refactor: update github-code-review skill to use MCP tools

Replace gh CLI and curl-based GitHub API interactions with native
GitHub MCP tools (mcp_github_*). This modernizes the skill to use
the agent's built-in MCP integration for all GitHub operations.

Key changes:
- Replace gh CLI commands with mcp_github_pull_request_read(),
  mcp_github_pull_request_review_write(), etc.
- Replace curl API calls with mcp_github_add_issue_comment(),
  mcp_github_add_comment_to_pending_review(), etc.
- Add mcp_github_run_secret_scanning() to security checklist
- Add mcp_github_request_copilot_review() as optional step
- Add quick reference table mapping tasks to MCP tools
- Keep git CLI for local diff operations (unchanged)
- Bump version to 2.0.0

.env.example

@@ -89,6 +89,15 @@
 # Optional base URL override:
 # HERMES_QWEN_BASE_URL=https://portal.qwen.ai/v1
 
+# =============================================================================
+# LLM PROVIDER (Xiaomi MiMo)
+# =============================================================================
+# Xiaomi MiMo models (mimo-v2-pro, mimo-v2-omni, mimo-v2-flash).
+# Get your key at: https://platform.xiaomimimo.com
+# XIAOMI_API_KEY=your_key_here
+# Optional base URL override:
+# XIAOMI_BASE_URL=https://api.xiaomimimo.com/v1
+
 # =============================================================================
 # TOOL API KEYS
 # =============================================================================

.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

AGENTS.md

@@ -351,8 +351,9 @@ Cache-breaking forces dramatically higher costs. The ONLY time we alter context
 
 ### Background Process Notifications (Gateway)
 
-When `terminal(background=true, check_interval=...)` is used, the gateway runs a watcher that
-pushes status updates to the user's chat. Control verbosity with `display.background_process_notifications`
+When `terminal(background=true, notify_on_complete=true)` is used, the gateway runs a watcher that
+detects process completion and triggers a new agent turn. Control verbosity of background process
+messages with `display.background_process_notifications`
 in config.yaml (or `HERMES_BACKGROUND_NOTIFICATIONS` env var):
 
 - `all` — running-output updates + final message (default)

Dockerfile

@@ -1,23 +1,44 @@
+FROM ghcr.io/astral-sh/uv:0.11.6-python3.13-trixie@sha256:b3c543b6c4f23a5f2df22866bd7857e5d304b67a564f4feab6ac22044dde719b AS uv_source
+FROM tianon/gosu:1.19-trixie@sha256:3b176695959c71e123eb390d427efc665eeb561b1540e82679c15e992006b8b9 AS gosu_source
 FROM debian:13.4
 
+# Disable Python stdout buffering to ensure logs are printed immediately
+ENV PYTHONUNBUFFERED=1
+
+# Store Playwright browsers outside the volume mount so the build-time
+# install survives the /opt/data volume overlay at runtime.
+ENV PLAYWRIGHT_BROWSERS_PATH=/opt/hermes/.playwright
+
 # 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 ripgrep ffmpeg gcc python3-dev libffi-dev procps && \
     rm -rf /var/lib/apt/lists/*
 
+# Non-root user for runtime; UID can be overridden via HERMES_UID at runtime
+RUN useradd -u 10000 -m -d /opt/data hermes
+
+COPY --chmod=0755 --from=gosu_source /gosu /usr/local/bin/
+COPY --chmod=0755 --from=uv_source /usr/local/bin/uv /usr/local/bin/uvx /usr/local/bin/
+
 COPY . /opt/hermes
 WORKDIR /opt/hermes
 
-# Install Python and Node dependencies in one layer, no cache
-RUN pip install --no-cache-dir -e ".[all]" --break-system-packages && \
-    npm install --prefer-offline --no-audit && \
+# Install Node dependencies and Playwright as root (--with-deps needs apt)
+RUN npm install --prefer-offline --no-audit && \
     npx playwright install --with-deps chromium --only-shell && \
     cd /opt/hermes/scripts/whatsapp-bridge && \
     npm install --prefer-offline --no-audit && \
     npm cache clean --force
 
-WORKDIR /opt/hermes
+# Hand ownership to hermes user, then install Python deps in a virtualenv
+RUN chown -R hermes:hermes /opt/hermes
+USER hermes
+
+RUN uv venv && \
+    uv pip install --no-cache-dir -e ".[all]"
+
+USER root
 RUN chmod +x /opt/hermes/docker/entrypoint.sh
 
 ENV HERMES_HOME=/opt/data

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

@@ -23,17 +23,13 @@ Resolution order for vision/multimodal tasks (auto mode):
   6. Custom endpoint (for local vision models: Qwen-VL, LLaVA, Pixtral, etc.)
   7. None
 
-Per-task provider overrides (e.g. AUXILIARY_VISION_PROVIDER,
-CONTEXT_COMPRESSION_PROVIDER) can force a specific provider for each task.
+Per-task overrides are configured in config.yaml under the ``auxiliary:`` section
+(e.g. ``auxiliary.vision.provider``, ``auxiliary.compression.model``).
 Default "auto" follows the chains above.
 
-Per-task model overrides (e.g. AUXILIARY_VISION_MODEL,
-AUXILIARY_WEB_EXTRACT_MODEL) let callers use a different model slug
-than the provider's default.
-
-Per-task direct endpoint overrides (e.g. AUXILIARY_VISION_BASE_URL,
-AUXILIARY_VISION_API_KEY) let callers route a specific auxiliary task to a
-custom OpenAI-compatible endpoint without touching the main model settings.
+Legacy env var overrides (AUXILIARY_{TASK}_PROVIDER, AUXILIARY_{TASK}_MODEL,
+AUXILIARY_{TASK}_BASE_URL, etc.) are still read as a backward-compat fallback
+but config.yaml takes priority.  New configuration should always use config.yaml.
 
 Payment / credit exhaustion fallback:
   When a resolved provider returns HTTP 402 or a credit-related error,
@@ -59,6 +55,9 @@ 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",
@@ -108,6 +107,14 @@ _API_KEY_PROVIDER_AUX_MODELS: Dict[str, str] = {
     "kilocode": "google/gemini-3-flash-preview",
 }
 
+# Vision-specific model overrides for direct providers.
+# When the user's main provider has a dedicated vision/multimodal model that
+# differs from their main chat model, map it here.  The vision auto-detect
+# "exotic provider" branch checks this before falling back to the main model.
+_PROVIDER_VISION_MODELS: Dict[str, str] = {
+    "xiaomi": "mimo-v2-omni",
+}
+
 # OpenRouter app attribution headers
 _OR_HEADERS = {
     "HTTP-Referer": "https://hermes-agent.nousresearch.com",
@@ -629,11 +636,19 @@ 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 +694,15 @@ 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 +714,13 @@ 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 +735,13 @@ 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 +868,7 @@ 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 +881,29 @@ 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 +912,33 @@ 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 +946,13 @@ 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 +1011,6 @@ 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 +1057,41 @@ 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 +1117,15 @@ 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 +1140,34 @@ 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 +1225,22 @@ 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 +1248,7 @@ 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 +1272,10 @@ 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 +1283,40 @@ 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 +1342,7 @@ 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 +1353,7 @@ 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 +1367,7 @@ 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 +1376,7 @@ 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 +1395,18 @@ 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 +1414,9 @@ 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 +1431,12 @@ 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 +1467,7 @@ 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 +1486,12 @@ 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 +1499,28 @@ 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 +1553,13 @@ 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 +1570,14 @@ 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 +1610,6 @@ 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 +1650,7 @@ 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)
@@ -1548,16 +1691,18 @@ def resolve_vision_provider_client(
                 if sync_client is not None:
                     return _finalize(main_provider, sync_client, default_model)
             else:
-                # Exotic provider (DeepSeek, Alibaba, named custom, etc.)
+                # Exotic provider (DeepSeek, Alibaba, Xiaomi, named custom, etc.)
+                # Use provider-specific vision model if available, otherwise main model.
+                vision_model = _PROVIDER_VISION_MODELS.get(main_provider, main_model)
                 rpc_client, rpc_model = resolve_provider_client(
-                    main_provider, main_model)
+                    main_provider, vision_model)
                 if rpc_client is not None:
                     logger.info(
                         "Vision auto-detect: using active provider %s (%s)",
-                        main_provider, rpc_model or main_model,
+                        main_provider, rpc_model or vision_model,
                     )
                     return _finalize(
-                        main_provider, rpc_client, rpc_model or main_model)
+                        main_provider, rpc_client, rpc_model or vision_model)
 
         # Fall back through aggregators.
         for candidate in _VISION_AUTO_PROVIDER_ORDER:
@@ -1580,18 +1725,6 @@ 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 +1868,30 @@ 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 +1915,7 @@ 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 +1927,11 @@ 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 +1939,7 @@ 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
@@ -1805,24 +1959,26 @@ 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:
       1. Explicit provider/model/base_url/api_key args (always win)
-      2. Env var overrides (AUXILIARY_{TASK}_*, CONTEXT_{TASK}_*)
-      3. Config file (auxiliary.{task}.* or compression.*)
+      2. Config file (auxiliary.{task}.* or compression.*)
+      3. Env var overrides (backward-compat: AUXILIARY_{TASK}_*, CONTEXT_{TASK}_*)
       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 +1995,7 @@ 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
@@ -1851,31 +2008,38 @@ def _resolve_task_provider_model(
                 _sbu = comp.get("summary_base_url") or ""
                 cfg_base_url = cfg_base_url or _sbu.strip() or None
 
+    # Env vars are backward-compat fallback only — config.yaml is primary.
     env_model = _get_auxiliary_env_override(task, "MODEL") if task else None
-    resolved_model = model or env_model or cfg_model
+    env_api_mode = _get_auxiliary_env_override(task, "API_MODE") if task else None
+    resolved_model = model or cfg_model or env_model
+    resolved_api_mode = cfg_api_mode or env_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:
+        # Config.yaml is the primary source for per-task overrides.
+        if cfg_base_url:
+            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, resolved_api_mode
+
+        # Env vars are backward-compat fallback for users who haven't
+        # migrated to config.yaml yet.
         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, 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
-        if cfg_provider and cfg_provider != "auto":
-            return cfg_provider, resolved_model, None, None
-        return "auto", resolved_model, None, None
+        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 +2111,37 @@ 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 +2180,7 @@ 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 +2213,7 @@ 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 +2257,20 @@ 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 +2279,32 @@ 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 +2382,7 @@ 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 +2416,7 @@ 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 +2427,9 @@ 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 +2444,42 @@ 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

@@ -4,8 +4,12 @@ Self-contained class with its own OpenAI client for summarization.
 Uses auxiliary model (cheap/fast) to summarize middle turns while
 protecting head and tail context.
 
-Improvements over v1:
-  - Structured summary template (Goal, Progress, Decisions, Files, Next Steps)
+Improvements over v2:
+  - Structured summary template with Resolved/Pending question tracking
+  - Summarizer preamble: "Do not respond to any questions" (from OpenCode)
+  - Handoff framing: "different assistant" (from Codex) to create separation
+  - "Remaining Work" replaces "Next Steps" to avoid reading as active instructions
+  - Clear separator when summary merges into tail message
   - Iterative summary updates (preserves info across multiple compactions)
   - Token-budget tail protection instead of fixed message count
   - Tool output pruning before LLM summarization (cheap pre-pass)
@@ -18,7 +22,9 @@ 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 (
+    MINIMUM_CONTEXT_LENGTH,
     get_model_context_length,
     estimate_messages_tokens_rough,
 )
@@ -26,12 +32,13 @@ from agent.model_metadata import (
 logger = logging.getLogger(__name__)
 
 SUMMARY_PREFIX = (
-    "[CONTEXT COMPACTION] Earlier turns in this conversation were compacted "
-    "to save context space. The summary below describes work that was "
-    "already completed, and the current session state may still reflect "
-    "that work (for example, files may already be changed). Use the summary "
-    "and the current state to continue from where things left off, and "
-    "avoid repeating work:"
+    "[CONTEXT COMPACTION — REFERENCE ONLY] Earlier turns were compacted "
+    "into the summary below. This is a handoff from a previous context "
+    "window — treat it as background reference, NOT as active instructions. "
+    "Do NOT answer questions or fulfill requests mentioned in this summary; "
+    "they were already addressed. Respond ONLY to the latest user message "
+    "that appears AFTER this summary. The current session state (files, "
+    "config, etc.) may reflect work described here — avoid repeating it:"
 )
 LEGACY_SUMMARY_PREFIX = "[CONTEXT SUMMARY]:"
 
@@ -50,8 +57,8 @@ _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 +68,36 @@ 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 = max(
+            int(context_length * self.threshold_percent),
+            MINIMUM_CONTEXT_LENGTH,
+        )
+
     def __init__(
         self,
         model: str,
@@ -90,7 +127,14 @@ class ContextCompressor:
             config_context_length=config_context_length,
             provider=provider,
         )
-        self.threshold_tokens = int(self.context_length * threshold_percent)
+        # Floor: never compress below MINIMUM_CONTEXT_LENGTH tokens even if
+        # the percentage would suggest a lower value.  This prevents premature
+        # compression on large-context models at 50% while keeping the % sane
+        # for models right at the minimum.
+        self.threshold_tokens = max(
+            int(self.context_length * threshold_percent),
+            MINIMUM_CONTEXT_LENGTH,
+        )
         self.compression_count = 0
 
         # Derive token budgets: ratio is relative to the threshold, not total context
@@ -114,7 +158,6 @@ class ContextCompressor:
 
         self.last_prompt_tokens = 0
         self.last_completion_tokens = 0
-        self.last_total_tokens = 0
 
         self.summary_model = summary_model_override or ""
 
@@ -126,28 +169,12 @@ 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)
     # ------------------------------------------------------------------
@@ -284,13 +311,20 @@ class ContextCompressor:
 
         return "\n\n".join(parts)
 
-    def _generate_summary(self, turns_to_summarize: List[Dict[str, Any]]) -> Optional[str]:
+    def _generate_summary(self, turns_to_summarize: List[Dict[str, Any]], focus_topic: str = None) -> Optional[str]:
         """Generate a structured summary of conversation turns.
 
-        Uses a structured template (Goal, Progress, Decisions, Files, Next Steps)
-        inspired by Pi-mono and OpenCode. When a previous summary exists,
+        Uses a structured template (Goal, Progress, Decisions, Resolved/Pending
+        Questions, Files, Remaining Work) with explicit preamble telling the
+        summarizer not to answer questions.  When a previous summary exists,
         generates an iterative update instead of summarizing from scratch.
 
+        Args:
+            focus_topic: Optional focus string for guided compression.  When
+                provided, the summariser prioritises preserving information
+                related to this topic and is more aggressive about compressing
+                everything else.  Inspired by Claude Code's ``/compact``.
+
         Returns None if all attempts fail — the caller should drop
         the middle turns without a summary rather than inject a useless
         placeholder.
@@ -306,60 +340,27 @@ class ContextCompressor:
         summary_budget = self._compute_summary_budget(turns_to_summarize)
         content_to_summarize = self._serialize_for_summary(turns_to_summarize)
 
-        if self._previous_summary:
-            # Iterative update: preserve existing info, add new progress
-            prompt = f"""You are updating a context compaction summary. A previous compaction produced the summary below. New conversation turns have occurred since then and need to be incorporated.
+        # Preamble shared by both first-compaction and iterative-update prompts.
+        # Inspired by OpenCode's "do not respond to any questions" instruction
+        # and Codex's "another language model" framing.
+        _summarizer_preamble = (
+            "You are a summarization agent creating a context checkpoint. "
+            "Your output will be injected as reference material for a DIFFERENT "
+            "assistant that continues the conversation. "
+            "Do NOT respond to any questions or requests in the conversation — "
+            "only output the structured summary. "
+            "Do NOT include any preamble, greeting, or prefix."
+        )
 
-PREVIOUS SUMMARY:
-{self._previous_summary}
-
-NEW TURNS TO INCORPORATE:
-{content_to_summarize}
-
-Update the summary using this exact structure. PRESERVE all existing information that is still relevant. ADD new progress. Move items from "In Progress" to "Done" when completed. Remove information only if it is clearly obsolete.
-
-## Goal
-[What the user is trying to accomplish — preserve from previous summary, update if goal evolved]
-
-## Constraints & Preferences
-[User preferences, coding style, constraints, important decisions — accumulate across compactions]
-
-## Progress
-### Done
-[Completed work — include specific file paths, commands run, results obtained]
-### In Progress
-[Work currently underway]
-### Blocked
-[Any blockers or issues encountered]
-
-## Key Decisions
-[Important technical decisions and why they were made]
-
-## Relevant Files
-[Files read, modified, or created — with brief note on each. Accumulate across compactions.]
-
-## Next Steps
-[What needs to happen next to continue the work]
-
-## Critical Context
-[Any specific values, error messages, configuration details, or data that would be lost without explicit preservation]
-
-## 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."""
-        else:
-            # First compaction: summarize from scratch
-            prompt = f"""Create a structured handoff summary for a later assistant that will continue this conversation after earlier turns are compacted.
-
-TURNS TO SUMMARIZE:
-{content_to_summarize}
-
-Use this exact structure:
-
-## Goal
+        # Shared structured template (used by both paths).
+        # Key changes vs v1:
+        #   - "Pending User Asks" section (from Claude Code) explicitly tracks
+        #     unanswered questions so the model knows what's resolved vs open
+        #   - "Remaining Work" replaces "Next Steps" to avoid reading as active
+        #     instructions
+        #   - "Resolved Questions" makes it clear which questions were already
+        #     answered (prevents model from re-answering them)
+        _template_sections = f"""## Goal
 [What the user is trying to accomplish]
 
 ## Constraints & Preferences
@@ -376,22 +377,64 @@ Use this exact structure:
 ## Key Decisions
 [Important technical decisions and why they were made]
 
+## Resolved Questions
+[Questions the user asked that were ALREADY answered — include the answer so the next assistant does not re-answer them]
+
+## Pending User Asks
+[Questions or requests from the user that have NOT yet been answered or fulfilled. If none, write "None."]
+
 ## Relevant Files
 [Files read, modified, or created — with brief note on each]
 
-## Next Steps
-[What needs to happen next to continue the work]
+## Remaining Work
+[What remains to be done — framed as context, not instructions]
 
 ## 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)]
+[Which tools were used, how they were used effectively, and any tool-specific discoveries]
 
-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.
+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."""
 
+        if self._previous_summary:
+            # Iterative update: preserve existing info, add new progress
+            prompt = f"""{_summarizer_preamble}
+
+You are updating a context compaction summary. A previous compaction produced the summary below. New conversation turns have occurred since then and need to be incorporated.
+
+PREVIOUS SUMMARY:
+{self._previous_summary}
+
+NEW TURNS TO INCORPORATE:
+{content_to_summarize}
+
+Update the summary using this exact structure. PRESERVE all existing information that is still relevant. ADD new progress. Move items from "In Progress" to "Done" when completed. Move answered questions to "Resolved Questions". Remove information only if it is clearly obsolete.
+
+{_template_sections}"""
+        else:
+            # First compaction: summarize from scratch
+            prompt = f"""{_summarizer_preamble}
+
+Create a structured handoff summary for a different assistant that will continue this conversation after earlier turns are compacted. The next assistant should be able to understand what happened without re-reading the original turns.
+
+TURNS TO SUMMARIZE:
+{content_to_summarize}
+
+Use this exact structure:
+
+{_template_sections}"""
+
+        # Inject focus topic guidance when the user provides one via /compress <focus>.
+        # This goes at the end of the prompt so it takes precedence.
+        if focus_topic:
+            prompt += f"""
+
+FOCUS TOPIC: "{focus_topic}"
+The user has requested that this compaction PRIORITISE preserving all information related to the focus topic above. For content related to "{focus_topic}", include full detail — exact values, file paths, command outputs, error messages, and decisions. For content NOT related to the focus topic, summarise more aggressively (brief one-liners or omit if truly irrelevant). The focus topic sections should receive roughly 60-70% of the summary token budget."""
+
         try:
             call_kwargs = {
                 "task": "compression",
@@ -609,7 +652,7 @@ Write only the summary body. Do not include any preamble or prefix."""
     # Main compression entry point
     # ------------------------------------------------------------------
 
-    def compress(self, messages: List[Dict[str, Any]], current_tokens: int = None) -> List[Dict[str, Any]]:
+    def compress(self, messages: List[Dict[str, Any]], current_tokens: int = None, focus_topic: str = None) -> List[Dict[str, Any]]:
         """Compress conversation messages by summarizing middle turns.
 
         Algorithm:
@@ -621,6 +664,12 @@ Write only the summary body. Do not include any preamble or prefix."""
 
         After compression, orphaned tool_call / tool_result pairs are cleaned
         up so the API never receives mismatched IDs.
+
+        Args:
+            focus_topic: Optional focus string for guided compression.  When
+                provided, the summariser will prioritise preserving information
+                related to this topic and be more aggressive about compressing
+                everything else.  Inspired by Claude Code's ``/compact``.
         """
         n_messages = len(messages)
         # Only need head + 3 tail messages minimum (token budget decides the real tail size)
@@ -678,7 +727,7 @@ Write only the summary body. Do not include any preamble or prefix."""
             )
 
         # Phase 3: Generate structured summary
-        summary = self._generate_summary(turns_to_summarize)
+        summary = self._generate_summary(turns_to_summarize, focus_topic=focus_topic)
 
         # Phase 4: Assemble compressed message list
         compressed = []
@@ -691,39 +740,54 @@ 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()
             if _merge_summary_into_tail and i == compress_end:
                 original = msg.get("content") or ""
-                msg["content"] = summary + "\n\n" + original
+                msg["content"] = (
+                    summary
+                    + "\n\n--- END OF CONTEXT SUMMARY — "
+                    "respond to the message below, not the summary above ---\n\n"
+                    + original
+                )
                 _merge_summary_into_tail = False
             compressed.append(msg)
 

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,
@@ -1018,6 +1128,23 @@ def _seed_from_singletons(provider: str, entries: List[PooledCredential]) -> Tup
     elif provider == "openai-codex":
         state = _load_provider_state(auth_store, "openai-codex")
         tokens = state.get("tokens") if isinstance(state, dict) else None
+        # Fallback: import from Codex CLI (~/.codex/auth.json) if Hermes auth
+        # store has no tokens.  This mirrors resolve_codex_runtime_credentials()
+        # so that load_pool() and list_authenticated_providers() detect tokens
+        # that only exist in the Codex CLI shared file.
+        if not (isinstance(tokens, dict) and tokens.get("access_token")):
+            try:
+                from hermes_cli.auth import _import_codex_cli_tokens, _save_codex_tokens
+                cli_tokens = _import_codex_cli_tokens()
+                if cli_tokens:
+                    logger.info("Importing Codex CLI tokens into Hermes auth store.")
+                    _save_codex_tokens(cli_tokens)
+                    # Re-read state after import
+                    auth_store = _load_auth_store()
+                    state = _load_provider_state(auth_store, "openai-codex")
+                    tokens = state.get("tokens") if isinstance(state, dict) else None
+            except Exception as exc:
+                logger.debug("Codex CLI token import failed: %s", exc)
         if isinstance(tokens, dict) and tokens.get("access_token"):
             active_sources.add("device_code")
             changed |= _upsert_entry(
@@ -1084,7 +1211,9 @@ 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

@@ -4,7 +4,6 @@ Pure display functions and classes with no AIAgent dependency.
 Used by AIAgent._execute_tool_calls for CLI feedback.
 """
 
-import json
 import logging
 import os
 import sys
@@ -14,6 +13,8 @@ from dataclasses import dataclass, field
 from difflib import unified_diff
 from pathlib import Path
 
+from utils import safe_json_loads
+
 # ANSI escape codes for coloring tool failure indicators
 _RED = "\033[31m"
 _RESET = "\033[0m"
@@ -21,11 +22,73 @@ _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 +130,6 @@ 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()
@@ -330,9 +373,8 @@ def _result_succeeded(result: str | None) -> bool:
     """Conservatively detect whether a tool result represents success."""
     if not result:
         return False
-    try:
-        data = json.loads(result)
-    except (json.JSONDecodeError, TypeError):
+    data = safe_json_loads(result)
+    if data is None:
         return False
     if not isinstance(data, dict):
         return False
@@ -381,10 +423,7 @@ def extract_edit_diff(
 ) -> str | None:
     """Extract a unified diff from a file-edit tool result."""
     if tool_name == "patch" and result:
-        try:
-            data = json.loads(result)
-        except (json.JSONDecodeError, TypeError):
-            data = None
+        data = safe_json_loads(result)
         if isinstance(data, dict):
             diff = data.get("diff")
             if isinstance(diff, str) and diff.strip():
@@ -423,19 +462,19 @@ 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 +540,7 @@ 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 +762,6 @@ 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)
 # =========================================================================
@@ -778,23 +777,19 @@ def _detect_tool_failure(tool_name: str, result: str | None) -> tuple[bool, str]
         return False, ""
 
     if tool_name == "terminal":
-        try:
-            data = json.loads(result)
+        data = safe_json_loads(result)
+        if isinstance(data, dict):
             exit_code = data.get("exit_code")
             if exit_code is not None and exit_code != 0:
                 return True, f" [exit {exit_code}]"
-        except (json.JSONDecodeError, TypeError, AttributeError):
-            logger.debug("Could not parse terminal result as JSON for exit code check")
         return False, ""
 
     # Memory-specific: distinguish "full" from real errors
     if tool_name == "memory":
-        try:
-            data = json.loads(result)
+        data = safe_json_loads(result)
+        if isinstance(data, dict):
             if data.get("success") is False and "exceed the limit" in data.get("error", ""):
                 return True, " [full]"
-        except (json.JSONDecodeError, TypeError, AttributeError):
-            logger.debug("Could not parse memory result as JSON for capacity check")
 
     # Generic heuristic for non-terminal tools
     lower = result[:500].lower()
@@ -970,22 +965,6 @@ _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

@@ -27,12 +27,14 @@ _PROVIDER_PREFIXES: frozenset[str] = frozenset({
     "gemini", "zai", "kimi-coding", "minimax", "minimax-cn", "anthropic", "deepseek",
     "opencode-zen", "opencode-go", "ai-gateway", "kilocode", "alibaba",
     "qwen-oauth",
+    "xiaomi",
     "custom", "local",
     # Common aliases
     "google", "google-gemini", "google-ai-studio",
     "glm", "z-ai", "z.ai", "zhipu", "github", "github-copilot",
     "github-models", "kimi", "moonshot", "claude", "deep-seek",
     "opencode", "zen", "go", "vercel", "kilo", "dashscope", "aliyun", "qwen",
+    "mimo", "xiaomi-mimo",
     "qwen-portal",
 })
 
@@ -83,6 +85,11 @@ CONTEXT_PROBE_TIERS = [
 # Default context length when no detection method succeeds.
 DEFAULT_FALLBACK_CONTEXT = CONTEXT_PROBE_TIERS[0]
 
+# Minimum context length required to run Hermes Agent.  Models with fewer
+# tokens cannot maintain enough working memory for tool-calling workflows.
+# Sessions, model switches, and cron jobs should reject models below this.
+MINIMUM_CONTEXT_LENGTH = 64_000
+
 # Thin fallback defaults — only broad model family patterns.
 # These fire only when provider is unknown AND models.dev/OpenRouter/Anthropic
 # all miss. Replaced the previous 80+ entry dict.
@@ -113,19 +120,31 @@ 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
@@ -136,10 +155,11 @@ DEFAULT_CONTEXT_LENGTHS = {
     "deepseek-ai/DeepSeek-V3.2": 65536,
     "moonshotai/Kimi-K2.5": 262144,
     "moonshotai/Kimi-K2-Thinking": 262144,
-    "MiniMaxAI/MiniMax-M2.5": 1048576,
-    "XiaomiMiMo/MiMo-V2-Flash": 32768,
-    "mimo-v2-pro": 1048576,
-    "mimo-v2-omni": 1048576,
+    "MiniMaxAI/MiniMax-M2.5": 204800,
+    "XiaomiMiMo/MiMo-V2-Flash": 256000,
+    "mimo-v2-pro": 1000000,
+    "mimo-v2-omni": 256000,
+    "mimo-v2-flash": 256000,
     "zai-org/GLM-5": 202752,
 }
 
@@ -164,6 +184,12 @@ _MAX_COMPLETION_KEYS = (
 
 # Local server hostnames / address patterns
 _LOCAL_HOSTS = ("localhost", "127.0.0.1", "::1", "0.0.0.0")
+# Docker / Podman / Lima DNS names that resolve to the host machine
+_CONTAINER_LOCAL_SUFFIXES = (
+    ".docker.internal",
+    ".containers.internal",
+    ".lima.internal",
+)
 
 
 def _normalize_base_url(base_url: str) -> str:
@@ -197,6 +223,10 @@ _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",
+    "api.xiaomimimo.com": "xiaomi",
+    "xiaomimimo.com": "xiaomi",
 }
 
 
@@ -235,6 +265,9 @@ def is_local_endpoint(base_url: str) -> bool:
         return False
     if host in _LOCAL_HOSTS:
         return True
+    # Docker / Podman / Lima internal DNS names (e.g. host.docker.internal)
+    if any(host.endswith(suffix) for suffix in _CONTAINER_LOCAL_SUFFIXES):
+        return True
     # RFC-1918 private ranges and link-local
     import ipaddress
     try:
@@ -602,6 +635,49 @@ 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).
 
