fix(claw): warn if gateway is running before migrating bot tokens

When hermes claw migrate copies Telegram/Discord/Slack bot tokens
from OpenClaw while the Hermes gateway is already polling with
those same tokens, the platforms conflict (e.g. Telegram 409
"terminated by other getUpdates request"). The gateway has runtime
detection for this, but the error only surfaces in logs and
gateway_state.json — users see their bot silently stop responding.

Two changes:

1. Pre-migration check in claw.py: reads gateway_state.json,
   verifies the PID is alive, and warns if platforms are connected.
   User can continue anyway or stop the gateway first.

2. Improved Telegram polling conflict message: mentions OpenClaw as
   a common cause and gives the restart command.

Refs #7907

.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
 # =============================================================================

Dockerfile

@@ -6,7 +6,7 @@ ENV PYTHONUNBUFFERED=1
 # Install system dependencies in one layer, clear APT cache
 RUN apt-get update && \
     apt-get install -y --no-install-recommends \
-        build-essential nodejs npm python3 python3-pip ripgrep ffmpeg gcc python3-dev libffi-dev && \
+        build-essential nodejs npm python3 python3-pip ripgrep ffmpeg gcc python3-dev libffi-dev procps && \
     rm -rf /var/lib/apt/lists/*
 
 COPY . /opt/hermes

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.
@@ -161,18 +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:
@@ -1304,9 +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):

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",
@@ -707,7 +714,9 @@ 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():
@@ -726,7 +735,9 @@ 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():
@@ -1075,11 +1086,12 @@ def _is_connection_error(exc: Exception) -> bool:
 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.
@@ -1105,15 +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, ""
 
@@ -1128,9 +1140,28 @@ 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()
@@ -1217,6 +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.
@@ -1240,6 +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.
@@ -1247,6 +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()
@@ -1336,6 +1406,7 @@ def resolve_provider_client(
                 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
@@ -1344,6 +1415,8 @@ def resolve_provider_client(
             client, default = try_fn()
             if client is not None:
                 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 "
@@ -1363,6 +1436,7 @@ def resolve_provider_client(
                     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)
@@ -1425,6 +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))
@@ -1457,12 +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,
     )
 
 
@@ -1473,13 +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,
     )
 
 
@@ -1552,7 +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)
@@ -1593,16 +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:
@@ -1768,12 +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.
 
@@ -1797,7 +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]
@@ -1809,9 +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,
@@ -1819,6 +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
@@ -1838,24 +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:
@@ -1872,6 +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
@@ -1884,31 +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
@@ -1980,6 +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,
     *,
@@ -2018,7 +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":
@@ -2051,6 +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
@@ -2094,18 +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
 
@@ -2122,19 +2287,24 @@ def call_llm(
         # 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)
-        if should_fallback:
+        # 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
 
 
@@ -2212,7 +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":
@@ -2246,6 +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()
@@ -2256,11 +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}. "
@@ -2275,11 +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/context_compressor.py

@@ -18,6 +18,7 @@ import time
 from typing import Any, Dict, List, Optional
 
 from agent.auxiliary_client import call_llm
+from agent.context_engine import ContextEngine
 from agent.model_metadata import (
     get_model_context_length,
     estimate_messages_tokens_rough,
@@ -50,8 +51,8 @@ _CHARS_PER_TOKEN = 4
 _SUMMARY_FAILURE_COOLDOWN_SECONDS = 600
 
 
-class ContextCompressor:
-    """Compresses conversation context when approaching the model's context limit.
+class ContextCompressor(ContextEngine):
+    """Default context engine — compresses conversation context via lossy summarization.
 
     Algorithm:
       1. Prune old tool results (cheap, no LLM call)
@@ -61,6 +62,33 @@ class ContextCompressor:
       5. On subsequent compactions, iteratively update the previous summary
     """
 
+    @property
+    def name(self) -> str:
+        return "compressor"
+
+    def on_session_reset(self) -> None:
+        """Reset all per-session state for /new or /reset."""
+        super().on_session_reset()
+        self._context_probed = False
+        self._context_probe_persistable = False
+        self._previous_summary = None
+
+    def update_model(
+        self,
+        model: str,
+        context_length: int,
+        base_url: str = "",
+        api_key: str = "",
+        provider: str = "",
+    ) -> None:
+        """Update model info after a model switch or fallback activation."""
+        self.model = model
+        self.base_url = base_url
+        self.api_key = api_key
+        self.provider = provider
+        self.context_length = context_length
+        self.threshold_tokens = int(context_length * self.threshold_percent)
+
     def __init__(
         self,
         model: str,

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/display.py

@@ -21,11 +21,73 @@ _RESET = "\033[0m"
 logger = logging.getLogger(__name__)
 
 _ANSI_RESET = "\033[0m"
-_ANSI_DIM = "\033[38;2;150;150;150m"
-_ANSI_FILE = "\033[38;2;180;160;255m"
-_ANSI_HUNK = "\033[38;2;120;120;140m"
-_ANSI_MINUS = "\033[38;2;255;255;255;48;2;120;20;20m"
-_ANSI_PLUS = "\033[38;2;255;255;255;48;2;20;90;20m"
+
+# Diff colors — resolved lazily from the skin engine so they adapt
+# to light/dark themes.  Falls back to sensible defaults on import
+# failure.  We cache after first resolution for performance.
+_diff_colors_cached: dict[str, str] | None = None
+
+
+def _diff_ansi() -> dict[str, str]:
+    """Return ANSI escapes for diff display, resolved from the active skin."""
+    global _diff_colors_cached
+    if _diff_colors_cached is not None:
+        return _diff_colors_cached
+
+    # Defaults that work on dark terminals
+    dim = "\033[38;2;150;150;150m"
+    file_c = "\033[38;2;180;160;255m"
+    hunk = "\033[38;2;120;120;140m"
+    minus = "\033[38;2;255;255;255;48;2;120;20;20m"
+    plus = "\033[38;2;255;255;255;48;2;20;90;20m"
+
+    try:
+        from hermes_cli.skin_engine import get_active_skin
+        skin = get_active_skin()
+
+        def _hex_fg(key: str, fallback_rgb: tuple[int, int, int]) -> str:
+            h = skin.get_color(key, "")
+            if h and len(h) == 7 and h[0] == "#":
+                r, g, b = int(h[1:3], 16), int(h[3:5], 16), int(h[5:7], 16)
+                return f"\033[38;2;{r};{g};{b}m"
+            r, g, b = fallback_rgb
+            return f"\033[38;2;{r};{g};{b}m"
+
+        dim = _hex_fg("banner_dim", (150, 150, 150))
+        file_c = _hex_fg("session_label", (180, 160, 255))
+        hunk = _hex_fg("session_border", (120, 120, 140))
+        # minus/plus use background colors — derive from ui_error/ui_ok
+        err_h = skin.get_color("ui_error", "#ef5350")
+        ok_h = skin.get_color("ui_ok", "#4caf50")
+        if err_h and len(err_h) == 7:
+            er, eg, eb = int(err_h[1:3], 16), int(err_h[3:5], 16), int(err_h[5:7], 16)
+            # Use a dark tinted version as background
+            minus = f"\033[38;2;255;255;255;48;2;{max(er//2,20)};{max(eg//4,10)};{max(eb//4,10)}m"
+        if ok_h and len(ok_h) == 7:
+            or_, og, ob = int(ok_h[1:3], 16), int(ok_h[3:5], 16), int(ok_h[5:7], 16)
+            plus = f"\033[38;2;255;255;255;48;2;{max(or_//4,10)};{max(og//2,20)};{max(ob//4,10)}m"
+    except Exception:
+        pass
+
+    _diff_colors_cached = {
+        "dim": dim, "file": file_c, "hunk": hunk,
+        "minus": minus, "plus": plus,
+    }
+    return _diff_colors_cached
+
+
+def reset_diff_colors() -> None:
+    """Reset cached diff colors (call after /skin switch)."""
+    global _diff_colors_cached
+    _diff_colors_cached = None
+
+
+# Module-level helpers — each call resolves from the active skin lazily.
+def _diff_dim():   return _diff_ansi()["dim"]
+def _diff_file():  return _diff_ansi()["file"]
+def _diff_hunk():  return _diff_ansi()["hunk"]
+def _diff_minus(): return _diff_ansi()["minus"]
+def _diff_plus():  return _diff_ansi()["plus"]
 _MAX_INLINE_DIFF_FILES = 6
 _MAX_INLINE_DIFF_LINES = 80
 
@@ -403,19 +465,19 @@ def _render_inline_unified_diff(diff: str) -> list[str]:
         if raw_line.startswith("+++ "):
             to_file = raw_line[4:].strip()
             if from_file or to_file:
-                rendered.append(f"{_ANSI_FILE}{from_file or 'a/?'} → {to_file or 'b/?'}{_ANSI_RESET}")
+                rendered.append(f"{_diff_file()}{from_file or 'a/?'} → {to_file or 'b/?'}{_ANSI_RESET}")
             continue
         if raw_line.startswith("@@"):
-            rendered.append(f"{_ANSI_HUNK}{raw_line}{_ANSI_RESET}")
+            rendered.append(f"{_diff_hunk()}{raw_line}{_ANSI_RESET}")
             continue
         if raw_line.startswith("-"):
-            rendered.append(f"{_ANSI_MINUS}{raw_line}{_ANSI_RESET}")
+            rendered.append(f"{_diff_minus()}{raw_line}{_ANSI_RESET}")
             continue
         if raw_line.startswith("+"):
-            rendered.append(f"{_ANSI_PLUS}{raw_line}{_ANSI_RESET}")
+            rendered.append(f"{_diff_plus()}{raw_line}{_ANSI_RESET}")
             continue
         if raw_line.startswith(" "):
-            rendered.append(f"{_ANSI_DIM}{raw_line}{_ANSI_RESET}")
+            rendered.append(f"{_diff_dim()}{raw_line}{_ANSI_RESET}")
             continue
         if raw_line:
             rendered.append(raw_line)
@@ -481,7 +543,7 @@ def _summarize_rendered_diff_sections(
         summary = f"… omitted {omitted_lines} diff line(s)"
         if omitted_files:
             summary += f" across {omitted_files} additional file(s)/section(s)"
-        rendered.append(f"{_ANSI_HUNK}{summary}{_ANSI_RESET}")
+        rendered.append(f"{_diff_hunk()}{summary}{_ANSI_RESET}")
 
     return rendered
 

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/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",
 })
 
@@ -113,17 +115,14 @@ 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,
@@ -151,10 +150,11 @@ 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,
 }
 
@@ -214,6 +214,8 @@ _URL_TO_PROVIDER: Dict[str, str] = {
     "api.fireworks.ai": "fireworks",
     "opencode.ai": "opencode-go",
     "api.x.ai": "xai",
+    "api.xiaomimimo.com": "xiaomi",
+    "xiaomimimo.com": "xiaomi",
 }
 
 

agent/models_dev.py

@@ -161,6 +161,7 @@ PROVIDER_TO_MODELS_DEV: Dict[str, str] = {
     "gemini": "google",
     "google": "google",
     "xai": "xai",
+    "xiaomi": "xiaomi",
     "nvidia": "nvidia",
     "groq": "groq",
     "mistral": "mistral",
@@ -383,7 +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

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)
 

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)
   #
@@ -480,6 +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
@@ -582,7 +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)
 #
@@ -611,7 +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)
 #

cli.py

@@ -987,11 +987,60 @@ def _prune_orphaned_branches(repo_root: str) -> None:
 # - Dim: #B8860B (muted text)
 
 # ANSI building blocks for conversation display
-_GOLD = "\033[1;38;2;255;215;0m"  # True-color #FFD700 bold — matches Rich Panel gold
+_ACCENT_ANSI_DEFAULT = "\033[1;38;2;255;215;0m"  # True-color #FFD700 bold — fallback
 _BOLD = "\033[1m"
 _DIM = "\033[2m"
 _RST = "\033[0m"
 
+
+def _hex_to_ansi_bold(hex_color: str) -> str:
+    """Convert a hex color like '#268bd2' to a bold true-color ANSI escape."""
+    try:
+        r = int(hex_color[1:3], 16)
+        g = int(hex_color[3:5], 16)
+        b = int(hex_color[5:7], 16)
+        return f"\033[1;38;2;{r};{g};{b}m"
+    except (ValueError, IndexError):
+        return _ACCENT_ANSI_DEFAULT
+
+
+class _SkinAwareAnsi:
+    """Lazy ANSI escape that resolves from the skin engine on first use.
+
+    Acts as a string in f-strings and concatenation.  Call ``.reset()`` to
+    force re-resolution after a ``/skin`` switch.
+    """
+
+    def __init__(self, skin_key: str, fallback_hex: str = "#FFD700"):
+        self._skin_key = skin_key
+        self._fallback_hex = fallback_hex
+        self._cached: str | None = None
+
+    def __str__(self) -> str:
+        if self._cached is None:
+            try:
+                from hermes_cli.skin_engine import get_active_skin
+                self._cached = _hex_to_ansi_bold(
+                    get_active_skin().get_color(self._skin_key, self._fallback_hex)
+                )
+            except Exception:
+                self._cached = _hex_to_ansi_bold(self._fallback_hex)
+        return self._cached
+
+    def __add__(self, other: str) -> str:
+        return str(self) + other
+
+    def __radd__(self, other: str) -> str:
+        return other + str(self)
+
+    def reset(self) -> None:
+        """Clear cache so the next access re-reads the skin."""
+        self._cached = None
+
+
+_ACCENT = _SkinAwareAnsi("response_border", "#FFD700")
+
+
 def _accent_hex() -> str:
     """Return the active skin accent color for legacy CLI output lines."""
     try:
@@ -1122,6 +1171,45 @@ def _resolve_attachment_path(raw_path: str) -> Path | None:
     return resolved
 
 
+def _format_process_notification(evt: dict) -> "str | None":
+    """Format a process notification event into a [SYSTEM: ...] message.
+
+    Handles both completion events (notify_on_complete) and watch pattern
+    match events from the unified completion_queue.
+    """
+    evt_type = evt.get("type", "completion")
+    _sid = evt.get("session_id", "unknown")
+    _cmd = evt.get("command", "unknown")
+
+    if evt_type == "watch_disabled":
+        return f"[SYSTEM: {evt.get('message', '')}]"
+
+    if evt_type == "watch_match":
+        _pat = evt.get("pattern", "?")
+        _out = evt.get("output", "")
+        _sup = evt.get("suppressed", 0)
+        text = (
+            f"[SYSTEM: Background process {_sid} matched "
+            f"watch pattern \"{_pat}\".\n"
+            f"Command: {_cmd}\n"
+            f"Matched output:\n{_out}"
+        )
+        if _sup:
+            text += f"\n({_sup} earlier matches were suppressed by rate limit)"
+        text += "]"
+        return text
+
+    # Default: completion event
+    _exit = evt.get("exit_code", "?")
+    _out = evt.get("output", "")
+    return (
+        f"[SYSTEM: Background process {_sid} completed "
+        f"(exit code {_exit}).\n"
+        f"Command: {_cmd}\n"
+        f"Output:\n{_out}]"
+    )
+
+
 def _detect_file_drop(user_input: str) -> "dict | None":
     """Detect if *user_input* starts with a real local file path.
 
@@ -2466,7 +2554,7 @@ class HermesCLI:
                 self._stream_text_ansi = ""
             w = shutil.get_terminal_size().columns
             fill = w - 2 - len(label)
-            _cprint(f"\n{_GOLD}╭─{label}{'─' * max(fill - 1, 0)}╮{_RST}")
+            _cprint(f"\n{_ACCENT}╭─{label}{'─' * max(fill - 1, 0)}╮{_RST}")
 
         self._stream_buf += text
 
@@ -2497,7 +2585,7 @@ class HermesCLI:
         # Close the response box
         if self._stream_box_opened:
             w = shutil.get_terminal_size().columns
-            _cprint(f"{_GOLD}╰{'─' * (w - 2)}╯{_RST}")
+            _cprint(f"{_ACCENT}╰{'─' * (w - 2)}╯{_RST}")
 
     def _reset_stream_state(self) -> None:
         """Reset streaming state before each agent invocation."""
@@ -2920,15 +3008,17 @@ class HermesCLI:
             title_part = ""
             if session_meta.get("title"):
                 title_part = f' "{session_meta["title"]}"'
+            accent_color = _accent_hex()
             self.console.print(
-                f"[#DAA520]↻ Resumed session [bold]{self.session_id}[/bold]"
+                f"[{accent_color}]↻ Resumed session [bold]{self.session_id}[/bold]"
                 f"{title_part} "
                 f"({msg_count} user message{'s' if msg_count != 1 else ''}, "
                 f"{len(restored)} total messages)[/]"
             )
         else:
+            accent_color = _accent_hex()
             self.console.print(
-                f"[#DAA520]Session {self.session_id} found but has no "
+                f"[{accent_color}]Session {self.session_id} found but has no "
                 f"messages. Starting fresh.[/]"
             )
             return False
@@ -3397,18 +3487,26 @@ class HermesCLI:
         else:
             api_indicator = "[red bold]●[/]"
 
-        # Build status line with proper markup
+        # Build status line with proper markup — skin-aware colors
+        try:
+            from hermes_cli.skin_engine import get_active_skin
+            skin = get_active_skin()
+            separator_color = skin.get_color("banner_dim", "#B8860B")
+            accent_color = skin.get_color("ui_accent", "#FFBF00")
+            label_color = skin.get_color("ui_label", "#4dd0e1")
+        except Exception:
+            separator_color, accent_color, label_color = "#B8860B", "#FFBF00", "cyan"
         toolsets_info = ""
         if self.enabled_toolsets and "all" not in self.enabled_toolsets:
-            toolsets_info = f" [dim #B8860B]·[/] [#CD7F32]toolsets: {', '.join(self.enabled_toolsets)}[/]"
+            toolsets_info = f" [dim {separator_color}]·[/] [{label_color}]toolsets: {', '.join(self.enabled_toolsets)}[/]"
 
-        provider_info = f" [dim #B8860B]·[/] [dim]provider: {self.provider}[/]"
+        provider_info = f" [dim {separator_color}]·[/] [dim]provider: {self.provider}[/]"
         if self._provider_source:
-            provider_info += f" [dim #B8860B]·[/] [dim]auth: {self._provider_source}[/]"
+            provider_info += f" [dim {separator_color}]·[/] [dim]auth: {self._provider_source}[/]"
 
         self.console.print(
-            f"  {api_indicator} [#FFBF00]{model_short}[/] "
-            f"[dim #B8860B]·[/] [bold cyan]{tool_count} tools[/]"
+            f"  {api_indicator} [{accent_color}]{model_short}[/] "
+            f"[dim {separator_color}]·[/] [bold {label_color}]{tool_count} tools[/]"
             f"{toolsets_info}{provider_info}"
         )
 
@@ -3599,7 +3697,7 @@ class HermesCLI:
         # TUI event loop (known pitfall).
         verb = "Disabling" if subcommand == "disable" else "Enabling"
         label = ", ".join(names)
-        _cprint(f"{_GOLD}{verb} {label}...{_RST}")
+        _cprint(f"{_ACCENT}{verb} {label}...{_RST}")
 
         tools_disable_enable_command(
             Namespace(tools_action=subcommand, names=names, platform="cli"))
@@ -5112,17 +5210,17 @@ class HermesCLI:
                     if full_name == typed_base:
                         # Already an exact token — no expansion possible; fall through
                         _cprint(f"\033[1;31mUnknown command: {cmd_lower}{_RST}")
-                        _cprint(f"{_DIM}{_GOLD}Type /help for available commands{_RST}")
+                        _cprint(f"{_DIM}{_ACCENT}Type /help for available commands{_RST}")
                     else:
                         remainder = cmd_original.strip()[len(typed_base):]
                         full_cmd = full_name + remainder
                         return self.process_command(full_cmd)
                 elif len(matches) > 1:
-                    _cprint(f"{_GOLD}Ambiguous command: {cmd_lower}{_RST}")
+                    _cprint(f"{_ACCENT}Ambiguous command: {cmd_lower}{_RST}")
                     _cprint(f"{_DIM}Did you mean: {', '.join(sorted(matches))}?{_RST}")
                 else:
                     _cprint(f"\033[1;31mUnknown command: {cmd_lower}{_RST}")
-                    _cprint(f"{_DIM}{_GOLD}Type /help for available commands{_RST}")
+                    _cprint(f"{_DIM}{_ACCENT}Type /help for available commands{_RST}")
         
         return True
     
@@ -5660,6 +5758,7 @@ class HermesCLI:
             return
 
         set_active_skin(new_skin)
+        _ACCENT.reset()  # Re-resolve ANSI color for the new skin
         if save_config_value("display.skin", new_skin):
             print(f"  Skin set to: {new_skin} (saved)")
         else:
@@ -5728,8 +5827,8 @@ class HermesCLI:
             else:
                 level = rc.get("effort", "medium")
             display_state = "on ✓" if self.show_reasoning else "off"
-            _cprint(f"  {_GOLD}Reasoning effort:  {level}{_RST}")
-            _cprint(f"  {_GOLD}Reasoning display: {display_state}{_RST}")
+            _cprint(f"  {_ACCENT}Reasoning effort:  {level}{_RST}")
+            _cprint(f"  {_ACCENT}Reasoning display: {display_state}{_RST}")
             _cprint(f"  {_DIM}Usage: /reasoning <none|minimal|low|medium|high|xhigh|show|hide>{_RST}")
             return
 
@@ -5741,7 +5840,7 @@ class HermesCLI:
             if self.agent:
                 self.agent.reasoning_callback = self._current_reasoning_callback()
             save_config_value("display.show_reasoning", True)
-            _cprint(f"  {_GOLD}✓ Reasoning display: ON (saved){_RST}")
+            _cprint(f"  {_ACCENT}✓ Reasoning display: ON (saved){_RST}")
             _cprint(f"  {_DIM}  Model thinking will be shown during and after each response.{_RST}")
             return
         if arg in ("hide", "off"):
@@ -5749,7 +5848,7 @@ class HermesCLI:
             if self.agent:
                 self.agent.reasoning_callback = self._current_reasoning_callback()
             save_config_value("display.show_reasoning", False)
-            _cprint(f"  {_GOLD}✓ Reasoning display: OFF (saved){_RST}")
+            _cprint(f"  {_ACCENT}✓ Reasoning display: OFF (saved){_RST}")
             return
 
         # Effort level change
@@ -5764,9 +5863,9 @@ class HermesCLI:
         self.agent = None  # Force agent re-init with new reasoning config
 
         if save_config_value("agent.reasoning_effort", arg):
-            _cprint(f"  {_GOLD}✓ Reasoning effort set to '{arg}' (saved to config){_RST}")
+            _cprint(f"  {_ACCENT}✓ Reasoning effort set to '{arg}' (saved to config){_RST}")
         else:
-            _cprint(f"  {_GOLD}✓ Reasoning effort set to '{arg}' (session only){_RST}")
+            _cprint(f"  {_ACCENT}✓ Reasoning effort set to '{arg}' (session only){_RST}")
 
     def _handle_fast_command(self, cmd: str):
         """Handle /fast — toggle fast mode (OpenAI Priority Processing / Anthropic Fast Mode)."""
@@ -5786,7 +5885,7 @@ class HermesCLI:
         parts = cmd.strip().split(maxsplit=1)
         if len(parts) < 2 or parts[1].strip().lower() == "status":
             status = "fast" if self.service_tier == "priority" else "normal"
-            _cprint(f"  {_GOLD}{feature_name}: {status}{_RST}")
+            _cprint(f"  {_ACCENT}{feature_name}: {status}{_RST}")
             _cprint(f"  {_DIM}Usage: /fast [normal|fast|status]{_RST}")
             return
 
@@ -5807,9 +5906,9 @@ class HermesCLI:
 
         self.agent = None  # Force agent re-init with new service-tier config
         if save_config_value("agent.service_tier", saved_value):
-            _cprint(f"  {_GOLD}✓ {feature_name} set to {label} (saved to config){_RST}")
+            _cprint(f"  {_ACCENT}✓ {feature_name} set to {label} (saved to config){_RST}")
         else:
-            _cprint(f"  {_GOLD}✓ {feature_name} set to {label} (session only){_RST}")
+            _cprint(f"  {_ACCENT}✓ {feature_name} set to {label} (session only){_RST}")
 
     def _on_reasoning(self, reasoning_text: str):
         """Callback for intermediate reasoning display during tool-call loops."""
@@ -5835,21 +5934,29 @@ class HermesCLI:
         original_count = len(self.conversation_history)
         try:
             from agent.model_metadata import estimate_messages_tokens_rough
-            approx_tokens = estimate_messages_tokens_rough(self.conversation_history)
+            from agent.manual_compression_feedback import summarize_manual_compression
+            original_history = list(self.conversation_history)
+            approx_tokens = estimate_messages_tokens_rough(original_history)
             print(f"🗜️  Compressing {original_count} messages (~{approx_tokens:,} tokens)...")
 
-            compressed, _new_system = self.agent._compress_context(
-                self.conversation_history,
+            compressed, _ = self.agent._compress_context(
+                original_history,
                 self.agent._cached_system_prompt or "",
                 approx_tokens=approx_tokens,
             )
             self.conversation_history = compressed
-            new_count = len(self.conversation_history)
             new_tokens = estimate_messages_tokens_rough(self.conversation_history)
-            print(
-                f"  ✅ Compressed: {original_count} → {new_count} messages "
-                f"(~{approx_tokens:,} → ~{new_tokens:,} tokens)"
+            summary = summarize_manual_compression(
+                original_history,
+                self.conversation_history,
+                approx_tokens,
+                new_tokens,
             )
+            icon = "🗜️" if summary["noop"] else "✅"
+            print(f"  {icon} {summary['headline']}")
+            print(f"     {summary['token_line']}")
+            if summary["note"]:
+                print(f"     {summary['note']}")
 
         except Exception as e:
             print(f"  ❌ Compression failed: {e}")
@@ -6301,7 +6408,7 @@ class HermesCLI:
             _recording_hint = "Termux:API capture | Ctrl+B to stop"
         else:
             _recording_hint = "Ctrl+B to stop"
-        _cprint(f"\n{_GOLD}● Recording...{_RST} {_DIM}({_recording_hint}){_RST}")
+        _cprint(f"\n{_ACCENT}● Recording...{_RST} {_DIM}({_recording_hint}){_RST}")
 
         # Periodically refresh prompt to update audio level indicator
         def _refresh_level():
@@ -6501,14 +6608,14 @@ class HermesCLI:
         # Environment detection -- warn and block in incompatible environments
         env_check = detect_audio_environment()
         if not env_check["available"]:
-            _cprint(f"\n{_GOLD}Voice mode unavailable in this environment:{_RST}")
+            _cprint(f"\n{_ACCENT}Voice mode unavailable in this environment:{_RST}")
             for warning in env_check["warnings"]:
                 _cprint(f"  {_DIM}{warning}{_RST}")
             return
 
         reqs = check_voice_requirements()
         if not reqs["available"]:
-            _cprint(f"\n{_GOLD}Voice mode requirements not met:{_RST}")
+            _cprint(f"\n{_ACCENT}Voice mode requirements not met:{_RST}")
             for line in reqs["details"].split("\n"):
                 _cprint(f"  {_DIM}{line}{_RST}")
             if reqs["missing_packages"]:
@@ -6546,7 +6653,7 @@ class HermesCLI:
         except Exception:
             _ptt_key = "c-b"
         _ptt_display = _ptt_key.replace("c-", "Ctrl+").upper()
-        _cprint(f"\n{_GOLD}Voice mode enabled{tts_status}{_RST}")
+        _cprint(f"\n{_ACCENT}Voice mode enabled{tts_status}{_RST}")
         _cprint(f"  {_DIM}{_ptt_display} to start/stop recording{_RST}")
         _cprint(f"  {_DIM}/voice tts  to toggle speech output{_RST}")
         _cprint(f"  {_DIM}/voice off  to disable voice mode{_RST}")
@@ -6598,7 +6705,7 @@ class HermesCLI:
             if not check_tts_requirements():
                 _cprint(f"{_DIM}Warning: No TTS provider available. Install edge-tts or set API keys.{_RST}")
 
-        _cprint(f"{_GOLD}Voice TTS {status}.{_RST}")
+        _cprint(f"{_ACCENT}Voice TTS {status}.{_RST}")
 
     def _show_voice_status(self):
         """Show current voice mode status."""
@@ -7083,7 +7190,7 @@ class HermesCLI:
                         w = self.console.width
                         label = " ⚕ Hermes "
                         fill = w - 2 - len(label)
-                        _cprint(f"\n{_GOLD}╭─{label}{'─' * max(fill - 1, 0)}╮{_RST}")
+                        _cprint(f"\n{_ACCENT}╭─{label}{'─' * max(fill - 1, 0)}╮{_RST}")
                     _cprint(sentence.rstrip())
 
                 tts_thread = threading.Thread(
@@ -7299,7 +7406,7 @@ class HermesCLI:
                 if use_streaming_tts and _streaming_box_opened and not is_error_response:
                     # Text was already printed sentence-by-sentence; just close the box
                     w = shutil.get_terminal_size().columns
-                    _cprint(f"\n{_GOLD}╰{'─' * (w - 2)}╯{_RST}")
+                    _cprint(f"\n{_ACCENT}╰{'─' * (w - 2)}╯{_RST}")
                 elif already_streamed:
                     # Response was already streamed token-by-token with box framing;
                     # _flush_stream() already closed the box. Skip Rich Panel.
@@ -8802,23 +8909,15 @@ class HermesCLI:
                         # Periodic config watcher — auto-reload MCP on mcp_servers change
                         if not self._agent_running:
                             self._check_config_mcp_changes()
-                            # Check for background process completion notifications
-                            # while the agent is idle (user hasn't typed anything yet).
+                            # Check for background process notifications (completions
+                            # and watch pattern matches) while agent is idle.
                             try:
                                 from tools.process_registry import process_registry
                                 if not process_registry.completion_queue.empty():
-                                    completion = process_registry.completion_queue.get_nowait()
-                                    _exit = completion.get("exit_code", "?")
-                                    _cmd = completion.get("command", "unknown")
-                                    _sid = completion.get("session_id", "unknown")
-                                    _out = completion.get("output", "")
-                                    _synth = (
-                                        f"[SYSTEM: Background process {_sid} completed "
-                                        f"(exit code {_exit}).\n"
-                                        f"Command: {_cmd}\n"
-                                        f"Output:\n{_out}]"
-                                    )
-                                    self._pending_input.put(_synth)
+                                    evt = process_registry.completion_queue.get_nowait()
+                                    _synth = _format_process_notification(evt)
+                                    if _synth:
+                                        self._pending_input.put(_synth)
                             except Exception:
                                 pass
                         continue
@@ -8936,25 +9035,15 @@ class HermesCLI:
                                     _cprint(f"{_DIM}Voice auto-restart failed: {e}{_RST}")
                             threading.Thread(target=_restart_recording, daemon=True).start()
 
-                        # Drain process completion notifications — any background
-                        # process that finished with notify_on_complete while the
-                        # agent was running (or before) gets auto-injected as a
-                        # new user message so the agent can react to it.
+                        # Drain process notifications (completions + watch matches)
+                        # that arrived while the agent was running.
                         try:
                             from tools.process_registry import process_registry
                             while not process_registry.completion_queue.empty():
-                                completion = process_registry.completion_queue.get_nowait()
-                                _exit = completion.get("exit_code", "?")
-                                _cmd = completion.get("command", "unknown")
-                                _sid = completion.get("session_id", "unknown")
-                                _out = completion.get("output", "")
-                                _synth = (
-                                    f"[SYSTEM: Background process {_sid} completed "
-                                    f"(exit code {_exit}).\n"
-                                    f"Command: {_cmd}\n"
-                                    f"Output:\n{_out}]"
-                                )
-                                self._pending_input.put(_synth)
+                                evt = process_registry.completion_queue.get_nowait()
+                                _synth = _format_process_notification(evt)
+                                if _synth:
+                                    self._pending_input.put(_synth)
                         except Exception:
                             pass  # Non-fatal — don't break the main loop
 

cron/scheduler.py

@@ -442,6 +442,14 @@ def _run_job_script(script_path: str) -> tuple[bool, str]:
         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:
@@ -450,13 +458,6 @@ 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:

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 `~/.moldbot`. 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`.

