 @@ def _is_service_installed() -> bool:
 
 def _is_service_running() -> bool:
     """Check if the gateway service is currently running."""
-    if is_linux():
+    if supports_systemd_services():
         user_unit_exists = get_systemd_unit_path(system=False).exists()
         system_unit_exists = get_systemd_unit_path(system=True).exists()
 
@@ -1822,6 +2032,133 @@ def _is_service_running() -> bool:
     return len(find_gateway_pids()) > 0
 
 
+def _setup_weixin():
+    """Interactive setup for Weixin / WeChat personal accounts."""
+    print()
+    print(color("  ─── 💬 Weixin / WeChat Setup ───", Colors.CYAN))
+    print()
+    print_info("  1. Hermes will open Tencent iLink QR login in this terminal.")
+    print_info("  2. Use WeChat to scan and confirm the QR code.")
+    print_info("  3. Hermes will store the returned account_id/token in ~/.hermes/.env.")
+    print_info("  4. This adapter supports native text, image, video, and document delivery.")
+
+    existing_account = get_env_value("WEIXIN_ACCOUNT_ID")
+    existing_token = get_env_value("WEIXIN_TOKEN")
+    if existing_account and existing_token:
+        print()
+        print_success("Weixin is already configured.")
+        if not prompt_yes_no("  Reconfigure Weixin?", False):
+            return
+
+    try:
+        from gateway.platforms.weixin import check_weixin_requirements, qr_login
+    except Exception as exc:
+        print_error(f"  Weixin adapter import failed: {exc}")
+        print_info("  Install gateway dependencies first, then retry.")
+        return
+
+    if not check_weixin_requirements():
+        print_error("  Missing dependencies: Weixin needs aiohttp and cryptography.")
+        print_info("  Install them, then rerun `hermes gateway setup`.")
+        return
+
+    print()
+    if not prompt_yes_no("  Start QR login now?", True):
+        print_info("  Cancelled.")
+        return
+
+    import asyncio
+    try:
+        credentials = asyncio.run(qr_login(str(get_hermes_home())))
+    except KeyboardInterrupt:
+        print()
+        print_warning("  Weixin setup cancelled.")
+        return
+    except Exception as exc:
+        print_error(f"  QR login failed: {exc}")
+        return
+
+    if not credentials:
+        print_warning("  QR login did not complete.")
+        return
+
+    account_id = credentials.get("account_id", "")
+    token = credentials.get("token", "")
+    base_url = credentials.get("base_url", "")
+    user_id = credentials.get("user_id", "")
+
+    save_env_value("WEIXIN_ACCOUNT_ID", account_id)
+    save_env_value("WEIXIN_TOKEN", token)
+    if base_url:
+        save_env_value("WEIXIN_BASE_URL", base_url)
+    save_env_value("WEIXIN_CDN_BASE_URL", get_env_value("WEIXIN_CDN_BASE_URL") or "https://novac2c.cdn.weixin.qq.com/c2c")
+
+    print()
+    access_choices = [
+        "Use DM pairing approval (recommended)",
+        "Allow all direct messages",
+        "Only allow listed user IDs",
+        "Disable direct messages",
+    ]
+    access_idx = prompt_choice("  How should direct messages be authorized?", access_choices, 0)
+    if access_idx == 0:
+        save_env_value("WEIXIN_DM_POLICY", "pairing")
+        save_env_value("WEIXIN_ALLOW_ALL_USERS", "false")
+        save_env_value("WEIXIN_ALLOWED_USERS", "")
+        print_success("  DM pairing enabled.")
+        print_info("  Unknown DM users can request access and you approve them with `hermes pairing approve`.")
+    elif access_idx == 1:
+        save_env_value("WEIXIN_DM_POLICY", "open")
+        save_env_value("WEIXIN_ALLOW_ALL_USERS", "true")
+        save_env_value("WEIXIN_ALLOWED_USERS", "")
+        print_warning("  Open DM access enabled for Weixin.")
+    elif access_idx == 2:
+        default_allow = user_id or ""
+        allowlist = prompt("  Allowed Weixin user IDs (comma-separated)", default_allow, password=False).replace(" ", "")
+        save_env_value("WEIXIN_DM_POLICY", "allowlist")
+        save_env_value("WEIXIN_ALLOW_ALL_USERS", "false")
+        save_env_value("WEIXIN_ALLOWED_USERS", allowlist)
+        print_success("  Weixin allowlist saved.")
+    else:
+        save_env_value("WEIXIN_DM_POLICY", "disabled")
+        save_env_value("WEIXIN_ALLOW_ALL_USERS", "false")
+        save_env_value("WEIXIN_ALLOWED_USERS", "")
+        print_warning("  Direct messages disabled.")
+
+    print()
+    group_choices = [
+        "Disable group chats (recommended)",
+        "Allow all group chats",
+        "Only allow listed group chat IDs",
+    ]
+    group_idx = prompt_choice("  How should group chats be handled?", group_choices, 0)
+    if group_idx == 0:
+        save_env_value("WEIXIN_GROUP_POLICY", "disabled")
+        save_env_value("WEIXIN_GROUP_ALLOWED_USERS", "")
+        print_info("  Group chats disabled.")
+    elif group_idx == 1:
+        save_env_value("WEIXIN_GROUP_POLICY", "open")
+        save_env_value("WEIXIN_GROUP_ALLOWED_USERS", "")
+        print_warning("  All group chats enabled.")
+    else:
+        allow_groups = prompt("  Allowed group chat IDs (comma-separated)", "", password=False).replace(" ", "")
+        save_env_value("WEIXIN_GROUP_POLICY", "allowlist")
+        save_env_value("WEIXIN_GROUP_ALLOWED_USERS", allow_groups)
+        print_success("  Group allowlist saved.")
+
+    if user_id:
+        print()
+        if prompt_yes_no(f"  Use your Weixin user ID ({user_id}) as the home channel?", True):
+            save_env_value("WEIXIN_HOME_CHANNEL", user_id)
+            print_success(f"  Home channel set to {user_id}")
+
+    print()
+    print_success("Weixin configured!")
+    print_info(f"  Account ID: {account_id}")
+    if user_id:
+        print_info(f"  User ID: {user_id}")
+
+
 def _setup_signal():
     """Interactive setup for Signal messenger."""
     import shutil
@@ -1955,7 +2292,7 @@ def gateway_setup():
     service_installed = _is_service_installed()
     service_running = _is_service_running()
 
-    if is_linux() and has_conflicting_systemd_units():
+    if supports_systemd_services() and has_conflicting_systemd_units():
         print_systemd_scope_conflict_warning()
         print()
 
@@ -1965,7 +2302,7 @@ def gateway_setup():
         print_warning("Gateway service is installed but not running.")
         if prompt_yes_no("  Start it now?", True):
             try:
-                if is_linux():
+                if supports_systemd_services():
                     systemd_start()
                 elif is_macos():
                     launchd_start()
@@ -1997,6 +2334,8 @@ def gateway_setup():
             _setup_whatsapp()
         elif platform["key"] == "signal":
             _setup_signal()
+        elif platform["key"] == "weixin":
+            _setup_weixin()
         else:
             _setup_standard_platform(platform)
 
@@ -2016,7 +2355,7 @@ def gateway_setup():
         if service_running:
             if prompt_yes_no("  Restart the gateway to pick up changes?", True):
                 try:
-                    if is_linux():
+                    if supports_systemd_services():
                         systemd_restart()
                     elif is_macos():
                         launchd_restart()
@@ -2028,7 +2367,7 @@ def gateway_setup():
         elif service_installed:
             if prompt_yes_no("  Start the gateway service?", True):
                 try:
-                    if is_linux():
+                    if supports_systemd_services():
                         systemd_start()
                     elif is_macos():
                         launchd_start()
@@ -2036,13 +2375,14 @@ def gateway_setup():
                     print_error(f"  Start failed: {e}")
         else:
             print()
-            if is_linux() or is_macos():
-                platform_name = "systemd" if is_linux() else "launchd"
-                if prompt_yes_no(f"  Install the gateway as a {platform_name} service? (runs in background, starts on boot)", True):
+            if supports_systemd_services() or is_macos():
+                platform_name = "systemd" if supports_systemd_services() else "launchd"
+                wsl_note = " (note: services may not survive WSL restarts)" if is_wsl() else ""
+                if prompt_yes_no(f"  Install the gateway as a {platform_name} service?{wsl_note} (runs in background, starts on boot)", True):
                     try:
                         installed_scope = None
                         did_install = False
-                        if is_linux():
+                        if supports_systemd_services():
                             installed_scope, did_install = install_linux_gateway_from_setup(force=False)
                         else:
                             launchd_install(force=False)
@@ -2050,7 +2390,7 @@ def gateway_setup():
                         print()
                         if did_install and prompt_yes_no("  Start the service now?", True):
                             try:
-                                if is_linux():
+                                if supports_systemd_services():
                                     systemd_start(system=installed_scope == "system")
                                 else:
                                     launchd_start()
@@ -2061,12 +2401,23 @@ def gateway_setup():
                         print_info("  You can try manually: hermes gateway install")
                 else:
                     print_info("  You can install later: hermes gateway install")
-                    if is_linux():
+                    if supports_systemd_services():
                         print_info("  Or as a boot-time service: sudo hermes gateway install --system")
-                    print_info("  Or run in foreground:  hermes gateway")
+                    print_info("  Or run in foreground:  hermes gateway run")
+            elif is_wsl():
+                print_info("  WSL detected but systemd is not running.")
+                print_info("  Run in foreground: hermes gateway run")
+                print_info("  For persistence:   tmux new -s hermes 'hermes gateway run'")
+                print_info("  To enable systemd: add systemd=true to /etc/wsl.conf, then 'wsl --shutdown'")
             else:
-                print_info("  Service install not supported on this platform.")
-                print_info("  Run in foreground: hermes gateway")
+                if is_termux():
+                    from hermes_constants import display_hermes_home as _dhh
+                    print_info("  Termux does not use systemd/launchd services.")
+                    print_info("  Run in foreground: hermes gateway run")
+                    print_info(f"  Or start it manually in the background (best effort): nohup hermes gateway run >{_dhh()}/logs/gateway.log 2>&1 &")
+                else:
+                    print_info("  Service install not supported on this platform.")
+                    print_info("  Run in foreground: hermes gateway run")
     else:
         print()
         print_info("No platforms configured. Run 'hermes gateway setup' when ready.")
@@ -2102,10 +2453,28 @@ def gateway_command(args):
         force = getattr(args, 'force', False)
         system = getattr(args, 'system', False)
         run_as_user = getattr(args, 'run_as_user', None)
-        if is_linux():
+        if is_termux():
+            print("Gateway service installation is not supported on Termux.")
+            print("Run manually: hermes gateway")
+            sys.exit(1)
+        if supports_systemd_services():
+            if is_wsl():
+                print_warning("WSL detected — systemd services may not survive WSL restarts.")
+                print_info("  Consider running in foreground instead: hermes gateway run")
+                print_info("  Or use tmux/screen for persistence: tmux new -s hermes 'hermes gateway run'")
+                print()
             systemd_install(force=force, system=system, run_as_user=run_as_user)
         elif is_macos():
             launchd_install(force)
+        elif is_wsl():
+            print("WSL detected but systemd is not running.")
+            print("Either enable systemd (add systemd=true to /etc/wsl.conf and restart WSL)")
+            print("or run the gateway in foreground mode:")
+            print()
+            print("  hermes gateway run                              # direct foreground")
+            print("  tmux new -s hermes 'hermes gateway run'         # persistent via tmux")
+            print("  nohup hermes gateway run > ~/.hermes/logs/gateway.log 2>&1 &  # background")
+            sys.exit(1)
         else:
             print("Service installation not supported on this platform.")
             print("Run manually: hermes gateway run")
@@ -2116,7 +2485,11 @@ def gateway_command(args):
             managed_error("uninstall gateway service (managed by NixOS)")
             return
         system = getattr(args, 'system', False)
-        if is_linux():
+        if is_termux():
+            print("Gateway service uninstall is not supported on Termux because there is no managed service to remove.")
+            print("Stop manual runs with: hermes gateway stop")
+            sys.exit(1)
+        if supports_systemd_services():
             systemd_uninstall(system=system)
         elif is_macos():
             launchd_uninstall()
@@ -2126,10 +2499,24 @@ def gateway_command(args):
     
     elif subcmd == "start":
         system = getattr(args, 'system', False)
-        if is_linux():
+        if is_termux():
+            print("Gateway service start is not supported on Termux because there is no system service manager.")
+            print("Run manually: hermes gateway")
+            sys.exit(1)
+        if supports_systemd_services():
             systemd_start(system=system)
         elif is_macos():
             launchd_start()
+        elif is_wsl():
+            print("WSL detected but systemd is not available.")
+            print("Run the gateway in foreground mode instead:")
+            print()
+            print("  hermes gateway run                              # direct foreground")
+            print("  tmux new -s hermes 'hermes gateway run'         # persistent via tmux")
+            print("  nohup hermes gateway run > ~/.hermes/logs/gateway.log 2>&1 &  # background")
+            print()
+            print("To enable systemd: add systemd=true to /etc/wsl.conf and run 'wsl --shutdown' from PowerShell.")
+            sys.exit(1)
         else:
             print("Not supported on this platform.")
             sys.exit(1)
@@ -2141,7 +2528,7 @@ def gateway_command(args):
         if stop_all:
             # --all: kill every gateway process on the machine
             service_available = False
-            if is_linux() and (get_systemd_unit_path(system=False).exists() or get_systemd_unit_path(system=True).exists()):
+            if supports_systemd_services() and (get_systemd_unit_path(system=False).exists() or get_systemd_unit_path(system=True).exists()):
                 try:
                     systemd_stop(system=system)
                     service_available = True
@@ -2162,7 +2549,7 @@ def gateway_command(args):
         else:
             # Default: stop only the current profile's gateway
             service_available = False
-            if is_linux() and (get_systemd_unit_path(system=False).exists() or get_systemd_unit_path(system=True).exists()):
+            if supports_systemd_services() and (get_systemd_unit_path(system=False).exists() or get_systemd_unit_path(system=True).exists()):
                 try:
                     systemd_stop(system=system)
                     service_available = True
@@ -2190,7 +2577,7 @@ def gateway_command(args):
         system = getattr(args, 'system', False)
         service_configured = False
         
-        if is_linux() and (get_systemd_unit_path(system=False).exists() or get_systemd_unit_path(system=True).exists()):
+        if supports_systemd_services() and (get_systemd_unit_path(system=False).exists() or get_systemd_unit_path(system=True).exists()):
             service_configured = True
             try:
                 systemd_restart(system=system)
@@ -2207,7 +2594,7 @@ def gateway_command(args):
         
         if not service_available:
             # systemd/launchd restart failed — check if linger is the issue
-            if is_linux():
+            if supports_systemd_services():
                 linger_ok, _detail = get_systemd_linger_status()
                 if linger_ok is not True:
                     import getpass
@@ -2244,7 +2631,7 @@ def gateway_command(args):
         system = getattr(args, 'system', False)
         
         # Check for service first
-        if is_linux() and (get_systemd_unit_path(system=False).exists() or get_systemd_unit_path(system=True).exists()):
+        if supports_systemd_services() and (get_systemd_unit_path(system=False).exists() or get_systemd_unit_path(system=True).exists()):
             systemd_status(deep, system=system)
         elif is_macos() and get_launchd_plist_path().exists():
             launchd_status(deep)
@@ -2261,9 +2648,17 @@ def gateway_command(args):
                     for line in runtime_lines:
                         print(f"  {line}")
                 print()
-                print("To install as a service:")
-                print("  hermes gateway install")
-                print("  sudo hermes gateway install --system")
+                if is_termux():
+                    print("Termux note:")
+                    print("  Android may stop background jobs when Termux is suspended")
+                elif is_wsl():
+                    print("WSL note:")
+                    print("  The gateway is running in foreground/manual mode (recommended for WSL).")
+                    print("  Use tmux or screen for persistence across terminal closes.")
+                else:
+                    print("To install as a service:")
+                    print("  hermes gateway install")
+                    print("  sudo hermes gateway install --system")
             else:
                 print("✗ Gateway is not running")
                 runtime_lines = _runtime_health_lines()
@@ -2274,6 +2669,12 @@ def gateway_command(args):
                         print(f"  {line}")
                 print()
                 print("To start:")
-                print("  hermes gateway          # Run in foreground")
-                print("  hermes gateway install  # Install as user service")
-                print("  sudo hermes gateway install --system  # Install as boot-time system service")
+                print("  hermes gateway run      # Run in foreground")
+                if is_termux():
+                    print("  nohup hermes gateway run > ~/.hermes/logs/gateway.log 2>&1 &  # Best-effort background start")
+                elif is_wsl():
+                    print("  tmux new -s hermes 'hermes gateway run'         # persistent via tmux")
+                    print("  nohup hermes gateway run > ~/.hermes/logs/gateway.log 2>&1 &  # background")
+                else:
+                    print("  hermes gateway install  # Install as user service")
+                    print("  sudo hermes gateway install --system  # Install as boot-time system service")

hermes_cli/main.py

@@ -97,10 +97,11 @@ def _apply_profile_override() -> None:
             consume = 1
             break
 
-    # 2. If no flag, check ~/.hermes/active_profile
+    # 2. If no flag, check active_profile in the hermes root
     if profile_name is None:
         try:
-            active_path = Path.home() / ".hermes" / "active_profile"
+            from hermes_constants import get_default_hermes_root
+            active_path = get_default_hermes_root() / "active_profile"
             if active_path.exists():
                 name = active_path.read_text().strip()
                 if name and name != "default":
@@ -646,6 +647,7 @@ def cmd_chat(args):
         "verbose": args.verbose,
         "quiet": getattr(args, "quiet", False),
         "query": args.query,
+        "image": getattr(args, "image", None),
         "resume": getattr(args, "resume", None),
         "worktree": getattr(args, "worktree", False),
         "checkpoints": getattr(args, "checkpoints", False),
@@ -857,7 +859,6 @@ def cmd_whatsapp(args):
 
 def cmd_setup(args):
     """Interactive setup wizard."""
-    _require_tty("setup")
     from hermes_cli.setup import run_setup_wizard
     run_setup_wizard(args)
 
@@ -967,10 +968,11 @@ def select_provider_and_model(args=None):
         ("alibaba", "Alibaba Cloud / DashScope Coding (Qwen + multi-provider)"),
     ]
 
-    # Add user-defined custom providers from config.yaml
-    custom_providers_cfg = config.get("custom_providers") or []
-    _custom_provider_map = {}  # key → {name, base_url, api_key}
-    if isinstance(custom_providers_cfg, list):
+    def _named_custom_provider_map(cfg) -> dict[str, dict[str, str]]:
+        custom_providers_cfg = cfg.get("custom_providers") or []
+        custom_provider_map = {}
+        if not isinstance(custom_providers_cfg, list):
+            return custom_provider_map
         for entry in custom_providers_cfg:
             if not isinstance(entry, dict):
                 continue
@@ -979,16 +981,23 @@ def select_provider_and_model(args=None):
             if not name or not base_url:
                 continue
             key = "custom:" + name.lower().replace(" ", "-")
-            short_url = base_url.replace("https://", "").replace("http://", "").rstrip("/")
-            saved_model = entry.get("model", "")
-            model_hint = f" — {saved_model}" if saved_model else ""
-            top_providers.append((key, f"{name} ({short_url}){model_hint}"))
-            _custom_provider_map[key] = {
+            custom_provider_map[key] = {
                 "name": name,
                 "base_url": base_url,
                 "api_key": entry.get("api_key", ""),
-                "model": saved_model,
+                "model": entry.get("model", ""),
             }
+        return custom_provider_map
+
+    # Add user-defined custom providers from config.yaml
+    _custom_provider_map = _named_custom_provider_map(config)  # key → {name, base_url, api_key}
+    for key, provider_info in _custom_provider_map.items():
+        name = provider_info["name"]
+        base_url = provider_info["base_url"]
+        short_url = base_url.replace("https://", "").replace("http://", "").rstrip("/")
+        saved_model = provider_info.get("model", "")
+        model_hint = f" — {saved_model}" if saved_model else ""
+        top_providers.append((key, f"{name} ({short_url}){model_hint}"))
 
     top_keys = {k for k, _ in top_providers}
     extended_keys = {k for k, _ in extended_providers}
@@ -1053,8 +1062,15 @@ def select_provider_and_model(args=None):
         _model_flow_copilot(config, current_model)
     elif selected_provider == "custom":
         _model_flow_custom(config)
-    elif selected_provider.startswith("custom:") and selected_provider in _custom_provider_map:
-        _model_flow_named_custom(config, _custom_provider_map[selected_provider])
+    elif selected_provider.startswith("custom:"):
+        provider_info = _named_custom_provider_map(load_config()).get(selected_provider)
+        if provider_info is None:
+            print(
+                "Warning: the selected saved custom provider is no longer available. "
+                "It may have been removed from config.yaml. No change."
+            )
+            return
+        _model_flow_named_custom(config, provider_info)
     elif selected_provider == "remove-custom":
         _remove_custom_provider(config)
     elif selected_provider == "anthropic":
@@ -1064,6 +1080,42 @@ def select_provider_and_model(args=None):
     elif selected_provider in ("gemini", "zai", "minimax", "minimax-cn", "kilocode", "opencode-zen", "opencode-go", "ai-gateway", "alibaba", "huggingface"):
         _model_flow_api_key_provider(config, selected_provider, current_model)
 
+    # ── Post-switch cleanup: clear stale OPENAI_BASE_URL ──────────────
+    # When the user switches to a named provider (anything except "custom"),
+    # a leftover OPENAI_BASE_URL in ~/.hermes/.env can poison auxiliary
+    # clients that use provider:auto. Clear it proactively.  (#5161)
+    if selected_provider not in ("custom", "cancel", "remove-custom") \
+            and not selected_provider.startswith("custom:"):
+        _clear_stale_openai_base_url()
+
+
+def _clear_stale_openai_base_url():
+    """Remove OPENAI_BASE_URL from ~/.hermes/.env if the active provider is not 'custom'.
+
+    After a provider switch, a leftover OPENAI_BASE_URL causes auxiliary
+    clients (compression, vision, delegation) with provider:auto to route
+    requests to the old custom endpoint instead of the newly selected
+    provider.  See issue #5161.
+    """
+    from hermes_cli.config import get_env_value, save_env_value, load_config
+
+    cfg = load_config()
+    model_cfg = cfg.get("model", {})
+    if isinstance(model_cfg, dict):
+        provider = (model_cfg.get("provider") or "").strip().lower()
+    else:
+        provider = ""
+
+    if provider == "custom" or not provider:
+        return  # custom provider legitimately uses OPENAI_BASE_URL
+
+    stale_url = get_env_value("OPENAI_BASE_URL")
+    if stale_url:
+        save_env_value("OPENAI_BASE_URL", "")
+        print(f"Cleared stale OPENAI_BASE_URL from .env (was: {stale_url[:40]}...)"
+              if len(stale_url) > 40
+              else f"Cleared stale OPENAI_BASE_URL from .env (was: {stale_url})")
+
 
 def _prompt_provider_choice(choices, *, default=0):
     """Show provider selection menu with curses arrow-key navigation.
@@ -1127,10 +1179,10 @@ def _model_flow_openrouter(config, current_model=""):
         print()
 
     from hermes_cli.models import model_ids, get_pricing_for_provider
-    openrouter_models = model_ids()
+    openrouter_models = model_ids(force_refresh=True)
 
     # Fetch live pricing (non-blocking — returns empty dict on failure)
-    pricing = get_pricing_for_provider("openrouter")
+    pricing = get_pricing_for_provider("openrouter", force_refresh=True)
 
     selected = _prompt_model_selection(openrouter_models, current_model=current_model, pricing=pricing)
     if selected:
@@ -1474,7 +1526,11 @@ def _model_flow_custom(config):
             f"Hermes will still save it."
         )
         if probe.get("suggested_base_url"):
-            print(f"  If this server expects /v1, try base URL: {probe['suggested_base_url']}")
+            suggested = probe["suggested_base_url"]
+            if suggested.endswith("/v1"):
+                print(f"  If this server expects /v1 in the path, try base URL: {suggested}")
+            else:
+                print(f"  If /v1 should not be in the base URL, try: {suggested}")
 
     # Select model — use probe results when available, fall back to manual input
     model_name = ""
@@ -1653,8 +1709,10 @@ def _remove_custom_provider(config):
             title="Select provider to remove:",
         )
         idx = menu.show()
+        from hermes_cli.curses_ui import flush_stdin
+        flush_stdin()
         print()
-    except (ImportError, NotImplementedError):
+    except (ImportError, NotImplementedError, OSError, subprocess.SubprocessError):
         for i, c in enumerate(choices, 1):
             print(f"  {i}. {c}")
         print()
@@ -1678,8 +1736,9 @@ def _remove_custom_provider(config):
 def _model_flow_named_custom(config, provider_info):
     """Handle a named custom provider from config.yaml custom_providers list.
 