@@ -969,16 +1045,21 @@ def get_model_context_length(
 
 
 def estimate_tokens_rough(text: str) -> int:
-    """Rough token estimate (~4 chars/token) for pre-flight checks."""
+    """Rough token estimate (~4 chars/token) for pre-flight checks.
+
+    Uses ceiling division so short texts (1-3 chars) never estimate as
+    0 tokens, which would cause the compressor and pre-flight checks to
+    systematically undercount when many short tool results are present.
+    """
     if not text:
         return 0
-    return len(text) // 4
+    return (len(text) + 3) // 4
 
 
 def estimate_messages_tokens_rough(messages: List[Dict[str, Any]]) -> int:
     """Rough token estimate for a message list (pre-flight only)."""
     total_chars = sum(len(str(msg)) for msg in messages)
-    return total_chars // 4
+    return (total_chars + 3) // 4
 
 
 def estimate_request_tokens_rough(
@@ -1001,4 +1082,4 @@ def estimate_request_tokens_rough(
         total_chars += sum(len(str(msg)) for msg in messages)
     if tools:
         total_chars += len(str(tools))
-    return total_chars // 4
+    return (total_chars + 3) // 4

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
@@ -164,6 +161,7 @@ PROVIDER_TO_MODELS_DEV: Dict[str, str] = {
     "gemini": "google",
     "google": "google",
     "xai": "xai",
+    "xiaomi": "xiaomi",
     "nvidia": "nvidia",
     "groq": "groq",
     "mistral": "mistral",
@@ -386,7 +384,14 @@ def get_model_capabilities(provider: str, model: str) -> Optional[ModelCapabilit
 
     # Extract capability flags (default to False if missing)
     supports_tools = bool(entry.get("tool_call", False))
-    supports_vision = bool(entry.get("attachment", False))
+    # Vision: check both the `attachment` flag and `modalities.input` for "image".
+    # Some models (e.g. gemma-4) list image in input modalities but not attachment.
+    input_mods = entry.get("modalities", {})
+    if isinstance(input_mods, dict):
+        input_mods = input_mods.get("input", [])
+    else:
+        input_mods = []
+    supports_vision = bool(entry.get("attachment", False)) or "image" in input_mods
     supports_reasoning = bool(entry.get("reasoning", False))
 
     # Extract limits
@@ -634,43 +639,6 @@ 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 +676,3 @@ 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

@@ -12,7 +12,7 @@ import threading
 from collections import OrderedDict
 from pathlib import Path
 
-from hermes_constants import get_hermes_home
+from hermes_constants import get_hermes_home, get_skills_dir
 from typing import Optional
 
 from agent.skill_utils import (
@@ -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"),
@@ -356,6 +356,14 @@ PLATFORM_HINTS = {
         "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
@@ -479,7 +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):
@@ -487,21 +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",
@@ -551,8 +548,7 @@ def build_skills_system_prompt(
     are read-only — they appear in the index but new skills are always created
     in the local dir.  Local skills take precedence when names collide.
     """
-    hermes_home = get_hermes_home()
-    skills_dir = hermes_home / "skills"
+    skills_dir = get_skills_dir()
     external_dirs = get_all_skills_dirs()[1:]  # skip local (index 0)
 
     if not skills_dir.exists() and not external_dirs:
@@ -561,9 +557,10 @@ 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

@@ -12,7 +12,7 @@ import sys
 from pathlib import Path
 from typing import Any, Dict, List, Set, Tuple
 
-from hermes_constants import get_hermes_home
+from hermes_constants import get_config_path, get_skills_dir
 
 logger = logging.getLogger(__name__)
 
@@ -130,7 +130,7 @@ def get_disabled_skill_names(platform: str | None = None) -> Set[str]:
     Reads the config file directly (no CLI config imports) to stay
     lightweight.
     """
-    config_path = get_hermes_home() / "config.yaml"
+    config_path = get_config_path()
     if not config_path.exists():
         return set()
     try:
@@ -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(
@@ -177,7 +178,7 @@ def get_external_skills_dirs() -> List[Path]:
     path.  Only directories that actually exist are returned.  Duplicates and
     paths that resolve to the local ``~/.hermes/skills/`` are silently skipped.
     """
-    config_path = get_hermes_home() / "config.yaml"
+    config_path = get_config_path()
     if not config_path.exists():
         return []
     try:
@@ -199,7 +200,7 @@ def get_external_skills_dirs() -> List[Path]:
     if not isinstance(raw_dirs, list):
         return []
 
-    local_skills = (get_hermes_home() / "skills").resolve()
+    local_skills = get_skills_dir().resolve()
     seen: Set[Path] = set()
     result: List[Path] = []
 
@@ -229,7 +230,7 @@ def get_all_skills_dirs() -> List[Path]:
     The local dir is always first (and always included even if it doesn't exist
     yet — callers handle that).  External dirs follow in config order.
     """
-    dirs = [get_hermes_home() / "skills"]
+    dirs = [get_skills_dir()]
     dirs.extend(get_external_skills_dirs())
     return dirs
 
@@ -383,7 +384,7 @@ def resolve_skill_config_values(
     current values (or the declared default if the key isn't set).
     Path values are expanded via ``os.path.expanduser``.
     """
-    config_path = get_hermes_home() / "config.yaml"
+    config_path = get_config_path()
     config: Dict[str, Any] = {}
     if config_path.exists():
         try:

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

@@ -24,6 +24,7 @@ model:
   #   "minimax"      - MiniMax global (requires: MINIMAX_API_KEY)
   #   "minimax-cn"   - MiniMax China (requires: MINIMAX_CN_API_KEY)
   #   "huggingface"  - Hugging Face Inference (requires: HF_TOKEN)
+  #   "xiaomi"       - Xiaomi MiMo (requires: XIAOMI_API_KEY)
   #   "kilocode"     - KiloCode gateway (requires: KILOCODE_API_KEY)
   #   "ai-gateway"   - Vercel AI Gateway (requires: AI_GATEWAY_API_KEY)
   #
@@ -48,6 +49,25 @@ 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 +137,8 @@ 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 +229,18 @@ 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)
@@ -455,6 +481,12 @@ agent:
   # 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
@@ -557,7 +589,7 @@ 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)
 #
@@ -586,7 +618,7 @@ 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)
 #
@@ -659,7 +691,11 @@ 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
 
@@ -738,6 +774,11 @@ display:
   # Toggle at runtime with /verbose in the CLI
   tool_progress: all
 
+  # Gateway-only natural mid-turn assistant updates.
+  # When true, completed assistant status messages are sent as separate chat
+  # messages. This is independent of tool_progress and gateway streaming.
+  interim_assistant_messages: true
+
   # What Enter does when Hermes is already busy in the CLI.
   #   interrupt: Interrupt the current run and redirect Hermes (default)
   #   queue:     Queue your message for the next turn
@@ -746,7 +787,7 @@ display:
 
   # Background process notifications (gateway/messaging only).
   # Controls how chatty the process watcher is when you use
-  # terminal(background=true, check_interval=...) from Telegram/Discord/etc.
+  # terminal(background=true, notify_on_complete=true) from Telegram/Discord/etc.
   #   off:     No watcher messages at all
   #   result:  Only the final completion message
   #   error:   Only the final message when exit code != 0

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", "bluebubbles",
+    "wecom", "wecom_callback", "weixin", "sms", "email", "webhook", "bluebubbles",
 })
 
 from cron.jobs import get_due_jobs, mark_job_run, save_job_output, advance_next_run
@@ -219,6 +219,21 @@ def _deliver_result(job: dict, content: str, adapters=None, loop=None) -> Option
     chat_id = target["chat_id"]
     thread_id = target.get("thread_id")
 
+    # Diagnostic: log thread_id for topic-aware delivery debugging
+    origin = job.get("origin") or {}
+    origin_thread = origin.get("thread_id")
+    if origin_thread and not thread_id:
+        logger.warning(
+            "Job '%s': origin has thread_id=%s but delivery target lost it "
+            "(deliver=%s, target=%s)",
+            job["id"], origin_thread, job.get("deliver", "local"), target,
+        )
+    elif thread_id:
+        logger.debug(
+            "Job '%s': delivering to %s:%s thread_id=%s",
+            job["id"], platform_name, chat_id, thread_id,
+        )
+
     from tools.send_message_tool import _send_to_platform
     from gateway.config import load_gateway_config, Platform
 
@@ -234,6 +249,8 @@ def _deliver_result(job: dict, content: str, adapters=None, loop=None) -> Option
         "dingtalk": Platform.DINGTALK,
         "feishu": Platform.FEISHU,
         "wecom": Platform.WECOM,
+        "wecom_callback": Platform.WECOM_CALLBACK,
+        "weixin": Platform.WEIXIN,
         "email": Platform.EMAIL,
         "sms": Platform.SMS,
         "bluebubbles": Platform.BLUEBUBBLES,
@@ -346,7 +363,42 @@ 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]:
@@ -393,17 +445,27 @@ 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:
@@ -412,17 +474,10 @@ 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}"
 
@@ -586,6 +641,15 @@ def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:
         except Exception as e:
             logger.warning("Job '%s': failed to load config.yaml, using defaults: %s", job_id, e)
 
+        # Apply IPv4 preference if configured.
+        try:
+            from hermes_constants import apply_ipv4_preference
+            _net_cfg = _cfg.get("network", {})
+            if isinstance(_net_cfg, dict) and _net_cfg.get("force_ipv4"):
+                apply_ipv4_preference(force=True)
+        except Exception:
+            pass
+
         # Reasoning config from config.yaml
         from hermes_constants import parse_reasoning_effort
         effort = str(_cfg.get("agent", {}).get("reasoning_effort", "")).strip()
@@ -646,6 +710,24 @@ 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"),
@@ -657,12 +739,15 @@ 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"),
             provider_sort=pr.get("sort"),
             disabled_toolsets=["cronjob", "messaging", "clarify"],
             quiet_mode=True,
+            skip_context_files=True,  # Don't inject SOUL.md/AGENTS.md from scheduler cwd
             skip_memory=True,  # Cron system prompts would corrupt user representations
             platform="cron",
             session_id=_cron_session_id,
@@ -711,7 +796,7 @@ 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

@@ -5,11 +5,41 @@ set -e
 HERMES_HOME="/opt/data"
 INSTALL_DIR="/opt/hermes"
 
+# --- Privilege dropping via gosu ---
+# When started as root (the default), optionally remap the hermes user/group
+# to match host-side ownership, fix volume permissions, then re-exec as hermes.
+if [ "$(id -u)" = "0" ]; then
+    if [ -n "$HERMES_UID" ] && [ "$HERMES_UID" != "$(id -u hermes)" ]; then
+        echo "Changing hermes UID to $HERMES_UID"
+        usermod -u "$HERMES_UID" hermes
+    fi
+
+    if [ -n "$HERMES_GID" ] && [ "$HERMES_GID" != "$(id -g hermes)" ]; then
+        echo "Changing hermes GID to $HERMES_GID"
+        groupmod -g "$HERMES_GID" hermes
+    fi
+
+    actual_hermes_uid=$(id -u hermes)
+    if [ "$(stat -c %u "$HERMES_HOME" 2>/dev/null)" != "$actual_hermes_uid" ]; then
+        echo "$HERMES_HOME is not owned by $actual_hermes_uid, fixing"
+        chown -R hermes:hermes "$HERMES_HOME"
+    fi
+
+    echo "Dropping root privileges"
+    exec gosu hermes "$0" "$@"
+fi
+
+# --- Running as hermes from here ---
+source "${INSTALL_DIR}/.venv/bin/activate"
+
 # Create essential directory structure.  Cache and platform directories
 # (cache/images, cache/audio, platforms/whatsapp, etc.) are created on
 # demand by the application — don't pre-create them here so new installs
 # get the consolidated layout from get_hermes_dir().
-mkdir -p "$HERMES_HOME"/{cron,sessions,logs,hooks,memories,skills}
+# 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

docs/migration/openclaw.md

@@ -11,12 +11,14 @@ When you run `hermes setup` for the first time and Hermes detects `~/.openclaw`,
 ### 2. CLI Command (quick, scriptable)
 
 ```bash
-hermes claw migrate                      # Full migration with confirmation prompt
-hermes claw migrate --dry-run            # Preview what would happen
+hermes claw migrate                      # Preview then migrate (always shows preview first)
+hermes claw migrate --dry-run            # Preview only, no changes
 hermes claw migrate --preset user-data   # Migrate without API keys/secrets
 hermes claw migrate --yes                # Skip confirmation prompt
 ```
 
+The migration always shows a full preview of what will be imported before making any changes. You review the preview and confirm before anything is written.
+
 **All options:**
 