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)

gateway/config.py

@@ -190,7 +190,7 @@ 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
 
@@ -210,7 +210,7 @@ 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", " ▉"),
         )
@@ -1017,6 +1017,9 @@ def _apply_env_overrides(config: GatewayConfig) -> None:
         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(

gateway/platforms/api_server.py

@@ -644,15 +644,35 @@ class APIServerAdapter(BasePlatformAdapter):
                     _stream_q.put(delta)
 
             def _on_tool_progress(event_type, name, preview, args, **kwargs):
-                """Inject tool progress into the SSE stream for Open WebUI."""
+                """Send tool progress as a separate SSE event.
+
+                Previously, progress markers like ``⏰ list`` were injected
+                directly into ``delta.content``.  OpenAI-compatible frontends
+                (Open WebUI, LobeChat, …) store ``delta.content`` verbatim as
+                the assistant message and send it back on subsequent requests.
+                After enough turns the model learns to *emit* the markers as
+                plain text instead of issuing real tool calls — silently
+                hallucinating tool results.  See #6972.
+
+                The fix: push a tagged tuple ``("__tool_progress__", payload)``
+                onto the stream queue.  The SSE writer emits it as a custom
+                ``event: hermes.tool.progress`` line that compliant frontends
+                can render for UX but will *not* persist into conversation
+                history.  Clients that don't understand the custom event type
+                silently ignore it per the SSE specification.
+                """
                 if event_type != "tool.started":
-                    return  # Only show tool start events in chat stream
+                    return
                 if name.startswith("_"):
-                    return  # Skip internal events (_thinking)
+                    return
                 from agent.display import get_tool_emoji
                 emoji = get_tool_emoji(name)
                 label = preview or name
-                _stream_q.put(f"\n`{emoji} {label}`\n")
+                _stream_q.put(("__tool_progress__", {
+                    "tool": name,
+                    "emoji": emoji,
+                    "label": label,
+                }))
 
             # Start agent in background.  agent_ref is a mutable container
             # so the SSE writer can interrupt the agent on client disconnect.
@@ -763,6 +783,29 @@ class APIServerAdapter(BasePlatformAdapter):
             }
             await response.write(f"data: {json.dumps(role_chunk)}\n\n".encode())
 
+            # Helper — route a queue item to the correct SSE event.
+            async def _emit(item):
+                """Write a single queue item to the SSE stream.
+
+                Plain strings are sent as normal ``delta.content`` chunks.
+                Tagged tuples ``("__tool_progress__", payload)`` are sent
+                as a custom ``event: hermes.tool.progress`` SSE event so
+                frontends can display them without storing the markers in
+                conversation history.  See #6972.
+                """
+                if isinstance(item, tuple) and len(item) == 2 and item[0] == "__tool_progress__":
+                    event_data = json.dumps(item[1])
+                    await response.write(
+                        f"event: hermes.tool.progress\ndata: {event_data}\n\n".encode()
+                    )
+                else:
+                    content_chunk = {
+                        "id": completion_id, "object": "chat.completion.chunk",
+                        "created": created, "model": model,
+                        "choices": [{"index": 0, "delta": {"content": item}, "finish_reason": None}],
+                    }
+                    await response.write(f"data: {json.dumps(content_chunk)}\n\n".encode())
+
             # Stream content chunks as they arrive from the agent
             loop = asyncio.get_event_loop()
             while True:
@@ -776,12 +819,7 @@ class APIServerAdapter(BasePlatformAdapter):
                                 delta = stream_q.get_nowait()
                                 if delta is None:
                                     break
-                                content_chunk = {
-                                    "id": completion_id, "object": "chat.completion.chunk",
-                                    "created": created, "model": model,
-                                    "choices": [{"index": 0, "delta": {"content": delta}, "finish_reason": None}],
-                                }
-                                await response.write(f"data: {json.dumps(content_chunk)}\n\n".encode())
+                                await _emit(delta)
                             except _q.Empty:
                                 break
                         break
@@ -790,12 +828,7 @@ class APIServerAdapter(BasePlatformAdapter):
                 if delta is None:  # End of stream sentinel
                     break
 
-                content_chunk = {
-                    "id": completion_id, "object": "chat.completion.chunk",
-                    "created": created, "model": model,
-                    "choices": [{"index": 0, "delta": {"content": delta}, "finish_reason": None}],
-                }
-                await response.write(f"data: {json.dumps(content_chunk)}\n\n".encode())
+                await _emit(delta)
 
             # Get usage from completed agent
             usage = {"input_tokens": 0, "output_tokens": 0, "total_tokens": 0}

gateway/platforms/base.py

@@ -673,6 +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)
@@ -727,6 +753,7 @@ class BasePlatformAdapter(ABC):
         # 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).
@@ -815,6 +842,10 @@ class BasePlatformAdapter(ABC):
         an optional response string.
         """
         self._message_handler = handler
+
+    def set_busy_session_handler(self, handler: Optional[Callable[[MessageEvent, str], Awaitable[bool]]]) -> None:
+        """Set an optional handler for messages arriving during active sessions."""
+        self._busy_session_handler = handler
     
     def set_session_store(self, session_store: Any) -> None:
         """
@@ -1396,7 +1427,7 @@ class BasePlatformAdapter(ABC):
             # session lifecycle and its cleanup races with the running task
             # (see PR #4926).
             cmd = event.get_command()
-            if cmd in ("approve", "deny", "status", "stop", "new", "reset", "background"):
+            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,
@@ -1415,19 +1446,19 @@ class BasePlatformAdapter(ABC):
                     logger.error("[%s] Command '/%s' dispatch failed: %s", self.name, cmd, e, exc_info=True)
                 return
 
+            if self._busy_session_handler is not None:
+                try:
+                    if await self._busy_session_handler(event, session_key):
+                        return
+                except Exception as e:
+                    logger.error("[%s] Busy-session handler failed: %s", self.name, e, exc_info=True)
+
             # Special case: photo bursts/albums frequently arrive as multiple near-
             # simultaneous messages. Queue them without interrupting the active run,
             # then process them immediately after the current task finishes.
             if event.message_type == MessageType.PHOTO:
                 logger.debug("[%s] Queuing photo follow-up for session %s without interrupt", self.name, session_key)
-                existing = self._pending_messages.get(session_key)
-                if existing and existing.message_type == MessageType.PHOTO:
-                    existing.media_urls.extend(event.media_urls)
-                    existing.media_types.extend(event.media_types)
-                    if event.text:
-                        existing.text = self._merge_caption(existing.text, event.text)
-                else:
-                    self._pending_messages[session_key] = event
+                merge_pending_message_event(self._pending_messages, session_key, event)
                 return  # Don't interrupt now - will run after current task completes
 
             # Default behavior for non-photo follow-ups: interrupt the running agent

gateway/platforms/telegram.py

@@ -300,9 +300,11 @@ 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)

gateway/platforms/weixin.py

@@ -755,23 +755,58 @@ def _pack_markdown_blocks_for_weixin(content: str, max_length: int) -> List[str]
     return packed
 
 
-def _split_text_for_weixin_delivery(content: str, max_length: int) -> List[str]:
+def _split_text_for_weixin_delivery(
+    content: str, max_length: int, split_per_line: bool = False,
+) -> List[str]:
     """Split content into sequential Weixin messages.
 
-    Prefer one message per top-level line/markdown unit when the author used
-    explicit line breaks. Oversized units fall back to block-aware packing so
-    long code fences still split safely.
-    """
-    if len(content) <= max_length and "\n" not in content:
-        return [content]
+    *compact* (default): Keep everything in a single message whenever it fits
+    within the platform limit, even when the author used explicit line breaks.
+    Only fall back to block-aware packing when the payload exceeds
+    ``max_length``.
 
-    chunks: List[str] = []
-    for unit in _split_delivery_units_for_weixin(content):
-        if len(unit) <= max_length:
-            chunks.append(unit)
-            continue
-        chunks.extend(_pack_markdown_blocks_for_weixin(unit, max_length))
-    return chunks or [content]
+    *per_line* (``split_per_line=True``): Legacy behavior — top-level line
+    breaks become separate chat messages; oversized units still use
+    block-aware packing.
+
+    The active mode is controlled via ``config.yaml`` ->
+    ``platforms.weixin.extra.split_multiline_messages`` (``true`` / ``false``)
+    or the env var ``WEIXIN_SPLIT_MULTILINE_MESSAGES``.
+    """
+    if split_per_line:
+        # Legacy: one message per top-level delivery unit.
+        if len(content) <= max_length and "\n" not in content:
+            return [content]
+        chunks: List[str] = []
+        for unit in _split_delivery_units_for_weixin(content):
+            if len(unit) <= max_length:
+                chunks.append(unit)
+                continue
+            chunks.extend(_pack_markdown_blocks_for_weixin(unit, max_length))
+        return chunks or [content]
+
+    # Compact (default): single message when under the limit.
+    if len(content) <= max_length:
+        return [content]
+    return _pack_markdown_blocks_for_weixin(content, max_length) or [content]
+
+
+def _coerce_bool(value: Any, default: bool = True) -> bool:
+    """Coerce a config value to bool, tolerating strings like ``"true"``."""
+    if value is None:
+        return default
+    if isinstance(value, bool):
+        return value
+    if isinstance(value, (int, float)):
+        return bool(value)
+    text = str(value).strip().lower()
+    if not text:
+        return default
+    if text in {"1", "true", "yes", "on"}:
+        return True
+    if text in {"0", "false", "no", "off"}:
+        return False
+    return default
 
 
 def _extract_text(item_list: List[Dict[str, Any]]) -> str:
@@ -991,6 +1026,11 @@ class WeixinAdapter(BasePlatformAdapter):
             group_allow_from = os.getenv("WEIXIN_GROUP_ALLOWED_USERS", "")
         self._allow_from = self._coerce_list(allow_from)
         self._group_allow_from = self._coerce_list(group_allow_from)
+        self._split_multiline_messages = _coerce_bool(
+            extra.get("split_multiline_messages")
+            or os.getenv("WEIXIN_SPLIT_MULTILINE_MESSAGES"),
+            default=False,
+        )
 
         if self._account_id and not self._token:
             persisted = load_weixin_account(hermes_home, self._account_id)
@@ -1330,7 +1370,9 @@ class WeixinAdapter(BasePlatformAdapter):
             logger.debug("[%s] getConfig failed for %s: %s", self.name, _safe_id(user_id), exc)
 
     def _split_text(self, content: str) -> List[str]:
-        return _split_text_for_weixin_delivery(content, self.MAX_MESSAGE_LENGTH)
+        return _split_text_for_weixin_delivery(
+            content, self.MAX_MESSAGE_LENGTH, self._split_multiline_messages,
+        )
 
     async def send(
         self,
@@ -1344,7 +1386,10 @@ class WeixinAdapter(BasePlatformAdapter):
         context_token = self._token_store.get(self._account_id, chat_id)
         last_message_id: Optional[str] = None
         try:
-            for chunk in self._split_text(self.format_message(content)):
+            chunks = self._split_text(self.format_message(content))
+            for idx, chunk in enumerate(chunks):
+                if idx > 0:
+                    await asyncio.sleep(0.3)
                 client_id = f"hermes-weixin-{uuid.uuid4().hex}"
                 await _send_message(
                     self._session,

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/status.py

@@ -158,6 +158,8 @@ def _build_runtime_status_record() -> dict[str, Any]:
     payload.update({
         "gateway_state": "starting",
         "exit_reason": None,
+        "restart_requested": False,
+        "active_agents": 0,
         "platforms": {},
         "updated_at": _utc_now_iso(),
     })
@@ -218,6 +220,8 @@ def write_runtime_status(
     *,
     gateway_state: Optional[str] = None,
     exit_reason: Optional[str] = None,
+    restart_requested: Optional[bool] = None,
+    active_agents: Optional[int] = None,
     platform: Optional[str] = None,
     platform_state: Optional[str] = None,
     error_code: Optional[str] = None,
@@ -236,6 +240,10 @@ def write_runtime_status(
         payload["gateway_state"] = gateway_state
     if exit_reason is not None:
         payload["exit_reason"] = exit_reason
+    if restart_requested is not None:
+        payload["restart_requested"] = bool(restart_requested)
+    if active_agents is not None:
+        payload["active_agents"] = max(0, int(active_agents))
 
     if platform is not None:
         platform_payload = payload["platforms"].get(platform, {})

gateway/stream_consumer.py

@@ -36,7 +36,7 @@ _NEW_SEGMENT = 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 +56,10 @@ 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,
@@ -76,6 +80,8 @@ class GatewayStreamConsumer:
         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
 
     @property
     def already_sent(self) -> bool:
@@ -129,7 +135,7 @@ class GatewayStreamConsumer:
                 should_edit = (
                     got_done
                     or got_segment_break
-                    or (elapsed >= self.cfg.edit_interval
+                    or (elapsed >= self._current_edit_interval
                         and self._accumulated)
                     or len(self._accumulated) >= self.cfg.buffer_threshold
                 )
@@ -173,12 +179,13 @@ 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
@@ -322,7 +329,10 @@ 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
@@ -339,12 +349,25 @@ 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
@@ -370,20 +393,52 @@ class GatewayStreamConsumer:
         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_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,
@@ -393,19 +448,52 @@ 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(
@@ -417,6 +505,7 @@ class GatewayStreamConsumer:
                     self._message_id = result.message_id
                     self._already_sent = True
                     self._last_sent_text = text
+                    return True
                 elif result.success:
                     # Platform accepted the message but returned no message_id
                     # (e.g. Signal).  Can't edit without an ID — switch to
@@ -428,8 +517,11 @@ class GatewayStreamConsumer:
                     self._fallback_final_send = True
                     # Sentinel prevents re-entering this branch on every delta
                     self._message_id = "__no_edit__"
+                    return True  # platform accepted, just can't edit
                 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

@@ -250,6 +250,14 @@ 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",
+    ),
 }
 
 
@@ -908,6 +916,7 @@ 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

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
@@ -51,6 +52,57 @@ _OPENCLAW_SCRIPT_INSTALLED = (
 # Known OpenClaw directory names (current + legacy)
 _OPENCLAW_DIR_NAMES = (".openclaw", ".clawdbot", ".moldbot")
 
+_GATEWAY_STATE_FILE = "gateway_state.json"
+
+
+def _warn_if_gateway_running(hermes_home: Path, 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.
+    """
+    import json
+    state_path = hermes_home / _GATEWAY_STATE_FILE
+    if not state_path.exists():
+        return
+    try:
+        data = json.loads(state_path.read_text())
+    except (json.JSONDecodeError, OSError):
+        return
+
+    # Check if the gateway PID is still alive
+    pid = data.get("pid")
+    if not pid:
+        return
+    try:
+        import os
+        os.kill(int(pid), 0)
+    except (ProcessLookupError, PermissionError, ValueError, TypeError):
+        return  # stale state file, gateway not running
+
+    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 that cause
 # confusion after migration (the agent discovers them and writes to them)
 _WORKSPACE_STATE_GLOBS = (
@@ -237,12 +289,12 @@ 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 +303,85 @@ 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(hermes_home, 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,
@@ -292,11 +398,11 @@ 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))
+    # After successful migration, offer to archive the source directory
+    if report.get("summary", {}).get("migrated", 0) > 0:
+        _offer_source_archival(source_dir, auto_yes)
 
 
 def _offer_source_archival(source_dir: Path, auto_yes: bool = False):
@@ -330,6 +436,11 @@ def _offer_source_archival(source_dir: Path, auto_yes: bool = False):
     print_info("You can always rename it back if needed.")
     print()
 
+    if not auto_yes and not sys.stdin.isatty():
+        print_info("Non-interactive session — skipping archival.")
+        print_info("Run later with: hermes claw cleanup")
+        return
+
     if auto_yes or prompt_yes_no(f"Archive {source_dir} now?", default=True):
         try:
             archive_path = _archive_directory(source_dir)
@@ -433,6 +544,9 @@ 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/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

@@ -140,6 +140,8 @@ 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("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]"),

hermes_cli/config.py

@@ -32,7 +32,6 @@ _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",
@@ -269,6 +268,11 @@ 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.
@@ -376,7 +380,7 @@ 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": {
@@ -453,7 +457,7 @@ 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
@@ -467,6 +471,10 @@ 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)
@@ -504,6 +512,16 @@ 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,
@@ -528,6 +546,8 @@ 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
@@ -847,6 +867,21 @@ 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": {
@@ -999,6 +1034,13 @@ 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",
@@ -1450,7 +1492,7 @@ _KNOWN_ROOT_KEYS = {
     "_config_version", "model", "providers", "fallback_model",
     "fallback_providers", "credential_pool_strategies", "toolsets",
     "agent", "terminal", "display", "compression", "delegation",
-    "auxiliary", "custom_providers", "memory", "gateway",
+    "auxiliary", "custom_providers", "context", "memory", "gateway",
 }
 
 # Valid fields inside a custom_providers list entry
@@ -2773,6 +2815,10 @@ 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/curses_ui.py

@@ -160,6 +160,133 @@ def curses_checklist(
         return _numbered_fallback(title, items, selected, cancel_returns, status_fn)
 
 
+def curses_radiolist(
+    title: str,
+    items: List[str],
+    selected: int = 0,
+    *,
+    cancel_returns: int | None = None,
+) -> int:
+    """Curses single-select radio list. Returns the selected index.
+
+    Args:
+        title: Header line displayed above the list.
+        items: Display labels for each row.
+        selected: Index that starts selected (pre-selected).
+        cancel_returns: Returned on ESC/q. Defaults to the original *selected*.
+    """
+    if cancel_returns is None:
+        cancel_returns = selected
+
+    if not sys.stdin.isatty():
+        return cancel_returns
+
+    try:
+        import curses
+        result_holder: list = [None]
+
+        def _draw(stdscr):
+            curses.curs_set(0)
+            if curses.has_colors():
+                curses.start_color()
+                curses.use_default_colors()
+                curses.init_pair(1, curses.COLOR_GREEN, -1)
+                curses.init_pair(2, curses.COLOR_YELLOW, -1)
+            cursor = selected
+            scroll_offset = 0
+
+            while True:
+                stdscr.clear()
+                max_y, max_x = stdscr.getmaxyx()
+
+                # Header
+                try:
+                    hattr = curses.A_BOLD
+                    if curses.has_colors():
+                        hattr |= curses.color_pair(2)
+                    stdscr.addnstr(0, 0, title, max_x - 1, hattr)
+                    stdscr.addnstr(
+                        1, 0,
+                        "  \u2191\u2193 navigate  ENTER/SPACE select  ESC cancel",
+                        max_x - 1, curses.A_DIM,
+                    )
+                except curses.error:
+                    pass
+
+                # Scrollable item list
+                visible_rows = max_y - 4
+                if cursor < scroll_offset:
+                    scroll_offset = cursor
+                elif cursor >= scroll_offset + visible_rows:
+                    scroll_offset = cursor - visible_rows + 1
+
+                for draw_i, i in enumerate(
+                    range(scroll_offset, min(len(items), scroll_offset + visible_rows))
+                ):
+                    y = draw_i + 3
+                    if y >= max_y - 1:
+                        break
+                    radio = "\u25cf" if i == selected else "\u25cb"
+                    arrow = "\u2192" if i == cursor else " "
+                    line = f" {arrow} ({radio}) {items[i]}"
+                    attr = curses.A_NORMAL
+                    if i == cursor:
+                        attr = curses.A_BOLD
+                        if curses.has_colors():
+                            attr |= curses.color_pair(1)
+                    try:
+                        stdscr.addnstr(y, 0, line, max_x - 1, attr)
+                    except curses.error:
+                        pass
+
+                stdscr.refresh()
+                key = stdscr.getch()
+
+                if key in (curses.KEY_UP, ord("k")):
+                    cursor = (cursor - 1) % len(items)
+                elif key in (curses.KEY_DOWN, ord("j")):
+                    cursor = (cursor + 1) % len(items)
+                elif key in (ord(" "), curses.KEY_ENTER, 10, 13):
+                    result_holder[0] = cursor
+                    return
+                elif key in (27, ord("q")):
+                    result_holder[0] = cancel_returns
+                    return
+
+        curses.wrapper(_draw)
+        flush_stdin()
+        return result_holder[0] if result_holder[0] is not None else cancel_returns
+
+    except Exception:
+        return _radio_numbered_fallback(title, items, selected, cancel_returns)
+
+
+def _radio_numbered_fallback(
+    title: str,
+    items: List[str],
+    selected: int,
+    cancel_returns: int,
+) -> int:
+    """Text-based numbered fallback for radio selection."""
+    print(color(f"\n  {title}", Colors.YELLOW))
+    print(color("  Select by number, Enter to confirm.\n", Colors.DIM))
+
+    for i, label in enumerate(items):
+        marker = color("(\u25cf)", Colors.GREEN) if i == selected else "(\u25cb)"
+        print(f"  {marker} {i + 1:>2}. {label}")
+    print()
+    try:
+        val = input(color(f"  Choice [default {selected + 1}]: ", Colors.DIM)).strip()
+        if not val:
+            return selected
+        idx = int(val) - 1
+        if 0 <= idx < len(items):
+            return idx
+        return selected
+    except (ValueError, KeyboardInterrupt, EOFError):
+        return cancel_returns
+
+
 def _numbered_fallback(
     title: str,
     items: List[str],

hermes_cli/doctor.py

@@ -51,6 +51,7 @@ _PROVIDER_ENV_HINTS = (
     "AI_GATEWAY_API_KEY",
     "OPENCODE_ZEN_API_KEY",
     "OPENCODE_GO_API_KEY",
+    "XIAOMI_API_KEY",
 )
 
 
@@ -722,9 +723,9 @@ 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),
@@ -749,6 +750,11 @@ 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():

hermes_cli/gateway.py

@@ -15,7 +15,19 @@ from pathlib import Path
 PROJECT_ROOT = Path(__file__).parent.parent.resolve()
 
 from gateway.status import terminate_pid
-from hermes_cli.config import get_env_value, get_hermes_home, save_env_value, is_managed, managed_error
+from gateway.restart import (
+    DEFAULT_GATEWAY_RESTART_DRAIN_TIMEOUT,
+    GATEWAY_SERVICE_RESTART_EXIT_CODE,
+    parse_restart_drain_timeout,
+)
+from hermes_cli.config import (
+    get_env_value,
+    get_hermes_home,
+    is_managed,
+    managed_error,
+    read_raw_config,
+    save_env_value,
+)
 # display_hermes_home is imported lazily at call sites to avoid ImportError
 # when hermes_constants is cached from a pre-update version during `hermes update`.
 from hermes_cli.setup import (
@@ -92,6 +104,59 @@ def _get_service_pids() -> set:
     return pids
 
 
+def _get_parent_pid(pid: int) -> int | None:
+    """Return the parent PID for ``pid``, or ``None`` when unavailable."""
+    if pid <= 1:
+        return None
+    try:
+        result = subprocess.run(
+            ["ps", "-o", "ppid=", "-p", str(pid)],
+            capture_output=True,
+            text=True,
+            timeout=5,
+        )
+    except (FileNotFoundError, subprocess.TimeoutExpired):
+        return None
+    if result.returncode != 0:
+        return None
+    raw = result.stdout.strip()
+    if not raw:
+        return None
+    try:
+        parent_pid = int(raw.splitlines()[-1].strip())
+    except ValueError:
+        return None
+    return parent_pid if parent_pid > 0 else None
+
+
+def _is_pid_ancestor_of_current_process(target_pid: int) -> bool:
+    """Return True when ``target_pid`` is this process or one of its ancestors."""
+    if target_pid <= 0:
+        return False
+
+    pid = os.getpid()
+    seen: set[int] = set()
+    while pid and pid not in seen:
+        if pid == target_pid:
+            return True
+        seen.add(pid)
+        pid = _get_parent_pid(pid) or 0
+    return False
+
+
+def _request_gateway_self_restart(pid: int) -> bool:
+    """Ask a running gateway ancestor to restart itself asynchronously."""
+    if not hasattr(signal, "SIGUSR1"):
+        return False
+    if not _is_pid_ancestor_of_current_process(pid):
+        return False
+    try:
+        os.kill(pid, signal.SIGUSR1)
+    except (ProcessLookupError, PermissionError, OSError):
+        return False
+    return True
+
+
 def find_gateway_pids(exclude_pids: set | None = None) -> list:
     """Find PIDs of running gateway processes.
 
@@ -226,11 +291,33 @@ def is_linux() -> bool:
     return sys.platform.startswith('linux')
 
 
-from hermes_constants import is_termux
+from hermes_constants import is_termux, is_wsl
+
+
+def _wsl_systemd_operational() -> bool:
+    """Check if systemd is actually running as PID 1 on WSL.
+
+    WSL2 with ``systemd=true`` in wsl.conf has working systemd.
+    WSL2 without it (or WSL1) does not — systemctl commands fail.
+    """
+    try:
+        result = subprocess.run(
+            ["systemctl", "is-system-running"],
+            capture_output=True, text=True, timeout=5,
+        )
+        # "running", "degraded", "starting" all mean systemd is PID 1
+        status = result.stdout.strip().lower()
+        return status in ("running", "degraded", "starting", "initializing")
+    except (FileNotFoundError, subprocess.TimeoutExpired, OSError):
+        return False
 
 
 def supports_systemd_services() -> bool:
-    return is_linux() and not is_termux()
+    if not is_linux() or is_termux():
+        return False
+    if is_wsl():
+        return _wsl_systemd_operational()
+    return True
 
 
 def is_macos() -> bool:
@@ -665,6 +752,7 @@ def generate_systemd_unit(system: bool = False, run_as_user: str | None = None)
             path_entries.append(resolved_node_dir)
 
     common_bin_paths = ["/usr/local/sbin", "/usr/local/bin", "/usr/sbin", "/usr/bin", "/sbin", "/bin"]
+    restart_timeout = max(60, int(_get_restart_drain_timeout() or 0))
 
     if system:
         username, group_name, home_dir = _system_service_identity(run_as_user)
@@ -703,9 +791,11 @@ Environment="VIRTUAL_ENV={venv_dir}"
 Environment="HERMES_HOME={hermes_home}"
 Restart=on-failure
 RestartSec=30
+RestartForceExitStatus={GATEWAY_SERVICE_RESTART_EXIT_CODE}
 KillMode=mixed
 KillSignal=SIGTERM
-TimeoutStopSec=60
+ExecReload=/bin/kill -USR1 $MAINPID
+TimeoutStopSec={restart_timeout}
 StandardOutput=journal
 StandardError=journal
 
@@ -733,9 +823,11 @@ Environment="VIRTUAL_ENV={venv_dir}"
 Environment="HERMES_HOME={hermes_home}"
 Restart=on-failure
 RestartSec=30
+RestartForceExitStatus={GATEWAY_SERVICE_RESTART_EXIT_CODE}
 KillMode=mixed
 KillSignal=SIGTERM
-TimeoutStopSec=60
+ExecReload=/bin/kill -USR1 $MAINPID
+TimeoutStopSec={restart_timeout}
 StandardOutput=journal
 StandardError=journal
 
@@ -838,6 +930,20 @@ def _select_systemd_scope(system: bool = False) -> bool:
     return get_systemd_unit_path(system=True).exists() and not get_systemd_unit_path(system=False).exists()
 
 
+def _get_restart_drain_timeout() -> float:
+    """Return the configured gateway restart drain timeout in seconds."""
+    raw = os.getenv("HERMES_RESTART_DRAIN_TIMEOUT", "").strip()
+    if not raw:
+        cfg = read_raw_config()
+        agent_cfg = cfg.get("agent", {}) if isinstance(cfg, dict) else {}
+        raw = str(
+            agent_cfg.get(
+                "restart_drain_timeout", DEFAULT_GATEWAY_RESTART_DRAIN_TIMEOUT
+            )
+        )
+    return parse_restart_drain_timeout(raw)
+
+
 def systemd_install(force: bool = False, system: bool = False, run_as_user: str | None = None):
     if system:
         _require_root_for_system_service("install")
@@ -923,7 +1029,13 @@ def systemd_restart(system: bool = False):
     if system:
         _require_root_for_system_service("restart")
     refresh_systemd_unit_if_needed(system=system)
-    subprocess.run(_systemctl_cmd(system) + ["restart", get_service_name()], check=True, timeout=90)
+    from gateway.status import get_running_pid
+
+    pid = get_running_pid()
+    if pid is not None and _request_gateway_self_restart(pid):
+        print(f"✓ {_service_scope_label(system).capitalize()} service restart requested")
+        return
+    subprocess.run(_systemctl_cmd(system) + ["reload-or-restart", get_service_name()], check=True, timeout=90)
     print(f"✓ {_service_scope_label(system).capitalize()} service restarted")
 
 
@@ -1211,7 +1323,7 @@ def launchd_stop():
     _wait_for_gateway_exit(timeout=10.0, force_after=5.0)
     print("✓ Service stopped")
 
-def _wait_for_gateway_exit(timeout: float = 10.0, force_after: float = 5.0):
+def _wait_for_gateway_exit(timeout: float = 10.0, force_after: float | None = 5.0) -> bool:
     """Wait for the gateway process (by saved PID) to exit.
 