-    If the entry has a saved model name, activates it immediately.
-    Otherwise probes the endpoint's /models API to let the user pick one.
+    Always probes the endpoint's /models API to let the user pick a model.
+    If a model was previously saved, it is pre-selected in the menu.
+    Falls back to the saved model if probing fails.
     """
     from hermes_cli.auth import _save_model_choice, deactivate_provider
     from hermes_cli.config import load_config, save_config
@@ -1690,54 +1749,46 @@ def _model_flow_named_custom(config, provider_info):
     api_key = provider_info.get("api_key", "")
     saved_model = provider_info.get("model", "")
 
-    # If a model is saved, just activate immediately — no probing needed
-    if saved_model:
-        _save_model_choice(saved_model)
-
-        cfg = load_config()
-        model = cfg.get("model")
-        if not isinstance(model, dict):
-            model = {"default": model} if model else {}
-            cfg["model"] = model
-        model["provider"] = "custom"
-        model["base_url"] = base_url
-        if api_key:
-            model["api_key"] = api_key
-        save_config(cfg)
-        deactivate_provider()
-
-        print(f"✅ Switched to: {saved_model}")
-        print(f"   Provider: {name} ({base_url})")
-        return
-
-    # No saved model — probe endpoint and let user pick
     print(f"  Provider: {name}")
     print(f"  URL:      {base_url}")
+    if saved_model:
+        print(f"  Current:  {saved_model}")
     print()
-    print("No model saved for this provider. Fetching available models...")
+
+    print("Fetching available models...")
     models = fetch_api_models(api_key, base_url, timeout=8.0)
 
     if models:
+        default_idx = 0
+        if saved_model and saved_model in models:
+            default_idx = models.index(saved_model)
+
         print(f"Found {len(models)} model(s):\n")
         try:
             from simple_term_menu import TerminalMenu
-            menu_items = [f"  {m}" for m in models] + ["  Cancel"]
+            menu_items = [
+                f"  {m} (current)" if m == saved_model else f"  {m}"
+                for m in models
+            ] + ["  Cancel"]
             menu = TerminalMenu(
-                menu_items, cursor_index=0,
+                menu_items, cursor_index=default_idx,
                 menu_cursor="-> ", menu_cursor_style=("fg_green", "bold"),
                 menu_highlight_style=("fg_green",),
                 cycle_cursor=True, clear_screen=False,
                 title=f"Select model from {name}:",
             )
             idx = menu.show()
+            from hermes_cli.curses_ui import flush_stdin
+            flush_stdin()
             print()
             if idx is None or idx >= len(models):
                 print("Cancelled.")
                 return
             model_name = models[idx]
-        except (ImportError, NotImplementedError):
+        except (ImportError, NotImplementedError, OSError, subprocess.SubprocessError):
             for i, m in enumerate(models, 1):
-                print(f"  {i}. {m}")
+                suffix = " (current)" if m == saved_model else ""
+                print(f"  {i}. {m}{suffix}")
             print(f"  {len(models) + 1}. Cancel")
             print()
             try:
@@ -1753,6 +1804,13 @@ def _model_flow_named_custom(config, provider_info):
             except (ValueError, KeyboardInterrupt, EOFError):
                 print("\nCancelled.")
                 return
+    elif saved_model:
+        print("Could not fetch models from endpoint.")
+        try:
+            model_name = input(f"Model name [{saved_model}]: ").strip() or saved_model
+        except (KeyboardInterrupt, EOFError):
+            print("\nCancelled.")
+            return
     else:
         print("Could not fetch models from endpoint. Enter model name manually.")
         try:
@@ -1807,7 +1865,10 @@ def _set_reasoning_effort(config, effort: str) -> None:
 
 def _prompt_reasoning_effort_selection(efforts, current_effort=""):
     """Prompt for a reasoning effort. Returns effort, 'none', or None to keep current."""
-    ordered = list(dict.fromkeys(str(effort).strip().lower() for effort in efforts if str(effort).strip()))
+    deduped = list(dict.fromkeys(str(effort).strip().lower() for effort in efforts if str(effort).strip()))
+    canonical_order = ("minimal", "low", "medium", "high", "xhigh")
+    ordered = [effort for effort in canonical_order if effort in deduped]
+    ordered.extend(effort for effort in deduped if effort not in canonical_order)
     if not ordered:
         return None
 
@@ -1845,6 +1906,8 @@ def _prompt_reasoning_effort_selection(efforts, current_effort=""):
             title="Select reasoning effort:",
         )
         idx = menu.show()
+        from hermes_cli.curses_ui import flush_stdin
+        flush_stdin()
         if idx is None:
             return None
         print()
@@ -1853,7 +1916,7 @@ def _prompt_reasoning_effort_selection(efforts, current_effort=""):
         if idx == len(ordered):
             return "none"
         return None
-    except (ImportError, NotImplementedError):
+    except (ImportError, NotImplementedError, OSError, subprocess.SubprocessError):
         pass
 
     print("Select reasoning effort:")
@@ -2639,6 +2702,12 @@ def cmd_doctor(args):
     run_doctor(args)
 
 
+def cmd_dump(args):
+    """Dump setup summary for support/debugging."""
+    from hermes_cli.dump import run_dump
+    run_dump(args)
+
+
 def cmd_config(args):
     """Configuration management."""
     from hermes_cli.config import config_command
@@ -3008,33 +3077,19 @@ def _restore_stashed_changes(
         print("\nYour stashed changes are preserved — nothing is lost.")
         print(f"  Stash ref: {stash_ref}")
 
-        # Ask before resetting (if interactive)
-        do_reset = True
-        if prompt_user:
-            print("\nReset working tree to clean state so Hermes can run?")
-            print("  (You can re-apply your changes later with: git stash apply)")
-            print("[Y/n] ", end="", flush=True)
-            response = input().strip().lower()
-            if response not in ("", "y", "yes"):
-                do_reset = False
-
-        if do_reset:
-            subprocess.run(
-                git_cmd + ["reset", "--hard", "HEAD"],
-                cwd=cwd,
-                capture_output=True,
-            )
-            print("Working tree reset to clean state.")
-        else:
-            print("Working tree left as-is (may have conflict markers).")
-            print("Resolve conflicts manually, then run: git stash drop")
-
-        print(f"Restore your changes with: git stash apply {stash_ref}")
-        # In non-interactive mode (gateway /update), don't abort — the code
-        # update itself succeeded, only the stash restore had conflicts.
-        # Aborting would report the entire update as failed.
-        if prompt_user:
-            sys.exit(1)
+        # Always reset to clean state — leaving conflict markers in source
+        # files makes hermes completely unrunnable (SyntaxError on import).
+        # The user's changes are safe in the stash for manual recovery.
+        subprocess.run(
+            git_cmd + ["reset", "--hard", "HEAD"],
+            cwd=cwd,
+            capture_output=True,
+        )
+        print("Working tree reset to clean state.")
+        print(f"Restore your changes later with: git stash apply {stash_ref}")
+        # Don't sys.exit — the code update itself succeeded, only the stash
+        # restore had conflicts.  Let cmd_update continue with pip install,
+        # skill sync, and gateway restart.
         return False
 
     stash_selector = _resolve_stash_selector(git_cmd, cwd, stash_ref)
@@ -3295,10 +3350,11 @@ def _invalidate_update_cache():
     ``hermes update``, every profile is now current.
     """
     homes = []
-    # Default profile home
-    default_home = Path.home() / ".hermes"
+    # Default profile home (Docker-aware — uses /opt/data in Docker)
+    from hermes_constants import get_default_hermes_root
+    default_home = get_default_hermes_root()
     homes.append(default_home)
-    # Named profiles under ~/.hermes/profiles/
+    # Named profiles under <root>/profiles/
     profiles_root = default_home / "profiles"
     if profiles_root.is_dir():
         for entry in profiles_root.iterdir():
@@ -3750,7 +3806,7 @@ def cmd_update(args):
         # running gateway needs restarting to pick up the new code.
         try:
             from hermes_cli.gateway import (
-                is_macos, is_linux, _ensure_user_systemd_env,
+                is_macos, supports_systemd_services, _ensure_user_systemd_env,
                 find_gateway_pids,
                 _get_service_pids,
             )
@@ -3761,7 +3817,7 @@ def cmd_update(args):
 
             # --- Systemd services (Linux) ---
             # Discover all hermes-gateway* units (default + profiles)
-            if is_linux():
+            if supports_systemd_services():
                 try:
                     _ensure_user_systemd_env()
                 except Exception:
@@ -4035,7 +4091,10 @@ def cmd_profile(args):
             print(f"  {name} chat               Start chatting")
             print(f"  {name} gateway start      Start the messaging gateway")
             if clone or clone_all:
-                profile_dir_display = f"~/.hermes/profiles/{name}"
+                try:
+                    profile_dir_display = "~/" + str(profile_dir.relative_to(Path.home()))
+                except ValueError:
+                    profile_dir_display = str(profile_dir)
                 print(f"\n  Edit {profile_dir_display}/.env for different API keys")
                 print(f"  Edit {profile_dir_display}/SOUL.md for different personality")
             print()
@@ -4278,6 +4337,10 @@ For more help on a command:
         "-q", "--query",
         help="Single query (non-interactive mode)"
     )
+    chat_parser.add_argument(
+        "--image",
+        help="Optional local image path to attach to a single query"
+    )
     chat_parser.add_argument(
         "-m", "--model",
         help="Model to use (e.g., anthropic/claude-sonnet-4)"
@@ -4420,7 +4483,7 @@ For more help on a command:
     gateway_subparsers = gateway_parser.add_subparsers(dest="gateway_command")
     
     # gateway run (default)
-    gateway_run = gateway_subparsers.add_parser("run", help="Run gateway in foreground")
+    gateway_run = gateway_subparsers.add_parser("run", help="Run gateway in foreground (recommended for WSL, Docker, Termux)")
     gateway_run.add_argument("-v", "--verbose", action="count", default=0,
                              help="Increase stderr log verbosity (-v=INFO, -vv=DEBUG)")
     gateway_run.add_argument("-q", "--quiet", action="store_true",
@@ -4429,7 +4492,7 @@ For more help on a command:
                              help="Replace any existing gateway instance (useful for systemd)")
     
     # gateway start
-    gateway_start = gateway_subparsers.add_parser("start", help="Start gateway service")
+    gateway_start = gateway_subparsers.add_parser("start", help="Start the installed systemd/launchd background service")
     gateway_start.add_argument("--system", action="store_true", help="Target the Linux system-level gateway service")
     
     # gateway stop
@@ -4447,7 +4510,7 @@ For more help on a command:
     gateway_status.add_argument("--system", action="store_true", help="Target the Linux system-level gateway service")
     
     # gateway install
-    gateway_install = gateway_subparsers.add_parser("install", help="Install gateway as service")
+    gateway_install = gateway_subparsers.add_parser("install", help="Install gateway as a systemd/launchd background service")
     gateway_install.add_argument("--force", action="store_true", help="Force reinstall")
     gateway_install.add_argument("--system", action="store_true", help="Install as a Linux system-level service (starts at boot)")
     gateway_install.add_argument("--run-as-user", dest="run_as_user", help="User account the Linux system service should run as")
@@ -4468,12 +4531,12 @@ For more help on a command:
         "setup",
         help="Interactive setup wizard",
         description="Configure Hermes Agent with an interactive wizard. "
-                    "Run a specific section: hermes setup model|terminal|gateway|tools|agent"
+                    "Run a specific section: hermes setup model|tts|terminal|gateway|tools|agent"
     )
     setup_parser.add_argument(
         "section",
         nargs="?",
-        choices=["model", "terminal", "gateway", "tools", "agent"],
+        choices=["model", "tts", "terminal", "gateway", "tools", "agent"],
         default=None,
         help="Run a specific setup section instead of the full wizard"
     )
@@ -4720,6 +4783,22 @@ For more help on a command:
         help="Attempt to fix issues automatically"
     )
     doctor_parser.set_defaults(func=cmd_doctor)
+
+    # =========================================================================
+    # dump command
+    # =========================================================================
+    dump_parser = subparsers.add_parser(
+        "dump",
+        help="Dump setup summary for support/debugging",
+        description="Output a compact, plain-text summary of your Hermes setup "
+                    "that can be copy-pasted into Discord/GitHub for support context"
+    )
+    dump_parser.add_argument(
+        "--show-keys",
+        action="store_true",
+        help="Show redacted API key prefixes (first/last 4 chars) instead of just set/not set"
+    )
+    dump_parser.set_defaults(func=cmd_dump)
     
     # =========================================================================
     # config command

hermes_cli/model_normalize.py

@@ -76,17 +76,22 @@ _STRIP_VENDOR_ONLY_PROVIDERS: frozenset[str] = frozenset({
     "copilot-acp",
 })
 
-# Providers whose own naming is authoritative -- pass through unchanged.
-_PASSTHROUGH_PROVIDERS: frozenset[str] = frozenset({
+# Providers whose native naming is authoritative -- pass through unchanged.
+_AUTHORITATIVE_NATIVE_PROVIDERS: frozenset[str] = frozenset({
     "gemini",
+    "huggingface",
+    "openai-codex",
+})
+
+# Direct providers that accept bare native names but should repair a matching
+# provider/ prefix when users copy the aggregator form into config.yaml.
+_MATCHING_PREFIX_STRIP_PROVIDERS: frozenset[str] = frozenset({
     "zai",
     "kimi-coding",
     "minimax",
     "minimax-cn",
     "alibaba",
     "qwen-oauth",
-    "huggingface",
-    "openai-codex",
     "custom",
 })
 
@@ -168,6 +173,40 @@ def _dots_to_hyphens(model_name: str) -> str:
     return model_name.replace(".", "-")
 
 
+def _normalize_provider_alias(provider_name: str) -> str:
+    """Resolve provider aliases to Hermes' canonical ids."""
+    raw = (provider_name or "").strip().lower()
+    if not raw:
+        return raw
+    try:
+        from hermes_cli.models import normalize_provider
+
+        return normalize_provider(raw)
+    except Exception:
+        return raw
+
+
+def _strip_matching_provider_prefix(model_name: str, target_provider: str) -> str:
+    """Strip ``provider/`` only when the prefix matches the target provider.
+
+    This prevents arbitrary slash-bearing model IDs from being mangled on
+    native providers while still repairing manual config values like
+    ``zai/glm-5.1`` for the ``zai`` provider.
+    """
+    if "/" not in model_name:
+        return model_name
+
+    prefix, remainder = model_name.split("/", 1)
+    if not prefix.strip() or not remainder.strip():
+        return model_name
+
+    normalized_prefix = _normalize_provider_alias(prefix)
+    normalized_target = _normalize_provider_alias(target_provider)
+    if normalized_prefix and normalized_prefix == normalized_target:
+        return remainder.strip()
+    return model_name
+
+
 def detect_vendor(model_name: str) -> Optional[str]:
     """Detect the vendor slug from a bare model name.
 
@@ -305,24 +344,37 @@ def normalize_model_for_provider(model_input: str, target_provider: str) -> str:
     if not name:
         return name
 
-    provider = (target_provider or "").strip().lower()
+    provider = _normalize_provider_alias(target_provider)
 
     # --- Aggregators: need vendor/model format ---
     if provider in _AGGREGATOR_PROVIDERS:
         return _prepend_vendor(name)
 
-    # --- Anthropic / OpenCode: strip vendor, dots -> hyphens ---
+    # --- Anthropic / OpenCode: strip matching provider prefix, dots -> hyphens ---
     if provider in _DOT_TO_HYPHEN_PROVIDERS:
-        bare = _strip_vendor_prefix(name)
+        bare = _strip_matching_provider_prefix(name, provider)
+        if "/" in bare:
+            return bare
         return _dots_to_hyphens(bare)
 
-    # --- Copilot: strip vendor, keep dots ---
+    # --- Copilot: strip matching provider prefix, keep dots ---
     if provider in _STRIP_VENDOR_ONLY_PROVIDERS:
-        return _strip_vendor_prefix(name)
+        return _strip_matching_provider_prefix(name, provider)
 
     # --- DeepSeek: map to one of two canonical names ---
     if provider == "deepseek":
-        return _normalize_for_deepseek(name)
+        bare = _strip_matching_provider_prefix(name, provider)
+        if "/" in bare:
+            return bare
+        return _normalize_for_deepseek(bare)
+
+    # --- Direct providers: repair matching provider prefixes only ---
+    if provider in _MATCHING_PREFIX_STRIP_PROVIDERS:
+        return _strip_matching_provider_prefix(name, provider)
+
+    # --- Authoritative native providers: preserve user-facing slugs as-is ---
+    if provider in _AUTHORITATIVE_NATIVE_PROVIDERS:
+        return name
 
     # --- Custom & all others: pass through as-is ---
     return name
@@ -332,31 +384,3 @@ def normalize_model_for_provider(model_input: str, target_provider: str) -> str:
 # Batch / convenience helpers
 # ---------------------------------------------------------------------------
 
-def model_display_name(model_id: str) -> str:
-    """Return a short, human-readable display name for a model id.
-
-    Strips the vendor prefix (if any) for a cleaner display in menus
-    and status bars, while preserving dots for readability.
-
-    Examples::
-
-        >>> model_display_name("anthropic/claude-sonnet-4.6")
-        'claude-sonnet-4.6'
-        >>> model_display_name("claude-sonnet-4-6")
-        'claude-sonnet-4-6'
-    """
-    return _strip_vendor_prefix((model_id or "").strip())
-
-
-def is_aggregator_provider(provider: str) -> bool:
-    """Check if a provider is an aggregator that needs vendor/model format."""
-    return (provider or "").strip().lower() in _AGGREGATOR_PROVIDERS
-
-
-def vendor_for_model(model_name: str) -> str:
-    """Return the vendor slug for a model, or ``""`` if unknown.
-
-    Convenience wrapper around :func:`detect_vendor` that never returns
-    ``None``.
-    """
-    return detect_vendor(model_name) or ""

hermes_cli/model_switch.py

@@ -25,6 +25,7 @@ from dataclasses import dataclass
 from typing import List, NamedTuple, Optional
 
 from hermes_cli.providers import (
+    custom_provider_slug,
     determine_api_mode,
     get_label,
     is_aggregator,
@@ -336,6 +337,7 @@ def resolve_alias(
 def get_authenticated_provider_slugs(
     current_provider: str = "",
     user_providers: dict = None,
+    custom_providers: list | None = None,
 ) -> list[str]:
     """Return slugs of providers that have credentials.
 
@@ -346,6 +348,7 @@ def get_authenticated_provider_slugs(
         providers = list_authenticated_providers(
             current_provider=current_provider,
             user_providers=user_providers,
+            custom_providers=custom_providers,
             max_models=0,
         )
         return [p["slug"] for p in providers]
@@ -383,6 +386,7 @@ def switch_model(
     is_global: bool = False,
     explicit_provider: str = "",
     user_providers: dict = None,
+    custom_providers: list | None = None,
 ) -> ModelSwitchResult:
     """Core model-switching pipeline shared between CLI and gateway.
 
@@ -416,6 +420,7 @@ def switch_model(
         is_global: Whether to persist the switch.
         explicit_provider: From --provider flag (empty = no explicit provider).
         user_providers: The ``providers:`` dict from config.yaml (for user endpoints).
+        custom_providers: The ``custom_providers:`` list from config.yaml.
 
     Returns:
         ModelSwitchResult with all information the caller needs.
@@ -436,7 +441,11 @@ def switch_model(
     # =================================================================
     if explicit_provider:
         # Resolve the provider
-        pdef = resolve_provider_full(explicit_provider, user_providers)
+        pdef = resolve_provider_full(
+            explicit_provider,
+            user_providers,
+            custom_providers,
+        )
         if pdef is None:
             _switch_err = (
                 f"Unknown provider '{explicit_provider}'. "
@@ -516,6 +525,7 @@ def switch_model(
                 authed = get_authenticated_provider_slugs(
                     current_provider=current_provider,
                     user_providers=user_providers,
+                    custom_providers=custom_providers,
                 )
                 fallback_result = _resolve_alias_fallback(raw_input, authed)
                 if fallback_result is not None:
@@ -537,8 +547,11 @@ def switch_model(
                     )
             else:
                 # --- Step c: On aggregator, convert vendor:model to vendor/model ---
+                # Only convert when there's no slash — a slash means the name
+                # is already in vendor/model format and the colon is a variant
+                # tag (:free, :extended, :fast) that must be preserved.
                 colon_pos = raw_input.find(":")
-                if colon_pos > 0 and is_aggregator(current_provider):
+                if colon_pos > 0 and "/" not in raw_input and is_aggregator(current_provider):
                     left = raw_input[:colon_pos].strip().lower()
                     right = raw_input[colon_pos + 1:].strip()
                     if left and right:
@@ -587,6 +600,14 @@ def switch_model(
 
     provider_changed = target_provider != current_provider
     provider_label = get_label(target_provider)
+    if target_provider.startswith("custom:"):
+        custom_pdef = resolve_provider_full(
+            target_provider,
+            user_providers,
+            custom_providers,
+        )
+        if custom_pdef is not None:
+            provider_label = custom_pdef.name
 
     # --- Resolve credentials ---
     api_key = current_api_key
@@ -705,6 +726,7 @@ def switch_model(
 def list_authenticated_providers(
     current_provider: str = "",
     user_providers: dict = None,
+    custom_providers: list | None = None,
     max_models: int = 8,
 ) -> List[dict]:
     """Detect which providers have credentials and list their curated models.
@@ -730,6 +752,7 @@ def list_authenticated_providers(
         fetch_models_dev,
         get_provider_info as _mdev_pinfo,
     )
+    from hermes_cli.auth import PROVIDER_REGISTRY
     from hermes_cli.models import OPENROUTER_MODELS, _PROVIDER_MODELS
 
     results: List[dict] = []
@@ -750,9 +773,16 @@ def list_authenticated_providers(
         if not isinstance(pdata, dict):
             continue
 
-        env_vars = pdata.get("env", [])
-        if not isinstance(env_vars, list):
-            continue
+        # Prefer auth.py PROVIDER_REGISTRY for env var names — it's our
+        # source of truth.  models.dev can have wrong mappings (e.g.
+        # minimax-cn → MINIMAX_API_KEY instead of MINIMAX_CN_API_KEY).
+        pconfig = PROVIDER_REGISTRY.get(hermes_id)
+        if pconfig and pconfig.api_key_env_vars:
+            env_vars = list(pconfig.api_key_env_vars)
+        else:
+            env_vars = pdata.get("env", [])
+            if not isinstance(env_vars, list):
+                continue
 
         # Check if any env var is set
         has_creds = any(os.environ.get(ev) for ev in env_vars)
@@ -779,42 +809,69 @@ def list_authenticated_providers(
         })
         seen_slugs.add(slug)
 
-    # --- 2. Check Hermes-only providers (nous, openai-codex, copilot) ---
+    # --- 2. Check Hermes-only providers (nous, openai-codex, copilot, opencode-go) ---
     from hermes_cli.providers import HERMES_OVERLAYS
+    from hermes_cli.auth import PROVIDER_REGISTRY as _auth_registry
+
+    # Build reverse mapping: models.dev ID → Hermes provider ID.
+    # HERMES_OVERLAYS keys may be models.dev IDs (e.g. "github-copilot")
+    # while _PROVIDER_MODELS and config.yaml use Hermes IDs ("copilot").
+    _mdev_to_hermes = {v: k for k, v in PROVIDER_TO_MODELS_DEV.items()}
+
     for pid, overlay in HERMES_OVERLAYS.items():
         if pid in seen_slugs:
             continue
+
+        # Resolve Hermes slug — e.g. "github-copilot" → "copilot"
+        hermes_slug = _mdev_to_hermes.get(pid, pid)
+        if hermes_slug in seen_slugs:
+            continue
+
         # Check if credentials exist
         has_creds = False
         if overlay.extra_env_vars:
             has_creds = any(os.environ.get(ev) for ev in overlay.extra_env_vars)
-        if overlay.auth_type in ("oauth_device_code", "oauth_external", "external_process"):
+        # Also check api_key_env_vars from PROVIDER_REGISTRY for api_key auth_type
+        if not has_creds and overlay.auth_type == "api_key":
+            for _key in (pid, hermes_slug):
+                pcfg = _auth_registry.get(_key)
+                if pcfg and pcfg.api_key_env_vars:
+                    if any(os.environ.get(ev) for ev in pcfg.api_key_env_vars):
+                        has_creds = True
+                        break
+        if not has_creds and overlay.auth_type in ("oauth_device_code", "oauth_external", "external_process"):
             # These use auth stores, not env vars — check for auth.json entries
             try:
                 from hermes_cli.auth import _load_auth_store
                 store = _load_auth_store()
-                if store and (pid in store.get("providers", {}) or pid in store.get("credential_pool", {})):
+                providers_store = store.get("providers", {})
+                pool_store = store.get("credential_pool", {})
+                if store and (
+                    pid in providers_store or hermes_slug in providers_store
+                    or pid in pool_store or hermes_slug in pool_store
+                ):
                     has_creds = True
             except Exception as exc:
                 logger.debug("Auth store check failed for %s: %s", pid, exc)
         if not has_creds:
             continue
 
-        # Use curated list
-        model_ids = curated.get(pid, [])
+        # Use curated list — look up by Hermes slug, fall back to overlay key
+        model_ids = curated.get(hermes_slug, []) or curated.get(pid, [])
         total = len(model_ids)
         top = model_ids[:max_models]
 
         results.append({
-            "slug": pid,
-            "name": get_label(pid),
-            "is_current": pid == current_provider,
+            "slug": hermes_slug,
+            "name": get_label(hermes_slug),
+            "is_current": hermes_slug == current_provider or pid == current_provider,
             "is_user_defined": False,
             "models": top,
             "total_models": total,
             "source": "hermes",
         })
         seen_slugs.add(pid)
+        seen_slugs.add(hermes_slug)
 
     # --- 3. User-defined endpoints from config ---
     if user_providers and isinstance(user_providers, dict):
@@ -842,80 +899,46 @@ def list_authenticated_providers(
                 "api_url": api_url,
             })
 
+    # --- 4. Saved custom providers from config ---
+    if custom_providers and isinstance(custom_providers, list):
+        for entry in custom_providers:
+            if not isinstance(entry, dict):
+                continue
+
+            display_name = (entry.get("name") or "").strip()
+            api_url = (
+                entry.get("base_url", "")
+                or entry.get("url", "")
+                or entry.get("api", "")
+                or ""
+            ).strip()
+            if not display_name or not api_url:
+                continue
+
+            slug = custom_provider_slug(display_name)
+            if slug in seen_slugs:
+                continue
+
+            models_list = []
+            default_model = (entry.get("model") or "").strip()
+            if default_model:
+                models_list.append(default_model)
+
+            results.append({
+                "slug": slug,
+                "name": display_name,
+                "is_current": slug == current_provider,
+                "is_user_defined": True,
+                "models": models_list,
+                "total_models": len(models_list),
+                "source": "user-config",
+                "api_url": api_url,
+            })
+            seen_slugs.add(slug)
+
     # Sort: current provider first, then by model count descending
     results.sort(key=lambda r: (not r["is_current"], -r["total_models"]))
 
     return results
 
 
-# ---------------------------------------------------------------------------
-# Fuzzy suggestions
-# ---------------------------------------------------------------------------
-
-def suggest_models(raw_input: str, limit: int = 3) -> List[str]:
-    """Return fuzzy model suggestions for a (possibly misspelled) input."""
-    query = raw_input.strip()
-    if not query:
-        return []
-
-    results = search_models_dev(query, limit=limit)
-    suggestions: list[str] = []
-    for r in results:
-        mid = r.get("model_id", "")
-        if mid:
-            suggestions.append(mid)
-
-    return suggestions[:limit]
-
-
-# ---------------------------------------------------------------------------
-# Custom provider switch
-# ---------------------------------------------------------------------------
-
-def switch_to_custom_provider() -> CustomAutoResult:
-    """Handle bare '/model --provider custom' — resolve endpoint and auto-detect model."""
-    from hermes_cli.runtime_provider import (
-        resolve_runtime_provider,
-        _auto_detect_local_model,
-    )
-
-    try:
-        runtime = resolve_runtime_provider(requested="custom")
-    except Exception as e:
-        return CustomAutoResult(
-            success=False,
-            error_message=f"Could not resolve custom endpoint: {e}",
-        )
-
-    cust_base = runtime.get("base_url", "")
-    cust_key = runtime.get("api_key", "")
-
-    if not cust_base or "openrouter.ai" in cust_base:
-        return CustomAutoResult(
-            success=False,
-            error_message=(
-                "No custom endpoint configured. "
-                "Set model.base_url in config.yaml, or set OPENAI_BASE_URL "
-                "in .env, or run: hermes setup -> Custom OpenAI-compatible endpoint"
-            ),
-        )
-
-    detected_model = _auto_detect_local_model(cust_base)
-    if not detected_model:
-        return CustomAutoResult(
-            success=False,
-            base_url=cust_base,
-            api_key=cust_key,
-            error_message=(
-                f"Custom endpoint at {cust_base} is reachable but no single "
-                f"model was auto-detected. Specify the model explicitly: "
-                f"/model <model-name> --provider custom"
-            ),
-        )
-
-    return CustomAutoResult(
-        success=True,
-        model=detected_model,
-        base_url=cust_base,
-        api_key=cust_key,
-    )

hermes_cli/models.py

@@ -20,22 +20,20 @@ COPILOT_EDITOR_VERSION = "vscode/1.104.1"
 COPILOT_REASONING_EFFORTS_GPT5 = ["minimal", "low", "medium", "high"]
 COPILOT_REASONING_EFFORTS_O_SERIES = ["low", "medium", "high"]
 