 | Flag | Description |
@@ -39,7 +41,7 @@ Ask the agent to run the migration for you:
 ```
 
 The agent will use the `openclaw-migration` skill to:
-1. Run a dry-run first to preview changes
+1. Run a preview first to show what would change
 2. Ask about conflict resolution (SOUL.md, skills, etc.)
 3. Let you choose between `user-data` and `full` presets
 4. Execute the migration with your choices
@@ -58,16 +60,31 @@ The agent will use the `openclaw-migration` skill to:
 | Messaging settings | `~/.openclaw/config.yaml` (TELEGRAM_ALLOWED_USERS, MESSAGING_CWD) | `~/.hermes/.env` |
 | TTS assets | `~/.openclaw/workspace/tts/` | `~/.hermes/tts/` |
 
+Workspace files are also checked at `workspace.default/` and `workspace-main/` as fallback paths (OpenClaw renamed `workspace/` to `workspace-main/` in recent versions).
+
 ### `full` preset (adds to `user-data`)
 | Item | Source | Destination |
 |------|--------|-------------|
-| Telegram bot token | `~/.openclaw/config.yaml` | `~/.hermes/.env` |
-| OpenRouter API key | `~/.openclaw/.env` or config | `~/.hermes/.env` |
-| OpenAI API key | `~/.openclaw/.env` or config | `~/.hermes/.env` |
-| Anthropic API key | `~/.openclaw/.env` or config | `~/.hermes/.env` |
-| ElevenLabs API key | `~/.openclaw/.env` or config | `~/.hermes/.env` |
+| Telegram bot token | `openclaw.json` channels config | `~/.hermes/.env` |
+| OpenRouter API key | `.env`, `openclaw.json`, or `openclaw.json["env"]` | `~/.hermes/.env` |
+| OpenAI API key | `.env`, `openclaw.json`, or `openclaw.json["env"]` | `~/.hermes/.env` |
+| Anthropic API key | `.env`, `openclaw.json`, or `openclaw.json["env"]` | `~/.hermes/.env` |
+| ElevenLabs API key | `.env`, `openclaw.json`, or `openclaw.json["env"]` | `~/.hermes/.env` |
 
-Only these 6 allowlisted secrets are ever imported. Other credentials are skipped and reported.
+API keys are searched across four sources: inline config values, `~/.openclaw/.env`, the `openclaw.json` `"env"` sub-object, and per-agent auth profiles.
+
+Only allowlisted secrets are ever imported. Other credentials are skipped and reported.
+
+## OpenClaw Schema Compatibility
+
+The migration handles both old and current OpenClaw config layouts:
+
+- **Channel tokens**: Reads from flat paths (`channels.telegram.botToken`) and the newer `accounts.default` layout (`channels.telegram.accounts.default.botToken`)
+- **TTS provider**: OpenClaw renamed "edge" to "microsoft" — both are recognized and mapped to Hermes' "edge"
+- **Provider API types**: Both short (`openai`, `anthropic`) and hyphenated (`openai-completions`, `anthropic-messages`, `google-generative-ai`) values are mapped correctly
+- **thinkingDefault**: All enum values are handled including newer ones (`minimal`, `xhigh`, `adaptive`)
+- **Matrix**: Uses `accessToken` field (not `botToken`)
+- **SecretRef formats**: Plain strings, env templates (`${VAR}`), and `source: "env"` SecretRefs are resolved. `source: "file"` and `source: "exec"` SecretRefs produce a warning — add those keys manually after migration.
 
 ## Conflict Handling
 
@@ -84,18 +101,24 @@ For skills, you can also use `--skill-conflict rename` to import conflicting ski
 
 ## Migration Report
 
-Every migration (including dry runs) produces a report showing:
+Every migration produces a report showing:
 - **Migrated items** — what was successfully imported
 - **Conflicts** — items skipped because they already exist
 - **Skipped items** — items not found in the source
 - **Errors** — items that failed to import
 
-For execute runs, the full report is saved to `~/.hermes/migration/openclaw/<timestamp>/`.
+For executed migrations, the full report is saved to `~/.hermes/migration/openclaw/<timestamp>/`.
+
+## Post-Migration Notes
+
+- **Skills require a new session** — imported skills take effect after restarting your agent or starting a new chat.
+- **WhatsApp requires re-pairing** — WhatsApp uses QR-code pairing, not token-based auth. Run `hermes whatsapp` to pair.
+- **Archive cleanup** — after migration, you'll be offered to rename `~/.openclaw/` to `.openclaw.pre-migration/` to prevent state confusion. You can also run `hermes claw cleanup` later.
 
 ## Troubleshooting
 
 ### "OpenClaw directory not found"
-The migration looks for `~/.openclaw` by default. If your OpenClaw is installed elsewhere, use `--source`:
+The migration looks for `~/.openclaw` by default, then tries `~/.clawdbot` and `~/.moltbot`. If your OpenClaw is installed elsewhere, use `--source`:
 ```bash
 hermes claw migrate --source /path/to/.openclaw
 ```
@@ -108,3 +131,12 @@ hermes skills install openclaw-migration
 
 ### Memory overflow
 If your OpenClaw MEMORY.md or USER.md exceeds Hermes' character limits, excess entries are exported to an overflow file in the migration report directory. You can manually review and add the most important ones.
+
+### API keys not found
+Keys might be stored in different places depending on your OpenClaw setup:
+- `~/.openclaw/.env` file
+- Inline in `openclaw.json` under `models.providers.*.apiKey`
+- In `openclaw.json` under the `"env"` or `"env.vars"` sub-objects
+- In `~/.openclaw/agents/main/agent/auth-profiles.json`
+
+The migration checks all four. If keys use `source: "file"` or `source: "exec"` SecretRefs, they can't be resolved automatically — add them via `hermes config set`.

docs/specs/container-cli-review-fixes.md

@@ -0,0 +1,329 @@
+# Container-Aware CLI Review Fixes Spec
+
+**PR:** NousResearch/hermes-agent#7543
+**Review:** cursor[bot] bugbot review (4094049442) + two prior rounds
+**Date:** 2026-04-12
+**Branch:** `feat/container-aware-cli-clean`
+
+## Review Issues Summary
+
+Six issues were raised across three bugbot review rounds. Three were fixed in intermediate commits (38277a6a, 726cf90f). This spec addresses remaining design concerns surfaced by those reviews and simplifies the implementation based on interview decisions.
+
+| # | Issue | Severity | Status |
+|---|-------|----------|--------|
+| 1 | `os.execvp` retry loop unreachable | Medium | Fixed in 79e8cd12 (switched to subprocess.run) |
+| 2 | Redundant `shutil.which("sudo")` | Medium | Fixed in 38277a6a (reuses `sudo` var) |
+| 3 | Missing `chown -h` on symlink update | Low | Fixed in 38277a6a |
+| 4 | Container routing after `parse_args()` | High | Fixed in 726cf90f |
+| 5 | Hardcoded `/home/${user}` | Medium | Fixed in 726cf90f |
+| 6 | Group membership not gated on `container.enable` | Low | Fixed in 726cf90f |
+
+The mechanical fixes are in place but the overall design needs revision. The retry loop, error swallowing, and process model have deeper issues than what the bugbot flagged.
+
+---
+
+## Spec: Revised `_exec_in_container`
+
+### Design Principles
+
+1. **Let it crash.** No silent fallbacks. If `.container-mode` exists but something goes wrong, the error propagates naturally (Python traceback). The only case where container routing is skipped is when `.container-mode` doesn't exist or `HERMES_DEV=1`.
+2. **No retries.** Probe once for sudo, exec once. If it fails, docker/podman's stderr reaches the user verbatim.
+3. **Completely transparent.** No error wrapping, no prefixes, no spinners. Docker's output goes straight through.
+4. **`os.execvp` on the happy path.** Replace the Python process entirely so there's no idle parent during interactive sessions. Note: `execvp` never returns on success (process is replaced) and raises `OSError` on failure (it does not return a value). The container process's exit code becomes the process exit code by definition — no explicit propagation needed.
+5. **One human-readable exception to "let it crash".** `subprocess.TimeoutExpired` from the sudo probe gets a specific catch with a readable message, since a raw traceback for "your Docker daemon is slow" is confusing. All other exceptions propagate naturally.
+
+### Execution Flow
+
+```
+1. get_container_exec_info()
+   - HERMES_DEV=1 → return None (skip routing)
+   - Inside container → return None (skip routing)
+   - .container-mode doesn't exist → return None (skip routing)
+   - .container-mode exists → parse and return dict
+   - .container-mode exists but malformed/unreadable → LET IT CRASH (no try/except)
+
+2. _exec_in_container(container_info, sys.argv[1:])
+   a. shutil.which(backend) → if None, print "{backend} not found on PATH" and sys.exit(1)
+   b. Sudo probe: subprocess.run([runtime, "inspect", "--format", "ok", container_name], timeout=15)
+      - If succeeds → needs_sudo = False
+      - If fails → try subprocess.run([sudo, "-n", runtime, "inspect", ...], timeout=15)
+        - If succeeds → needs_sudo = True
+        - If fails → print error with sudoers hint (including why -n is required) and sys.exit(1)
+      - If TimeoutExpired → catch specifically, print human-readable message about slow daemon
+   c. Build exec_cmd: [sudo? + runtime, "exec", tty_flags, "-u", exec_user, env_flags, container, hermes_bin, *cli_args]
+   d. os.execvp(exec_cmd[0], exec_cmd)
+      - On success: process is replaced — Python is gone, container exit code IS the process exit code
+      - On OSError: let it crash (natural traceback)
+```
+
+### Changes to `hermes_cli/main.py`
+
+#### `_exec_in_container` — rewrite
+
+Remove:
+- The entire retry loop (`max_retries`, `for attempt in range(...)`)
+- Spinner logic (`"Waiting for container..."`, dots)
+- Exit code classification (125/126/127 handling)
+- `subprocess.run` for the exec call (keep it only for the sudo probe)
+- Special TTY vs non-TTY retry counts
+- The `time` import (no longer needed)
+
+Change:
+- Use `os.execvp(exec_cmd[0], exec_cmd)` as the final call
+- Keep the `subprocess` import only for the sudo probe
+- Keep TTY detection for the `-it` vs `-i` flag
+- Keep env var forwarding (TERM, COLORTERM, LANG, LC_ALL)
+- Keep the sudo probe as-is (it's the one "smart" part)
+- Bump probe `timeout` from 5s to 15s — cold podman on a loaded machine needs headroom
+- Catch `subprocess.TimeoutExpired` specifically on both probe calls — print a readable message about the daemon being unresponsive instead of a raw traceback
+- Expand the sudoers hint error message to explain *why* `-n` (non-interactive) is required: a password prompt would hang the CLI or break piped commands
+
+The function becomes roughly:
+
+```python
+def _exec_in_container(container_info: dict, cli_args: list):
+    """Replace the current process with a command inside the managed container.
+
+    Probes whether sudo is needed (rootful containers), then os.execvp
+    into the container. If exec fails, the OS error propagates naturally.
+    """
+    import shutil
+    import subprocess
+
+    backend = container_info["backend"]
+    container_name = container_info["container_name"]
+    exec_user = container_info["exec_user"]
+    hermes_bin = container_info["hermes_bin"]
+
+    runtime = shutil.which(backend)
+    if not runtime:
+        print(f"Error: {backend} not found on PATH. Cannot route to container.",
+              file=sys.stderr)
+        sys.exit(1)
+
+    # Probe whether we need sudo to see the rootful container.
+    # Timeout is 15s — cold podman on a loaded machine can take a while.
+    # TimeoutExpired is caught specifically for a human-readable message;
+    # all other exceptions propagate naturally.
+    needs_sudo = False
+    sudo = None
+    try:
+        probe = subprocess.run(
+            [runtime, "inspect", "--format", "ok", container_name],
+            capture_output=True, text=True, timeout=15,
+        )
+    except subprocess.TimeoutExpired:
+        print(
+            f"Error: timed out waiting for {backend} to respond.\n"
+            f"The {backend} daemon may be unresponsive or starting up.",
+            file=sys.stderr,
+        )
+        sys.exit(1)
+
+    if probe.returncode != 0:
+        sudo = shutil.which("sudo")
+        if sudo:
+            try:
+                probe2 = subprocess.run(
+                    [sudo, "-n", runtime, "inspect", "--format", "ok", container_name],
+                    capture_output=True, text=True, timeout=15,
+                )
+            except subprocess.TimeoutExpired:
+                print(
+                    f"Error: timed out waiting for sudo {backend} to respond.",
+                    file=sys.stderr,
+                )
+                sys.exit(1)
+
+            if probe2.returncode == 0:
+                needs_sudo = True
+            else:
+                print(
+                    f"Error: container '{container_name}' not found via {backend}.\n"
+                    f"\n"
+                    f"The NixOS service runs the container as root. Your user cannot\n"
+                    f"see it because {backend} uses per-user namespaces.\n"
+                    f"\n"
+                    f"Fix: grant passwordless sudo for {backend}. The -n (non-interactive)\n"
+                    f"flag is required because the CLI calls sudo non-interactively —\n"
+                    f"a password prompt would hang or break piped commands:\n"
+                    f"\n"
+                    f'  security.sudo.extraRules = [{{\n'
+                    f'    users = [ "{os.getenv("USER", "your-user")}" ];\n'
+                    f'    commands = [{{ command = "{runtime}"; options = [ "NOPASSWD" ]; }}];\n'
+                    f'  }}];\n'
+                    f"\n"
+                    f"Or run: sudo hermes {' '.join(cli_args)}",
+                    file=sys.stderr,
+                )
+                sys.exit(1)
+        else:
+            print(
+                f"Error: container '{container_name}' not found via {backend}.\n"
+                f"The container may be running under root. Try: sudo hermes {' '.join(cli_args)}",
+                file=sys.stderr,
+            )
+            sys.exit(1)
+
+    is_tty = sys.stdin.isatty()
+    tty_flags = ["-it"] if is_tty else ["-i"]
+
+    env_flags = []
+    for var in ("TERM", "COLORTERM", "LANG", "LC_ALL"):
+        val = os.environ.get(var)
+        if val:
+            env_flags.extend(["-e", f"{var}={val}"])
+
+    cmd_prefix = [sudo, "-n", runtime] if needs_sudo else [runtime]
+    exec_cmd = (
+        cmd_prefix + ["exec"]
+        + tty_flags
+        + ["-u", exec_user]
+        + env_flags
+        + [container_name, hermes_bin]
+        + cli_args
+    )
+
+    # execvp replaces this process entirely — it never returns on success.
+    # On failure it raises OSError, which propagates naturally.
+    os.execvp(exec_cmd[0], exec_cmd)
+```
+
+#### Container routing call site in `main()` — remove try/except
+
+Current:
+```python
+try:
+    from hermes_cli.config import get_container_exec_info
+    container_info = get_container_exec_info()
+    if container_info:
+        _exec_in_container(container_info, sys.argv[1:])
+        sys.exit(1)  # exec failed if we reach here
+except SystemExit:
+    raise
+except Exception:
+    pass  # Container routing unavailable, proceed locally
+```
+
+Revised:
+```python
+from hermes_cli.config import get_container_exec_info
+container_info = get_container_exec_info()
+if container_info:
+    _exec_in_container(container_info, sys.argv[1:])
+    # Unreachable: os.execvp never returns on success (process is replaced)
+    # and raises OSError on failure (which propagates as a traceback).
+    # This line exists only as a defensive assertion.
+    sys.exit(1)
+```
+
+No try/except. If `.container-mode` doesn't exist, `get_container_exec_info()` returns `None` and we skip routing. If it exists but is broken, the exception propagates with a natural traceback.
+
+Note: `sys.exit(1)` after `_exec_in_container` is dead code in all paths — `os.execvp` either replaces the process or raises. It's kept as a belt-and-suspenders assertion with a comment marking it unreachable, not as actual error handling.
+
+### Changes to `hermes_cli/config.py`
+
+#### `get_container_exec_info` — remove inner try/except
+
+Current code catches `(OSError, IOError)` and returns `None`. This silently hides permission errors, corrupt files, etc.
+
+Change: Remove the try/except around file reading. Keep the early returns for `HERMES_DEV=1` and `_is_inside_container()`. The `FileNotFoundError` from `open()` when `.container-mode` doesn't exist should still return `None` (this is the "container mode not enabled" case). All other exceptions propagate.
+
+```python
+def get_container_exec_info() -> Optional[dict]:
+    if os.environ.get("HERMES_DEV") == "1":
+        return None
+    if _is_inside_container():
+        return None
+
+    container_mode_file = get_hermes_home() / ".container-mode"
+
+    try:
+        with open(container_mode_file, "r") as f:
+            # ... parse key=value lines ...
+    except FileNotFoundError:
+        return None
+    # All other exceptions (PermissionError, malformed data, etc.) propagate
+
+    return { ... }
+```
+
+---
+
+## Spec: NixOS Module Changes
+
+### Symlink creation — simplify to two branches
+
+Current: 4 branches (symlink exists, directory exists, other file, doesn't exist).
+
+Revised: 2 branches.
+
+```bash
+if [ -d "${symlinkPath}" ] && [ ! -L "${symlinkPath}" ]; then
+  # Real directory — back it up, then create symlink
+  _backup="${symlinkPath}.bak.$(date +%s)"
+  echo "hermes-agent: backing up existing ${symlinkPath} to $_backup"
+  mv "${symlinkPath}" "$_backup"
+fi
+# For everything else (symlink, doesn't exist, etc.) — just force-create
+ln -sfn "${target}" "${symlinkPath}"
+chown -h ${user}:${cfg.group} "${symlinkPath}"
+```
+
+`ln -sfn` handles: existing symlink (replaces), doesn't exist (creates), and after the `mv` above (creates). The only case that needs special handling is a real directory, because `ln -sfn` cannot atomically replace a directory.
+
+Note: there is a theoretical race between the `[ -d ... ]` check and the `mv` (something could create/remove the directory in between). In practice this is a NixOS activation script running as root during `nixos-rebuild switch` — no other process should be touching `~/.hermes` at that moment. Not worth adding locking for.
+
+### Sudoers — document, don't auto-configure
+
+Do NOT add `security.sudo.extraRules` to the module. Document the sudoers requirement in the module's description/comments and in the error message the CLI prints when sudo probe fails.
+
+### Group membership gating — keep as-is
+
+The fix in 726cf90f (`cfg.container.enable && cfg.container.hostUsers != []`) is correct. Leftover group membership when container mode is disabled is harmless. No cleanup needed.
+
+---
+
+## Spec: Test Rewrite
+
+The existing test file (`tests/hermes_cli/test_container_aware_cli.py`) has 16 tests. With the simplified exec model, several are obsolete.
+
+### Tests to keep (update as needed)
+
+- `test_is_inside_container_dockerenv` — unchanged
+- `test_is_inside_container_containerenv` — unchanged
+- `test_is_inside_container_cgroup_docker` — unchanged
+- `test_is_inside_container_false_on_host` — unchanged
+- `test_get_container_exec_info_returns_metadata` — unchanged
+- `test_get_container_exec_info_none_inside_container` — unchanged
+- `test_get_container_exec_info_none_without_file` — unchanged
+- `test_get_container_exec_info_skipped_when_hermes_dev` — unchanged
+- `test_get_container_exec_info_not_skipped_when_hermes_dev_zero` — unchanged
+- `test_get_container_exec_info_defaults` — unchanged
+- `test_get_container_exec_info_docker_backend` — unchanged
+
+### Tests to add
+
+- `test_get_container_exec_info_crashes_on_permission_error` — verify that `PermissionError` propagates (no silent `None` return)
+- `test_exec_in_container_calls_execvp` — verify `os.execvp` is called with correct args (runtime, tty flags, user, env, container, binary, cli args)
+- `test_exec_in_container_sudo_probe_sets_prefix` — verify that when first probe fails and sudo probe succeeds, `os.execvp` is called with `sudo -n` prefix
+- `test_exec_in_container_no_runtime_hard_fails` — keep existing, verify `sys.exit(1)` when `shutil.which` returns None
+- `test_exec_in_container_non_tty_uses_i_only` — update to check `os.execvp` args instead of `subprocess.run` args
+- `test_exec_in_container_probe_timeout_prints_message` — verify that `subprocess.TimeoutExpired` from the probe produces a human-readable error and `sys.exit(1)`, not a raw traceback
+- `test_exec_in_container_container_not_running_no_sudo` — verify the path where runtime exists (`shutil.which` returns a path) but probe returns non-zero and no sudo is available. Should print the "container may be running under root" error. This is distinct from `no_runtime_hard_fails` which covers `shutil.which` returning None.
+
+### Tests to delete
+
+- `test_exec_in_container_tty_retries_on_container_failure` — retry loop removed
+- `test_exec_in_container_non_tty_retries_silently_exits_126` — retry loop removed
+- `test_exec_in_container_propagates_hermes_exit_code` — no subprocess.run to check exit codes; execvp replaces the process. Note: exit code propagation still works correctly — when `os.execvp` succeeds, the container's process *becomes* this process, so its exit code is the process exit code by OS semantics. No application code needed, no test needed. A comment in the function docstring documents this intent for future readers.
+
+---
+
+## Out of Scope
+
+- Auto-configuring sudoers rules in the NixOS module
+- Any changes to `get_container_exec_info` parsing logic beyond the try/except narrowing
+- Changes to `.container-mode` file format
+- Changes to the `HERMES_DEV=1` bypass
+- Changes to container detection logic (`_is_inside_container`)

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", "bluebubbles"):
-        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"
+    WECOM_CALLBACK = "wecom_callback"
+    WEIXIN = "weixin"
     BLUEBUBBLES = "bluebubbles"
 
 
@@ -189,7 +191,7 @@ class StreamingConfig:
     """Configuration for real-time token streaming to messaging platforms."""
     enabled: bool = False
     transport: str = "edit"       # "edit" (progressive editMessageText) or "off"
-    edit_interval: float = 0.3    # Seconds between message edits
+    edit_interval: float = 1.0    # Seconds between message edits (Telegram rate-limits at ~1/s)
     buffer_threshold: int = 40    # Chars before forcing an edit
     cursor: str = " ▉"           # Cursor shown during streaming
 
@@ -209,7 +211,7 @@ class StreamingConfig:
         return cls(
             enabled=data.get("enabled", False),
             transport=data.get("transport", "edit"),
-            edit_interval=float(data.get("edit_interval", 0.3)),
+            edit_interval=float(data.get("edit_interval", 1.0)),
             buffer_threshold=int(data.get("buffer_threshold", 40)),
             cursor=data.get("cursor", " ▉"),
         )
@@ -261,6 +263,11 @@ 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)
@@ -285,9 +292,14 @@ class GatewayConfig:
             # Feishu uses extra dict for app credentials
             elif platform == Platform.FEISHU and config.extra.get("app_id"):
                 connected.append(platform)
-            # WeCom uses extra dict for bot credentials
+            # WeCom bot mode uses extra dict for bot credentials
             elif platform == Platform.WECOM and config.extra.get("bot_id"):
                 connected.append(platform)
+            # WeCom callback mode uses corp_id or apps list
+            elif platform == Platform.WECOM_CALLBACK and (
+                config.extra.get("corp_id") or config.extra.get("apps")
+            ):
+                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)
@@ -532,8 +544,12 @@ 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, {})
@@ -546,6 +562,19 @@ 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):
@@ -566,6 +595,12 @@ 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"):
@@ -613,6 +648,8 @@ 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(
@@ -651,6 +688,7 @@ 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:
@@ -886,6 +924,9 @@ 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")
@@ -952,6 +993,64 @@ def _apply_env_overrides(config: GatewayConfig) -> None:
                 name=os.getenv("WECOM_HOME_CHANNEL_NAME", "Home"),
             )
 
+    # WeCom callback mode (self-built apps)
+    wecom_callback_corp_id = os.getenv("WECOM_CALLBACK_CORP_ID")
+    wecom_callback_corp_secret = os.getenv("WECOM_CALLBACK_CORP_SECRET")
+    if wecom_callback_corp_id and wecom_callback_corp_secret:
+        if Platform.WECOM_CALLBACK not in config.platforms:
+            config.platforms[Platform.WECOM_CALLBACK] = PlatformConfig()
+        config.platforms[Platform.WECOM_CALLBACK].enabled = True
+        config.platforms[Platform.WECOM_CALLBACK].extra.update({
+            "corp_id": wecom_callback_corp_id,
+            "corp_secret": wecom_callback_corp_secret,
+            "agent_id": os.getenv("WECOM_CALLBACK_AGENT_ID", ""),
+            "token": os.getenv("WECOM_CALLBACK_TOKEN", ""),
+            "encoding_aes_key": os.getenv("WECOM_CALLBACK_ENCODING_AES_KEY", ""),
+            "host": os.getenv("WECOM_CALLBACK_HOST", "0.0.0.0"),
+            "port": int(os.getenv("WECOM_CALLBACK_PORT", "8645")),
+        })
+
+    # 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_split_multiline = os.getenv("WEIXIN_SPLIT_MULTILINE_MESSAGES", "").strip()
+        if weixin_split_multiline:
+            extra["split_multiline_messages"] = weixin_split_multiline
+        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")

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/display_config.py

@@ -0,0 +1,206 @@
+"""Per-platform display/verbosity configuration resolver.
+
+Provides ``resolve_display_setting()`` — the single entry-point for reading
+display settings with platform-specific overrides and sensible defaults.
+
+Resolution order (first non-None wins):
+    1. ``display.platforms.<platform>.<key>``  — explicit per-platform user override
+    2. ``display.<key>``                       — global user setting
+    3. ``_PLATFORM_DEFAULTS[<platform>][<key>]``  — built-in sensible default
+    4. ``_GLOBAL_DEFAULTS[<key>]``              — built-in global default
+
+Backward compatibility: ``display.tool_progress_overrides`` is still read as a
+fallback for ``tool_progress`` when no ``display.platforms`` entry exists.  A
+config migration (version bump) automatically moves the old format into the new
+``display.platforms`` structure.
+"""
+
+from __future__ import annotations
+
+from typing import Any
+
+# ---------------------------------------------------------------------------
+# Overrideable display settings and their global defaults
+# ---------------------------------------------------------------------------
+# These are the settings that can be configured per-platform.
+# Other display settings (compact, personality, skin, etc.) are CLI-only
+# and don't participate in per-platform resolution.
+
+_GLOBAL_DEFAULTS: dict[str, Any] = {
+    "tool_progress": "all",
+    "show_reasoning": False,
+    "tool_preview_length": 0,
+    "streaming": None,  # None = follow top-level streaming config
+}
+
+# ---------------------------------------------------------------------------
+# Sensible per-platform defaults — tiered by platform capability
+# ---------------------------------------------------------------------------
+# Tier 1 (high): Supports message editing, typically personal/team use
+# Tier 2 (medium): Supports editing but often workspace/customer-facing
+# Tier 3 (low): No edit support — each progress msg is permanent
+# Tier 4 (minimal): Batch/non-interactive delivery
+
+_TIER_HIGH = {
+    "tool_progress": "all",
+    "show_reasoning": False,
+    "tool_preview_length": 40,
+    "streaming": None,  # follow global
+}
+
+_TIER_MEDIUM = {
+    "tool_progress": "new",
+    "show_reasoning": False,
+    "tool_preview_length": 40,
+    "streaming": None,
+}
+
+_TIER_LOW = {
+    "tool_progress": "off",
+    "show_reasoning": False,
+    "tool_preview_length": 40,
+    "streaming": False,
+}
+
+_TIER_MINIMAL = {
+    "tool_progress": "off",
+    "show_reasoning": False,
+    "tool_preview_length": 0,
+    "streaming": False,
+}
+
+_PLATFORM_DEFAULTS: dict[str, dict[str, Any]] = {
+    # Tier 1 — full edit support, personal/team use
+    "telegram":    _TIER_HIGH,
+    "discord":     _TIER_HIGH,
+
+    # Tier 2 — edit support, often customer/workspace channels
+    "slack":           _TIER_MEDIUM,
+    "mattermost":      _TIER_MEDIUM,
+    "matrix":          _TIER_MEDIUM,
+    "feishu":          _TIER_MEDIUM,
+
+    # Tier 3 — no edit support, progress messages are permanent
+    "signal":          _TIER_LOW,
+    "whatsapp":        _TIER_LOW,
+    "bluebubbles":     _TIER_LOW,
+    "weixin":          _TIER_LOW,
+    "wecom":           _TIER_LOW,
+    "wecom_callback":  _TIER_LOW,
+    "dingtalk":        _TIER_LOW,
+
+    # Tier 4 — batch or non-interactive delivery
+    "email":           _TIER_MINIMAL,
+    "sms":             _TIER_MINIMAL,
+    "webhook":         _TIER_MINIMAL,
+    "homeassistant":   _TIER_MINIMAL,
+    "api_server":      {**_TIER_HIGH, "tool_preview_length": 0},
+}
+
+# Canonical set of per-platform overrideable keys (for validation).
+OVERRIDEABLE_KEYS = frozenset(_GLOBAL_DEFAULTS.keys())
+
+
+def resolve_display_setting(
+    user_config: dict,
+    platform_key: str,
+    setting: str,
+    fallback: Any = None,
+) -> Any:
+    """Resolve a display setting with per-platform override support.
+
+    Parameters
+    ----------
+    user_config : dict
+        The full parsed config.yaml dict.
+    platform_key : str
+        Platform config key (e.g. ``"telegram"``, ``"slack"``).  Use
+        ``_platform_config_key(source.platform)`` from gateway/run.py.
+    setting : str
+        Display setting name (e.g. ``"tool_progress"``, ``"show_reasoning"``).
+    fallback : Any
+        Fallback value when the setting isn't found anywhere.
+
+    Returns
+    -------
+    The resolved value, or *fallback* if nothing is configured.
+    """
+    display_cfg = user_config.get("display") or {}
+
+    # 1. Explicit per-platform override (display.platforms.<platform>.<key>)
+    platforms = display_cfg.get("platforms") or {}
+    plat_overrides = platforms.get(platform_key)
+    if isinstance(plat_overrides, dict):
+        val = plat_overrides.get(setting)
+        if val is not None:
+            return _normalise(setting, val)
+
+    # 1b. Backward compat: display.tool_progress_overrides.<platform>
+    if setting == "tool_progress":
+        legacy = display_cfg.get("tool_progress_overrides")
+        if isinstance(legacy, dict):
+            val = legacy.get(platform_key)
+            if val is not None:
+                return _normalise(setting, val)
+
+    # 2. Global user setting (display.<key>)
+    val = display_cfg.get(setting)
+    if val is not None:
+        return _normalise(setting, val)
+
+    # 3. Built-in platform default
+    plat_defaults = _PLATFORM_DEFAULTS.get(platform_key)
+    if plat_defaults:
+        val = plat_defaults.get(setting)
+        if val is not None:
+            return val
+
+    # 4. Built-in global default
+    val = _GLOBAL_DEFAULTS.get(setting)
+    if val is not None:
+        return val
+
+    return fallback
+
+
+def get_platform_defaults(platform_key: str) -> dict[str, Any]:
+    """Return the built-in default display settings for a platform.
+
+    Falls back to ``_GLOBAL_DEFAULTS`` for unknown platforms.
+    """
+    return dict(_PLATFORM_DEFAULTS.get(platform_key, _GLOBAL_DEFAULTS))
+
+
+def get_effective_display(user_config: dict, platform_key: str) -> dict[str, Any]:
+    """Return the fully-resolved display settings for a platform.
+
+    Useful for status commands that want to show all effective settings.
+    """
+    return {
+        key: resolve_display_setting(user_config, platform_key, key)
+        for key in OVERRIDEABLE_KEYS
+    }
+
+
+# ---------------------------------------------------------------------------
+# Helpers
+# ---------------------------------------------------------------------------
+
+def _normalise(setting: str, value: Any) -> Any:
+    """Normalise YAML quirks (bare ``off`` → False in YAML 1.1)."""
+    if setting == "tool_progress":
+        if value is False:
+            return "off"
+        if value is True:
+            return "all"
+        return str(value).lower()
+    if setting in ("show_reasoning", "streaming"):
+        if isinstance(value, str):
+            return value.lower() in ("true", "1", "yes", "on")
+        return bool(value)
+    if setting == "tool_preview_length":
+        try:
+            return int(value)
+        except (TypeError, ValueError):
+            return 0
+    return value

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__)
@@ -49,6 +53,7 @@ DEFAULT_HOST = "127.0.0.1"
 DEFAULT_PORT = 8642
 MAX_STORED_RESPONSES = 100
 MAX_REQUEST_BYTES = 1_000_000  # 1 MB default limit for POST bodies
+CHAT_COMPLETIONS_SSE_KEEPALIVE_SECONDS = 30.0
 
 
 def check_api_server_requirements() -> bool:
@@ -282,6 +287,24 @@ 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 +322,9 @@ 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 +350,26 @@ 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 +409,8 @@ 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 +515,12 @@ 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 +578,32 @@ 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 +613,20 @@ 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 +645,35 @@ 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.
@@ -663,7 +763,11 @@ class APIServerAdapter(BasePlatformAdapter):
         """
         import queue as _q
 
-        sse_headers = {"Content-Type": "text/event-stream", "Cache-Control": "no-cache"}
+        sse_headers = {
+            "Content-Type": "text/event-stream",
+            "Cache-Control": "no-cache",
+            "X-Accel-Buffering": "no",
+        }
         # CORS middleware can't inject headers into StreamResponse after
         # prepare() flushes them, so resolve CORS headers up front.
         origin = request.headers.get("Origin", "")
@@ -676,6 +780,8 @@ class APIServerAdapter(BasePlatformAdapter):
         await response.prepare(request)
 
         try:
+            last_activity = time.monotonic()
+
             # Role chunk
             role_chunk = {
                 "id": completion_id, "object": "chat.completion.chunk",
@@ -683,6 +789,31 @@ class APIServerAdapter(BasePlatformAdapter):
                 "choices": [{"index": 0, "delta": {"role": "assistant"}, "finish_reason": None}],
             }
             await response.write(f"data: {json.dumps(role_chunk)}\n\n".encode())
+            last_activity = time.monotonic()
+
+            # 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())
+                return time.monotonic()
 
             # Stream content chunks as they arrive from the agent
             loop = asyncio.get_event_loop()
@@ -697,26 +828,19 @@ 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())
+                                last_activity = await _emit(delta)
                             except _q.Empty:
                                 break
                         break
+                    if time.monotonic() - last_activity >= CHAT_COMPLETIONS_SSE_KEEPALIVE_SECONDS:
+                        await response.write(b": keepalive\n\n")
+                        last_activity = time.monotonic()
                     continue
 
                 if delta is None:  # End of stream sentinel
                     break
 
-                content_chunk = {
-                    "id": completion_id, "object": "chat.completion.chunk",
-                    "created": created, "model": model,
-                    "choices": [{"index": 0, "delta": {"content": delta}, "finish_reason": None}],
-                }
-                await response.write(f"data: {json.dumps(content_chunk)}\n\n".encode())
+                last_activity = await _emit(delta)
 
             # Get usage from completed agent
             usage = {"input_tokens": 0, "output_tokens": 0, "total_tokens": 0}
@@ -923,7 +1047,7 @@ 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 +1442,7 @@ 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 +1609,7 @@ 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 +1761,16 @@ 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 +1786,17 @@ 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:
     """
@@ -404,8 +626,9 @@ 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.
@@ -427,6 +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:
@@ -447,6 +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)
@@ -500,6 +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).
@@ -569,7 +823,36 @@ class BasePlatformAdapter(ABC):
         result = handler(self)
         if asyncio.iscoroutine(result):
             await result
-    
+
+    def _acquire_platform_lock(self, scope: str, identity: str, resource_desc: str) -> bool:
+        """Acquire a scoped lock for this adapter. Returns True on success."""
+        from gateway.status import acquire_scoped_lock
+        self._platform_lock_scope = scope
+        self._platform_lock_identity = identity
+        acquired, existing = acquire_scoped_lock(
+            scope, identity, metadata={'platform': self.platform.value}
+        )
+        if acquired:
+            return True
+        owner_pid = existing.get('pid') if isinstance(existing, dict) else None
+        message = (
+            f'{resource_desc} already in use'
+            + (f' (PID {owner_pid})' if owner_pid else '')
+            + '. Stop the other gateway first.'
+        )
+        logger.error('[%s] %s', self.name, message)
+        self._set_fatal_error(f'{scope}_lock', message, retryable=False)
+        return False
+
+    def _release_platform_lock(self) -> None:
+        """Release the scoped lock acquired by _acquire_platform_lock."""
+        identity = getattr(self, '_platform_lock_identity', None)
+        if not identity:
+            return
+        from gateway.status import release_scoped_lock
+        release_scoped_lock(self._platform_lock_scope, identity)
+        self._platform_lock_identity = None
+
     @property
     def name(self) -> str:
         """Human-readable name for this adapter."""
@@ -588,6 +871,10 @@ 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:
         """
@@ -1008,7 +1295,7 @@ 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:
@@ -1169,7 +1456,7 @@ 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,
@@ -1188,19 +1475,19 @@ 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
@@ -1227,6 +1514,7 @@ 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:
@@ -1363,7 +1651,7 @@ 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
@@ -1455,7 +1743,11 @@ 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:
@@ -1474,10 +1766,14 @@ 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:
@@ -1521,10 +1817,12 @@ 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

@@ -30,6 +30,7 @@ from gateway.platforms.base import (
     cache_audio_from_bytes,
     cache_document_from_bytes,
 )
+from gateway.platforms.helpers import strip_markdown
 
 logger = logging.getLogger(__name__)
 
@@ -89,18 +90,7 @@ def _normalize_server_url(raw: str) -> str:
     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()
+
 
 
 # ---------------------------------------------------------------------------
@@ -207,9 +197,17 @@ class BlueBubblesAdapter(BasePlatformAdapter):
             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
@@ -218,6 +216,105 @@ class BlueBubblesAdapter(BasePlatformAdapter):
             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
     # ------------------------------------------------------------------
@@ -286,7 +383,7 @@ class BlueBubblesAdapter(BasePlatformAdapter):
         reply_to: Optional[str] = None,
         metadata: Optional[Dict[str, Any]] = None,
     ) -> SendResult:
-        text = _strip_markdown(content or "")
+        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)
@@ -572,7 +669,7 @@ class BlueBubblesAdapter(BasePlatformAdapter):
         return info
 
     def format_message(self, content: str) -> str:
-        return _strip_markdown(content)
+        return strip_markdown(content)
 
     # ------------------------------------------------------------------
     # Inbound attachment downloading (from #4588)
@@ -826,3 +923,4 @@ class BlueBubblesAdapter(BasePlatformAdapter):
             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