     Uses the PID from the gateway.pid file — not launchd labels — so this
@@ -1226,21 +1338,21 @@ def _wait_for_gateway_exit(timeout: float = 10.0, force_after: float = 5.0):
     from gateway.status import get_running_pid
 
     deadline = time.monotonic() + timeout
-    force_deadline = time.monotonic() + force_after
+    force_deadline = (time.monotonic() + force_after) if force_after is not None else None
     force_sent = False
 
     while time.monotonic() < deadline:
         pid = get_running_pid()
         if pid is None:
-            return  # Process exited cleanly.
+            return True  # Process exited cleanly.
 
-        if not force_sent and time.monotonic() >= force_deadline:
+        if force_after is not None and not force_sent and time.monotonic() >= force_deadline:
             # Grace period expired — force-kill the specific PID.
             try:
                 terminate_pid(pid, force=True)
                 print(f"⚠ Gateway PID {pid} did not exit gracefully; sent SIGKILL")
             except (ProcessLookupError, PermissionError, OSError):
-                return  # Already gone or we can't touch it.
+                return True  # Already gone or we can't touch it.
             force_sent = True
 
         time.sleep(0.3)
@@ -1249,15 +1361,30 @@ def _wait_for_gateway_exit(timeout: float = 10.0, force_after: float = 5.0):
     remaining_pid = get_running_pid()
     if remaining_pid is not None:
         print(f"⚠ Gateway PID {remaining_pid} still running after {timeout}s — restart may fail")
+        return False
+    return True
 
 
 def launchd_restart():
     label = get_launchd_label()
     target = f"{_launchd_domain()}/{label}"
-    # Use kickstart -k so launchd performs an atomic kill+restart.
-    # A two-step stop/start from inside the gateway's own process tree
-    # would kill the shell before the start command is reached.
+    drain_timeout = _get_restart_drain_timeout()
+    from gateway.status import get_running_pid
+
     try:
+        pid = get_running_pid()
+        if pid is not None and _request_gateway_self_restart(pid):
+            print("✓ Service restart requested")
+            return
+        if pid is not None:
+            try:
+                terminate_pid(pid, force=False)
+            except (ProcessLookupError, PermissionError, OSError):
+                pid = None
+            if pid is not None:
+                exited = _wait_for_gateway_exit(timeout=drain_timeout, force_after=None)
+                if not exited:
+                    print(f"⚠ Gateway drain timed out after {drain_timeout:.0f}s — forcing launchd restart")
         subprocess.run(["launchctl", "kickstart", "-k", target], check=True, timeout=90)
         print("✓ Service restarted")
     except subprocess.CalledProcessError as e:
@@ -1442,7 +1569,7 @@ _PLATFORMS = [
             "   Or via API: curl -X POST https://your-server/_matrix/client/v3/login \\",
             "     -d '{\"type\":\"m.login.password\",\"user\":\"@bot:server\",\"password\":\"...\"}'",
             "4. Alternatively, provide user ID + password and Hermes will log in directly",
-            "5. For E2EE: set MATRIX_ENCRYPTION=true (requires pip install 'matrix-nio[e2e]')",
+            "5. For E2EE: set MATRIX_ENCRYPTION=true (requires pip install 'mautrix[encryption]')",
             "6. To find your user ID: it's @username:your-server (shown in Element profile)",
         ],
         "vars": [
@@ -1728,6 +1855,8 @@ def _runtime_health_lines() -> list[str]:
     lines: list[str] = []
     gateway_state = state.get("gateway_state")
     exit_reason = state.get("exit_reason")
+    active_agents = state.get("active_agents")
+    restart_requested = state.get("restart_requested")
     platforms = state.get("platforms", {}) or {}
 
     for platform, pdata in platforms.items():
@@ -1737,6 +1866,10 @@ def _runtime_health_lines() -> list[str]:
 
     if gateway_state == "startup_failed" and exit_reason:
         lines.append(f"⚠ Last startup issue: {exit_reason}")
+    elif gateway_state == "draining":
+        action = "restart" if restart_requested else "shutdown"
+        count = int(active_agents or 0)
+        lines.append(f"⏳ Gateway draining for {action} ({count} active agent(s))")
     elif gateway_state == "stopped" and exit_reason:
         lines.append(f"⚠ Last shutdown reason: {exit_reason}")
 
@@ -2244,7 +2377,8 @@ def gateway_setup():
             print()
             if supports_systemd_services() or is_macos():
                 platform_name = "systemd" if supports_systemd_services() else "launchd"
-                if prompt_yes_no(f"  Install the gateway as a {platform_name} service? (runs in background, starts on boot)", True):
+                wsl_note = " (note: services may not survive WSL restarts)" if is_wsl() else ""
+                if prompt_yes_no(f"  Install the gateway as a {platform_name} service?{wsl_note} (runs in background, starts on boot)", True):
                     try:
                         installed_scope = None
                         did_install = False
@@ -2269,16 +2403,21 @@ def gateway_setup():
                     print_info("  You can install later: hermes gateway install")
                     if supports_systemd_services():
                         print_info("  Or as a boot-time service: sudo hermes gateway install --system")
-                    print_info("  Or run in foreground:  hermes gateway")
+                    print_info("  Or run in foreground:  hermes gateway run")
+            elif is_wsl():
+                print_info("  WSL detected but systemd is not running.")
+                print_info("  Run in foreground: hermes gateway run")
+                print_info("  For persistence:   tmux new -s hermes 'hermes gateway run'")
+                print_info("  To enable systemd: add systemd=true to /etc/wsl.conf, then 'wsl --shutdown'")
             else:
                 if is_termux():
                     from hermes_constants import display_hermes_home as _dhh
                     print_info("  Termux does not use systemd/launchd services.")
-                    print_info("  Run in foreground: hermes gateway")
-                    print_info(f"  Or start it manually in the background (best effort): nohup hermes gateway >{_dhh()}/logs/gateway.log 2>&1 &")
+                    print_info("  Run in foreground: hermes gateway run")
+                    print_info(f"  Or start it manually in the background (best effort): nohup hermes gateway run >{_dhh()}/logs/gateway.log 2>&1 &")
                 else:
                     print_info("  Service install not supported on this platform.")
-                    print_info("  Run in foreground: hermes gateway")
+                    print_info("  Run in foreground: hermes gateway run")
     else:
         print()
         print_info("No platforms configured. Run 'hermes gateway setup' when ready.")
@@ -2319,9 +2458,23 @@ def gateway_command(args):
             print("Run manually: hermes gateway")
             sys.exit(1)
         if supports_systemd_services():
+            if is_wsl():
+                print_warning("WSL detected — systemd services may not survive WSL restarts.")
+                print_info("  Consider running in foreground instead: hermes gateway run")
+                print_info("  Or use tmux/screen for persistence: tmux new -s hermes 'hermes gateway run'")
+                print()
             systemd_install(force=force, system=system, run_as_user=run_as_user)
         elif is_macos():
             launchd_install(force)
+        elif is_wsl():
+            print("WSL detected but systemd is not running.")
+            print("Either enable systemd (add systemd=true to /etc/wsl.conf and restart WSL)")
+            print("or run the gateway in foreground mode:")
+            print()
+            print("  hermes gateway run                              # direct foreground")
+            print("  tmux new -s hermes 'hermes gateway run'         # persistent via tmux")
+            print("  nohup hermes gateway run > ~/.hermes/logs/gateway.log 2>&1 &  # background")
+            sys.exit(1)
         else:
             print("Service installation not supported on this platform.")
             print("Run manually: hermes gateway run")
@@ -2354,6 +2507,16 @@ def gateway_command(args):
             systemd_start(system=system)
         elif is_macos():
             launchd_start()
+        elif is_wsl():
+            print("WSL detected but systemd is not available.")
+            print("Run the gateway in foreground mode instead:")
+            print()
+            print("  hermes gateway run                              # direct foreground")
+            print("  tmux new -s hermes 'hermes gateway run'         # persistent via tmux")
+            print("  nohup hermes gateway run > ~/.hermes/logs/gateway.log 2>&1 &  # background")
+            print()
+            print("To enable systemd: add systemd=true to /etc/wsl.conf and run 'wsl --shutdown' from PowerShell.")
+            sys.exit(1)
         else:
             print("Not supported on this platform.")
             sys.exit(1)
@@ -2488,6 +2651,10 @@ def gateway_command(args):
                 if is_termux():
                     print("Termux note:")
                     print("  Android may stop background jobs when Termux is suspended")
+                elif is_wsl():
+                    print("WSL note:")
+                    print("  The gateway is running in foreground/manual mode (recommended for WSL).")
+                    print("  Use tmux or screen for persistence across terminal closes.")
                 else:
                     print("To install as a service:")
                     print("  hermes gateway install")
@@ -2502,9 +2669,12 @@ def gateway_command(args):
                         print(f"  {line}")
                 print()
                 print("To start:")
-                print("  hermes gateway          # Run in foreground")
+                print("  hermes gateway run      # Run in foreground")
                 if is_termux():
-                    print("  nohup hermes gateway > ~/.hermes/logs/gateway.log 2>&1 &  # Best-effort background start")
+                    print("  nohup hermes gateway run > ~/.hermes/logs/gateway.log 2>&1 &  # Best-effort background start")
+                elif is_wsl():
+                    print("  tmux new -s hermes 'hermes gateway run'         # persistent via tmux")
+                    print("  nohup hermes gateway run > ~/.hermes/logs/gateway.log 2>&1 &  # background")
                 else:
                     print("  hermes gateway install  # Install as user service")
                     print("  sudo hermes gateway install --system  # Install as boot-time system service")

hermes_cli/main.py

@@ -934,6 +934,7 @@ 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"
@@ -966,6 +967,7 @@ 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)"),
     ]
 
     def _named_custom_provider_map(cfg) -> dict[str, dict[str, str]]:
@@ -1077,9 +1079,45 @@ def select_provider_and_model(args=None):
         _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.
@@ -4321,7 +4359,7 @@ 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)"
     )
@@ -4447,7 +4485,7 @@ 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",
@@ -4456,7 +4494,7 @@ 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
@@ -4474,7 +4512,7 @@ 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")
@@ -5375,7 +5413,8 @@ 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",
@@ -5384,7 +5423,7 @@ 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",

hermes_cli/model_normalize.py

@@ -92,6 +92,7 @@ _MATCHING_PREFIX_STRIP_PROVIDERS: frozenset[str] = frozenset({
     "minimax-cn",
     "alibaba",
     "qwen-oauth",
+    "xiaomi",
     "custom",
 })
 

hermes_cli/models.py

@@ -56,6 +56,18 @@ OPENROUTER_MODELS: list[tuple[str, str]] = [
 
 _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",
     ],
@@ -157,22 +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",
@@ -187,6 +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",
@@ -492,6 +498,7 @@ _PROVIDER_LABELS = {
     "alibaba": "Alibaba Cloud (DashScope)",
     "qwen-oauth": "Qwen OAuth (Portal)",
     "huggingface": "Hugging Face",
+    "xiaomi": "Xiaomi MiMo",
     "custom": "Custom endpoint",
 }
 
@@ -534,6 +541,8 @@ _PROVIDER_ALIASES = {
     "hf": "huggingface",
     "hugging-face": "huggingface",
     "huggingface-hub": "huggingface",
+    "mimo": "xiaomi",
+    "xiaomi-mimo": "xiaomi",
 }
 
 
@@ -818,7 +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",
     ]

hermes_cli/nous_subscription.py

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

hermes_cli/plugins.py

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

hermes_cli/plugins_cmd.py

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

hermes_cli/providers.py

@@ -88,11 +88,11 @@ HERMES_OVERLAYS: Dict[str, HermesOverlay] = {
         base_url_env_var="KIMI_BASE_URL",
     ),
     "minimax": HermesOverlay(
-        transport="openai_chat",
+        transport="anthropic_messages",
         base_url_env_var="MINIMAX_BASE_URL",
     ),
     "minimax-cn": HermesOverlay(
-        transport="openai_chat",
+        transport="anthropic_messages",
         base_url_env_var="MINIMAX_CN_BASE_URL",
     ),
     "deepseek": HermesOverlay(
@@ -132,6 +132,10 @@ HERMES_OVERLAYS: Dict[str, HermesOverlay] = {
         base_url_override="https://api.x.ai/v1",
         base_url_env_var="XAI_BASE_URL",
     ),
+    "xiaomi": HermesOverlay(
+        transport="openai_chat",
+        base_url_env_var="XIAOMI_BASE_URL",
+    ),
 }
 
 
@@ -222,6 +226,10 @@ ALIASES: Dict[str, str] = {
     "hugging-face": "huggingface",
     "huggingface-hub": "huggingface",
 
+    # xiaomi
+    "mimo": "xiaomi",
+    "xiaomi-mimo": "xiaomi",
+
     # Local server aliases → virtual "local" concept (resolved via user config)
     "lmstudio": "lmstudio",
     "lm-studio": "lmstudio",
@@ -242,6 +250,7 @@ _LABEL_OVERRIDES: Dict[str, str] = {
     "nous": "Nous Portal",
     "openai-codex": "OpenAI Codex",
     "copilot-acp": "GitHub Copilot ACP",
+    "xiaomi": "Xiaomi MiMo",
     "local": "Local endpoint",
 }
 

hermes_cli/setup.py

@@ -106,8 +106,8 @@ _DEFAULT_PROVIDER_MODELS = {
     ],
     "zai": ["glm-5", "glm-4.7", "glm-4.5", "glm-4.5-flash"],
     "kimi-coding": ["kimi-k2.5", "kimi-k2-thinking", "kimi-k2-turbo-preview"],
-    "minimax": ["MiniMax-M1", "MiniMax-M1-40k", "MiniMax-M1-80k", "MiniMax-M1-128k", "MiniMax-M1-256k", "MiniMax-M2.5", "MiniMax-M2.7"],
-    "minimax-cn": ["MiniMax-M1", "MiniMax-M1-40k", "MiniMax-M1-80k", "MiniMax-M1-128k", "MiniMax-M1-256k", "MiniMax-M2.5", "MiniMax-M2.7"],
+    "minimax": ["MiniMax-M2.7", "MiniMax-M2.5", "MiniMax-M2.1", "MiniMax-M2"],
+    "minimax-cn": ["MiniMax-M2.7", "MiniMax-M2.5", "MiniMax-M2.1", "MiniMax-M2"],
     "ai-gateway": ["anthropic/claude-opus-4.6", "anthropic/claude-sonnet-4.6", "openai/gpt-5", "google/gemini-3-flash"],
     "kilocode": ["anthropic/claude-opus-4.6", "anthropic/claude-sonnet-4.6", "openai/gpt-5.4", "google/gemini-3-pro-preview", "google/gemini-3-flash-preview"],
     "opencode-zen": ["gpt-5.4", "gpt-5.3-codex", "claude-sonnet-4-6", "gemini-3-flash", "glm-5", "kimi-k2.5", "minimax-m2.7"],
@@ -557,6 +557,8 @@ def _print_setup_summary(config: dict, hermes_home):
         tool_status.append(("Text-to-Speech (OpenAI)", True, None))
     elif tts_provider == "minimax" and get_env_value("MINIMAX_API_KEY"):
         tool_status.append(("Text-to-Speech (MiniMax)", True, None))
+    elif tts_provider == "mistral" and get_env_value("MISTRAL_API_KEY"):
+        tool_status.append(("Text-to-Speech (Mistral Voxtral)", True, None))
     elif tts_provider == "neutts":
         try:
             import importlib.util
@@ -1044,6 +1046,7 @@ def _setup_tts_provider(config: dict):
         "elevenlabs": "ElevenLabs",
         "openai": "OpenAI TTS",
         "minimax": "MiniMax TTS",
+        "mistral": "Mistral Voxtral TTS",
         "neutts": "NeuTTS",
     }
     current_label = provider_labels.get(current_provider, current_provider)
@@ -1064,10 +1067,11 @@ def _setup_tts_provider(config: dict):
             "ElevenLabs (premium quality, needs API key)",
             "OpenAI TTS (good quality, needs API key)",
             "MiniMax TTS (high quality with voice cloning, needs API key)",
+            "Mistral Voxtral TTS (multilingual, native Opus, needs API key)",
             "NeuTTS (local on-device, free, ~300MB model download)",
         ]
     )
-    providers.extend(["edge", "elevenlabs", "openai", "minimax", "neutts"])
+    providers.extend(["edge", "elevenlabs", "openai", "minimax", "mistral", "neutts"])
     choices.append(f"Keep current ({current_label})")
     keep_current_idx = len(choices) - 1
     idx = prompt_choice("Select TTS provider:", choices, keep_current_idx)
@@ -1145,6 +1149,18 @@ def _setup_tts_provider(config: dict):
                 print_warning("No API key provided. Falling back to Edge TTS.")
                 selected = "edge"
 
+    elif selected == "mistral":
+        existing = get_env_value("MISTRAL_API_KEY")
+        if not existing:
+            print()
+            api_key = prompt("Mistral API key for TTS", password=True)
+            if api_key:
+                save_env_value("MISTRAL_API_KEY", api_key)
+                print_success("Mistral TTS API key saved")
+            else:
+                print_warning("No API key provided. Falling back to Edge TTS.")
+                selected = "edge"
+
     # Save the selection
     if "tts" not in config:
         config["tts"] = {}
@@ -1925,9 +1941,9 @@ def _setup_matrix():
             save_env_value("MATRIX_ENCRYPTION", "true")
             print_success("E2EE enabled")
 
-        matrix_pkg = "matrix-nio[e2e]" if want_e2ee else "matrix-nio"
+        matrix_pkg = "mautrix[encryption]" if want_e2ee else "mautrix"
         try:
-            __import__("nio")
+            __import__("mautrix")
         except ImportError:
             print_info(f"Installing {matrix_pkg}...")
             import subprocess
@@ -2922,19 +2938,33 @@ def run_setup_wizard(args):
     _offer_launch_chat()
 
 
+def _resolve_hermes_chat_argv() -> Optional[list[str]]:
+    """Resolve argv for launching ``hermes chat`` in a fresh process."""
+    hermes_bin = shutil.which("hermes")
+    if hermes_bin:
+        return [hermes_bin, "chat"]
+
+    try:
+        if importlib.util.find_spec("hermes_cli") is not None:
+            return [sys.executable, "-m", "hermes_cli.main", "chat"]
+    except Exception:
+        pass
+
+    return None
+
+
 def _offer_launch_chat():
     """Prompt the user to jump straight into chat after setup."""
     print()
-    if prompt_yes_no("Launch hermes chat now?", True):
-        from hermes_cli.main import cmd_chat
-        from types import SimpleNamespace
-        cmd_chat(SimpleNamespace(
-            query=None, resume=None, continue_last=None, model=None,
-            provider=None, effort=None, skin=None, oneshot=False,
-            quiet=False, verbose=False, toolsets=None, skills=None,
-            yolo=False, source=None, worktree=False, checkpoints=False,
-            pass_session_id=False, max_turns=None,
-        ))
+    if not prompt_yes_no("Launch hermes chat now?", True):
+        return
+
+    chat_argv = _resolve_hermes_chat_argv()
+    if not chat_argv:
+        print_info("Could not relaunch Hermes automatically. Run 'hermes chat' manually.")
+        return
+
+    os.execvp(chat_argv[0], chat_argv)
 
 
 def _run_first_time_quick_setup(config: dict, hermes_home, is_existing: bool):

hermes_cli/tools_config.py

@@ -181,6 +181,14 @@ TOOL_CATEGORIES = {
                 ],
                 "tts_provider": "elevenlabs",
             },
+            {
+                "name": "Mistral (Voxtral TTS)",
+                "tag": "Multilingual, native Opus, needs MISTRAL_API_KEY",
+                "env_vars": [
+                    {"key": "MISTRAL_API_KEY", "prompt": "Mistral API key", "url": "https://console.mistral.ai/"},
+                ],
+                "tts_provider": "mistral",
+            },
         ],
     },
     "web": {
@@ -501,6 +509,10 @@ def _get_platform_tools(
         default_ts = PLATFORMS[platform]["default_toolset"]
         toolset_names = [default_ts]
 
+    # YAML may parse bare numeric names (e.g. ``12306:``) as int.
+    # Normalise to str so downstream sorted() never mixes types.
+    toolset_names = [str(ts) for ts in toolset_names]
+
     configurable_keys = {ts_key for ts_key, _, _ in CONFIGURABLE_TOOLSETS}
 
     # If the saved list contains any configurable keys directly, the user
@@ -559,7 +571,7 @@ def _get_platform_tools(
     # Special sentinel: "no_mcp" in the toolset list disables all MCP servers.
     mcp_servers = config.get("mcp_servers") or {}
     enabled_mcp_servers = {
-        name
+        str(name)
         for name, server_cfg in mcp_servers.items()
         if isinstance(server_cfg, dict)
         and _parse_enabled_flag(server_cfg.get("enabled", True), default=True)

hermes_constants.py

@@ -168,6 +168,27 @@ def is_termux() -> bool:
     return bool(os.getenv("TERMUX_VERSION") or "com.termux/files/usr" in prefix)
 
 
+_wsl_detected: bool | None = None
+
+
+def is_wsl() -> bool:
+    """Return True when running inside WSL (Windows Subsystem for Linux).
+
+    Checks ``/proc/version`` for the ``microsoft`` marker that both WSL1
+    and WSL2 inject.  Result is cached for the process lifetime.
+    Import-safe — no heavy deps.
+    """
+    global _wsl_detected
+    if _wsl_detected is not None:
+        return _wsl_detected
+    try:
+        with open("/proc/version", "r") as f:
+            _wsl_detected = "microsoft" in f.read().lower()
+    except Exception:
+        _wsl_detected = False
+    return _wsl_detected
+
+
 OPENROUTER_BASE_URL = "https://openrouter.ai/api/v1"
 OPENROUTER_MODELS_URL = f"{OPENROUTER_BASE_URL}/models"
 

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

@@ -617,6 +617,19 @@ class Migrator:
             candidate = self.source_root / rel
             if candidate.exists():
                 return candidate
+            # OpenClaw renamed workspace/ to workspace-main/ (and workspace-{agentId}
+            # for multi-agent).  Try the new path as a fallback.
+            if rel.startswith("workspace/"):
+                suffix = rel[len("workspace/"):]
+                for variant in ("workspace-main", "workspace-assistant"):
+                    alt = self.source_root / variant / suffix
+                    if alt.exists():
+                        return alt
+            elif rel.startswith("workspace.default/"):
+                suffix = rel[len("workspace.default/"):]
+                alt = self.source_root / "workspace-main" / suffix
+                if alt.exists():
+                    return alt
         return None
 
     def resolve_skill_destination(self, destination: Path) -> Path:
@@ -1033,11 +1046,8 @@ class Migrator:
     def migrate_secret_settings(self, config: Dict[str, Any]) -> None:
         secret_additions: Dict[str, str] = {}
 
-        telegram_token = (
-            config.get("channels", {})
-            .get("telegram", {})
-            .get("botToken")
-        )
+        tg_cfg = config.get("channels", {}).get("telegram", {})
+        telegram_token = self._get_channel_field(tg_cfg, "botToken") if isinstance(tg_cfg, dict) else None
         if isinstance(telegram_token, str) and telegram_token.strip():
             secret_additions["TELEGRAM_BOT_TOKEN"] = telegram_token.strip()
 
@@ -1057,15 +1067,28 @@ class Migrator:
         """Resolve a channel config value that may be a SecretRef."""
         return resolve_secret_input(value, self.load_openclaw_env())
 
+    @staticmethod
+    def _get_channel_field(ch_cfg: Dict[str, Any], field: str) -> Any:
+        """Get a field from channel config, checking both flat and accounts.default layout."""
+        val = ch_cfg.get(field)
+        if val is not None:
+            return val
+        accounts = ch_cfg.get("accounts")
+        if isinstance(accounts, dict):
+            default = accounts.get("default")
+            if isinstance(default, dict):
+                return default.get(field)
+        return None
+
     def migrate_discord_settings(self, config: Optional[Dict[str, Any]] = None) -> None:
         config = config or self.load_openclaw_config()
         additions: Dict[str, str] = {}
         discord = config.get("channels", {}).get("discord", {})
         if isinstance(discord, dict):
-            token = discord.get("token")
+            token = self._get_channel_field(discord, "token")
             if isinstance(token, str) and token.strip():
                 additions["DISCORD_BOT_TOKEN"] = token.strip()
-            allow_from = discord.get("allowFrom", [])
+            allow_from = self._get_channel_field(discord, "allowFrom") or []
             if isinstance(allow_from, list):
                 users = [str(u).strip() for u in allow_from if str(u).strip()]
                 if users:
@@ -1080,13 +1103,13 @@ class Migrator:
         additions: Dict[str, str] = {}
         slack = config.get("channels", {}).get("slack", {})
         if isinstance(slack, dict):
-            bot_token = slack.get("botToken")
+            bot_token = self._get_channel_field(slack, "botToken")
             if isinstance(bot_token, str) and bot_token.strip():
                 additions["SLACK_BOT_TOKEN"] = bot_token.strip()
-            app_token = slack.get("appToken")
+            app_token = self._get_channel_field(slack, "appToken")
             if isinstance(app_token, str) and app_token.strip():
                 additions["SLACK_APP_TOKEN"] = app_token.strip()
-            allow_from = slack.get("allowFrom", [])
+            allow_from = self._get_channel_field(slack, "allowFrom") or []
             if isinstance(allow_from, list):
                 users = [str(u).strip() for u in allow_from if str(u).strip()]
                 if users:
@@ -1101,7 +1124,7 @@ class Migrator:
         additions: Dict[str, str] = {}
         whatsapp = config.get("channels", {}).get("whatsapp", {})
         if isinstance(whatsapp, dict):
-            allow_from = whatsapp.get("allowFrom", [])
+            allow_from = self._get_channel_field(whatsapp, "allowFrom") or []
             if isinstance(allow_from, list):
                 users = [str(u).strip() for u in allow_from if str(u).strip()]
                 if users:
@@ -1116,13 +1139,13 @@ class Migrator:
         additions: Dict[str, str] = {}
         signal = config.get("channels", {}).get("signal", {})
         if isinstance(signal, dict):
-            account = signal.get("account")
+            account = self._get_channel_field(signal, "account")
             if isinstance(account, str) and account.strip():
                 additions["SIGNAL_ACCOUNT"] = account.strip()
-            http_url = signal.get("httpUrl")
+            http_url = self._get_channel_field(signal, "httpUrl")
             if isinstance(http_url, str) and http_url.strip():
                 additions["SIGNAL_HTTP_URL"] = http_url.strip()
-            allow_from = signal.get("allowFrom", [])
+            allow_from = self._get_channel_field(signal, "allowFrom") or []
             if isinstance(allow_from, list):
                 users = [str(u).strip() for u in allow_from if str(u).strip()]
                 if users:
@@ -1161,6 +1184,16 @@ class Migrator:
                 raw_key = provider_cfg.get("apiKey")
                 api_key = resolve_secret_input(raw_key, openclaw_env)
                 if not api_key:
+                    # Warn if a SecretRef with file/exec source was silently unresolvable
+                    if isinstance(raw_key, dict) and raw_key.get("source") in ("file", "exec"):
+                        self.record(
+                            "provider-keys",
+                            self.source_root / "openclaw.json",
+                            None,
+                            "skipped",
+                            f"Provider '{provider_name}' uses a {raw_key['source']}-backed SecretRef "
+                            f"that cannot be auto-migrated. Add this key manually via: hermes config set",
+                        )
                     continue
 
                 base_url = provider_cfg.get("baseUrl", "")
@@ -1224,6 +1257,21 @@ class Migrator:
             if val and hermes_key not in secret_additions:
                 secret_additions[hermes_key] = val
 
+        # Check the openclaw.json "env" sub-object — some OpenClaw setups
+        # store API keys here instead of in a separate .env file.
+        # Keys can be at env.<KEY> or env.vars.<KEY>.
+        json_env = config.get("env")
+        if isinstance(json_env, dict):
+            env_vars = json_env.get("vars")
+            sources = [json_env]
+            if isinstance(env_vars, dict):
+                sources.append(env_vars)
+            for src in sources:
+                for oc_key, hermes_key in env_key_mapping.items():
+                    val = src.get(oc_key)
+                    if isinstance(val, str) and val.strip() and hermes_key not in secret_additions:
+                        secret_additions[hermes_key] = val.strip()
+
         # Check per-agent auth-profiles.json for additional credentials
         auth_profiles_path = self.source_root / "agents" / "main" / "agent" / "auth-profiles.json"
         if auth_profiles_path.exists():
@@ -1324,8 +1372,9 @@ class Migrator:
         tts_data: Dict[str, Any] = {}
 
         provider = tts.get("provider")
-        if isinstance(provider, str) and provider in ("elevenlabs", "openai", "edge"):
-            tts_data["provider"] = provider
+        if isinstance(provider, str) and provider in ("elevenlabs", "openai", "edge", "microsoft"):
+            # OpenClaw renamed "edge" to "microsoft"; Hermes still uses "edge"
+            tts_data["provider"] = "edge" if provider == "microsoft" else provider
 