-# Backward-compatible aliases for the earlier GitHub Models-backed Copilot work.
-GITHUB_MODELS_BASE_URL = COPILOT_BASE_URL
-GITHUB_MODELS_CATALOG_URL = COPILOT_MODELS_URL
 
+# Fallback OpenRouter snapshot used when the live catalog is unavailable.
 # (model_id, display description shown in menus)
 OPENROUTER_MODELS: list[tuple[str, str]] = [
     ("anthropic/claude-opus-4.6",       "recommended"),
     ("anthropic/claude-sonnet-4.6",     ""),
-    ("qwen/qwen3.6-plus:free", "free"),
+    ("qwen/qwen3.6-plus",               ""),
     ("anthropic/claude-sonnet-4.5",     ""),
     ("anthropic/claude-haiku-4.5",      ""),
     ("openai/gpt-5.4",                  ""),
     ("openai/gpt-5.4-mini",             ""),
     ("xiaomi/mimo-v2-pro",               ""),
     ("openai/gpt-5.3-codex",            ""),
-    ("google/gemini-3-pro-preview",     ""),
+    ("google/gemini-3-pro-image-preview", ""),
     ("google/gemini-3-flash-preview",   ""),
     ("google/gemini-3.1-pro-preview",     ""),
     ("google/gemini-3.1-flash-lite-preview",   ""),
@@ -47,7 +45,7 @@ OPENROUTER_MODELS: list[tuple[str, str]] = [
     ("z-ai/glm-5.1",                    ""),
     ("z-ai/glm-5-turbo",                ""),
     ("moonshotai/kimi-k2.5",            ""),
-    ("x-ai/grok-4.20-beta",             ""),
+    ("x-ai/grok-4.20",                  ""),
     ("nvidia/nemotron-3-super-120b-a12b",      ""),
     ("nvidia/nemotron-3-super-120b-a12b:free", "free"),
     ("arcee-ai/trinity-large-preview:free", "free"),
@@ -56,6 +54,8 @@ OPENROUTER_MODELS: list[tuple[str, str]] = [
     ("openai/gpt-5.4-nano",             ""),
 ]
 
+_openrouter_catalog_cache: list[tuple[str, str]] | None = None
+
 _PROVIDER_MODELS: dict[str, list[str]] = {
     "nous": [
         "anthropic/claude-opus-4.6",
@@ -87,6 +87,8 @@ _PROVIDER_MODELS: dict[str, list[str]] = {
         "openai/gpt-5.4-nano",
     ],
     "openai-codex": [
+        "gpt-5.4",
+        "gpt-5.4-mini",
         "gpt-5.3-codex",
         "gpt-5.2-codex",
         "gpt-5.1-codex-mini",
@@ -129,6 +131,19 @@ _PROVIDER_MODELS: dict[str, list[str]] = {
         "glm-4.5",
         "glm-4.5-flash",
     ],
+    "xai": [
+        "grok-4.20-0309-reasoning",
+        "grok-4.20-0309-non-reasoning",
+        "grok-4.20-multi-agent-0309",
+        "grok-4-1-fast-reasoning",
+        "grok-4-1-fast-non-reasoning",
+        "grok-4-fast-reasoning",
+        "grok-4-fast-non-reasoning",
+        "grok-4-0709",
+        "grok-code-fast-1",
+        "grok-3",
+        "grok-3-mini",
+    ],
     "kimi-coding": [
         "kimi-for-coding",
         "kimi-k2.5",
@@ -144,22 +159,16 @@ _PROVIDER_MODELS: dict[str, list[str]] = {
         "kimi-k2-0905-preview",
     ],
     "minimax": [
-        "MiniMax-M1",
-        "MiniMax-M1-40k",
-        "MiniMax-M1-80k",
-        "MiniMax-M1-128k",
-        "MiniMax-M1-256k",
-        "MiniMax-M2.5",
         "MiniMax-M2.7",
+        "MiniMax-M2.5",
+        "MiniMax-M2.1",
+        "MiniMax-M2",
     ],
     "minimax-cn": [
-        "MiniMax-M1",
-        "MiniMax-M1-40k",
-        "MiniMax-M1-80k",
-        "MiniMax-M1-128k",
-        "MiniMax-M1-256k",
-        "MiniMax-M2.5",
         "MiniMax-M2.7",
+        "MiniMax-M2.5",
+        "MiniMax-M2.1",
+        "MiniMax-M2",
     ],
     "anthropic": [
         "claude-opus-4-6",
@@ -416,12 +425,6 @@ _FREE_TIER_CACHE_TTL: int = 180  # seconds (3 minutes)
 _free_tier_cache: tuple[bool, float] | None = None  # (result, timestamp)
 
 
-def clear_nous_free_tier_cache() -> None:
-    """Invalidate the cached free-tier result (e.g. after login/logout)."""
-    global _free_tier_cache
-    _free_tier_cache = None
-
-
 def check_nous_free_tier() -> bool:
     """Check if the current Nous Portal user is on a free (unpaid) tier.
 
@@ -530,19 +533,84 @@ _PROVIDER_ALIASES = {
 }
 
 
-def model_ids() -> list[str]:
+def _openrouter_model_is_free(pricing: Any) -> bool:
+    """Return True when both prompt and completion pricing are zero."""
+    if not isinstance(pricing, dict):
+        return False
+    try:
+        return float(pricing.get("prompt", "0")) == 0 and float(pricing.get("completion", "0")) == 0
+    except (TypeError, ValueError):
+        return False
+
+
+def fetch_openrouter_models(
+    timeout: float = 8.0,
+    *,
+    force_refresh: bool = False,
+) -> list[tuple[str, str]]:
+    """Return the curated OpenRouter picker list, refreshed from the live catalog when possible."""
+    global _openrouter_catalog_cache
+
+    if _openrouter_catalog_cache is not None and not force_refresh:
+        return list(_openrouter_catalog_cache)
+
+    fallback = list(OPENROUTER_MODELS)
+    preferred_ids = [mid for mid, _ in fallback]
+
+    try:
+        req = urllib.request.Request(
+            "https://openrouter.ai/api/v1/models",
+            headers={"Accept": "application/json"},
+        )
+        with urllib.request.urlopen(req, timeout=timeout) as resp:
+            payload = json.loads(resp.read().decode())
+    except Exception:
+        return list(_openrouter_catalog_cache or fallback)
+
+    live_items = payload.get("data", [])
+    if not isinstance(live_items, list):
+        return list(_openrouter_catalog_cache or fallback)
+
+    live_by_id: dict[str, dict[str, Any]] = {}
+    for item in live_items:
+        if not isinstance(item, dict):
+            continue
+        mid = str(item.get("id") or "").strip()
+        if not mid:
+            continue
+        live_by_id[mid] = item
+
+    curated: list[tuple[str, str]] = []
+    for preferred_id in preferred_ids:
+        live_item = live_by_id.get(preferred_id)
+        if live_item is None:
+            continue
+        desc = "free" if _openrouter_model_is_free(live_item.get("pricing")) else ""
+        curated.append((preferred_id, desc))
+
+    if not curated:
+        return list(_openrouter_catalog_cache or fallback)
+
+    first_id, _ = curated[0]
+    curated[0] = (first_id, "recommended")
+    _openrouter_catalog_cache = curated
+    return list(curated)
+
+
+def model_ids(*, force_refresh: bool = False) -> list[str]:
     """Return just the OpenRouter model-id strings."""
-    return [mid for mid, _ in OPENROUTER_MODELS]
+    return [mid for mid, _ in fetch_openrouter_models(force_refresh=force_refresh)]
 
 
-def menu_labels() -> list[str]:
+def menu_labels(*, force_refresh: bool = False) -> list[str]:
     """Return display labels like 'anthropic/claude-opus-4.6 (recommended)'."""
     labels = []
-    for mid, desc in OPENROUTER_MODELS:
+    for mid, desc in fetch_openrouter_models(force_refresh=force_refresh):
         labels.append(f"{mid} ({desc})" if desc else mid)
     return labels
 
 
+
 # ---------------------------------------------------------------------------
 # Pricing helpers — fetch live pricing from OpenRouter-compatible /v1/models
 # ---------------------------------------------------------------------------
@@ -575,31 +643,6 @@ def _format_price_per_mtok(per_token_str: str) -> str:
     return f"${per_m:.2f}"
 
 
-def format_pricing_label(pricing: dict[str, str] | None) -> str:
-    """Build a compact pricing label like 'in $3 · out $15 · cache $0.30/Mtok'.
-
-    Returns empty string when pricing is unavailable.
-    """
-    if not pricing:
-        return ""
-    prompt_price = pricing.get("prompt", "")
-    completion_price = pricing.get("completion", "")
-    if not prompt_price and not completion_price:
-        return ""
-    inp = _format_price_per_mtok(prompt_price)
-    out = _format_price_per_mtok(completion_price)
-    if inp == "free" and out == "free":
-        return "free"
-    cache_read = pricing.get("input_cache_read", "")
-    cache_str = _format_price_per_mtok(cache_read) if cache_read else ""
-    if inp == out and not cache_str:
-        return f"{inp}/Mtok"
-    parts = [f"in {inp}", f"out {out}"]
-    if cache_str and cache_str != "?" and cache_str != inp:
-        parts.append(f"cache {cache_str}")
-    return " · ".join(parts) + "/Mtok"
-
-
 def format_model_pricing_table(
     models: list[tuple[str, str]],
     pricing_map: dict[str, dict[str, str]],
@@ -727,13 +770,14 @@ def _resolve_nous_pricing_credentials() -> tuple[str, str]:
     return ("", "")
 
 
-def get_pricing_for_provider(provider: str) -> dict[str, dict[str, str]]:
+def get_pricing_for_provider(provider: str, *, force_refresh: bool = False) -> dict[str, dict[str, str]]:
     """Return live pricing for providers that support it (openrouter, nous)."""
     normalized = normalize_provider(provider)
     if normalized == "openrouter":
         return fetch_models_with_pricing(
             api_key=_resolve_openrouter_api_key(),
             base_url="https://openrouter.ai/api",
+            force_refresh=force_refresh,
         )
     if normalized == "nous":
         api_key, base_url = _resolve_nous_pricing_credentials()
@@ -746,6 +790,7 @@ def get_pricing_for_provider(provider: str) -> dict[str, dict[str, str]]:
             return fetch_models_with_pricing(
                 api_key=api_key,
                 base_url=stripped,
+                force_refresh=force_refresh,
             )
     return {}
 
@@ -854,7 +899,11 @@ def _get_custom_base_url() -> str:
     return ""
 
 
-def curated_models_for_provider(provider: Optional[str]) -> list[tuple[str, str]]:
+def curated_models_for_provider(
+    provider: Optional[str],
+    *,
+    force_refresh: bool = False,
+) -> list[tuple[str, str]]:
     """Return ``(model_id, description)`` tuples for a provider's model list.
 
     Tries to fetch the live model list from the provider's API first,
@@ -863,7 +912,7 @@ def curated_models_for_provider(provider: Optional[str]) -> list[tuple[str, str]
     """
     normalized = normalize_provider(provider)
     if normalized == "openrouter":
-        return list(OPENROUTER_MODELS)
+        return fetch_openrouter_models(force_refresh=force_refresh)
 
     # Try live API first (Codex, Nous, etc. all support /models)
     live = provider_model_ids(normalized)
@@ -982,12 +1031,12 @@ def _find_openrouter_slug(model_name: str) -> Optional[str]:
         return None
 
     # Exact match (already has provider/ prefix)
-    for mid, _ in OPENROUTER_MODELS:
+    for mid in model_ids():
         if name_lower == mid.lower():
             return mid
 
     # Try matching just the model part (after the /)
-    for mid, _ in OPENROUTER_MODELS:
+    for mid in model_ids():
         if "/" in mid:
             _, model_part = mid.split("/", 1)
             if name_lower == model_part.lower():
@@ -1017,6 +1066,79 @@ def provider_label(provider: Optional[str]) -> str:
     return _PROVIDER_LABELS.get(normalized, original or "OpenRouter")
 
 
+# Models that support OpenAI Priority Processing (service_tier="priority").
+# See https://openai.com/api-priority-processing/ for the canonical list.
+# Only the bare model slug is stored (no vendor prefix).
+_PRIORITY_PROCESSING_MODELS: frozenset[str] = frozenset({
+    "gpt-5.4",
+    "gpt-5.4-mini",
+    "gpt-5.2",
+    "gpt-5.1",
+    "gpt-5",
+    "gpt-5-mini",
+    "gpt-4.1",
+    "gpt-4.1-mini",
+    "gpt-4.1-nano",
+    "gpt-4o",
+    "gpt-4o-mini",
+    "o3",
+    "o4-mini",
+})
+
+# Models that support Anthropic Fast Mode (speed="fast").
+# See https://platform.claude.com/docs/en/build-with-claude/fast-mode
+# Currently only Claude Opus 4.6.  Both hyphen and dot variants are stored
+# to handle native Anthropic (claude-opus-4-6) and OpenRouter (claude-opus-4.6).
+_ANTHROPIC_FAST_MODE_MODELS: frozenset[str] = frozenset({
+    "claude-opus-4-6",
+    "claude-opus-4.6",
+})
+
+
+def _strip_vendor_prefix(model_id: str) -> str:
+    """Strip vendor/ prefix from a model ID (e.g. 'anthropic/claude-opus-4-6' -> 'claude-opus-4-6')."""
+    raw = str(model_id or "").strip().lower()
+    if "/" in raw:
+        raw = raw.split("/", 1)[1]
+    return raw
+
+
+def model_supports_fast_mode(model_id: Optional[str]) -> bool:
+    """Return whether Hermes should expose the /fast toggle for this model."""
+    raw = _strip_vendor_prefix(str(model_id or ""))
+    if raw in _PRIORITY_PROCESSING_MODELS:
+        return True
+    # Anthropic fast mode — strip date suffixes (e.g. claude-opus-4-6-20260401)
+    # and OpenRouter variant tags (:fast, :beta) for matching.
+    base = raw.split(":")[0]
+    return base in _ANTHROPIC_FAST_MODE_MODELS
+
+
+def _is_anthropic_fast_model(model_id: Optional[str]) -> bool:
+    """Return True if the model supports Anthropic's fast mode (speed='fast')."""
+    raw = _strip_vendor_prefix(str(model_id or ""))
+    base = raw.split(":")[0]
+    return base in _ANTHROPIC_FAST_MODE_MODELS
+
+
+def resolve_fast_mode_overrides(model_id: Optional[str]) -> dict[str, Any] | None:
+    """Return request_overrides for fast/priority mode, or None if unsupported.
+
+    Returns provider-appropriate overrides:
+    - OpenAI models: ``{"service_tier": "priority"}`` (Priority Processing)
+    - Anthropic models: ``{"speed": "fast"}`` (Anthropic Fast Mode beta)
+
+    The overrides are injected into the API request kwargs by
+    ``_build_api_kwargs`` in run_agent.py — each API path handles its own
+    keys (service_tier for OpenAI/Codex, speed for Anthropic Messages).
+    """
+    if not model_supports_fast_mode(model_id):
+        return None
+    if _is_anthropic_fast_model(model_id):
+        return {"speed": "fast"}
+    return {"service_tier": "priority"}
+
+
 def _resolve_copilot_catalog_api_key() -> str:
     """Best-effort GitHub token for fetching the Copilot model catalog."""
     try:
@@ -1028,7 +1150,7 @@ def _resolve_copilot_catalog_api_key() -> str:
         return ""
 
 
-def provider_model_ids(provider: Optional[str]) -> list[str]:
+def provider_model_ids(provider: Optional[str], *, force_refresh: bool = False) -> list[str]:
     """Return the best known model catalog for a provider.
 
     Tries live API endpoints for providers that support them (Codex, Nous),
@@ -1036,7 +1158,7 @@ def provider_model_ids(provider: Optional[str]) -> list[str]:
     """
     normalized = normalize_provider(provider)
     if normalized == "openrouter":
-        return model_ids()
+        return model_ids(force_refresh=force_refresh)
     if normalized == "openai-codex":
         from hermes_cli.codex_models import get_codex_model_ids
 
@@ -1532,7 +1654,7 @@ def probe_api_models(
 
     return {
         "models": None,
-        "probed_url": tried[-1] if tried else normalized.rstrip("/") + "/models",
+        "probed_url": tried[0] if tried else normalized.rstrip("/") + "/models",
         "resolved_base_url": normalized,
         "suggested_base_url": alternate_base if alternate_base != normalized else None,
         "used_fallback": False,

hermes_cli/nous_subscription.py

@@ -143,6 +143,7 @@ def _tts_label(current_provider: str) -> str:
         "openai": "OpenAI TTS",
         "elevenlabs": "ElevenLabs",
         "edge": "Edge TTS",
+        "mistral": "Mistral Voxtral TTS",
         "neutts": "NeuTTS",
     }
     return mapping.get(current_provider or "edge", current_provider or "Edge TTS")
@@ -309,6 +310,7 @@ def get_nous_subscription_features(
         tts_current_provider in {"edge", "neutts"}
         or (tts_current_provider == "openai" and (managed_tts_available or direct_openai_tts))
         or (tts_current_provider == "elevenlabs" and direct_elevenlabs)
+        or (tts_current_provider == "mistral" and bool(get_env_value("MISTRAL_API_KEY")))
     )
     tts_active = bool(tts_tool_enabled and tts_available)
 

hermes_cli/plugins.py

@@ -201,8 +201,7 @@ class PluginContext:
 
         The *setup_fn* receives an argparse subparser and should add any
         arguments/sub-subparsers.  If *handler_fn* is provided it is set
-        as the default dispatch function via ``set_defaults(func=...)``.
-        """
+        as the default dispatch function via ``set_defaults(func=...)``."""
         self._manager._cli_commands[name] = {
             "name": name,
             "help": help,
@@ -213,6 +212,38 @@ class PluginContext:
         }
         logger.debug("Plugin %s registered CLI command: %s", self.manifest.name, name)
 
+    # -- context engine registration -----------------------------------------
+
+    def register_context_engine(self, engine) -> None:
+        """Register a context engine to replace the built-in ContextCompressor.
+
+        Only one context engine plugin is allowed. If a second plugin tries
+        to register one, it is rejected with a warning.
+
+        The engine must be an instance of ``agent.context_engine.ContextEngine``.
+        """
+        if self._manager._context_engine is not None:
+            logger.warning(
+                "Plugin '%s' tried to register a context engine, but one is "
+                "already registered. Only one context engine plugin is allowed.",
+                self.manifest.name,
+            )
+            return
+        # Defer the import to avoid circular deps at module level
+        from agent.context_engine import ContextEngine
+        if not isinstance(engine, ContextEngine):
+            logger.warning(
+                "Plugin '%s' tried to register a context engine that does not "
+                "inherit from ContextEngine. Ignoring.",
+                self.manifest.name,
+            )
+            return
+        self._manager._context_engine = engine
+        logger.info(
+            "Plugin '%s' registered context engine: %s",
+            self.manifest.name, engine.name,
+        )
+
     # -- hook registration --------------------------------------------------
 
     def register_hook(self, hook_name: str, callback: Callable) -> None:
@@ -245,6 +276,7 @@ class PluginManager:
         self._hooks: Dict[str, List[Callable]] = {}
         self._plugin_tool_names: Set[str] = set()
         self._cli_commands: Dict[str, dict] = {}
+        self._context_engine = None  # Set by a plugin via register_context_engine()
         self._discovered: bool = False
         self._cli_ref = None  # Set by CLI after plugin discovery
 
@@ -566,6 +598,11 @@ def get_plugin_cli_commands() -> Dict[str, dict]:
     return dict(get_plugin_manager()._cli_commands)
 
 
+def get_plugin_context_engine():
+    """Return the plugin-registered context engine, or None."""
+    return get_plugin_manager()._context_engine
+
+
 def get_plugin_toolsets() -> List[tuple]:
     """Return plugin toolsets as ``(key, label, description)`` tuples.
 

hermes_cli/plugins_cmd.py

@@ -531,7 +531,7 @@ def cmd_disable(name: str) -> None:
 
     disabled.add(name)
     _save_disabled_set(disabled)
-    console.print(f"[yellow]⊘[/yellow] Plugin [bold]{name}[/bold] disabled. Takes effect on next session.")
+    console.print(f"[yellow]\u2298[/yellow] Plugin [bold]{name}[/bold] disabled. Takes effect on next session.")
 
 
 def cmd_list() -> None:
@@ -594,8 +594,152 @@ def cmd_list() -> None:
     console.print("[dim]Enable/disable:[/dim] hermes plugins enable/disable <name>")
 
 
+# ---------------------------------------------------------------------------
+# Provider plugin discovery helpers
+# ---------------------------------------------------------------------------
+
+
+def _discover_memory_providers() -> list[tuple[str, str]]:
+    """Return [(name, description), ...] for available memory providers."""
+    try:
+        from plugins.memory import discover_memory_providers
+        return [(name, desc) for name, desc, _avail in discover_memory_providers()]
+    except Exception:
+        return []
+
+
+def _discover_context_engines() -> list[tuple[str, str]]:
+    """Return [(name, description), ...] for available context engines."""
+    try:
+        from plugins.context_engine import discover_context_engines
+        return [(name, desc) for name, desc, _avail in discover_context_engines()]
+    except Exception:
+        return []
+
+
+def _get_current_memory_provider() -> str:
+    """Return the current memory.provider from config (empty = built-in)."""
+    try:
+        from hermes_cli.config import load_config
+        config = load_config()
+        return config.get("memory", {}).get("provider", "") or ""
+    except Exception:
+        return ""
+
+
+def _get_current_context_engine() -> str:
+    """Return the current context.engine from config."""
+    try:
+        from hermes_cli.config import load_config
+        config = load_config()
+        return config.get("context", {}).get("engine", "compressor") or "compressor"
+    except Exception:
+        return "compressor"
+
+
+def _save_memory_provider(name: str) -> None:
+    """Persist memory.provider to config.yaml."""
+    from hermes_cli.config import load_config, save_config
+    config = load_config()
+    if "memory" not in config:
+        config["memory"] = {}
+    config["memory"]["provider"] = name
+    save_config(config)
+
+
+def _save_context_engine(name: str) -> None:
+    """Persist context.engine to config.yaml."""
+    from hermes_cli.config import load_config, save_config
+    config = load_config()
+    if "context" not in config:
+        config["context"] = {}
+    config["context"]["engine"] = name
+    save_config(config)
+
+
+def _configure_memory_provider() -> bool:
+    """Launch a radio picker for memory providers. Returns True if changed."""
+    from hermes_cli.curses_ui import curses_radiolist
+
+    current = _get_current_memory_provider()
+    providers = _discover_memory_providers()
+
+    # Build items: "built-in" first, then discovered providers
+    items = ["built-in (default)"]
+    names = [""]  # empty string = built-in
+    selected = 0
+
+    for name, desc in providers:
+        names.append(name)
+        label = f"{name} \u2014 {desc}" if desc else name
+        items.append(label)
+        if name == current:
+            selected = len(items) - 1
+
+    # If current provider isn't in discovered list, add it
+    if current and current not in names:
+        names.append(current)
+        items.append(f"{current} (not found)")
+        selected = len(items) - 1
+
+    choice = curses_radiolist(
+        title="Memory Provider (select one)",
+        items=items,
+        selected=selected,
+    )
+
+    new_provider = names[choice]
+    if new_provider != current:
+        _save_memory_provider(new_provider)
+        return True
+    return False
+
+
+def _configure_context_engine() -> bool:
+    """Launch a radio picker for context engines. Returns True if changed."""
+    from hermes_cli.curses_ui import curses_radiolist
+
+    current = _get_current_context_engine()
+    engines = _discover_context_engines()
+
+    # Build items: "compressor" first (built-in), then discovered engines
+    items = ["compressor (default)"]
+    names = ["compressor"]
+    selected = 0
+
+    for name, desc in engines:
+        names.append(name)
+        label = f"{name} \u2014 {desc}" if desc else name
+        items.append(label)
+        if name == current:
+            selected = len(items) - 1
+
+    # If current engine isn't in discovered list and isn't compressor, add it
+    if current != "compressor" and current not in names:
+        names.append(current)
+        items.append(f"{current} (not found)")
+        selected = len(items) - 1
+
+    choice = curses_radiolist(
+        title="Context Engine (select one)",
+        items=items,
+        selected=selected,
+    )
+
+    new_engine = names[choice]
+    if new_engine != current:
+        _save_context_engine(new_engine)
+        return True
+    return False
+
+
+# ---------------------------------------------------------------------------
+# Composite plugins UI
+# ---------------------------------------------------------------------------
+
+
 def cmd_toggle() -> None:
-    """Interactive curses checklist to enable/disable installed plugins."""
+    """Interactive composite UI — general plugins + provider plugin categories."""
     from rich.console import Console
 
     try:
@@ -606,18 +750,13 @@ def cmd_toggle() -> None:
     console = Console()
     plugins_dir = _plugins_dir()
 
+    # -- General plugins discovery --
     dirs = sorted(d for d in plugins_dir.iterdir() if d.is_dir())
-    if not dirs:
-        console.print("[dim]No plugins installed.[/dim]")
-        console.print("[dim]Install with:[/dim] hermes plugins install owner/repo")
-        return
-
     disabled = _get_disabled_set()
 
-    # Build items list: "name — description" for display
-    names = []
-    labels = []
-    selected = set()
+    plugin_names = []
+    plugin_labels = []
+    plugin_selected = set()
 
     for i, d in enumerate(dirs):
         manifest_file = d / "plugin.yaml"
@@ -633,36 +772,335 @@ def cmd_toggle() -> None:
             except Exception:
                 pass
 