@@ -41,6 +42,7 @@ except ImportError:
     httpx = None  # type: ignore[assignment]
 
 from gateway.config import Platform, PlatformConfig
+from gateway.platforms.helpers import MessageDeduplicator
 from gateway.platforms.base import (
     BasePlatformAdapter,
     MessageEvent,
@@ -51,9 +53,9 @@ from gateway.platforms.base import (
 logger = logging.getLogger(__name__)
 
 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:
@@ -86,8 +88,8 @@ class DingTalkAdapter(BasePlatformAdapter):
         self._stream_task: Optional[asyncio.Task] = None
         self._http_client: Optional["httpx.AsyncClient"] = None
 
-        # Message deduplication: msg_id -> timestamp
-        self._seen_messages: Dict[str, float] = {}
+        # Message deduplication
+        self._dedup = MessageDeduplicator(max_size=1000)
         # Map chat_id -> session_webhook for reply routing
         self._session_webhooks: Dict[str, str] = {}
 
@@ -167,7 +169,7 @@ class DingTalkAdapter(BasePlatformAdapter):
 
         self._stream_client = None
         self._session_webhooks.clear()
-        self._seen_messages.clear()
+        self._dedup.clear()
         logger.info("[%s] Disconnected", self.name)
 
     # -- Inbound message processing -----------------------------------------
@@ -175,7 +177,7 @@ class DingTalkAdapter(BasePlatformAdapter):
     async def _on_message(self, message: "ChatbotMessage") -> None:
         """Process an incoming DingTalk chatbot message."""
         msg_id = getattr(message, "message_id", None) or uuid.uuid4().hex
-        if self._is_duplicate(msg_id):
+        if self._dedup.is_duplicate(msg_id):
             logger.debug("[%s] Duplicate message %s, skipping", self.name, msg_id)
             return
 
@@ -195,9 +197,15 @@ 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(
@@ -247,20 +255,6 @@ class DingTalkAdapter(BasePlatformAdapter):
                 content = " ".join(parts).strip()
         return content
 
-    # -- Deduplication ------------------------------------------------------
-
-    def _is_duplicate(self, msg_id: str) -> bool:
-        """Check and record a message ID. Returns True if already seen."""
-        now = time.time()
-        if len(self._seen_messages) > DEDUP_MAX_SIZE:
-            cutoff = now - DEDUP_WINDOW_SECONDS
-            self._seen_messages = {k: v for k, v in self._seen_messages.items() if v > cutoff}
-
-        if msg_id in self._seen_messages:
-            return True
-        self._seen_messages[msg_id] = now
-        return False
-
     # -- Outbound messaging -------------------------------------------------
 
     async def send(

gateway/platforms/discord.py

@@ -45,10 +45,12 @@ sys.path.insert(0, str(_Path(__file__).resolve().parents[2]))
 from gateway.config import Platform, PlatformConfig
 import re
 
+from gateway.platforms.helpers import MessageDeduplicator, ThreadParticipationTracker
 from gateway.platforms.base import (
     BasePlatformAdapter,
     MessageEvent,
     MessageType,
+    ProcessingOutcome,
     SendResult,
     cache_image_from_url,
     cache_audio_from_url,
@@ -422,6 +424,7 @@ 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 +436,11 @@ 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
@@ -443,18 +451,15 @@ class DiscordAdapter(BasePlatformAdapter):
         # Track threads where the bot has participated so follow-up messages
         # in those threads don't require @mention.  Persisted to disk so the
         # set survives gateway restarts.
-        self._bot_participated_threads: set = self._load_participated_threads()
+        self._threads = ThreadParticipationTracker("discord")
         # Persistent typing indicator loops per channel (DMs don't reliably
         # show the standard typing gateway event for bots)
         self._typing_tasks: Dict[str, asyncio.Task] = {}
         self._bot_task: Optional[asyncio.Task] = None
-        # Cap to prevent unbounded growth (Discord threads get archived).
-        self._MAX_TRACKED_THREADS = 500
-        # Dedup cache: message_id → timestamp.  Prevents duplicate bot
-        # responses when Discord RESUME replays events after reconnects.
-        self._seen_messages: Dict[str, float] = {}
-        self._SEEN_TTL = 300   # 5 minutes
-        self._SEEN_MAX = 2000  # prune threshold
+        self._post_connect_task: Optional[asyncio.Task] = None
+        # Dedup cache: prevents duplicate bot responses when Discord
+        # RESUME replays events after reconnects.
+        self._dedup = MessageDeduplicator()
         # Reply threading mode: "off" (no replies), "first" (reply on first
         # chunk only, default), "all" (reply-reference on every chunk).
         self._reply_to_mode: str = getattr(config, 'reply_to_mode', 'first') or 'first'
@@ -495,18 +500,9 @@ class DiscordAdapter(BasePlatformAdapter):
             return False
 
         try:
-            # Acquire scoped lock to prevent duplicate bot token usage
-            from gateway.status import acquire_scoped_lock
-            self._token_lock_identity = self.config.token
-            acquired, existing = acquire_scoped_lock('discord-bot-token', self._token_lock_identity, metadata={'platform': 'discord'})
-            if not acquired:
-                owner_pid = existing.get('pid') if isinstance(existing, dict) else None
-                message = f'Discord bot token already in use' + (f' (PID {owner_pid})' if owner_pid else '') + '. Stop the other gateway first.'
-                logger.error('[%s] %s', self.name, message)
-                self._set_fatal_error('discord_token_lock', message, retryable=False)
+            if not self._acquire_platform_lock('discord-bot-token', self.config.token, 'Discord bot token'):
                 return False
 
-
             # Parse allowed user entries (may contain usernames or IDs)
             allowed_env = os.getenv("DISCORD_ALLOWED_USERS", "")
             if allowed_env:
@@ -529,10 +525,17 @@ 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
 
@@ -543,29 +546,19 @@ class DiscordAdapter(BasePlatformAdapter):
 
                 # Resolve any usernames in the allowed list to numeric IDs
                 await adapter_self._resolve_allowed_usernames()
-
-                # Sync slash commands with Discord
-                try:
-                    synced = await adapter_self._client.tree.sync()
-                    logger.info("[%s] Synced %d slash command(s)", adapter_self.name, len(synced))
-                except Exception as e:  # pragma: no cover - defensive logging
-                    logger.warning("[%s] Slash command sync failed: %s", adapter_self.name, e, exc_info=True)
                 adapter_self._ready_event.set()
 
+                if adapter_self._post_connect_task and not adapter_self._post_connect_task.done():
+                    adapter_self._post_connect_task.cancel()
+                adapter_self._post_connect_task = asyncio.create_task(
+                    adapter_self._run_post_connect_initialization()
+                )
+
             @self._client.event
             async def on_message(message: DiscordMessage):
                 # Dedup: Discord RESUME replays events after reconnects (#4777)
-                msg_id = str(message.id)
-                now = time.time()
-                if msg_id in adapter_self._seen_messages:
+                if adapter_self._dedup.is_duplicate(str(message.id)):
                     return
-                adapter_self._seen_messages[msg_id] = now
-                if len(adapter_self._seen_messages) > adapter_self._SEEN_MAX:
-                    cutoff = now - adapter_self._SEEN_TTL
-                    adapter_self._seen_messages = {
-                        k: v for k, v in adapter_self._seen_messages.items()
-                        if v > cutoff
-                    }
 
                 # Always ignore our own messages
                 if message.author == self._client.user:
@@ -592,22 +585,35 @@ 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)
 
@@ -658,23 +664,11 @@ class DiscordAdapter(BasePlatformAdapter):
 
         except asyncio.TimeoutError:
             logger.error("[%s] Timeout waiting for connection to Discord", self.name, exc_info=True)
-            try:
-                from gateway.status import release_scoped_lock
-                if getattr(self, '_token_lock_identity', None):
-                    release_scoped_lock('discord-bot-token', self._token_lock_identity)
-                    self._token_lock_identity = None
-            except Exception:
-                pass
+            self._release_platform_lock()
             return False
         except Exception as e:  # pragma: no cover - defensive logging
             logger.error("[%s] Failed to connect to Discord: %s", self.name, e, exc_info=True)
-            try:
-                from gateway.status import release_scoped_lock
-                if getattr(self, '_token_lock_identity', None):
-                    release_scoped_lock('discord-bot-token', self._token_lock_identity)
-                    self._token_lock_identity = None
-            except Exception:
-                pass
+            self._release_platform_lock()
             return False
 
     async def disconnect(self) -> None:
@@ -692,21 +686,36 @@ class DiscordAdapter(BasePlatformAdapter):
             except Exception as e:  # pragma: no cover - defensive logging
                 logger.warning("[%s] Error during disconnect: %s", self.name, e, exc_info=True)
 
+        if self._post_connect_task and not self._post_connect_task.done():
+            self._post_connect_task.cancel()
+            try:
+                await self._post_connect_task
+            except asyncio.CancelledError:
+                pass
+
         self._running = False
         self._client = None
         self._ready_event.clear()
+        self._post_connect_task = None
 
-        # Release the token lock
-        try:
-            from gateway.status import release_scoped_lock
-            if getattr(self, '_token_lock_identity', None):
-                release_scoped_lock('discord-bot-token', self._token_lock_identity)
-                self._token_lock_identity = None
-        except Exception:
-            pass
+        self._release_platform_lock()
 
         logger.info("[%s] Disconnected", self.name)
 
+    async def _run_post_connect_initialization(self) -> None:
+        """Finish non-critical startup work after Discord is connected."""
+        if not self._client:
+            return
+        try:
+            synced = await asyncio.wait_for(self._client.tree.sync(), timeout=30)
+            logger.info("[%s] Synced %d slash command(s)", self.name, len(synced))
+        except asyncio.TimeoutError:
+            logger.warning("[%s] Slash command sync timed out after 30s", self.name)
+        except asyncio.CancelledError:
+            raise
+        except Exception as e:  # pragma: no cover - defensive logging
+            logger.warning("[%s] Slash command sync failed: %s", self.name, e, exc_info=True)
+
     async def _add_reaction(self, message: Any, emoji: str) -> bool:
         """Add an emoji reaction to a Discord message."""
         if not message or not hasattr(message, "add_reaction"):
@@ -741,14 +750,17 @@ 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 +769,34 @@ 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 +1259,8 @@ 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 +1334,11 @@ 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 +1615,7 @@ 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())
 
@@ -1822,7 +1852,7 @@ class DiscordAdapter(BasePlatformAdapter):
 
         # Track thread participation so follow-ups don't require @mention
         if thread_id:
-            self._track_thread(thread_id)
+            self._threads.mark(thread_id)
 
         # If a message was provided, kick off a new Hermes session in the thread
         starter = (message or "").strip()
@@ -1857,14 +1887,42 @@ class DiscordAdapter(BasePlatformAdapter):
             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
@@ -2165,49 +2223,6 @@ class DiscordAdapter(BasePlatformAdapter):
             return f"{parent_name} / {thread_name}"
         return thread_name
 
-    # ------------------------------------------------------------------
-    # Thread participation persistence
-    # ------------------------------------------------------------------
-
-    @staticmethod
-    def _thread_state_path() -> Path:
-        """Path to the persisted thread participation set."""
-        from hermes_cli.config import get_hermes_home
-        return get_hermes_home() / "discord_threads.json"
-
-    @classmethod
-    def _load_participated_threads(cls) -> set:
-        """Load persisted thread IDs from disk."""
-        path = cls._thread_state_path()
-        try:
-            if path.exists():
-                data = json.loads(path.read_text(encoding="utf-8"))
-                if isinstance(data, list):
-                    return set(data)
-        except Exception as e:
-            logger.debug("Could not load discord thread state: %s", e)
-        return set()
-
-    def _save_participated_threads(self) -> None:
-        """Persist the current thread set to disk (best-effort)."""
-        path = self._thread_state_path()
-        try:
-            # Trim to most recent entries if over cap
-            thread_list = list(self._bot_participated_threads)
-            if len(thread_list) > self._MAX_TRACKED_THREADS:
-                thread_list = thread_list[-self._MAX_TRACKED_THREADS:]
-                self._bot_participated_threads = set(thread_list)
-            path.parent.mkdir(parents=True, exist_ok=True)
-            path.write_text(json.dumps(thread_list), encoding="utf-8")
-        except Exception as e:
-            logger.debug("Could not save discord thread state: %s", e)
-
-    def _track_thread(self, thread_id: str) -> None:
-        """Add a thread to the participation set and persist."""
-        if thread_id not in self._bot_participated_threads:
-            self._bot_participated_threads.add(thread_id)
-            self._save_participated_threads()
-
     async def _handle_message(self, message: DiscordMessage) -> None:
         """Handle incoming Discord messages."""
         # In server channels (not DMs), require the bot to be @mentioned
@@ -2218,6 +2233,7 @@ 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)
 
@@ -2229,12 +2245,21 @@ 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
@@ -2249,7 +2274,7 @@ class DiscordAdapter(BasePlatformAdapter):
 
             # Skip the mention check if the message is in a thread where
             # the bot has previously participated (auto-created or replied in).
-            in_bot_thread = is_thread and thread_id in self._bot_participated_threads
+            in_bot_thread = is_thread and thread_id in self._threads
 
             if require_mention and not is_free_channel and not in_bot_thread:
                 if self._client.user not in message.mentions:
@@ -2275,7 +2300,7 @@ class DiscordAdapter(BasePlatformAdapter):
                     is_thread = True
                     thread_id = str(thread.id)
                     auto_threaded_channel = thread
-                    self._track_thread(thread_id)
+                    self._threads.mark(thread_id)
 
         # Determine message type
         msg_type = MessageType.TEXT
@@ -2382,7 +2407,7 @@ 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",
@@ -2391,10 +2416,14 @@ 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}")
@@ -2406,9 +2435,9 @@ 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}"
@@ -2435,6 +2464,10 @@ 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,
@@ -2445,14 +2478,88 @@ 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
         # follow-up messages in threads it has already engaged in.
         if thread_id:
-            self._track_thread(thread_id)
+            self._threads.mark(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
@@ -359,19 +360,21 @@ def _render_code_block_element(element: Dict[str, Any]) -> str:
 
 
 def _strip_markdown_to_plain_text(text: str) -> str:
+    """Strip markdown formatting to plain text for Feishu text fallbacks.
+
+    Delegates common markdown stripping to the shared helper and adds
+    Feishu-specific patterns (blockquotes, strikethrough, underline tags,
+    horizontal rules, \\r\\n normalisation).
+    """
+    from gateway.platforms.helpers import strip_markdown
     plain = text.replace("\r\n", "\n")
     plain = _MARKDOWN_LINK_RE.sub(lambda m: f"{m.group(1)} ({m.group(2).strip()})", plain)
-    plain = re.sub(r"^#{1,6}\s+", "", plain, flags=re.MULTILINE)
     plain = re.sub(r"^>\s?", "", plain, flags=re.MULTILINE)
     plain = re.sub(r"^\s*---+\s*$", "---", plain, flags=re.MULTILINE)
-    plain = re.sub(r"```(?:[^\n]*\n)?([\s\S]*?)```", lambda m: m.group(1).strip("\n"), plain)
-    plain = re.sub(r"`([^`\n]+)`", r"\1", plain)
-    plain = re.sub(r"\*\*([^*\n]+)\*\*", r"\1", plain)
-    plain = re.sub(r"\*([^*\n]+)\*", r"\1", plain)
     plain = re.sub(r"~~([^~\n]+)~~", r"\1", plain)
     plain = re.sub(r"<u>([\s\S]*?)</u>", r"\1", plain)
-    plain = re.sub(r"\n{3,}", "\n\n", plain)
-    return plain.strip()
+    plain = strip_markdown(plain)
+    return plain
 
 
 def _coerce_int(value: Any, default: Optional[int] = None, min_value: int = 0) -> Optional[int]:
@@ -972,7 +975,8 @@ 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 +1018,10 @@ 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 +1113,9 @@ 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 +1163,7 @@ 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 +1192,8 @@ 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 +1584,18 @@ 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 +2497,10 @@ 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 +2525,7 @@ 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 +2552,22 @@ 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/helpers.py

@@ -0,0 +1,261 @@
+"""Shared helper classes for gateway platform adapters.
+
+Extracts common patterns that were duplicated across 5-7 adapters:
+message deduplication, text batch aggregation, markdown stripping,
+and thread participation tracking.
+"""
+
+import asyncio
+import json
+import logging
+import re
+import time
+from pathlib import Path
+from typing import TYPE_CHECKING, Dict, Optional
+
+if TYPE_CHECKING:
+    from gateway.platforms.base import BasePlatformAdapter, MessageEvent
+
+logger = logging.getLogger(__name__)
+
+
+# ─── Message Deduplication ────────────────────────────────────────────────────
+
+
+class MessageDeduplicator:
+    """TTL-based message deduplication cache.
+
+    Replaces the identical ``_seen_messages`` / ``_is_duplicate()`` pattern
+    previously duplicated in discord, slack, dingtalk, wecom, weixin,
+    mattermost, and feishu adapters.
+
+    Usage::
+
+        self._dedup = MessageDeduplicator()
+
+        # In message handler:
+        if self._dedup.is_duplicate(msg_id):
+            return
+    """
+
+    def __init__(self, max_size: int = 2000, ttl_seconds: float = 300):
+        self._seen: Dict[str, float] = {}
+        self._max_size = max_size
+        self._ttl = ttl_seconds
+
+    def is_duplicate(self, msg_id: str) -> bool:
+        """Return True if *msg_id* was already seen within the TTL window."""
+        if not msg_id:
+            return False
+        now = time.time()
+        if msg_id in self._seen:
+            return True
+        self._seen[msg_id] = now
+        if len(self._seen) > self._max_size:
+            cutoff = now - self._ttl
+            self._seen = {k: v for k, v in self._seen.items() if v > cutoff}
+        return False
+
+    def clear(self):
+        """Clear all tracked messages."""
+        self._seen.clear()
+
+
+# ─── Text Batch Aggregation ──────────────────────────────────────────────────
+
+
+class TextBatchAggregator:
+    """Aggregates rapid-fire text events into single messages.
+
+    Replaces the ``_enqueue_text_event`` / ``_flush_text_batch`` pattern
+    previously duplicated in telegram, discord, matrix, wecom, and feishu.
+
+    Usage::
+
+        self._text_batcher = TextBatchAggregator(
+            handler=self._message_handler,
+            batch_delay=0.6,
+            split_threshold=1900,
+        )
+
+        # In message dispatch:
+        if msg_type == MessageType.TEXT and self._text_batcher.is_enabled():
+            self._text_batcher.enqueue(event, session_key)
+            return
+    """
+
+    def __init__(
+        self,
+        handler,
+        *,
+        batch_delay: float = 0.6,
+        split_delay: float = 2.0,
+        split_threshold: int = 4000,
+    ):
+        self._handler = handler
+        self._batch_delay = batch_delay
+        self._split_delay = split_delay
+        self._split_threshold = split_threshold
+        self._pending: Dict[str, "MessageEvent"] = {}
+        self._pending_tasks: Dict[str, asyncio.Task] = {}
+
+    def is_enabled(self) -> bool:
+        """Return True if batching is active (delay > 0)."""
+        return self._batch_delay > 0
+
+    def enqueue(self, event: "MessageEvent", key: str) -> None:
+        """Add *event* to the pending batch for *key*."""
+        chunk_len = len(event.text or "")
+        existing = self._pending.get(key)
+        if not existing:
+            event._last_chunk_len = chunk_len  # type: ignore[attr-defined]
+            self._pending[key] = event
+        else:
+            existing.text = f"{existing.text}\n{event.text}"
+            existing._last_chunk_len = chunk_len  # type: ignore[attr-defined]
+
+        # Cancel prior flush timer, start a new one
+        prior = self._pending_tasks.get(key)
+        if prior and not prior.done():
+            prior.cancel()
+        self._pending_tasks[key] = asyncio.create_task(self._flush(key))
+
+    async def _flush(self, key: str) -> None:
+        """Wait then dispatch the batched event for *key*."""
+        current_task = self._pending_tasks.get(key)
+        pending = self._pending.get(key)
+        last_len = getattr(pending, "_last_chunk_len", 0) if pending else 0
+
+        # Use longer delay when the last chunk looks like a split message
+        delay = self._split_delay if last_len >= self._split_threshold else self._batch_delay
+        await asyncio.sleep(delay)
+
+        event = self._pending.pop(key, None)
+        if event:
+            try:
+                await self._handler(event)
+            except Exception:
+                logger.exception("[TextBatchAggregator] Error dispatching batched event for %s", key)
+
+        if self._pending_tasks.get(key) is current_task:
+            self._pending_tasks.pop(key, None)
+
+    def cancel_all(self) -> None:
+        """Cancel all pending flush tasks."""
+        for task in self._pending_tasks.values():
+            if not task.done():
+                task.cancel()
+        self._pending_tasks.clear()
+        self._pending.clear()
+
+
+# ─── Markdown Stripping ──────────────────────────────────────────────────────
+
+# Pre-compiled regexes for performance
+_RE_BOLD = re.compile(r"\*\*(.+?)\*\*", re.DOTALL)
+_RE_ITALIC_STAR = re.compile(r"\*(.+?)\*", re.DOTALL)
+_RE_BOLD_UNDER = re.compile(r"__(.+?)__", re.DOTALL)
+_RE_ITALIC_UNDER = re.compile(r"_(.+?)_", re.DOTALL)
+_RE_CODE_BLOCK = re.compile(r"```[a-zA-Z0-9_+-]*\n?")
+_RE_INLINE_CODE = re.compile(r"`(.+?)`")
+_RE_HEADING = re.compile(r"^#{1,6}\s+", re.MULTILINE)
+_RE_LINK = re.compile(r"\[([^\]]+)\]\([^\)]+\)")
+_RE_MULTI_NEWLINE = re.compile(r"\n{3,}")
+
+
+def strip_markdown(text: str) -> str:
+    """Strip markdown formatting for plain-text platforms (SMS, iMessage, etc.).
+
+    Replaces the identical ``_strip_markdown()`` functions previously
+    duplicated in sms.py, bluebubbles.py, and feishu.py.
+    """
+    text = _RE_BOLD.sub(r"\1", text)
+    text = _RE_ITALIC_STAR.sub(r"\1", text)
+    text = _RE_BOLD_UNDER.sub(r"\1", text)
+    text = _RE_ITALIC_UNDER.sub(r"\1", text)
+    text = _RE_CODE_BLOCK.sub("", text)
+    text = _RE_INLINE_CODE.sub(r"\1", text)
+    text = _RE_HEADING.sub("", text)
+    text = _RE_LINK.sub(r"\1", text)
+    text = _RE_MULTI_NEWLINE.sub("\n\n", text)
+    return text.strip()
+
+
+# ─── Thread Participation Tracking ───────────────────────────────────────────
+
+
+class ThreadParticipationTracker:
+    """Persistent tracking of threads the bot has participated in.
+
+    Replaces the identical ``_load/_save_participated_threads`` +
+    ``_mark_thread_participated`` pattern previously duplicated in
+    discord.py and matrix.py.
+
+    Usage::
+
+        self._threads = ThreadParticipationTracker("discord")
+
+        # Check membership:
+        if thread_id in self._threads:
+            ...
+
+        # Mark participation:
+        self._threads.mark(thread_id)
+    """
+
+    _MAX_TRACKED = 500
+
+    def __init__(self, platform_name: str, max_tracked: int = 500):
+        self._platform = platform_name
+        self._max_tracked = max_tracked
+        self._threads: set = self._load()
+
+    def _state_path(self) -> Path:
+        from hermes_constants import get_hermes_home
+        return get_hermes_home() / f"{self._platform}_threads.json"
+
+    def _load(self) -> set:
+        path = self._state_path()
+        if path.exists():
+            try:
+                return set(json.loads(path.read_text(encoding="utf-8")))
+            except Exception:
+                pass
+        return set()
+
+    def _save(self) -> None:
+        path = self._state_path()
+        path.parent.mkdir(parents=True, exist_ok=True)
+        thread_list = list(self._threads)
+        if len(thread_list) > self._max_tracked:
+            thread_list = thread_list[-self._max_tracked:]
+            self._threads = set(thread_list)
+        path.write_text(json.dumps(thread_list), encoding="utf-8")
+
+    def mark(self, thread_id: str) -> None:
+        """Mark *thread_id* as participated and persist."""
+        if thread_id not in self._threads:
+            self._threads.add(thread_id)
+            self._save()
+
+    def __contains__(self, thread_id: str) -> bool:
+        return thread_id in self._threads
+
+    def clear(self) -> None:
+        self._threads.clear()
+
+
+# ─── Phone Number Redaction ──────────────────────────────────────────────────
+
+
+def redact_phone(phone: str) -> str:
+    """Redact a phone number for logging, preserving country code and last 4.
+
+    Replaces the identical ``_redact_phone()`` functions in signal.py,
+    sms.py, and bluebubbles.py.
+    """
+    if not phone:
+        return "<none>"
+    if len(phone) <= 8:
+        return phone[:2] + "****" + phone[-2:] if len(phone) > 4 else "****"
+    return phone[:4] + "****" + phone[-4:]

gateway/platforms/mattermost.py

@@ -18,11 +18,11 @@ import json
 import logging
 import os
 import re
-import time
 from pathlib import Path
 from typing import Any, Dict, List, Optional
 
 from gateway.config import Platform, PlatformConfig
+from gateway.platforms.helpers import MessageDeduplicator
 from gateway.platforms.base import (
     BasePlatformAdapter,
     MessageEvent,
@@ -96,10 +96,8 @@ class MattermostAdapter(BasePlatformAdapter):
             or os.getenv("MATTERMOST_REPLY_MODE", "off")
         ).lower()
 
-        # Dedup cache: post_id → timestamp (prevent reprocessing)
-        self._seen_posts: Dict[str, float] = {}
-        self._SEEN_MAX = 2000
-        self._SEEN_TTL = 300  # 5 minutes
+        # Dedup cache (prevent reprocessing)
+        self._dedup = MessageDeduplicator()
 
     # ------------------------------------------------------------------
     # HTTP helpers
@@ -604,10 +602,8 @@ class MattermostAdapter(BasePlatformAdapter):
         post_id = post.get("id", "")
 
         # Dedup.
-        self._prune_seen()
-        if post_id in self._seen_posts:
+        if self._dedup.is_duplicate(post_id):
             return
-        self._seen_posts[post_id] = time.time()
 
         # Build message event.
         channel_id = post.get("channel_id", "")
@@ -734,13 +730,4 @@ class MattermostAdapter(BasePlatformAdapter):
 
         await self.handle_message(msg_event)
 
-    def _prune_seen(self) -> None:
-        """Remove expired entries from the dedup cache."""
-        if len(self._seen_posts) < self._SEEN_MAX:
-            return
-        now = time.time()
-        self._seen_posts = {
-            pid: ts
-            for pid, ts in self._seen_posts.items()
-            if now - ts < self._SEEN_TTL
-        }
+

gateway/platforms/signal.py

@@ -37,6 +37,7 @@ from gateway.platforms.base import (
     cache_document_from_bytes,
     cache_image_from_url,
 )
+from gateway.platforms.helpers import redact_phone
 
 logger = logging.getLogger(__name__)
 
@@ -51,22 +52,10 @@ SSE_RETRY_DELAY_MAX = 60.0
 HEALTH_CHECK_INTERVAL = 30.0  # seconds between health checks
 HEALTH_CHECK_STALE_THRESHOLD = 120.0  # seconds without SSE activity before concern
 
-# E.164 phone number pattern for redaction
-_PHONE_RE = re.compile(r"\+[1-9]\d{6,14}")
-
-
 # ---------------------------------------------------------------------------
 # Helpers
 # ---------------------------------------------------------------------------
 
-def _redact_phone(phone: str) -> str:
-    """Redact a phone number for logging: +15551234567 -> +155****4567."""
-    if not phone:
-        return "<none>"
-    if len(phone) <= 8:
-        return phone[:2] + "****" + phone[-2:] if len(phone) > 4 else "****"
-    return phone[:4] + "****" + phone[-4:]
-
 
 def _parse_comma_list(value: str) -> List[str]:
     """Split a comma-separated string into a list, stripping whitespace."""
@@ -184,10 +173,8 @@ class SignalAdapter(BasePlatformAdapter):
         self._recent_sent_timestamps: set = set()
         self._max_recent_timestamps = 50
 
-        self._phone_lock_identity: Optional[str] = None
-
         logger.info("Signal adapter initialized: url=%s account=%s groups=%s",
-                     self.http_url, _redact_phone(self.account),
+                     self.http_url, redact_phone(self.account),
                      "enabled" if self.group_allow_from else "disabled")
 
     # ------------------------------------------------------------------
@@ -202,23 +189,7 @@ class SignalAdapter(BasePlatformAdapter):
 
         # Acquire scoped lock to prevent duplicate Signal listeners for the same phone
         try:
-            from gateway.status import acquire_scoped_lock
-
-            self._phone_lock_identity = self.account
-            acquired, existing = acquire_scoped_lock(
-                "signal-phone",
-                self._phone_lock_identity,
-                metadata={"platform": self.platform.value},
-            )
-            if not acquired:
-                owner_pid = existing.get("pid") if isinstance(existing, dict) else None
-                message = (
-                    "Another local Hermes gateway is already using this Signal account"
-                    + (f" (PID {owner_pid})." if owner_pid else ".")
-                    + " Stop the other gateway before starting a second Signal listener."
-                )
-                logger.error("Signal: %s", message)
-                self._set_fatal_error("signal_phone_lock", message, retryable=False)
+            if not self._acquire_platform_lock('signal-phone', self.account, 'Signal account'):
                 return False
         except Exception as e:
             logger.warning("Signal: Could not acquire phone lock (non-fatal): %s", e)
@@ -270,13 +241,7 @@ class SignalAdapter(BasePlatformAdapter):
             await self.client.aclose()
             self.client = None
 
-        if self._phone_lock_identity:
-            try:
-                from gateway.status import release_scoped_lock
-                release_scoped_lock("signal-phone", self._phone_lock_identity)
-            except Exception as e:
-                logger.warning("Signal: Error releasing phone lock: %s", e, exc_info=True)
-            self._phone_lock_identity = None
+        self._release_platform_lock()
 
         logger.info("Signal: disconnected")
 
@@ -542,7 +507,7 @@ class SignalAdapter(BasePlatformAdapter):
         )
 
         logger.debug("Signal: message from %s in %s: %s",
-                      _redact_phone(sender), chat_id[:20], (text or "")[:50])
+                      redact_phone(sender), chat_id[:20], (text or "")[:50])
 
         await self.handle_message(event)
 

gateway/platforms/slack.py

@@ -14,6 +14,7 @@ import logging
 import os
 import re
 import time
+from dataclasses import dataclass, field
 from typing import Dict, Optional, Any, Tuple
 
 try:
@@ -32,12 +33,14 @@ from pathlib import Path as _Path
 sys.path.insert(0, str(_Path(__file__).resolve().parents[2]))
 
 from gateway.config import Platform, PlatformConfig
+from gateway.platforms.helpers import MessageDeduplicator
 from gateway.platforms.base import (
     BasePlatformAdapter,
     MessageEvent,
     MessageType,
     SendResult,
     SUPPORTED_DOCUMENT_TYPES,
+    safe_url_for_log,
     cache_document_from_bytes,
 )
 
@@ -45,6 +48,14 @@ 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
@@ -79,11 +90,9 @@ class SlackAdapter(BasePlatformAdapter):
         self._team_clients: Dict[str, AsyncWebClient] = {}   # team_id → WebClient
         self._team_bot_user_ids: Dict[str, str] = {}          # team_id → bot_user_id
         self._channel_team: Dict[str, str] = {}                # channel_id → team_id
-        # Dedup cache: event_ts → timestamp.  Prevents duplicate bot
-        # responses when Socket Mode reconnects redeliver events.
-        self._seen_messages: Dict[str, float] = {}
-        self._SEEN_TTL = 300   # 5 minutes
-        self._SEEN_MAX = 2000  # prune threshold
+        # Dedup cache: prevents duplicate bot responses when Socket Mode
+        # reconnects redeliver events.
+        self._dedup = MessageDeduplicator()
         # Track pending approval message_ts → resolved flag to prevent
         # double-clicks on approval buttons.
         self._approval_resolved: Dict[str, bool] = {}
@@ -101,6 +110,9 @@ class SlackAdapter(BasePlatformAdapter):
         # 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."""
@@ -139,15 +151,7 @@ class SlackAdapter(BasePlatformAdapter):
                 logger.warning("[Slack] Failed to read %s: %s", tokens_file, e)
 
         try:
-            # Acquire scoped lock to prevent duplicate app token usage
-            from gateway.status import acquire_scoped_lock
-            self._token_lock_identity = app_token
-            acquired, existing = acquire_scoped_lock('slack-app-token', app_token, metadata={'platform': 'slack'})
-            if not acquired:
-                owner_pid = existing.get('pid') if isinstance(existing, dict) else None
-                message = f'Slack app token already in use' + (f' (PID {owner_pid})' if owner_pid else '') + '. Stop the other gateway first.'
-                logger.error('[%s] %s', self.name, message)
-                self._set_fatal_error('slack_token_lock', message, retryable=False)
+            if not self._acquire_platform_lock('slack-app-token', app_token, 'Slack app token'):
                 return False
 
             # First token is the primary — used for AsyncApp / Socket Mode
@@ -234,14 +238,7 @@ class SlackAdapter(BasePlatformAdapter):
                 logger.warning("[Slack] Error while closing Socket Mode handler: %s", e, exc_info=True)
         self._running = False
 
-        # Release the token lock (use stored identity, not re-read env)
-        try:
-            from gateway.status import release_scoped_lock
-            if getattr(self, '_token_lock_identity', None):
-                release_scoped_lock('slack-app-token', self._token_lock_identity)
-                self._token_lock_identity = None
-        except Exception:
-            pass
+        self._release_platform_lock()
 
         logger.info("[Slack] Disconnected")
 
@@ -281,6 +278,7 @@ class SlackAdapter(BasePlatformAdapter):
                 kwargs = {
                     "channel": chat_id,
                     "text": chunk,
+                    "mrkdwn": True,
                 }
                 if thread_ts:
                     kwargs["thread_ts"] = thread_ts
@@ -323,9 +321,7 @@ 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,
@@ -457,13 +453,36 @@ 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
@@ -474,34 +493,39 @@ 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
@@ -617,8 +641,19 @@ 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()
 
@@ -635,7 +670,7 @@ 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,
             )
@@ -902,22 +937,30 @@ class SlackAdapter(BasePlatformAdapter):
         """Handle an incoming Slack message event."""
         # Dedup: Slack Socket Mode can redeliver events after reconnects (#4777)
         event_ts = event.get("ts", "")
-        if event_ts:
-            now = time.time()
-            if event_ts in self._seen_messages:
-                return
-            self._seen_messages[event_ts] = now
-            if len(self._seen_messages) > self._SEEN_MAX:
-                cutoff = now - self._SEEN_TTL
-                self._seen_messages = {
-                    k: v for k, v in self._seen_messages.items()
-                    if v > cutoff
-                }
-
-        # Ignore bot messages (including our own)
-        if event.get("bot_id") or event.get("subtype") == "bot_message":
+        if event_ts and self._dedup.is_duplicate(event_ts):
             return
 
+        # 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":
+            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")
         if subtype in ("message_changed", "message_deleted"):
@@ -948,7 +991,7 @@ class SlackAdapter(BasePlatformAdapter):
         channel_type = event.get("channel_type", "")
         if not channel_type and channel_id.startswith("D"):
             channel_type = "im"
-        is_dm = 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
@@ -961,6 +1004,8 @@ class SlackAdapter(BasePlatformAdapter):
             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
@@ -970,24 +1015,29 @@ 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
@@ -1128,14 +1178,19 @@ 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) -----
 
@@ -1229,6 +1284,20 @@ 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 = {
@@ -1239,10 +1308,9 @@ 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 = {
@@ -1297,8 +1365,7 @@ 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 -----
 
@@ -1309,57 +1376,104 @@ 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 ""
@@ -1469,6 +1583,18 @@ 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)
@@ -1515,3 +1641,30 @@ 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/sms.py

@@ -10,6 +10,9 @@ Shares credentials with the optional telephony skill — same env vars:
 
 Gateway-specific env vars:
   - SMS_WEBHOOK_PORT     (default 8080)
+  - SMS_WEBHOOK_HOST     (default 0.0.0.0)
+  - SMS_WEBHOOK_URL      (public URL for Twilio signature validation — required)
+  - SMS_INSECURE_NO_SIGNATURE  (true to disable signature validation — dev only)
   - SMS_ALLOWED_USERS    (comma-separated E.164 phone numbers)
   - SMS_ALLOW_ALL_USERS  (true/false)
   - SMS_HOME_CHANNEL     (phone number for cron delivery)
@@ -17,9 +20,10 @@ Gateway-specific env vars:
 
 import asyncio
 import base64
+import hashlib
+import hmac
 import logging
 import os
-import re
 import urllib.parse
 from typing import Any, Dict, Optional
 
@@ -30,24 +34,14 @@ from gateway.platforms.base import (
     MessageType,
     SendResult,
 )
+from gateway.platforms.helpers import redact_phone, strip_markdown
 
 logger = logging.getLogger(__name__)
 
 TWILIO_API_BASE = "https://api.twilio.com/2010-04-01/Accounts"
 MAX_SMS_LENGTH = 1600  # ~10 SMS segments
 DEFAULT_WEBHOOK_PORT = 8080
-
-# E.164 phone number pattern for redaction
-_PHONE_RE = re.compile(r"\+[1-9]\d{6,14}")
-
-
-def _redact_phone(phone: str) -> str:
-    """Redact a phone number for logging: +15551234567 -> +1555***4567."""
-    if not phone:
-        return "<none>"
-    if len(phone) <= 8:
-        return phone[:2] + "***" + phone[-2:] if len(phone) > 4 else "****"
-    return phone[:5] + "***" + phone[-4:]
+DEFAULT_WEBHOOK_HOST = "0.0.0.0"
 
 
 def check_sms_requirements() -> bool:
@@ -77,6 +71,8 @@ class SmsAdapter(BasePlatformAdapter):