         # TTS provider settings live under messages.tts.providers.{provider}
         # in OpenClaw (not messages.tts.elevenlabs directly)
@@ -1374,9 +1423,9 @@ class Migrator:
                 tts_data["openai"] = oai_settings
 
         edge_tts = (
-            (providers.get("edge") or {})
-            if isinstance(providers.get("edge"), dict) else
-            (tts.get("edge") or {})
+            (providers.get("edge") or providers.get("microsoft") or {})
+            if isinstance(providers.get("edge"), dict) or isinstance(providers.get("microsoft"), dict) else
+            (tts.get("edge") or tts.get("microsoft") or {})
         )
         if isinstance(edge_tts, dict):
             edge_voice = edge_tts.get("voice")
@@ -1890,11 +1939,11 @@ class Migrator:
         if defaults.get("thinkingDefault"):
             # Map OpenClaw thinking -> Hermes reasoning_effort
             thinking = defaults["thinkingDefault"]
-            if thinking in ("always", "high"):
+            if thinking in ("always", "high", "xhigh"):
                 agent_cfg["reasoning_effort"] = "high"
-            elif thinking in ("auto", "medium"):
+            elif thinking in ("auto", "medium", "adaptive"):
                 agent_cfg["reasoning_effort"] = "medium"
-            elif thinking in ("off", "low", "none"):
+            elif thinking in ("off", "low", "none", "minimal"):
                 agent_cfg["reasoning_effort"] = "low"
             changes = True
 
@@ -2099,10 +2148,14 @@ class Migrator:
                                 f"Provider '{prov_name}' already exists")
                     continue
 
-                api_type = prov_cfg.get("apiType") or prov_cfg.get("type") or "openai"
+                api_type = prov_cfg.get("apiType") or prov_cfg.get("api") or prov_cfg.get("type") or "openai"
                 api_mode_map = {
                     "openai": "chat_completions",
+                    "openai-completions": "chat_completions",
+                    "openai-responses": "chat_completions",
                     "anthropic": "anthropic_messages",
+                    "anthropic-messages": "anthropic_messages",
+                    "google-generative-ai": "chat_completions",
                     "cohere": "chat_completions",
                 }
                 entry = {
@@ -2142,7 +2195,7 @@ class Migrator:
 
         # Extended channel token/allowlist mapping
         CHANNEL_ENV_MAP = {
-            "matrix": {"token": "MATRIX_ACCESS_TOKEN", "allowFrom": "MATRIX_ALLOWED_USERS",
+            "matrix": {"token": "MATRIX...OKEN", "tokenField": "accessToken", "allowFrom": "MATRIX_ALLOWED_USERS",
                         "extras": {"homeserverUrl": "MATRIX_HOMESERVER_URL", "userId": "MATRIX_USER_ID"}},
             "mattermost": {"token": "MATTERMOST_BOT_TOKEN", "allowFrom": "MATTERMOST_ALLOWED_USERS",
                            "extras": {"url": "MATTERMOST_URL", "teamId": "MATTERMOST_TEAM_ID"}},
@@ -2160,19 +2213,21 @@ class Migrator:
             if not ch_cfg:
                 continue
 
-            # Extract tokens
-            if ch_mapping.get("token") and ch_cfg.get("botToken") and self.migrate_secrets:
-                self._set_env_var(ch_mapping["token"], ch_cfg["botToken"],
-                                  f"channels.{ch_name}.botToken")
-            if ch_mapping.get("allowFrom") and ch_cfg.get("allowFrom"):
-                allow_val = ch_cfg["allowFrom"]
+            # Extract tokens (check flat path, then accounts.default)
+            token_field = ch_mapping.get("tokenField", "botToken")
+            bot_token = self._get_channel_field(ch_cfg, token_field)
+            if ch_mapping.get("token") and bot_token and self.migrate_secrets:
+                self._set_env_var(ch_mapping["token"], str(bot_token),
+                                  f"channels.{ch_name}.{token_field}")
+            allow_val = self._get_channel_field(ch_cfg, "allowFrom")
+            if ch_mapping.get("allowFrom") and allow_val:
                 if isinstance(allow_val, list):
                     allow_val = ",".join(str(x) for x in allow_val)
                 self._set_env_var(ch_mapping["allowFrom"], str(allow_val),
                                   f"channels.{ch_name}.allowFrom")
             # Extra fields
             for oc_key, env_key in (ch_mapping.get("extras") or {}).items():
-                val = ch_cfg.get(oc_key)
+                val = self._get_channel_field(ch_cfg, oc_key)
                 if val:
                     if isinstance(val, list):
                         val = ",".join(str(x) for x in val)
@@ -2495,6 +2550,33 @@ class Migrator:
         elif has_cron_store_archive:
             notes.append("- Run `hermes cron` to recreate scheduled tasks (see archived cron-store)")
 
+        # Check if skills were imported
+        has_skills = any(i.kind == "skills" and i.status == "migrated" for i in self.items)
+        if has_skills:
+            notes.extend([
+                "",
+                "## Imported Skills",
+                "",
+                "Imported skills require a new session to take effect. After migration,",
+                "restart your agent or start a new chat session, then run `/skills`",
+                "to verify they loaded correctly.",
+                "",
+            ])
+
+        # Check if WhatsApp was detected
+        has_whatsapp = any(i.kind == "whatsapp-settings" and i.status == "migrated" for i in self.items)
+        if has_whatsapp:
+            notes.extend([
+                "",
+                "## WhatsApp Requires Re-Pairing",
+                "",
+                "WhatsApp uses QR-code pairing, not token-based auth. Your allowlist",
+                "was migrated, but you must re-pair the device by running:",
+                "",
+                "    hermes whatsapp",
+                "",
+            ])
+
         notes.extend([
             "- Run `hermes gateway install` if you need the gateway service",
             "- Review `~/.hermes/config.yaml` for any adjustments",

plugins/context_engine/__init__.py

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

plugins/memory/honcho/__init__.py

@@ -218,9 +218,11 @@ class HonchoMemoryProvider(MemoryProvider):
                 return
 
             # Override peer_name with gateway user_id for per-user memory scoping.
-            # CLI sessions won't have user_id, so the config default is preserved.
+            # Only when no explicit peerName was configured — an explicit peerName
+            # means the user chose their identity; a raw user_id (e.g. Telegram
+            # chat ID) should not silently replace it.
             _gw_user_id = kwargs.get("user_id")
-            if _gw_user_id:
+            if _gw_user_id and not cfg.peer_name:
                 cfg.peer_name = _gw_user_id
 
             self._config = cfg
@@ -248,6 +250,12 @@ class HonchoMemoryProvider(MemoryProvider):
 
             # ----- Port #1957: lazy session init for tools-only mode -----
             if self._recall_mode == "tools":
+                if cfg.init_on_session_start:
+                    # Eager init: create session now so sync_turn() works from turn 1.
+                    # Does NOT enable auto-injection — prefetch() still returns empty.
+                    logger.debug("Honcho tools-only mode — eager session init (initOnSessionStart=true)")
+                    self._do_session_init(cfg, session_id, **kwargs)
+                    return
                 # Defer actual session creation until first tool call
                 self._lazy_init_kwargs = kwargs
                 self._lazy_init_session_id = session_id

plugins/memory/honcho/client.py

@@ -189,6 +189,11 @@ class HonchoClientConfig:
     # "context" — auto-injected context only, Honcho tools removed
     # "tools"   — Honcho tools only, no auto-injected context
     recall_mode: str = "hybrid"
+    # When True and recallMode is "tools", create the Honcho session eagerly
+    # during initialize() instead of deferring to the first tool call.
+    # This ensures sync_turn() can write from the very first turn.
+    # Does NOT enable automatic context injection — only changes init timing.
+    init_on_session_start: bool = False
     # Observation mode: legacy string shorthand ("directional" or "unified").
     # Kept for backward compat; granular per-peer booleans below are preferred.
     observation_mode: str = "directional"
@@ -366,6 +371,11 @@ class HonchoClientConfig:
                 or raw.get("recallMode")
                 or "hybrid"
             ),
+            init_on_session_start=_resolve_bool(
+                host_block.get("initOnSessionStart"),
+                raw.get("initOnSessionStart"),
+                default=False,
+            ),
             # Migration guard: existing configs without an explicit
             # observationMode keep the old "unified" default so users
             # aren't silently switched to full bidirectional observation.

pyproject.toml

@@ -43,7 +43,7 @@ dev = ["debugpy>=1.8.0,<2", "pytest>=9.0.2,<10", "pytest-asyncio>=1.3.0,<2", "py
 messaging = ["python-telegram-bot[webhooks]>=22.6,<23", "discord.py[voice]>=2.7.1,<3", "aiohttp>=3.13.3,<4", "slack-bolt>=1.18.0,<2", "slack-sdk>=3.27.0,<4"]
 cron = ["croniter>=6.0.0,<7"]
 slack = ["slack-bolt>=1.18.0,<2", "slack-sdk>=3.27.0,<4"]
-matrix = ["matrix-nio[e2e]>=0.24.0,<1", "Markdown>=3.6,<4"]
+matrix = ["mautrix[encryption]>=0.20,<1", "Markdown>=3.6,<4"]
 cli = ["simple-term-menu>=1.0,<2"]
 tts-premium = ["elevenlabs>=1.0,<2"]
 voice = [

run_agent.py

@@ -700,10 +700,14 @@ class AIAgent:
         except Exception:
             pass
 
-        # Direct OpenAI sessions use the Responses API path.  GPT-5.x tool
-        # calls with reasoning are rejected on /v1/chat/completions, and
-        # Hermes is a tool-using client by default.
-        if self.api_mode == "chat_completions" and self._is_direct_openai_url():
+        # GPT-5.x models require the Responses API path — they are rejected
+        # on /v1/chat/completions by both OpenAI and OpenRouter.  Also
+        # auto-upgrade for direct OpenAI URLs (api.openai.com) since all
+        # newer tool-calling models prefer Responses there.
+        if self.api_mode == "chat_completions" and (
+            self._is_direct_openai_url()
+            or self._model_requires_responses_api(self.model)
+        ):
             self.api_mode = "codex_responses"
 
         # Pre-warm OpenRouter model metadata cache in a background thread.
@@ -766,7 +770,7 @@ class AIAgent:
         # conversation prefix. Uses system_and_3 strategy (4 breakpoints).
         is_openrouter = self._is_openrouter_url()
         is_claude = "claude" in self.model.lower()
-        is_native_anthropic = self.api_mode == "anthropic_messages"
+        is_native_anthropic = self.api_mode == "anthropic_messages" and self.provider == "anthropic"
         self._use_prompt_caching = (is_openrouter and is_claude) or is_native_anthropic
         self._cache_ttl = "5m"  # Default 5-minute TTL (1.25x write cost)
         
@@ -1268,20 +1272,88 @@ class AIAgent:
                                         pass
                         break
         
-        self.context_compressor = ContextCompressor(
-            model=self.model,
-            threshold_percent=compression_threshold,
-            protect_first_n=3,
-            protect_last_n=compression_protect_last,
-            summary_target_ratio=compression_target_ratio,
-            summary_model_override=compression_summary_model,
-            quiet_mode=self.quiet_mode,
-            base_url=self.base_url,
-            api_key=getattr(self, "api_key", ""),
-            config_context_length=_config_context_length,
-            provider=self.provider,
-        )
+        # Select context engine: config-driven (like memory providers).
+        # 1. Check config.yaml context.engine setting
+        # 2. Check plugins/context_engine/<name>/ directory (repo-shipped)
+        # 3. Check general plugin system (user-installed plugins)
+        # 4. Fall back to built-in ContextCompressor
+        _selected_engine = None
+        _engine_name = "compressor"  # default
+        try:
+            _ctx_cfg = _agent_cfg.get("context", {}) if isinstance(_agent_cfg, dict) else {}
+            _engine_name = _ctx_cfg.get("engine", "compressor") or "compressor"
+        except Exception:
+            pass
+
+        if _engine_name != "compressor":
+            # Try loading from plugins/context_engine/<name>/
+            try:
+                from plugins.context_engine import load_context_engine
+                _selected_engine = load_context_engine(_engine_name)
+            except Exception as _ce_load_err:
+                logger.debug("Context engine load from plugins/context_engine/: %s", _ce_load_err)
+
+            # Try general plugin system as fallback
+            if _selected_engine is None:
+                try:
+                    from hermes_cli.plugins import get_plugin_context_engine
+                    _candidate = get_plugin_context_engine()
+                    if _candidate and _candidate.name == _engine_name:
+                        _selected_engine = _candidate
+                except Exception:
+                    pass
+
+            if _selected_engine is None:
+                logger.warning(
+                    "Context engine '%s' not found — falling back to built-in compressor",
+                    _engine_name,
+                )
+        # else: config says "compressor" — use built-in, don't auto-activate plugins
+
+        if _selected_engine is not None:
+            self.context_compressor = _selected_engine
+            if not self.quiet_mode:
+                logger.info("Using context engine: %s", _selected_engine.name)
+        else:
+            self.context_compressor = ContextCompressor(
+                model=self.model,
+                threshold_percent=compression_threshold,
+                protect_first_n=3,
+                protect_last_n=compression_protect_last,
+                summary_target_ratio=compression_target_ratio,
+                summary_model_override=compression_summary_model,
+                quiet_mode=self.quiet_mode,
+                base_url=self.base_url,
+                api_key=getattr(self, "api_key", ""),
+                config_context_length=_config_context_length,
+                provider=self.provider,
+            )
         self.compression_enabled = compression_enabled
+
+        # Inject context engine tool schemas (e.g. lcm_grep, lcm_describe, lcm_expand)
+        self._context_engine_tool_names: set = set()
+        if hasattr(self, "context_compressor") and self.context_compressor and self.tools is not None:
+            for _schema in self.context_compressor.get_tool_schemas():
+                _wrapped = {"type": "function", "function": _schema}
+                self.tools.append(_wrapped)
+                _tname = _schema.get("name", "")
+                if _tname:
+                    self.valid_tool_names.add(_tname)
+                    self._context_engine_tool_names.add(_tname)
+
+        # Notify context engine of session start
+        if hasattr(self, "context_compressor") and self.context_compressor:
+            try:
+                self.context_compressor.on_session_start(
+                    self.session_id,
+                    hermes_home=str(get_hermes_home()),
+                    platform=self.platform or "cli",
+                    model=self.model,
+                    context_length=getattr(self.context_compressor, "context_length", 0),
+                )
+            except Exception as _ce_err:
+                logger.debug("Context engine on_session_start: %s", _ce_err)
+
         self._subdirectory_hints = SubdirectoryHintTracker(
             working_dir=os.getenv("TERMINAL_CWD") or None,
         )
@@ -1334,6 +1406,12 @@ class AIAgent:
             else:
                 print(f"📊 Context limit: {self.context_compressor.context_length:,} tokens (auto-compression disabled)")
 
+        # Check immediately so CLI users see the warning at startup.
+        # Gateway status_callback is not yet wired, so any warning is stored
+        # in _compression_warning and replayed in the first run_conversation().
+        self._compression_warning = None
+        self._check_compression_model_feasibility()
+
         # Snapshot primary runtime for per-turn restoration.  When fallback
         # activates during a turn, the next turn restores these values so the
         # preferred model gets a fresh attempt each time.  Uses a single dict
@@ -1347,11 +1425,13 @@ class AIAgent:
             "api_key": getattr(self, "api_key", ""),
             "client_kwargs": dict(self._client_kwargs),
             "use_prompt_caching": self._use_prompt_caching,
-            # Compressor state that _try_activate_fallback() overwrites
-            "compressor_model": _cc.model,
-            "compressor_base_url": _cc.base_url,
+            # Context engine state that _try_activate_fallback() overwrites.
+            # Use getattr for model/base_url/api_key/provider since plugin
+            # engines may not have these (they're ContextCompressor-specific).
+            "compressor_model": getattr(_cc, "model", self.model),
+            "compressor_base_url": getattr(_cc, "base_url", self.base_url),
             "compressor_api_key": getattr(_cc, "api_key", ""),
-            "compressor_provider": _cc.provider,
+            "compressor_provider": getattr(_cc, "provider", self.provider),
             "compressor_context_length": _cc.context_length,
             "compressor_threshold_tokens": _cc.threshold_tokens,
         }
@@ -1397,15 +1477,9 @@ class AIAgent:
         # Turn counter (added after reset_session_state was first written — #2635)
         self._user_turn_count = 0
 
-        # Context compressor internal counters (if present)
+        # Context engine reset (works for both built-in compressor and plugins)
         if hasattr(self, "context_compressor") and self.context_compressor:
-            self.context_compressor.last_prompt_tokens = 0
-            self.context_compressor.last_completion_tokens = 0
-            self.context_compressor.compression_count = 0
-            self.context_compressor._context_probed = False
-            self.context_compressor._context_probe_persistable = False
-            # Iterative summary from previous session must not bleed into new one (#2635)
-            self.context_compressor._previous_summary = None
+            self.context_compressor.on_session_reset()
     
     def switch_model(self, new_model, new_provider, api_key='', base_url='', api_mode=''):
         """Switch the model/provider in-place for a live agent.
@@ -1446,7 +1520,11 @@ class AIAgent:
                 resolve_anthropic_token,
                 _is_oauth_token,
             )
-            effective_key = api_key or self.api_key or resolve_anthropic_token() or ""
+            # Only fall back to ANTHROPIC_TOKEN when the provider is actually Anthropic.
+            # Other anthropic_messages providers (MiniMax, Alibaba, etc.) must use their own
+            # API key — falling back would send Anthropic credentials to third-party endpoints.
+            _is_native_anthropic = new_provider == "anthropic"
+            effective_key = (api_key or self.api_key or resolve_anthropic_token() or "") if _is_native_anthropic else (api_key or self.api_key or "")
             self.api_key = effective_key
             self._anthropic_api_key = effective_key
             self._anthropic_base_url = base_url or getattr(self, "_anthropic_base_url", None)
@@ -1470,7 +1548,7 @@ class AIAgent:
             )
 
         # ── Re-evaluate prompt caching ──
-        is_native_anthropic = api_mode == "anthropic_messages"
+        is_native_anthropic = api_mode == "anthropic_messages" and new_provider == "anthropic"
         self._use_prompt_caching = (
             ("openrouter" in (self.base_url or "").lower() and "claude" in new_model.lower())
             or is_native_anthropic
@@ -1486,13 +1564,12 @@ class AIAgent:
                 provider=self.provider,
                 config_context_length=getattr(self, "_config_context_length", None),
             )
-            self.context_compressor.model = self.model
-            self.context_compressor.base_url = self.base_url
-            self.context_compressor.api_key = self.api_key
-            self.context_compressor.provider = self.provider
-            self.context_compressor.context_length = new_context_length
-            self.context_compressor.threshold_tokens = int(
-                new_context_length * self.context_compressor.threshold_percent
+            self.context_compressor.update_model(
+                model=self.model,
+                context_length=new_context_length,
+                base_url=self.base_url,
+                api_key=getattr(self, "api_key", ""),
+                provider=self.provider,
             )
 
         # ── Invalidate cached system prompt so it rebuilds next turn ──
@@ -1508,10 +1585,10 @@ class AIAgent:
             "api_key": getattr(self, "api_key", ""),
             "client_kwargs": dict(self._client_kwargs),
             "use_prompt_caching": self._use_prompt_caching,
-            "compressor_model": _cc.model if _cc else self.model,
-            "compressor_base_url": _cc.base_url if _cc else self.base_url,
+            "compressor_model": getattr(_cc, "model", self.model) if _cc else self.model,
+            "compressor_base_url": getattr(_cc, "base_url", self.base_url) if _cc else self.base_url,
             "compressor_api_key": getattr(_cc, "api_key", "") if _cc else "",
-            "compressor_provider": _cc.provider if _cc else self.provider,
+            "compressor_provider": getattr(_cc, "provider", self.provider) if _cc else self.provider,
             "compressor_context_length": _cc.context_length if _cc else 0,
             "compressor_threshold_tokens": _cc.threshold_tokens if _cc else 0,
         }
@@ -1626,6 +1703,104 @@ class AIAgent:
             except Exception:
                 logger.debug("status_callback error in _emit_status", exc_info=True)
 
+    def _check_compression_model_feasibility(self) -> None:
+        """Warn at session start if the auxiliary compression model's context
+        window is smaller than the main model's compression threshold.
+
+        When the auxiliary model cannot fit the content that needs summarising,
+        compression will either fail outright (the LLM call errors) or produce
+        a severely truncated summary.
+
+        Called during ``__init__`` so CLI users see the warning immediately
+        (via ``_vprint``).  The gateway sets ``status_callback`` *after*
+        construction, so ``_replay_compression_warning()`` re-sends the
+        stored warning through the callback on the first
+        ``run_conversation()`` call.
+        """
+        if not self.compression_enabled:
+            return
+        try:
+            from agent.auxiliary_client import get_text_auxiliary_client
+            from agent.model_metadata import get_model_context_length
+
+            client, aux_model = get_text_auxiliary_client("compression")
+            if client is None or not aux_model:
+                msg = (
+                    "⚠ No auxiliary LLM provider configured — context "
+                    "compression will drop middle turns without a summary. "
+                    "Run `hermes setup` or set OPENROUTER_API_KEY."
+                )
+                self._compression_warning = msg
+                self._emit_status(msg)
+                logger.warning(
+                    "No auxiliary LLM provider for compression — "
+                    "summaries will be unavailable."
+                )
+                return
+
+            aux_base_url = str(getattr(client, "base_url", ""))
+            aux_api_key = str(getattr(client, "api_key", ""))
+            aux_context = get_model_context_length(
+                aux_model,
+                base_url=aux_base_url,
+                api_key=aux_api_key,
+            )
+
+            threshold = self.context_compressor.threshold_tokens
+            if aux_context < threshold:
+                # Suggest a threshold that would fit the aux model,
+                # rounded down to a clean percentage.
+                safe_pct = int((aux_context / self.context_compressor.context_length) * 100)
+                msg = (
+                    f"⚠ Compression model ({aux_model}) context "
+                    f"is {aux_context:,} tokens, but the main model's "
+                    f"compression threshold is {threshold:,} tokens. "
+                    f"Context compression will not be possible — the "
+                    f"content to summarise will exceed the auxiliary "
+                    f"model's context window.\n"
+                    f"  Fix options (config.yaml):\n"
+                    f"  1. Use a larger compression model:\n"
+                    f"       auxiliary:\n"
+                    f"         compression:\n"
+                    f"           model: <model-with-{threshold:,}+-context>\n"
+                    f"  2. Lower the compression threshold to fit "
+                    f"the current model:\n"
+                    f"       compression:\n"
+                    f"         threshold: 0.{safe_pct:02d}"
+                )
+                self._compression_warning = msg
+                self._emit_status(msg)
+                logger.warning(
+                    "Auxiliary compression model %s has %d token context, "
+                    "below the main model's compression threshold of %d "
+                    "tokens — compression summaries will fail or be "
+                    "severely truncated.",
+                    aux_model,
+                    aux_context,
+                    threshold,
+                )
+        except Exception as exc:
+            logger.debug(
+                "Compression feasibility check failed (non-fatal): %s", exc
+            )
+
+    def _replay_compression_warning(self) -> None:
+        """Re-send the compression warning through ``status_callback``.
+
+        During ``__init__`` the gateway's ``status_callback`` is not yet
+        wired, so ``_emit_status`` only reaches ``_vprint`` (CLI).  This
+        method is called once at the start of the first
+        ``run_conversation()`` — by then the gateway has set the callback,
+        so every platform (Telegram, Discord, Slack, etc.) receives the
+        warning.
+        """
+        msg = getattr(self, "_compression_warning", None)
+        if msg and self.status_callback:
+            try:
+                self.status_callback("lifecycle", msg)
+            except Exception:
+                pass
+
     def _is_direct_openai_url(self, base_url: str = None) -> bool:
         """Return True when a base URL targets OpenAI's native API."""
         url = (base_url or self._base_url_lower).lower()
@@ -1635,6 +1810,21 @@ class AIAgent:
         """Return True when the base URL targets OpenRouter."""
         return "openrouter" in self._base_url_lower
 
+    @staticmethod
+    def _model_requires_responses_api(model: str) -> bool:
+        """Return True for models that require the Responses API path.
+
+        GPT-5.x models are rejected on /v1/chat/completions by both
+        OpenAI and OpenRouter (error: ``unsupported_api_for_model``).
+        Detect these so the correct api_mode is set regardless of
+        which provider is serving the model.
+        """
+        m = model.lower()
+        # Strip vendor prefix (e.g. "openai/gpt-5.4" → "gpt-5.4")
+        if "/" in m:
+            m = m.rsplit("/", 1)[-1]
+        return m.startswith("gpt-5")
+
     def _max_tokens_param(self, value: int) -> dict:
         """Return the correct max tokens kwarg for the current provider.
         
@@ -2708,10 +2898,11 @@ class AIAgent:
         }
 
     def shutdown_memory_provider(self, messages: list = None) -> None:
-        """Shut down the memory provider — call at actual session boundaries.
+        """Shut down the memory provider and context engine — call at actual session boundaries.
 
         This calls on_session_end() then shutdown_all() on the memory
-        manager. NOT called per-turn — only at CLI exit, /reset, gateway
+        manager, and on_session_end() on the context engine.
+        NOT called per-turn — only at CLI exit, /reset, gateway
         session expiry, etc.
         """
         if self._memory_manager:
@@ -2723,6 +2914,15 @@ class AIAgent:
                 self._memory_manager.shutdown_all()
             except Exception:
                 pass
+        # Notify context engine of session end (flush DAG, close DBs, etc.)
+        if hasattr(self, "context_compressor") and self.context_compressor:
+            try:
+                self.context_compressor.on_session_end(
+                    self.session_id or "",
+                    messages or [],
+                )
+            except Exception:
+                pass
     
     def close(self) -> None:
         """Release all resources held by this agent instance.
@@ -4352,7 +4552,7 @@ class AIAgent:
             self._anthropic_api_key = runtime_key
             self._anthropic_base_url = runtime_base
             self._anthropic_client = build_anthropic_client(runtime_key, runtime_base)
-            self._is_anthropic_oauth = _is_oauth_token(runtime_key) if self.provider == "anthropic" else False
+            self._is_anthropic_oauth = _is_oauth_token(runtime_key)
             self.api_key = runtime_key
             self.base_url = runtime_base
             return
@@ -5174,7 +5374,7 @@ class AIAgent:
             except Exception:
                 pass
 
-            # Determine api_mode from provider / base URL
+            # Determine api_mode from provider / base URL / model
             fb_api_mode = "chat_completions"
             fb_base_url = str(fb_client.base_url)
             if fb_provider == "openai-codex":
@@ -5183,6 +5383,10 @@ class AIAgent:
                 fb_api_mode = "anthropic_messages"
             elif self._is_direct_openai_url(fb_base_url):
                 fb_api_mode = "codex_responses"
+            elif self._model_requires_responses_api(fb_model):
+                # GPT-5.x models need Responses API on every provider
+                # (OpenRouter, Copilot, direct OpenAI, etc.)
+                fb_api_mode = "codex_responses"
 
             old_model = self.model
             self.model = fb_model
@@ -5224,7 +5428,7 @@ class AIAgent:
                 }
 
             # Re-evaluate prompt caching for the new provider/model
-            is_native_anthropic = fb_api_mode == "anthropic_messages"
+            is_native_anthropic = fb_api_mode == "anthropic_messages" and fb_provider == "anthropic"
             self._use_prompt_caching = (
                 ("openrouter" in fb_base_url.lower() and "claude" in fb_model.lower())
                 or is_native_anthropic
@@ -5240,13 +5444,12 @@ class AIAgent:
                     self.model, base_url=self.base_url,
                     api_key=self.api_key, provider=self.provider,
                 )
-                self.context_compressor.model = self.model
-                self.context_compressor.base_url = self.base_url
-                self.context_compressor.api_key = self.api_key
-                self.context_compressor.provider = self.provider
-                self.context_compressor.context_length = fb_context_length
-                self.context_compressor.threshold_tokens = int(
-                    fb_context_length * self.context_compressor.threshold_percent
+                self.context_compressor.update_model(
+                    model=self.model,
+                    context_length=fb_context_length,
+                    base_url=self.base_url,
+                    api_key=getattr(self, "api_key", ""),
+                    provider=self.provider,
                 )
 
             self._emit_status(
@@ -5272,8 +5475,8 @@ class AIAgent:
         to the fallback provider for every subsequent turn.  Calling this at
         the top of ``run_conversation()`` makes fallback turn-scoped.
 