-        names.append(name)
-        label = f"{name} — {description}" if description else name
-        labels.append(label)
+        plugin_names.append(name)
+        label = f"{name} \u2014 {description}" if description else name
+        plugin_labels.append(label)
 
         if name not in disabled and d.name not in disabled:
-            selected.add(i)
+            plugin_selected.add(i)
 
-    from hermes_cli.curses_ui import curses_checklist
+    # -- Provider categories --
+    current_memory = _get_current_memory_provider() or "built-in"
+    current_context = _get_current_context_engine()
+    categories = [
+        ("Memory Provider", current_memory, _configure_memory_provider),
+        ("Context Engine", current_context, _configure_context_engine),
+    ]
 
-    result = curses_checklist(
-        title="Plugins — toggle enabled/disabled",
-        items=labels,
-        selected=selected,
-    )
+    has_plugins = bool(plugin_names)
+    has_categories = bool(categories)
 
-    # Compute new disabled set from deselected items
+    if not has_plugins and not has_categories:
+        console.print("[dim]No plugins installed and no provider categories available.[/dim]")
+        console.print("[dim]Install with:[/dim] hermes plugins install owner/repo")
+        return
+
+    # Non-TTY fallback
+    if not sys.stdin.isatty():
+        console.print("[dim]Interactive mode requires a terminal.[/dim]")
+        return
+
+    # Launch the composite curses UI
+    try:
+        import curses
+        _run_composite_ui(curses, plugin_names, plugin_labels, plugin_selected,
+                          disabled, categories, console)
+    except ImportError:
+        _run_composite_fallback(plugin_names, plugin_labels, plugin_selected,
+                                disabled, categories, console)
+
+
+def _run_composite_ui(curses, plugin_names, plugin_labels, plugin_selected,
+                      disabled, categories, console):
+    """Custom curses screen with checkboxes + category action rows."""
+    from hermes_cli.curses_ui import flush_stdin
+
+    chosen = set(plugin_selected)
+    n_plugins = len(plugin_names)
+    # Total rows: plugins + separator + categories
+    # separator is not navigable
+    n_categories = len(categories)
+    total_items = n_plugins + n_categories  # navigable items
+
+    result_holder = {"plugins_changed": False, "providers_changed": False}
+
+    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, curses.COLOR_CYAN, -1)
+            curses.init_pair(4, 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, "Plugins", max_x - 1, hattr)
+                stdscr.addnstr(
+                    1, 0,
+                    "  \u2191\u2193 navigate  SPACE toggle  ENTER configure/confirm  ESC done",
+                    max_x - 1, curses.A_DIM,
+                )
+            except curses.error:
+                pass
+
+            # Build display rows
+            # Row layout:
+            #   [plugins section header] (not navigable, skipped in scroll math)
+            #   plugin checkboxes (navigable, indices 0..n_plugins-1)
+            #   [separator] (not navigable)
+            #   [categories section header] (not navigable)
+            #   category action rows (navigable, indices n_plugins..total_items-1)
+
+            visible_rows = max_y - 4
+            if cursor < scroll_offset:
+                scroll_offset = cursor
+            elif cursor >= scroll_offset + visible_rows:
+                scroll_offset = cursor - visible_rows + 1
+
+            y = 3  # start drawing after header
+
+            # Determine which items are visible based on scroll
+            # We need to map logical cursor positions to screen rows
+            # accounting for non-navigable separator/headers
+
+            draw_row = 0  # tracks navigable item index
+
+            # --- General Plugins section ---
+            if n_plugins > 0:
+                # Section header
+                if y < max_y - 1:
+                    try:
+                        sattr = curses.A_BOLD
+                        if curses.has_colors():
+                            sattr |= curses.color_pair(2)
+                        stdscr.addnstr(y, 0, "  General Plugins", max_x - 1, sattr)
+                    except curses.error:
+                        pass
+                    y += 1
+
+                for i in range(n_plugins):
+                    if y >= max_y - 1:
+                        break
+                    check = "\u2713" if i in chosen else " "
+                    arrow = "\u2192" if i == cursor else " "
+                    line = f" {arrow} [{check}] {plugin_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
+                    y += 1
+
+            # --- Separator ---
+            if y < max_y - 1:
+                y += 1  # blank line
+
+            # --- Provider Plugins section ---
+            if n_categories > 0 and y < max_y - 1:
+                try:
+                    sattr = curses.A_BOLD
+                    if curses.has_colors():
+                        sattr |= curses.color_pair(2)
+                    stdscr.addnstr(y, 0, "  Provider Plugins", max_x - 1, sattr)
+                except curses.error:
+                    pass
+                y += 1
+
+                for ci, (cat_name, cat_current, _cat_fn) in enumerate(categories):
+                    if y >= max_y - 1:
+                        break
+                    cat_idx = n_plugins + ci
+                    arrow = "\u2192" if cat_idx == cursor else " "
+                    line = f" {arrow}   {cat_name:<24} \u25b8 {cat_current}"
+                    attr = curses.A_NORMAL
+                    if cat_idx == cursor:
+                        attr = curses.A_BOLD
+                        if curses.has_colors():
+                            attr |= curses.color_pair(3)
+                    try:
+                        stdscr.addnstr(y, 0, line, max_x - 1, attr)
+                    except curses.error:
+                        pass
+                    y += 1
+
+            stdscr.refresh()
+            key = stdscr.getch()
+
+            if key in (curses.KEY_UP, ord("k")):
+                if total_items > 0:
+                    cursor = (cursor - 1) % total_items
+            elif key in (curses.KEY_DOWN, ord("j")):
+                if total_items > 0:
+                    cursor = (cursor + 1) % total_items
+            elif key == ord(" "):
+                if cursor < n_plugins:
+                    # Toggle general plugin
+                    chosen.symmetric_difference_update({cursor})
+                else:
+                    # Provider category — launch sub-screen
+                    ci = cursor - n_plugins
+                    if 0 <= ci < n_categories:
+                        curses.endwin()
+                        _cat_name, _cat_cur, cat_fn = categories[ci]
+                        changed = cat_fn()
+                        if changed:
+                            result_holder["providers_changed"] = True
+                            # Refresh current values
+                            categories[ci] = (
+                                _cat_name,
+                                _get_current_memory_provider() or "built-in" if ci == 0
+                                else _get_current_context_engine(),
+                                cat_fn,
+                            )
+                        # Re-enter curses
+                        stdscr = curses.initscr()
+                        curses.noecho()
+                        curses.cbreak()
+                        stdscr.keypad(True)
+                        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, curses.COLOR_CYAN, -1)
+                            curses.init_pair(4, 8, -1)
+                        curses.curs_set(0)
+            elif key in (curses.KEY_ENTER, 10, 13):
+                if cursor < n_plugins:
+                    # ENTER on a plugin checkbox — confirm and exit
+                    result_holder["plugins_changed"] = True
+                    return
+                else:
+                    # ENTER on a category — same as SPACE, launch sub-screen
+                    ci = cursor - n_plugins
+                    if 0 <= ci < n_categories:
+                        curses.endwin()
+                        _cat_name, _cat_cur, cat_fn = categories[ci]
+                        changed = cat_fn()
+                        if changed:
+                            result_holder["providers_changed"] = True
+                            categories[ci] = (
+                                _cat_name,
+                                _get_current_memory_provider() or "built-in" if ci == 0
+                                else _get_current_context_engine(),
+                                cat_fn,
+                            )
+                        stdscr = curses.initscr()
+                        curses.noecho()
+                        curses.cbreak()
+                        stdscr.keypad(True)
+                        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, curses.COLOR_CYAN, -1)
+                            curses.init_pair(4, 8, -1)
+                        curses.curs_set(0)
+            elif key in (27, ord("q")):
+                # Save plugin changes on exit
+                result_holder["plugins_changed"] = True
+                return
+
+    curses.wrapper(_draw)
+    flush_stdin()
+
+    # Persist general plugin changes
     new_disabled = set()
-    for i, name in enumerate(names):
-        if i not in result:
+    for i, name in enumerate(plugin_names):
+        if i not in chosen:
             new_disabled.add(name)
 
     if new_disabled != disabled:
         _save_disabled_set(new_disabled)
-        enabled_count = len(names) - len(new_disabled)
+        enabled_count = len(plugin_names) - len(new_disabled)
         console.print(
-            f"\n[green]✓[/green] {enabled_count} enabled, {len(new_disabled)} disabled. "
-            f"Takes effect on next session."
+            f"\n[green]\u2713[/green] General plugins: {enabled_count} enabled, "
+            f"{len(new_disabled)} disabled."
         )
-    else:
-        console.print("\n[dim]No changes.[/dim]")
+    elif n_plugins > 0:
+        console.print("\n[dim]General plugins unchanged.[/dim]")
+
+    if result_holder["providers_changed"]:
+        new_memory = _get_current_memory_provider() or "built-in"
+        new_context = _get_current_context_engine()
+        console.print(
+            f"[green]\u2713[/green] Memory provider: [bold]{new_memory}[/bold]  "
+            f"Context engine: [bold]{new_context}[/bold]"
+        )
+
+    if n_plugins > 0 or result_holder["providers_changed"]:
+        console.print("[dim]Changes take effect on next session.[/dim]")
+    console.print()
+
+
+def _run_composite_fallback(plugin_names, plugin_labels, plugin_selected,
+                            disabled, categories, console):
+    """Text-based fallback for the composite plugins UI."""
+    from hermes_cli.colors import Colors, color
+
+    print(color("\n  Plugins", Colors.YELLOW))
+
+    # General plugins
+    if plugin_names:
+        chosen = set(plugin_selected)
+        print(color("\n  General Plugins", Colors.YELLOW))
+        print(color("  Toggle by number, Enter to confirm.\n", Colors.DIM))
+
+        while True:
+            for i, label in enumerate(plugin_labels):
+                marker = color("[\u2713]", 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(plugin_names):
+                    chosen.symmetric_difference_update({idx})
+            except (ValueError, KeyboardInterrupt, EOFError):
+                return
+            print()
+
+        new_disabled = set()
+        for i, name in enumerate(plugin_names):
+            if i not in chosen:
+                new_disabled.add(name)
+        if new_disabled != disabled:
+            _save_disabled_set(new_disabled)
+
+    # Provider categories
+    if categories:
+        print(color("\n  Provider Plugins", Colors.YELLOW))
+        for ci, (cat_name, cat_current, cat_fn) in enumerate(categories):
+            print(f"  {ci + 1}. {cat_name} [{cat_current}]")
+        print()
+        try:
+            val = input(color("  Configure # (or Enter to skip): ", Colors.DIM)).strip()
+            if val:
+                ci = int(val) - 1
+                if 0 <= ci < len(categories):
+                    categories[ci][2]()  # call the configure function
+        except (ValueError, KeyboardInterrupt, EOFError):
+            pass
+
+    print()
 
 
 def plugins_command(args) -> None:

hermes_cli/profiles.py

@@ -42,6 +42,11 @@ _PROFILE_DIRS = [
     "plans",
     "workspace",
     "cron",
+    # Per-profile HOME for subprocesses: isolates system tool configs (git,
+    # ssh, gh, npm …) so credentials don't bleed between profiles.  In Docker
+    # this also ensures tool configs land inside the persistent volume.
+    # See hermes_constants.get_subprocess_home() and issue #4426.
+    "home",
 ]
 
 # Files copied during --clone (if they exist in the source)
@@ -102,7 +107,7 @@ _RESERVED_NAMES = frozenset({
 # Hermes subcommands that cannot be used as profile names/aliases
 _HERMES_SUBCOMMANDS = frozenset({
     "chat", "model", "gateway", "setup", "whatsapp", "login", "logout",
-    "status", "cron", "doctor", "config", "pairing", "skills", "tools",
+    "status", "cron", "doctor", "dump", "config", "pairing", "skills", "tools",
     "mcp", "sessions", "insights", "version", "update", "uninstall",
     "profile", "plugins", "honcho", "acp",
 })
@@ -115,16 +120,26 @@ _HERMES_SUBCOMMANDS = frozenset({
 def _get_profiles_root() -> Path:
     """Return the directory where named profiles are stored.
 
-    Always ``~/.hermes/profiles/`` — anchored to the user's home,
-    NOT to the current HERMES_HOME (which may itself be a profile).
-    This ensures ``coder profile list`` can see all profiles.
+    Anchored to the hermes root, NOT to the current HERMES_HOME
+    (which may itself be a profile).  This ensures ``coder profile list``
+    can see all profiles.
+
+    In Docker/custom deployments where HERMES_HOME points outside
+    ``~/.hermes``, profiles live under ``HERMES_HOME/profiles/`` so
+    they persist on the mounted volume.
     """
-    return Path.home() / ".hermes" / "profiles"
+    return _get_default_hermes_home() / "profiles"
 
 
 def _get_default_hermes_home() -> Path:
-    """Return the default (pre-profile) HERMES_HOME path."""
-    return Path.home() / ".hermes"
+    """Return the default (pre-profile) HERMES_HOME path.
+
+    In standard deployments this is ``~/.hermes``.
+    In Docker/custom deployments where HERMES_HOME is outside ``~/.hermes``
+    (e.g. ``/opt/data``), returns HERMES_HOME directly.
+    """
+    from hermes_constants import get_default_hermes_root
+    return get_default_hermes_root()
 
 
 def _get_active_profile_path() -> Path:
@@ -1007,7 +1022,7 @@ _hermes_completion() {
 
     # Top-level subcommands
     if [[ "$COMP_CWORD" == 1 ]]; then
-        local commands="chat model gateway setup status cron doctor config skills tools mcp sessions profile update version"
+        local commands="chat model gateway setup status cron doctor dump config skills tools mcp sessions profile update version"
         COMPREPLY=($(compgen -W "$commands" -- "$cur"))
     fi
 }
@@ -1032,7 +1047,7 @@ _hermes() {
     _arguments \\
         '-p[Profile name]:profile:($profiles)' \\
         '--profile[Profile name]:profile:($profiles)' \\
-        '1:command:(chat model gateway setup status cron doctor config skills tools mcp sessions profile update version)' \\
+        '1:command:(chat model gateway setup status cron doctor dump config skills tools mcp sessions profile update version)' \\
         '*::arg:->args'
 
     case $words[1] in

hermes_cli/providers.py

@@ -88,11 +88,11 @@ HERMES_OVERLAYS: Dict[str, HermesOverlay] = {
         base_url_env_var="KIMI_BASE_URL",
     ),
     "minimax": HermesOverlay(
-        transport="openai_chat",
+        transport="anthropic_messages",
         base_url_env_var="MINIMAX_BASE_URL",
     ),
     "minimax-cn": HermesOverlay(
-        transport="openai_chat",
+        transport="anthropic_messages",
         base_url_env_var="MINIMAX_CN_BASE_URL",
     ),
     "deepseek": HermesOverlay(
@@ -127,6 +127,11 @@ HERMES_OVERLAYS: Dict[str, HermesOverlay] = {
         is_aggregator=True,
         base_url_env_var="HF_BASE_URL",
     ),
+    "xai": HermesOverlay(
+        transport="openai_chat",
+        base_url_override="https://api.x.ai/v1",
+        base_url_env_var="XAI_BASE_URL",
+    ),
 }
 
 
@@ -148,10 +153,6 @@ class ProviderDef:
     doc: str = ""
     source: str = ""                      # "models.dev", "hermes", "user-config"
 
-    @property
-    def is_user_defined(self) -> bool:
-        return self.source == "user-config"
-
 
 # -- Aliases ------------------------------------------------------------------
 # Maps human-friendly / legacy names to canonical provider IDs.
@@ -167,6 +168,10 @@ ALIASES: Dict[str, str] = {
     "z.ai": "zai",
     "zhipu": "zai",
 
+    # xai
+    "x-ai": "xai",
+    "x.ai": "xai",
+
     # kimi-for-coding (models.dev ID)
     "kimi": "kimi-for-coding",
     "kimi-coding": "kimi-for-coding",
@@ -262,12 +267,6 @@ def normalize_provider(name: str) -> str:
     return ALIASES.get(key, key)
 
 
-def get_overlay(provider_id: str) -> Optional[HermesOverlay]:
-    """Get Hermes overlay for a provider, if one exists."""
-    canonical = normalize_provider(provider_id)
-    return HERMES_OVERLAYS.get(canonical)
-
-
 def get_provider(name: str) -> Optional[ProviderDef]:
     """Look up a provider by id or alias, merging all data sources.
 
@@ -350,36 +349,6 @@ def get_label(provider_id: str) -> str:
     return canonical
 
 
-# For direct import compat, expose as module-level dict
-# Built on demand by get_label() calls
-LABELS: Dict[str, str] = {
-    # Static entries for backward compat — get_label() is the proper API
-    "openrouter": "OpenRouter",
-    "nous": "Nous Portal",
-    "openai-codex": "OpenAI Codex",
-    "copilot-acp": "GitHub Copilot ACP",
-    "github-copilot": "GitHub Copilot",
-    "anthropic": "Anthropic",
-    "zai": "Z.AI / GLM",
-    "kimi-for-coding": "Kimi / Moonshot",
-    "minimax": "MiniMax",
-    "minimax-cn": "MiniMax (China)",
-    "deepseek": "DeepSeek",
-    "alibaba": "Alibaba Cloud (DashScope)",
-    "vercel": "Vercel AI Gateway",
-    "opencode": "OpenCode Zen",
-    "opencode-go": "OpenCode Go",
-    "kilo": "Kilo Gateway",
-    "huggingface": "Hugging Face",
-    "local": "Local endpoint",
-    "custom": "Custom endpoint",
-    # Legacy Hermes IDs (point to same providers)
-    "ai-gateway": "Vercel AI Gateway",
-    "kilocode": "Kilo Gateway",
-    "copilot": "GitHub Copilot",
-    "kimi-coding": "Kimi / Moonshot",
-    "opencode-zen": "OpenCode Zen",
-}
 
 
 def is_aggregator(provider: str) -> bool:
@@ -452,9 +421,64 @@ def resolve_user_provider(name: str, user_config: Dict[str, Any]) -> Optional[Pr
     )
 
 
+def custom_provider_slug(display_name: str) -> str:
+    """Build a canonical slug for a custom_providers entry.
+
+    Matches the convention used by runtime_provider and credential_pool
+    (``custom:<normalized-name>``).  Centralised here so all call-sites
+    produce identical slugs.
+    """
+    return "custom:" + display_name.strip().lower().replace(" ", "-")
+
+
+def resolve_custom_provider(
+    name: str,
+    custom_providers: Optional[List[Dict[str, Any]]],
+) -> Optional[ProviderDef]:
+    """Resolve a provider from the user's config.yaml ``custom_providers`` list."""
+    if not custom_providers or not isinstance(custom_providers, list):
+        return None
+
+    requested = (name or "").strip().lower()
+    if not requested:
+        return None
+
+    for entry in custom_providers:
+        if not isinstance(entry, dict):
+            continue
+
+        display_name = (entry.get("name") or "").strip()
+        api_url = (
+            entry.get("base_url", "")
+            or entry.get("url", "")
+            or entry.get("api", "")
+            or ""
+        ).strip()
+        if not display_name or not api_url:
+            continue
+
+        slug = custom_provider_slug(display_name)
+        if requested not in {display_name.lower(), slug}:
+            continue
+
+        return ProviderDef(
+            id=slug,
+            name=display_name,
+            transport="openai_chat",
+            api_key_env_vars=(),
+            base_url=api_url,
+            is_aggregator=False,
+            auth_type="api_key",
+            source="user-config",
+        )
+
+    return None
+
+
 def resolve_provider_full(
     name: str,
     user_providers: Optional[Dict[str, Any]] = None,
+    custom_providers: Optional[List[Dict[str, Any]]] = None,
 ) -> Optional[ProviderDef]:
     """Full resolution chain: built-in → models.dev → user config.
 
@@ -463,6 +487,7 @@ def resolve_provider_full(
     Args:
         name: Provider name or alias.
         user_providers: The ``providers:`` dict from config.yaml (optional).
+        custom_providers: The ``custom_providers:`` list from config.yaml (optional).
 
     Returns:
         ProviderDef if found, else None.
@@ -485,6 +510,11 @@ def resolve_provider_full(
         if user_pdef is not None:
             return user_pdef
 
+    # 2b. Saved custom providers from config
+    custom_pdef = resolve_custom_provider(name, custom_providers)
+    if custom_pdef is not None:
+        return custom_pdef
+
     # 3. Try models.dev directly (for providers not in our ALIASES)
     try:
         from agent.models_dev import get_provider_info as _mdev_provider

hermes_cli/runtime_provider.py

@@ -16,6 +16,7 @@ from hermes_cli.auth import (
     DEFAULT_CODEX_BASE_URL,
     DEFAULT_QWEN_BASE_URL,
     PROVIDER_REGISTRY,
+    _agent_key_is_usable,
     format_auth_error,
     resolve_provider,
     resolve_nous_runtime_credentials,
@@ -644,6 +645,21 @@ def resolve_runtime_provider(
                 getattr(entry, "runtime_api_key", None)
                 or getattr(entry, "access_token", "")
             )
+        # For Nous, the pool entry's runtime_api_key is the agent_key — a
+        # short-lived inference credential (~30 min TTL).  The pool doesn't
+        # refresh it during selection (that would trigger network calls in
+        # non-runtime contexts like `hermes auth list`).  If the key is
+        # expired, clear pool_api_key so we fall through to
+        # resolve_nous_runtime_credentials() which handles refresh + mint.
+        if provider == "nous" and entry is not None and pool_api_key:
+            min_ttl = max(60, int(os.getenv("HERMES_NOUS_MIN_KEY_TTL_SECONDS", "1800")))
+            nous_state = {
+                "agent_key": getattr(entry, "agent_key", None),
+                "agent_key_expires_at": getattr(entry, "agent_key_expires_at", None),
+            }
+            if not _agent_key_is_usable(nous_state, min_ttl):
+                logger.debug("Nous pool entry agent_key expired/missing, falling through to runtime resolution")
+                pool_api_key = ""
         if entry is not None and pool_api_key:
             return _resolve_runtime_from_pool_entry(
                 provider=provider,

hermes_cli/setup.py

@@ -16,6 +16,7 @@ import logging
 import os
 import shutil
 import sys
+import copy
 from pathlib import Path
 from typing import Optional, Dict, Any
 
@@ -105,8 +106,8 @@ _DEFAULT_PROVIDER_MODELS = {
     ],
     "zai": ["glm-5", "glm-4.7", "glm-4.5", "glm-4.5-flash"],
     "kimi-coding": ["kimi-k2.5", "kimi-k2-thinking", "kimi-k2-turbo-preview"],
-    "minimax": ["MiniMax-M1", "MiniMax-M1-40k", "MiniMax-M1-80k", "MiniMax-M1-128k", "MiniMax-M1-256k", "MiniMax-M2.5", "MiniMax-M2.7"],
-    "minimax-cn": ["MiniMax-M1", "MiniMax-M1-40k", "MiniMax-M1-80k", "MiniMax-M1-128k", "MiniMax-M1-256k", "MiniMax-M2.5", "MiniMax-M2.7"],
+    "minimax": ["MiniMax-M2.7", "MiniMax-M2.5", "MiniMax-M2.1", "MiniMax-M2"],
+    "minimax-cn": ["MiniMax-M2.7", "MiniMax-M2.5", "MiniMax-M2.1", "MiniMax-M2"],
     "ai-gateway": ["anthropic/claude-opus-4.6", "anthropic/claude-sonnet-4.6", "openai/gpt-5", "google/gemini-3-flash"],
     "kilocode": ["anthropic/claude-opus-4.6", "anthropic/claude-sonnet-4.6", "openai/gpt-5.4", "google/gemini-3-pro-preview", "google/gemini-3-flash-preview"],
     "opencode-zen": ["gpt-5.4", "gpt-5.3-codex", "claude-sonnet-4-6", "gemini-3-flash", "glm-5", "kimi-k2.5", "minimax-m2.7"],
@@ -172,150 +173,10 @@ def _setup_copilot_reasoning_selection(
         _set_reasoning_effort(config, "none")
 
 
-def _setup_provider_model_selection(config, provider_id, current_model, prompt_choice, prompt_fn):
-    """Model selection for API-key providers with live /models detection.
-
-    Tries the provider's /models endpoint first.  Falls back to a
-    hardcoded default list with a warning if the endpoint is unreachable.
-    Always offers a 'Custom model' escape hatch.
-    """
-    from hermes_cli.auth import PROVIDER_REGISTRY, resolve_api_key_provider_credentials
-    from hermes_cli.config import get_env_value
-    from hermes_cli.models import (
-        copilot_model_api_mode,
-        fetch_api_models,
-        fetch_github_model_catalog,
-        normalize_copilot_model_id,
-        normalize_opencode_model_id,
-        opencode_model_api_mode,
-    )
-
-    pconfig = PROVIDER_REGISTRY[provider_id]
-    is_copilot_catalog_provider = provider_id in {"copilot", "copilot-acp"}
-
-    # Resolve API key and base URL for the probe
-    if is_copilot_catalog_provider:
-        api_key = ""
-        if provider_id == "copilot":
-            creds = resolve_api_key_provider_credentials(provider_id)
-            api_key = creds.get("api_key", "")
-            base_url = creds.get("base_url", "") or pconfig.inference_base_url
-        else:
-            try:
-                creds = resolve_api_key_provider_credentials("copilot")
-                api_key = creds.get("api_key", "")
-            except Exception:
-                pass
-            base_url = pconfig.inference_base_url
-        catalog = fetch_github_model_catalog(api_key)
-        current_model = normalize_copilot_model_id(
-            current_model,
-            catalog=catalog,
-            api_key=api_key,
-        ) or current_model
-    else:
-        api_key = ""
-        for ev in pconfig.api_key_env_vars:
-            api_key = get_env_value(ev) or os.getenv(ev, "")
-            if api_key:
-                break
-        base_url_env = pconfig.base_url_env_var or ""
-        base_url = (get_env_value(base_url_env) if base_url_env else "") or pconfig.inference_base_url
-        catalog = None
-
-    # Try live /models endpoint
-    if is_copilot_catalog_provider and catalog:
-        live_models = [item.get("id", "") for item in catalog if item.get("id")]
-    else:
-        live_models = fetch_api_models(api_key, base_url)
-
-    if live_models:
-        provider_models = live_models
-        print_info(f"Found {len(live_models)} model(s) from {pconfig.name} API")
-    else:
-        fallback_provider_id = "copilot" if provider_id == "copilot-acp" else provider_id
-        provider_models = _DEFAULT_PROVIDER_MODELS.get(fallback_provider_id, [])
-        if provider_models:
-            print_warning(
-                f"Could not auto-detect models from {pconfig.name} API — showing defaults.\n"
-                f"    Use \"Custom model\" if the model you expect isn't listed."
-            )
-
-    if provider_id in {"opencode-zen", "opencode-go"}:
-        provider_models = [normalize_opencode_model_id(provider_id, mid) for mid in provider_models]
-        current_model = normalize_opencode_model_id(provider_id, current_model)
-        provider_models = list(dict.fromkeys(mid for mid in provider_models if mid))
-
-    model_choices = list(provider_models)
-    model_choices.append("Custom model")
-    model_choices.append(f"Keep current ({current_model})")
-
-    keep_idx = len(model_choices) - 1
-    model_idx = prompt_choice("Select default model:", model_choices, keep_idx)
-
-    selected_model = current_model
-
-    if model_idx < len(provider_models):
-        selected_model = provider_models[model_idx]
-        if is_copilot_catalog_provider:
-            selected_model = normalize_copilot_model_id(
-                selected_model,
-                catalog=catalog,
-                api_key=api_key,
-            ) or selected_model
-        elif provider_id in {"opencode-zen", "opencode-go"}:
-            selected_model = normalize_opencode_model_id(provider_id, selected_model)
-        _set_default_model(config, selected_model)
-    elif model_idx == len(provider_models):
-        custom = prompt_fn("Enter model name")
-        if custom:
-            if is_copilot_catalog_provider:
-                selected_model = normalize_copilot_model_id(
-                    custom,
-                    catalog=catalog,
-                    api_key=api_key,
-                ) or custom
-            elif provider_id in {"opencode-zen", "opencode-go"}:
-                selected_model = normalize_opencode_model_id(provider_id, custom)
-            else:
-                selected_model = custom
-            _set_default_model(config, selected_model)
-    else:
-        # "Keep current" selected — validate it's compatible with the new
-        # provider.  OpenRouter-formatted names (containing "/") won't work
-        # on direct-API providers and would silently break the gateway.
-        if "/" in (current_model or "") and provider_models:
-            print_warning(
-                f"Current model \"{current_model}\" looks like an OpenRouter model "
-                f"and won't work with {pconfig.name}. "
-                f"Switching to {provider_models[0]}."
-            )
-            selected_model = provider_models[0]
-            _set_default_model(config, provider_models[0])
-
-    if provider_id == "copilot" and selected_model:
-        model_cfg = _model_config_dict(config)
-        model_cfg["api_mode"] = copilot_model_api_mode(
-            selected_model,
-            catalog=catalog,
-            api_key=api_key,
-        )
-        config["model"] = model_cfg
-        _setup_copilot_reasoning_selection(
-            config,
-            selected_model,
-            prompt_choice,
-            catalog=catalog,
-            api_key=api_key,
-        )
-    elif provider_id in {"opencode-zen", "opencode-go"} and selected_model:
-        model_cfg = _model_config_dict(config)
-        model_cfg["api_mode"] = opencode_model_api_mode(provider_id, selected_model)
-        config["model"] = model_cfg
-
 