         self._webhook_port: int = int(
             os.getenv("SMS_WEBHOOK_PORT", str(DEFAULT_WEBHOOK_PORT))
         )
+        self._webhook_host: str = os.getenv("SMS_WEBHOOK_HOST", DEFAULT_WEBHOOK_HOST)
+        self._webhook_url: str = os.getenv("SMS_WEBHOOK_URL", "").strip()
         self._runner = None
         self._http_session: Optional["aiohttp.ClientSession"] = None
 
@@ -98,13 +94,33 @@ class SmsAdapter(BasePlatformAdapter):
             logger.error("[sms] TWILIO_PHONE_NUMBER not set — cannot send replies")
             return False
 
+        insecure_no_sig = os.getenv("SMS_INSECURE_NO_SIGNATURE", "").lower() == "true"
+
+        if not self._webhook_url and not insecure_no_sig:
+            logger.error(
+                "[sms] Refusing to start: SMS_WEBHOOK_URL is required for Twilio "
+                "signature validation. Set it to the public URL configured in your "
+                "Twilio console (e.g. https://example.com/webhooks/twilio). "
+                "For local development without validation, set "
+                "SMS_INSECURE_NO_SIGNATURE=true (NOT recommended for production).",
+            )
+            return False
+
+        if insecure_no_sig and not self._webhook_url:
+            logger.warning(
+                "[sms] SMS_INSECURE_NO_SIGNATURE=true — Twilio signature validation "
+                "is DISABLED. Any client that can reach port %d can inject messages. "
+                "Do NOT use this in production.",
+                self._webhook_port,
+            )
+
         app = web.Application()
         app.router.add_post("/webhooks/twilio", self._handle_webhook)
         app.router.add_get("/health", lambda _: web.Response(text="ok"))
 
         self._runner = web.AppRunner(app)
         await self._runner.setup()
-        site = web.TCPSite(self._runner, "0.0.0.0", self._webhook_port)
+        site = web.TCPSite(self._runner, self._webhook_host, self._webhook_port)
         await site.start()
         self._http_session = aiohttp.ClientSession(
             timeout=aiohttp.ClientTimeout(total=30),
@@ -112,9 +128,10 @@ class SmsAdapter(BasePlatformAdapter):
         self._running = True
 
         logger.info(
-            "[sms] Twilio webhook server listening on port %d, from: %s",
+            "[sms] Twilio webhook server listening on %s:%d, from: %s",
+            self._webhook_host,
             self._webhook_port,
-            _redact_phone(self._from_number),
+            redact_phone(self._from_number),
         )
         return True
 
@@ -163,7 +180,7 @@ class SmsAdapter(BasePlatformAdapter):
                             error_msg = body.get("message", str(body))
                             logger.error(
                                 "[sms] send failed to %s: %s %s",
-                                _redact_phone(chat_id),
+                                redact_phone(chat_id),
                                 resp.status,
                                 error_msg,
                             )
@@ -174,7 +191,7 @@ class SmsAdapter(BasePlatformAdapter):
                         msg_sid = body.get("sid", "")
                         last_result = SendResult(success=True, message_id=msg_sid)
                 except Exception as e:
-                    logger.error("[sms] send error to %s: %s", _redact_phone(chat_id), e)
+                    logger.error("[sms] send error to %s: %s", redact_phone(chat_id), e)
                     return SendResult(success=False, error=str(e))
         finally:
             # Close session only if we created a fallback (no persistent session)
@@ -192,16 +209,75 @@ class SmsAdapter(BasePlatformAdapter):
 
     def format_message(self, content: str) -> str:
         """Strip markdown — SMS renders it as literal characters."""
-        content = re.sub(r"\*\*(.+?)\*\*", r"\1", content, flags=re.DOTALL)
-        content = re.sub(r"\*(.+?)\*", r"\1", content, flags=re.DOTALL)
-        content = re.sub(r"__(.+?)__", r"\1", content, flags=re.DOTALL)
-        content = re.sub(r"_(.+?)_", r"\1", content, flags=re.DOTALL)
-        content = re.sub(r"```[a-z]*\n?", "", content)
-        content = re.sub(r"`(.+?)`", r"\1", content)
-        content = re.sub(r"^#{1,6}\s+", "", content, flags=re.MULTILINE)
-        content = re.sub(r"\[([^\]]+)\]\([^\)]+\)", r"\1", content)
-        content = re.sub(r"\n{3,}", "\n\n", content)
-        return content.strip()
+        return strip_markdown(content)
+
+    # ------------------------------------------------------------------
+    # Twilio signature validation
+    # ------------------------------------------------------------------
+
+    def _validate_twilio_signature(
+        self, url: str, post_params: dict, signature: str,
+    ) -> bool:
+        """Validate ``X-Twilio-Signature`` header (HMAC-SHA1, base64).
+
+        Tries both with and without the default port for the URL scheme,
+        since Twilio may sign with either variant.
+
+        Algorithm: https://www.twilio.com/docs/usage/security#validating-requests
+        """
+        if self._check_signature(url, post_params, signature):
+            return True
+
+        variant = self._port_variant_url(url)
+        if variant and self._check_signature(variant, post_params, signature):
+            return True
+
+        return False
+
+    def _check_signature(
+        self, url: str, post_params: dict, signature: str,
+    ) -> bool:
+        """Compute and compare a single Twilio signature."""
+        data_to_sign = url
+        for key in sorted(post_params.keys()):
+            data_to_sign += key + post_params[key]
+        mac = hmac.new(
+            self._auth_token.encode("utf-8"),
+            data_to_sign.encode("utf-8"),
+            hashlib.sha1,
+        )
+        computed = base64.b64encode(mac.digest()).decode("utf-8")
+        return hmac.compare_digest(computed, signature)
+
+    @staticmethod
+    def _port_variant_url(url: str) -> str | None:
+        """Return the URL with the default port toggled, or None.
+
+        Only toggles default ports (443 for https, 80 for http).
+        Non-standard ports are never modified.
+        """
+        parsed = urllib.parse.urlparse(url)
+        default_ports = {"https": 443, "http": 80}
+        default_port = default_ports.get(parsed.scheme)
+        if default_port is None:
+            return None
+
+        if parsed.port == default_port:
+            # Has explicit default port → strip it
+            return urllib.parse.urlunparse(
+                (parsed.scheme, parsed.hostname, parsed.path,
+                 parsed.params, parsed.query, parsed.fragment)
+            )
+        elif parsed.port is None:
+            # No port → add default
+            netloc = f"{parsed.hostname}:{default_port}"
+            return urllib.parse.urlunparse(
+                (parsed.scheme, netloc, parsed.path,
+                 parsed.params, parsed.query, parsed.fragment)
+            )
+
+        # Non-standard port — no variant
+        return None
 
     # ------------------------------------------------------------------
     # Twilio webhook handler
@@ -213,7 +289,7 @@ class SmsAdapter(BasePlatformAdapter):
         try:
             raw = await request.read()
             # Twilio sends form-encoded data, not JSON
-            form = urllib.parse.parse_qs(raw.decode("utf-8"))
+            form = urllib.parse.parse_qs(raw.decode("utf-8"), keep_blank_values=True)
         except Exception as e:
             logger.error("[sms] webhook parse error: %s", e)
             return web.Response(
@@ -222,6 +298,27 @@ class SmsAdapter(BasePlatformAdapter):
                 status=400,
             )
 
+        # Validate Twilio request signature when SMS_WEBHOOK_URL is configured
+        if self._webhook_url:
+            twilio_sig = request.headers.get("X-Twilio-Signature", "")
+            if not twilio_sig:
+                logger.warning("[sms] Rejected: missing X-Twilio-Signature header")
+                return web.Response(
+                    text='<?xml version="1.0" encoding="UTF-8"?><Response></Response>',
+                    content_type="application/xml",
+                    status=403,
+                )
+            flat_params = {k: v[0] for k, v in form.items() if v}
+            if not self._validate_twilio_signature(
+                self._webhook_url, flat_params, twilio_sig
+            ):
+                logger.warning("[sms] Rejected: invalid Twilio signature")
+                return web.Response(
+                    text='<?xml version="1.0" encoding="UTF-8"?><Response></Response>',
+                    content_type="application/xml",
+                    status=403,
+                )
+
         # Extract fields (parse_qs returns lists)
         from_number = (form.get("From", [""]))[0].strip()
         to_number = (form.get("To", [""]))[0].strip()
@@ -236,7 +333,7 @@ class SmsAdapter(BasePlatformAdapter):
 
         # Ignore messages from our own number (echo prevention)
         if from_number == self._from_number:
-            logger.debug("[sms] ignoring echo from own number %s", _redact_phone(from_number))
+            logger.debug("[sms] ignoring echo from own number %s", redact_phone(from_number))
             return web.Response(
                 text='<?xml version="1.0" encoding="UTF-8"?><Response></Response>',
                 content_type="application/xml",
@@ -244,8 +341,8 @@ class SmsAdapter(BasePlatformAdapter):
 
         logger.info(
             "[sms] inbound from %s -> %s: %s",
-            _redact_phone(from_number),
-            _redact_phone(to_number),
+            redact_phone(from_number),
+            redact_phone(to_number),
             text[:80],
         )
 

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):
@@ -140,9 +144,9 @@ 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
         self._polling_error_task: Optional[asyncio.Task] = None
         self._polling_conflict_count: int = 0
         self._polling_network_error_count: int = 0
@@ -295,9 +299,11 @@ class TelegramAdapter(BasePlatformAdapter):
 
         # Exhausted retries — fatal
         message = (
-            "Another Telegram bot poller is already using this token. "
+            "Another process is already polling this Telegram bot token "
+            "(possibly OpenClaw or another Hermes instance). "
             "Hermes stopped Telegram polling after %d retries. "
-            "Make sure only one gateway instance is running for this bot token."
+            "Only one poller can run per token — stop the other process "
+            "and restart with 'hermes start'."
             % MAX_CONFLICT_RETRIES
         )
         logger.error("[%s] %s Original error: %s", self.name, message, error)
@@ -492,27 +498,50 @@ class TelegramAdapter(BasePlatformAdapter):
             return False
         
         try:
-            from gateway.status import acquire_scoped_lock
-
-            self._token_lock_identity = self.config.token
-            acquired, existing = acquire_scoped_lock(
-                "telegram-bot-token",
-                self._token_lock_identity,
-                metadata={"platform": self.platform.value},
-            )
-            if not acquired:
-                owner_pid = existing.get("pid") if isinstance(existing, dict) else None
-                message = (
-                    "Another local Hermes gateway is already using this Telegram bot token"
-                    + (f" (PID {owner_pid})." if owner_pid else ".")
-                    + " Stop the other gateway before starting a second Telegram poller."
-                )
-                logger.error("[%s] %s", self.name, message)
-                self._set_fatal_error("telegram_token_lock", message, retryable=False)
+            if not self._acquire_platform_lock('telegram-bot-token', self.config.token, 'Telegram bot token'):
                 return False
 
             # 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 +550,32 @@ 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
             
@@ -677,12 +722,7 @@ class TelegramAdapter(BasePlatformAdapter):
             return True
             
         except Exception as e:
-            if self._token_lock_identity:
-                try:
-                    from gateway.status import release_scoped_lock
-                    release_scoped_lock("telegram-bot-token", self._token_lock_identity)
-                except Exception:
-                    pass
+            self._release_platform_lock()
             message = f"Telegram startup failed: {e}"
             self._set_fatal_error("telegram_connect_error", message, retryable=True)
             logger.error("[%s] Failed to connect to Telegram: %s", self.name, e, exc_info=True)
@@ -708,12 +748,7 @@ class TelegramAdapter(BasePlatformAdapter):
                 await self._app.shutdown()
             except Exception as e:
                 logger.warning("[%s] Error during Telegram disconnect: %s", self.name, e, exc_info=True)
-        if self._token_lock_identity:
-            try:
-                from gateway.status import release_scoped_lock
-                release_scoped_lock("telegram-bot-token", self._token_lock_identity)
-            except Exception as e:
-                logger.warning("[%s] Error releasing Telegram token lock: %s", self.name, e, exc_info=True)
+        self._release_platform_lock()
 
         for task in self._pending_photo_batch_tasks.values():
             if task and not task.done():
@@ -724,7 +759,6 @@ class TelegramAdapter(BasePlatformAdapter):
         self._mark_disconnected()
         self._app = None
         self._bot = None
-        self._token_lock_identity = None
         logger.info("[%s] Disconnected from Telegram", self.name)
 
     def _should_thread_reply(self, reply_to: Optional[str], chunk_index: int) -> bool:
@@ -1398,6 +1432,15 @@ 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 +2194,15 @@ 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 +2217,22 @@ 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 +2762,7 @@ 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 +2772,9 @@ 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 +186,24 @@ 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",
+            "wecom_callback",
+            "weixin",
+            "bluebubbles",
         ):
             return await self._deliver_cross_platform(
                 deliver_type, content, delivery
@@ -262,7 +273,7 @@ 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

@@ -59,6 +59,7 @@ except ImportError:
     httpx = None  # type: ignore[assignment]
 
 from gateway.config import Platform, PlatformConfig
+from gateway.platforms.helpers import MessageDeduplicator
 from gateway.platforms.base import (
     BasePlatformAdapter,
     MessageEvent,
@@ -92,7 +93,6 @@ REQUEST_TIMEOUT_SECONDS = 15.0
 HEARTBEAT_INTERVAL_SECONDS = 30.0
 RECONNECT_BACKOFF = [2, 5, 10, 30, 60]
 
-DEDUP_WINDOW_SECONDS = 300
 DEDUP_MAX_SIZE = 1000
 
 IMAGE_MAX_BYTES = 10 * 1024 * 1024
@@ -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)
@@ -169,9 +172,16 @@ class WeComAdapter(BasePlatformAdapter):
         self._listen_task: Optional[asyncio.Task] = None
         self._heartbeat_task: Optional[asyncio.Task] = None
         self._pending_responses: Dict[str, asyncio.Future] = {}
-        self._seen_messages: Dict[str, float] = {}
+        self._dedup = MessageDeduplicator(max_size=DEDUP_MAX_SIZE)
         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
     # ------------------------------------------------------------------
@@ -240,7 +250,7 @@ class WeComAdapter(BasePlatformAdapter):
             await self._http_client.aclose()
             self._http_client = None
 
-        self._seen_messages.clear()
+        self._dedup.clear()
         logger.info("[%s] Disconnected", self.name)
 
     async def _cleanup_ws(self) -> None:
@@ -466,7 +476,7 @@ class WeComAdapter(BasePlatformAdapter):
             return
 
         msg_id = str(body.get("msgid") or self._payload_req_id(payload) or uuid.uuid4().hex)
-        if self._is_duplicate(msg_id):
+        if self._dedup.is_duplicate(msg_id):
             logger.debug("[%s] Duplicate message %s ignored", self.name, msg_id)
             return
         self._remember_reply_req_id(msg_id, self._payload_req_id(payload))
@@ -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]]:
@@ -551,6 +636,13 @@ class WeComAdapter(BasePlatformAdapter):
                 if voice_text:
                     text_parts.append(voice_text)
 
+            # Extract appmsg title (filename) for WeCom AI Bot attachments
+            if msgtype == "appmsg":
+                appmsg = body.get("appmsg") if isinstance(body.get("appmsg"), dict) else {}
+                title = str(appmsg.get("title") or "").strip()
+                if title:
+                    text_parts.append(title)
+
         quote = body.get("quote") if isinstance(body.get("quote"), dict) else {}
         quote_type = str(quote.get("msgtype") or "").lower()
         if quote_type == "text":
@@ -583,6 +675,13 @@ class WeComAdapter(BasePlatformAdapter):
                 refs.append(("image", body["image"]))
             if msgtype == "file" and isinstance(body.get("file"), dict):
                 refs.append(("file", body["file"]))
+            # Handle appmsg (WeCom AI Bot attachments with PDF/Word/Excel)
+            if msgtype == "appmsg" and isinstance(body.get("appmsg"), dict):
+                appmsg = body["appmsg"]
+                if isinstance(appmsg.get("file"), dict):
+                    refs.append(("file", appmsg["file"]))
+                elif isinstance(appmsg.get("image"), dict):
+                    refs.append(("image", appmsg["image"]))
 
         quote = body.get("quote") if isinstance(body.get("quote"), dict) else {}
         quote_type = str(quote.get("msgtype") or "").lower()
@@ -611,7 +710,11 @@ 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 +740,11 @@ 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
@@ -732,24 +839,6 @@ class WeComAdapter(BasePlatformAdapter):
         wildcard = self._groups.get("*")
         return wildcard if isinstance(wildcard, dict) else {}
 
-    def _is_duplicate(self, msg_id: str) -> bool:
-        now = time.time()
-        if len(self._seen_messages) > DEDUP_MAX_SIZE:
-            cutoff = now - DEDUP_WINDOW_SECONDS
-            self._seen_messages = {
-                key: ts for key, ts in self._seen_messages.items() if ts > cutoff
-            }
-            if self._reply_req_ids:
-                self._reply_req_ids = {
-                    key: value for key, value in self._reply_req_ids.items() if key in self._seen_messages
-                }
-
-        if msg_id in self._seen_messages:
-            return True
-
-        self._seen_messages[msg_id] = now
-        return False
-
     def _remember_reply_req_id(self, message_id: str, req_id: str) -> None:
         normalized_message_id = str(message_id or "").strip()
         normalized_req_id = str(req_id or "").strip()

gateway/platforms/wecom_callback.py

@@ -0,0 +1,387 @@
+"""WeCom callback-mode adapter for self-built enterprise applications.
+
+Unlike the bot/websocket adapter in ``wecom.py``, this handles the standard
+WeCom callback flow: WeCom POSTs encrypted XML to an HTTP endpoint, the
+adapter decrypts it, queues the message for the agent, and immediately
+acknowledges.  The agent's reply is delivered later via the proactive
+``message/send`` API using an access-token.
+
+Supports multiple self-built apps under one gateway instance, scoped by
+``corp_id:user_id`` to avoid cross-corp collisions.
+"""
+
+from __future__ import annotations
+
+import asyncio
+import logging
+import socket as _socket
+import time
+from typing import Any, Dict, List, Optional
+from xml.etree import ElementTree as ET
+
+try:
+    from aiohttp import web
+
+    AIOHTTP_AVAILABLE = True
+except ImportError:
+    web = None  # type: ignore[assignment]
+    AIOHTTP_AVAILABLE = False
+
+try:
+    import httpx
+
+    HTTPX_AVAILABLE = True
+except ImportError:
+    httpx = None  # type: ignore[assignment]
+    HTTPX_AVAILABLE = False
+
+from gateway.config import Platform, PlatformConfig
+from gateway.platforms.base import BasePlatformAdapter, MessageEvent, MessageType, SendResult
+from gateway.platforms.wecom_crypto import WXBizMsgCrypt, WeComCryptoError
+
+logger = logging.getLogger(__name__)
+
+DEFAULT_HOST = "0.0.0.0"
+DEFAULT_PORT = 8645
+DEFAULT_PATH = "/wecom/callback"
+ACCESS_TOKEN_TTL_SECONDS = 7200
+MESSAGE_DEDUP_TTL_SECONDS = 300
+
+
+def check_wecom_callback_requirements() -> bool:
+    return AIOHTTP_AVAILABLE and HTTPX_AVAILABLE
+
+
+class WecomCallbackAdapter(BasePlatformAdapter):
+    def __init__(self, config: PlatformConfig):
+        super().__init__(config, Platform.WECOM_CALLBACK)
+        extra = config.extra or {}
+        self._host = str(extra.get("host") or DEFAULT_HOST)
+        self._port = int(extra.get("port") or DEFAULT_PORT)
+        self._path = str(extra.get("path") or DEFAULT_PATH)
+        self._apps: List[Dict[str, Any]] = self._normalize_apps(extra)
+        self._runner: Optional[web.AppRunner] = None
+        self._site: Optional[web.TCPSite] = None
+        self._app: Optional[web.Application] = None
+        self._http_client: Optional[httpx.AsyncClient] = None
+        self._message_queue: asyncio.Queue[MessageEvent] = asyncio.Queue()
+        self._poll_task: Optional[asyncio.Task] = None
+        self._seen_messages: Dict[str, float] = {}
+        self._user_app_map: Dict[str, str] = {}
+        self._access_tokens: Dict[str, Dict[str, Any]] = {}
+
+    # ------------------------------------------------------------------
+    # App normalisation
+    # ------------------------------------------------------------------
+
+    @staticmethod
+    def _user_app_key(corp_id: str, user_id: str) -> str:
+        return f"{corp_id}:{user_id}" if corp_id else user_id
+
+    @staticmethod
+    def _normalize_apps(extra: Dict[str, Any]) -> List[Dict[str, Any]]:
+        apps = extra.get("apps")
+        if isinstance(apps, list) and apps:
+            return [dict(app) for app in apps if isinstance(app, dict)]
+        if extra.get("corp_id"):
+            return [
+                {
+                    "name": extra.get("name") or "default",
+                    "corp_id": extra.get("corp_id", ""),
+                    "corp_secret": extra.get("corp_secret", ""),
+                    "agent_id": str(extra.get("agent_id", "")),
+                    "token": extra.get("token", ""),
+                    "encoding_aes_key": extra.get("encoding_aes_key", ""),
+                }
+            ]
+        return []
+
+    # ------------------------------------------------------------------
+    # Lifecycle
+    # ------------------------------------------------------------------
+
+    async def connect(self) -> bool:
+        if not self._apps:
+            logger.warning("[WecomCallback] No callback apps configured")
+            return False
+        if not check_wecom_callback_requirements():
+            logger.warning("[WecomCallback] aiohttp/httpx not installed")
+            return False
+
+        # Quick port-in-use check.
+        try:
+            with _socket.socket(_socket.AF_INET, _socket.SOCK_STREAM) as sock:
+                sock.settimeout(1)
+                sock.connect(("127.0.0.1", self._port))
+            logger.error("[WecomCallback] Port %d already in use", self._port)
+            return False
+        except (ConnectionRefusedError, OSError):
+            pass
+
+        try:
+            self._http_client = httpx.AsyncClient(timeout=20.0)
+            self._app = web.Application()
+            self._app.router.add_get("/health", self._handle_health)
+            self._app.router.add_get(self._path, self._handle_verify)
+            self._app.router.add_post(self._path, self._handle_callback)
+            self._runner = web.AppRunner(self._app)
+            await self._runner.setup()
+            self._site = web.TCPSite(self._runner, self._host, self._port)
+            await self._site.start()
+            self._poll_task = asyncio.create_task(self._poll_loop())
+            self._mark_connected()
+            logger.info(
+                "[WecomCallback] HTTP server listening on %s:%s%s",
+                self._host, self._port, self._path,
+            )
+            for app in self._apps:
+                try:
+                    await self._refresh_access_token(app)
+                except Exception as exc:
+                    logger.warning(
+                        "[WecomCallback] Initial token refresh failed for app '%s': %s",
+                        app.get("name", "default"), exc,
+                    )
+            return True
+        except Exception:
+            await self._cleanup()
+            logger.exception("[WecomCallback] Failed to start")
+            return False
+
+    async def disconnect(self) -> None:
+        self._running = False
+        if self._poll_task:
+            self._poll_task.cancel()
+            try:
+                await self._poll_task
+            except asyncio.CancelledError:
+                pass
+            self._poll_task = None
+        await self._cleanup()
+        self._mark_disconnected()
+        logger.info("[WecomCallback] Disconnected")
+
+    async def _cleanup(self) -> None:
+        self._site = None
+        if self._runner:
+            await self._runner.cleanup()
+            self._runner = None
+        self._app = None
+        if self._http_client:
+            await self._http_client.aclose()
+            self._http_client = None
+
+    # ------------------------------------------------------------------
+    # Outbound: proactive send via access-token API
+    # ------------------------------------------------------------------
+
+    async def send(
+        self,
+        chat_id: str,
+        content: str,
+        reply_to: Optional[str] = None,
+        metadata: Optional[Dict[str, Any]] = None,
+    ) -> SendResult:
+        app = self._resolve_app_for_chat(chat_id)
+        touser = chat_id.split(":", 1)[1] if ":" in chat_id else chat_id
+        try:
+            token = await self._get_access_token(app)
+            payload = {
+                "touser": touser,
+                "msgtype": "text",
+                "agentid": int(str(app.get("agent_id") or 0)),
+                "text": {"content": content[:2048]},
+                "safe": 0,
+            }
+            resp = await self._http_client.post(
+                f"https://qyapi.weixin.qq.com/cgi-bin/message/send?access_token={token}",
+                json=payload,
+            )
+            data = resp.json()
+            if data.get("errcode") != 0:
+                return SendResult(success=False, error=str(data))
+            return SendResult(
+                success=True,
+                message_id=str(data.get("msgid", "")),
+                raw_response=data,
+            )
+        except Exception as exc:
+            return SendResult(success=False, error=str(exc))
+
+    def _resolve_app_for_chat(self, chat_id: str) -> Dict[str, Any]:
+        """Pick the app associated with *chat_id*, falling back sensibly."""
+        app_name = self._user_app_map.get(chat_id)
+        if not app_name and ":" not in chat_id:
+            # Legacy bare user_id — try to find a unique match.
+            matching = [k for k in self._user_app_map if k.endswith(f":{chat_id}")]
+            if len(matching) == 1:
+                app_name = self._user_app_map.get(matching[0])
+        app = self._get_app_by_name(app_name) if app_name else None
+        return app or self._apps[0]
+
+    async def get_chat_info(self, chat_id: str) -> Dict[str, Any]:
+        return {"name": chat_id, "type": "dm"}
+
+    # ------------------------------------------------------------------
+    # Inbound: HTTP callback handlers
+    # ------------------------------------------------------------------
+
+    async def _handle_health(self, request: web.Request) -> web.Response:
+        return web.json_response({"status": "ok", "platform": "wecom_callback"})
+
+    async def _handle_verify(self, request: web.Request) -> web.Response:
+        """GET endpoint — WeCom URL verification handshake."""
+        msg_signature = request.query.get("msg_signature", "")
+        timestamp = request.query.get("timestamp", "")
+        nonce = request.query.get("nonce", "")
+        echostr = request.query.get("echostr", "")
+        for app in self._apps:
+            try:
+                crypt = self._crypt_for_app(app)
+                plain = crypt.verify_url(msg_signature, timestamp, nonce, echostr)
+                return web.Response(text=plain, content_type="text/plain")
+            except Exception:
+                continue
+        return web.Response(status=403, text="signature verification failed")
+
+    async def _handle_callback(self, request: web.Request) -> web.Response:
+        """POST endpoint — receive an encrypted message callback."""
+        msg_signature = request.query.get("msg_signature", "")
+        timestamp = request.query.get("timestamp", "")
+        nonce = request.query.get("nonce", "")
+        body = await request.text()
+
+        for app in self._apps:
+            try:
+                decrypted = self._decrypt_request(
+                    app, body, msg_signature, timestamp, nonce,
+                )
+                event = self._build_event(app, decrypted)
+                if event is not None:
+                    # Record which app this user belongs to.
+                    if event.source and event.source.user_id:
+                        map_key = self._user_app_key(
+                            str(app.get("corp_id") or ""), event.source.user_id,
+                        )
+                        self._user_app_map[map_key] = app["name"]
+                    await self._message_queue.put(event)
+                # Immediately acknowledge — the agent's reply will arrive
+                # later via the proactive message/send API.
+                return web.Response(text="success", content_type="text/plain")
+            except WeComCryptoError:
+                continue
+            except Exception:
+                logger.exception("[WecomCallback] Error handling message")
+                break
+        return web.Response(status=400, text="invalid callback payload")
+
+    async def _poll_loop(self) -> None:
+        """Drain the message queue and dispatch to the gateway runner."""
+        while True:
+            event = await self._message_queue.get()
+            try:
+                task = asyncio.create_task(self.handle_message(event))
+                self._background_tasks.add(task)
+                task.add_done_callback(self._background_tasks.discard)
+            except Exception:
+                logger.exception("[WecomCallback] Failed to enqueue event")
+
+    # ------------------------------------------------------------------
+    # XML / crypto helpers
+    # ------------------------------------------------------------------
+
+    def _decrypt_request(
+        self, app: Dict[str, Any], body: str,
+        msg_signature: str, timestamp: str, nonce: str,
+    ) -> str:
+        root = ET.fromstring(body)
+        encrypt = root.findtext("Encrypt", default="")
+        crypt = self._crypt_for_app(app)
+        return crypt.decrypt(msg_signature, timestamp, nonce, encrypt).decode("utf-8")
+
+    def _build_event(self, app: Dict[str, Any], xml_text: str) -> Optional[MessageEvent]:
+        root = ET.fromstring(xml_text)
+        msg_type = (root.findtext("MsgType") or "").lower()
+        # Silently acknowledge lifecycle events.
+        if msg_type == "event":
+            event_name = (root.findtext("Event") or "").lower()
+            if event_name in {"enter_agent", "subscribe"}:
+                return None
+        if msg_type not in {"text", "event"}:
+            return None
+
+        user_id = root.findtext("FromUserName", default="")
+        corp_id = root.findtext("ToUserName", default=app.get("corp_id", ""))
+        scoped_chat_id = self._user_app_key(corp_id, user_id)
+        content = root.findtext("Content", default="").strip()
+        if not content and msg_type == "event":
+            content = "/start"
+        msg_id = (
+            root.findtext("MsgId")
+            or f"{user_id}:{root.findtext('CreateTime', default='0')}"
+        )
+        source = self.build_source(
+            chat_id=scoped_chat_id,
+            chat_name=user_id,
+            chat_type="dm",
+            user_id=user_id,
+            user_name=user_id,
+        )
+        return MessageEvent(
+            text=content,
+            message_type=MessageType.TEXT,
+            source=source,
+            raw_message=xml_text,
+            message_id=msg_id,
+        )
+
+    def _crypt_for_app(self, app: Dict[str, Any]) -> WXBizMsgCrypt:
+        return WXBizMsgCrypt(
+            token=str(app.get("token") or ""),
+            encoding_aes_key=str(app.get("encoding_aes_key") or ""),
+            receive_id=str(app.get("corp_id") or ""),
+        )
+
+    def _get_app_by_name(self, name: Optional[str]) -> Optional[Dict[str, Any]]:
+        if not name:
+            return None
+        for app in self._apps:
+            if app.get("name") == name:
+                return app
+        return None
+
+    # ------------------------------------------------------------------
+    # Access-token management
+    # ------------------------------------------------------------------
+
+    async def _get_access_token(self, app: Dict[str, Any]) -> str:
+        cached = self._access_tokens.get(app["name"])
+        now = time.time()
+        if cached and cached.get("expires_at", 0) > now + 60:
+            return cached["token"]
+        return await self._refresh_access_token(app)
+
+    async def _refresh_access_token(self, app: Dict[str, Any]) -> str:
+        resp = await self._http_client.get(
+            "https://qyapi.weixin.qq.com/cgi-bin/gettoken",
+            params={
+                "corpid": app.get("corp_id"),
+                "corpsecret": app.get("corp_secret"),
+            },
+        )
+        data = resp.json()
+        if data.get("errcode") != 0:
+            raise RuntimeError(f"WeCom token refresh failed: {data}")
+        token = data["access_token"]
+        expires_in = int(data.get("expires_in", ACCESS_TOKEN_TTL_SECONDS))
+        self._access_tokens[app["name"]] = {
+            "token": token,
+            "expires_at": time.time() + expires_in,
+        }
+        logger.info(
+            "[WecomCallback] Token refreshed for app '%s' (corp=%s), expires in %ss",
+            app.get("name", "default"),
+            app.get("corp_id", ""),
+            expires_in,
+        )
+        return token

gateway/platforms/wecom_crypto.py

@@ -0,0 +1,142 @@
+"""WeCom BizMsgCrypt-compatible AES-CBC encryption for callback mode.
+
+Implements the same wire format as Tencent's official ``WXBizMsgCrypt``
+SDK so that WeCom can verify, encrypt, and decrypt callback payloads.
+"""
+
+from __future__ import annotations
+
+import base64
+import hashlib
+import os
+import secrets
+import socket
+import struct
+from typing import Optional
+from xml.etree import ElementTree as ET
+
+from cryptography.hazmat.backends import default_backend
+from cryptography.hazmat.primitives.ciphers import Cipher, algorithms, modes
+
+
+class WeComCryptoError(Exception):
+    pass
+
+
+class SignatureError(WeComCryptoError):
+    pass
+
+
+class DecryptError(WeComCryptoError):
+    pass
+
+
+class EncryptError(WeComCryptoError):
+    pass
+
+
+class PKCS7Encoder:
+    block_size = 32
+
+    @classmethod
+    def encode(cls, text: bytes) -> bytes:
+        amount_to_pad = cls.block_size - (len(text) % cls.block_size)
+        if amount_to_pad == 0:
+            amount_to_pad = cls.block_size
+        pad = bytes([amount_to_pad]) * amount_to_pad
+        return text + pad
+
+    @classmethod
+    def decode(cls, decrypted: bytes) -> bytes:
+        if not decrypted:
+            raise DecryptError("empty decrypted payload")
+        pad = decrypted[-1]
+        if pad < 1 or pad > cls.block_size:
+            raise DecryptError("invalid PKCS7 padding")
+        if decrypted[-pad:] != bytes([pad]) * pad:
+            raise DecryptError("malformed PKCS7 padding")
+        return decrypted[:-pad]
+
+
+def _sha1_signature(token: str, timestamp: str, nonce: str, encrypt: str) -> str:
+    parts = sorted([token, timestamp, nonce, encrypt])
+    return hashlib.sha1("".join(parts).encode("utf-8")).hexdigest()
+
+
+class WXBizMsgCrypt:
+    """Minimal WeCom callback crypto helper compatible with BizMsgCrypt semantics."""
+
+    def __init__(self, token: str, encoding_aes_key: str, receive_id: str):
+        if not token:
+            raise ValueError("token is required")
+        if not encoding_aes_key:
+            raise ValueError("encoding_aes_key is required")
+        if len(encoding_aes_key) != 43:
+            raise ValueError("encoding_aes_key must be 43 chars")
+        if not receive_id:
+            raise ValueError("receive_id is required")
+
+        self.token = token
+        self.receive_id = receive_id
+        self.key = base64.b64decode(encoding_aes_key + "=")
+        self.iv = self.key[:16]
+
+    def verify_url(self, msg_signature: str, timestamp: str, nonce: str, echostr: str) -> str:
+        plain = self.decrypt(msg_signature, timestamp, nonce, echostr)
+        return plain.decode("utf-8")
+
+    def decrypt(self, msg_signature: str, timestamp: str, nonce: str, encrypt: str) -> bytes:
+        expected = _sha1_signature(self.token, timestamp, nonce, encrypt)
+        if expected != msg_signature:
+            raise SignatureError("signature mismatch")
+        try:
+            cipher_text = base64.b64decode(encrypt)
+        except Exception as exc:
+            raise DecryptError(f"invalid base64 payload: {exc}") from exc
+        try:
+            cipher = Cipher(algorithms.AES(self.key), modes.CBC(self.iv), backend=default_backend())
+            decryptor = cipher.decryptor()
+            padded = decryptor.update(cipher_text) + decryptor.finalize()
+            plain = PKCS7Encoder.decode(padded)
+            content = plain[16:]  # skip 16-byte random prefix
+            xml_length = socket.ntohl(struct.unpack("I", content[:4])[0])
+            xml_content = content[4:4 + xml_length]
+            receive_id = content[4 + xml_length:].decode("utf-8")
+        except WeComCryptoError:
+            raise
+        except Exception as exc:
+            raise DecryptError(f"decrypt failed: {exc}") from exc
+
+        if receive_id != self.receive_id:
+            raise DecryptError("receive_id mismatch")
+        return xml_content
+
+    def encrypt(self, plaintext: str, nonce: Optional[str] = None, timestamp: Optional[str] = None) -> str:
+        nonce = nonce or self._random_nonce()
+        timestamp = timestamp or str(int(__import__("time").time()))
+        encrypt = self._encrypt_bytes(plaintext.encode("utf-8"))
+        signature = _sha1_signature(self.token, timestamp, nonce, encrypt)
+        root = ET.Element("xml")
+        ET.SubElement(root, "Encrypt").text = encrypt
+        ET.SubElement(root, "MsgSignature").text = signature
+        ET.SubElement(root, "TimeStamp").text = timestamp
+        ET.SubElement(root, "Nonce").text = nonce
+        return ET.tostring(root, encoding="unicode")
+
+    def _encrypt_bytes(self, raw: bytes) -> str:
+        try:
+            random_prefix = os.urandom(16)
+            msg_len = struct.pack("I", socket.htonl(len(raw)))
+            payload = random_prefix + msg_len + raw + self.receive_id.encode("utf-8")
+            padded = PKCS7Encoder.encode(payload)
+            cipher = Cipher(algorithms.AES(self.key), modes.CBC(self.iv), backend=default_backend())
+            encryptor = cipher.encryptor()
+            encrypted = encryptor.update(padded) + encryptor.finalize()
+            return base64.b64encode(encrypted).decode("utf-8")
+        except Exception as exc:
+            raise EncryptError(f"encrypt failed: {exc}") from exc
+
+    @staticmethod
+    def _random_nonce(length: int = 10) -> str:
+        alphabet = "0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ"
+        return "".join(secrets.choice(alphabet) for _ in range(length))