-        The gateway creates a fresh agent per message so this is a no-op
-        there (``_fallback_activated`` is always False at turn start).
+        The gateway caches agents across messages (``_agent_cache`` in
+        ``gateway/run.py``), so this restoration IS needed there too.
         """
         if not self._fallback_activated:
             return False
@@ -5306,14 +5509,15 @@ class AIAgent:
                     shared=True,
                 )
 
-            # ── Restore context compressor state ──
+            # ── Restore context engine state ──
             cc = self.context_compressor
-            cc.model = rt["compressor_model"]
-            cc.base_url = rt["compressor_base_url"]
-            cc.api_key = rt["compressor_api_key"]
-            cc.provider = rt["compressor_provider"]
-            cc.context_length = rt["compressor_context_length"]
-            cc.threshold_tokens = rt["compressor_threshold_tokens"]
+            cc.update_model(
+                model=rt["compressor_model"],
+                context_length=rt["compressor_context_length"],
+                base_url=rt["compressor_base_url"],
+                api_key=rt["compressor_api_key"],
+                provider=rt["compressor_provider"],
+            )
 
             # ── Reset fallback chain for the new turn ──
             self._fallback_activated = False
@@ -5560,11 +5764,12 @@ class AIAgent:
     def _anthropic_preserve_dots(self) -> bool:
         """True when using an anthropic-compatible endpoint that preserves dots in model names.
         Alibaba/DashScope keeps dots (e.g. qwen3.5-plus).
+        MiniMax keeps dots (e.g. MiniMax-M2.7).
         OpenCode Go keeps dots (e.g. minimax-m2.7)."""
-        if (getattr(self, "provider", "") or "").lower() in {"alibaba", "opencode-go"}:
+        if (getattr(self, "provider", "") or "").lower() in {"alibaba", "minimax", "minimax-cn", "opencode-go"}:
             return True
         base = (getattr(self, "base_url", "") or "").lower()
-        return "dashscope" in base or "aliyuncs" in base or "opencode.ai/zen/go" in base
+        return "dashscope" in base or "aliyuncs" in base or "minimax" in base or "opencode.ai/zen/go" in base
 
     def _is_qwen_portal(self) -> bool:
         """Return True when the base URL targets Qwen Portal."""
@@ -5810,8 +6015,16 @@ class AIAgent:
             api_kwargs["tools"] = self.tools
 
         if self.max_tokens is not None:
-            if not self._is_qwen_portal():
-                api_kwargs.update(self._max_tokens_param(self.max_tokens))
+            api_kwargs.update(self._max_tokens_param(self.max_tokens))
+        elif self._is_qwen_portal():
+            # Qwen Portal defaults to a very low max_tokens when omitted.
+            # Reasoning models (qwen3-coder-plus) exhaust that budget on
+            # thinking tokens alone, causing the portal to return
+            # finish_reason="stop" with truncated output — the agent sees
+            # this as an intentional stop and exits the loop.  Send 65536
+            # (the documented max output for qwen3-coder models) so the
+            # model has adequate output budget for tool calls.
+            api_kwargs.update(self._max_tokens_param(65536))
         elif (self._is_openrouter_url() or "nousresearch" in self._base_url_lower) and "claude" in (self.model or "").lower():
             # OpenRouter and Nous Portal translate requests to Anthropic's
             # Messages API, which requires max_tokens as a mandatory field.
@@ -6878,6 +7091,29 @@ class AIAgent:
                         spinner.stop(cute_msg)
                     elif self._should_emit_quiet_tool_messages():
                         self._vprint(f"  {cute_msg}")
+            elif self._context_engine_tool_names and function_name in self._context_engine_tool_names:
+                # Context engine tools (lcm_grep, lcm_describe, lcm_expand, etc.)
+                spinner = None
+                if self.quiet_mode and not self.tool_progress_callback:
+                    face = random.choice(KawaiiSpinner.KAWAII_WAITING)
+                    emoji = _get_tool_emoji(function_name)
+                    preview = _build_tool_preview(function_name, function_args) or function_name
+                    spinner = KawaiiSpinner(f"{face} {emoji} {preview}", spinner_type='dots', print_fn=self._print_fn)
+                    spinner.start()
+                _ce_result = None
+                try:
+                    function_result = self.context_compressor.handle_tool_call(function_name, function_args, messages=messages)
+                    _ce_result = function_result
+                except Exception as tool_error:
+                    function_result = json.dumps({"error": f"Context engine tool '{function_name}' failed: {tool_error}"})
+                    logger.error("context_engine.handle_tool_call raised for %s: %s", function_name, tool_error, exc_info=True)
+                finally:
+                    tool_duration = time.time() - tool_start_time
+                    cute_msg = _get_cute_tool_message_impl(function_name, function_args, tool_duration, result=_ce_result)
+                    if spinner:
+                        spinner.stop(cute_msg)
+                    elif self.quiet_mode:
+                        self._vprint(f"  {cute_msg}")
             elif self._memory_manager and self._memory_manager.has_tool(function_name):
                 # Memory provider tools (hindsight_retain, honcho_search, etc.)
                 # These are not in the tool registry — route through MemoryManager.
@@ -7336,6 +7572,12 @@ class AIAgent:
                     )
             except Exception:
                 pass
+        # Replay compression warning through status_callback for gateway
+        # platforms (the callback was not wired during __init__).
+        if self._compression_warning:
+            self._replay_compression_warning()
+            self._compression_warning = None  # send once
+
         # NOTE: _turns_since_memory and _iters_since_skill are NOT reset here.
         # They are initialized in __init__ and must persist across run_conversation
         # calls so that nudge logic accumulates correctly in CLI mode.
@@ -7533,6 +7775,7 @@ class AIAgent:
                 is_first_turn=(not bool(conversation_history)),
                 model=self.model,
                 platform=getattr(self, "platform", None) or "",
+                sender_id=getattr(self, "_user_id", None) or "",
             )
             _ctx_parts: list[str] = []
             for r in _pre_results:
@@ -8192,7 +8435,7 @@ class AIAgent:
                         # Cache discovered context length after successful call.
                         # Only persist limits confirmed by the provider (parsed
                         # from the error message), not guessed probe tiers.
-                        if self.context_compressor._context_probed:
+                        if getattr(self.context_compressor, "_context_probed", False):
                             ctx = self.context_compressor.context_length
                             if getattr(self.context_compressor, "_context_probe_persistable", False):
                                 save_context_length(self.model, self.base_url, ctx)
@@ -8531,16 +8774,22 @@ class AIAgent:
                         compressor = self.context_compressor
                         old_ctx = compressor.context_length
                         if old_ctx > _reduced_ctx:
-                            compressor.context_length = _reduced_ctx
-                            compressor.threshold_tokens = int(
-                                _reduced_ctx * compressor.threshold_percent
+                            compressor.update_model(
+                                model=self.model,
+                                context_length=_reduced_ctx,
+                                base_url=self.base_url,
+                                api_key=getattr(self, "api_key", ""),
+                                provider=self.provider,
                             )
-                            compressor._context_probed = True
-                            # Don't persist — this is a subscription-tier
-                            # limitation, not a model capability.  If the user
-                            # later enables extra usage the 1M limit should
-                            # come back automatically.
-                            compressor._context_probe_persistable = False
+                            # Context probing flags — only set on built-in
+                            # compressor (plugin engines manage their own).
+                            if hasattr(compressor, "_context_probed"):
+                                compressor._context_probed = True
+                                # Don't persist — this is a subscription-tier
+                                # limitation, not a model capability.  If the
+                                # user later enables extra usage the 1M limit
+                                # should come back automatically.
+                                compressor._context_probe_persistable = False
                             self._vprint(
                                 f"{self.log_prefix}⚠️  Anthropic long-context tier "
                                 f"requires extra usage — reducing context: "
@@ -8704,17 +8953,25 @@ class AIAgent:
                             new_ctx = get_next_probe_tier(old_ctx)
 
                         if new_ctx and new_ctx < old_ctx:
-                            compressor.context_length = new_ctx
-                            compressor.threshold_tokens = int(new_ctx * compressor.threshold_percent)
-                            compressor._context_probed = True
-                            # Only persist limits parsed from the provider's
-                            # error message (a real number).  Guessed fallback
-                            # tiers from get_next_probe_tier() should stay
-                            # in-memory only — persisting them pollutes the
-                            # cache with wrong values.
-                            compressor._context_probe_persistable = bool(
-                                parsed_limit and parsed_limit == new_ctx
+                            compressor.update_model(
+                                model=self.model,
+                                context_length=new_ctx,
+                                base_url=self.base_url,
+                                api_key=getattr(self, "api_key", ""),
+                                provider=self.provider,
                             )
+                            # Context probing flags — only set on built-in
+                            # compressor (plugin engines manage their own).
+                            if hasattr(compressor, "_context_probed"):
+                                compressor._context_probed = True
+                                # Only persist limits parsed from the provider's
+                                # error message (a real number).  Guessed fallback
+                                # tiers from get_next_probe_tier() should stay
+                                # in-memory only — persisting them pollutes the
+                                # cache with wrong values.
+                                compressor._context_probe_persistable = bool(
+                                    parsed_limit and parsed_limit == new_ctx
+                                )
                             self._vprint(f"{self.log_prefix}⚠️  Context length exceeded — stepping down: {old_ctx:,} → {new_ctx:,} tokens", force=True)
                         else:
                             self._vprint(f"{self.log_prefix}⚠️  Context length exceeded at minimum tier — attempting compression...", force=True)
@@ -9459,7 +9716,8 @@ class AIAgent:
                         fallback = getattr(self, '_last_content_with_tools', None)
                         if fallback:
                             _turn_exit_reason = "fallback_prior_turn_content"
-                            logger.debug("Empty follow-up after tool calls — using prior turn content as final response")
+                            logger.info("Empty follow-up after tool calls — using prior turn content as final response")
+                            self._emit_status("↻ Empty response after tool calls — using earlier content as final answer")
                             self._last_content_with_tools = None
                             self._empty_content_retries = 0
                             for i in range(len(messages) - 1, -1, -1):
@@ -9490,9 +9748,13 @@ class AIAgent:
                         )
                         if _has_structured and self._thinking_prefill_retries < 2:
                             self._thinking_prefill_retries += 1
-                            self._vprint(
-                                f"{self.log_prefix}↻ Thinking-only response — "
-                                f"prefilling to continue "
+                            logger.info(
+                                "Thinking-only response (no visible content) — "
+                                "prefilling to continue (%d/2)",
+                                self._thinking_prefill_retries,
+                            )
+                            self._emit_status(
+                                f"↻ Thinking-only response — prefilling to continue "
                                 f"({self._thinking_prefill_retries}/2)"
                             )
                             interim_msg = self._build_assistant_message(
@@ -9508,23 +9770,57 @@ class AIAgent:
                         # Model returned nothing — no content, no
                         # structured reasoning, no tool calls.  Common
                         # with open models (transient provider issues,
-                        # rate limits, sampling flukes).  Silently retry
-                        # up to 3 times before giving up.  Skip when
+                        # rate limits, sampling flukes).  Retry up to 3
+                        # times before attempting fallback.  Skip when
                         # content has inline <think> tags (model chose
                         # to reason, just no visible text).
                         _truly_empty = not final_response.strip()
                         if _truly_empty and not _has_structured and self._empty_content_retries < 3:
                             self._empty_content_retries += 1
-                            self._vprint(
-                                f"{self.log_prefix}↻ Empty response (no content or reasoning) "
-                                f"— retrying ({self._empty_content_retries}/3)",
-                                force=True,
+                            logger.warning(
+                                "Empty response (no content or reasoning) — "
+                                "retry %d/3 (model=%s)",
+                                self._empty_content_retries, self.model,
+                            )
+                            self._emit_status(
+                                f"⚠️ Empty response from model — retrying "
+                                f"({self._empty_content_retries}/3)"
                             )
                             continue
 
-                        # Exhausted prefill attempts, empty retries, or
-                        # structured reasoning with no content —
-                        # fall through to "(empty)" terminal.
+                        # ── Exhausted retries — try fallback provider ──
+                        # Before giving up with "(empty)", attempt to
+                        # switch to the next provider in the fallback
+                        # chain.  This covers the case where a model
+                        # (e.g. GLM-4.5-Air) consistently returns empty
+                        # due to context degradation or provider issues.
+                        if _truly_empty and self._fallback_chain:
+                            logger.warning(
+                                "Empty response after %d retries — "
+                                "attempting fallback (model=%s, provider=%s)",
+                                self._empty_content_retries, self.model,
+                                self.provider,
+                            )
+                            self._emit_status(
+                                "⚠️ Model returning empty responses — "
+                                "switching to fallback provider..."
+                            )
+                            if self._try_activate_fallback():
+                                self._empty_content_retries = 0
+                                self._emit_status(
+                                    f"↻ Switched to fallback: {self.model} "
+                                    f"({self.provider})"
+                                )
+                                logger.info(
+                                    "Fallback activated after empty responses: "
+                                    "now using %s on %s",
+                                    self.model, self.provider,
+                                )
+                                continue
+
+                        # Exhausted retries and fallback chain (or no
+                        # fallback configured).  Fall through to the
+                        # "(empty)" terminal.
                         _turn_exit_reason = "empty_response_exhausted"
                         reasoning_text = self._extract_reasoning(assistant_message)
                         assistant_msg = self._build_assistant_message(assistant_message, finish_reason)
@@ -9533,9 +9829,28 @@ class AIAgent:
 
                         if reasoning_text:
                             reasoning_preview = reasoning_text[:500] + "..." if len(reasoning_text) > 500 else reasoning_text
-                            self._vprint(f"{self.log_prefix}ℹ️  Reasoning-only response (no visible content). Reasoning: {reasoning_preview}")
+                            logger.warning(
+                                "Reasoning-only response (no visible content) "
+                                "after exhausting retries and fallback. "
+                                "Reasoning: %s", reasoning_preview,
+                            )
+                            self._emit_status(
+                                "⚠️ Model produced reasoning but no visible "
+                                "response after all retries. Returning empty."
+                            )
                         else:
-                            self._vprint(f"{self.log_prefix}ℹ️  Empty response (no content or reasoning) after 3 retries.")
+                            logger.warning(
+                                "Empty response (no content or reasoning) "
+                                "after %d retries. No fallback available. "
+                                "model=%s provider=%s",
+                                self._empty_content_retries, self.model,
+                                self.provider,
+                            )
+                            self._emit_status(
+                                "❌ Model returned no content after all retries"
+                                + (" and fallback attempts." if self._fallback_chain else
+                                   ". No fallback providers configured.")
+                            )
 
                         final_response = "(empty)"
                         break

scripts/discord-voice-doctor.py

@@ -249,8 +249,12 @@ def check_config(groq_key, eleven_key):
 
             if stt_provider == "groq" and not groq_key:
                 warn("STT config says groq but GROQ_API_KEY is missing")
+            if stt_provider == "mistral" and not os.getenv("MISTRAL_API_KEY"):
+                warn("STT config says mistral but MISTRAL_API_KEY is missing")
             if tts_provider == "elevenlabs" and not eleven_key:
                 warn("TTS config says elevenlabs but ELEVENLABS_API_KEY is missing")
+            if tts_provider == "mistral" and not os.getenv("MISTRAL_API_KEY"):
+                warn("TTS config says mistral but MISTRAL_API_KEY is missing")
         except Exception as e:
             warn("config.yaml", f"parse error: {e}")
     else:

skills/creative/ascii-video/SKILL.md

@@ -203,3 +203,30 @@ For segmented videos (quotes, scenes, chapters), render each as a separate clip
 | `references/inputs.md` | Audio analysis (FFT, bands, beats), video sampling, image conversion, text/lyrics, TTS integration (ElevenLabs, voice assignment, audio mixing) |
 | `references/optimization.md` | Hardware detection, quality profiles, vectorized patterns, parallel rendering, memory management, performance budgets |
 | `references/troubleshooting.md` | NumPy broadcasting traps, blend mode pitfalls, multiprocessing/pickling, brightness diagnostics, ffmpeg issues, font problems, common mistakes |
+
+---
+
+## Creative Divergence (use only when user requests experimental/creative/unique output)
+
+If the user asks for creative, experimental, surprising, or unconventional output, select the strategy that best fits and reason through its steps BEFORE generating code.
+
+- **Forced Connections** — when the user wants cross-domain inspiration ("make it look organic," "industrial aesthetic")
+- **Conceptual Blending** — when the user names two things to combine ("ocean meets music," "space + calligraphy")
+- **Oblique Strategies** — when the user is maximally open ("surprise me," "something I've never seen")
+
+### Forced Connections
+1. Pick a domain unrelated to the visual goal (weather systems, microbiology, architecture, fluid dynamics, textile weaving)
+2. List its core visual/structural elements (erosion → gradual reveal; mitosis → splitting duplication; weaving → interlocking patterns)
+3. Map those elements onto ASCII characters and animation patterns
+4. Synthesize — what does "erosion" or "crystallization" look like in a character grid?
+
+### Conceptual Blending
+1. Name two distinct visual/conceptual spaces (e.g., ocean waves + sheet music)
+2. Map correspondences (crests = high notes, troughs = rests, foam = staccato)
+3. Blend selectively — keep the most interesting mappings, discard forced ones
+4. Develop emergent properties that exist only in the blend
+
+### Oblique Strategies
+1. Draw one: "Honor thy error as a hidden intention" / "Use an old idea" / "What would your closest friend do?" / "Emphasize the flaws" / "Turn it upside down" / "Only a part, not the whole" / "Reverse"
+2. Interpret the directive against the current ASCII animation challenge
+3. Apply the lateral insight to the visual design before writing code

skills/creative/creative-ideation/SKILL.md

@@ -0,0 +1,147 @@
+---
+name: ideation
+title: Creative Ideation — Constraint-Driven Project Generation
+description: "Generate project ideas through creative constraints. Use when the user says 'I want to build something', 'give me a project idea', 'I'm bored', 'what should I make', 'inspire me', or any variant of 'I have tools but no direction'. Works for code, art, hardware, writing, tools, and anything that can be made."
+version: 1.0.0
+author: SHL0MS
+license: MIT
+metadata:
+  hermes:
+    tags: [Creative, Ideation, Projects, Brainstorming, Inspiration]
+    category: creative
+    requires_toolsets: []
+---
+
+# Creative Ideation
+
+Generate project ideas through creative constraints. Constraint + direction = creativity.
+
+## How It Works
+
+1. **Pick a constraint** from the library below — random, or matched to the user's domain/mood
+2. **Interpret it broadly** — a coding prompt can become a hardware project, an art prompt can become a CLI tool
+3. **Generate 3 concrete project ideas** that satisfy the constraint
+4. **If they pick one, build it** — create the project, write the code, ship it
+
+## The Rule
+
+Every prompt is interpreted as broadly as possible. "Does this include X?" → Yes. The prompts provide direction and mild constraint. Without either, there is no creativity.
+
+## Constraint Library
+
+### For Developers
+
+**Solve your own itch:**
+Build the tool you wished existed this week. Under 50 lines. Ship it today.
+
+**Automate the annoying thing:**
+What's the most tedious part of your workflow? Script it away. Two hours to fix a problem that costs you five minutes a day.
+
+**The CLI tool that should exist:**
+Think of a command you've wished you could type. `git undo-that-thing-i-just-did`. `docker why-is-this-broken`. `npm explain-yourself`. Now build it.
+
+**Nothing new except glue:**
+Make something entirely from existing APIs, libraries, and datasets. The only original contribution is how you connect them.
+
+**Frankenstein week:**
+Take something that does X and make it do Y. A git repo that plays music. A Dockerfile that generates poetry. A cron job that sends compliments.
+
+**Subtract:**
+How much can you remove from a codebase before it breaks? Strip a tool to its minimum viable function. Delete until only the essence remains.
+
+**High concept, low effort:**
+A deep idea, lazily executed. The concept should be brilliant. The implementation should take an afternoon. If it takes longer, you're overthinking it.
+
+### For Makers & Artists
+
+**Blatantly copy something:**
+Pick something you admire — a tool, an artwork, an interface. Recreate it from scratch. The learning is in the gap between your version and theirs.
+
+**One million of something:**
+One million is both a lot and not that much. One million pixels is a 1MB photo. One million API calls is a Tuesday. One million of anything becomes interesting at scale.
+
+**Make something that dies:**
+A website that loses a feature every day. A chatbot that forgets. A countdown to nothing. An exercise in rot, killing, or letting go.
+
+**Do a lot of math:**
+Generative geometry, shader golf, mathematical art, computational origami. Time to re-learn what an arcsin is.
+
+### For Anyone
+
+**Text is the universal interface:**
+Build something where text is the only interface. No buttons, no graphics, just words in and words out. Text can go in and out of almost anything.
+
+**Start at the punchline:**
+Think of something that would be a funny sentence. Work backwards to make it real. "I taught my thermostat to gaslight me" → now build it.
+
+**Hostile UI:**
+Make something intentionally painful to use. A password field that requires 47 conditions. A form where every label lies. A CLI that judges your commands.
+
+**Take two:**
+Remember an old project. Do it again from scratch. No looking at the original. See what changed about how you think.
+
+See `references/full-prompt-library.md` for 30+ additional constraints across communication, scale, philosophy, transformation, and more.
+
+## Matching Constraints to Users
+
+| User says | Pick from |
+|-----------|-----------|
+| "I want to build something" (no direction) | Random — any constraint |
+| "I'm learning [language]" | Blatantly copy something, Automate the annoying thing |
+| "I want something weird" | Hostile UI, Frankenstein week, Start at the punchline |
+| "I want something useful" | Solve your own itch, The CLI that should exist, Automate the annoying thing |
+| "I want something beautiful" | Do a lot of math, One million of something |
+| "I'm burned out" | High concept low effort, Make something that dies |
+| "Weekend project" | Nothing new except glue, Start at the punchline |
+| "I want a challenge" | One million of something, Subtract, Take two |
+
+## Output Format
+
+```
+## Constraint: [Name]
+> [The constraint, one sentence]
+
+### Ideas
+
+1. **[One-line pitch]**
+   [2-3 sentences: what you'd build and why it's interesting]
+   ⏱ [weekend / week / month] • 🔧 [stack]
+
+2. **[One-line pitch]**
+   [2-3 sentences]
+   ⏱ ... • 🔧 ...
+
+3. **[One-line pitch]**
+   [2-3 sentences]
+   ⏱ ... • 🔧 ...
+```
+
+## Example
+
+```
+## Constraint: The CLI tool that should exist
+> Think of a command you've wished you could type. Now build it.
+
+### Ideas
+
+1. **`git whatsup` — show what happened while you were away**
+   Compares your last active commit to HEAD and summarizes what changed,
+   who committed, and what PRs merged. Like a morning standup from your repo.
+   ⏱ weekend • 🔧 Python, GitPython, click
+
+2. **`explain 503` — HTTP status codes for humans**
+   Pipe any status code or error message and get a plain-English explanation
+   with common causes and fixes. Pulls from a curated database, not an LLM.
+   ⏱ weekend • 🔧 Rust or Go, static dataset
+
+3. **`deps why <package>` — why is this in my dependency tree**
+   Traces a transitive dependency back to the direct dependency that pulled
+   it in. Answers "why do I have 47 copies of lodash" in one command.
+   ⏱ weekend • 🔧 Node.js, npm/yarn lockfile parsing
+```
+
+After the user picks one, start building — create the project, write the code, iterate.
+
+## Attribution
+
+Constraint approach inspired by [wttdotm.com/prompts.html](https://wttdotm.com/prompts.html). Adapted and expanded for software development and general-purpose ideation.

skills/creative/creative-ideation/references/full-prompt-library.md

@@ -0,0 +1,110 @@
+# Full Prompt Library
+
+Extended constraint library beyond the core set in SKILL.md. Load these when the user wants more variety or a specific category.
+
+## Communication & Connection
+
+**Create a means of distribution:**
+The project works when you can use what you made to give something to somebody else.
+
+**Make a way to communicate:**
+The project works when you can hold a conversation with someone else using what you created. Not chat — something weirder.
+
+**Write a love letter:**
+To a person, a programming language, a game, a place, a tool. On paper, in code, in music, in light. Mail it.
+
+**Mail chess / Asynchronous games:**
+Something turn-based played with no time limit. No requirement to be there at the same time. The game happens in the gaps.
+
+**Twitch plays X:**
+A group of people share control over something. Collective input, emergent behavior.
+
+## Screens & Interfaces
+
+**Something for your desktop:**
+You spend a lot of time there. Spruce it up. A custom clock, a pet that lives in your terminal, a wallpaper that changes based on your git activity.
+
+**One screen, two screen, old screen, new screen:**
+Take something you associate with one screen and put it on a very different one. DOOM on a smart fridge. A spreadsheet on a watch. A terminal in a painting.
+
+**Make a mirror:**
+Something that reflects the viewer back at themselves. A website that shows your browsing history. A CLI that prints your git sins.
+
+## Philosophy & Concept
+
+**Code as koan, koan as code:**
+What is the sound of one hand clapping? A program that answers a question it wasn't asked. A function that returns before it's called.
+
+**The useless tree:**
+Make something useless. Deliberately, completely, beautifully useless. No utility. No purpose. No point. That's the point.
+
+**Artificial stupidity:**
+Make fun of AI by showcasing its faults. Mistrain it. Lie to it. Build the opposite of what AI is supposed to be good at.
+
+**"I use technology in order to hate it properly":**
+Make something inspired by the tension between loving and hating your tools.
+
+**The more things change, the more they stay the same:**
+Reflect on time, difference, and similarity.
+
+## Transformation
+
+**Translate:**
+Take something meant for one audience and make it understandable by another. A research paper as a children's book. An API as a board game. A song as an architecture diagram.
+
+**I mean, I GUESS you could store something that way:**
+The project works when you can save and open something. Store data in DNS caches. Encode a novel in emoji. Write a file system on top of something that isn't a file system.
+
+**I mean, I GUESS those could be pixels:**
+The project works when you can display an image. Render anything visual in a medium that wasn't meant for rendering.
+
+## Identity & Reflection
+
+**Make a self-portrait:**
+Be yourself? Be fake? Be real? In code, in data, in sound, in a directory structure.
+
+**Make a pun:**
+The stupider the better. Physical, digital, linguistic, visual. The project IS the joke.
+
+**Doors, walls, borders, barriers, boundaries:**
+Things that intermediate two places: opening, closing, permeating, excluding, combining.
+
+## Scale & Repetition
+
+**Lists!:**
+Itemizations, taxonomies, exhaustive recountings, iterations. This one. A list of list of lists.
+
+**Did you mean *recursion*?**
+Did you mean recursion?
+
+**Animals:**
+Lions, and tigers, and bears. Crab logic gates. Fish plays the stock market.
+
+**Cats:**
+Where would the internet be without them.
+
+## Starting Points
+
+**An idea that comes from a book:**
+Read something. Make something inspired by it.
+
+**Go to a museum:**
+Project ensues.
+
+**NPC loot:**
+What do you drop when you die? What do you take on your journey? Build the item.
+
+**Mythological objects and entities:**
+Pandora's box, the ocarina of time, the palantir. Build the artifact.
+
+**69:**
+Nice. Make something with the joke being the number 69.
+
+**Office Space printer scene:**
+Capture the same energy. Channel the catharsis of destroying the thing that frustrates you.
+
+**Borges week:**
+Something inspired by the Argentine. The library of babel. The map that is the territory.
+
+**Lights!:**
+LED throwies, light installations, illuminated anything. Make something that glows.

skills/creative/manim-video/SKILL.md

@@ -239,3 +239,26 @@ Always iterate at `-ql`. Only render `-qh` for final output.
 | `references/paper-explainer.md` | Turning research papers into animations — workflow, templates, domain patterns |
 | `references/decorations.md` | SurroundingRectangle, Brace, arrows, DashedLine, Angle, annotation lifecycle |
 | `references/production-quality.md` | Pre-code, pre-render, post-render checklists, spatial layout, color, tempo |
+
+---
+
+## Creative Divergence (use only when user requests experimental/creative/unique output)
+
+If the user asks for creative, experimental, or unconventional explanatory approaches, select a strategy and reason through it BEFORE designing the animation.
+
+- **SCAMPER** — when the user wants a fresh take on a standard explanation
+- **Assumption Reversal** — when the user wants to challenge how something is typically taught
+
+### SCAMPER Transformation
+Take a standard mathematical/technical visualization and transform it:
+- **Substitute**: replace the standard visual metaphor (number line → winding path, matrix → city grid)
+- **Combine**: merge two explanation approaches (algebraic + geometric simultaneously)
+- **Reverse**: derive backward — start from the result and deconstruct to axioms
+- **Modify**: exaggerate a parameter to show why it matters (10x the learning rate, 1000x the sample size)
+- **Eliminate**: remove all notation — explain purely through animation and spatial relationships
+
+### Assumption Reversal
+1. List what's "standard" about how this topic is visualized (left-to-right, 2D, discrete steps, formal notation)
+2. Pick the most fundamental assumption
+3. Reverse it (right-to-left derivation, 3D embedding of a 2D concept, continuous morphing instead of steps, zero notation)
+4. Explore what the reversal reveals that the standard approach hides

skills/creative/p5js/SKILL.md

@@ -511,3 +511,37 @@ When building p5.js sketches:
 | `references/export-pipeline.md` | `saveCanvas()`, `saveGif()`, `saveFrames()`, deterministic headless capture, ffmpeg frame-to-video, CCapture.js, SVG export, per-clip architecture, platform export (fxhash), video gotchas |
 | `references/troubleshooting.md` | Performance profiling, per-pixel budgets, common mistakes, browser compatibility, WebGL debugging, font loading issues, pixel density traps, memory leaks, CORS |
 | `templates/viewer.html` | Interactive viewer template: seed navigation (prev/next/random/jump), parameter sliders, download PNG, responsive canvas. Start from this for explorable generative art |
+
+---
+
+## Creative Divergence (use only when user requests experimental/creative/unique output)
+
+If the user asks for creative, experimental, surprising, or unconventional output, select the strategy that best fits and reason through its steps BEFORE generating code.
+
+- **Conceptual Blending** — when the user names two things to combine or wants hybrid aesthetics
+- **SCAMPER** — when the user wants a twist on a known generative art pattern
+- **Distance Association** — when the user gives a single concept and wants exploration ("make something about time")
+
+### Conceptual Blending
+1. Name two distinct visual systems (e.g., particle physics + handwriting)
+2. Map correspondences (particles = ink drops, forces = pen pressure, fields = letterforms)
+3. Blend selectively — keep mappings that produce interesting emergent visuals
+4. Code the blend as a unified system, not two systems side-by-side
+
+### SCAMPER Transformation
+Take a known generative pattern (flow field, particle system, L-system, cellular automata) and systematically transform it:
+- **Substitute**: replace circles with text characters, lines with gradients
+- **Combine**: merge two patterns (flow field + voronoi)
+- **Adapt**: apply a 2D pattern to a 3D projection
+- **Modify**: exaggerate scale, warp the coordinate space
+- **Purpose**: use a physics sim for typography, a sorting algorithm for color
+- **Eliminate**: remove the grid, remove color, remove symmetry
+- **Reverse**: run the simulation backward, invert the parameter space
+
+### Distance Association
+1. Anchor on the user's concept (e.g., "loneliness")
+2. Generate associations at three distances:
+   - Close (obvious): empty room, single figure, silence
+   - Medium (interesting): one fish in a school swimming the wrong way, a phone with no notifications, the gap between subway cars
+   - Far (abstract): prime numbers, asymptotic curves, the color of 3am
+3. Develop the medium-distance associations — they're specific enough to visualize but unexpected enough to be interesting

tests/agent/test_anthropic_adapter.py

@@ -39,8 +39,13 @@ class TestIsOAuthToken:
         assert _is_oauth_token("sk-ant-api03-abcdef1234567890") is False
 
     def test_managed_key(self):
-        # Managed keys from ~/.claude.json are NOT regular API keys
-        assert _is_oauth_token("ou1R1z-ft0A-bDeZ9wAA") is True
+        # Managed keys from ~/.claude.json without a recognisable Anthropic
+        # prefix are not positively identified as OAuth.  They enter the system
+        # via diagnostics-only read_claude_managed_key(), not via
+        # resolve_anthropic_token(), so they don't reach the OAuth gate in
+        # practice.  Third-party provider keys (MiniMax, Alibaba) also lack
+        # the sk-ant- prefix and must NOT be treated as OAuth.
+        assert _is_oauth_token("ou1R1z-ft0A-bDeZ9wAA") is False
 
     def test_jwt_token(self):
         # JWTs from OAuth flow

tests/agent/test_auxiliary_client.py

@@ -1,9 +1,10 @@
 """Tests for agent.auxiliary_client resolution chain, provider overrides, and model overrides."""
 