 # Import config helpers
 from hermes_cli.config import (
+    DEFAULT_CONFIG,
     get_hermes_home,
     get_config_path,
     get_env_path,
@@ -477,6 +338,8 @@ def _curses_prompt_choice(question: str, choices: list, default: int = 0) -> int
                     return
 
         curses.wrapper(_curses_menu)
+        from hermes_cli.curses_ui import flush_stdin
+        flush_stdin()
         return result_holder[0]
     except Exception:
         return -1
@@ -694,6 +557,8 @@ def _print_setup_summary(config: dict, hermes_home):
         tool_status.append(("Text-to-Speech (OpenAI)", True, None))
     elif tts_provider == "minimax" and get_env_value("MINIMAX_API_KEY"):
         tool_status.append(("Text-to-Speech (MiniMax)", True, None))
+    elif tts_provider == "mistral" and get_env_value("MISTRAL_API_KEY"):
+        tool_status.append(("Text-to-Speech (Mistral Voxtral)", True, None))
     elif tts_provider == "neutts":
         try:
             import importlib.util
@@ -921,8 +786,10 @@ def setup_model_provider(config: dict, *, quick: bool = False):
     # changes with stale values (#4172).
     _refreshed = load_config()
     config["model"] = _refreshed.get("model", config.get("model"))
-    if _refreshed.get("custom_providers"):
+    if "custom_providers" in _refreshed:
         config["custom_providers"] = _refreshed["custom_providers"]
+    else:
+        config.pop("custom_providers", None)
 
     # Derive the selected provider for downstream steps (vision setup).
     selected_provider = None
@@ -1006,8 +873,6 @@ def setup_model_provider(config: dict, *, quick: bool = False):
                 strategy_value = ["fill_first", "round_robin", "random"][strategy_idx]
                 _set_credential_pool_strategy(config, selected_provider, strategy_value)
                 print_success(f"Saved {selected_provider} rotation strategy: {strategy_value}")
-            else:
-                _set_credential_pool_strategy(config, selected_provider, "fill_first")
         except Exception as exc:
             logger.debug("Could not configure same-provider fallback in setup: %s", exc)
 
@@ -1181,6 +1046,7 @@ def _setup_tts_provider(config: dict):
         "elevenlabs": "ElevenLabs",
         "openai": "OpenAI TTS",
         "minimax": "MiniMax TTS",
+        "mistral": "Mistral Voxtral TTS",
         "neutts": "NeuTTS",
     }
     current_label = provider_labels.get(current_provider, current_provider)
@@ -1201,10 +1067,11 @@ def _setup_tts_provider(config: dict):
             "ElevenLabs (premium quality, needs API key)",
             "OpenAI TTS (good quality, needs API key)",
             "MiniMax TTS (high quality with voice cloning, needs API key)",
+            "Mistral Voxtral TTS (multilingual, native Opus, needs API key)",
             "NeuTTS (local on-device, free, ~300MB model download)",
         ]
     )
-    providers.extend(["edge", "elevenlabs", "openai", "minimax", "neutts"])
+    providers.extend(["edge", "elevenlabs", "openai", "minimax", "mistral", "neutts"])
     choices.append(f"Keep current ({current_label})")
     keep_current_idx = len(choices) - 1
     idx = prompt_choice("Select TTS provider:", choices, keep_current_idx)
@@ -1282,6 +1149,18 @@ def _setup_tts_provider(config: dict):
                 print_warning("No API key provided. Falling back to Edge TTS.")
                 selected = "edge"
 
+    elif selected == "mistral":
+        existing = get_env_value("MISTRAL_API_KEY")
+        if not existing:
+            print()
+            api_key = prompt("Mistral API key for TTS", password=True)
+            if api_key:
+                save_env_value("MISTRAL_API_KEY", api_key)
+                print_success("Mistral TTS API key saved")
+            else:
+                print_warning("No API key provided. Falling back to Edge TTS.")
+                selected = "edge"
+
     # Save the selection
     if "tts" not in config:
         config["tts"] = {}
@@ -2062,9 +1941,9 @@ def _setup_matrix():
             save_env_value("MATRIX_ENCRYPTION", "true")
             print_success("E2EE enabled")
 
-        matrix_pkg = "matrix-nio[e2e]" if want_e2ee else "matrix-nio"
+        matrix_pkg = "mautrix[encryption]" if want_e2ee else "mautrix"
         try:
-            __import__("nio")
+            __import__("mautrix")
         except ImportError:
             print_info(f"Installing {matrix_pkg}...")
             import subprocess
@@ -2167,6 +2046,77 @@ def _setup_whatsapp():
         print_info("or personal self-chat) and pair via QR code.")
 
 
+def _setup_weixin():
+    """Configure Weixin (personal WeChat) via iLink Bot API QR login."""
+    from hermes_cli.gateway import _setup_weixin as _gateway_setup_weixin
+    _gateway_setup_weixin()
+
+
+def _setup_bluebubbles():
+    """Configure BlueBubbles iMessage gateway."""
+    print_header("BlueBubbles (iMessage)")
+    existing = get_env_value("BLUEBUBBLES_SERVER_URL")
+    if existing:
+        print_info("BlueBubbles: already configured")
+        if not prompt_yes_no("Reconfigure BlueBubbles?", False):
+            return
+
+    print_info("Connects Hermes to iMessage via BlueBubbles — a free, open-source")
+    print_info("macOS server that bridges iMessage to any device.")
+    print_info("   Requires a Mac running BlueBubbles Server v1.0.0+")
+    print_info("   Download: https://bluebubbles.app/")
+    print()
+    print_info("In BlueBubbles Server → Settings → API, note your Server URL and Password.")
+    print()
+
+    server_url = prompt("BlueBubbles server URL (e.g. http://192.168.1.10:1234)")
+    if not server_url:
+        print_warning("Server URL is required — skipping BlueBubbles setup")
+        return
+    save_env_value("BLUEBUBBLES_SERVER_URL", server_url.rstrip("/"))
+
+    password = prompt("BlueBubbles server password", password=True)
+    if not password:
+        print_warning("Password is required — skipping BlueBubbles setup")
+        return
+    save_env_value("BLUEBUBBLES_PASSWORD", password)
+    print_success("BlueBubbles credentials saved")
+
+    print()
+    print_info("🔒 Security: Restrict who can message your bot")
+    print_info("   Use iMessage addresses: email (user@icloud.com) or phone (+15551234567)")
+    print()
+    allowed_users = prompt("Allowed iMessage addresses (comma-separated, leave empty for open access)")
+    if allowed_users:
+        save_env_value("BLUEBUBBLES_ALLOWED_USERS", allowed_users.replace(" ", ""))
+        print_success("BlueBubbles allowlist configured")
+    else:
+        print_info("⚠️  No allowlist set — anyone who can iMessage you can use the bot!")
+
+    print()
+    print_info("📬 Home Channel: phone or email for cron job delivery and notifications.")
+    print_info("   You can also set this later with /set-home in your iMessage chat.")
+    home_channel = prompt("Home channel address (leave empty to set later)")
+    if home_channel:
+        save_env_value("BLUEBUBBLES_HOME_CHANNEL", home_channel)
+
+    print()
+    print_info("Advanced settings (defaults are fine for most setups):")
+    if prompt_yes_no("Configure webhook listener settings?", False):
+        webhook_port = prompt("Webhook listener port (default: 8645)")
+        if webhook_port:
+            try:
+                save_env_value("BLUEBUBBLES_WEBHOOK_PORT", str(int(webhook_port)))
+                print_success(f"Webhook port set to {webhook_port}")
+            except ValueError:
+                print_warning("Invalid port number, using default 8645")
+
+    print()
+    print_info("Requires the BlueBubbles Private API helper for typing indicators,")
+    print_info("read receipts, and tapback reactions. Basic messaging works without it.")
+    print_info("   Install: https://docs.bluebubbles.app/helper-bundle/installation")
+
+
 def _setup_webhooks():
     """Configure webhook integration."""
     print_header("Webhooks")
@@ -2221,6 +2171,8 @@ _GATEWAY_PLATFORMS = [
     ("Matrix", "MATRIX_ACCESS_TOKEN", _setup_matrix),
     ("Mattermost", "MATTERMOST_TOKEN", _setup_mattermost),
     ("WhatsApp", "WHATSAPP_ENABLED", _setup_whatsapp),
+    ("Weixin (WeChat)", "WEIXIN_ACCOUNT_ID", _setup_weixin),
+    ("BlueBubbles (iMessage)", "BLUEBUBBLES_SERVER_URL", _setup_bluebubbles),
     ("Webhooks (GitHub, GitLab, etc.)", "WEBHOOK_ENABLED", _setup_webhooks),
 ]
 
@@ -2264,6 +2216,7 @@ def setup_gateway(config: dict):
         or get_env_value("MATRIX_ACCESS_TOKEN")
         or get_env_value("MATRIX_PASSWORD")
         or get_env_value("WHATSAPP_ENABLED")
+        or get_env_value("BLUEBUBBLES_SERVER_URL")
         or get_env_value("WEBHOOK_ENABLED")
     )
     if any_messaging:
@@ -2283,6 +2236,8 @@ def setup_gateway(config: dict):
             missing_home.append("Discord")
         if get_env_value("SLACK_BOT_TOKEN") and not get_env_value("SLACK_HOME_CHANNEL"):
             missing_home.append("Slack")
+        if get_env_value("BLUEBUBBLES_SERVER_URL") and not get_env_value("BLUEBUBBLES_HOME_CHANNEL"):
+            missing_home.append("BlueBubbles")
 
         if missing_home:
             print()
@@ -2453,6 +2408,8 @@ def _get_section_config_summary(config: dict, section_key: str) -> Optional[str]
             platforms.append("WhatsApp")
         if get_env_value("SIGNAL_ACCOUNT"):
             platforms.append("Signal")
+        if get_env_value("BLUEBUBBLES_SERVER_URL"):
+            platforms.append("BlueBubbles")
         if platforms:
             return ", ".join(platforms)
         return None  # No platforms configured — section must run
@@ -2501,9 +2458,120 @@ _OPENCLAW_SCRIPT = (
 )
 
 
+def _load_openclaw_migration_module():
+    """Load the openclaw_to_hermes migration script as a module.
+
+    Returns the loaded module, or None if the script can't be loaded.
+    """
+    if not _OPENCLAW_SCRIPT.exists():
+        return None
+
+    spec = importlib.util.spec_from_file_location(
+        "openclaw_to_hermes", _OPENCLAW_SCRIPT
+    )
+    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)
+    import sys as _sys
+    _sys.modules[spec.name] = mod
+    try:
+        spec.loader.exec_module(mod)
+    except Exception:
+        _sys.modules.pop(spec.name, None)
+        raise
+    return mod
+
+
+# Item kinds that represent high-impact changes warranting explicit warnings.
+# Gateway tokens/channels can hijack messaging platforms from the old agent.
+# Config values may have different semantics between OpenClaw and Hermes.
+# Instruction/context files (.md) can contain incompatible setup procedures.
+_HIGH_IMPACT_KIND_KEYWORDS = {
+    "gateway": "⚠ Gateway/messaging — this will configure Hermes to use your OpenClaw messaging channels",
+    "telegram": "⚠ Telegram — this will point Hermes at your OpenClaw Telegram bot",
+    "slack": "⚠ Slack — this will point Hermes at your OpenClaw Slack workspace",
+    "discord": "⚠ Discord — this will point Hermes at your OpenClaw Discord bot",
+    "whatsapp": "⚠ WhatsApp — this will point Hermes at your OpenClaw WhatsApp connection",
+    "config": "⚠ Config values — OpenClaw settings may not map 1:1 to Hermes equivalents",
+    "soul": "⚠ Instruction file — may contain OpenClaw-specific setup/restart procedures",
+    "memory": "⚠ Memory/context file — may reference OpenClaw-specific infrastructure",
+    "context": "⚠ Context file — may contain OpenClaw-specific instructions",
+}
+
+
+def _print_migration_preview(report: dict):
+    """Print a detailed dry-run preview of what migration would do.
+
+    Groups items by category and adds explicit warnings for high-impact
+    changes like gateway token takeover and config value differences.
+    """
+    items = report.get("items", [])
+    if not items:
+        print_info("Nothing to migrate.")
+        return
+
+    migrated_items = [i for i in items if i.get("status") == "migrated"]
+    conflict_items = [i for i in items if i.get("status") == "conflict"]
+    skipped_items = [i for i in items if i.get("status") == "skipped"]
+
+    warnings_shown = set()
+
+    if migrated_items:
+        print(color("  Would import:", 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}")
+
+            # Check for high-impact items and collect warnings
+            kind_lower = kind.lower()
+            dest_lower = str(dest).lower()
+            for keyword, warning in _HIGH_IMPACT_KIND_KEYWORDS.items():
+                if keyword in kind_lower or keyword in dest_lower:
+                    warnings_shown.add(warning)
+        print()
+
+    if conflict_items:
+        print(color("  Would overwrite (conflicts with existing Hermes config):", 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("  Would skip:", Colors.DIM))
+        for item in skipped_items:
+            kind = item.get("kind", "unknown")
+            reason = item.get("reason", "")
+            print(f"      {kind:<22s}  {reason}")
+        print()
+
+    # Print collected warnings
+    if warnings_shown:
+        print(color("  ── Warnings ──", Colors.YELLOW))
+        for warning in sorted(warnings_shown):
+            print(color(f"    {warning}", Colors.YELLOW))
+        print()
+        print(color("  Note: OpenClaw config values may have different semantics in Hermes.", Colors.YELLOW))
+        print(color("  For example, OpenClaw's tool_call_execution: \"auto\" ≠ Hermes's yolo mode.", Colors.YELLOW))
+        print(color("  Instruction files (.md) from OpenClaw may contain incompatible procedures.", Colors.YELLOW))
+        print()
+
+
 def _offer_openclaw_migration(hermes_home: Path) -> bool:
     """Detect ~/.openclaw and offer to migrate during first-time setup.
 
+    Runs a dry-run first to show the user exactly what would be imported,
+    overwritten, or taken over. Only executes after explicit confirmation.
+
     Returns True if migration ran successfully, False otherwise.
     """
     openclaw_dir = Path.home() / ".openclaw"
@@ -2516,12 +2584,12 @@ def _offer_openclaw_migration(hermes_home: Path) -> bool:
     print()
     print_header("OpenClaw Installation Detected")
     print_info(f"Found OpenClaw data at {openclaw_dir}")
-    print_info("Hermes can import your settings, memories, skills, and API keys.")
+    print_info("Hermes can preview what would be imported before making any changes.")
     print()
 
-    if not prompt_yes_no("Would you like to import from OpenClaw?", default=True):
+    if not prompt_yes_no("Would you like to see what can be imported?", default=True):
         print_info(
-            "Skipping migration. You can run it later via the openclaw-migration skill."
+            "Skipping migration. You can run it later with: hermes claw migrate --dry-run"
         )
         return False
 
@@ -2530,34 +2598,71 @@ def _offer_openclaw_migration(hermes_home: Path) -> bool:
     if not config_path.exists():
         save_config(load_config())
 
-    # Dynamically load the migration script
+    # Load the migration module
     try:
-        spec = importlib.util.spec_from_file_location(
-            "openclaw_to_hermes", _OPENCLAW_SCRIPT
-        )
-        if spec is None or spec.loader is None:
+        mod = _load_openclaw_migration_module()
+        if mod is None:
             print_warning("Could not load migration script.")
             return False
+    except Exception as e:
+        print_warning(f"Could not load migration script: {e}")
+        logger.debug("OpenClaw migration module load error", exc_info=True)
+        return False
 
-        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)
-        import sys as _sys
-        _sys.modules[spec.name] = mod
-        try:
-            spec.loader.exec_module(mod)
-        except Exception:
-            _sys.modules.pop(spec.name, None)
-            raise
-
-        # Run migration with the "full" preset, execute mode, no overwrite
+    # ── Phase 1: Dry-run preview ──
+    try:
         selected = mod.resolve_selected_options(None, None, preset="full")
+        dry_migrator = mod.Migrator(
+            source_root=openclaw_dir.resolve(),
+            target_root=hermes_home.resolve(),
+            execute=False,  # dry-run — no files modified
+            workspace_target=None,
+            overwrite=True,  # show everything including conflicts
+            migrate_secrets=True,
+            output_dir=None,
+            selected_options=selected,
+            preset_name="full",
+        )
+        preview_report = dry_migrator.migrate()
+    except Exception as e:
+        print_warning(f"Migration preview failed: {e}")
+        logger.debug("OpenClaw migration preview error", exc_info=True)
+        return False
+
+    # Display the full preview
+    preview_summary = preview_report.get("summary", {})
+    preview_count = preview_summary.get("migrated", 0)
+
+    if preview_count == 0:
+        print()
+        print_info("Nothing to import from OpenClaw.")
+        return False
+
+    print()
+    print_header(f"Migration Preview — {preview_count} item(s) would be imported")
+    print_info("No changes have been made yet. Review the list below:")
+    print()
+    _print_migration_preview(preview_report)
+
+    # ── Phase 2: Confirm and execute ──
+    if not prompt_yes_no("Proceed with migration?", default=False):
+        print_info(
+            "Migration cancelled. You can run it later with: hermes claw migrate"
+        )
+        print_info(
+            "Use --dry-run to preview again, or --preset minimal for a lighter import."
+        )
+        return False
+
+    # Execute the migration — overwrite=False so existing Hermes configs are
+    # preserved. The user saw the preview; conflicts are skipped by default.
+    try:
         migrator = mod.Migrator(
             source_root=openclaw_dir.resolve(),
             target_root=hermes_home.resolve(),
             execute=True,
             workspace_target=None,
-            overwrite=True,
+            overwrite=False,  # preserve existing Hermes config
             migrate_secrets=True,
             output_dir=None,
             selected_options=selected,
@@ -2569,7 +2674,7 @@ def _offer_openclaw_migration(hermes_home: Path) -> bool:
         logger.debug("OpenClaw migration error", exc_info=True)
         return False
 
-    # Print summary
+    # Print final summary
     summary = report.get("summary", {})
     migrated = summary.get("migrated", 0)
     skipped = summary.get("skipped", 0)
@@ -2580,7 +2685,7 @@ def _offer_openclaw_migration(hermes_home: Path) -> bool:
     if migrated:
         print_success(f"Imported {migrated} item(s) from OpenClaw.")
     if conflicts:
-        print_info(f"Skipped {conflicts} item(s) that already exist in Hermes.")
+        print_info(f"Skipped {conflicts} item(s) that already exist in Hermes (use hermes claw migrate --overwrite to force).")
     if skipped:
         print_info(f"Skipped {skipped} item(s) (not found or unchanged).")
     if errors:
@@ -2625,6 +2730,7 @@ def run_setup_wizard(args):
     Supports full, quick, and section-specific setup:
       hermes setup           — full or quick (auto-detected)
       hermes setup model     — just model/provider
+      hermes setup tts       — just text-to-speech
       hermes setup terminal  — just terminal backend
       hermes setup gateway   — just messaging platforms
       hermes setup tools     — just tool configuration
@@ -2636,6 +2742,11 @@ def run_setup_wizard(args):
         return
     ensure_hermes_home()
 
+    reset_requested = bool(getattr(args, "reset", False))
+    if reset_requested:
+        save_config(copy.deepcopy(DEFAULT_CONFIG))
+        print_success("Configuration reset to defaults.")
+
     config = load_config()
     hermes_home = get_hermes_home()
 
@@ -2736,18 +2847,13 @@ def run_setup_wizard(args):
         menu_choices = [
             "Quick Setup - configure missing items only",
             "Full Setup - reconfigure everything",
-            "---",
             "Model & Provider",
             "Terminal Backend",
             "Messaging Platforms (Gateway)",
             "Tools",
             "Agent Settings",
-            "---",
             "Exit",
         ]
-
-        # Separator indices (not selectable, but prompt_choice doesn't filter them,
-        # so we handle them below)
         choice = prompt_choice("What would you like to do?", menu_choices, 0)
 
         if choice == 0:
@@ -2757,18 +2863,14 @@ def run_setup_wizard(args):
         elif choice == 1:
             # Full setup — fall through to run all sections
             pass
-        elif choice in (2, 8):
-            # Separator — treat as exit
+        elif choice == 7:
             print_info("Exiting. Run 'hermes setup' again when ready.")
             return
-        elif choice == 9:
-            print_info("Exiting. Run 'hermes setup' again when ready.")
-            return
-        elif 3 <= choice <= 7:
+        elif 2 <= choice <= 6:
             # Individual section — map by key, not by position.
             # SETUP_SECTIONS includes TTS but the returning-user menu skips it,
-            # so positional indexing (choice - 3) would dispatch the wrong section.
-            section_key = RETURNING_USER_MENU_SECTION_KEYS[choice - 3]
+            # so positional indexing (choice - 2) would dispatch the wrong section.
+            section_key = RETURNING_USER_MENU_SECTION_KEYS[choice - 2]
             section = next((s for s in SETUP_SECTIONS if s[0] == section_key), None)
             if section:
                 _, label, func = section
@@ -2836,19 +2938,33 @@ def run_setup_wizard(args):
     _offer_launch_chat()
 
 
+def _resolve_hermes_chat_argv() -> Optional[list[str]]:
+    """Resolve argv for launching ``hermes chat`` in a fresh process."""
+    hermes_bin = shutil.which("hermes")
+    if hermes_bin:
+        return [hermes_bin, "chat"]
+
+    try:
+        if importlib.util.find_spec("hermes_cli") is not None:
+            return [sys.executable, "-m", "hermes_cli.main", "chat"]
+    except Exception:
+        pass
+
+    return None
+
+
 def _offer_launch_chat():
     """Prompt the user to jump straight into chat after setup."""
     print()
-    if prompt_yes_no("Launch hermes chat now?", True):
-        from hermes_cli.main import cmd_chat
-        from types import SimpleNamespace
-        cmd_chat(SimpleNamespace(
-            query=None, resume=None, continue_last=None, model=None,
-            provider=None, effort=None, skin=None, oneshot=False,
-            quiet=False, verbose=False, toolsets=None, skills=None,
-            yolo=False, source=None, worktree=False, checkpoints=False,
-            pass_session_id=False, max_turns=None,
-        ))
+    if not prompt_yes_no("Launch hermes chat now?", True):
+        return
+
+    chat_argv = _resolve_hermes_chat_argv()
+    if not chat_argv:
+        print_info("Could not relaunch Hermes automatically. Run 'hermes chat' manually.")
+        return
+
+    os.execvp(chat_argv[0], chat_argv)
 
 
 def _run_first_time_quick_setup(config: dict, hermes_home, is_existing: bool):

hermes_cli/skills_config.py

@@ -23,6 +23,7 @@ PLATFORMS = {
     "slack":    "💼 Slack",
     "whatsapp": "📱 WhatsApp",
     "signal":   "📡 Signal",
+    "bluebubbles": "💬 BlueBubbles",
     "email":    "📧 Email",
     "homeassistant": "🏠 Home Assistant",
     "mattermost": "💬 Mattermost",
@@ -30,6 +31,7 @@ PLATFORMS = {
     "dingtalk": "💬 DingTalk",
     "feishu": "🪽 Feishu",
     "wecom": "💬 WeCom",
+    "weixin": "💬 Weixin",
     "webhook": "🔗 Webhook",
 }
 

hermes_cli/skills_hub.py

@@ -151,7 +151,8 @@ def do_search(query: str, source: str = "all", limit: int = 10,
 
     auth = GitHubAuth()
     sources = create_source_router(auth)
-    results = unified_search(query, sources, source_filter=source, limit=limit)
+    with c.status("[bold]Searching registries..."):
+        results = unified_search(query, sources, source_filter=source, limit=limit)
 
     if not results:
         c.print("[dim]No skills found matching your query.[/]\n")
@@ -187,7 +188,7 @@ def do_browse(page: int = 1, page_size: int = 20, source: str = "all",
     Official skills are always shown first, regardless of source filter.
     """
     from tools.skills_hub import (
-        GitHubAuth, create_source_router,
+        GitHubAuth, create_source_router, parallel_search_sources,
     )
 