gateway/platforms/whatsapp.py

@@ -145,7 +145,6 @@ class WhatsAppAdapter(BasePlatformAdapter):
         self._bridge_log: Optional[Path] = None
         self._poll_task: Optional[asyncio.Task] = None
         self._http_session: Optional["aiohttp.ClientSession"] = None
-        self._session_lock_identity: Optional[str] = None
 
     def _whatsapp_require_mention(self) -> bool:
         configured = self.config.extra.get("require_mention")
@@ -290,23 +289,7 @@ class WhatsAppAdapter(BasePlatformAdapter):
         
         # Acquire scoped lock to prevent duplicate sessions
         try:
-            from gateway.status import acquire_scoped_lock
-
-            self._session_lock_identity = str(self._session_path)
-            acquired, existing = acquire_scoped_lock(
-                "whatsapp-session",
-                self._session_lock_identity,
-                metadata={"platform": self.platform.value},
-            )
-            if not acquired:
-                owner_pid = existing.get("pid") if isinstance(existing, dict) else None
-                message = (
-                    "Another local Hermes gateway is already using this WhatsApp session"
-                    + (f" (PID {owner_pid})." if owner_pid else ".")
-                    + " Stop the other gateway before starting a second WhatsApp bridge."
-                )
-                logger.error("[%s] %s", self.name, message)
-                self._set_fatal_error("whatsapp_session_lock", message, retryable=False)
+            if not self._acquire_platform_lock('whatsapp-session', str(self._session_path), 'WhatsApp session'):
                 return False
         except Exception as e:
             logger.warning("[%s] Could not acquire session lock (non-fatal): %s", self.name, e)
@@ -468,12 +451,7 @@ class WhatsAppAdapter(BasePlatformAdapter):
             return True
             
         except Exception as e:
-            if self._session_lock_identity:
-                try:
-                    from gateway.status import release_scoped_lock
-                    release_scoped_lock("whatsapp-session", self._session_lock_identity)
-                except Exception:
-                    pass
+            self._release_platform_lock()
             logger.error("[%s] Failed to start bridge: %s", self.name, e, exc_info=True)
             self._close_bridge_log()
             return False
@@ -546,17 +524,11 @@ class WhatsAppAdapter(BasePlatformAdapter):
             await self._http_session.close()
         self._http_session = None
 
-        if self._session_lock_identity:
-            try:
-                from gateway.status import release_scoped_lock
-                release_scoped_lock("whatsapp-session", self._session_lock_identity)
-            except Exception as e:
-                logger.warning("[%s] Error releasing WhatsApp session lock: %s", self.name, e, exc_info=True)
+        self._release_platform_lock()
 
         self._mark_disconnected()
         self._bridge_process = None
         self._close_bridge_log()
-        self._session_lock_identity = None
         print(f"[{self.name}] Disconnected")
     
     async def send(

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
@@ -384,6 +368,11 @@ class SessionEntry:
     # survives gateway restarts (the old in-memory _pre_flushed_sessions
     # set was lost on restart, causing redundant re-flushes).
     memory_flushed: bool = False
+
+    # When True the next call to get_or_create_session() will auto-reset
+    # this session (create a new session_id) so the user starts fresh.
+    # Set by /stop to break stuck-resume loops (#7536).
+    suspended: bool = False
     
     def to_dict(self) -> Dict[str, Any]:
         result = {
@@ -403,6 +392,7 @@ class SessionEntry:
             "estimated_cost_usd": self.estimated_cost_usd,
             "cost_status": self.cost_status,
             "memory_flushed": self.memory_flushed,
+            "suspended": self.suspended,
         }
         if self.origin:
             result["origin"] = self.origin.to_dict()
@@ -439,6 +429,7 @@ class SessionEntry:
             estimated_cost_usd=data.get("estimated_cost_usd", 0.0),
             cost_status=data.get("cost_status", "unknown"),
             memory_flushed=data.get("memory_flushed", False),
+            suspended=data.get("suspended", False),
         )
 
 
@@ -510,8 +501,7 @@ 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] = {}
@@ -715,7 +705,12 @@ class SessionStore:
             if session_key in self._entries and not force_new:
                 entry = self._entries[session_key]
 
-                reset_reason = self._should_reset(entry, source)
+                # Auto-reset sessions marked as suspended (e.g. after /stop
+                # broke a stuck loop — #7536).
+                if entry.suspended:
+                    reset_reason = "suspended"
+                else:
+                    reset_reason = self._should_reset(entry, source)
                 if not reset_reason:
                     entry.updated_at = now
                     self._save()
@@ -770,41 +765,6 @@ 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(
@@ -823,6 +783,44 @@ class SessionStore:
                     entry.last_prompt_tokens = last_prompt_tokens
                 self._save()
 
+    def suspend_session(self, session_key: str) -> bool:
+        """Mark a session as suspended so it auto-resets on next access.
+
+        Used by ``/stop`` to prevent stuck sessions from being resumed
+        after a gateway restart (#7536).  Returns True if the session
+        existed and was marked.
+        """
+        with self._lock:
+            self._ensure_loaded_locked()
+            if session_key in self._entries:
+                self._entries[session_key].suspended = True
+                self._save()
+                return True
+        return False
+
+    def suspend_recently_active(self, max_age_seconds: int = 120) -> int:
+        """Mark recently-active sessions as suspended.
+
+        Called on gateway startup to prevent sessions that were likely
+        in-flight when the gateway last exited from being blindly resumed
+        (#7536).  Only suspends sessions updated within *max_age_seconds*
+        to avoid resetting long-idle sessions that are harmless to resume.
+        Returns the number of sessions that were suspended.
+        """
+        from datetime import timedelta
+
+        cutoff = _now() - timedelta(seconds=max_age_seconds)
+        count = 0
+        with self._lock:
+            self._ensure_loaded_locked()
+            for entry in self._entries.values():
+                if not entry.suspended and entry.updated_at >= cutoff:
+                    entry.suspended = True
+                    count += 1
+            if count:
+                self._save()
+        return count
+
     def reset_session(self, session_key: str) -> Optional[SessionEntry]:
         """Force reset a session, creating a new session ID."""
         db_end_session_id = None

gateway/session_context.py

@@ -0,0 +1,128 @@
+"""
+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="")
+_SESSION_USER_ID: ContextVar[str] = ContextVar("HERMES_SESSION_USER_ID", default="")
+_SESSION_USER_NAME: ContextVar[str] = ContextVar("HERMES_SESSION_USER_NAME", default="")
+_SESSION_KEY: ContextVar[str] = ContextVar("HERMES_SESSION_KEY", 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,
+    "HERMES_SESSION_USER_ID": _SESSION_USER_ID,
+    "HERMES_SESSION_USER_NAME": _SESSION_USER_NAME,
+    "HERMES_SESSION_KEY": _SESSION_KEY,
+}
+
+
+def set_session_vars(
+    platform: str = "",
+    chat_id: str = "",
+    chat_name: str = "",
+    thread_id: str = "",
+    user_id: str = "",
+    user_name: str = "",
+    session_key: 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),
+        _SESSION_USER_ID.set(user_id),
+        _SESSION_USER_NAME.set(user_name),
+        _SESSION_KEY.set(session_key),
+    ]
+    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,
+        _SESSION_USER_ID,
+        _SESSION_USER_NAME,
+        _SESSION_KEY,
+    ]
+    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 +25,8 @@ from typing import Any, Optional
 _GATEWAY_KIND = "hermes-gateway"
 _RUNTIME_STATUS_FILE = "gateway_state.json"
 _LOCKS_DIRNAME = "gateway-locks"
+_IS_WINDOWS = sys.platform == "win32"
+_UNSET = object()
 
 
 def _get_pid_path() -> Path:
@@ -49,6 +53,33 @@ 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 +159,8 @@ 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(),
     })
@@ -186,12 +219,14 @@ def write_pid_file() -> None:
 
 def write_runtime_status(
     *,
-    gateway_state: Optional[str] = None,
-    exit_reason: Optional[str] = None,
-    platform: Optional[str] = None,
-    platform_state: Optional[str] = None,
-    error_code: Optional[str] = None,
-    error_message: Optional[str] = None,
+    gateway_state: Any = _UNSET,
+    exit_reason: Any = _UNSET,
+    restart_requested: Any = _UNSET,
+    active_agents: Any = _UNSET,
+    platform: Any = _UNSET,
+    platform_state: Any = _UNSET,
+    error_code: Any = _UNSET,
+    error_message: Any = _UNSET,
 ) -> None:
     """Persist gateway runtime health information for diagnostics/status."""
     path = _get_runtime_status_path()
@@ -202,18 +237,22 @@ def write_runtime_status(
     payload["start_time"] = _get_process_start_time(os.getpid())
     payload["updated_at"] = _utc_now_iso()
 
-    if gateway_state is not None:
+    if gateway_state is not _UNSET:
         payload["gateway_state"] = gateway_state
-    if exit_reason is not None:
+    if exit_reason is not _UNSET:
         payload["exit_reason"] = exit_reason
+    if restart_requested is not _UNSET:
+        payload["restart_requested"] = bool(restart_requested)
+    if active_agents is not _UNSET:
+        payload["active_agents"] = max(0, int(active_agents))
 
-    if platform is not None:
+    if platform is not _UNSET:
         platform_payload = payload["platforms"].get(platform, {})
-        if platform_state is not None:
+        if platform_state is not _UNSET:
             platform_payload["state"] = platform_state
-        if error_code is not None:
+        if error_code is not _UNSET:
             platform_payload["error_code"] = error_code
-        if error_message is not None:
+        if error_message is not _UNSET:
             platform_payload["error_message"] = error_message
         platform_payload["updated_at"] = _utc_now_iso()
         payload["platforms"][platform] = platform_payload

gateway/stream_consumer.py

@@ -32,11 +32,15 @@ _DONE = object()
 # new one so that subsequent text appears below tool progress messages.
 _NEW_SEGMENT = object()
 
+# Queue marker for a completed assistant commentary message emitted between
+# API/tool iterations (for example: "I'll inspect the repo first.").
+_COMMENTARY = object()
+
 
 @dataclass
 class StreamConsumerConfig:
     """Runtime config for a single stream consumer instance."""
-    edit_interval: float = 0.3
+    edit_interval: float = 1.0
     buffer_threshold: int = 40
     cursor: str = " ▉"
 
@@ -56,6 +60,10 @@ class GatewayStreamConsumer:
         await task         # wait for final edit
     """
 
+    # After this many consecutive flood-control failures, permanently disable
+    # progressive edits for the remainder of the stream.
+    _MAX_FLOOD_STRIKES = 3
+
     def __init__(
         self,
         adapter: Any,
@@ -71,18 +79,43 @@ class GatewayStreamConsumer:
         self._accumulated = ""
         self._message_id: Optional[str] = None
         self._already_sent = False
-        self._edit_supported = True  # Disabled on first edit failure (Signal/Email/HA)
+        self._edit_supported = True  # Disabled when progressive edits are no longer usable
         self._last_edit_time = 0.0
         self._last_sent_text = ""   # Track last-sent text to skip redundant edits
         self._fallback_final_send = False
         self._fallback_prefix = ""
+        self._flood_strikes = 0         # Consecutive flood-control edit failures
+        self._current_edit_interval = self.cfg.edit_interval  # Adaptive backoff
+        self._final_response_sent = False
 
     @property
     def already_sent(self) -> bool:
-        """True if at least one message was sent/edited — signals the base
-        adapter to skip re-sending the final response."""
+        """True if at least one message was sent or edited during the run."""
         return self._already_sent
 
+    @property
+    def final_response_sent(self) -> bool:
+        """True when the stream consumer delivered the final assistant reply."""
+        return self._final_response_sent
+
+    def on_segment_break(self) -> None:
+        """Finalize the current stream segment and start a fresh message."""
+        self._queue.put(_NEW_SEGMENT)
+
+    def on_commentary(self, text: str) -> None:
+        """Queue a completed interim assistant commentary message."""
+        if text:
+            self._queue.put((_COMMENTARY, text))
+
+    def _reset_segment_state(self, *, preserve_no_edit: bool = False) -> None:
+        if preserve_no_edit and self._message_id == "__no_edit__":
+            return
+        self._message_id = None
+        self._accumulated = ""
+        self._last_sent_text = ""
+        self._fallback_final_send = False
+        self._fallback_prefix = ""
+
     def on_delta(self, text: str) -> None:
         """Thread-safe callback — called from the agent's worker thread.
 
@@ -93,7 +126,7 @@ class GatewayStreamConsumer:
         if text:
             self._queue.put(text)
         elif text is None:
-            self._queue.put(_NEW_SEGMENT)
+            self.on_segment_break()
 
     def finish(self) -> None:
         """Signal that the stream is complete."""
@@ -110,6 +143,7 @@ class GatewayStreamConsumer:
                 # Drain all available items from the queue
                 got_done = False
                 got_segment_break = False
+                commentary_text = None
                 while True:
                     try:
                         item = self._queue.get_nowait()
@@ -119,6 +153,9 @@ class GatewayStreamConsumer:
                         if item is _NEW_SEGMENT:
                             got_segment_break = True
                             break
+                        if isinstance(item, tuple) and len(item) == 2 and item[0] is _COMMENTARY:
+                            commentary_text = item[1]
+                            break
                         self._accumulated += item
                     except queue.Empty:
                         break
@@ -129,14 +166,44 @@ class GatewayStreamConsumer:
                 should_edit = (
                     got_done
                     or got_segment_break
-                    or (elapsed >= self.cfg.edit_interval
+                    or commentary_text is not None
+                    or (elapsed >= self._current_edit_interval
                         and self._accumulated)
                     or len(self._accumulated) >= self.cfg.buffer_threshold
                 )
 
+                current_update_visible = False
                 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:
+                            self._final_response_sent = self._already_sent
+                            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
@@ -146,22 +213,23 @@ class GatewayStreamConsumer:
                         if split_at < _safe_limit // 2:
                             split_at = _safe_limit
                         chunk = self._accumulated[:split_at]
-                        await self._send_or_edit(chunk)
-                        if self._fallback_final_send:
-                            # Edit failed while attempting to split an oversized
-                            # message. Keep the full accumulated text intact so
-                            # the fallback final-send path can deliver the
-                            # remaining continuation without dropping content.
+                        ok = await self._send_or_edit(chunk)
+                        if self._fallback_final_send or not ok:
+                            # Edit failed (or backed off due to flood control)
+                            # while attempting to split an oversized message.
+                            # Keep the full accumulated text intact so the
+                            # fallback final-send path can deliver the remaining
+                            # continuation without dropping content.
                             break
                         self._accumulated = self._accumulated[split_at:].lstrip("\n")
                         self._message_id = None
                         self._last_sent_text = ""
 
                     display_text = self._accumulated
-                    if not got_done and not got_segment_break:
+                    if not got_done and not got_segment_break and commentary_text is None:
                         display_text += self.cfg.cursor
 
-                    await self._send_or_edit(display_text)
+                    current_update_visible = await self._send_or_edit(display_text)
                     self._last_edit_time = time.monotonic()
 
                 if got_done:
@@ -172,22 +240,36 @@ class GatewayStreamConsumer:
                     if self._accumulated:
                         if self._fallback_final_send:
                             await self._send_fallback_final(self._accumulated)
+                        elif current_update_visible:
+                            self._final_response_sent = True
                         elif self._message_id:
-                            await self._send_or_edit(self._accumulated)
+                            self._final_response_sent = await self._send_or_edit(self._accumulated)
                         elif not self._already_sent:
-                            await self._send_or_edit(self._accumulated)
+                            self._final_response_sent = 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 commentary_text is not None:
+                    self._reset_segment_state()
+                    await self._send_commentary(commentary_text)
+                    self._last_edit_time = time.monotonic()
+                    self._reset_segment_state()
+
+                # 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, preserve the sentinel
+                # 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:
-                    self._message_id = None
-                    self._accumulated = ""
-                    self._last_sent_text = ""
-                    self._fallback_final_send = False
-                    self._fallback_prefix = ""
+                    self._reset_segment_state(preserve_no_edit=True)
 
                 await asyncio.sleep(0.05)  # Small yield to not busy-loop
 
@@ -226,6 +308,34 @@ 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 ""
@@ -258,13 +368,17 @@ class GatewayStreamConsumer:
         return chunks
 
     async def _send_fallback_final(self, text: str) -> None:
-        """Send the final continuation after streaming edits stop working."""
+        """Send the final continuation after streaming edits stop working.
+
+        Retries each chunk once on flood-control failures with a short delay.
+        """
         final_text = self._clean_for_display(text)
         continuation = self._continuation_text(final_text)
         self._fallback_final_send = False
         if not continuation.strip():
             # Nothing new to send — the visible partial already matches final text.
             self._already_sent = True
+            self._final_response_sent = True
             return
 
         raw_limit = getattr(self.adapter, "MAX_MESSAGE_LENGTH", 4096)
@@ -275,17 +389,31 @@ class GatewayStreamConsumer:
         last_successful_chunk = ""
         sent_any_chunk = False
         for chunk in chunks:
-            result = await self.adapter.send(
-                chat_id=self.chat_id,
-                content=chunk,
-                metadata=self.metadata,
-            )
-            if not result.success:
+            # Try sending with one retry on flood-control errors.
+            result = None
+            for attempt in range(2):
+                result = await self.adapter.send(
+                    chat_id=self.chat_id,
+                    content=chunk,
+                    metadata=self.metadata,
+                )
+                if result.success:
+                    break
+                if attempt == 0 and self._is_flood_error(result):
+                    logger.debug(
+                        "Flood control on fallback send, retrying in 3s"
+                    )
+                    await asyncio.sleep(3.0)
+                else:
+                    break  # non-flood error or second attempt failed
+
+            if not result or not result.success:
                 if sent_any_chunk:
                     # Some continuation text already reached the user. Suppress
                     # the base gateway final-send path so we don't resend the
                     # full response and create another duplicate.
                     self._already_sent = True
+                    self._final_response_sent = True
                     self._message_id = last_message_id
                     self._last_sent_text = last_successful_chunk
                     self._fallback_prefix = ""
@@ -303,23 +431,74 @@ class GatewayStreamConsumer:
 
         self._message_id = last_message_id
         self._already_sent = True
+        self._final_response_sent = True
         self._last_sent_text = chunks[-1]
         self._fallback_prefix = ""
 
-    async def _send_or_edit(self, text: str) -> None:
-        """Send or edit the streaming message."""
+    def _is_flood_error(self, result) -> bool:
+        """Check if a SendResult failure is due to flood control / rate limiting."""
+        err = getattr(result, "error", "") or ""
+        err_lower = err.lower()
+        return "flood" in err_lower or "retry after" in err_lower or "rate" in err_lower
+
+    async def _try_strip_cursor(self) -> None:
+        """Best-effort edit to remove the cursor from the last visible message.
+
+        Called when entering fallback mode so the user doesn't see a stuck
+        cursor (▉) in the partial message.
+        """
+        if not self._message_id or self._message_id == "__no_edit__":
+            return
+        prefix = self._visible_prefix()
+        if not prefix or not prefix.strip():
+            return
+        try:
+            await self.adapter.edit_message(
+                chat_id=self.chat_id,
+                message_id=self._message_id,
+                content=prefix,
+            )
+            self._last_sent_text = prefix
+        except Exception:
+            pass  # best-effort — don't let this block the fallback path
+
+    async def _send_commentary(self, text: str) -> bool:
+        """Send a completed interim assistant commentary message."""
+        text = self._clean_for_display(text)
+        if not text.strip():
+            return False
+        try:
+            result = await self.adapter.send(
+                chat_id=self.chat_id,
+                content=text,
+                metadata=self.metadata,
+            )
+            if result.success:
+                self._already_sent = True
+                return True
+        except Exception as e:
+            logger.error("Commentary send error: %s", e)
+        return False
+
+    async def _send_or_edit(self, text: str) -> bool:
+        """Send or edit the streaming message.
+
+        Returns True if the text was successfully delivered (sent or edited),
+        False otherwise.  Callers like the overflow split loop use this to
+        decide whether to advance past the delivered chunk.
+        """
         # Strip MEDIA: directives so they don't appear as visible text.
         # Media files are delivered as native attachments after the stream
         # finishes (via _deliver_media_from_response in gateway/run.py).
         text = self._clean_for_display(text)
         if not text.strip():
-            return
+            return True  # nothing to send is "success"
         try:
             if self._message_id is not None:
                 if self._edit_supported:
                     # Skip if text is identical to what we last sent
                     if text == self._last_sent_text:
-                        return
+                        return True
                     # Edit existing message
                     result = await self.adapter.edit_message(
                         chat_id=self.chat_id,
@@ -329,19 +508,52 @@ class GatewayStreamConsumer:
                     if result.success:
                         self._already_sent = True
                         self._last_sent_text = text
+                        # Successful edit — reset flood strike counter
+                        self._flood_strikes = 0
+                        return True
                     else:
-                        # If an edit fails mid-stream (especially Telegram flood control),
-                        # stop progressive edits and send only the missing tail once the
+                        # Edit failed.  If this looks like flood control / rate
+                        # limiting, use adaptive backoff: double the edit interval
+                        # and retry on the next cycle.  Only permanently disable
+                        # edits after _MAX_FLOOD_STRIKES consecutive failures.
+                        if self._is_flood_error(result):
+                            self._flood_strikes += 1
+                            self._current_edit_interval = min(
+                                self._current_edit_interval * 2, 10.0,
+                            )
+                            logger.debug(
+                                "Flood control on edit (strike %d/%d), "
+                                "backoff interval → %.1fs",
+                                self._flood_strikes,
+                                self._MAX_FLOOD_STRIKES,
+                                self._current_edit_interval,
+                            )
+                            if self._flood_strikes < self._MAX_FLOOD_STRIKES:
+                                # Don't disable edits yet — just slow down.
+                                # Update _last_edit_time so the next edit
+                                # respects the new interval.
+                                self._last_edit_time = time.monotonic()
+                                return False
+
+                        # Non-flood error OR flood strikes exhausted: enter
+                        # fallback mode — send only the missing tail once the
                         # final response is available.
-                        logger.debug("Edit failed, disabling streaming for this adapter")
+                        logger.debug(
+                            "Edit failed (strikes=%d), entering fallback mode",
+                            self._flood_strikes,
+                        )
                         self._fallback_prefix = self._visible_prefix()
                         self._fallback_final_send = True
                         self._edit_supported = False
                         self._already_sent = True
+                        # Best-effort: strip the cursor from the last visible
+                        # message so the user doesn't see a stuck ▉.
+                        await self._try_strip_cursor()
+                        return False
                 else:
                     # Editing not supported — skip intermediate updates.
                     # The final response will be sent by the fallback path.
-                    pass
+                    return False
             else:
                 # First message — send new
                 result = await self.adapter.send(
@@ -349,23 +561,25 @@ class GatewayStreamConsumer:
                     content=text,
                     metadata=self.metadata,
                 )
-                if result.success and result.message_id:
-                    self._message_id = result.message_id
+                if result.success:
+                    if result.message_id:
+                        self._message_id = result.message_id
+                    else:
+                        self._edit_supported = False
                     self._already_sent = True
                     self._last_sent_text = text
-                elif result.success:
-                    # Platform accepted the message but returned no message_id
-                    # (e.g. Signal).  Can't edit without an ID — switch to
-                    # fallback mode: suppress intermediate deltas, send only
-                    # the missing tail once the final response is ready.
-                    self._already_sent = True
-                    self._edit_supported = False
-                    self._fallback_prefix = self._clean_for_display(text)
-                    self._fallback_final_send = True
-                    # Sentinel prevents re-entering this branch on every delta
-                    self._message_id = "__no_edit__"
+                    if not result.message_id:
+                        self._fallback_prefix = self._visible_prefix()
+                        self._fallback_final_send = True
+                        # Sentinel prevents re-entering the first-send path on
+                        # every delta/tool boundary when platforms accept a
+                        # message but do not return an editable message id.
+                        self._message_id = "__no_edit__"
+                    return True
                 else:
                     # Initial send failed — disable streaming for this session
                     self._edit_supported = False
+                    return False
         except Exception as e:
             logger.error("Stream send/edit error: %s", e)
+            return False

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",
@@ -243,14 +250,44 @@ PROVIDER_REGISTRY: Dict[str, ProviderConfig] = {
         api_key_env_vars=("HF_TOKEN",),
         base_url_env_var="HF_BASE_URL",
     ),
+    "xiaomi": ProviderConfig(
+        id="xiaomi",
+        name="Xiaomi MiMo",
+        auth_type="api_key",
+        inference_base_url="https://api.xiaomimimo.com/v1",
+        api_key_env_vars=("XIAOMI_API_KEY",),
+        base_url_env_var="XIAOMI_BASE_URL",
+    ),
 }
 
 
+# =============================================================================
+# Anthropic Key Helper
+# =============================================================================
+
+def get_anthropic_key() -> str:
+    """Return the first usable Anthropic credential, or ``""``.
+
+    Checks both the ``.env`` file (via ``get_env_value``) and the process
+    environment (``os.getenv``).  The fallback order mirrors the
+    ``PROVIDER_REGISTRY["anthropic"].api_key_env_vars`` tuple:
+
+        ANTHROPIC_API_KEY -> ANTHROPIC_TOKEN -> CLAUDE_CODE_OAUTH_TOKEN
+    """
+    from hermes_cli.config import get_env_value
+
+    for var in PROVIDER_REGISTRY["anthropic"].api_key_env_vars:
+        value = get_env_value(var) or os.getenv(var, "")
+        if value:
+            return value
+    return ""
+
+
 # =============================================================================
 # 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 +742,27 @@ 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 +775,57 @@ 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 +928,7 @@ 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",
@@ -829,6 +938,7 @@ def resolve_provider(
         "opencode": "opencode-zen", "zen": "opencode-zen",
         "qwen-portal": "qwen-oauth", "qwen-cli": "qwen-oauth", "qwen-oauth": "qwen-oauth",
         "hf": "huggingface", "hugging-face": "huggingface", "huggingface-hub": "huggingface",
+        "mimo": "xiaomi", "xiaomi-mimo": "xiaomi",
         "go": "opencode-go", "opencode-go-sub": "opencode-go",
         "kilo": "kilocode", "kilo-code": "kilocode", "kilo-gateway": "kilocode",
         # Local server aliases — route through the generic custom provider
@@ -1442,7 +1552,15 @@ 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 +2460,6 @@ 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 +2663,8 @@ 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 +2674,7 @@ 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 +3110,15 @@ 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 +3152,6 @@ 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 +3163,15 @@ 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/backup.py

@@ -0,0 +1,399 @@
+"""
+Backup and import commands for hermes CLI.
+
+`hermes backup` creates a zip archive of the entire ~/.hermes/ directory
+(excluding the hermes-agent repo and transient files).
+
+`hermes import` restores from a backup zip, overlaying onto the current
+HERMES_HOME root.
+"""
+
+import os
+import sys
+import time
+import zipfile
+from datetime import datetime
+from pathlib import Path
+
+from hermes_constants import get_default_hermes_root, display_hermes_home
+
+
+# ---------------------------------------------------------------------------
+# Exclusion rules
+# ---------------------------------------------------------------------------
+
+# Directory names to skip entirely (matched against each path component)
+_EXCLUDED_DIRS = {
+    "hermes-agent",     # the codebase repo — re-clone instead
+    "__pycache__",      # bytecode caches — regenerated on import
+    ".git",             # nested git dirs (profiles shouldn't have these, but safety)
+    "node_modules",     # js deps if website/ somehow leaks in
+}
+
+# File-name suffixes to skip
+_EXCLUDED_SUFFIXES = (
+    ".pyc",
+    ".pyo",
+)
+
+# File names to skip (runtime state that's meaningless on another machine)
+_EXCLUDED_NAMES = {
+    "gateway.pid",
+    "cron.pid",
+}
+
+
+def _should_exclude(rel_path: Path) -> bool:
+    """Return True if *rel_path* (relative to hermes root) should be skipped."""
+    parts = rel_path.parts
+
+    # Any path component matches an excluded dir name
+    for part in parts:
+        if part in _EXCLUDED_DIRS:
+            return True
+
+    name = rel_path.name
+
+    if name in _EXCLUDED_NAMES:
+        return True
+
+    if name.endswith(_EXCLUDED_SUFFIXES):
+        return True
+
+    return False
+
+
+# ---------------------------------------------------------------------------
+# Backup
+# ---------------------------------------------------------------------------
+
+def _format_size(nbytes: int) -> str:
+    """Human-readable file size."""
+    for unit in ("B", "KB", "MB", "GB"):
+        if nbytes < 1024:
+            return f"{nbytes:.1f} {unit}" if unit != "B" else f"{nbytes} {unit}"
+        nbytes /= 1024
+    return f"{nbytes:.1f} TB"
+
+
+def run_backup(args) -> None:
+    """Create a zip backup of the Hermes home directory."""
+    hermes_root = get_default_hermes_root()
+
+    if not hermes_root.is_dir():
+        print(f"Error: Hermes home directory not found at {hermes_root}")
+        sys.exit(1)
+
+    # Determine output path
+    if args.output:
+        out_path = Path(args.output).expanduser().resolve()
+        # If user gave a directory, put the zip inside it
+        if out_path.is_dir():
+            stamp = datetime.now().strftime("%Y-%m-%d-%H%M%S")
+            out_path = out_path / f"hermes-backup-{stamp}.zip"
+    else:
+        stamp = datetime.now().strftime("%Y-%m-%d-%H%M%S")
+        out_path = Path.home() / f"hermes-backup-{stamp}.zip"
+
+    # Ensure the suffix is .zip
+    if out_path.suffix.lower() != ".zip":
+        out_path = out_path.with_suffix(out_path.suffix + ".zip")
+
+    # Ensure parent directory exists
+    out_path.parent.mkdir(parents=True, exist_ok=True)
+
+    # Collect files
+    print(f"Scanning {display_hermes_home()} ...")
+    files_to_add: list[tuple[Path, Path]] = []  # (absolute, relative)
+    skipped_dirs = set()
+
+    for dirpath, dirnames, filenames in os.walk(hermes_root, followlinks=False):
+        dp = Path(dirpath)
+        rel_dir = dp.relative_to(hermes_root)
+
+        # Prune excluded directories in-place so os.walk doesn't descend
+        orig_dirnames = dirnames[:]
+        dirnames[:] = [
+            d for d in dirnames
+            if d not in _EXCLUDED_DIRS
+        ]
+        for removed in set(orig_dirnames) - set(dirnames):
+            skipped_dirs.add(str(rel_dir / removed))
+
+        for fname in filenames:
+            fpath = dp / fname
+            rel = fpath.relative_to(hermes_root)
+
+            if _should_exclude(rel):
+                continue
+
+            # Skip the output zip itself if it happens to be inside hermes root
+            try:
+                if fpath.resolve() == out_path.resolve():
+                    continue
+            except (OSError, ValueError):
+                pass
+
+            files_to_add.append((fpath, rel))
+
+    if not files_to_add:
+        print("No files to back up.")
+        return
+
+    # Create the zip
+    file_count = len(files_to_add)
+    print(f"Backing up {file_count} files ...")
+
+    total_bytes = 0
+    errors = []
+    t0 = time.monotonic()
+
+    with zipfile.ZipFile(out_path, "w", zipfile.ZIP_DEFLATED, compresslevel=6) as zf:
+        for i, (abs_path, rel_path) in enumerate(files_to_add, 1):
+            try:
+                zf.write(abs_path, arcname=str(rel_path))
+                total_bytes += abs_path.stat().st_size
+            except (PermissionError, OSError) as exc:
+                errors.append(f"  {rel_path}: {exc}")
+                continue
+
+            # Progress every 500 files
+            if i % 500 == 0:
+                print(f"  {i}/{file_count} files ...")
+
+    elapsed = time.monotonic() - t0
+    zip_size = out_path.stat().st_size
+
+    # Summary
+    print()
+    print(f"Backup complete: {out_path}")
+    print(f"  Files:       {file_count}")
+    print(f"  Original:    {_format_size(total_bytes)}")
+    print(f"  Compressed:  {_format_size(zip_size)}")
+    print(f"  Time:        {elapsed:.1f}s")
+
+    if skipped_dirs:
+        print(f"\n  Excluded directories:")
+        for d in sorted(skipped_dirs):
+            print(f"    {d}/")
+
+    if errors:
+        print(f"\n  Warnings ({len(errors)} files skipped):")
+        for e in errors[:10]:
+            print(e)
+        if len(errors) > 10:
+            print(f"  ... and {len(errors) - 10} more")
+
+    print(f"\nRestore with: hermes import {out_path.name}")
+
+
+# ---------------------------------------------------------------------------
+# Import
+# ---------------------------------------------------------------------------
+
+def _validate_backup_zip(zf: zipfile.ZipFile) -> tuple[bool, str]:
+    """Check that a zip looks like a Hermes backup.
+
+    Returns (ok, reason).
+    """
+    names = zf.namelist()
+    if not names:
+        return False, "zip archive is empty"
+
+    # Look for telltale files that a hermes home would have
+    markers = {"config.yaml", ".env", "hermes_state.db", "memory_store.db"}
+    found = set()
+    for n in names:
+        # Could be at the root or one level deep (if someone zipped the directory)
+        basename = Path(n).name
+        if basename in markers:
+            found.add(basename)
+
+    if not found:
+        return False, (
+            "zip does not appear to be a Hermes backup "
+            "(no config.yaml, .env, or state databases found)"
+        )
+
+    return True, ""
+
+
+def _detect_prefix(zf: zipfile.ZipFile) -> str:
+    """Detect if the zip has a common directory prefix wrapping all entries.
+
+    Some tools zip as `.hermes/config.yaml` instead of `config.yaml`.
+    Returns the prefix to strip (empty string if none).
+    """
+    names = [n for n in zf.namelist() if not n.endswith("/")]
+    if not names:
+        return ""
+
+    # Find common prefix
+    parts_list = [Path(n).parts for n in names]
+
+    # Check if all entries share a common first directory
+    first_parts = {p[0] for p in parts_list if len(p) > 1}
+    if len(first_parts) == 1:
+        prefix = first_parts.pop()
+        # Only strip if it looks like a hermes dir name
+        if prefix in (".hermes", "hermes"):
+            return prefix + "/"
+
+    return ""
+
+