 import json
+import logging
 import os
 from pathlib import Path
-from unittest.mock import patch, MagicMock
+from unittest.mock import patch, MagicMock, AsyncMock
 
 import pytest
 
@@ -14,6 +15,7 @@ from agent.auxiliary_client import (
     resolve_provider_client,
     auxiliary_max_tokens_param,
     call_llm,
+    async_call_llm,
     _read_codex_access_token,
     _get_auxiliary_provider,
     _get_provider_chain,
@@ -756,6 +758,69 @@ class TestAuxiliaryPoolAwareness:
         assert call_kwargs["base_url"] == "https://api.githubcopilot.com"
         assert call_kwargs["default_headers"]["Editor-Version"]
 
+    def test_copilot_responses_api_model_wrapped_in_codex_client(self, monkeypatch):
+        """Copilot GPT-5+ models (needing Responses API) are wrapped in CodexAuxiliaryClient."""
+        monkeypatch.delenv("GITHUB_TOKEN", raising=False)
+        monkeypatch.delenv("GH_TOKEN", raising=False)
+
+        with (
+            patch(
+                "hermes_cli.auth.resolve_api_key_provider_credentials",
+                return_value={
+                    "provider": "copilot",
+                    "api_key": "test-token",
+                    "base_url": "https://api.githubcopilot.com",
+                    "source": "gh auth token",
+                },
+            ),
+            patch("agent.auxiliary_client.OpenAI"),
+        ):
+            client, model = resolve_provider_client("copilot", model="gpt-5.4-mini")
+
+        from agent.auxiliary_client import CodexAuxiliaryClient
+        assert isinstance(client, CodexAuxiliaryClient)
+        assert model == "gpt-5.4-mini"
+
+    def test_copilot_chat_completions_model_not_wrapped(self, monkeypatch):
+        """Copilot models using Chat Completions are returned as plain OpenAI clients."""
+        monkeypatch.delenv("GITHUB_TOKEN", raising=False)
+        monkeypatch.delenv("GH_TOKEN", raising=False)
+
+        with (
+            patch(
+                "hermes_cli.auth.resolve_api_key_provider_credentials",
+                return_value={
+                    "provider": "copilot",
+                    "api_key": "test-token",
+                    "base_url": "https://api.githubcopilot.com",
+                    "source": "gh auth token",
+                },
+            ),
+            patch("agent.auxiliary_client.OpenAI") as mock_openai,
+        ):
+            client, model = resolve_provider_client("copilot", model="gpt-4.1-mini")
+
+        from agent.auxiliary_client import CodexAuxiliaryClient
+        assert not isinstance(client, CodexAuxiliaryClient)
+        assert model == "gpt-4.1-mini"
+        # Should be the raw mock OpenAI client
+        assert client is mock_openai.return_value
+
+    def test_vision_auto_uses_active_provider_as_fallback(self, monkeypatch):
+        """When no OpenRouter/Nous available, vision auto falls back to active provider."""
+        monkeypatch.setenv("ANTHROPIC_API_KEY", "***")
+        with (
+            patch("agent.auxiliary_client._read_nous_auth", return_value=None),
+            patch("agent.auxiliary_client._read_main_provider", return_value="anthropic"),
+            patch("agent.auxiliary_client._read_main_model", return_value="claude-sonnet-4"),
+            patch("agent.anthropic_adapter.build_anthropic_client", return_value=MagicMock()),
+            patch("agent.anthropic_adapter.resolve_anthropic_token", return_value="***"),
+        ):
+            client, model = get_vision_auxiliary_client()
+
+        assert client is not None
+        assert client.__class__.__name__ == "AnthropicAuxiliaryClient"
+
     def test_vision_auto_prefers_active_provider_over_openrouter(self, monkeypatch):
         """Active provider is tried before OpenRouter in vision auto."""
         monkeypatch.setenv("OPENROUTER_API_KEY", "or-key")
@@ -1059,8 +1124,8 @@ class TestCallLlmPaymentFallback:
         exc.status_code = 402
         return exc
 
-    def test_402_triggers_fallback(self, monkeypatch):
-        """When the primary provider returns 402, call_llm tries the next one."""
+    def test_402_triggers_fallback_when_auto(self, monkeypatch):
+        """When provider is auto and returns 402, call_llm tries the next one."""
         monkeypatch.setenv("OPENROUTER_API_KEY", "or-key")
 
         primary_client = MagicMock()
@@ -1073,7 +1138,7 @@ class TestCallLlmPaymentFallback:
         with patch("agent.auxiliary_client._get_cached_client",
                     return_value=(primary_client, "google/gemini-3-flash-preview")), \
              patch("agent.auxiliary_client._resolve_task_provider_model",
-                    return_value=("openrouter", "google/gemini-3-flash-preview", None, None)), \
+                    return_value=("auto", "google/gemini-3-flash-preview", None, None, None)), \
              patch("agent.auxiliary_client._try_payment_fallback",
                     return_value=(fallback_client, "gpt-5.2-codex", "openai-codex")) as mock_fb:
             result = call_llm(
@@ -1082,13 +1147,62 @@ class TestCallLlmPaymentFallback:
             )
 
         assert result is fallback_response
-        mock_fb.assert_called_once_with("openrouter", "compression")
+        mock_fb.assert_called_once_with("auto", "compression", reason="payment error")
         # Fallback call should use the fallback model
         fb_kwargs = fallback_client.chat.completions.create.call_args.kwargs
         assert fb_kwargs["model"] == "gpt-5.2-codex"
 
+    def test_402_no_fallback_when_explicit_provider(self, monkeypatch):
+        """When provider is explicitly configured (not auto), 402 should NOT fallback (#7559)."""
+        monkeypatch.setenv("OPENROUTER_API_KEY", "or-key")
+
+        primary_client = MagicMock()
+        primary_client.chat.completions.create.side_effect = self._make_402_error()
+
+        with patch("agent.auxiliary_client._get_cached_client",
+                    return_value=(primary_client, "local-model")), \
+             patch("agent.auxiliary_client._resolve_task_provider_model",
+                    return_value=("custom", "local-model", None, None, None)), \
+             patch("agent.auxiliary_client._try_payment_fallback") as mock_fb:
+            with pytest.raises(Exception, match="insufficient credits"):
+                call_llm(
+                    task="compression",
+                    messages=[{"role": "user", "content": "hello"}],
+                )
+
+        # Fallback should NOT be attempted when provider is explicit
+        mock_fb.assert_not_called()
+
+    def test_connection_error_triggers_fallback_when_auto(self, monkeypatch):
+        """Connection errors also trigger fallback when provider is auto."""
+        monkeypatch.setenv("OPENROUTER_API_KEY", "or-key")
+
+        primary_client = MagicMock()
+        conn_err = Exception("Connection refused")
+        conn_err.status_code = None
+        primary_client.chat.completions.create.side_effect = conn_err
+
+        fallback_client = MagicMock()
+        fallback_response = MagicMock()
+        fallback_client.chat.completions.create.return_value = fallback_response
+
+        with patch("agent.auxiliary_client._get_cached_client",
+                    return_value=(primary_client, "model")), \
+             patch("agent.auxiliary_client._resolve_task_provider_model",
+                    return_value=("auto", "model", None, None, None)), \
+             patch("agent.auxiliary_client._is_connection_error", return_value=True), \
+             patch("agent.auxiliary_client._try_payment_fallback",
+                    return_value=(fallback_client, "fb-model", "nous")) as mock_fb:
+            result = call_llm(
+                task="compression",
+                messages=[{"role": "user", "content": "hello"}],
+            )
+
+        assert result is fallback_response
+        mock_fb.assert_called_once_with("auto", "compression", reason="connection error")
+
     def test_non_payment_error_not_caught(self, monkeypatch):
-        """Non-payment errors (500, connection, etc.) should NOT trigger fallback."""
+        """Non-payment/non-connection errors (500) should NOT trigger fallback."""
         monkeypatch.setenv("OPENROUTER_API_KEY", "or-key")
 
         primary_client = MagicMock()
@@ -1099,7 +1213,7 @@ class TestCallLlmPaymentFallback:
         with patch("agent.auxiliary_client._get_cached_client",
                     return_value=(primary_client, "google/gemini-3-flash-preview")), \
              patch("agent.auxiliary_client._resolve_task_provider_model",
-                    return_value=("openrouter", "google/gemini-3-flash-preview", None, None)):
+                    return_value=("auto", "google/gemini-3-flash-preview", None, None, None)):
             with pytest.raises(Exception, match="Internal Server Error"):
                 call_llm(
                     task="compression",
@@ -1116,7 +1230,7 @@ class TestCallLlmPaymentFallback:
         with patch("agent.auxiliary_client._get_cached_client",
                     return_value=(primary_client, "google/gemini-3-flash-preview")), \
              patch("agent.auxiliary_client._resolve_task_provider_model",
-                    return_value=("openrouter", "google/gemini-3-flash-preview", None, None)), \
+                    return_value=("auto", "google/gemini-3-flash-preview", None, None, None)), \
              patch("agent.auxiliary_client._try_payment_fallback",
                     return_value=(None, None, "")):
             with pytest.raises(Exception, match="insufficient credits"):
@@ -1166,3 +1280,283 @@ def test_resolve_api_key_provider_skips_unconfigured_anthropic(monkeypatch):
 
     assert "anthropic" not in called, \
         "_try_anthropic() should not be called when anthropic is not explicitly configured"
+
+
+# ---------------------------------------------------------------------------
+# model="default" elimination (#7512)
+# ---------------------------------------------------------------------------
+
+
+class TestModelDefaultElimination:
+    """_resolve_api_key_provider must skip providers without known aux models."""
+
+    def test_unknown_provider_skipped(self, monkeypatch):
+        """Providers not in _API_KEY_PROVIDER_AUX_MODELS are skipped, not sent model='default'."""
+        from agent.auxiliary_client import _API_KEY_PROVIDER_AUX_MODELS
+
+        # Verify our known providers have entries
+        assert "gemini" in _API_KEY_PROVIDER_AUX_MODELS
+        assert "kimi-coding" in _API_KEY_PROVIDER_AUX_MODELS
+
+        # A random provider_id not in the dict should return None
+        assert _API_KEY_PROVIDER_AUX_MODELS.get("totally-unknown-provider") is None
+
+    def test_known_provider_gets_real_model(self):
+        """Known providers get a real model name, not 'default'."""
+        from agent.auxiliary_client import _API_KEY_PROVIDER_AUX_MODELS
+
+        for provider_id, model in _API_KEY_PROVIDER_AUX_MODELS.items():
+            assert model != "default", f"{provider_id} should not map to 'default'"
+            assert isinstance(model, str) and model.strip(), \
+                f"{provider_id} should have a non-empty model string"
+
+
+# ---------------------------------------------------------------------------
+# _try_payment_fallback reason parameter (#7512 bug 3)
+# ---------------------------------------------------------------------------
+
+
+class TestTryPaymentFallbackReason:
+    """_try_payment_fallback uses the reason parameter in log messages."""
+
+    def test_reason_parameter_passed_through(self, monkeypatch):
+        """The reason= parameter is accepted without error."""
+        from agent.auxiliary_client import _try_payment_fallback
+
+        # Mock the provider chain to return nothing
+        monkeypatch.setattr(
+            "agent.auxiliary_client._get_provider_chain",
+            lambda: [],
+        )
+        monkeypatch.setattr(
+            "agent.auxiliary_client._read_main_provider",
+            lambda: "",
+        )
+
+        client, model, label = _try_payment_fallback(
+            "openrouter", task="compression", reason="connection error"
+        )
+        assert client is None
+        assert label == ""
+
+
+# ---------------------------------------------------------------------------
+# _is_connection_error coverage
+# ---------------------------------------------------------------------------
+
+
+class TestIsConnectionError:
+    """Tests for _is_connection_error detection."""
+
+    def test_connection_refused(self):
+        from agent.auxiliary_client import _is_connection_error
+        err = Exception("Connection refused")
+        assert _is_connection_error(err) is True
+
+    def test_timeout(self):
+        from agent.auxiliary_client import _is_connection_error
+        err = Exception("Request timed out.")
+        assert _is_connection_error(err) is True
+
+    def test_dns_failure(self):
+        from agent.auxiliary_client import _is_connection_error
+        err = Exception("Name or service not known")
+        assert _is_connection_error(err) is True
+
+    def test_normal_api_error_not_connection(self):
+        from agent.auxiliary_client import _is_connection_error
+        err = Exception("Bad Request: invalid model")
+        err.status_code = 400
+        assert _is_connection_error(err) is False
+
+    def test_500_not_connection(self):
+        from agent.auxiliary_client import _is_connection_error
+        err = Exception("Internal Server Error")
+        err.status_code = 500
+        assert _is_connection_error(err) is False
+
+
+# ---------------------------------------------------------------------------
+# async_call_llm payment / connection fallback (#7512 bug 2)
+# ---------------------------------------------------------------------------
+
+
+class TestAsyncCallLlmFallback:
+    """async_call_llm mirrors call_llm fallback behavior."""
+
+    def _make_402_error(self, msg="Payment Required: insufficient credits"):
+        exc = Exception(msg)
+        exc.status_code = 402
+        return exc
+
+    @pytest.mark.asyncio
+    async def test_402_triggers_async_fallback_when_auto(self, monkeypatch):
+        """When provider is auto and returns 402, async_call_llm tries fallback."""
+        monkeypatch.setenv("OPENROUTER_API_KEY", "or-key")
+
+        primary_client = MagicMock()
+        primary_client.chat.completions.create = AsyncMock(
+            side_effect=self._make_402_error())
+
+        # Fallback client (sync) returned by _try_payment_fallback
+        fb_sync_client = MagicMock()
+        fb_async_client = MagicMock()
+        fb_response = MagicMock()
+        fb_async_client.chat.completions.create = AsyncMock(return_value=fb_response)
+
+        with patch("agent.auxiliary_client._get_cached_client",
+                    return_value=(primary_client, "google/gemini-3-flash-preview")), \
+             patch("agent.auxiliary_client._resolve_task_provider_model",
+                    return_value=("auto", "google/gemini-3-flash-preview", None, None, None)), \
+             patch("agent.auxiliary_client._try_payment_fallback",
+                    return_value=(fb_sync_client, "gpt-5.2-codex", "openai-codex")) as mock_fb, \
+             patch("agent.auxiliary_client._to_async_client",
+                    return_value=(fb_async_client, "gpt-5.2-codex")):
+            result = await async_call_llm(
+                task="compression",
+                messages=[{"role": "user", "content": "hello"}],
+            )
+
+        assert result is fb_response
+        mock_fb.assert_called_once_with("auto", "compression", reason="payment error")
+
+    @pytest.mark.asyncio
+    async def test_402_no_async_fallback_when_explicit(self, monkeypatch):
+        """When provider is explicit, 402 should NOT trigger async fallback."""
+        monkeypatch.setenv("OPENROUTER_API_KEY", "or-key")
+
+        primary_client = MagicMock()
+        primary_client.chat.completions.create = AsyncMock(
+            side_effect=self._make_402_error())
+
+        with patch("agent.auxiliary_client._get_cached_client",
+                    return_value=(primary_client, "local-model")), \
+             patch("agent.auxiliary_client._resolve_task_provider_model",
+                    return_value=("custom", "local-model", None, None, None)), \
+             patch("agent.auxiliary_client._try_payment_fallback") as mock_fb:
+            with pytest.raises(Exception, match="insufficient credits"):
+                await async_call_llm(
+                    task="compression",
+                    messages=[{"role": "user", "content": "hello"}],
+                )
+
+        mock_fb.assert_not_called()
+
+    @pytest.mark.asyncio
+    async def test_connection_error_triggers_async_fallback(self, monkeypatch):
+        """Connection errors trigger async fallback when provider is auto."""
+        monkeypatch.setenv("OPENROUTER_API_KEY", "or-key")
+
+        primary_client = MagicMock()
+        conn_err = Exception("Connection refused")
+        conn_err.status_code = None
+        primary_client.chat.completions.create = AsyncMock(side_effect=conn_err)
+
+        fb_sync_client = MagicMock()
+        fb_async_client = MagicMock()
+        fb_response = MagicMock()
+        fb_async_client.chat.completions.create = AsyncMock(return_value=fb_response)
+
+        with patch("agent.auxiliary_client._get_cached_client",
+                    return_value=(primary_client, "model")), \
+             patch("agent.auxiliary_client._resolve_task_provider_model",
+                    return_value=("auto", "model", None, None, None)), \
+             patch("agent.auxiliary_client._is_connection_error", return_value=True), \
+             patch("agent.auxiliary_client._try_payment_fallback",
+                    return_value=(fb_sync_client, "fb-model", "nous")) as mock_fb, \
+             patch("agent.auxiliary_client._to_async_client",
+                    return_value=(fb_async_client, "fb-model")):
+            result = await async_call_llm(
+                task="compression",
+                messages=[{"role": "user", "content": "hello"}],
+            )
+
+        assert result is fb_response
+        mock_fb.assert_called_once_with("auto", "compression", reason="connection error")
+class TestStaleBaseUrlWarning:
+    """_resolve_auto() warns when OPENAI_BASE_URL conflicts with config provider (#5161)."""
+
+    def test_warns_when_openai_base_url_set_with_named_provider(self, monkeypatch, caplog):
+        """Warning fires when OPENAI_BASE_URL is set but provider is a named provider."""
+        import agent.auxiliary_client as mod
+        # Reset the module-level flag so the warning fires
+        monkeypatch.setattr(mod, "_stale_base_url_warned", False)
+        monkeypatch.setenv("OPENAI_BASE_URL", "http://localhost:11434/v1")
+        monkeypatch.setenv("OPENROUTER_API_KEY", "sk-or-test")
+
+        with patch("agent.auxiliary_client._read_main_provider", return_value="openrouter"), \
+             patch("agent.auxiliary_client._read_main_model", return_value="google/gemini-flash"), \
+             caplog.at_level(logging.WARNING, logger="agent.auxiliary_client"):
+            _resolve_auto()
+
+        assert any("OPENAI_BASE_URL is set" in rec.message for rec in caplog.records), \
+            "Expected a warning about stale OPENAI_BASE_URL"
+        assert mod._stale_base_url_warned is True
+
+    def test_no_warning_when_provider_is_custom(self, monkeypatch, caplog):
+        """No warning when the provider is 'custom' — OPENAI_BASE_URL is expected."""
+        import agent.auxiliary_client as mod
+        monkeypatch.setattr(mod, "_stale_base_url_warned", False)
+        monkeypatch.setenv("OPENAI_BASE_URL", "http://localhost:11434/v1")
+        monkeypatch.setenv("OPENAI_API_KEY", "test-key")
+
+        with patch("agent.auxiliary_client._read_main_provider", return_value="custom"), \
+             patch("agent.auxiliary_client._read_main_model", return_value="llama3"), \
+             patch("agent.auxiliary_client._resolve_custom_runtime",
+                   return_value=("http://localhost:11434/v1", "test-key", None)), \
+             patch("agent.auxiliary_client.OpenAI") as mock_openai, \
+             caplog.at_level(logging.WARNING, logger="agent.auxiliary_client"):
+            mock_openai.return_value = MagicMock()
+            _resolve_auto()
+
+        assert not any("OPENAI_BASE_URL is set" in rec.message for rec in caplog.records), \
+            "Should NOT warn when provider is 'custom'"
+
+    def test_no_warning_when_provider_is_named_custom(self, monkeypatch, caplog):
+        """No warning when the provider is 'custom:myname' — base_url comes from config."""
+        import agent.auxiliary_client as mod
+        monkeypatch.setattr(mod, "_stale_base_url_warned", False)
+        monkeypatch.setenv("OPENAI_BASE_URL", "http://localhost:11434/v1")
+        monkeypatch.setenv("OPENAI_API_KEY", "test-key")
+
+        with patch("agent.auxiliary_client._read_main_provider", return_value="custom:ollama-local"), \
+             patch("agent.auxiliary_client._read_main_model", return_value="llama3"), \
+             patch("agent.auxiliary_client.resolve_provider_client",
+                   return_value=(MagicMock(), "llama3")), \
+             caplog.at_level(logging.WARNING, logger="agent.auxiliary_client"):
+            _resolve_auto()
+
+        assert not any("OPENAI_BASE_URL is set" in rec.message for rec in caplog.records), \
+            "Should NOT warn when provider is 'custom:*'"
+
+    def test_no_warning_when_openai_base_url_not_set(self, monkeypatch, caplog):
+        """No warning when OPENAI_BASE_URL is absent."""
+        import agent.auxiliary_client as mod
+        monkeypatch.setattr(mod, "_stale_base_url_warned", False)
+        monkeypatch.delenv("OPENAI_BASE_URL", raising=False)
+        monkeypatch.setenv("OPENROUTER_API_KEY", "sk-or-test")
+
+        with patch("agent.auxiliary_client._read_main_provider", return_value="openrouter"), \
+             patch("agent.auxiliary_client._read_main_model", return_value="google/gemini-flash"), \
+             caplog.at_level(logging.WARNING, logger="agent.auxiliary_client"):
+            _resolve_auto()
+
+        assert not any("OPENAI_BASE_URL is set" in rec.message for rec in caplog.records), \
+            "Should NOT warn when OPENAI_BASE_URL is not set"
+
+    def test_warning_only_fires_once(self, monkeypatch, caplog):
+        """Warning is suppressed after the first invocation."""
+        import agent.auxiliary_client as mod
+        monkeypatch.setattr(mod, "_stale_base_url_warned", False)
+        monkeypatch.setenv("OPENAI_BASE_URL", "http://localhost:11434/v1")
+        monkeypatch.setenv("OPENROUTER_API_KEY", "sk-or-test")
+
+        with patch("agent.auxiliary_client._read_main_provider", return_value="openrouter"), \
+             patch("agent.auxiliary_client._read_main_model", return_value="google/gemini-flash"), \
+             caplog.at_level(logging.WARNING, logger="agent.auxiliary_client"):
+            _resolve_auto()
+            caplog.clear()
+            _resolve_auto()
+
+        assert not any("OPENAI_BASE_URL is set" in rec.message for rec in caplog.records), \
+            "Warning should not fire a second time"

tests/agent/test_context_engine.py

@@ -0,0 +1,250 @@
+"""Tests for the ContextEngine ABC and plugin slot."""
+
+import json
+import pytest
+from typing import Any, Dict, List
+
+from agent.context_engine import ContextEngine
+from agent.context_compressor import ContextCompressor
+
+
+# ---------------------------------------------------------------------------
+# A minimal concrete engine for testing the ABC
+# ---------------------------------------------------------------------------
+
+class StubEngine(ContextEngine):
+    """Minimal engine that satisfies the ABC without doing real work."""
+
+    def __init__(self, context_length=200000, threshold_pct=0.50):
+        self.context_length = context_length
+        self.threshold_tokens = int(context_length * threshold_pct)
+        self._compress_called = False
+        self._tools_called = []
+
+    @property
+    def name(self) -> str:
+        return "stub"
+
+    def update_from_response(self, usage: Dict[str, Any]) -> None:
+        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:
+        tokens = prompt_tokens if prompt_tokens is not None else self.last_prompt_tokens
+        return tokens >= self.threshold_tokens
+
+    def compress(self, messages: List[Dict[str, Any]], current_tokens: int = None) -> List[Dict[str, Any]]:
+        self._compress_called = True
+        self.compression_count += 1
+        # Trivial: just return as-is
+        return messages
+
+    def get_tool_schemas(self) -> List[Dict[str, Any]]:
+        return [
+            {
+                "name": "stub_search",
+                "description": "Search the stub engine",
+                "parameters": {"type": "object", "properties": {}},
+            }
+        ]
+
+    def handle_tool_call(self, name: str, args: Dict[str, Any]) -> str:
+        self._tools_called.append(name)
+        return json.dumps({"ok": True, "tool": name})
+
+
+# ---------------------------------------------------------------------------
+# ABC contract tests
+# ---------------------------------------------------------------------------
+
+class TestContextEngineABC:
+    """Verify the ABC enforces the required interface."""
+
+    def test_cannot_instantiate_abc_directly(self):
+        with pytest.raises(TypeError):
+            ContextEngine()
+
+    def test_missing_methods_raises(self):
+        """A subclass missing required methods cannot be instantiated."""
+        class Incomplete(ContextEngine):
+            @property
+            def name(self):
+                return "incomplete"
+        with pytest.raises(TypeError):
+            Incomplete()
+
+    def test_stub_engine_satisfies_abc(self):
+        engine = StubEngine()
+        assert isinstance(engine, ContextEngine)
+        assert engine.name == "stub"
+
+    def test_compressor_is_context_engine(self):
+        c = ContextCompressor(model="test", quiet_mode=True, config_context_length=200000)
+        assert isinstance(c, ContextEngine)
+        assert c.name == "compressor"
+
+
+# ---------------------------------------------------------------------------
+# Default method behavior
+# ---------------------------------------------------------------------------
+
+class TestDefaults:
+    """Verify ABC default implementations work correctly."""
+
+    def test_default_tool_schemas_empty(self):
+        engine = StubEngine()
+        # StubEngine overrides this, so test the base via super
+        assert ContextEngine.get_tool_schemas(engine) == []
+
+    def test_default_handle_tool_call_returns_error(self):
+        engine = StubEngine()
+        result = ContextEngine.handle_tool_call(engine, "unknown", {})
+        data = json.loads(result)
+        assert "error" in data
+
+    def test_default_get_status(self):
+        engine = StubEngine()
+        engine.last_prompt_tokens = 50000
+        status = engine.get_status()
+        assert status["last_prompt_tokens"] == 50000
+        assert status["context_length"] == 200000
+        assert status["threshold_tokens"] == 100000
+        assert 0 < status["usage_percent"] <= 100
+
+    def test_on_session_reset(self):
+        engine = StubEngine()
+        engine.last_prompt_tokens = 999
+        engine.compression_count = 3
+        engine.on_session_reset()
+        assert engine.last_prompt_tokens == 0
+        assert engine.compression_count == 0
+
+    def test_should_compress_preflight_default_false(self):
+        engine = StubEngine()
+        assert engine.should_compress_preflight([]) is False
+
+
+# ---------------------------------------------------------------------------
+# StubEngine behavior
+# ---------------------------------------------------------------------------
+
+class TestStubEngine:
+
+    def test_should_compress(self):
+        engine = StubEngine(context_length=100000, threshold_pct=0.50)
+        assert not engine.should_compress(40000)
+        assert engine.should_compress(50000)
+        assert engine.should_compress(60000)
+
+    def test_compress_tracks_count(self):
+        engine = StubEngine()
+        msgs = [{"role": "user", "content": "hello"}]
+        result = engine.compress(msgs)
+        assert result == msgs
+        assert engine._compress_called
+        assert engine.compression_count == 1
+
+    def test_tool_schemas(self):
+        engine = StubEngine()
+        schemas = engine.get_tool_schemas()
+        assert len(schemas) == 1
+        assert schemas[0]["name"] == "stub_search"
+
+    def test_handle_tool_call(self):
+        engine = StubEngine()
+        result = engine.handle_tool_call("stub_search", {})
+        assert json.loads(result)["ok"] is True
+        assert "stub_search" in engine._tools_called
+
+    def test_update_from_response(self):
+        engine = StubEngine()
+        engine.update_from_response({"prompt_tokens": 1000, "completion_tokens": 200, "total_tokens": 1200})
+        assert engine.last_prompt_tokens == 1000
+        assert engine.last_completion_tokens == 200
+
+
+# ---------------------------------------------------------------------------
+# ContextCompressor session reset via ABC
+# ---------------------------------------------------------------------------
+
+class TestCompressorSessionReset:
+    """Verify ContextCompressor.on_session_reset() clears all state."""
+
+    def test_reset_clears_state(self):
+        c = ContextCompressor(model="test", quiet_mode=True, config_context_length=200000)
+        c.last_prompt_tokens = 50000
+        c.compression_count = 3
+        c._previous_summary = "some old summary"
+        c._context_probed = True
+        c._context_probe_persistable = True
+
+        c.on_session_reset()
+
+        assert c.last_prompt_tokens == 0
+        assert c.last_completion_tokens == 0
+        assert c.last_total_tokens == 0
+        assert c.compression_count == 0
+        assert c._context_probed is False
+        assert c._context_probe_persistable is False
+        assert c._previous_summary is None
+
+
+# ---------------------------------------------------------------------------
+# Plugin slot (PluginManager integration)
+# ---------------------------------------------------------------------------
+
+class TestPluginContextEngineSlot:
+    """Test register_context_engine on PluginContext."""
+
+    def test_register_engine(self):
+        from hermes_cli.plugins import PluginManager, PluginContext, PluginManifest
+        mgr = PluginManager()
+        manifest = PluginManifest(name="test-lcm")
+        ctx = PluginContext(manifest, mgr)
+
+        engine = StubEngine()
+        ctx.register_context_engine(engine)
+
+        assert mgr._context_engine is engine
+        assert mgr._context_engine.name == "stub"
+
+    def test_reject_second_engine(self):
+        from hermes_cli.plugins import PluginManager, PluginContext, PluginManifest
+        mgr = PluginManager()
+        manifest = PluginManifest(name="test-lcm")
+        ctx = PluginContext(manifest, mgr)
+
+        engine1 = StubEngine()
+        engine2 = StubEngine()
+        ctx.register_context_engine(engine1)
+        ctx.register_context_engine(engine2)  # should be rejected
+
+        assert mgr._context_engine is engine1
+
+    def test_reject_non_engine(self):
+        from hermes_cli.plugins import PluginManager, PluginContext, PluginManifest
+        mgr = PluginManager()
+        manifest = PluginManifest(name="test-bad")
+        ctx = PluginContext(manifest, mgr)
+
+        ctx.register_context_engine("not an engine")
+        assert mgr._context_engine is None
+
+    def test_get_plugin_context_engine(self):
+        from hermes_cli.plugins import PluginManager, PluginContext, PluginManifest, get_plugin_context_engine, _plugin_manager
+        import hermes_cli.plugins as plugins_mod
+
+        # Inject a test manager
+        old_mgr = plugins_mod._plugin_manager
+        try:
+            mgr = PluginManager()
+            plugins_mod._plugin_manager = mgr
+
+            assert get_plugin_context_engine() is None
+
+            engine = StubEngine()
+            mgr._context_engine = engine
+            assert get_plugin_context_engine() is engine
+        finally:
+            plugins_mod._plugin_manager = old_mgr

tests/agent/test_minimax_provider.py

@@ -1,37 +1,37 @@
-"""Tests for MiniMax provider hardening — context lengths, thinking guard, catalog, beta headers."""
+"""Tests for MiniMax provider hardening — context lengths, thinking, catalog, beta headers, transport."""
 
 from unittest.mock import patch
 
 
 class TestMinimaxContextLengths:
-    """Verify per-model context length entries for MiniMax models."""
+    """Verify context length entries match official docs (204,800 for all models).
 