     # Clamp page_size to safe range
@@ -198,27 +199,23 @@ def do_browse(page: int = 1, page_size: int = 20, source: str = "all",
     auth = GitHubAuth()
     sources = create_source_router(auth)
 
-    # Collect results from all (or filtered) sources
-    # Use empty query to get everything; per-source limits prevent overload
+    # Collect results from all (or filtered) sources in parallel.
+    # Per-source limits are generous — parallelism + 30s timeout cap prevents hangs.
     _TRUST_RANK = {"builtin": 3, "trusted": 2, "community": 1}
-    _PER_SOURCE_LIMIT = {"official": 100, "skills-sh": 100, "well-known": 25, "github": 100, "clawhub": 50,
-                         "claude-marketplace": 50, "lobehub": 50}
+    _PER_SOURCE_LIMIT = {
+        "official": 200, "skills-sh": 200, "well-known": 50,
+        "github": 200, "clawhub": 500, "claude-marketplace": 100,
+        "lobehub": 500,
+    }
 
-    all_results: list = []
-    source_counts: dict = {}
-
-    for src in sources:
-        sid = src.source_id()
-        if source != "all" and sid != source and sid != "official":
-            # Always include official source for the "first" placement
-            continue
-        try:
-            limit = _PER_SOURCE_LIMIT.get(sid, 50)
-            results = src.search("", limit=limit)
-            source_counts[sid] = len(results)
-            all_results.extend(results)
-        except Exception:
-            continue
+    with c.status("[bold]Fetching skills from registries..."):
+        all_results, source_counts, timed_out = parallel_search_sources(
+            sources,
+            query="",
+            per_source_limits=_PER_SOURCE_LIMIT,
+            source_filter=source,
+            overall_timeout=30,
+        )
 
     if not all_results:
         c.print("[dim]No skills found in the Skills Hub.[/]\n")
@@ -252,8 +249,11 @@ def do_browse(page: int = 1, page_size: int = 20, source: str = "all",
 
     # Build header
     source_label = f"— {source}" if source != "all" else "— all sources"
+    loaded_label = f"{total} skills loaded"
+    if timed_out:
+        loaded_label += f", {len(timed_out)} source(s) still loading"
     c.print(f"\n[bold]Skills Hub — Browse {source_label}[/]"
-            f"  [dim]({total} skills, page {page}/{total_pages})[/]")
+            f"  [dim]({loaded_label}, page {page}/{total_pages})[/]")
     if official_count > 0 and page == 1:
         c.print(f"[bright_cyan]★ {official_count} official optional skill(s) from Nous Research[/]")
     c.print()
@@ -300,8 +300,11 @@ def do_browse(page: int = 1, page_size: int = 20, source: str = "all",
         parts = [f"{sid}: {ct}" for sid, ct in sorted(source_counts.items())]
         c.print(f"  [dim]Sources: {', '.join(parts)}[/]")
 
-    c.print("[dim]Use: hermes skills inspect <identifier> to preview, "
-            "hermes skills install <identifier> to install[/]\n")
+    if timed_out:
+        c.print(f"  [yellow]⚡ Slow sources skipped: {', '.join(timed_out)} "
+                f"— run again for cached results[/]")
+
+    c.print("[dim]Tip: 'hermes skills search <query>' searches deeper across all registries[/]\n")
 
 
 def do_install(identifier: str, category: str = "", force: bool = False,

hermes_cli/status.py

@@ -79,6 +79,9 @@ def _effective_provider_label() -> str:
     return provider_label(effective)
 
 
+from hermes_constants import is_termux as _is_termux
+
+
 def show_status(args):
     """Show status of all Hermes Agent components."""
     show_all = getattr(args, 'all', False)
@@ -302,6 +305,8 @@ def show_status(args):
         "DingTalk": ("DINGTALK_CLIENT_ID", None),
         "Feishu": ("FEISHU_APP_ID", "FEISHU_HOME_CHANNEL"),
         "WeCom": ("WECOM_BOT_ID", "WECOM_HOME_CHANNEL"),
+        "Weixin": ("WEIXIN_ACCOUNT_ID", "WEIXIN_HOME_CHANNEL"),
+        "BlueBubbles": ("BLUEBUBBLES_SERVER_URL", "BLUEBUBBLES_HOME_CHANNEL"),
     }
     
     for name, (token_var, home_var) in platforms.items():
@@ -324,7 +329,25 @@ def show_status(args):
     print()
     print(color("◆ Gateway Service", Colors.CYAN, Colors.BOLD))
     
-    if sys.platform.startswith('linux'):
+    if _is_termux():
+        try:
+            from hermes_cli.gateway import find_gateway_pids
+            gateway_pids = find_gateway_pids()
+        except Exception:
+            gateway_pids = []
+        is_running = bool(gateway_pids)
+        print(f"  Status:       {check_mark(is_running)} {'running' if is_running else 'stopped'}")
+        print("  Manager:      Termux / manual process")
+        if gateway_pids:
+            rendered = ", ".join(str(pid) for pid in gateway_pids[:3])
+            if len(gateway_pids) > 3:
+                rendered += ", ..."
+            print(f"  PID(s):       {rendered}")
+        else:
+            print("  Start with:   hermes gateway")
+            print("  Note:         Android may stop background jobs when Termux is suspended")
+
+    elif sys.platform.startswith('linux'):
         try:
             from hermes_cli.gateway import get_service_name
             _gw_svc = get_service_name()
@@ -338,7 +361,7 @@ def show_status(args):
                 timeout=5
             )
             is_active = result.stdout.strip() == "active"
-        except subprocess.TimeoutExpired:
+        except (FileNotFoundError, subprocess.TimeoutExpired):
             is_active = False
         print(f"  Status:       {check_mark(is_active)} {'running' if is_active else 'stopped'}")
         print("  Manager:      systemd (user)")

hermes_cli/tools_config.py

@@ -126,12 +126,14 @@ PLATFORMS = {
     "slack":    {"label": "💼 Slack",      "default_toolset": "hermes-slack"},
     "whatsapp": {"label": "📱 WhatsApp",   "default_toolset": "hermes-whatsapp"},
     "signal":   {"label": "📡 Signal",     "default_toolset": "hermes-signal"},
+    "bluebubbles": {"label": "💙 BlueBubbles", "default_toolset": "hermes-bluebubbles"},
     "homeassistant": {"label": "🏠 Home Assistant", "default_toolset": "hermes-homeassistant"},
     "email":    {"label": "📧 Email",      "default_toolset": "hermes-email"},
     "matrix":   {"label": "💬 Matrix",     "default_toolset": "hermes-matrix"},
  "dingtalk": {"label": "💬 DingTalk", "default_toolset": "hermes-dingtalk"},
     "feishu": {"label": "🪽 Feishu", "default_toolset": "hermes-feishu"},
     "wecom": {"label": "💬 WeCom", "default_toolset": "hermes-wecom"},
+    "weixin": {"label": "💬 Weixin", "default_toolset": "hermes-weixin"},
     "api_server": {"label": "🌐 API Server", "default_toolset": "hermes-api-server"},
     "mattermost": {"label": "💬 Mattermost", "default_toolset": "hermes-mattermost"},
     "webhook": {"label": "🔗 Webhook", "default_toolset": "hermes-webhook"},
@@ -179,6 +181,14 @@ TOOL_CATEGORIES = {
                 ],
                 "tts_provider": "elevenlabs",
             },
+            {
+                "name": "Mistral (Voxtral TTS)",
+                "tag": "Multilingual, native Opus, needs MISTRAL_API_KEY",
+                "env_vars": [
+                    {"key": "MISTRAL_API_KEY", "prompt": "Mistral API key", "url": "https://console.mistral.ai/"},
+                ],
+                "tts_provider": "mistral",
+            },
         ],
     },
     "web": {
@@ -499,6 +509,10 @@ def _get_platform_tools(
         default_ts = PLATFORMS[platform]["default_toolset"]
         toolset_names = [default_ts]
 
+    # YAML may parse bare numeric names (e.g. ``12306:``) as int.
+    # Normalise to str so downstream sorted() never mixes types.
+    toolset_names = [str(ts) for ts in toolset_names]
+
     configurable_keys = {ts_key for ts_key, _, _ in CONFIGURABLE_TOOLSETS}
 
     # If the saved list contains any configurable keys directly, the user
@@ -557,7 +571,7 @@ def _get_platform_tools(
     # Special sentinel: "no_mcp" in the toolset list disables all MCP servers.
     mcp_servers = config.get("mcp_servers") or {}
     enabled_mcp_servers = {
-        name
+        str(name)
         for name, server_cfg in mcp_servers.items()
         if isinstance(server_cfg, dict)
         and _parse_enabled_flag(server_cfg.get("enabled", True), default=True)
@@ -719,6 +733,8 @@ def _prompt_choice(question: str, choices: list, default: int = 0) -> int:
                     return
 
         curses.wrapper(_curses_menu)
+        from hermes_cli.curses_ui import flush_stdin
+        flush_stdin()
         return result_holder[0]
 
     except Exception:

hermes_cli/uninstall.py

@@ -6,6 +6,8 @@ Provides options for:
 - Keep data: Remove code but keep ~/.hermes/ (configs, sessions, logs)
 """
 
+import os
+import platform
 import shutil
 import subprocess
 from pathlib import Path
@@ -122,6 +124,10 @@ def uninstall_gateway_service():
     
     if platform.system() != "Linux":
         return False
+
+    prefix = os.getenv("PREFIX", "")
+    if os.getenv("TERMUX_VERSION") or "com.termux/files/usr" in prefix:
+        return False
     
     try:
         from hermes_cli.gateway import get_service_name

hermes_constants.py

@@ -17,6 +17,45 @@ def get_hermes_home() -> Path:
     return Path(os.getenv("HERMES_HOME", Path.home() / ".hermes"))
 
 
+def get_default_hermes_root() -> Path:
+    """Return the root Hermes directory for profile-level operations.
+
+    In standard deployments this is ``~/.hermes``.
+
+    In Docker or custom deployments where ``HERMES_HOME`` points outside
+    ``~/.hermes`` (e.g. ``/opt/data``), returns ``HERMES_HOME`` directly
+    — that IS the root.
+
+    In profile mode where ``HERMES_HOME`` is ``<root>/profiles/<name>``,
+    returns ``<root>`` so that ``profile list`` can see all profiles.
+    Works both for standard (``~/.hermes/profiles/coder``) and Docker
+    (``/opt/data/profiles/coder``) layouts.
+
+    Import-safe — no dependencies beyond stdlib.
+    """
+    native_home = Path.home() / ".hermes"
+    env_home = os.environ.get("HERMES_HOME", "")
+    if not env_home:
+        return native_home
+    env_path = Path(env_home)
+    try:
+        env_path.resolve().relative_to(native_home.resolve())
+        # HERMES_HOME is under ~/.hermes (normal or profile mode)
+        return native_home
+    except ValueError:
+        pass
+
+    # Docker / custom deployment.
+    # Check if this is a profile path: <root>/profiles/<name>
+    # If the immediate parent dir is named "profiles", the root is
+    # the grandparent — this covers Docker profiles correctly.
+    if env_path.parent.name == "profiles":
+        return env_path.parent.parent
+
+    # Not a profile path — HERMES_HOME itself is the root
+    return env_path
+
+
 def get_optional_skills_dir(default: Path | None = None) -> Path:
     """Return the optional-skills directory, honoring package-manager wrappers.
 
@@ -72,13 +111,39 @@ def display_hermes_home() -> str:
         return str(home)
 
 
-VALID_REASONING_EFFORTS = ("xhigh", "high", "medium", "low", "minimal")
+def get_subprocess_home() -> str | None:
+    """Return a per-profile HOME directory for subprocesses, or None.
+
+    When ``{HERMES_HOME}/home/`` exists on disk, subprocesses should use it
+    as ``HOME`` so system tools (git, ssh, gh, npm …) write their configs
+    inside the Hermes data directory instead of the OS-level ``/root`` or
+    ``~/``.  This provides:
+
+    * **Docker persistence** — tool configs land inside the persistent volume.
+    * **Profile isolation** — each profile gets its own git identity, SSH
+      keys, gh tokens, etc.
+
+    The Python process's own ``os.environ["HOME"]`` and ``Path.home()`` are
+    **never** modified — only subprocess environments should inject this value.
+    Activation is directory-based: if the ``home/`` subdirectory doesn't
+    exist, returns ``None`` and behavior is unchanged.
+    """
+    hermes_home = os.getenv("HERMES_HOME")
+    if not hermes_home:
+        return None
+    profile_home = os.path.join(hermes_home, "home")
+    if os.path.isdir(profile_home):
+        return profile_home
+    return None
+
+
+VALID_REASONING_EFFORTS = ("minimal", "low", "medium", "high", "xhigh")
 
 
 def parse_reasoning_effort(effort: str) -> dict | None:
     """Parse a reasoning effort level into a config dict.
 
-    Valid levels: "xhigh", "high", "medium", "low", "minimal", "none".
+    Valid levels: "none", "minimal", "low", "medium", "high", "xhigh".
     Returns None when the input is empty or unrecognized (caller uses default).
     Returns {"enabled": False} for "none".
     Returns {"enabled": True, "effort": <level>} for valid effort levels.
@@ -93,13 +158,40 @@ def parse_reasoning_effort(effort: str) -> dict | None:
     return None
 
 
+def is_termux() -> bool:
+    """Return True when running inside a Termux (Android) environment.
+
+    Checks ``TERMUX_VERSION`` (set by Termux) or the Termux-specific
+    ``PREFIX`` path.  Import-safe — no heavy deps.
+    """
+    prefix = os.getenv("PREFIX", "")
+    return bool(os.getenv("TERMUX_VERSION") or "com.termux/files/usr" in prefix)
+
+
+_wsl_detected: bool | None = None
+
+
+def is_wsl() -> bool:
+    """Return True when running inside WSL (Windows Subsystem for Linux).
+
+    Checks ``/proc/version`` for the ``microsoft`` marker that both WSL1
+    and WSL2 inject.  Result is cached for the process lifetime.
+    Import-safe — no heavy deps.
+    """
+    global _wsl_detected
+    if _wsl_detected is not None:
+        return _wsl_detected
+    try:
+        with open("/proc/version", "r") as f:
+            _wsl_detected = "microsoft" in f.read().lower()
+    except Exception:
+        _wsl_detected = False
+    return _wsl_detected
+
+
 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"
 
 AI_GATEWAY_BASE_URL = "https://ai-gateway.vercel.sh/v1"
-AI_GATEWAY_MODELS_URL = f"{AI_GATEWAY_BASE_URL}/models"
-AI_GATEWAY_CHAT_URL = f"{AI_GATEWAY_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_logging.py

@@ -13,6 +13,7 @@ secrets are never written to disk.
 """
 
 import logging
+import os
 from logging.handlers import RotatingFileHandler
 from pathlib import Path
 from typing import Optional
@@ -177,6 +178,38 @@ def setup_verbose_logging() -> None:
 # Internal helpers
 # ---------------------------------------------------------------------------
 
+class _ManagedRotatingFileHandler(RotatingFileHandler):
+    """RotatingFileHandler that ensures group-writable perms in managed mode.
+
+    In managed mode (NixOS), the stateDir uses setgid (2770) so new files
+    inherit the hermes group. However, both _open() (initial creation) and
+    doRollover() create files via open(), which uses the process umask —
+    typically 0022, producing 0644. This subclass applies chmod 0660 after
+    both operations so the gateway and interactive users can share log files.
+    """
+
+    def __init__(self, *args, **kwargs):
+        from hermes_cli.config import is_managed
+        self._managed = is_managed()
+        super().__init__(*args, **kwargs)
+
+    def _chmod_if_managed(self):
+        if self._managed:
+            try:
+                os.chmod(self.baseFilename, 0o660)
+            except OSError:
+                pass
+
+    def _open(self):
+        stream = super()._open()
+        self._chmod_if_managed()
+        return stream
+
+    def doRollover(self):
+        super().doRollover()
+        self._chmod_if_managed()
+
+
 def _add_rotating_handler(
     logger: logging.Logger,
     path: Path,
@@ -198,7 +231,7 @@ def _add_rotating_handler(
             return  # already attached
 
     path.parent.mkdir(parents=True, exist_ok=True)
-    handler = RotatingFileHandler(
+    handler = _ManagedRotatingFileHandler(
         str(path), maxBytes=max_bytes, backupCount=backup_count,
     )
     handler.setLevel(level)

hermes_state.py

@@ -520,72 +520,6 @@ class SessionDB:
             )
         self._execute_write(_do)
 
-    def set_token_counts(
-        self,
-        session_id: str,
-        input_tokens: int = 0,
-        output_tokens: int = 0,
-        model: str = None,
-        cache_read_tokens: int = 0,
-        cache_write_tokens: int = 0,
-        reasoning_tokens: int = 0,
-        estimated_cost_usd: Optional[float] = None,
-        actual_cost_usd: Optional[float] = None,
-        cost_status: Optional[str] = None,
-        cost_source: Optional[str] = None,
-        pricing_version: Optional[str] = None,
-        billing_provider: Optional[str] = None,
-        billing_base_url: Optional[str] = None,
-        billing_mode: Optional[str] = None,
-    ) -> None:
-        """Set token counters to absolute values (not increment).
-
-        Use this when the caller provides cumulative totals from a completed
-        conversation run (e.g. the gateway, where the cached agent's
-        session_prompt_tokens already reflects the running total).
-        """
-        def _do(conn):
-            conn.execute(
-                """UPDATE sessions SET
-                   input_tokens = ?,
-                   output_tokens = ?,
-                   cache_read_tokens = ?,
-                   cache_write_tokens = ?,
-                   reasoning_tokens = ?,
-                   estimated_cost_usd = ?,
-                   actual_cost_usd = CASE
-                       WHEN ? IS NULL THEN actual_cost_usd
-                       ELSE ?
-                   END,
-                   cost_status = COALESCE(?, cost_status),
-                   cost_source = COALESCE(?, cost_source),
-                   pricing_version = COALESCE(?, pricing_version),
-                   billing_provider = COALESCE(billing_provider, ?),
-                   billing_base_url = COALESCE(billing_base_url, ?),
-                   billing_mode = COALESCE(billing_mode, ?),
-                   model = COALESCE(model, ?)
-                   WHERE id = ?""",
-                (
-                    input_tokens,
-                    output_tokens,
-                    cache_read_tokens,
-                    cache_write_tokens,
-                    reasoning_tokens,
-                    estimated_cost_usd,
-                    actual_cost_usd,
-                    actual_cost_usd,
-                    cost_status,
-                    cost_source,
-                    pricing_version,
-                    billing_provider,
-                    billing_base_url,
-                    billing_mode,
-                    model,
-                    session_id,
-                ),
-            )
-        self._execute_write(_do)
-
     def get_session(self, session_id: str) -> Optional[Dict[str, Any]]:
         """Get a session by ID."""
         with self._lock:
@@ -944,7 +878,8 @@ class SessionDB:
                 try:
                     msg["tool_calls"] = json.loads(msg["tool_calls"])
                 except (json.JSONDecodeError, TypeError):
-                    pass
+                    logger.warning("Failed to deserialize tool_calls in get_messages, falling back to []")
+                    msg["tool_calls"] = []
             result.append(msg)
         return result
 
@@ -972,7 +907,8 @@ class SessionDB:
                 try:
                     msg["tool_calls"] = json.loads(row["tool_calls"])
                 except (json.JSONDecodeError, TypeError):
-                    pass
+                    logger.warning("Failed to deserialize tool_calls in conversation replay, falling back to []")
+                    msg["tool_calls"] = []
             # Restore reasoning fields on assistant messages so providers
             # that replay reasoning (OpenRouter, OpenAI, Nous) receive
             # coherent multi-turn reasoning context.
@@ -983,12 +919,14 @@ class SessionDB:
                     try:
                         msg["reasoning_details"] = json.loads(row["reasoning_details"])
                     except (json.JSONDecodeError, TypeError):
-                        pass
+                        logger.warning("Failed to deserialize reasoning_details, falling back to None")
+                        msg["reasoning_details"] = None
                 if row["codex_reasoning_items"]:
                     try:
                         msg["codex_reasoning_items"] = json.loads(row["codex_reasoning_items"])
                     except (json.JSONDecodeError, TypeError):
-                        pass
+                        logger.warning("Failed to deserialize codex_reasoning_items, falling back to None")
+                        msg["codex_reasoning_items"] = None
             messages.append(msg)
         return messages
 
@@ -1235,10 +1173,10 @@ class SessionDB:
         self._execute_write(_do)
 
     def delete_session(self, session_id: str) -> bool:
-        """Delete a session, its child sessions, and all their messages.
+        """Delete a session and all its messages.
 
-        Child sessions (subagent runs, compression continuations) are deleted
-        first to satisfy the ``parent_session_id`` foreign key constraint.
+        Child sessions are orphaned (parent_session_id set to NULL) rather
+        than cascade-deleted, so they remain accessible independently.
         Returns True if the session was found and deleted.
         """
         def _do(conn):
@@ -1247,15 +1185,12 @@ class SessionDB:
             )
             if cursor.fetchone()[0] == 0:
                 return False
-            # Delete child sessions first (FK constraint)
-            child_ids = [r[0] for r in conn.execute(
-                "SELECT id FROM sessions WHERE parent_session_id = ?",
+            # Orphan child sessions so FK constraint is satisfied
+            conn.execute(
+                "UPDATE sessions SET parent_session_id = NULL "
+                "WHERE parent_session_id = ?",
                 (session_id,),
-            ).fetchall()]
-            for cid in child_ids:
-                conn.execute("DELETE FROM messages WHERE session_id = ?", (cid,))
-                conn.execute("DELETE FROM sessions WHERE id = ?", (cid,))
-            # Delete the session itself
+            )
             conn.execute("DELETE FROM messages WHERE session_id = ?", (session_id,))
             conn.execute("DELETE FROM sessions WHERE id = ?", (session_id,))
             return True
@@ -1264,9 +1199,9 @@ class SessionDB:
     def prune_sessions(self, older_than_days: int = 90, source: str = None) -> int:
         """Delete sessions older than N days. Returns count of deleted sessions.
 
-        Only prunes ended sessions (not active ones).  Child sessions whose
-        parents are being pruned are deleted first to satisfy the
-        ``parent_session_id`` foreign key constraint.
+        Only prunes ended sessions (not active ones).  Child sessions outside
+        the prune window are orphaned (parent_session_id set to NULL) rather
+        than cascade-deleted.
         """
         cutoff = time.time() - (older_than_days * 86400)
 
@@ -1284,17 +1219,16 @@ class SessionDB:
                 )
             session_ids = set(row["id"] for row in cursor.fetchall())
 
-            # Delete children first whose parents are in the prune set
-            # (avoids FK constraint errors)
-            for sid in list(session_ids):
-                child_ids = [r[0] for r in conn.execute(
-                    "SELECT id FROM sessions WHERE parent_session_id = ?",
-                    (sid,),
-                ).fetchall()]
-                for cid in child_ids:
-                    conn.execute("DELETE FROM messages WHERE session_id = ?", (cid,))
-                    conn.execute("DELETE FROM sessions WHERE id = ?", (cid,))
-                    session_ids.discard(cid)  # don't double-delete
+            if not session_ids:
+                return 0
+
+            # Orphan any sessions whose parent is about to be deleted
+            placeholders = ",".join("?" * len(session_ids))
+            conn.execute(
+                f"UPDATE sessions SET parent_session_id = NULL "
+                f"WHERE parent_session_id IN ({placeholders})",
+                list(session_ids),
+            )
 
             for sid in session_ids:
                 conn.execute("DELETE FROM messages WHERE session_id = ?", (sid,))

hermes_time.py

@@ -89,13 +89,6 @@ def get_timezone() -> Optional[ZoneInfo]:
     return _cached_tz
 
 
-def get_timezone_name() -> str:
-    """Return the IANA name of the configured timezone, or empty string."""
-    if not _cache_resolved:
-        get_timezone()  # populates cache
-    return _cached_tz_name or ""
-
-
 def now() -> datetime:
     """
     Return the current time as a timezone-aware datetime.
@@ -110,9 +103,3 @@ def now() -> datetime:
     return datetime.now().astimezone()
 
 
-def reset_cache() -> None:
-    """Clear the cached timezone. Used by tests and after config changes."""
-    global _cached_tz, _cached_tz_name, _cache_resolved
-    _cached_tz = None
-    _cached_tz_name = None
-    _cache_resolved = False

nix/nixosModules.nix

@@ -560,22 +560,40 @@
       # ── Directories ───────────────────────────────────────────────────
       {
         systemd.tmpfiles.rules = [
-          "d ${cfg.stateDir}                0750 ${cfg.user} ${cfg.group} - -"
-          "d ${cfg.stateDir}/.hermes        0750 ${cfg.user} ${cfg.group} - -"
+          "d ${cfg.stateDir}                2770 ${cfg.user} ${cfg.group} - -"
+          "d ${cfg.stateDir}/.hermes        2770 ${cfg.user} ${cfg.group} - -"
+          "d ${cfg.stateDir}/.hermes/cron   2770 ${cfg.user} ${cfg.group} - -"
+          "d ${cfg.stateDir}/.hermes/sessions 2770 ${cfg.user} ${cfg.group} - -"
+          "d ${cfg.stateDir}/.hermes/logs   2770 ${cfg.user} ${cfg.group} - -"
+          "d ${cfg.stateDir}/.hermes/memories 2770 ${cfg.user} ${cfg.group} - -"
           "d ${cfg.stateDir}/home           0750 ${cfg.user} ${cfg.group} - -"
-          "d ${cfg.workingDirectory}         0750 ${cfg.user} ${cfg.group} - -"
+          "d ${cfg.workingDirectory}         2770 ${cfg.user} ${cfg.group} - -"
         ];
       }
 
       # ── Activation: link config + auth + documents ────────────────────
       {
-        system.activationScripts."hermes-agent-setup" = lib.stringAfter [ "users" "setupSecrets" ] ''
+        system.activationScripts."hermes-agent-setup" = lib.stringAfter ([ "users" ] ++ lib.optional (config.system.activationScripts ? setupSecrets) "setupSecrets") ''
           # Ensure directories exist (activation runs before tmpfiles)
           mkdir -p ${cfg.stateDir}/.hermes
           mkdir -p ${cfg.stateDir}/home
           mkdir -p ${cfg.workingDirectory}
           chown ${cfg.user}:${cfg.group} ${cfg.stateDir} ${cfg.stateDir}/.hermes ${cfg.stateDir}/home ${cfg.workingDirectory}
-          chmod 0750 ${cfg.stateDir} ${cfg.stateDir}/.hermes ${cfg.stateDir}/home ${cfg.workingDirectory}
+          chmod 2770 ${cfg.stateDir} ${cfg.stateDir}/.hermes ${cfg.workingDirectory}
+          chmod 0750 ${cfg.stateDir}/home
+
+          # Create subdirs, set setgid + group-writable, migrate existing files.
+          # Nix-managed files (config.yaml, .env, .managed) stay 0640/0644.
+          find ${cfg.stateDir}/.hermes -maxdepth 1 \
+            \( -name "*.db" -o -name "*.db-wal" -o -name "*.db-shm" -o -name "SOUL.md" \) \
+            -exec chmod g+rw {} + 2>/dev/null || true
+          for _subdir in cron sessions logs memories; do
+            mkdir -p "${cfg.stateDir}/.hermes/$_subdir"
+            chown ${cfg.user}:${cfg.group} "${cfg.stateDir}/.hermes/$_subdir"
+            chmod 2770 "${cfg.stateDir}/.hermes/$_subdir"
+            find "${cfg.stateDir}/.hermes/$_subdir" -type f \
+              -exec chmod g+rw {} + 2>/dev/null || true
+          done
 