+def run_import(args) -> None:
+    """Restore a Hermes backup from a zip file."""
+    zip_path = Path(args.zipfile).expanduser().resolve()
+
+    if not zip_path.is_file():
+        print(f"Error: File not found: {zip_path}")
+        sys.exit(1)
+
+    if not zipfile.is_zipfile(zip_path):
+        print(f"Error: Not a valid zip file: {zip_path}")
+        sys.exit(1)
+
+    hermes_root = get_default_hermes_root()
+
+    with zipfile.ZipFile(zip_path, "r") as zf:
+        # Validate
+        ok, reason = _validate_backup_zip(zf)
+        if not ok:
+            print(f"Error: {reason}")
+            sys.exit(1)
+
+        prefix = _detect_prefix(zf)
+        members = [n for n in zf.namelist() if not n.endswith("/")]
+        file_count = len(members)
+
+        print(f"Backup contains {file_count} files")
+        print(f"Target: {display_hermes_home()}")
+
+        if prefix:
+            print(f"Detected archive prefix: {prefix!r} (will be stripped)")
+
+        # Check for existing installation
+        has_config = (hermes_root / "config.yaml").exists()
+        has_env = (hermes_root / ".env").exists()
+
+        if (has_config or has_env) and not args.force:
+            print()
+            print("Warning: Target directory already has Hermes configuration.")
+            print("Importing will overwrite existing files with backup contents.")
+            print()
+            try:
+                answer = input("Continue? [y/N] ").strip().lower()
+            except (EOFError, KeyboardInterrupt):
+                print("\nAborted.")
+                sys.exit(1)
+            if answer not in ("y", "yes"):
+                print("Aborted.")
+                return
+
+        # Extract
+        print(f"\nImporting {file_count} files ...")
+        hermes_root.mkdir(parents=True, exist_ok=True)
+
+        errors = []
+        restored = 0
+        t0 = time.monotonic()
+
+        for member in members:
+            # Strip prefix if detected
+            if prefix and member.startswith(prefix):
+                rel = member[len(prefix):]
+            else:
+                rel = member
+
+            if not rel:
+                continue
+
+            target = hermes_root / rel
+
+            # Security: reject absolute paths and traversals
+            try:
+                target.resolve().relative_to(hermes_root.resolve())
+            except ValueError:
+                errors.append(f"  {rel}: path traversal blocked")
+                continue
+
+            try:
+                target.parent.mkdir(parents=True, exist_ok=True)
+                with zf.open(member) as src, open(target, "wb") as dst:
+                    dst.write(src.read())
+                restored += 1
+            except (PermissionError, OSError) as exc:
+                errors.append(f"  {rel}: {exc}")
+
+            if restored % 500 == 0:
+                print(f"  {restored}/{file_count} files ...")
+
+        elapsed = time.monotonic() - t0
+
+        # Summary
+        print()
+        print(f"Import complete: {restored} files restored in {elapsed:.1f}s")
+        print(f"  Target: {display_hermes_home()}")
+
+        if errors:
+            print(f"\n  Warnings ({len(errors)} files skipped):")
+            for e in errors[:10]:
+                print(e)
+            if len(errors) > 10:
+                print(f"  ... and {len(errors) - 10} more")
+
+        # Post-import: restore profile wrapper scripts
+        profiles_dir = hermes_root / "profiles"
+        restored_profiles = []
+        if profiles_dir.is_dir():
+            try:
+                from hermes_cli.profiles import (
+                    create_wrapper_script, check_alias_collision,
+                    _is_wrapper_dir_in_path, _get_wrapper_dir,
+                )
+                for entry in sorted(profiles_dir.iterdir()):
+                    if not entry.is_dir():
+                        continue
+                    profile_name = entry.name
+                    # Only create wrappers for directories with config
+                    if not (entry / "config.yaml").exists() and not (entry / ".env").exists():
+                        continue
+                    collision = check_alias_collision(profile_name)
+                    if collision:
+                        print(f"  Skipped alias '{profile_name}': {collision}")
+                        restored_profiles.append((profile_name, False))
+                    else:
+                        wrapper = create_wrapper_script(profile_name)
+                        restored_profiles.append((profile_name, wrapper is not None))
+
+                if restored_profiles:
+                    created = [n for n, ok in restored_profiles if ok]
+                    skipped = [n for n, ok in restored_profiles if not ok]
+                    if created:
+                        print(f"\n  Profile aliases restored: {', '.join(created)}")
+                    if skipped:
+                        print(f"  Profile aliases skipped:  {', '.join(skipped)}")
+                    if not _is_wrapper_dir_in_path():
+                        print(f"\n  Note: {_get_wrapper_dir()} is not in your PATH.")
+                        print('  Add to your shell config (~/.bashrc or ~/.zshrc):')
+                        print('    export PATH="$HOME/.local/bin:$PATH"')
+            except ImportError:
+                # hermes_cli.profiles might not be available (fresh install)
+                if any(profiles_dir.iterdir()):
+                    print(f"\n  Profiles detected but aliases could not be created.")
+                    print(f"  Run: hermes profile list  (after installing hermes)")
+
+        # Guidance
+        print()
+        if not (hermes_root / "hermes-agent").is_dir():
+            print("Note: The hermes-agent codebase was not included in the backup.")
+            print("  If this is a fresh install, run: hermes update")
+
+        if restored_profiles:
+            gw_profiles = [n for n, _ in restored_profiles]
+            print("\nTo re-enable gateway services for profiles:")
+            for pname in gw_profiles:
+                print(f"  hermes -p {pname} gateway install")
+
+        print("Done. Your Hermes configuration has been restored.")

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/claw.py

@@ -1,8 +1,9 @@
 """hermes claw — OpenClaw migration commands.
 
 Usage:
-    hermes claw migrate              # Interactive migration from ~/.openclaw
-    hermes claw migrate --dry-run    # Preview what would be migrated
+    hermes claw migrate              # Preview then migrate (always shows preview first)
+    hermes claw migrate --dry-run    # Preview only, no changes
+    hermes claw migrate --yes        # Skip confirmation prompt
     hermes claw migrate --preset full --overwrite  # Full migration, overwrite conflicts
     hermes claw cleanup              # Archive leftover OpenClaw directories
     hermes claw cleanup --dry-run    # Preview what would be archived
@@ -49,10 +50,45 @@ _OPENCLAW_SCRIPT_INSTALLED = (
 )
 
 # Known OpenClaw directory names (current + legacy)
-_OPENCLAW_DIR_NAMES = (".openclaw", ".clawdbot", ".moldbot")
+_OPENCLAW_DIR_NAMES = (".openclaw", ".clawdbot", ".moltbot")
 
-# State files commonly found in OpenClaw workspace directories that cause
-# confusion after migration (the agent discovers them and writes to them)
+def _warn_if_gateway_running(auto_yes: bool) -> None:
+    """Check if a Hermes gateway is running with connected platforms.
+
+    Migrating bot tokens while the gateway is polling will cause conflicts
+    (e.g. Telegram 409 "terminated by other getUpdates request"). Warn the
+    user and let them decide whether to continue.
+    """
+    from gateway.status import get_running_pid, read_runtime_status
+
+    if not get_running_pid():
+        return
+
+    data = read_runtime_status() or {}
+    platforms = data.get("platforms") or {}
+    connected = [name for name, info in platforms.items()
+                 if isinstance(info, dict) and info.get("state") == "connected"]
+    if not connected:
+        return
+
+    print()
+    print_error(
+        "Hermes gateway is running with active connections: "
+        + ", ".join(connected)
+    )
+    print_info(
+        "Migrating bot tokens while the gateway is active will cause "
+        "conflicts (Telegram, Discord, and Slack only allow one active "
+        "session per token)."
+    )
+    print_info("Recommendation: stop the gateway first with 'hermes stop'.")
+    print()
+    if not auto_yes and not prompt_yes_no("Continue anyway?", default=False):
+        print_info("Migration cancelled. Stop the gateway and try again.")
+        sys.exit(0)
+
+# State files commonly found in OpenClaw workspace directories — listed
+# during cleanup to help the user decide whether to archive
 _WORKSPACE_STATE_GLOBS = (
     "*/todo.json",
     "*/sessions/*",
@@ -97,7 +133,7 @@ def _find_openclaw_dirs() -> list[Path]:
 
 
 def _scan_workspace_state(source_dir: Path) -> list[tuple[Path, str]]:
-    """Scan an OpenClaw directory for workspace state files that cause confusion.
+    """Scan an OpenClaw directory for workspace state files.
 
     Returns a list of (path, description) tuples.
     """
@@ -180,7 +216,7 @@ def _cmd_migrate(args):
         source_dir = Path.home() / ".openclaw"
         if not source_dir.is_dir():
             # Try legacy directory names
-            for legacy in (".clawdbot", ".moldbot"):
+            for legacy in (".clawdbot", ".moltbot"):
                 candidate = Path.home() / legacy
                 if candidate.is_dir():
                     source_dir = candidate
@@ -237,12 +273,12 @@ def _cmd_migrate(args):
 
     # Show what we're doing
     hermes_home = get_hermes_home()
+    auto_yes = getattr(args, "yes", False)
     print()
     print_header("Migration Settings")
     print_info(f"Source:      {source_dir}")
     print_info(f"Target:      {hermes_home}")
     print_info(f"Preset:      {preset}")
-    print_info(f"Mode:        {'dry run (preview only)' if dry_run else 'execute'}")
     print_info(f"Overwrite:   {'yes' if overwrite else 'no (skip conflicts)'}")
     print_info(f"Secrets:     {'yes (allowlisted only)' if migrate_secrets else 'no'}")
     if skill_conflict != "skip":
@@ -251,31 +287,85 @@ def _cmd_migrate(args):
         print_info(f"Workspace:   {workspace_target}")
     print()
 
-    # For execute mode (non-dry-run), confirm unless --yes was passed
-    if not dry_run and not getattr(args, "yes", False):
-        if not prompt_yes_no("Proceed with migration?", default=True):
-            print_info("Migration cancelled.")
-            return
+    # Check if a gateway is running with connected platforms — migrating tokens
+    # while the gateway is active will cause conflicts (e.g. Telegram 409).
+    _warn_if_gateway_running(auto_yes)
 
     # Ensure config.yaml exists before migration tries to read it
     config_path = get_config_path()
     if not config_path.exists():
         save_config(load_config())
 
-    # Load and run the migration
+    # Load the migration module
     try:
         mod = _load_migration_module(script_path)
         if mod is None:
             print_error("Could not load migration script.")
             return
+    except Exception as e:
+        print()
+        print_error(f"Could not load migration script: {e}")
+        logger.debug("OpenClaw migration error", exc_info=True)
+        return
 
-        selected = mod.resolve_selected_options(None, None, preset=preset)
-        ws_target = Path(workspace_target).resolve() if workspace_target else None
+    selected = mod.resolve_selected_options(None, None, preset=preset)
+    ws_target = Path(workspace_target).resolve() if workspace_target else None
 
+    # ── Phase 1: Always preview first ──────────────────────────
+    try:
+        preview = mod.Migrator(
+            source_root=source_dir.resolve(),
+            target_root=hermes_home.resolve(),
+            execute=False,
+            workspace_target=ws_target,
+            overwrite=overwrite,
+            migrate_secrets=migrate_secrets,
+            output_dir=None,
+            selected_options=selected,
+            preset_name=preset,
+            skill_conflict_mode=skill_conflict,
+        )
+        preview_report = preview.migrate()
+    except Exception as e:
+        print()
+        print_error(f"Migration preview failed: {e}")
+        logger.debug("OpenClaw migration preview error", exc_info=True)
+        return
+
+    preview_summary = preview_report.get("summary", {})
+    preview_count = preview_summary.get("migrated", 0)
+
+    if preview_count == 0:
+        print()
+        print_info("Nothing to migrate from OpenClaw.")
+        _print_migration_report(preview_report, dry_run=True)
+        return
+
+    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_migration_report(preview_report, dry_run=True)
+
+    # If --dry-run, stop here
+    if dry_run:
+        return
+
+    # ── Phase 2: Confirm and execute ───────────────────────────
+    print()
+    if not auto_yes:
+        if not sys.stdin.isatty():
+            print_info("Non-interactive session — preview only.")
+            print_info("To execute, re-run with: hermes claw migrate --yes")
+            return
+        if not prompt_yes_no("Proceed with migration?", default=True):
+            print_info("Migration cancelled.")
+            return
+
+    try:
         migrator = mod.Migrator(
             source_root=source_dir.resolve(),
             target_root=hermes_home.resolve(),
-            execute=not dry_run,
+            execute=True,
             workspace_target=ws_target,
             overwrite=overwrite,
             migrate_secrets=migrate_secrets,
@@ -292,62 +382,18 @@ def _cmd_migrate(args):
         return
 
     # Print results
-    _print_migration_report(report, dry_run)
+    _print_migration_report(report, dry_run=False)
 
-    # After successful non-dry-run migration, offer to archive the source directory
-    if not dry_run and report.get("summary", {}).get("migrated", 0) > 0:
-        _offer_source_archival(source_dir, getattr(args, "yes", False))
-
-
-def _offer_source_archival(source_dir: Path, auto_yes: bool = False):
-    """After migration, offer to rename the source directory to prevent state fragmentation.
-
-    OpenClaw workspace directories contain state files (todo.json, sessions, etc.)
-    that the agent may discover and write to, causing confusion. Renaming the
-    directory prevents this.
-    """
-    if not source_dir.is_dir():
-        return
-
-    # Scan for state files that could cause problems
-    state_files = _scan_workspace_state(source_dir)
-
-    print()
-    print_header("Post-Migration Cleanup")
-    print_info("The OpenClaw directory still exists and contains workspace state files")
-    print_info("that can confuse the agent (todo lists, sessions, logs).")
-    if state_files:
-        print()
-        print(color("  Found state files:", Colors.YELLOW))
-        # Show up to 10 most relevant findings
-        for path, desc in state_files[:10]:
-            print(f"      {desc}")
-        if len(state_files) > 10:
-            print(f"      ... and {len(state_files) - 10} more")
-    print()
-    print_info(f"Recommend: rename {source_dir.name}/ to {source_dir.name}.pre-migration/")
-    print_info("This prevents the agent from discovering old workspace directories.")
-    print_info("You can always rename it back if needed.")
-    print()
-
-    if auto_yes or prompt_yes_no(f"Archive {source_dir} now?", default=True):
-        try:
-            archive_path = _archive_directory(source_dir)
-            print_success(f"Archived: {source_dir} → {archive_path}")
-            print_info("The original directory has been renamed, not deleted.")
-            print_info(f"To undo: mv {archive_path} {source_dir}")
-        except OSError as e:
-            print_error(f"Could not archive: {e}")
-            print_info(f"You can do it manually: mv {source_dir} {source_dir}.pre-migration")
-    else:
-        print_info("Skipped. You can archive later with: hermes claw cleanup")
+    # Source directory is left untouched — archiving is not the migration
+    # tool's responsibility.  Users who want to clean up can run
+    # 'hermes claw cleanup' separately.
 
 
 def _cmd_cleanup(args):
     """Archive leftover OpenClaw directories after migration.
 
     Scans for OpenClaw directories that still exist after migration and offers
-    to rename them to .pre-migration to prevent state fragmentation.
+    to rename them to .pre-migration to free disk space.
     """
     dry_run = getattr(args, "dry_run", False)
     auto_yes = getattr(args, "yes", False)
@@ -422,7 +468,7 @@ def _cmd_cleanup(args):
 
         if state_files:
             print()
-            print(color(f"  {len(state_files)} state file(s) that could cause confusion:", Colors.YELLOW))
+            print(color(f"  {len(state_files)} state file(s) found:", Colors.YELLOW))
             for path, desc in state_files[:8]:
                 print(f"      {desc}")
             if len(state_files) > 8:
@@ -433,6 +479,9 @@ def _cmd_cleanup(args):
         if dry_run:
             archive_path = _archive_directory(source_dir, dry_run=True)
             print_info(f"Would archive: {source_dir} → {archive_path}")
+        elif not auto_yes and not sys.stdin.isatty():
+            print_info(f"Non-interactive session — would archive: {source_dir}")
+            print_info("To execute, re-run with: hermes claw cleanup --yes")
         else:
             if auto_yes or prompt_yes_no(f"Archive {source_dir}?", default=True):
                 try:

hermes_cli/cli_output.py

@@ -0,0 +1,79 @@
+"""Shared CLI output helpers for Hermes CLI modules.
+
+Extracts the identical ``print_info/success/warning/error`` and ``prompt()``
+functions previously duplicated across setup.py, tools_config.py,
+mcp_config.py, and memory_setup.py.
+"""
+
+import getpass
+import sys
+
+from hermes_cli.colors import Colors, color
+
+
+# ─── Print Helpers ────────────────────────────────────────────────────────────
+
+
+def print_info(text: str) -> None:
+    """Print a dim informational message."""
+    print(color(f"  {text}", Colors.DIM))
+
+
+def print_success(text: str) -> None:
+    """Print a green success message with ✓ prefix."""
+    print(color(f"✓ {text}", Colors.GREEN))
+
+
+def print_warning(text: str) -> None:
+    """Print a yellow warning message with ⚠ prefix."""
+    print(color(f"⚠ {text}", Colors.YELLOW))
+
+
+def print_error(text: str) -> None:
+    """Print a red error message with ✗ prefix."""
+    print(color(f"✗ {text}", Colors.RED))
+
+
+def print_header(text: str) -> None:
+    """Print a bold yellow header."""
+    print(color(f"\n  {text}", Colors.YELLOW))
+
+
+# ─── Input Prompts ────────────────────────────────────────────────────────────
+
+
+def prompt(
+    question: str,
+    default: str | None = None,
+    password: bool = False,
+) -> str:
+    """Prompt the user for input with optional default and password masking.
+
+    Replaces the four independent ``_prompt()`` / ``prompt()`` implementations
+    in setup.py, tools_config.py, mcp_config.py, and memory_setup.py.
+
+    Returns the user's input (stripped), or *default* if the user presses Enter.
+    Returns empty string on Ctrl-C or EOF.
+    """
+    suffix = f" [{default}]" if default else ""
+    display = color(f"  {question}{suffix}: ", Colors.YELLOW)
+
+    try:
+        if password:
+            value = getpass.getpass(display)
+        else:
+            value = input(display)
+        value = value.strip()
+        return value if value else (default or "")
+    except (KeyboardInterrupt, EOFError):
+        print()
+        return ""
+
+
+def prompt_yes_no(question: str, default: bool = True) -> bool:
+    """Prompt for a yes/no answer. Returns bool."""
+    hint = "Y/n" if default else "y/N"
+    answer = prompt(f"{question} ({hint})")
+    if not answer:
+        return default
+    return answer.lower().startswith("y")

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]
 
 
 # ---------------------------------------------------------------------------
@@ -59,7 +69,8 @@ COMMAND_REGISTRY: list[CommandDef] = [
                args_hint="[name]"),
     CommandDef("branch", "Branch the current session (explore a different path)", "Session",
                aliases=("fork",), args_hint="[name]"),
-    CommandDef("compress", "Manually compress conversation context", "Session"),
+    CommandDef("compress", "Manually compress conversation context", "Session",
+               args_hint="[focus topic]"),
     CommandDef("rollback", "List or restore filesystem checkpoints", "Session",
                args_hint="[number]"),
     CommandDef("stop", "Kill all running background processes", "Session"),
@@ -73,8 +84,7 @@ 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 +97,7 @@ 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 +109,10 @@ 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 +141,17 @@ 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 +186,6 @@ 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 +648,18 @@ 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 +937,7 @@ 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 +950,8 @@ 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 +1010,8 @@ 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 +1022,8 @@ 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

@@ -32,13 +32,18 @@ _ENV_VAR_NAME_RE = re.compile(r"^[A-Za-z_][A-Za-z0-9_]*$")
 _EXTRA_ENV_KEYS = frozenset({
     "OPENAI_API_KEY", "OPENAI_BASE_URL",
     "ANTHROPIC_API_KEY", "ANTHROPIC_TOKEN",
-    "AUXILIARY_VISION_MODEL",
     "DISCORD_HOME_CHANNEL", "TELEGRAM_HOME_CHANNEL",
     "SIGNAL_ACCOUNT", "SIGNAL_HTTP_URL",
     "SIGNAL_ALLOWED_USERS", "SIGNAL_GROUP_ALLOWED_USERS",
     "DINGTALK_CLIENT_ID", "DINGTALK_CLIENT_SECRET",
     "FEISHU_APP_ID", "FEISHU_APP_SECRET", "FEISHU_ENCRYPT_KEY", "FEISHU_VERIFICATION_TOKEN",
     "WECOM_BOT_ID", "WECOM_SECRET",
+    "WECOM_CALLBACK_CORP_ID", "WECOM_CALLBACK_CORP_SECRET", "WECOM_CALLBACK_AGENT_ID",
+    "WECOM_CALLBACK_TOKEN", "WECOM_CALLBACK_ENCODING_AES_KEY",
+    "WECOM_CALLBACK_HOST", "WECOM_CALLBACK_PORT",
+    "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",
@@ -138,6 +143,73 @@ def managed_error(action: str = "modify configuration"):
     print(format_managed_message(action), file=sys.stderr)
 
 
+# =============================================================================
+# Container-aware CLI (NixOS container mode)
+# =============================================================================
+
+def _is_inside_container() -> bool:
+    """Detect if we're already running inside a Docker/Podman container."""
+    # Standard Docker/Podman indicators
+    if os.path.exists("/.dockerenv"):
+        return True
+    # Podman uses /run/.containerenv
+    if os.path.exists("/run/.containerenv"):
+        return True
+    # Check cgroup for container runtime evidence (works for both Docker & Podman)
+    try:
+        with open("/proc/1/cgroup", "r") as f:
+            cgroup = f.read()
+            if "docker" in cgroup or "podman" in cgroup or "/lxc/" in cgroup:
+                return True
+    except OSError:
+        pass
+    return False
+
+
+def get_container_exec_info() -> Optional[dict]:
+    """Read container mode metadata from HERMES_HOME/.container-mode.
+
+    Returns a dict with keys: backend, container_name, exec_user, hermes_bin
+    or None if container mode is not active, we're already inside the
+    container, or HERMES_DEV=1 is set.
+
+    The .container-mode file is written by the NixOS activation script when
+    container.enable = true. It tells the host CLI to exec into the container
+    instead of running locally.
+    """
+    if os.environ.get("HERMES_DEV") == "1":
+        return None
+
+    if _is_inside_container():
+        return None
+
+    container_mode_file = get_hermes_home() / ".container-mode"
+
+    try:
+        info = {}
+        with open(container_mode_file, "r") as f:
+            for line in f:
+                line = line.strip()
+                if "=" in line and not line.startswith("#"):
+                    key, _, value = line.partition("=")
+                    info[key.strip()] = value.strip()
+    except FileNotFoundError:
+        return None
+    # All other exceptions (PermissionError, malformed data, etc.) propagate
+
+    backend = info.get("backend", "docker")
+    container_name = info.get("container_name", "hermes-agent")
+    exec_user = info.get("exec_user", "hermes")
+    hermes_bin = info.get("hermes_bin", "/data/current-package/bin/hermes")
+
+    return {
+        "backend": backend,
+        "container_name": container_name,
+        "exec_user": exec_user,
+        "hermes_bin": hermes_bin,
+    }
+
+
 # =============================================================================
 # Config paths
 # =============================================================================
@@ -158,16 +230,27 @@ 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
 
@@ -197,14 +280,44 @@ 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)
 
 
@@ -225,6 +338,12 @@ 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
@@ -331,7 +450,7 @@ DEFAULT_CONFIG = {
             "model": "",           # e.g. "google/gemini-2.5-flash", "gpt-4o"
             "base_url": "",        # direct OpenAI-compatible endpoint (takes precedence over provider)
             "api_key": "",         # API key for base_url (falls back to OPENAI_API_KEY)
-            "timeout": 30,         # seconds — LLM API call timeout; increase for slow local vision models
+            "timeout": 120,        # seconds — LLM API call timeout; vision payloads need generous timeout
             "download_timeout": 30,  # seconds — image HTTP download timeout; increase for slow connections
         },
         "web_extract": {
@@ -396,9 +515,11 @@ DEFAULT_CONFIG = {
         "inline_diffs": True,     # Show inline diff previews for write actions (write_file, patch, skill_manage)
         "show_cost": False,       # Show $ cost in the status bar (off by default)
         "skin": "default",
+        "interim_assistant_messages": True,  # Gateway: show natural mid-turn assistant status messages
         "tool_progress_command": False,  # Enable /verbose command in messaging gateway
-        "tool_progress_overrides": {},  # Per-platform overrides: {"signal": "off", "telegram": "all"}
+        "tool_progress_overrides": {},  # DEPRECATED — use display.platforms instead
         "tool_preview_length": 0,  # Max chars for tool call previews (0 = no limit, show full paths/commands)
+        "platforms": {},  # Per-platform display overrides: {"telegram": {"tool_progress": "all"}, "slack": {"tool_progress": "off"}}
     },
 
     # Privacy settings
@@ -408,7 +529,7 @@ 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
@@ -422,6 +543,10 @@ 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)
@@ -459,6 +584,16 @@ 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,
@@ -483,6 +618,8 @@ 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
@@ -510,6 +647,7 @@ 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
     },
@@ -568,8 +706,16 @@ DEFAULT_CONFIG = {
         "backup_count": 3,     # Number of rotated backup files to keep
     },
 
+    # Network settings — workarounds for connectivity issues.
+    "network": {
+        # Force IPv4 connections.  On servers with broken or unreachable IPv6,
+        # Python tries AAAA records first and hangs for the full TCP timeout
+        # before falling back to IPv4.  Set to true to skip IPv6 entirely.
+        "force_ipv4": False,
+    },
+
     # Config schema version - bump this when adding new required fields
-    "_config_version": 12,
+    "_config_version": 16,
 }
 
 # =============================================================================
@@ -801,6 +947,21 @@ OPTIONAL_ENV_VARS = {
         "category": "provider",
         "advanced": True,
     },
+    "XIAOMI_API_KEY": {
+        "description": "Xiaomi MiMo API key for MiMo models (mimo-v2-pro, mimo-v2-omni, mimo-v2-flash)",
+        "prompt": "Xiaomi MiMo API Key",
+        "url": "https://platform.xiaomimimo.com",
+        "password": True,
+        "category": "provider",
+    },
+    "XIAOMI_BASE_URL": {
+        "description": "Xiaomi MiMo base URL override (default: https://api.xiaomimimo.com/v1)",
+        "prompt": "Xiaomi base URL (leave empty for default)",
+        "url": None,
+        "password": False,
+        "category": "provider",
+        "advanced": True,
+    },
 
     # ── Tool API keys ──
     "EXA_API_KEY": {
@@ -953,6 +1114,13 @@ 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",
@@ -1125,6 +1293,27 @@ 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)",
@@ -1142,8 +1331,8 @@ 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",
@@ -1158,13 +1347,21 @@ 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)",
@@ -1196,7 +1393,7 @@ 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,
@@ -1375,12 +1572,12 @@ _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
 _VALID_CUSTOM_PROVIDER_FIELDS = {
-    "name", "base_url", "api_key", "api_mode", "models",
+    "name", "base_url", "api_key", "api_mode", "model", "models",
     "context_length", "rate_limit_delay",
 }
 
@@ -1680,6 +1877,109 @@ 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")
+
+    # ── Version 14 → 15: add explicit gateway interim-message gate ──
+    if current_ver < 15:
+        config = read_raw_config()
+        display = config.get("display", {})
+        if not isinstance(display, dict):
+            display = {}
+        if "interim_assistant_messages" not in display:
+            display["interim_assistant_messages"] = True
+            config["display"] = display
+            results["config_added"].append("display.interim_assistant_messages=true (default)")
+            save_config(config)
+            if not quiet:
+                print("  ✓ Added display.interim_assistant_messages=true")
+
+    # ── Version 15 → 16: migrate tool_progress_overrides into display.platforms ──
+    if current_ver < 16:
+        config = read_raw_config()
+        display = config.get("display", {})
+        if not isinstance(display, dict):
+            display = {}
+        old_overrides = display.get("tool_progress_overrides")
+        if isinstance(old_overrides, dict) and old_overrides:
+            platforms = display.get("platforms", {})
+            if not isinstance(platforms, dict):
+                platforms = {}
+            for plat, mode in old_overrides.items():
+                if plat not in platforms:
+                    platforms[plat] = {}
+                if "tool_progress" not in platforms[plat]:
+                    platforms[plat]["tool_progress"] = mode
+            display["platforms"] = platforms
+            config["display"] = display
+            save_config(config)
+            if not quiet:
+                migrated = ", ".join(f"{p}={m}" for p, m in old_overrides.items())
+                print(f"  ✓ Migrated tool_progress_overrides → display.platforms: {migrated}")
+            results["config_added"].append("display.platforms (migrated from tool_progress_overrides)")
+
     if current_ver < latest_ver and not quiet:
         print(f"Config version: {current_ver} → {latest_ver}")
     
@@ -2400,7 +2700,8 @@ def show_config():
     for env_key, name in keys:
         value = get_env_value(env_key)
         print(f"  {name:<14} {redact_key(value)}")
-    anthropic_value = get_env_value("ANTHROPIC_TOKEN") or get_env_value("ANTHROPIC_API_KEY")
+    from hermes_cli.auth import get_anthropic_key
+    anthropic_value = get_anthropic_key()
     print(f"  {'Anthropic':<14} {redact_key(anthropic_value)}")
     
     # Model settings
@@ -2616,8 +2917,8 @@ def set_config_value(key: str, value: str):
     
     # Write only user config back (not the full merged defaults)
     ensure_hermes_home()
-    with open(config_path, 'w', encoding="utf-8") as f:
-        yaml.dump(user_config, f, default_flow_style=False, sort_keys=False)
+    from utils import atomic_yaml_write
+    atomic_yaml_write(config_path, user_config, sort_keys=False)
     
     # Keep .env in sync for keys that terminal_tool reads directly from env vars.
     # config.yaml is authoritative, but terminal_tool only reads TERMINAL_ENV etc.
@@ -2633,6 +2934,10 @@ 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 +153,263 @@ 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 curses_single_select(
+    title: str,
+    items: List[str],
+    default_index: int = 0,
+    *,
+    cancel_label: str = "Cancel",
+) -> int | None:
+    """Curses single-select menu. Returns selected index or None on cancel.
+
+    Works inside prompt_toolkit because curses.wrapper() restores the terminal
+    safely, unlike simple_term_menu which conflicts with /dev/tty.
+    """
+    if not sys.stdin.isatty():
+        return None
+
+    try:
+        import curses
+        result_holder: list = [None]
+
+        all_items = list(items) + [cancel_label]
+        cancel_idx = len(items)
+
+        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 = min(default_index, len(all_items) - 1)
+            scroll_offset = 0
+
+            while True:
+                stdscr.clear()
+                max_y, max_x = stdscr.getmaxyx()
+
+                try:
+                    hattr = curses.A_BOLD
+                    if curses.has_colors():
+                        hattr |= curses.color_pair(2)
+                    stdscr.addnstr(0, 0, title, max_x - 1, hattr)
+                    stdscr.addnstr(
+                        1, 0,
+                        "  ↑↓ navigate  ENTER confirm  ESC/q cancel",
+                        max_x - 1, curses.A_DIM,
+                    )
+                except curses.error:
+                    pass
+
+                visible_rows = max_y - 3
+                if cursor < scroll_offset:
+                    scroll_offset = cursor
+                elif cursor >= scroll_offset + visible_rows:
+                    scroll_offset = cursor - visible_rows + 1
+
+                for draw_i, i in enumerate(
+                    range(scroll_offset, min(len(all_items), scroll_offset + visible_rows))
+                ):
+                    y = draw_i + 3
+                    if y >= max_y - 1:
+                        break
+                    arrow = "→" if i == cursor else " "
+                    line = f" {arrow} {all_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(all_items)
+                elif key in (curses.KEY_DOWN, ord("j")):
+                    cursor = (cursor + 1) % len(all_items)
+                elif key in (curses.KEY_ENTER, 10, 13):
+                    result_holder[0] = cursor
+                    return
+                elif key in (27, ord("q")):
+                    result_holder[0] = None
+                    return
+
+        curses.wrapper(_draw)
+        flush_stdin()
+        if result_holder[0] is not None and result_holder[0] >= cancel_idx:
+            return None
+        return result_holder[0]
+
+    except Exception:
+        all_items = list(items) + [cancel_label]
+        cancel_idx = len(items)
+        return _numbered_single_fallback(title, all_items, cancel_idx)
+
+
+def _numbered_single_fallback(
+    title: str,
+    items: List[str],
+    cancel_idx: int,
+) -> int | None:
+    """Text-based numbered fallback for single-select."""
+    print(f"\n  {title}\n")
+    for i, label in enumerate(items, 1):
+        print(f"  {i}. {label}")
+    print()
+    try:
+        val = input(f"  Choice [1-{len(items)}]: ").strip()
+        if not val:
+            return None
+        idx = int(val) - 1
+        if 0 <= idx < len(items) and idx < cancel_idx:
+            return idx
+        if idx == cancel_idx:
+            return None
+    except (ValueError, KeyboardInterrupt, EOFError):
+        pass
+    return None
+
+
 def _numbered_fallback(
     title: str,
     items: List[str],

hermes_cli/doctor.py

@@ -51,9 +51,36 @@ _PROVIDER_ENV_HINTS = (
     "AI_GATEWAY_API_KEY",
     "OPENCODE_ZEN_API_KEY",
     "OPENCODE_GO_API_KEY",
+    "XIAOMI_API_KEY",
 )
 
 
+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 +227,7 @@ 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:
@@ -309,8 +336,8 @@ def run_doctor(args):
                             model_section[k] = raw_config.pop(k)
                         else:
                             raw_config.pop(k)
-                    with open(config_path, "w") as f:
-                        yaml.dump(raw_config, f, default_flow_style=False)
+                    from utils import atomic_yaml_write
+                    atomic_yaml_write(config_path, raw_config)
                     check_ok("Migrated stale root-level keys into model section")
                     fixed_count += 1
                 else:
@@ -503,7 +530,7 @@ 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 +553,10 @@ 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 +604,23 @@ 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"):
@@ -642,7 +686,8 @@ def run_doctor(args):
     else:
         check_warn("OpenRouter API", "(not configured)")
     
-    anthropic_key = os.getenv("ANTHROPIC_TOKEN") or os.getenv("ANTHROPIC_API_KEY")
+    from hermes_cli.auth import get_anthropic_key
+    anthropic_key = get_anthropic_key()
     if anthropic_key:
         print("  Checking Anthropic API...", end="", flush=True)
         try:
@@ -679,9 +724,9 @@ 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 +751,15 @@ 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 +789,9 @@ 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 +1,334 @@
+"""
+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",
+        "wecom_callback": "WECOM_CALLBACK_CORP_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/logs.py

@@ -1,16 +1,18 @@
 """``hermes logs`` — view and filter Hermes log files.
 
-Supports tailing, following, session filtering, level filtering, and
-relative time ranges.  All log files live under ``~/.hermes/logs/``.
+Supports tailing, following, session filtering, level filtering,
+component filtering, and relative time ranges.  All log files live
+under ``~/.hermes/logs/``.
 
 Usage examples::
 
     hermes logs                    # last 50 lines of agent.log
     hermes logs -f                 # follow agent.log in real time
     hermes logs errors             # last 50 lines of errors.log
-    hermes logs gateway -n 100     # last 100 lines of gateway.log
+    hermes logs gateway -n 100    # last 100 lines of gateway.log
     hermes logs --level WARNING    # only WARNING+ lines
     hermes logs --session abc123   # filter by session ID substring
+    hermes logs --component tools  # only tool-related lines
     hermes logs --since 1h         # lines from the last hour
     hermes logs --since 30m -f     # follow, starting 30 min ago
 """
@@ -20,7 +22,7 @@ import sys
 import time
 from datetime import datetime, timedelta
 from pathlib import Path
-from typing import Optional
+from typing import Optional, Sequence
 
 from hermes_constants import get_hermes_home, display_hermes_home
 
@@ -38,6 +40,15 @@ _TS_RE = re.compile(r"^(\d{4}-\d{2}-\d{2}\s+\d{2}:\d{2}:\d{2})")
 # Level extraction — matches " INFO ", " WARNING ", " ERROR ", " DEBUG ", " CRITICAL "
 _LEVEL_RE = re.compile(r"\s(DEBUG|INFO|WARNING|ERROR|CRITICAL)\s")
 
+# Logger name extraction — after level and optional session tag, the next
+# non-space token before ":" is the logger name.
+# Matches: "INFO gateway.run:" or "INFO [sess_abc] tools.terminal_tool:"
+_LOGGER_NAME_RE = re.compile(
+    r"\s(?:DEBUG|INFO|WARNING|ERROR|CRITICAL)"  # level
+    r"(?:\s+\[.*?\])?"                           # optional session tag
+    r"\s+(\S+):"                                 # logger name
+)
+
 # Level ordering for >= filtering
 _LEVEL_ORDER = {"DEBUG": 0, "INFO": 1, "WARNING": 2, "ERROR": 3, "CRITICAL": 4}
 
@@ -79,12 +90,27 @@ def _extract_level(line: str) -> Optional[str]:
     return m.group(1) if m else None
 
 
+def _extract_logger_name(line: str) -> Optional[str]:
+    """Extract the logger name from a log line."""
+    m = _LOGGER_NAME_RE.search(line)
+    return m.group(1) if m else None
+
+
+def _line_matches_component(line: str, prefixes: Sequence[str]) -> bool:
+    """Check if a log line's logger name starts with any of *prefixes*."""
+    name = _extract_logger_name(line)
+    if name is None:
+        return False
+    return name.startswith(tuple(prefixes))
+
+
 def _matches_filters(
     line: str,
     *,
     min_level: Optional[str] = None,
     session_filter: Optional[str] = None,
     since: Optional[datetime] = None,
+    component_prefixes: Optional[Sequence[str]] = None,
 ) -> bool:
     """Check if a log line passes all active filters."""
     if since is not None:
@@ -102,6 +128,10 @@ def _matches_filters(
         if session_filter not in line:
             return False
 
+    if component_prefixes is not None:
+        if not _line_matches_component(line, component_prefixes):
+            return False
+
     return True
 
 
@@ -113,6 +143,7 @@ def tail_log(
     level: Optional[str] = None,
     session: Optional[str] = None,
     since: Optional[str] = None,
+    component: Optional[str] = None,
 ) -> None:
     """Read and display log lines, optionally following in real time.
 
@@ -130,6 +161,8 @@ def tail_log(
         Session ID substring to filter on.
     since
         Relative time string (e.g. ``"1h"``, ``"30m"``).
+    component
+        Component name to filter by (e.g. ``"gateway"``, ``"tools"``).
     """
     filename = LOG_FILES.get(log_name)
     if filename is None:
@@ -155,13 +188,29 @@ def tail_log(
         print(f"Invalid --level: {level!r}. Use DEBUG, INFO, WARNING, ERROR, or CRITICAL.")
         sys.exit(1)
 
-    has_filters = min_level is not None or session is not None or since_dt is not None
+    # Resolve component to logger name prefixes
+    component_prefixes = None
+    if component:
+        from hermes_logging import COMPONENT_PREFIXES
+        component_lower = component.lower()
+        if component_lower not in COMPONENT_PREFIXES:
+            available = ", ".join(sorted(COMPONENT_PREFIXES))
+            print(f"Unknown component: {component!r}. Available: {available}")
+            sys.exit(1)
+        component_prefixes = COMPONENT_PREFIXES[component_lower]
+
+    has_filters = (
+        min_level is not None
+        or session is not None
+        or since_dt is not None
+        or component_prefixes is not None
+    )
 
     # Read and display the tail
     try:
         lines = _read_tail(log_path, num_lines, has_filters=has_filters,
                            min_level=min_level, session_filter=session,
-                           since=since_dt)
+                           since=since_dt, component_prefixes=component_prefixes)
     except PermissionError:
         print(f"Permission denied: {log_path}")
         sys.exit(1)
@@ -172,6 +221,8 @@ def tail_log(
         filter_parts.append(f"level>={min_level}")
     if session:
         filter_parts.append(f"session={session}")
+    if component:
+        filter_parts.append(f"component={component}")
     if since:
         filter_parts.append(f"since={since}")
     filter_desc = f" [{', '.join(filter_parts)}]" if filter_parts else ""
@@ -190,7 +241,7 @@ def tail_log(
     # Follow mode — poll for new content
     try:
         _follow_log(log_path, min_level=min_level, session_filter=session,
-                     since=since_dt)
+                     since=since_dt, component_prefixes=component_prefixes)
     except KeyboardInterrupt:
         print("\n--- stopped ---")
 
@@ -203,6 +254,7 @@ def _read_tail(
     min_level: Optional[str] = None,
     session_filter: Optional[str] = None,
     since: Optional[datetime] = None,
+    component_prefixes: Optional[Sequence[str]] = None,
 ) -> list:
     """Read the last *num_lines* matching lines from a log file.
 
@@ -215,7 +267,8 @@ def _read_tail(
         filtered = [
             l for l in raw_lines
             if _matches_filters(l, min_level=min_level,
-                                session_filter=session_filter, since=since)
+                                session_filter=session_filter, since=since,
+                                component_prefixes=component_prefixes)
         ]
         return filtered[-num_lines:]
     else:
@@ -284,6 +337,7 @@ def _follow_log(
     min_level: Optional[str] = None,
     session_filter: Optional[str] = None,
     since: Optional[datetime] = None,
+    component_prefixes: Optional[Sequence[str]] = None,
 ) -> None:
     """Poll a log file for new content and print matching lines."""
     with open(path, "r", encoding="utf-8", errors="replace") as f:
@@ -293,7 +347,8 @@ def _follow_log(
             line = f.readline()
             if line:
                 if _matches_filters(line, min_level=min_level,
-                                    session_filter=session_filter, since=since):
+                                    session_filter=session_filter, since=since,
+                                    component_prefixes=component_prefixes):
                     print(line, end="")
                     sys.stdout.flush()
             else:

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":
@@ -150,6 +151,18 @@ try:
 except Exception:
     pass  # best-effort — don't crash the CLI if logging setup fails
 
+# Apply IPv4 preference early, before any HTTP clients are created.
+try:
+    from hermes_cli.config import load_config as _load_config_early
+    from hermes_constants import apply_ipv4_preference as _apply_ipv4
+    _early_cfg = _load_config_early()
+    _net = _early_cfg.get("network", {})
+    if isinstance(_net, dict) and _net.get("force_ipv4"):
+        _apply_ipv4(force=True)
+    del _early_cfg, _net
+except Exception:
+    pass  # best-effort — don't crash if config isn't available yet
+
 import logging
 import time as _time
 from datetime import datetime
@@ -527,6 +540,113 @@ def _resolve_last_cli_session() -> Optional[str]:
     return None
 
 
+def _probe_container(cmd: list, backend: str, via_sudo: bool = False):
+    """Run a container inspect probe, returning the CompletedProcess.
+
+    Catches TimeoutExpired specifically for a human-readable message;
+    all other exceptions propagate naturally.
+    """
+    try:
+        return subprocess.run(cmd, capture_output=True, text=True, timeout=15)
+    except subprocess.TimeoutExpired:
+        label = f"sudo {backend}" if via_sudo else backend
+        print(
+            f"Error: timed out waiting for {label} to respond.\n"
+            f"The {backend} daemon may be unresponsive or starting up.",
+            file=sys.stderr,
+        )
+        sys.exit(1)
+
+
+def _exec_in_container(container_info: dict, cli_args: list):
+    """Replace the current process with a command inside the managed container.
+
+    Probes whether sudo is needed (rootful containers), then os.execvp
+    into the container. On success the Python process is replaced entirely
+    and the container's exit code becomes the process exit code (OS semantics).
+    On failure, OSError propagates naturally.
+
+    Args:
+        container_info: dict with backend, container_name, exec_user, hermes_bin
+        cli_args: the original CLI arguments (everything after 'hermes')
+    """
+    import shutil
+
+    backend = container_info["backend"]
+    container_name = container_info["container_name"]
+    exec_user = container_info["exec_user"]
+    hermes_bin = container_info["hermes_bin"]
+
+    runtime = shutil.which(backend)
+    if not runtime:
+        print(f"Error: {backend} not found on PATH. Cannot route to container.",
+              file=sys.stderr)
+        sys.exit(1)
+
+    # Rootful containers (NixOS systemd service) are invisible to unprivileged
+    # users — Podman uses per-user namespaces, Docker needs group access.
+    # Probe whether the runtime can see the container; if not, try via sudo.
+    sudo_path = None
+    probe = _probe_container(
+        [runtime, "inspect", "--format", "ok", container_name], backend,
+    )
+    if probe.returncode != 0:
+        sudo_path = shutil.which("sudo")
+        if sudo_path:
+            probe2 = _probe_container(
+                [sudo_path, "-n", runtime, "inspect", "--format", "ok", container_name],
+                backend, via_sudo=True,
+            )
+            if probe2.returncode != 0:
+                print(
+                    f"Error: container '{container_name}' not found via {backend}.\n"
+                    f"\n"
+                    f"The container is likely running as root. Your user cannot see it\n"
+                    f"because {backend} uses per-user namespaces. Grant passwordless\n"
+                    f"sudo for {backend} — the -n (non-interactive) flag is required\n"
+                    f"because a password prompt would hang or break piped commands.\n"
+                    f"\n"
+                    f"On NixOS:\n"
+                    f"\n"
+                    f'  security.sudo.extraRules = [{{\n'
+                    f'    users = [ "{os.getenv("USER", "your-user")}" ];\n'
+                    f'    commands = [{{ command = "{runtime}"; options = [ "NOPASSWD" ]; }}];\n'
+                    f'  }}];\n'
+                    f"\n"
+                    f"Or run: sudo hermes {' '.join(cli_args)}",
+                    file=sys.stderr,
+                )
+                sys.exit(1)
+        else:
+            print(
+                f"Error: container '{container_name}' not found via {backend}.\n"
+                f"The container may be running under root. Try: sudo hermes {' '.join(cli_args)}",
+                file=sys.stderr,
+            )
+            sys.exit(1)
+
+    is_tty = sys.stdin.isatty()
+    tty_flags = ["-it"] if is_tty else ["-i"]
+
+    env_flags = []
+    for var in ("TERM", "COLORTERM", "LANG", "LC_ALL"):
+        val = os.environ.get(var)
+        if val:
+            env_flags.extend(["-e", f"{var}={val}"])
+
+    cmd_prefix = [sudo_path, "-n", runtime] if sudo_path else [runtime]
+    exec_cmd = (
+        cmd_prefix + ["exec"]
+        + tty_flags
+        + ["-u", exec_user]
+        + env_flags
+        + [container_name, hermes_bin]
+        + cli_args
+    )
+
+    os.execvp(exec_cmd[0], exec_cmd)
+
+
 def _resolve_session_by_name_or_id(name_or_id: str) -> Optional[str]:
     """Resolve a session name (title) or ID to a session ID.
 
@@ -646,6 +766,7 @@ 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 +978,6 @@ 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)
 
@@ -933,6 +1053,7 @@ def select_provider_and_model(args=None):
         "kilocode": "Kilo Code",
         "alibaba": "Alibaba Cloud (DashScope)",
         "huggingface": "Hugging Face",
+        "xiaomi": "Xiaomi MiMo",
         "custom": "Custom endpoint",
     }
     active_label = provider_labels.get(active, active) if active else "none"
@@ -965,12 +1086,14 @@ def select_provider_and_model(args=None):
         ("opencode-go", "OpenCode Go (open models, $10/month subscription)"),
         ("ai-gateway", "AI Gateway (Vercel — 200+ models, pay-per-use)"),
         ("alibaba", "Alibaba Cloud / DashScope Coding (Qwen + multi-provider)"),
+        ("xiaomi", "Xiaomi MiMo (MiMo-V2 models — pro, omni, flash)"),
     ]
 
-    # 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 +1102,23 @@ 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}
@@ -1053,17 +1183,60 @@ 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":
         _model_flow_anthropic(config, current_model)
     elif selected_provider == "kimi-coding":
         _model_flow_kimi(config, current_model)
-    elif selected_provider in ("gemini", "zai", "minimax", "minimax-cn", "kilocode", "opencode-zen", "opencode-go", "ai-gateway", "alibaba", "huggingface"):
+    elif selected_provider in ("gemini", "zai", "minimax", "minimax-cn", "kilocode", "opencode-zen", "opencode-go", "ai-gateway", "alibaba", "huggingface", "xiaomi"):
         _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 +1300,10 @@ 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 +1647,11 @@ 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 +1830,10 @@ 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 +1857,9 @@ 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 +1870,46 @@ 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 +1925,13 @@ 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 +1986,10 @@ 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 +2027,8 @@ 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 +2037,7 @@ 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:")
@@ -2484,13 +2668,8 @@ def _model_flow_anthropic(config, current_model=""):
     from hermes_cli.models import _PROVIDER_MODELS
 
     # Check ALL credential sources
-    existing_key = (
-        get_env_value("ANTHROPIC_TOKEN")
-        or os.getenv("ANTHROPIC_TOKEN", "")
-        or get_env_value("ANTHROPIC_API_KEY")
-        or os.getenv("ANTHROPIC_API_KEY", "")
-        or os.getenv("CLAUDE_CODE_OAUTH_TOKEN", "")
-    )
+    from hermes_cli.auth import get_anthropic_key
+    existing_key = get_anthropic_key()
     cc_available = False
     try:
         from agent.anthropic_adapter import read_claude_code_credentials, is_claude_code_token_valid
@@ -2639,12 +2818,30 @@ 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
     config_command(args)
 
 
+def cmd_backup(args):
+    """Back up Hermes home directory to a zip file."""
+    from hermes_cli.backup import run_backup
+    run_backup(args)
+
+
+def cmd_import(args):
+    """Restore a Hermes backup from a zip file."""
+    from hermes_cli.backup import run_import
+    run_import(args)
+
+
 def cmd_version(args):
     """Show version."""
     print(f"Hermes Agent v{__version__} ({__release_date__})")
@@ -3008,33 +3205,19 @@ 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 +3478,11 @@ 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 +3934,7 @@ 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 +3945,7 @@ 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:
@@ -3823,7 +4007,7 @@ def cmd_update(args):
             # Exclude PIDs that belong to just-restarted services so we don't
             # immediately kill the process that systemd/launchd just spawned.
             service_pids = _get_service_pids()
-            manual_pids = find_gateway_pids(exclude_pids=service_pids)
+            manual_pids = find_gateway_pids(exclude_pids=service_pids, all_profiles=True)
             for pid in manual_pids:
                 try:
                     os.kill(pid, _signal.SIGTERM)
@@ -4035,7 +4219,10 @@ 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()
@@ -4175,6 +4362,7 @@ def cmd_logs(args):
         level=getattr(args, "level", None),
         session=getattr(args, "session", None),
         since=getattr(args, "since", None),
+        component=getattr(args, "component", None),
     )
 
 
@@ -4278,6 +4466,10 @@ 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)"
@@ -4294,7 +4486,7 @@ For more help on a command:
     )
     chat_parser.add_argument(
         "--provider",
-        choices=["auto", "openrouter", "nous", "openai-codex", "copilot-acp", "copilot", "anthropic", "gemini", "huggingface", "zai", "kimi-coding", "minimax", "minimax-cn", "kilocode"],
+        choices=["auto", "openrouter", "nous", "openai-codex", "copilot-acp", "copilot", "anthropic", "gemini", "huggingface", "zai", "kimi-coding", "minimax", "minimax-cn", "kilocode", "xiaomi"],
         default=None,
         help="Inference provider (default: auto)"
     )
@@ -4420,7 +4612,7 @@ 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 +4621,7 @@ 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 +4639,7 @@ 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 +4660,12 @@ 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"
     )
@@ -4720,7 +4912,59 @@ 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)
+
+    # =========================================================================
+    # backup command
+    # =========================================================================
+    backup_parser = subparsers.add_parser(
+        "backup",
+        help="Back up Hermes home directory to a zip file",
+        description="Create a zip archive of your entire Hermes configuration, "
+                    "skills, sessions, and data (excludes the hermes-agent codebase)"
+    )
+    backup_parser.add_argument(
+        "-o", "--output",
+        help="Output path for the zip file (default: ~/hermes-backup-<timestamp>.zip)"
+    )
+    backup_parser.set_defaults(func=cmd_backup)
+
+    # =========================================================================
+    # import command
+    # =========================================================================
+    import_parser = subparsers.add_parser(
+        "import",
+        help="Restore a Hermes backup from a zip file",
+        description="Extract a previously created Hermes backup into your "
+                    "Hermes home directory, restoring configuration, skills, "
+                    "sessions, and data"
+    )
+    import_parser.add_argument(
+        "zipfile",
+        help="Path to the backup zip file"
+    )
+    import_parser.add_argument(
+        "--force", "-f",
+        action="store_true",
+        help="Overwrite existing files without confirmation"
+    )
+    import_parser.set_defaults(func=cmd_import)
+
     # =========================================================================
     # config command
     # =========================================================================
@@ -5070,6 +5314,8 @@ For more help on a command:
     mcp_add_p.add_argument("--command", help="Stdio command (e.g. npx)")
     mcp_add_p.add_argument("--args", nargs="*", default=[], help="Arguments for stdio command")
     mcp_add_p.add_argument("--auth", choices=["oauth", "header"], help="Auth method")
+    mcp_add_p.add_argument("--preset", help="Known MCP preset name")
+    mcp_add_p.add_argument("--env", nargs="*", default=[], help="Environment variables for stdio servers (KEY=VALUE)")
 
     mcp_rm_p = mcp_sub.add_parser("remove", aliases=["rm"], help="Remove an MCP server")
     mcp_rm_p.add_argument("name", help="Server name to remove")
@@ -5332,7 +5578,8 @@ For more help on a command:
     claw_migrate = claw_subparsers.add_parser(
         "migrate",
         help="Migrate from OpenClaw to Hermes",
-        description="Import settings, memories, skills, and API keys from an OpenClaw installation"
+        description="Import settings, memories, skills, and API keys from an OpenClaw installation. "
+                    "Always shows a preview before making changes."
     )
     claw_migrate.add_argument(
         "--source",
@@ -5341,7 +5588,7 @@ For more help on a command:
     claw_migrate.add_argument(
         "--dry-run",
         action="store_true",
-        help="Preview what would be migrated without making changes"
+        help="Preview only — stop after showing what would be migrated"
     )
     claw_migrate.add_argument(
         "--preset",
@@ -5551,6 +5798,7 @@ Examples:
     hermes logs gateway -n 100     Show last 100 lines of gateway.log
     hermes logs --level WARNING    Only show WARNING and above
     hermes logs --session abc123   Filter by session ID
+    hermes logs --component tools  Only show tool-related lines
     hermes logs --since 1h         Lines from the last hour
     hermes logs --since 30m -f     Follow, starting from 30 min ago
     hermes logs list               List available log files with sizes
@@ -5580,6 +5828,10 @@ Examples:
         "--since", metavar="TIME",
         help="Show lines since TIME ago (e.g. 1h, 30m, 2d)",
     )
+    logs_parser.add_argument(
+        "--component", metavar="NAME",
+        help="Filter by component: gateway, agent, tools, cli, cron",
+    )
     logs_parser.set_defaults(func=cmd_logs)
 
     # =========================================================================
@@ -5588,9 +5840,22 @@ Examples:
     # Pre-process argv so unquoted multi-word session names after -c / -r
     # are merged into a single token before argparse sees them.
     # e.g. ``hermes -c Pokemon Agent Dev`` → ``hermes -c 'Pokemon Agent Dev'``
+    # ── Container-aware routing ────────────────────────────────────────
+    # When NixOS container mode is active, route ALL subcommands into
+    # the managed container.  This MUST run before parse_args() so that
+    # --help, unrecognised flags, and every subcommand are forwarded
+    # transparently instead of being intercepted by argparse on the host.
+    from hermes_cli.config import get_container_exec_info
+    container_info = get_container_exec_info()
+    if container_info:
+        _exec_in_container(container_info, sys.argv[1:])
+        # Unreachable: os.execvp never returns on success (process is replaced)
+        # and raises OSError on failure (which propagates as a traceback).
+        sys.exit(1)
+
     _processed_argv = _coalesce_session_name_args(sys.argv[1:])
     args = parser.parse_args(_processed_argv)
-    
+
     # Handle --version flag
     if args.version:
         cmd_version(args)

hermes_cli/mcp_config.py

@@ -9,7 +9,6 @@ configuration in ~/.hermes/config.yaml under the ``mcp_servers`` key.
 """
 
 import asyncio
-import getpass
 import logging
 import os
 import re
@@ -28,6 +27,11 @@ from hermes_constants import display_hermes_home
 
 logger = logging.getLogger(__name__)
 
+_ENV_VAR_NAME_RE = re.compile(r"^[A-Za-z_][A-Za-z0-9_]*$")
+
+
+_MCP_PRESETS: Dict[str, Dict[str, Any]] = {}
+
 
 # ─── UI Helpers ───────────────────────────────────────────────────────────────
 
@@ -57,19 +61,8 @@ def _confirm(question: str, default: bool = True) -> bool:
 
 
 def _prompt(question: str, *, password: bool = False, default: str = "") -> str:
-    display = f"  {question}"
-    if default:
-        display += f" [{default}]"
-    display += ": "
-    try:
-        if password:
-            value = getpass.getpass(color(display, Colors.YELLOW))
-        else:
-            value = input(color(display, Colors.YELLOW))
-        return value.strip() or default
-    except (KeyboardInterrupt, EOFError):
-        print()
-        return default
+    from hermes_cli.cli_output import prompt as _shared_prompt
+    return _shared_prompt(question, default=default, password=password)
 
 
 # ─── Config Helpers ───────────────────────────────────────────────────────────
@@ -109,6 +102,59 @@ def _env_key_for_server(name: str) -> str:
     return f"MCP_{name.upper().replace('-', '_')}_API_KEY"
 
 
+def _parse_env_assignments(raw_env: Optional[List[str]]) -> Dict[str, str]:
+    """Parse ``KEY=VALUE`` strings from CLI args into an env dict."""
+    parsed: Dict[str, str] = {}
+    for item in raw_env or []:
+        text = str(item or "").strip()
+        if not text:
+            continue
+        if "=" not in text:
+            raise ValueError(f"Invalid --env value '{text}' (expected KEY=VALUE)")
+        key, value = text.split("=", 1)
+        key = key.strip()
+        if not key:
+            raise ValueError(f"Invalid --env value '{text}' (missing variable name)")
+        if not _ENV_VAR_NAME_RE.match(key):
+            raise ValueError(f"Invalid --env variable name '{key}'")
+        parsed[key] = value
+    return parsed
+
+
+def _apply_mcp_preset(
+    name: str,
+    *,
+    preset_name: Optional[str],
+    url: Optional[str],
+    command: Optional[str],
+    cmd_args: List[str],
+    server_config: Dict[str, Any],
+) -> tuple[Optional[str], Optional[str], List[str], bool]:
+    """Apply a known MCP preset when transport details were omitted."""
+    if not preset_name:
+        return url, command, cmd_args, False
+
+    preset = _MCP_PRESETS.get(preset_name)
+    if not preset:
+        raise ValueError(f"Unknown MCP preset: {preset_name}")
+
+    if url or command:
+        return url, command, cmd_args, False
+
+    url = preset.get("url")
+    command = preset.get("command")
+    cmd_args = list(preset.get("args") or [])
+
+    if url:
+        server_config["url"] = url
+    if command:
+        server_config["command"] = command
+    if cmd_args:
+        server_config["args"] = cmd_args
+
+    return url, command, cmd_args, True
+
+
 # ─── Discovery (temporary connect) ───────────────────────────────────────────
 
 def _probe_single_server(
@@ -177,13 +223,35 @@ def cmd_mcp_add(args):
     command = getattr(args, "command", None)
     cmd_args = getattr(args, "args", None) or []
     auth_type = getattr(args, "auth", None)
+    preset_name = getattr(args, "preset", None)
+    raw_env = getattr(args, "env", None)
+
+    server_config: Dict[str, Any] = {}
+    try:
+        explicit_env = _parse_env_assignments(raw_env)
+        url, command, cmd_args, _preset_applied = _apply_mcp_preset(
+            name,
+            preset_name=preset_name,
+            url=url,
+            command=command,
+            cmd_args=list(cmd_args),
+            server_config=server_config,
+        )
+    except ValueError as exc:
+        _error(str(exc))
+        return
+
+    if url and explicit_env:
+        _error("--env is only supported for stdio MCP servers (--command or stdio presets)")
+        return
 
     # Validate transport
     if not url and not command:
-        _error("Must specify --url <endpoint> or --command <cmd>")
+        _error("Must specify --url <endpoint>, --command <cmd>, or --preset <name>")
         _info("Examples:")
         _info('  hermes mcp add ink --url "https://mcp.ml.ink/mcp"')
         _info('  hermes mcp add github --command npx --args @modelcontextprotocol/server-github')
+        _info('  hermes mcp add myserver --preset mypreset')
         return
 
     # Check if server already exists
@@ -194,13 +262,15 @@ def cmd_mcp_add(args):
             return
 
     # Build initial config
-    server_config: Dict[str, Any] = {}
     if url:
         server_config["url"] = url
     else:
         server_config["command"] = command
         if cmd_args:
             server_config["args"] = cmd_args
+        if explicit_env:
+            server_config["env"] = explicit_env
+
 
     # ── Authentication ────────────────────────────────────────────────
 
@@ -638,6 +708,7 @@ def mcp_command(args):
         _info("hermes mcp serve                              Run as MCP server")
         _info("hermes mcp add <name> --url <endpoint>        Add an MCP server")
         _info("hermes mcp add <name> --command <cmd>         Add a stdio server")
+        _info("hermes mcp add <name> --preset <preset>       Add from a known preset")
         _info("hermes mcp remove <name>                      Remove a server")
         _info("hermes mcp list                               List servers")
         _info("hermes mcp test <name>                        Test connection")

hermes_cli/memory_setup.py

@@ -25,85 +25,13 @@ def _curses_select(title: str, items: list[tuple[str, str]], default: int = 0) -
     items: list of (label, description) tuples.
     Returns selected index, or default on escape/quit.
     """
-    try:
-        import curses
-        result = [default]
-
-        def _menu(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)
-            cursor = default
-
-            while True:
-                stdscr.clear()
-                max_y, max_x = stdscr.getmaxyx()
-
-                # Title
-                try:
-                    stdscr.addnstr(0, 0, title, max_x - 1,
-                                   curses.A_BOLD | (curses.color_pair(2) if curses.has_colors() else 0))
-                    stdscr.addnstr(1, 0, "  ↑↓ navigate  ⏎ select  q quit", max_x - 1,
-                                   curses.color_pair(3) if curses.has_colors() else curses.A_DIM)
-                except curses.error:
-                    pass
-
-                for i, (label, desc) in enumerate(items):
-                    y = i + 3
-                    if y >= max_y - 1:
-                        break
-                    arrow = "→" if i == cursor else " "
-                    line = f" {arrow}  {label}"
-                    if desc:
-                        line += f"  {desc}"
-
-                    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], 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 (curses.KEY_ENTER, 10, 13):
-                    result[0] = cursor
-                    return
-                elif key in (27, ord('q')):
-                    return
-
-        curses.wrapper(_menu)
-        return result[0]
-
-    except Exception:
-        # Fallback: numbered input
-        print(f"\n  {title}\n")
-        for i, (label, desc) in enumerate(items):
-            marker = "→" if i == default else " "
-            d = f"  {desc}" if desc else ""
-            print(f"  {marker} {i + 1}. {label}{d}")
-        while True:
-            try:
-                val = input(f"\n  Select [1-{len(items)}] ({default + 1}): ")
-                if not val:
-                    return default
-                idx = int(val) - 1
-                if 0 <= idx < len(items):
-                    return idx
-            except (ValueError, EOFError):
-                return default
+    from hermes_cli.curses_ui import curses_radiolist
+    # Format (label, desc) tuples into display strings
+    display_items = [
+        f"{label}  {desc}" if desc else label
+        for label, desc in items
+    ]
+    return curses_radiolist(title, display_items, selected=default, cancel_returns=default)
 
 
 def _prompt(label: str, default: str | None = None, secret: bool = False) -> str:

hermes_cli/model_normalize.py

@@ -74,19 +74,25 @@ _DOT_TO_HYPHEN_PROVIDERS: frozenset[str] = frozenset({
 _STRIP_VENDOR_ONLY_PROVIDERS: frozenset[str] = frozenset({
     "copilot",
     "copilot-acp",
+    "openai-codex",
 })
 
-# 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",
+})
+
+# 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",
+    "xiaomi",
     "custom",
 })
 
@@ -168,6 +174,40 @@ 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 +345,41 @@ 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)
+        stripped = _strip_matching_provider_prefix(name, provider)
+        if stripped == name and name.startswith("openai/"):
+            # openai-codex maps openai/gpt-5.4 -> gpt-5.4
+            return name.split("/", 1)[1]
+        return stripped
 
     # --- 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 +389,3 @@ 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:
@@ -590,6 +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
@@ -708,6 +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.
@@ -733,6 +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] = []
@@ -753,9 +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)
@@ -782,42 +809,104 @@ 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"):
-            # These use auth stores, not env vars — check for auth.json entries
+        # 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
+        # Check auth store and credential pool for non-env-var credentials.
+        # This applies to OAuth providers AND api_key providers that also
+        # support OAuth (e.g. anthropic supports both API key and Claude Code
+        # OAuth via external credential files).
+        if not has_creds:
             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)
+        # Fallback: check the credential pool with full auto-seeding.
+        # This catches credentials that exist in external stores (e.g.
+        # Codex CLI ~/.codex/auth.json) which _seed_from_singletons()
+        # imports on demand but aren't in the raw auth.json yet.
+        if not has_creds:
+            try:
+                from agent.credential_pool import load_pool
+                pool = load_pool(hermes_slug)
+                if pool.has_credentials():
+                    has_creds = True
+            except Exception as exc:
+                logger.debug("Credential pool check failed for %s: %s", hermes_slug, exc)
+        # Fallback: check external credential files directly.
+        # The credential pool gates anthropic behind
+        # is_provider_explicitly_configured() to prevent auxiliary tasks
+        # from silently consuming Claude Code tokens (PR #4210).
+        # But the /model picker is discovery-oriented — we WANT to show
+        # providers the user can switch to, even if they aren't currently
+        # configured.
+        if not has_creds and hermes_slug == "anthropic":
+            try:
+                from agent.anthropic_adapter import (
+                    read_claude_code_credentials,
+                    read_hermes_oauth_credentials,
+                )
+                hermes_creds = read_hermes_oauth_credentials()
+                cc_creds = read_claude_code_credentials()
+                if (hermes_creds and hermes_creds.get("accessToken")) or \
+                   (cc_creds and cc_creds.get("accessToken")):
+                    has_creds = True
+            except Exception as exc:
+                logger.debug("Anthropic external creds check failed: %s", 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):
@@ -845,80 +934,46 @@ 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 +54,20 @@ OPENROUTER_MODELS: list[tuple[str, str]] = [
     ("openai/gpt-5.4-nano",             ""),
 ]
 
+_openrouter_catalog_cache: list[tuple[str, str]] | None = None
+
+
+def _codex_curated_models() -> list[str]:
+    """Derive the openai-codex curated list from codex_models.py.
+
+    Single source of truth: DEFAULT_CODEX_MODELS + forward-compat synthesis.
+    This keeps the gateway /model picker in sync with the CLI `hermes model`
+    flow without maintaining a separate static list.
+    """
+    from hermes_cli.codex_models import DEFAULT_CODEX_MODELS, _add_forward_compat_models
+    return _add_forward_compat_models(list(DEFAULT_CODEX_MODELS))
+
+
 _PROVIDER_MODELS: dict[str, list[str]] = {
     "nous": [
         "anthropic/claude-opus-4.6",
@@ -86,12 +98,7 @@ _PROVIDER_MODELS: dict[str, list[str]] = {
         "openai/gpt-5.4-pro",
         "openai/gpt-5.4-nano",
     ],
-    "openai-codex": [
-        "gpt-5.3-codex",
-        "gpt-5.2-codex",
-        "gpt-5.1-codex-mini",
-        "gpt-5.1-codex-max",
-    ],
+    "openai-codex": _codex_curated_models(),
     "copilot-acp": [
         "copilot-acp",
     ],
@@ -129,6 +136,19 @@ _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 +164,16 @@ _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",
@@ -174,6 +188,11 @@ _PROVIDER_MODELS: dict[str, list[str]] = {
         "deepseek-chat",
         "deepseek-reasoner",
     ],
+    "xiaomi": [
+        "mimo-v2-pro",
+        "mimo-v2-omni",
+        "mimo-v2-flash",
+    ],
     "opencode-zen": [
         "gpt-5.4-pro",
         "gpt-5.4",
@@ -416,12 +435,6 @@ _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.
 
@@ -485,6 +498,7 @@ _PROVIDER_LABELS = {
     "alibaba": "Alibaba Cloud (DashScope)",
     "qwen-oauth": "Qwen OAuth (Portal)",
     "huggingface": "Hugging Face",
+    "xiaomi": "Xiaomi MiMo",
     "custom": "Custom endpoint",
 }
 
@@ -527,22 +541,89 @@ _PROVIDER_ALIASES = {
     "hf": "huggingface",
     "hugging-face": "huggingface",
     "huggingface-hub": "huggingface",
+    "mimo": "xiaomi",
+    "xiaomi-mimo": "xiaomi",
 }
 
 
-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 +656,6 @@ 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 +783,14 @@ 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 +803,7 @@ 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 {}
 
@@ -769,7 +827,7 @@ def list_available_providers() -> list[dict[str, str]]:
         "openrouter", "nous", "openai-codex", "copilot", "copilot-acp",
         "gemini", "huggingface",
         "zai", "kimi-coding", "minimax", "minimax-cn", "kilocode", "anthropic", "alibaba",
-        "qwen-oauth",
+        "qwen-oauth", "xiaomi",
         "opencode-zen", "opencode-go",
         "ai-gateway", "deepseek", "custom",
     ]
@@ -854,7 +912,11 @@ 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 +925,7 @@ 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 +1044,12 @@ 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 +1079,79 @@ 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 +1163,7 @@ 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 +1171,7 @@ 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 +1667,7 @@ 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,
@@ -1674,6 +1809,35 @@ def validate_requested_model(
             "message": message,
         }
 
+    # OpenAI Codex has its own catalog path; /v1/models probing is not the right validation path.
+    if normalized == "openai-codex":
+        try:
+            codex_models = provider_model_ids("openai-codex")
+        except Exception:
+            codex_models = []
+        if codex_models:
+            if requested_for_lookup in set(codex_models):
+                return {
+                    "accepted": True,
+                    "persist": True,
+                    "recognized": True,
+                    "message": None,
+                }
+            suggestions = get_close_matches(requested_for_lookup, codex_models, n=3, cutoff=0.5)
+            suggestion_text = ""
+            if suggestions:
+                suggestion_text = "\n  Similar models: " + ", ".join(f"`{s}`" for s in suggestions)
+            return {
+                "accepted": True,
+                "persist": True,
+                "recognized": False,
+                "message": (
+                    f"Note: `{requested}` was not found in the OpenAI Codex model listing. "
+                    f"It may still work if your account has access to it."
+                    f"{suggestion_text}"
+                ),
+            }
+
     # Probe the live API to check if the model actually exists
     api_models = fetch_api_models(api_key, base_url)
 

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/platforms.py

@@ -0,0 +1,46 @@
+"""
+Shared platform registry for Hermes Agent.
+
+Single source of truth for platform metadata consumed by both
+skills_config (label display) and tools_config (default toolset
+resolution).  Import ``PLATFORMS`` from here instead of maintaining
+duplicate dicts in each module.
+"""
+
+from collections import OrderedDict
+from typing import NamedTuple
+
+
+class PlatformInfo(NamedTuple):
+    """Metadata for a single platform entry."""
+    label: str
+    default_toolset: str
+
+
+# Ordered so that TUI menus are deterministic.
+PLATFORMS: OrderedDict[str, PlatformInfo] = OrderedDict([
+    ("cli",            PlatformInfo(label="🖥️  CLI",            default_toolset="hermes-cli")),
+    ("telegram",       PlatformInfo(label="📱 Telegram",        default_toolset="hermes-telegram")),
+    ("discord",        PlatformInfo(label="💬 Discord",         default_toolset="hermes-discord")),
+    ("slack",          PlatformInfo(label="💼 Slack",           default_toolset="hermes-slack")),
+    ("whatsapp",       PlatformInfo(label="📱 WhatsApp",        default_toolset="hermes-whatsapp")),
+    ("signal",         PlatformInfo(label="📡 Signal",          default_toolset="hermes-signal")),
+    ("bluebubbles",    PlatformInfo(label="💙 BlueBubbles",     default_toolset="hermes-bluebubbles")),
+    ("email",          PlatformInfo(label="📧 Email",           default_toolset="hermes-email")),
+    ("homeassistant",  PlatformInfo(label="🏠 Home Assistant",  default_toolset="hermes-homeassistant")),
+    ("mattermost",     PlatformInfo(label="💬 Mattermost",      default_toolset="hermes-mattermost")),
+    ("matrix",         PlatformInfo(label="💬 Matrix",          default_toolset="hermes-matrix")),
+    ("dingtalk",       PlatformInfo(label="💬 DingTalk",        default_toolset="hermes-dingtalk")),
+    ("feishu",         PlatformInfo(label="🪽 Feishu",          default_toolset="hermes-feishu")),
+    ("wecom",          PlatformInfo(label="💬 WeCom",           default_toolset="hermes-wecom")),
+    ("wecom_callback", PlatformInfo(label="💬 WeCom Callback",  default_toolset="hermes-wecom-callback")),
+    ("weixin",         PlatformInfo(label="💬 Weixin",          default_toolset="hermes-weixin")),
+    ("webhook",        PlatformInfo(label="🔗 Webhook",         default_toolset="hermes-webhook")),
+    ("api_server",     PlatformInfo(label="🌐 API Server",      default_toolset="hermes-api-server")),
+])
+
+
+def platform_label(key: str, default: str = "") -> str:
+    """Return the display label for a platform key, or *default*."""
+    info = PLATFORMS.get(key)
+    return info.label if info is not None else default

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