-    def test_m1_variants_have_1m_context(self):
+    Source: https://platform.minimax.io/docs/api-reference/text-anthropic-api
+    """
+
+    def test_minimax_prefix_has_correct_context(self):
         from agent.model_metadata import DEFAULT_CONTEXT_LENGTHS
-        # Keys are lowercase because the lookup lowercases model names
-        for model in ("minimax-m1", "minimax-m1-40k", "minimax-m1-80k",
-                       "minimax-m1-128k", "minimax-m1-256k"):
-            assert model in DEFAULT_CONTEXT_LENGTHS, f"{model} missing from context lengths"
-            assert DEFAULT_CONTEXT_LENGTHS[model] == 1_000_000, f"{model} expected 1M"
+        assert DEFAULT_CONTEXT_LENGTHS["minimax"] == 204_800
 
-    def test_m2_variants_have_1m_context(self):
-        from agent.model_metadata import DEFAULT_CONTEXT_LENGTHS
-        # Keys are lowercase because the lookup lowercases model names
-        for model in ("minimax-m2.5", "minimax-m2.7"):
-            assert model in DEFAULT_CONTEXT_LENGTHS, f"{model} missing from context lengths"
-            assert DEFAULT_CONTEXT_LENGTHS[model] == 1_048_576, f"{model} expected 1048576"
-
-    def test_minimax_prefix_fallback(self):
-        from agent.model_metadata import DEFAULT_CONTEXT_LENGTHS
-        # The generic "minimax" prefix entry should be 1M for unknown models
-        assert DEFAULT_CONTEXT_LENGTHS["minimax"] == 1_048_576
+    def test_minimax_models_resolve_via_prefix(self):
+        from agent.model_metadata import get_model_context_length
+        # All MiniMax models should resolve to 204,800 via the "minimax" prefix
+        for model in ("MiniMax-M2.7", "MiniMax-M2.5", "MiniMax-M2.1", "MiniMax-M2"):
+            ctx = get_model_context_length(model, "")
+            assert ctx == 204_800, f"{model} expected 204800, got {ctx}"
 
 
 
-class TestMinimaxThinkingGuard:
-    """Verify that build_anthropic_kwargs does NOT add thinking params for MiniMax models."""
+class TestMinimaxThinkingSupport:
+    """Verify that MiniMax gets manual thinking (not adaptive).
 
-    def test_no_thinking_for_minimax_m27(self):
+    MiniMax's Anthropic-compat endpoint officially supports the thinking
+    parameter (https://platform.minimax.io/docs/api-reference/text-anthropic-api).
+    It should get manual thinking (type=enabled + budget_tokens), NOT adaptive
+    thinking (which is Claude 4.6-only).
+    """
+
+    def test_minimax_m27_gets_manual_thinking(self):
         from agent.anthropic_adapter import build_anthropic_kwargs
         kwargs = build_anthropic_kwargs(
             model="MiniMax-M2.7",
@@ -40,19 +40,23 @@ class TestMinimaxThinkingGuard:
             max_tokens=4096,
             reasoning_config={"enabled": True, "effort": "medium"},
         )
-        assert "thinking" not in kwargs
+        assert "thinking" in kwargs
+        assert kwargs["thinking"]["type"] == "enabled"
+        assert "budget_tokens" in kwargs["thinking"]
+        # MiniMax should NOT get adaptive thinking or output_config
         assert "output_config" not in kwargs
 
-    def test_no_thinking_for_minimax_m1(self):
+    def test_minimax_m25_gets_manual_thinking(self):
         from agent.anthropic_adapter import build_anthropic_kwargs
         kwargs = build_anthropic_kwargs(
-            model="MiniMax-M1-128k",
+            model="MiniMax-M2.5",
             messages=[{"role": "user", "content": "hello"}],
             tools=None,
             max_tokens=4096,
             reasoning_config={"enabled": True, "effort": "high"},
         )
-        assert "thinking" not in kwargs
+        assert "thinking" in kwargs
+        assert kwargs["thinking"]["type"] == "enabled"
 
     def test_thinking_still_works_for_claude(self):
         from agent.anthropic_adapter import build_anthropic_kwargs
@@ -81,25 +85,30 @@ class TestMinimaxAuxModel:
 
 
 class TestMinimaxModelCatalog:
-    """Verify the model catalog includes M1 family and excludes deprecated models."""
+    """Verify the model catalog matches official Anthropic-compat endpoint models.
 
-    def test_catalog_includes_m1_family(self):
+    Source: https://platform.minimax.io/docs/api-reference/text-anthropic-api
+    """
+
+    def test_catalog_includes_current_models(self):
         from hermes_cli.models import _PROVIDER_MODELS
         for provider in ("minimax", "minimax-cn"):
             models = _PROVIDER_MODELS[provider]
-            assert "MiniMax-M1" in models
-            assert "MiniMax-M1-40k" in models
-            assert "MiniMax-M1-80k" in models
-            assert "MiniMax-M1-128k" in models
-            assert "MiniMax-M1-256k" in models
+            assert "MiniMax-M2.7" in models
+            assert "MiniMax-M2.5" in models
+            assert "MiniMax-M2.1" in models
+            assert "MiniMax-M2" in models
 
-    def test_catalog_excludes_deprecated(self):
+    def test_catalog_excludes_m1_family(self):
+        """M1 models are not available on the /anthropic endpoint."""
         from hermes_cli.models import _PROVIDER_MODELS
         for provider in ("minimax", "minimax-cn"):
             models = _PROVIDER_MODELS[provider]
-            assert "MiniMax-M2.1" not in models
+            assert "MiniMax-M1" not in models
 
     def test_catalog_excludes_highspeed(self):
+        """Highspeed variants are available but not shown in default catalog
+        (users can still specify them manually)."""
         from hermes_cli.models import _PROVIDER_MODELS
         for provider in ("minimax", "minimax-cn"):
             models = _PROVIDER_MODELS[provider]
@@ -202,3 +211,154 @@ class TestMinimaxBetaHeaders:
     def test_common_betas_regular_url(self):
         from agent.anthropic_adapter import _common_betas_for_base_url, _COMMON_BETAS
         assert _common_betas_for_base_url("https://api.anthropic.com") == _COMMON_BETAS
+
+
+class TestMinimaxApiMode:
+    """Verify determine_api_mode returns anthropic_messages for MiniMax providers.
+
+    The MiniMax /anthropic endpoint speaks Anthropic Messages wire format,
+    not OpenAI chat completions.  The overlay transport must reflect this
+    so that code paths calling determine_api_mode() without a base_url
+    (e.g. /model switch) get the correct api_mode.
+    """
+
+    def test_minimax_returns_anthropic_messages(self):
+        from hermes_cli.providers import determine_api_mode
+        assert determine_api_mode("minimax") == "anthropic_messages"
+
+    def test_minimax_cn_returns_anthropic_messages(self):
+        from hermes_cli.providers import determine_api_mode
+        assert determine_api_mode("minimax-cn") == "anthropic_messages"
+
+    def test_minimax_with_url_also_works(self):
+        from hermes_cli.providers import determine_api_mode
+        # Even with explicit base_url, provider lookup takes priority
+        assert determine_api_mode("minimax", "https://api.minimax.io/anthropic") == "anthropic_messages"
+
+    def test_anthropic_still_returns_anthropic_messages(self):
+        from hermes_cli.providers import determine_api_mode
+        assert determine_api_mode("anthropic") == "anthropic_messages"
+
+    def test_openai_returns_chat_completions(self):
+        from hermes_cli.providers import determine_api_mode
+        # Sanity check: standard providers are unaffected
+        result = determine_api_mode("deepseek")
+        assert result == "chat_completions"
+
+
+class TestMinimaxMaxOutput:
+    """Verify _get_anthropic_max_output returns correct limits for MiniMax models.
+
+    MiniMax max output is 131,072 tokens (source: OpenClaw model definitions,
+    cross-referenced with MiniMax API behavior).
+    """
+
+    def test_minimax_m27_output_limit(self):
+        from agent.anthropic_adapter import _get_anthropic_max_output
+        assert _get_anthropic_max_output("MiniMax-M2.7") == 131_072
+
+    def test_minimax_m25_output_limit(self):
+        from agent.anthropic_adapter import _get_anthropic_max_output
+        assert _get_anthropic_max_output("MiniMax-M2.5") == 131_072
+
+    def test_minimax_m2_output_limit(self):
+        from agent.anthropic_adapter import _get_anthropic_max_output
+        assert _get_anthropic_max_output("MiniMax-M2") == 131_072
+
+    def test_claude_output_unaffected(self):
+        from agent.anthropic_adapter import _get_anthropic_max_output
+        # Sanity: Claude limits are not broken by the MiniMax entry
+        assert _get_anthropic_max_output("claude-sonnet-4-6") == 64_000
+
+
+class TestMinimaxPreserveDots:
+    """Verify that MiniMax model names preserve dots through the Anthropic adapter.
+
+    MiniMax model IDs like 'MiniMax-M2.7' must NOT have dots converted to
+    hyphens — the endpoint expects the exact name with dots.
+    """
+
+    def test_minimax_provider_preserves_dots(self):
+        from types import SimpleNamespace
+        agent = SimpleNamespace(provider="minimax", base_url="")
+        from run_agent import AIAgent
+        assert AIAgent._anthropic_preserve_dots(agent) is True
+
+    def test_minimax_cn_provider_preserves_dots(self):
+        from types import SimpleNamespace
+        agent = SimpleNamespace(provider="minimax-cn", base_url="")
+        from run_agent import AIAgent
+        assert AIAgent._anthropic_preserve_dots(agent) is True
+
+    def test_minimax_url_preserves_dots(self):
+        from types import SimpleNamespace
+        agent = SimpleNamespace(provider="custom", base_url="https://api.minimax.io/anthropic")
+        from run_agent import AIAgent
+        assert AIAgent._anthropic_preserve_dots(agent) is True
+
+    def test_minimax_cn_url_preserves_dots(self):
+        from types import SimpleNamespace
+        agent = SimpleNamespace(provider="custom", base_url="https://api.minimaxi.com/anthropic")
+        from run_agent import AIAgent
+        assert AIAgent._anthropic_preserve_dots(agent) is True
+
+    def test_anthropic_does_not_preserve_dots(self):
+        from types import SimpleNamespace
+        agent = SimpleNamespace(provider="anthropic", base_url="https://api.anthropic.com")
+        from run_agent import AIAgent
+        assert AIAgent._anthropic_preserve_dots(agent) is False
+
+    def test_normalize_preserves_m27_dot(self):
+        from agent.anthropic_adapter import normalize_model_name
+        assert normalize_model_name("MiniMax-M2.7", preserve_dots=True) == "MiniMax-M2.7"
+
+    def test_normalize_converts_without_preserve(self):
+        from agent.anthropic_adapter import normalize_model_name
+        # Without preserve_dots, dots become hyphens (broken for MiniMax)
+        assert normalize_model_name("MiniMax-M2.7", preserve_dots=False) == "MiniMax-M2-7"
+
+
+class TestMinimaxSwitchModelCredentialGuard:
+    """Verify switch_model() does not leak Anthropic credentials to MiniMax.
+
+    The __init__ path correctly guards against this (line 761), but switch_model()
+    must mirror that guard. Without it, /model switch to minimax with no explicit
+    api_key would fall back to resolve_anthropic_token() and send Anthropic creds
+    to the MiniMax endpoint.
+    """
+
+    def test_switch_to_minimax_does_not_resolve_anthropic_token(self):
+        """switch_model() should NOT call resolve_anthropic_token() for MiniMax."""
+        from unittest.mock import patch, MagicMock
+
+        with patch("run_agent.AIAgent.__init__", return_value=None):
+            from run_agent import AIAgent
+            agent = AIAgent.__new__(AIAgent)
+            agent.provider = "anthropic"
+            agent.model = "claude-sonnet-4"
+            agent.api_key = "sk-ant-fake"
+            agent.base_url = "https://api.anthropic.com"
+            agent.api_mode = "anthropic_messages"
+            agent._anthropic_base_url = "https://api.anthropic.com"
+            agent._anthropic_api_key = "sk-ant-fake"
+            agent._is_anthropic_oauth = False
+            agent._client_kwargs = {}
+            agent.client = None
+            agent._anthropic_client = MagicMock()
+
+        with patch("agent.anthropic_adapter.build_anthropic_client") as mock_build, \
+             patch("agent.anthropic_adapter.resolve_anthropic_token", return_value="sk-ant-leaked") as mock_resolve, \
+             patch("agent.anthropic_adapter._is_oauth_token", return_value=False):
+
+            agent.switch_model(
+                new_model="MiniMax-M2.7",
+                new_provider="minimax",
+                api_mode="anthropic_messages",
+                api_key="mm-key-123",
+                base_url="https://api.minimax.io/anthropic",
+            )
+            # resolve_anthropic_token should NOT be called for non-Anthropic providers
+            mock_resolve.assert_not_called()
+            # The key passed to build_anthropic_client should be the MiniMax key
+            build_args = mock_build.call_args
+            assert build_args[0][0] == "mm-key-123"

tests/agent/test_model_metadata.py

@@ -222,6 +222,24 @@ class TestGetModelContextLength:
         mock_fetch.return_value = {}
         assert get_model_context_length("openai/gpt-4o") == 128000
 
+    @patch("agent.model_metadata.fetch_model_metadata")
+    def test_qwen3_coder_plus_context_length(self, mock_fetch):
+        """qwen3-coder-plus has a 1M context window, not the generic 128K Qwen default."""
+        mock_fetch.return_value = {}
+        assert get_model_context_length("qwen3-coder-plus") == 1000000
+
+    @patch("agent.model_metadata.fetch_model_metadata")
+    def test_qwen3_coder_context_length(self, mock_fetch):
+        """qwen3-coder has a 256K context window, not the generic 128K Qwen default."""
+        mock_fetch.return_value = {}
+        assert get_model_context_length("qwen3-coder") == 262144
+
+    @patch("agent.model_metadata.fetch_model_metadata")
+    def test_qwen_generic_context_length(self, mock_fetch):
+        """Generic qwen models still get the 128K default."""
+        mock_fetch.return_value = {}
+        assert get_model_context_length("qwen3-plus") == 131072
+
     @patch("agent.model_metadata.fetch_model_metadata")
     def test_api_missing_context_length_key(self, mock_fetch):
         """Model in API but without context_length → defaults to 128000."""

tests/agent/test_models_dev.py

@@ -7,6 +7,7 @@ from agent.models_dev import (
     PROVIDER_TO_MODELS_DEV,
     _extract_context,
     fetch_models_dev,
+    get_model_capabilities,
     lookup_models_dev_context,
 )
 
@@ -195,3 +196,88 @@ class TestFetchModelsDev:
         result = fetch_models_dev()
         mock_get.assert_not_called()
         assert result == SAMPLE_REGISTRY
+
+
+# ---------------------------------------------------------------------------
+# get_model_capabilities — vision via modalities.input
+# ---------------------------------------------------------------------------
+
+
+CAPS_REGISTRY = {
+    "google": {
+        "id": "google",
+        "models": {
+            "gemma-4-31b-it": {
+                "id": "gemma-4-31b-it",
+                "attachment": False,
+                "tool_call": True,
+                "modalities": {"input": ["text", "image"]},
+                "limit": {"context": 128000, "output": 8192},
+            },
+            "gemma-3-1b": {
+                "id": "gemma-3-1b",
+                "tool_call": True,
+                "limit": {"context": 32000, "output": 8192},
+            },
+        },
+    },
+    "anthropic": {
+        "id": "anthropic",
+        "models": {
+            "claude-sonnet-4": {
+                "id": "claude-sonnet-4",
+                "attachment": True,
+                "tool_call": True,
+                "limit": {"context": 200000, "output": 64000},
+            },
+        },
+    },
+}
+
+
+class TestGetModelCapabilities:
+    """Tests for get_model_capabilities vision detection."""
+
+    def test_vision_from_attachment_flag(self):
+        """Models with attachment=True should report supports_vision=True."""
+        with patch("agent.models_dev.fetch_models_dev", return_value=CAPS_REGISTRY):
+            caps = get_model_capabilities("anthropic", "claude-sonnet-4")
+        assert caps is not None
+        assert caps.supports_vision is True
+
+    def test_vision_from_modalities_input_image(self):
+        """Models with 'image' in modalities.input but attachment=False should
+        still report supports_vision=True (the core fix in this PR)."""
+        with patch("agent.models_dev.fetch_models_dev", return_value=CAPS_REGISTRY):
+            caps = get_model_capabilities("google", "gemma-4-31b-it")
+        assert caps is not None
+        assert caps.supports_vision is True
+
+    def test_no_vision_without_attachment_or_modalities(self):
+        """Models with neither attachment nor image modality should be non-vision."""
+        with patch("agent.models_dev.fetch_models_dev", return_value=CAPS_REGISTRY):
+            caps = get_model_capabilities("google", "gemma-3-1b")
+        assert caps is not None
+        assert caps.supports_vision is False
+
+    def test_modalities_non_dict_handled(self):
+        """Non-dict modalities field should not crash."""
+        registry = {
+            "google": {"id": "google", "models": {
+                "weird-model": {
+                    "id": "weird-model",
+                    "modalities": "text",  # not a dict
+                    "limit": {"context": 200000, "output": 8192},
+                },
+            }},
+        }
+        with patch("agent.models_dev.fetch_models_dev", return_value=registry):
+            caps = get_model_capabilities("gemini", "weird-model")
+        assert caps is not None
+        assert caps.supports_vision is False
+
+    def test_model_not_found_returns_none(self):
+        """Unknown model should return None."""
+        with patch("agent.models_dev.fetch_models_dev", return_value=CAPS_REGISTRY):
+            caps = get_model_capabilities("anthropic", "nonexistent-model")
+        assert caps is None

tests/cli/test_manual_compress.py

@@ -0,0 +1,66 @@
+"""Tests for CLI manual compression messaging."""
+
+from unittest.mock import MagicMock, patch
+
+from tests.cli.test_cli_init import _make_cli
+
+
+def _make_history() -> list[dict[str, str]]:
+    return [
+        {"role": "user", "content": "one"},
+        {"role": "assistant", "content": "two"},
+        {"role": "user", "content": "three"},
+        {"role": "assistant", "content": "four"},
+    ]
+
+
+def test_manual_compress_reports_noop_without_success_banner(capsys):
+    shell = _make_cli()
+    history = _make_history()
+    shell.conversation_history = history
+    shell.agent = MagicMock()
+    shell.agent.compression_enabled = True
+    shell.agent._cached_system_prompt = ""
+    shell.agent._compress_context.return_value = (list(history), "")
+
+    def _estimate(messages):
+        assert messages == history
+        return 100
+
+    with patch("agent.model_metadata.estimate_messages_tokens_rough", side_effect=_estimate):
+        shell._manual_compress()
+
+    output = capsys.readouterr().out
+    assert "No changes from compression" in output
+    assert "✅ Compressed" not in output
+    assert "Rough transcript estimate: ~100 tokens (unchanged)" in output
+
+
+def test_manual_compress_explains_when_token_estimate_rises(capsys):
+    shell = _make_cli()
+    history = _make_history()
+    compressed = [
+        history[0],
+        {"role": "assistant", "content": "Dense summary that still counts as more tokens."},
+        history[-1],
+    ]
+    shell.conversation_history = history
+    shell.agent = MagicMock()
+    shell.agent.compression_enabled = True
+    shell.agent._cached_system_prompt = ""
+    shell.agent._compress_context.return_value = (compressed, "")
+
+    def _estimate(messages):
+        if messages == history:
+            return 100
+        if messages == compressed:
+            return 120
+        raise AssertionError(f"unexpected transcript: {messages!r}")
+
+    with patch("agent.model_metadata.estimate_messages_tokens_rough", side_effect=_estimate):
+        shell._manual_compress()
+
+    output = capsys.readouterr().out
+    assert "✅ Compressed: 4 → 3 messages" in output
+    assert "Rough transcript estimate: ~100 → ~120 tokens" in output
+    assert "denser summaries" in output

tests/gateway/restart_test_helpers.py

@@ -0,0 +1,110 @@
+import asyncio
+from unittest.mock import AsyncMock, MagicMock
+
+from gateway.config import GatewayConfig, Platform, PlatformConfig
+from gateway.platforms.base import BasePlatformAdapter, MessageEvent, SendResult
+from gateway.restart import DEFAULT_GATEWAY_RESTART_DRAIN_TIMEOUT
+from gateway.run import GatewayRunner
+from gateway.session import SessionSource
+
+
+class RestartTestAdapter(BasePlatformAdapter):
+    def __init__(self):
+        super().__init__(PlatformConfig(enabled=True, token="***"), Platform.TELEGRAM)
+        self.sent: list[str] = []
+
+    async def connect(self):
+        return True
+
+    async def disconnect(self):
+        return None
+
+    async def send(self, chat_id, content, reply_to=None, metadata=None):
+        self.sent.append(content)
+        return SendResult(success=True, message_id="1")
+
+    async def send_typing(self, chat_id, metadata=None):
+        return None
+
+    async def get_chat_info(self, chat_id):
+        return {"id": chat_id}
+
+
+def make_restart_source(chat_id: str = "123456", chat_type: str = "dm") -> SessionSource:
+    return SessionSource(
+        platform=Platform.TELEGRAM,
+        chat_id=chat_id,
+        chat_type=chat_type,
+    )
+
+
+def make_restart_runner(
+    adapter: BasePlatformAdapter | None = None,
+) -> tuple[GatewayRunner, BasePlatformAdapter]:
+    runner = object.__new__(GatewayRunner)
+    runner.config = GatewayConfig(
+        platforms={Platform.TELEGRAM: PlatformConfig(enabled=True, token="***")}
+    )
+    runner._running = True
+    runner._shutdown_event = asyncio.Event()
+    runner._exit_reason = None
+    runner._exit_code = None
+    runner._running_agents = {}
+    runner._running_agents_ts = {}
+    runner._pending_messages = {}
+    runner._pending_approvals = {}
+    runner._pending_model_notes = {}
+    runner._background_tasks = set()
+    runner._draining = False
+    runner._restart_requested = False
+    runner._restart_task_started = False
+    runner._restart_detached = False
+    runner._restart_via_service = False
+    runner._restart_drain_timeout = DEFAULT_GATEWAY_RESTART_DRAIN_TIMEOUT
+    runner._stop_task = None
+    runner._busy_input_mode = "interrupt"
+    runner._update_prompt_pending = {}
+    runner._voice_mode = {}
+    runner._session_model_overrides = {}
+    runner._shutdown_all_gateway_honcho = lambda: None
+    runner._update_runtime_status = MagicMock()
+    runner._queue_or_replace_pending_event = GatewayRunner._queue_or_replace_pending_event.__get__(
+        runner, GatewayRunner
+    )
+    runner._session_key_for_source = GatewayRunner._session_key_for_source.__get__(
+        runner, GatewayRunner
+    )
+    runner._handle_active_session_busy_message = (
+        GatewayRunner._handle_active_session_busy_message.__get__(runner, GatewayRunner)
+    )
+    runner._handle_restart_command = GatewayRunner._handle_restart_command.__get__(
+        runner, GatewayRunner
+    )
+    runner._status_action_label = GatewayRunner._status_action_label.__get__(
+        runner, GatewayRunner
+    )
+    runner._status_action_gerund = GatewayRunner._status_action_gerund.__get__(
+        runner, GatewayRunner
+    )
+    runner._queue_during_drain_enabled = GatewayRunner._queue_during_drain_enabled.__get__(
+        runner, GatewayRunner
+    )
+    runner._running_agent_count = GatewayRunner._running_agent_count.__get__(
+        runner, GatewayRunner
+    )
+    runner._launch_detached_restart_command = GatewayRunner._launch_detached_restart_command.__get__(
+        runner, GatewayRunner
+    )
+    runner.request_restart = GatewayRunner.request_restart.__get__(runner, GatewayRunner)
+    runner._is_user_authorized = lambda _source: True
+    runner.hooks = MagicMock()
+    runner.hooks.emit = AsyncMock()
+    runner.pairing_store = MagicMock()
+    runner.session_store = MagicMock()
+    runner.delivery_router = MagicMock()
+
+    platform_adapter = adapter or RestartTestAdapter()
+    platform_adapter.set_message_handler(AsyncMock(return_value=None))
+    platform_adapter.set_busy_session_handler(runner._handle_active_session_busy_message)
+    runner.adapters = {Platform.TELEGRAM: platform_adapter}
+    return runner, platform_adapter

tests/gateway/test_api_server.py

@@ -464,7 +464,7 @@ class TestChatCompletionsEndpoint:
 
     @pytest.mark.asyncio
     async def test_stream_includes_tool_progress(self, adapter):
-        """tool_progress_callback fires → progress appears in the SSE stream."""
+        """tool_progress_callback fires → progress appears as custom SSE event, not in delta.content."""
         import asyncio
 
         app = _create_app(adapter)
@@ -495,8 +495,26 @@ class TestChatCompletionsEndpoint:
                 assert resp.status == 200
                 body = await resp.text()
                 assert "[DONE]" in body
-                # Tool progress message must appear in the stream
-                assert "ls -la" in body
+                # Tool progress must appear as a custom SSE event, not in
+                # delta.content — prevents model from learning to imitate
+                # markers instead of calling tools (#6972).
+                assert "event: hermes.tool.progress" in body
+                assert '"tool": "terminal"' in body
+                assert '"label": "ls -la"' in body
+                # The progress marker must NOT appear inside any
+                # chat.completion.chunk delta.content field.
+                import json as _json
+                for line in body.splitlines():
+                    if line.startswith("data: ") and line.strip() != "data: [DONE]":
+                        try:
+                            chunk = _json.loads(line[len("data: "):])
+                        except _json.JSONDecodeError:
+                            continue
+                        if chunk.get("object") == "chat.completion.chunk":
+                            for choice in chunk.get("choices", []):
+                                content = choice.get("delta", {}).get("content", "")
+                                # Tool emoji markers must never leak into content
+                                assert "ls -la" not in content or content == "Here are the files."
                 # Final content must also be present
                 assert "Here are the files." in body
 
@@ -532,10 +550,12 @@ class TestChatCompletionsEndpoint:
                 )
                 assert resp.status == 200
                 body = await resp.text()
-                # Internal _thinking event should NOT appear
+                # Internal _thinking event should NOT appear anywhere
                 assert "some internal state" not in body
-                # Real tool progress should appear
-                assert "Python docs" in body
+                # Real tool progress should appear as custom SSE event
+                assert "event: hermes.tool.progress" in body
+                assert '"tool": "web_search"' in body
+                assert '"label": "Python docs"' in body
 