           # Merge Nix settings into existing config.yaml.
           # Preserves user-added keys (skills, streaming, etc.); Nix keys win.
@@ -662,6 +680,10 @@ HERMES_NIX_ENV_EOF
             Restart = cfg.restart;
             RestartSec = cfg.restartSec;
 
+            # Shared-state: files created by the gateway should be group-writable
+            # so interactive users in the hermes group can read/write them.
+            UMask = "0007";
+
             # Hardening
             NoNewPrivileges = true;
             ProtectSystem = "strict";

nix/packages.nix

@@ -14,7 +14,7 @@
       };
 
       runtimeDeps = with pkgs; [
-        nodejs_20 ripgrep git openssh ffmpeg
+        nodejs_20 ripgrep git openssh ffmpeg tirith
       ];
 
       runtimePath = pkgs.lib.makeBinPath runtimeDeps;

optional-skills/migration/openclaw-migration/scripts/openclaw_to_hermes.py

@@ -1803,30 +1803,34 @@ class Migrator:
     def migrate_cron_jobs(self, config: Optional[Dict[str, Any]] = None) -> None:
         config = config or self.load_openclaw_config()
         cron = config.get("cron") or {}
-        if not cron:
-            self.record("cron-jobs", None, None, "skipped", "No cron configuration found")
-            return
-
-        # Archive the full cron config
-        if self.archive_dir and self.execute:
-            self.archive_dir.mkdir(parents=True, exist_ok=True)
-            dest = self.archive_dir / "cron-config.json"
-            dest.write_text(json.dumps(cron, indent=2, ensure_ascii=False) + "\n", encoding="utf-8")
-            self.record("cron-jobs", "openclaw.json cron.*", str(dest), "archived",
-                        "Cron config archived. Use 'hermes cron' to recreate jobs manually.")
-        else:
-            self.record("cron-jobs", "openclaw.json cron.*", "archive/cron-config.json",
-                        "archived", "Would archive cron config")
-
-        # Also check for cron store files
         cron_store = self.source_root / "cron"
+        found_any = False
+
+        # Archive the full cron config when present
+        if cron:
+            found_any = True
+            if self.archive_dir and self.execute:
+                self.archive_dir.mkdir(parents=True, exist_ok=True)
+                dest = self.archive_dir / "cron-config.json"
+                dest.write_text(json.dumps(cron, indent=2, ensure_ascii=False) + "\n", encoding="utf-8")
+                self.record("cron-jobs", "openclaw.json cron.*", str(dest), "archived",
+                            "Cron config archived. Use 'hermes cron' to recreate jobs manually.")
+            else:
+                self.record("cron-jobs", "openclaw.json cron.*", "archive/cron-config.json",
+                            "archived", "Would archive cron config")
+
+        # Also check for cron store files even when config.cron is missing
         if cron_store.is_dir() and self.archive_dir:
+            found_any = True
             dest_cron = self.archive_dir / "cron-store"
             if self.execute:
                 shutil.copytree(cron_store, dest_cron, dirs_exist_ok=True)
             self.record("cron-jobs", str(cron_store), str(dest_cron), "archived",
                         "Cron job store archived")
 
+        if not found_any:
+            self.record("cron-jobs", None, None, "skipped", "No cron configuration found")
+
     # ── Hooks ─────────────────────────────────────────────────
     def migrate_hooks_config(self, config: Optional[Dict[str, Any]] = None) -> None:
         config = config or self.load_openclaw_config()
@@ -2454,6 +2458,15 @@ class Migrator:
                 notes.append(f"- **{item.kind}**: {item.reason}")
             notes.append("")
 
+        has_cron_config_archive = any(
+            i.kind == "cron-jobs" and i.status == "archived" and i.destination and i.destination.endswith("cron-config.json")
+            for i in self.items
+        )
+        has_cron_store_archive = any(
+            i.kind == "cron-jobs" and i.status == "archived" and i.destination and i.destination.endswith("cron-store")
+            for i in self.items
+        )
+
         notes.extend([
             "## IMPORTANT: Archive the OpenClaw Directory",
             "",
@@ -2475,7 +2488,14 @@ class Migrator:
             "- Run `hermes claw cleanup` to archive the OpenClaw directory (prevents state confusion)",
             "- Run `hermes setup` to configure any remaining settings",
             "- Run `hermes mcp list` to verify MCP servers were imported correctly",
-            "- Run `hermes cron` to recreate scheduled tasks (see archive/cron-config.json)",
+        ])
+
+        if has_cron_config_archive:
+            notes.append("- Run `hermes cron` to recreate scheduled tasks (see archive/cron-config.json)")
+        elif has_cron_store_archive:
+            notes.append("- Run `hermes cron` to recreate scheduled tasks (see archived cron-store)")
+
+        notes.extend([
             "- Run `hermes gateway install` if you need the gateway service",
             "- Review `~/.hermes/config.yaml` for any adjustments",
             "",

plugins/context_engine/__init__.py

@@ -0,0 +1,219 @@
+"""Context engine plugin discovery.
+
+Scans ``plugins/context_engine/<name>/`` directories for context engine
+plugins.  Each subdirectory must contain ``__init__.py`` with a class
+implementing the ContextEngine ABC.
+
+Context engines are separate from the general plugin system — they live
+in the repo and are always available without user installation.  Only ONE
+can be active at a time, selected via ``context.engine`` in config.yaml.
+The default engine is ``"compressor"`` (the built-in ContextCompressor).
+
+Usage:
+    from plugins.context_engine import discover_context_engines, load_context_engine
+
+    available = discover_context_engines()   # [(name, desc, available), ...]
+    engine = load_context_engine("lcm")      # ContextEngine instance
+"""
+
+from __future__ import annotations
+
+import importlib
+import importlib.util
+import logging
+import sys
+from pathlib import Path
+from typing import List, Optional, Tuple
+
+logger = logging.getLogger(__name__)
+
+_CONTEXT_ENGINE_PLUGINS_DIR = Path(__file__).parent
+
+
+def discover_context_engines() -> List[Tuple[str, str, bool]]:
+    """Scan plugins/context_engine/ for available engines.
+
+    Returns list of (name, description, is_available) tuples.
+    Does NOT import the engines — just reads plugin.yaml for metadata
+    and does a lightweight availability check.
+    """
+    results = []
+    if not _CONTEXT_ENGINE_PLUGINS_DIR.is_dir():
+        return results
+
+    for child in sorted(_CONTEXT_ENGINE_PLUGINS_DIR.iterdir()):
+        if not child.is_dir() or child.name.startswith(("_", ".")):
+            continue
+        init_file = child / "__init__.py"
+        if not init_file.exists():
+            continue
+
+        # Read description from plugin.yaml if available
+        desc = ""
+        yaml_file = child / "plugin.yaml"
+        if yaml_file.exists():
+            try:
+                import yaml
+                with open(yaml_file) as f:
+                    meta = yaml.safe_load(f) or {}
+                desc = meta.get("description", "")
+            except Exception:
+                pass
+
+        # Quick availability check — try loading and calling is_available()
+        available = True
+        try:
+            engine = _load_engine_from_dir(child)
+            if engine is None:
+                available = False
+            elif hasattr(engine, "is_available"):
+                available = engine.is_available()
+        except Exception:
+            available = False
+
+        results.append((child.name, desc, available))
+
+    return results
+
+
+def load_context_engine(name: str) -> Optional["ContextEngine"]:
+    """Load and return a ContextEngine instance by name.
+
+    Returns None if the engine is not found or fails to load.
+    """
+    engine_dir = _CONTEXT_ENGINE_PLUGINS_DIR / name
+    if not engine_dir.is_dir():
+        logger.debug("Context engine '%s' not found in %s", name, _CONTEXT_ENGINE_PLUGINS_DIR)
+        return None
+
+    try:
+        engine = _load_engine_from_dir(engine_dir)
+        if engine:
+            return engine
+        logger.warning("Context engine '%s' loaded but no engine instance found", name)
+        return None
+    except Exception as e:
+        logger.warning("Failed to load context engine '%s': %s", name, e)
+        return None
+
+
+def _load_engine_from_dir(engine_dir: Path) -> Optional["ContextEngine"]:
+    """Import an engine module and extract the ContextEngine instance.
+
+    The module must have either:
+    - A register(ctx) function (plugin-style) — we simulate a ctx
+    - A top-level class that extends ContextEngine — we instantiate it
+    """
+    name = engine_dir.name
+    module_name = f"plugins.context_engine.{name}"
+    init_file = engine_dir / "__init__.py"
+
+    if not init_file.exists():
+        return None
+
+    # Check if already loaded
+    if module_name in sys.modules:
+        mod = sys.modules[module_name]
+    else:
+        # Handle relative imports within the plugin
+        # First ensure the parent packages are registered
+        for parent in ("plugins", "plugins.context_engine"):
+            if parent not in sys.modules:
+                parent_path = Path(__file__).parent
+                if parent == "plugins":
+                    parent_path = parent_path.parent
+                parent_init = parent_path / "__init__.py"
+                if parent_init.exists():
+                    spec = importlib.util.spec_from_file_location(
+                        parent, str(parent_init),
+                        submodule_search_locations=[str(parent_path)]
+                    )
+                    if spec:
+                        parent_mod = importlib.util.module_from_spec(spec)
+                        sys.modules[parent] = parent_mod
+                        try:
+                            spec.loader.exec_module(parent_mod)
+                        except Exception:
+                            pass
+
+        # Now load the engine module
+        spec = importlib.util.spec_from_file_location(
+            module_name, str(init_file),
+            submodule_search_locations=[str(engine_dir)]
+        )
+        if not spec:
+            return None
+
+        mod = importlib.util.module_from_spec(spec)
+        sys.modules[module_name] = mod
+
+        # Register submodules so relative imports work
+        for sub_file in engine_dir.glob("*.py"):
+            if sub_file.name == "__init__.py":
+                continue
+            sub_name = sub_file.stem
+            full_sub_name = f"{module_name}.{sub_name}"
+            if full_sub_name not in sys.modules:
+                sub_spec = importlib.util.spec_from_file_location(
+                    full_sub_name, str(sub_file)
+                )
+                if sub_spec:
+                    sub_mod = importlib.util.module_from_spec(sub_spec)
+                    sys.modules[full_sub_name] = sub_mod
+                    try:
+                        sub_spec.loader.exec_module(sub_mod)
+                    except Exception as e:
+                        logger.debug("Failed to load submodule %s: %s", full_sub_name, e)
+
+        try:
+            spec.loader.exec_module(mod)
+        except Exception as e:
+            logger.debug("Failed to exec_module %s: %s", module_name, e)
+            sys.modules.pop(module_name, None)
+            return None
+
+    # Try register(ctx) pattern first (how plugins are written)
+    if hasattr(mod, "register"):
+        collector = _EngineCollector()
+        try:
+            mod.register(collector)
+            if collector.engine:
+                return collector.engine
+        except Exception as e:
+            logger.debug("register() failed for %s: %s", name, e)
+
+    # Fallback: find a ContextEngine subclass and instantiate it
+    from agent.context_engine import ContextEngine
+    for attr_name in dir(mod):
+        attr = getattr(mod, attr_name, None)
+        if (isinstance(attr, type) and issubclass(attr, ContextEngine)
+                and attr is not ContextEngine):
+            try:
+                return attr()
+            except Exception:
+                pass
+
+    return None
+
+
+class _EngineCollector:
+    """Fake plugin context that captures register_context_engine calls."""
+
+    def __init__(self):
+        self.engine = None
+
+    def register_context_engine(self, engine):
+        self.engine = engine
+
+    # No-op for other registration methods
+    def register_tool(self, *args, **kwargs):
+        pass
+
+    def register_hook(self, *args, **kwargs):
+        pass
+
+    def register_cli_command(self, *args, **kwargs):
+        pass
+
+    def register_memory_provider(self, *args, **kwargs):
+        pass

plugins/memory/hindsight/README.md

@@ -1,11 +1,12 @@
 # Hindsight Memory Provider
 
-Long-term memory with knowledge graph, entity resolution, and multi-strategy retrieval. Supports cloud and local (embedded) modes.
+Long-term memory with knowledge graph, entity resolution, and multi-strategy retrieval. Supports cloud, local embedded, and local external modes.
 
 ## Requirements
 
 - **Cloud:** API key from [ui.hindsight.vectorize.io](https://ui.hindsight.vectorize.io)
-- **Local:** API key for a supported LLM provider (OpenAI, Anthropic, Gemini, Groq, MiniMax, or Ollama). Embeddings and reranking run locally — no additional API keys needed.
+- **Local Embedded:** API key for a supported LLM provider (OpenAI, Anthropic, Gemini, Groq, OpenRouter, MiniMax, Ollama, or any OpenAI-compatible endpoint). Embeddings and reranking run locally — no additional API keys needed.
+- **Local External:** A running Hindsight instance (Docker or self-hosted) reachable over HTTP.
 
 ## Setup
 
@@ -21,17 +22,28 @@ hermes config set memory.provider hindsight
 echo "HINDSIGHT_API_KEY=your-key" >> ~/.hermes/.env
 ```
 
-### Cloud Mode
+### Cloud
 
 Connects to the Hindsight Cloud API. Requires an API key from [ui.hindsight.vectorize.io](https://ui.hindsight.vectorize.io).
 
-### Local Mode
+### Local Embedded
 
-Runs an embedded Hindsight server with built-in PostgreSQL. Requires an LLM API key (e.g. Groq, OpenAI, Anthropic) for memory extraction and synthesis. The daemon starts automatically in the background on first use and stops after 5 minutes of inactivity.
+Hermes spins up a local Hindsight daemon with built-in PostgreSQL. Requires an LLM API key for memory extraction and synthesis. The daemon starts automatically in the background on first use and stops after 5 minutes of inactivity.
+
+Supports any OpenAI-compatible LLM endpoint (llama.cpp, vLLM, LM Studio, etc.) — pick `openai_compatible` as the provider and enter the base URL.
 
 Daemon startup logs: `~/.hermes/logs/hindsight-embed.log`
 Daemon runtime logs: `~/.hindsight/profiles/<profile>.log`
 
+To open the Hindsight web UI (local embedded mode only):
+```bash
+hindsight-embed -p hermes ui start
+```
+
+### Local External
+
+Points the plugin at an existing Hindsight instance you're already running (Docker, self-hosted, etc.). No daemon management — just a URL and an optional API key.
+
 ## Config
 
 Config file: `~/.hermes/hindsight/config.json`
@@ -40,40 +52,58 @@ Config file: `~/.hermes/hindsight/config.json`
 
 | Key | Default | Description |
 |-----|---------|-------------|
-| `mode` | `cloud` | `cloud` or `local` |
-| `api_url` | `https://api.hindsight.vectorize.io` | API URL (cloud mode) |
-| `api_url` | `http://localhost:8888` | API URL (local mode, unused — daemon manages its own port) |
+| `mode` | `cloud` | `cloud`, `local_embedded`, or `local_external` |
+| `api_url` | `https://api.hindsight.vectorize.io` | API URL (cloud and local_external modes) |
 
-### Memory
+### Memory Bank
 
 | Key | Default | Description |
 |-----|---------|-------------|
 | `bank_id` | `hermes` | Memory bank name |
-| `budget` | `mid` | Recall thoroughness: `low` / `mid` / `high` |
+| `bank_mission` | — | Reflect mission (identity/framing for reflect reasoning). Applied via Banks API. |
+| `bank_retain_mission` | — | Retain mission (steers what gets extracted). Applied via Banks API. |
+
+### Recall
+
+| Key | Default | Description |
+|-----|---------|-------------|
+| `recall_budget` | `mid` | Recall thoroughness: `low` / `mid` / `high` |
+| `recall_prefetch_method` | `recall` | Auto-recall method: `recall` (raw facts) or `reflect` (LLM synthesis) |
+| `recall_max_tokens` | `4096` | Maximum tokens for recall results |
+| `recall_max_input_chars` | `800` | Maximum input query length for auto-recall |
+| `recall_prompt_preamble` | — | Custom preamble for recalled memories in context |
+| `recall_tags` | — | Tags to filter when searching memories |
+| `recall_tags_match` | `any` | Tag matching mode: `any` / `all` / `any_strict` / `all_strict` |
+| `auto_recall` | `true` | Automatically recall memories before each turn |
+
+### Retain
+
+| Key | Default | Description |
+|-----|---------|-------------|
+| `auto_retain` | `true` | Automatically retain conversation turns |
+| `retain_async` | `true` | Process retain asynchronously on the Hindsight server |
+| `retain_every_n_turns` | `1` | Retain every N turns (1 = every turn) |
+| `retain_context` | `conversation between Hermes Agent and the User` | Context label for retained memories |
+| `tags` | — | Tags applied when storing memories |
 
 ### Integration
 
 | Key | Default | Description |
 |-----|---------|-------------|
 | `memory_mode` | `hybrid` | How memories are integrated into the agent |
-| `prefetch_method` | `recall` | Method for automatic context injection |
 
 **memory_mode:**
 - `hybrid` — automatic context injection + tools available to the LLM
 - `context` — automatic injection only, no tools exposed
 - `tools` — tools only, no automatic injection
 
-**prefetch_method:**
-- `recall` — injects raw memory facts (fast)
-- `reflect` — injects LLM-synthesized summary (slower, more coherent)
-
-### Local Mode LLM
+### Local Embedded LLM
 
 | Key | Default | Description |
 |-----|---------|-------------|
-| `llm_provider` | `openai` | LLM provider: `openai`, `anthropic`, `gemini`, `groq`, `minimax`, `ollama` |
-| `llm_model` | per-provider | Model name (e.g. `gpt-4o-mini`, `openai/gpt-oss-120b`) |
-| `llm_base_url` | — | LLM Base URL override (e.g. `https://openrouter.ai/api/v1`) |
+| `llm_provider` | `openai` | `openai`, `anthropic`, `gemini`, `groq`, `openrouter`, `minimax`, `ollama`, `lmstudio`, `openai_compatible` |
+| `llm_model` | per-provider | Model name (e.g. `gpt-4o-mini`, `qwen/qwen3.5-9b`) |
+| `llm_base_url` | — | Endpoint URL for `openai_compatible` (e.g. `http://192.168.1.10:8080/v1`) |
 
 The LLM API key is stored in `~/.hermes/.env` as `HINDSIGHT_LLM_API_KEY`.
 
@@ -97,4 +127,8 @@ Available in `hybrid` and `tools` memory modes:
 | `HINDSIGHT_API_URL` | Override API endpoint |
 | `HINDSIGHT_BANK_ID` | Override bank name |
 | `HINDSIGHT_BUDGET` | Override recall budget |
-| `HINDSIGHT_MODE` | Override mode (`cloud` / `local`) |
+| `HINDSIGHT_MODE` | Override mode (`cloud`, `local_embedded`, `local_external`) |
+
+## Client Version
+
+Requires `hindsight-client >= 0.4.22`. The plugin auto-upgrades on session start if an older version is detected.

plugins/memory/hindsight/__init__.py

@@ -28,21 +28,25 @@ from hermes_constants import get_hermes_home
 from typing import Any, Dict, List
 
 from agent.memory_provider import MemoryProvider
+from hermes_constants import get_hermes_home
 from tools.registry import tool_error
 
 logger = logging.getLogger(__name__)
 
 _DEFAULT_API_URL = "https://api.hindsight.vectorize.io"
 _DEFAULT_LOCAL_URL = "http://localhost:8888"
+_MIN_CLIENT_VERSION = "0.4.22"
 _VALID_BUDGETS = {"low", "mid", "high"}
 _PROVIDER_DEFAULT_MODELS = {
     "openai": "gpt-4o-mini",
     "anthropic": "claude-haiku-4-5",
     "gemini": "gemini-2.5-flash",
     "groq": "openai/gpt-oss-120b",
+    "openrouter": "qwen/qwen3.5-9b",
     "minimax": "MiniMax-M2.7",
     "ollama": "gemma3:12b",
     "lmstudio": "local-model",
+    "openai_compatible": "your-model-name",
 }
 
 
@@ -188,6 +192,7 @@ class HindsightMemoryProvider(MemoryProvider):
         self._bank_id = "hermes"
         self._budget = "mid"
         self._mode = "cloud"
+        self._llm_base_url = ""
         self._memory_mode = "hybrid"  # "context", "tools", or "hybrid"
         self._prefetch_method = "recall"  # "recall" or "reflect"
         self._client = None
@@ -195,6 +200,31 @@ class HindsightMemoryProvider(MemoryProvider):
         self._prefetch_lock = threading.Lock()
         self._prefetch_thread = None
         self._sync_thread = None
+        self._session_id = ""
+
+        # Tags
+        self._tags: list[str] | None = None
+        self._recall_tags: list[str] | None = None
+        self._recall_tags_match = "any"
+
+        # Retain controls
+        self._auto_retain = True
+        self._retain_every_n_turns = 1
+        self._retain_context = "conversation between Hermes Agent and the User"
+        self._turn_counter = 0
+        self._session_turns: list[str] = []  # accumulates ALL turns for the session
+
+        # Recall controls
+        self._auto_recall = True
+        self._recall_max_tokens = 4096
+        self._recall_types: list[str] | None = None
+        self._recall_prompt_preamble = ""
+        self._recall_max_input_chars = 800
+
+        # Bank
+        self._bank_mission = ""
+        self._bank_retain_mission: str | None = None
+        self._retain_async = True
 
     @property
     def name(self) -> str:
@@ -204,7 +234,7 @@ class HindsightMemoryProvider(MemoryProvider):
         try:
             cfg = _load_config()
             mode = cfg.get("mode", "cloud")
-            if mode == "local":
+            if mode in ("local", "local_embedded", "local_external"):
                 return True
             has_key = bool(cfg.get("apiKey") or os.environ.get("HINDSIGHT_API_KEY", ""))
             has_url = bool(cfg.get("api_url") or os.environ.get("HINDSIGHT_API_URL", ""))
@@ -228,73 +258,306 @@ class HindsightMemoryProvider(MemoryProvider):
         existing.update(values)
         config_path.write_text(json.dumps(existing, indent=2))
 
+    def post_setup(self, hermes_home: str, config: dict) -> None:
+        """Custom setup wizard — installs only the deps needed for the selected mode."""
+        import getpass
+        import subprocess
+        import shutil
+        import sys
+        from pathlib import Path
+
+        from hermes_cli.config import save_config
+
+        from hermes_cli.memory_setup import _curses_select
+
+        print("\n  Configuring Hindsight memory:\n")
+
+        # Step 1: Mode selection
+        mode_items = [
+            ("Cloud", "Hindsight Cloud API (lightweight, just needs an API key)"),
+            ("Local Embedded", "Run Hindsight locally (downloads ~200MB, needs LLM key)"),
+            ("Local External", "Connect to an existing Hindsight instance"),
+        ]
+        mode_idx = _curses_select("  Select mode", mode_items, default=0)
+        mode = ["cloud", "local_embedded", "local_external"][mode_idx]
+
+        provider_config: dict = {"mode": mode}
+        env_writes: dict = {}
+
+        # Step 2: Install/upgrade deps for selected mode
+        _MIN_CLIENT_VERSION = "0.4.22"
+        cloud_dep = f"hindsight-client>={_MIN_CLIENT_VERSION}"
+        local_dep = "hindsight-all"
+        if mode == "local_embedded":
+            deps_to_install = [local_dep]
+        elif mode == "local_external":
+            deps_to_install = [cloud_dep]
+        else:
+            deps_to_install = [cloud_dep]
+
+        print(f"\n  Checking dependencies...")
+        uv_path = shutil.which("uv")
+        if not uv_path:
+            print("  ⚠ uv not found — install it: curl -LsSf https://astral.sh/uv/install.sh | sh")
+            print(f"  Then run manually: uv pip install --python {sys.executable} {' '.join(deps_to_install)}")
+        else:
+            try:
+                subprocess.run(
+                    [uv_path, "pip", "install", "--python", sys.executable, "--quiet", "--upgrade"] + deps_to_install,
+                    check=True, timeout=120, capture_output=True,
+                )
+                print(f"  ✓ Dependencies up to date")
+            except Exception as e:
+                print(f"  ⚠ Install failed: {e}")
+                print(f"  Run manually: uv pip install --python {sys.executable} {' '.join(deps_to_install)}")
+
+        # Step 3: Mode-specific config
+        if mode == "cloud":
+            print(f"\n  Get your API key at https://ui.hindsight.vectorize.io\n")
+            existing_key = os.environ.get("HINDSIGHT_API_KEY", "")
+            if existing_key:
+                masked = f"...{existing_key[-4:]}" if len(existing_key) > 4 else "set"
+                sys.stdout.write(f"  API key (current: {masked}, blank to keep): ")
+                sys.stdout.flush()
+                api_key = getpass.getpass(prompt="") if sys.stdin.isatty() else sys.stdin.readline().strip()
+            else:
+                sys.stdout.write("  API key: ")
+                sys.stdout.flush()
+                api_key = getpass.getpass(prompt="") if sys.stdin.isatty() else sys.stdin.readline().strip()
+            if api_key:
+                env_writes["HINDSIGHT_API_KEY"] = api_key
+
+            val = input(f"  API URL [{_DEFAULT_API_URL}]: ").strip()
+            if val:
+                provider_config["api_url"] = val
+
+        elif mode == "local_external":
+            val = input(f"  Hindsight API URL [{_DEFAULT_LOCAL_URL}]: ").strip()
+            provider_config["api_url"] = val or _DEFAULT_LOCAL_URL
+
+            sys.stdout.write("  API key (optional, blank to skip): ")
+            sys.stdout.flush()
+            api_key = getpass.getpass(prompt="") if sys.stdin.isatty() else sys.stdin.readline().strip()
+            if api_key:
+                env_writes["HINDSIGHT_API_KEY"] = api_key
+
+        else:  # local_embedded
+            providers_list = list(_PROVIDER_DEFAULT_MODELS.keys())
+            llm_items = [
+                (p, f"default model: {_PROVIDER_DEFAULT_MODELS[p]}")
+                for p in providers_list
+            ]
+            llm_idx = _curses_select("  Select LLM provider", llm_items, default=0)
+            llm_provider = providers_list[llm_idx]
+
+            provider_config["llm_provider"] = llm_provider
+
+            if llm_provider == "openai_compatible":
+                val = input("  LLM endpoint URL (e.g. http://192.168.1.10:8080/v1): ").strip()
+                if val:
+                    provider_config["llm_base_url"] = val
+            elif llm_provider == "openrouter":
+                provider_config["llm_base_url"] = "https://openrouter.ai/api/v1"
+
+            default_model = _PROVIDER_DEFAULT_MODELS.get(llm_provider, "gpt-4o-mini")
+            val = input(f"  LLM model [{default_model}]: ").strip()
+            provider_config["llm_model"] = val or default_model
+
+            sys.stdout.write("  LLM API key: ")
+            sys.stdout.flush()
+            llm_key = getpass.getpass(prompt="") if sys.stdin.isatty() else sys.stdin.readline().strip()
+            if llm_key:
+                env_writes["HINDSIGHT_LLM_API_KEY"] = llm_key
+
+        # Step 4: Save everything
+        provider_config["bank_id"] = "hermes"
+        provider_config["recall_budget"] = "mid"
+        bank_id = "hermes"
+        config["memory"]["provider"] = "hindsight"
+        save_config(config)
+
+        self.save_config(provider_config, hermes_home)
+
+        if env_writes:
+            env_path = Path(hermes_home) / ".env"
+            env_path.parent.mkdir(parents=True, exist_ok=True)
+            existing_lines = []
+            if env_path.exists():
+                existing_lines = env_path.read_text().splitlines()
+            updated_keys = set()
+            new_lines = []
+            for line in existing_lines:
+                key_match = line.split("=", 1)[0].strip() if "=" in line and not line.startswith("#") else None
+                if key_match and key_match in env_writes:
+                    new_lines.append(f"{key_match}={env_writes[key_match]}")
+                    updated_keys.add(key_match)
+                else:
+                    new_lines.append(line)
+            for k, v in env_writes.items():
+                if k not in updated_keys:
+                    new_lines.append(f"{k}={v}")
+            env_path.write_text("\n".join(new_lines) + "\n")
+
+        print(f"\n  ✓ Hindsight memory configured ({mode} mode)")
+        if env_writes:
+            print(f"  API keys saved to .env")
+        print(f"\n  Start a new session to activate.\n")
+
     def get_config_schema(self):
         return [
-            {"key": "mode", "description": "Cloud API or local embedded mode", "default": "cloud", "choices": ["cloud", "local"]},
-            {"key": "api_url", "description": "Hindsight API URL", "default": _DEFAULT_API_URL, "when": {"mode": "cloud"}},
+            {"key": "mode", "description": "Connection mode", "default": "cloud", "choices": ["cloud", "local_embedded", "local_external"]},
+            # Cloud mode
+            {"key": "api_url", "description": "Hindsight Cloud API URL", "default": _DEFAULT_API_URL, "when": {"mode": "cloud"}},
             {"key": "api_key", "description": "Hindsight Cloud API key", "secret": True, "env_var": "HINDSIGHT_API_KEY", "url": "https://ui.hindsight.vectorize.io", "when": {"mode": "cloud"}},
-            {"key": "llm_provider", "description": "LLM provider for local mode", "default": "openai", "choices": ["openai", "anthropic", "gemini", "groq", "minimax", "ollama"], "when": {"mode": "local"}},
-            {"key": "llm_api_key", "description": "LLM API key for local Hindsight", "secret": True, "env_var": "HINDSIGHT_LLM_API_KEY", "when": {"mode": "local"}},
-            {"key": "llm_base_url", "description": "LLM Base URL (e.g. for OpenRouter)", "default": "", "env_var": "HINDSIGHT_API_LLM_BASE_URL", "when": {"mode": "local"}},
-            {"key": "llm_model", "description": "LLM model for local mode", "default": "gpt-4o-mini", "default_from": {"field": "llm_provider", "map": _PROVIDER_DEFAULT_MODELS}, "when": {"mode": "local"}},
+            # Local external mode
+            {"key": "api_url", "description": "Hindsight API URL", "default": _DEFAULT_LOCAL_URL, "when": {"mode": "local_external"}},
+            {"key": "api_key", "description": "API key (optional)", "secret": True, "env_var": "HINDSIGHT_API_KEY", "when": {"mode": "local_external"}},
+            # Local embedded mode
+            {"key": "llm_provider", "description": "LLM provider", "default": "openai", "choices": ["openai", "anthropic", "gemini", "groq", "openrouter", "minimax", "ollama", "lmstudio", "openai_compatible"], "when": {"mode": "local_embedded"}},
+            {"key": "llm_base_url", "description": "Endpoint URL (e.g. http://192.168.1.10:8080/v1)", "default": "", "when": {"mode": "local_embedded", "llm_provider": "openai_compatible"}},
+            {"key": "llm_api_key", "description": "LLM API key (optional for openai_compatible)", "secret": True, "env_var": "HINDSIGHT_LLM_API_KEY", "when": {"mode": "local_embedded"}},
+            {"key": "llm_model", "description": "LLM model", "default": "gpt-4o-mini", "default_from": {"field": "llm_provider", "map": _PROVIDER_DEFAULT_MODELS}, "when": {"mode": "local_embedded"}},
             {"key": "bank_id", "description": "Memory bank name", "default": "hermes"},
-            {"key": "budget", "description": "Recall thoroughness", "default": "mid", "choices": ["low", "mid", "high"]},
+            {"key": "bank_mission", "description": "Mission/purpose description for the memory bank"},
+            {"key": "bank_retain_mission", "description": "Custom extraction prompt for memory retention"},
+            {"key": "recall_budget", "description": "Recall thoroughness", "default": "mid", "choices": ["low", "mid", "high"]},
             {"key": "memory_mode", "description": "Memory integration mode", "default": "hybrid", "choices": ["hybrid", "context", "tools"]},
-            {"key": "prefetch_method", "description": "Auto-recall method", "default": "recall", "choices": ["recall", "reflect"]},
+            {"key": "recall_prefetch_method", "description": "Auto-recall method", "default": "recall", "choices": ["recall", "reflect"]},
+            {"key": "tags", "description": "Tags applied when storing memories (comma-separated)", "default": ""},
+            {"key": "recall_tags", "description": "Tags to filter when searching memories (comma-separated)", "default": ""},
+            {"key": "recall_tags_match", "description": "Tag matching mode for recall", "default": "any", "choices": ["any", "all", "any_strict", "all_strict"]},
+            {"key": "auto_recall", "description": "Automatically recall memories before each turn", "default": True},
+            {"key": "auto_retain", "description": "Automatically retain conversation turns", "default": True},
+            {"key": "retain_every_n_turns", "description": "Retain every N turns (1 = every turn)", "default": 1},
+            {"key": "retain_async","description": "Process retain asynchronously on the Hindsight server", "default": True},
+            {"key": "retain_context", "description": "Context label for retained memories", "default": "conversation between Hermes Agent and the User"},
+            {"key": "recall_max_tokens", "description": "Maximum tokens for recall results", "default": 4096},
+            {"key": "recall_max_input_chars", "description": "Maximum input query length for auto-recall", "default": 800},
+            {"key": "recall_prompt_preamble", "description": "Custom preamble for recalled memories in context"},
         ]
 
     def _get_client(self):
         """Return the cached Hindsight client (created once, reused)."""
         if self._client is None:
-            if self._mode == "local":
+            if self._mode == "local_embedded":
                 from hindsight import HindsightEmbedded
-                # Disable __del__ on the class to prevent "attached to a
-                # different loop" errors during GC — we handle cleanup in
-                # shutdown() instead.
                 HindsightEmbedded.__del__ = lambda self: None
+                llm_provider = self._config.get("llm_provider", "")
+                if llm_provider in ("openai_compatible", "openrouter"):
+                    llm_provider = "openai"
+                logger.debug("Creating HindsightEmbedded client (profile=%s, provider=%s)",
+                             self._config.get("profile", "hermes"), llm_provider)
                 kwargs = dict(
                     profile=self._config.get("profile", "hermes"),
-                    llm_provider=self._config.get("llm_provider", ""),
-                    llm_api_key=self._config.get("llm_api_key") or os.environ.get("HINDSIGHT_LLM_API_KEY", ""),
+                    llm_provider=llm_provider,
+                    llm_api_key=self._config.get("llmApiKey") or self._config.get("llm_api_key") or os.environ.get("HINDSIGHT_LLM_API_KEY", ""),
                     llm_model=self._config.get("llm_model", ""),
                 )
-                base_url = self._config.get("llm_base_url") or os.environ.get("HINDSIGHT_API_LLM_BASE_URL", "")
-                if base_url:
-                    kwargs["llm_base_url"] = base_url
+                if self._llm_base_url:
+                    kwargs["llm_base_url"] = self._llm_base_url
                 self._client = HindsightEmbedded(**kwargs)
             else:
                 from hindsight_client import Hindsight
                 kwargs = {"base_url": self._api_url, "timeout": 30.0}
                 if self._api_key:
                     kwargs["api_key"] = self._api_key
+                logger.debug("Creating Hindsight cloud client (url=%s, has_key=%s)",
+                             self._api_url, bool(self._api_key))
                 self._client = Hindsight(**kwargs)
         return self._client
 
     def initialize(self, session_id: str, **kwargs) -> None:
+        self._session_id = session_id
+
+        # Check client version and auto-upgrade if needed
+        try:
+            from importlib.metadata import version as pkg_version
+            from packaging.version import Version
+            installed = pkg_version("hindsight-client")
+            if Version(installed) < Version(_MIN_CLIENT_VERSION):
+                logger.warning("hindsight-client %s is outdated (need >=%s), attempting upgrade...",
+                               installed, _MIN_CLIENT_VERSION)
+                import shutil, subprocess, sys
+                uv_path = shutil.which("uv")
+                if uv_path:
+                    try:
+                        subprocess.run(
+                            [uv_path, "pip", "install", "--python", sys.executable,
+                             "--quiet", "--upgrade", f"hindsight-client>={_MIN_CLIENT_VERSION}"],
+                            check=True, timeout=120, capture_output=True,
+                        )
+                        logger.info("hindsight-client upgraded to >=%s", _MIN_CLIENT_VERSION)
+                    except Exception as e:
+                        logger.warning("Auto-upgrade failed: %s. Run: uv pip install 'hindsight-client>=%s'",
+                                       e, _MIN_CLIENT_VERSION)
+                else:
+                    logger.warning("uv not found. Run: pip install 'hindsight-client>=%s'", _MIN_CLIENT_VERSION)
+        except Exception:
+            pass  # packaging not available or other issue — proceed anyway
+
         self._config = _load_config()
         self._mode = self._config.get("mode", "cloud")
-        self._api_key = self._config.get("apiKey") or os.environ.get("HINDSIGHT_API_KEY", "")
-        default_url = _DEFAULT_LOCAL_URL if self._mode == "local" else _DEFAULT_API_URL
+        # "local" is a legacy alias for "local_embedded"
+        if self._mode == "local":
+            self._mode = "local_embedded"
+        self._api_key = self._config.get("apiKey") or self._config.get("api_key") or os.environ.get("HINDSIGHT_API_KEY", "")
+        default_url = _DEFAULT_LOCAL_URL if self._mode in ("local_embedded", "local_external") else _DEFAULT_API_URL
         self._api_url = self._config.get("api_url") or os.environ.get("HINDSIGHT_API_URL", default_url)
+        self._llm_base_url = self._config.get("llm_base_url", "")
 
         banks = self._config.get("banks", {}).get("hermes", {})
         self._bank_id = self._config.get("bank_id") or banks.get("bankId", "hermes")
-        budget = self._config.get("budget") or banks.get("budget", "mid")
+        budget = self._config.get("recall_budget") or self._config.get("budget") or banks.get("budget", "mid")
         self._budget = budget if budget in _VALID_BUDGETS else "mid"
 
         memory_mode = self._config.get("memory_mode", "hybrid")
         self._memory_mode = memory_mode if memory_mode in ("context", "tools", "hybrid") else "hybrid"
 
-        prefetch_method = self._config.get("prefetch_method", "recall")
+        prefetch_method = self._config.get("recall_prefetch_method", "recall")
         self._prefetch_method = prefetch_method if prefetch_method in ("recall", "reflect") else "recall"
 
-        logger.info("Hindsight initialized: mode=%s, api_url=%s, bank=%s, budget=%s, memory_mode=%s, prefetch_method=%s",
-                     self._mode, self._api_url, self._bank_id, self._budget, self._memory_mode, self._prefetch_method)
+        # Bank options
+        self._bank_mission = self._config.get("bank_mission", "")
+        self._bank_retain_mission = self._config.get("bank_retain_mission") or None
+
+        # Tags
+        self._tags = self._config.get("tags") or None
+        self._recall_tags = self._config.get("recall_tags") or None
+        self._recall_tags_match = self._config.get("recall_tags_match", "any")
+
+        # Retain controls
+        self._auto_retain = self._config.get("auto_retain", True)
+        self._retain_every_n_turns = max(1, int(self._config.get("retain_every_n_turns", 1)))
+        self._retain_context = self._config.get("retain_context", "conversation between Hermes Agent and the User")
+
+        # Recall controls
+        self._auto_recall = self._config.get("auto_recall", True)
+        self._recall_max_tokens = int(self._config.get("recall_max_tokens", 4096))
+        self._recall_types = self._config.get("recall_types") or None
+        self._recall_prompt_preamble = self._config.get("recall_prompt_preamble", "")
+        self._recall_max_input_chars = int(self._config.get("recall_max_input_chars", 800))
+        self._retain_async = self._config.get("retain_async", True)
+
+        _client_version = "unknown"
+        try:
+            from importlib.metadata import version as pkg_version
+            _client_version = pkg_version("hindsight-client")
+        except Exception:
+            pass
+        logger.info("Hindsight initialized: mode=%s, api_url=%s, bank=%s, budget=%s, memory_mode=%s, prefetch_method=%s, client=%s",
+                     self._mode, self._api_url, self._bank_id, self._budget, self._memory_mode, self._prefetch_method, _client_version)
+        logger.debug("Hindsight config: auto_retain=%s, auto_recall=%s, retain_every_n=%d, "
+                     "retain_async=%s, retain_context=%s, "
+                     "recall_max_tokens=%d, recall_max_input_chars=%d, tags=%s, recall_tags=%s",
+                     self._auto_retain, self._auto_recall, self._retain_every_n_turns,
+                     self._retain_async, self._retain_context,
+                     self._recall_max_tokens, self._recall_max_input_chars,
+                     self._tags, self._recall_tags)
 
         # For local mode, start the embedded daemon in the background so it
         # doesn't block the chat. Redirect stdout/stderr to a log file to
         # prevent rich startup output from spamming the terminal.
-        if self._mode == "local":
+        if self._mode == "local_embedded":
             def _start_daemon():
                 import traceback
                 log_dir = get_hermes_home() / "logs"
@@ -320,6 +583,8 @@ class HindsightMemoryProvider(MemoryProvider):
                     current_provider = self._config.get("llm_provider", "")
                     current_model = self._config.get("llm_model", "")
                     current_base_url = self._config.get("llm_base_url") or os.environ.get("HINDSIGHT_API_LLM_BASE_URL", "")
+                    # Map openai_compatible/openrouter → openai for the daemon (OpenAI wire format)
+                    daemon_provider = "openai" if current_provider in ("openai_compatible", "openrouter") else current_provider
 
                     # Read saved profile config
                     saved = {}
@@ -330,7 +595,7 @@ class HindsightMemoryProvider(MemoryProvider):
                                 saved[k.strip()] = v.strip()
 
                     config_changed = (
-                        saved.get("HINDSIGHT_API_LLM_PROVIDER") != current_provider or
+                        saved.get("HINDSIGHT_API_LLM_PROVIDER") != daemon_provider or
                         saved.get("HINDSIGHT_API_LLM_MODEL") != current_model or
                         saved.get("HINDSIGHT_API_LLM_API_KEY") != current_key or
                         saved.get("HINDSIGHT_API_LLM_BASE_URL", "") != current_base_url
@@ -340,7 +605,7 @@ class HindsightMemoryProvider(MemoryProvider):
                         # Write updated profile .env
                         profile_env.parent.mkdir(parents=True, exist_ok=True)
                         env_lines = (
-                            f"HINDSIGHT_API_LLM_PROVIDER={current_provider}\n"
+                            f"HINDSIGHT_API_LLM_PROVIDER={daemon_provider}\n"
                             f"HINDSIGHT_API_LLM_API_KEY={current_key}\n"
                             f"HINDSIGHT_API_LLM_MODEL={current_model}\n"
                             f"HINDSIGHT_API_LOG_LEVEL=info\n"
@@ -388,47 +653,118 @@ class HindsightMemoryProvider(MemoryProvider):
 
     def prefetch(self, query: str, *, session_id: str = "") -> str:
         if self._prefetch_thread and self._prefetch_thread.is_alive():
+            logger.debug("Prefetch: waiting for background thread to complete")
             self._prefetch_thread.join(timeout=3.0)
         with self._prefetch_lock:
             result = self._prefetch_result
             self._prefetch_result = ""
         if not result:
+            logger.debug("Prefetch: no results available")
             return ""
-        return f"## Hindsight Memory\n{result}"
+        logger.debug("Prefetch: returning %d chars of context", len(result))
+        header = self._recall_prompt_preamble or (
+            "# Hindsight Memory (persistent cross-session context)\n"
+            "Use this to answer questions about the user and prior sessions. "
+            "Do not call tools to look up information that is already present here."
+        )
+        return f"{header}\n\n{result}"
 
     def queue_prefetch(self, query: str, *, session_id: str = "") -> None:
         if self._memory_mode == "tools":
+            logger.debug("Prefetch: skipped (tools-only mode)")
             return
+        if not self._auto_recall:
+            logger.debug("Prefetch: skipped (auto_recall disabled)")
+            return
+        # Truncate query to max chars
+        if self._recall_max_input_chars and len(query) > self._recall_max_input_chars:
+            query = query[:self._recall_max_input_chars]
+
         def _run():
             try:
                 client = self._get_client()
                 if self._prefetch_method == "reflect":
+                    logger.debug("Prefetch: calling reflect (bank=%s, query_len=%d)", self._bank_id, len(query))
                     resp = _run_sync(client.areflect(bank_id=self._bank_id, query=query, budget=self._budget))
                     text = resp.text or ""
                 else:
-                    resp = _run_sync(client.arecall(bank_id=self._bank_id, query=query, budget=self._budget))
-                    text = "\n".join(r.text for r in resp.results if r.text) if resp.results else ""
+                    recall_kwargs: dict = {
+                        "bank_id": self._bank_id, "query": query,
+                        "budget": self._budget, "max_tokens": self._recall_max_tokens,
+                    }
+                    if self._recall_tags:
+                        recall_kwargs["tags"] = self._recall_tags
+                        recall_kwargs["tags_match"] = self._recall_tags_match
+                    if self._recall_types:
+                        recall_kwargs["types"] = self._recall_types
+                    logger.debug("Prefetch: calling recall (bank=%s, query_len=%d, budget=%s)",
+                                 self._bank_id, len(query), self._budget)
+                    resp = _run_sync(client.arecall(**recall_kwargs))
+                    num_results = len(resp.results) if resp.results else 0
+                    logger.debug("Prefetch: recall returned %d results", num_results)
+                    text = "\n".join(f"- {r.text}" for r in resp.results if r.text) if resp.results else ""
                 if text:
                     with self._prefetch_lock:
                         self._prefetch_result = text
             except Exception as e:
-                logger.debug("Hindsight prefetch failed: %s", e)
+                logger.debug("Hindsight prefetch failed: %s", e, exc_info=True)
 
         self._prefetch_thread = threading.Thread(target=_run, daemon=True, name="hindsight-prefetch")
         self._prefetch_thread.start()
 
     def sync_turn(self, user_content: str, assistant_content: str, *, session_id: str = "") -> None:
-        """Retain conversation turn in background (non-blocking)."""
-        combined = f"User: {user_content}\nAssistant: {assistant_content}"
+        """Retain conversation turn in background (non-blocking).
+
+        Respects retain_every_n_turns for batching.
+        """
+        if not self._auto_retain:
+            logger.debug("sync_turn: skipped (auto_retain disabled)")
+            return
+
+        from datetime import datetime, timezone
+        now = datetime.now(timezone.utc).isoformat()
+
+        messages = [
+            {"role": "user", "content": user_content, "timestamp": now},
+            {"role": "assistant", "content": assistant_content, "timestamp": now},
+        ]
+
+        turn = json.dumps(messages)
+        self._session_turns.append(turn)
+        self._turn_counter += 1
+
+        # Only retain every N turns
+        if self._turn_counter % self._retain_every_n_turns != 0:
+            logger.debug("sync_turn: buffered turn %d (will retain at turn %d)",
+                         self._turn_counter, self._turn_counter + (self._retain_every_n_turns - self._turn_counter % self._retain_every_n_turns))
+            return
+
+        logger.debug("sync_turn: retaining %d turns, total session content %d chars",
+                     len(self._session_turns), sum(len(t) for t in self._session_turns))
+        # Send the ENTIRE session as a single JSON array (document_id deduplicates).
+        # Each element in _session_turns is a JSON string of that turn's messages.
+        content = "[" + ",".join(self._session_turns) + "]"
 
         def _sync():
             try:
                 client = self._get_client()
-                _run_sync(client.aretain(
-                    bank_id=self._bank_id, content=combined, context="conversation"
+                item: dict = {
+                    "content": content,
+                    "context": self._retain_context,
+                }
+                if self._tags:
+                    item["tags"] = self._tags
+                logger.debug("Hindsight retain: bank=%s, doc=%s, async=%s, content_len=%d, num_turns=%d",
+                             self._bank_id, self._session_id, self._retain_async, len(content), len(self._session_turns))
+                _run_sync(client.aretain_batch(
+                    bank_id=self._bank_id,
+                    items=[item],
+                    document_id=self._session_id,
+                    retain_async=self._retain_async,
                 ))
+                logger.debug("Hindsight retain succeeded")
             except Exception as e:
-                logger.warning("Hindsight sync failed: %s", e)
+                logger.warning("Hindsight sync failed: %s", e, exc_info=True)
 
         if self._sync_thread and self._sync_thread.is_alive():
             self._sync_thread.join(timeout=5.0)
@@ -453,12 +789,18 @@ class HindsightMemoryProvider(MemoryProvider):
                 return tool_error("Missing required parameter: content")
             context = args.get("context")
             try:
-                _run_sync(client.aretain(
-                    bank_id=self._bank_id, content=content, context=context
-                ))
+                retain_kwargs: dict = {
+                    "bank_id": self._bank_id, "content": content, "context": context,
+                }
+                if self._tags:
+                    retain_kwargs["tags"] = self._tags
+                logger.debug("Tool hindsight_retain: bank=%s, content_len=%d, context=%s",
+                             self._bank_id, len(content), context)
+                _run_sync(client.aretain(**retain_kwargs))
+                logger.debug("Tool hindsight_retain: success")
                 return json.dumps({"result": "Memory stored successfully."})
             except Exception as e:
-                logger.warning("hindsight_retain failed: %s", e)
+                logger.warning("hindsight_retain failed: %s", e, exc_info=True)
                 return tool_error(f"Failed to store memory: {e}")
 
         elif tool_name == "hindsight_recall":
@@ -466,15 +808,26 @@ class HindsightMemoryProvider(MemoryProvider):
             if not query:
                 return tool_error("Missing required parameter: query")
             try:
-                resp = _run_sync(client.arecall(
-                    bank_id=self._bank_id, query=query, budget=self._budget
-                ))
+                recall_kwargs: dict = {
+                    "bank_id": self._bank_id, "query": query, "budget": self._budget,
+                    "max_tokens": self._recall_max_tokens,
+                }
+                if self._recall_tags:
+                    recall_kwargs["tags"] = self._recall_tags
+                    recall_kwargs["tags_match"] = self._recall_tags_match
+                if self._recall_types:
+                    recall_kwargs["types"] = self._recall_types
+                logger.debug("Tool hindsight_recall: bank=%s, query_len=%d, budget=%s",
+                             self._bank_id, len(query), self._budget)
+                resp = _run_sync(client.arecall(**recall_kwargs))
+                num_results = len(resp.results) if resp.results else 0
+                logger.debug("Tool hindsight_recall: %d results", num_results)
                 if not resp.results:
                     return json.dumps({"result": "No relevant memories found."})
                 lines = [f"{i}. {r.text}" for i, r in enumerate(resp.results, 1)]
                 return json.dumps({"result": "\n".join(lines)})
             except Exception as e:
-                logger.warning("hindsight_recall failed: %s", e)
+                logger.warning("hindsight_recall failed: %s", e, exc_info=True)
                 return tool_error(f"Failed to search memory: {e}")
 
         elif tool_name == "hindsight_reflect":
@@ -482,24 +835,28 @@ class HindsightMemoryProvider(MemoryProvider):
             if not query:
                 return tool_error("Missing required parameter: query")
             try:
+                logger.debug("Tool hindsight_reflect: bank=%s, query_len=%d, budget=%s",
+                             self._bank_id, len(query), self._budget)
                 resp = _run_sync(client.areflect(
                     bank_id=self._bank_id, query=query, budget=self._budget
                 ))
+                logger.debug("Tool hindsight_reflect: response_len=%d", len(resp.text or ""))
                 return json.dumps({"result": resp.text or "No relevant memories found."})
             except Exception as e:
-                logger.warning("hindsight_reflect failed: %s", e)
+                logger.warning("hindsight_reflect failed: %s", e, exc_info=True)
                 return tool_error(f"Failed to reflect: {e}")
 
         return tool_error(f"Unknown tool: {tool_name}")
 
     def shutdown(self) -> None:
+        logger.debug("Hindsight shutdown: waiting for background threads")
         global _loop, _loop_thread
         for t in (self._prefetch_thread, self._sync_thread):
             if t and t.is_alive():
                 t.join(timeout=5.0)
         if self._client is not None:
             try:
-                if self._mode == "local":
+                if self._mode == "local_embedded":
                     # Use the public close() API. The RuntimeError from
                     # aiohttp's "attached to a different loop" is expected
                     # and harmless — the daemon keeps running independently.

plugins/memory/hindsight/plugin.yaml

@@ -2,9 +2,7 @@ name: hindsight
 version: 1.0.0
 description: "Hindsight — long-term memory with knowledge graph, entity resolution, and multi-strategy retrieval."
 pip_dependencies:
-  - hindsight-client
-  - hindsight-all
-requires_env:
-  - HINDSIGHT_API_KEY
+  - "hindsight-client>=0.4.22"
+requires_env: []
 hooks:
   - on_session_end