     @pytest.mark.asyncio
     async def test_no_user_message_returns_400(self, adapter):

tests/gateway/test_approve_deny_commands.py

@@ -345,6 +345,11 @@ class TestBlockingApprovalE2E:
 
     def setup_method(self):
         _clear_approval_state()
+        os.environ.pop("HERMES_YOLO_MODE", None)
+        os.environ.pop("HERMES_INTERACTIVE", None)
+        os.environ.pop("HERMES_GATEWAY_SESSION", None)
+        os.environ.pop("HERMES_EXEC_ASK", None)
+        os.environ.pop("HERMES_SESSION_KEY", None)
 
     def test_blocking_approval_approve_once(self):
         """check_all_command_guards blocks until resolve_gateway_approval is called."""
@@ -364,6 +369,7 @@ class TestBlockingApprovalE2E:
             from tools.approval import reset_current_session_key, set_current_session_key
 
             token = set_current_session_key(session_key)
+            os.environ["HERMES_GATEWAY_SESSION"] = "1"
             os.environ["HERMES_EXEC_ASK"] = "1"
             os.environ["HERMES_SESSION_KEY"] = session_key
             try:
@@ -371,6 +377,7 @@ class TestBlockingApprovalE2E:
                     "rm -rf /important", "local"
                 )
             finally:
+                os.environ.pop("HERMES_GATEWAY_SESSION", None)
                 os.environ.pop("HERMES_EXEC_ASK", None)
                 os.environ.pop("HERMES_SESSION_KEY", None)
                 reset_current_session_key(token)
@@ -410,6 +417,7 @@ class TestBlockingApprovalE2E:
             from tools.approval import reset_current_session_key, set_current_session_key
 
             token = set_current_session_key(session_key)
+            os.environ["HERMES_GATEWAY_SESSION"] = "1"
             os.environ["HERMES_EXEC_ASK"] = "1"
             os.environ["HERMES_SESSION_KEY"] = session_key
             try:
@@ -417,6 +425,7 @@ class TestBlockingApprovalE2E:
                     "rm -rf /important", "local"
                 )
             finally:
+                os.environ.pop("HERMES_GATEWAY_SESSION", None)
                 os.environ.pop("HERMES_EXEC_ASK", None)
                 os.environ.pop("HERMES_SESSION_KEY", None)
                 reset_current_session_key(token)
@@ -451,6 +460,7 @@ class TestBlockingApprovalE2E:
             from tools.approval import reset_current_session_key, set_current_session_key
 
             token = set_current_session_key(session_key)
+            os.environ["HERMES_GATEWAY_SESSION"] = "1"
             os.environ["HERMES_EXEC_ASK"] = "1"
             os.environ["HERMES_SESSION_KEY"] = session_key
             try:
@@ -460,6 +470,7 @@ class TestBlockingApprovalE2E:
                         "rm -rf /important", "local"
                     )
             finally:
+                os.environ.pop("HERMES_GATEWAY_SESSION", None)
                 os.environ.pop("HERMES_EXEC_ASK", None)
                 os.environ.pop("HERMES_SESSION_KEY", None)
                 reset_current_session_key(token)
@@ -491,11 +502,13 @@ class TestBlockingApprovalE2E:
                 from tools.approval import reset_current_session_key, set_current_session_key
 
                 token = set_current_session_key(session_key)
+                os.environ["HERMES_GATEWAY_SESSION"] = "1"
                 os.environ["HERMES_EXEC_ASK"] = "1"
                 os.environ["HERMES_SESSION_KEY"] = session_key
                 try:
                     results[idx] = check_all_command_guards(cmd, "local")
                 finally:
+                    os.environ.pop("HERMES_GATEWAY_SESSION", None)
                     os.environ.pop("HERMES_EXEC_ASK", None)
                     os.environ.pop("HERMES_SESSION_KEY", None)
                     reset_current_session_key(token)
@@ -546,11 +559,13 @@ class TestBlockingApprovalE2E:
                 from tools.approval import reset_current_session_key, set_current_session_key
 
                 token = set_current_session_key(session_key)
+                os.environ["HERMES_GATEWAY_SESSION"] = "1"
                 os.environ["HERMES_EXEC_ASK"] = "1"
                 os.environ["HERMES_SESSION_KEY"] = session_key
                 try:
                     results[idx] = check_all_command_guards(cmd, "local")
                 finally:
+                    os.environ.pop("HERMES_GATEWAY_SESSION", None)
                     os.environ.pop("HERMES_EXEC_ASK", None)
                     os.environ.pop("HERMES_SESSION_KEY", None)
                     reset_current_session_key(token)

tests/gateway/test_compress_command.py

@@ -0,0 +1,121 @@
+"""Tests for gateway /compress user-facing messaging."""
+
+from datetime import datetime
+from unittest.mock import MagicMock, patch
+
+import pytest
+
+from gateway.config import GatewayConfig, Platform, PlatformConfig
+from gateway.platforms.base import MessageEvent
+from gateway.session import SessionEntry, SessionSource, build_session_key
+
+
+def _make_source() -> SessionSource:
+    return SessionSource(
+        platform=Platform.TELEGRAM,
+        user_id="u1",
+        chat_id="c1",
+        user_name="tester",
+        chat_type="dm",
+    )
+
+
+def _make_event(text: str = "/compress") -> MessageEvent:
+    return MessageEvent(text=text, source=_make_source(), message_id="m1")
+
+
+def _make_history() -> list[dict[str, str]]:
+    return [
+        {"role": "user", "content": "one"},
+        {"role": "assistant", "content": "two"},
+        {"role": "user", "content": "three"},
+        {"role": "assistant", "content": "four"},
+    ]
+
+
+def _make_runner(history: list[dict[str, str]]):
+    from gateway.run import GatewayRunner
+
+    runner = object.__new__(GatewayRunner)
+    runner.config = GatewayConfig(
+        platforms={Platform.TELEGRAM: PlatformConfig(enabled=True, token="***")}
+    )
+    session_entry = SessionEntry(
+        session_key=build_session_key(_make_source()),
+        session_id="sess-1",
+        created_at=datetime.now(),
+        updated_at=datetime.now(),
+        platform=Platform.TELEGRAM,
+        chat_type="dm",
+    )
+    runner.session_store = MagicMock()
+    runner.session_store.get_or_create_session.return_value = session_entry
+    runner.session_store.load_transcript.return_value = history
+    runner.session_store.rewrite_transcript = MagicMock()
+    runner.session_store.update_session = MagicMock()
+    runner.session_store._save = MagicMock()
+    return runner
+
+
+@pytest.mark.asyncio
+async def test_compress_command_reports_noop_without_success_banner():
+    history = _make_history()
+    runner = _make_runner(history)
+    agent_instance = MagicMock()
+    agent_instance.context_compressor.protect_first_n = 0
+    agent_instance.context_compressor._align_boundary_forward.return_value = 0
+    agent_instance.context_compressor._find_tail_cut_by_tokens.return_value = 2
+    agent_instance.session_id = "sess-1"
+    agent_instance._compress_context.return_value = (list(history), "")
+
+    def _estimate(messages):
+        assert messages == history
+        return 100
+
+    with (
+        patch("gateway.run._resolve_runtime_agent_kwargs", return_value={"api_key": "test-key"}),
+        patch("gateway.run._resolve_gateway_model", return_value="test-model"),
+        patch("run_agent.AIAgent", return_value=agent_instance),
+        patch("agent.model_metadata.estimate_messages_tokens_rough", side_effect=_estimate),
+    ):
+        result = await runner._handle_compress_command(_make_event())
+
+    assert "No changes from compression" in result
+    assert "Compressed:" not in result
+    assert "Rough transcript estimate: ~100 tokens (unchanged)" in result
+
+
+@pytest.mark.asyncio
+async def test_compress_command_explains_when_token_estimate_rises():
+    history = _make_history()
+    compressed = [
+        history[0],
+        {"role": "assistant", "content": "Dense summary that still counts as more tokens."},
+        history[-1],
+    ]
+    runner = _make_runner(history)
+    agent_instance = MagicMock()
+    agent_instance.context_compressor.protect_first_n = 0
+    agent_instance.context_compressor._align_boundary_forward.return_value = 0
+    agent_instance.context_compressor._find_tail_cut_by_tokens.return_value = 2
+    agent_instance.session_id = "sess-1"
+    agent_instance._compress_context.return_value = (compressed, "")
+
+    def _estimate(messages):
+        if messages == history:
+            return 100
+        if messages == compressed:
+            return 120
+        raise AssertionError(f"unexpected transcript: {messages!r}")
+
+    with (
+        patch("gateway.run._resolve_runtime_agent_kwargs", return_value={"api_key": "test-key"}),
+        patch("gateway.run._resolve_gateway_model", return_value="test-model"),
+        patch("run_agent.AIAgent", return_value=agent_instance),
+        patch("agent.model_metadata.estimate_messages_tokens_rough", side_effect=_estimate),
+    ):
+        result = await runner._handle_compress_command(_make_event())
+
+    assert "Compressed: 4 → 3 messages" in result
+    assert "Rough transcript estimate: ~100 → ~120 tokens" in result
+    assert "denser summaries" in result

tests/gateway/test_fallback_eviction.py

@@ -0,0 +1,44 @@
+"""Tests for fallback-eviction gating on failed runs (#7130).
+
+When a run fails, the gateway must NOT evict the cached agent — doing so
+forces MCP reinit on the next message, creating a CPU-burning restart loop.
+Eviction should only happen on successful runs where fallback activated.
+"""
+
+import sys
+from pathlib import Path
+from unittest.mock import MagicMock, patch
+
+import pytest
+
+sys.path.insert(0, str(Path(__file__).resolve().parent.parent.parent))
+
+
+class TestFallbackEvictionGating:
+    """The fallback-eviction code path should skip eviction on failed runs."""
+
+    def test_failed_run_does_not_evict_cached_agent(self):
+        """When result has failed=True, the cached agent should NOT be evicted."""
+        # The fix: `and not _run_failed` guard on the eviction check.
+        # Simulate the variables that the eviction block uses.
+        result = {"failed": True, "final_response": None, "error": "400 invalid model"}
+        _run_failed = result.get("failed") if result else False
+        assert _run_failed is True, "Failed run should be detected"
+
+    def test_successful_run_allows_eviction(self):
+        """When result is successful, fallback eviction should proceed."""
+        result = {"completed": True, "final_response": "Hello!", "failed": False}
+        _run_failed = result.get("failed") if result else False
+        assert _run_failed is False, "Successful run should not be flagged"
+
+    def test_none_result_treated_as_not_failed(self):
+        """When result is None (edge case), treat as not-failed."""
+        result = None
+        _run_failed = result.get("failed") if result else False
+        assert _run_failed is False
+
+    def test_missing_failed_key_treated_as_not_failed(self):
+        """When result dict doesn't have 'failed' key, treat as not-failed."""
+        result = {"completed": True, "final_response": "Hello!"}
+        _run_failed = result.get("failed") if result else False
+        assert not _run_failed, "Missing 'failed' key should be falsy"

tests/gateway/test_gateway_shutdown.py

@@ -3,43 +3,15 @@ from unittest.mock import AsyncMock, MagicMock, patch
 
 import pytest
 
-from gateway.config import GatewayConfig, Platform, PlatformConfig
-from gateway.platforms.base import BasePlatformAdapter, MessageEvent, SendResult
-from gateway.run import GatewayRunner
-from gateway.session import SessionSource, build_session_key
-
-
-class StubAdapter(BasePlatformAdapter):
-    def __init__(self):
-        super().__init__(PlatformConfig(enabled=True, token="***"), Platform.TELEGRAM)
-
-    async def connect(self):
-        return True
-
-    async def disconnect(self):
-        return None
-
-    async def send(self, chat_id, content, reply_to=None, metadata=None):
-        return SendResult(success=True, message_id="1")
-
-    async def send_typing(self, chat_id, metadata=None):
-        return None
-
-    async def get_chat_info(self, chat_id):
-        return {"id": chat_id}
-
-
-def _source(chat_id="123456", chat_type="dm"):
-    return SessionSource(
-        platform=Platform.TELEGRAM,
-        chat_id=chat_id,
-        chat_type=chat_type,
-    )
+from gateway.platforms.base import MessageEvent
+from gateway.restart import GATEWAY_SERVICE_RESTART_EXIT_CODE
+from gateway.session import build_session_key
+from tests.gateway.restart_test_helpers import make_restart_runner, make_restart_source
 
 
 @pytest.mark.asyncio
 async def test_cancel_background_tasks_cancels_inflight_message_processing():
-    adapter = StubAdapter()
+    _runner, adapter = make_restart_runner()
     release = asyncio.Event()
 
     async def block_forever(_event):
@@ -47,7 +19,7 @@ async def test_cancel_background_tasks_cancels_inflight_message_processing():
         return None
 
     adapter.set_message_handler(block_forever)
-    event = MessageEvent(text="work", source=_source(), message_id="1")
+    event = MessageEvent(text="work", source=make_restart_source(), message_id="1")
 
     await adapter.handle_message(event)
     await asyncio.sleep(0)
@@ -65,17 +37,11 @@ async def test_cancel_background_tasks_cancels_inflight_message_processing():
 
 @pytest.mark.asyncio
 async def test_gateway_stop_interrupts_running_agents_and_cancels_adapter_tasks():
-    runner = object.__new__(GatewayRunner)
-    runner.config = GatewayConfig(platforms={Platform.TELEGRAM: PlatformConfig(enabled=True, token="***")})
-    runner._running = True
-    runner._shutdown_event = asyncio.Event()
-    runner._exit_reason = None
+    runner, adapter = make_restart_runner()
     runner._pending_messages = {"session": "pending text"}
     runner._pending_approvals = {"session": {"command": "rm -rf /tmp/x"}}
-    runner._background_tasks = set()
-    runner._shutdown_all_gateway_honcho = lambda: None
+    runner._restart_drain_timeout = 0.0
 
-    adapter = StubAdapter()
     release = asyncio.Event()
 
     async def block_forever(_event):
@@ -83,7 +49,7 @@ async def test_gateway_stop_interrupts_running_agents_and_cancels_adapter_tasks(
         return None
 
     adapter.set_message_handler(block_forever)
-    event = MessageEvent(text="work", source=_source(), message_id="1")
+    event = MessageEvent(text="work", source=make_restart_source(), message_id="1")
     await adapter.handle_message(event)
     await asyncio.sleep(0)
 
@@ -93,7 +59,6 @@ async def test_gateway_stop_interrupts_running_agents_and_cancels_adapter_tasks(
     session_key = build_session_key(event.source)
     running_agent = MagicMock()
     runner._running_agents = {session_key: running_agent}
-    runner.adapters = {Platform.TELEGRAM: adapter}
 
     with patch("gateway.status.remove_pid_file"), patch("gateway.status.write_runtime_status"):
         await runner.stop()
@@ -105,3 +70,78 @@ async def test_gateway_stop_interrupts_running_agents_and_cancels_adapter_tasks(
     assert runner._pending_messages == {}
     assert runner._pending_approvals == {}
     assert runner._shutdown_event.is_set() is True
+
+
+@pytest.mark.asyncio
+async def test_gateway_stop_drains_running_agents_before_disconnect():
+    runner, adapter = make_restart_runner()
+    disconnect_mock = AsyncMock()
+    adapter.disconnect = disconnect_mock
+
+    running_agent = MagicMock()
+    runner._running_agents = {"session": running_agent}
+
+    async def finish_agent():
+        await asyncio.sleep(0.05)
+        runner._running_agents.clear()
+
+    asyncio.create_task(finish_agent())
+
+    with patch("gateway.status.remove_pid_file"), patch("gateway.status.write_runtime_status"):
+        await runner.stop()
+
+    running_agent.interrupt.assert_not_called()
+    disconnect_mock.assert_awaited_once()
+    assert runner._shutdown_event.is_set() is True
+
+
+@pytest.mark.asyncio
+async def test_gateway_stop_interrupts_after_drain_timeout():
+    runner, adapter = make_restart_runner()
+    runner._restart_drain_timeout = 0.05
+
+    disconnect_mock = AsyncMock()
+    adapter.disconnect = disconnect_mock
+
+    running_agent = MagicMock()
+    runner._running_agents = {"session": running_agent}
+
+    with patch("gateway.status.remove_pid_file"), patch("gateway.status.write_runtime_status"):
+        await runner.stop()
+
+    running_agent.interrupt.assert_called_once_with("Gateway shutting down")
+    disconnect_mock.assert_awaited_once()
+    assert runner._shutdown_event.is_set() is True
+
+
+@pytest.mark.asyncio
+async def test_gateway_stop_service_restart_sets_named_exit_code():
+    runner, adapter = make_restart_runner()
+    adapter.disconnect = AsyncMock()
+
+    with patch("gateway.status.remove_pid_file"), patch("gateway.status.write_runtime_status"):
+        await runner.stop(restart=True, service_restart=True)
+
+    assert runner._exit_code == GATEWAY_SERVICE_RESTART_EXIT_CODE
+
+
+@pytest.mark.asyncio
+async def test_drain_active_agents_throttles_status_updates():
+    runner, _adapter = make_restart_runner()
+    runner._update_runtime_status = MagicMock()
+
+    runner._running_agents = {"a": MagicMock(), "b": MagicMock()}
+
+    async def finish_agents():
+        await asyncio.sleep(0.12)
+        runner._running_agents.pop("a")
+        await asyncio.sleep(0.12)
+        runner._running_agents.clear()
+
+    task = asyncio.create_task(finish_agents())
+    await runner._drain_active_agents(1.0)
+    await task
+
+    # Start, one count-change update, and final update. Allow one extra update
+    # if the loop observes the zero-agent state before exiting.
+    assert 3 <= runner._update_runtime_status.call_count <= 4

tests/gateway/test_matrix_mention.py

@@ -11,24 +11,10 @@ import pytest
 from gateway.config import PlatformConfig
 
 
-def _ensure_nio_mock():
-    """Install a mock nio module when matrix-nio isn't available."""
-    if "nio" in sys.modules and hasattr(sys.modules["nio"], "__file__"):
-        return
-    nio_mod = MagicMock()
-    nio_mod.MegolmEvent = type("MegolmEvent", (), {})
-    nio_mod.RoomMessageText = type("RoomMessageText", (), {})
-    nio_mod.RoomMessageImage = type("RoomMessageImage", (), {})
-    nio_mod.RoomMessageAudio = type("RoomMessageAudio", (), {})
-    nio_mod.RoomMessageVideo = type("RoomMessageVideo", (), {})
-    nio_mod.RoomMessageFile = type("RoomMessageFile", (), {})
-    nio_mod.DownloadResponse = type("DownloadResponse", (), {})
-    nio_mod.MemoryDownloadResponse = type("MemoryDownloadResponse", (), {})
-    nio_mod.InviteMemberEvent = type("InviteMemberEvent", (), {})
-    sys.modules.setdefault("nio", nio_mod)
-
-
-_ensure_nio_mock()
+# The matrix adapter module is importable without mautrix installed
+# (module-level imports use try/except with stubs).  No need for
+# module-level mock installation — tests that call adapter methods
+# needing real mautrix APIs mock them individually.
 
 
 def _make_adapter(tmp_path=None):
@@ -50,24 +36,25 @@ def _make_adapter(tmp_path=None):
     return adapter
 
 
-def _make_room(room_id="!room1:example.org", member_count=5, is_dm=False):
-    """Create a fake Matrix room."""
-    room = SimpleNamespace(
-        room_id=room_id,
-        member_count=member_count,
-        users={},
-    )
-    return room
+def _set_dm(adapter, room_id="!room1:example.org", is_dm=True):
+    """Mark a room as DM (or not) in the adapter's cache."""
+    adapter._dm_rooms[room_id] = is_dm
 
 
 def _make_event(
     body,
     sender="@alice:example.org",
     event_id="$evt1",
+    room_id="!room1:example.org",
     formatted_body=None,
     thread_id=None,
 ):
-    """Create a fake RoomMessageText event."""
+    """Create a fake room message event.
+
+    The mautrix adapter reads ``event.room_id``, ``event.sender``,
+    ``event.event_id``, ``event.timestamp``, and ``event.content``
+    (a dict with ``msgtype``, ``body``, etc.).
+    """
     content = {"body": body, "msgtype": "m.text"}
     if formatted_body:
         content["formatted_body"] = formatted_body
@@ -83,9 +70,9 @@ def _make_event(
     return SimpleNamespace(
         sender=sender,
         event_id=event_id,
-        server_timestamp=int(time.time() * 1000),
-        body=body,
-        source={"content": content},
+        room_id=room_id,
+        timestamp=int(time.time() * 1000),
+        content=content,
     )
 
 
@@ -152,10 +139,9 @@ async def test_require_mention_default_ignores_unmentioned(monkeypatch):
     monkeypatch.delenv("MATRIX_AUTO_THREAD", raising=False)
 
     adapter = _make_adapter()
-    room = _make_room()
     event = _make_event("hello everyone")
 
-    await adapter._on_room_message(room, event)
+    await adapter._on_room_message(event)
     adapter.handle_message.assert_not_awaited()
 
 
@@ -167,10 +153,9 @@ async def test_require_mention_default_processes_mentioned(monkeypatch):
     monkeypatch.setenv("MATRIX_AUTO_THREAD", "false")
 
     adapter = _make_adapter()
-    room = _make_room()
     event = _make_event("@hermes:example.org help me")
 
-    await adapter._on_room_message(room, event)
+    await adapter._on_room_message(event)
     adapter.handle_message.assert_awaited_once()
     msg = adapter.handle_message.await_args.args[0]
     assert msg.text == "help me"
@@ -184,11 +169,10 @@ async def test_require_mention_html_pill(monkeypatch):
     monkeypatch.setenv("MATRIX_AUTO_THREAD", "false")
 
     adapter = _make_adapter()
-    room = _make_room()
     formatted = '<a href="https://matrix.to/#/@hermes:example.org">Hermes</a> help'
     event = _make_event("Hermes help", formatted_body=formatted)
 
-    await adapter._on_room_message(room, event)
+    await adapter._on_room_message(event)
     adapter.handle_message.assert_awaited_once()
 
 
@@ -200,11 +184,11 @@ async def test_require_mention_dm_always_responds(monkeypatch):
     monkeypatch.setenv("MATRIX_AUTO_THREAD", "false")
 
     adapter = _make_adapter()
-    # member_count=2 triggers DM detection
-    room = _make_room(member_count=2)
+    # Mark the room as a DM via the adapter's cache.
+    _set_dm(adapter)
     event = _make_event("hello without mention")
 
-    await adapter._on_room_message(room, event)
+    await adapter._on_room_message(event)
     adapter.handle_message.assert_awaited_once()
 
 
@@ -216,10 +200,10 @@ async def test_dm_strips_mention(monkeypatch):
     monkeypatch.setenv("MATRIX_AUTO_THREAD", "false")
 
     adapter = _make_adapter()
-    room = _make_room(member_count=2)
+    _set_dm(adapter)
     event = _make_event("@hermes:example.org help me")
 
-    await adapter._on_room_message(room, event)
+    await adapter._on_room_message(event)
     adapter.handle_message.assert_awaited_once()
     msg = adapter.handle_message.await_args.args[0]
     assert msg.text == "help me"
@@ -233,10 +217,9 @@ async def test_bare_mention_passes_empty_string(monkeypatch):
     monkeypatch.setenv("MATRIX_AUTO_THREAD", "false")
 
     adapter = _make_adapter()
-    room = _make_room()
     event = _make_event("@hermes:example.org")
 
-    await adapter._on_room_message(room, event)
+    await adapter._on_room_message(event)
     adapter.handle_message.assert_awaited_once()
     msg = adapter.handle_message.await_args.args[0]
     assert msg.text == ""
@@ -250,10 +233,9 @@ async def test_require_mention_free_response_room(monkeypatch):
     monkeypatch.setenv("MATRIX_AUTO_THREAD", "false")
 
     adapter = _make_adapter()
-    room = _make_room(room_id="!room1:example.org")
-    event = _make_event("hello without mention")
+    event = _make_event("hello without mention", room_id="!room1:example.org")
 
-    await adapter._on_room_message(room, event)
+    await adapter._on_room_message(event)
     adapter.handle_message.assert_awaited_once()
 
 
@@ -267,10 +249,9 @@ async def test_require_mention_bot_participated_thread(monkeypatch):
     adapter = _make_adapter()
     adapter._bot_participated_threads.add("$thread1")
 
-    room = _make_room()
     event = _make_event("hello without mention", thread_id="$thread1")
 
-    await adapter._on_room_message(room, event)
+    await adapter._on_room_message(event)
     adapter.handle_message.assert_awaited_once()
 
 
@@ -282,10 +263,9 @@ async def test_require_mention_disabled(monkeypatch):
     monkeypatch.setenv("MATRIX_AUTO_THREAD", "false")
 
     adapter = _make_adapter()
-    room = _make_room()
     event = _make_event("hello without mention")
 
-    await adapter._on_room_message(room, event)
+    await adapter._on_room_message(event)
     adapter.handle_message.assert_awaited_once()
     msg = adapter.handle_message.await_args.args[0]
     assert msg.text == "hello without mention"
@@ -303,10 +283,9 @@ async def test_auto_thread_default_creates_thread(monkeypatch):
     monkeypatch.delenv("MATRIX_AUTO_THREAD", raising=False)
 
     adapter = _make_adapter()
-    room = _make_room()
     event = _make_event("hello", event_id="$msg1")
 
-    await adapter._on_room_message(room, event)
+    await adapter._on_room_message(event)
     adapter.handle_message.assert_awaited_once()
     msg = adapter.handle_message.await_args.args[0]
     assert msg.source.thread_id == "$msg1"
@@ -320,10 +299,9 @@ async def test_auto_thread_preserves_existing_thread(monkeypatch):
 
     adapter = _make_adapter()
     adapter._bot_participated_threads.add("$thread_root")
-    room = _make_room()
     event = _make_event("reply in thread", thread_id="$thread_root")
 
-    await adapter._on_room_message(room, event)
+    await adapter._on_room_message(event)
     adapter.handle_message.assert_awaited_once()
     msg = adapter.handle_message.await_args.args[0]
     assert msg.source.thread_id == "$thread_root"
@@ -336,10 +314,10 @@ async def test_auto_thread_skips_dm(monkeypatch):
     monkeypatch.delenv("MATRIX_AUTO_THREAD", raising=False)
 
     adapter = _make_adapter()
-    room = _make_room(member_count=2)
+    _set_dm(adapter)
     event = _make_event("hello dm", event_id="$dm1")
 
-    await adapter._on_room_message(room, event)
+    await adapter._on_room_message(event)
     adapter.handle_message.assert_awaited_once()
     msg = adapter.handle_message.await_args.args[0]
     assert msg.source.thread_id is None
@@ -352,10 +330,9 @@ async def test_auto_thread_disabled(monkeypatch):
     monkeypatch.setenv("MATRIX_AUTO_THREAD", "false")
 
     adapter = _make_adapter()
-    room = _make_room()
     event = _make_event("hello", event_id="$msg1")
 
-    await adapter._on_room_message(room, event)
+    await adapter._on_room_message(event)
     adapter.handle_message.assert_awaited_once()
     msg = adapter.handle_message.await_args.args[0]
     assert msg.source.thread_id is None
@@ -368,11 +345,10 @@ async def test_auto_thread_tracks_participation(monkeypatch):
     monkeypatch.delenv("MATRIX_AUTO_THREAD", raising=False)
 
     adapter = _make_adapter()
-    room = _make_room()
     event = _make_event("hello", event_id="$msg1")
 
     with patch.object(adapter, "_save_participated_threads"):
-        await adapter._on_room_message(room, event)
+        await adapter._on_room_message(event)
 
     assert "$msg1" in adapter._bot_participated_threads
 
@@ -385,8 +361,9 @@ async def test_auto_thread_tracks_participation(monkeypatch):
 class TestThreadPersistence:
     def test_empty_state_file(self, tmp_path, monkeypatch):
         """No state file → empty set."""
+        from gateway.platforms.matrix import MatrixAdapter
         monkeypatch.setattr(
-            "gateway.platforms.matrix.MatrixAdapter._thread_state_path",
+            MatrixAdapter, "_thread_state_path",
             staticmethod(lambda: tmp_path / "matrix_threads.json"),
         )
         adapter = _make_adapter()
@@ -395,9 +372,10 @@ class TestThreadPersistence:
 
     def test_track_thread_persists(self, tmp_path, monkeypatch):
         """_track_thread writes to disk."""
+        from gateway.platforms.matrix import MatrixAdapter
         state_path = tmp_path / "matrix_threads.json"
         monkeypatch.setattr(
-            "gateway.platforms.matrix.MatrixAdapter._thread_state_path",
+            MatrixAdapter, "_thread_state_path",
             staticmethod(lambda: state_path),
         )
         adapter = _make_adapter()
@@ -408,10 +386,11 @@ class TestThreadPersistence:
 
     def test_threads_survive_reload(self, tmp_path, monkeypatch):
         """Persisted threads are loaded by a new adapter instance."""
+        from gateway.platforms.matrix import MatrixAdapter
         state_path = tmp_path / "matrix_threads.json"
         state_path.write_text(json.dumps(["$t1", "$t2"]))
         monkeypatch.setattr(
-            "gateway.platforms.matrix.MatrixAdapter._thread_state_path",
+            MatrixAdapter, "_thread_state_path",
             staticmethod(lambda: state_path),
         )
         adapter = _make_adapter()
@@ -420,9 +399,10 @@ class TestThreadPersistence:
 
     def test_cap_max_tracked_threads(self, tmp_path, monkeypatch):
         """Thread set is trimmed to _MAX_TRACKED_THREADS."""
+        from gateway.platforms.matrix import MatrixAdapter
         state_path = tmp_path / "matrix_threads.json"
         monkeypatch.setattr(
-            "gateway.platforms.matrix.MatrixAdapter._thread_state_path",
+            MatrixAdapter, "_thread_state_path",
             staticmethod(lambda: state_path),
         )
         adapter = _make_adapter()
@@ -448,10 +428,10 @@ async def test_dm_mention_thread_disabled_by_default(monkeypatch):
     monkeypatch.setenv("MATRIX_AUTO_THREAD", "false")
 
     adapter = _make_adapter()
-    room = _make_room(member_count=2)
+    _set_dm(adapter)
     event = _make_event("@hermes:example.org help me", event_id="$dm1")
 
-    await adapter._on_room_message(room, event)
+    await adapter._on_room_message(event)
     adapter.handle_message.assert_awaited_once()
     msg = adapter.handle_message.await_args.args[0]
     assert msg.source.thread_id is None
@@ -464,11 +444,11 @@ async def test_dm_mention_thread_creates_thread(monkeypatch):
     monkeypatch.setenv("MATRIX_AUTO_THREAD", "false")
 
     adapter = _make_adapter()
-    room = _make_room(member_count=2)
+    _set_dm(adapter)
     event = _make_event("@hermes:example.org help me", event_id="$dm1")
 
     with patch.object(adapter, "_save_participated_threads"):
-        await adapter._on_room_message(room, event)
+        await adapter._on_room_message(event)
 
     adapter.handle_message.assert_awaited_once()
     msg = adapter.handle_message.await_args.args[0]
@@ -483,10 +463,10 @@ async def test_dm_mention_thread_no_mention_no_thread(monkeypatch):
     monkeypatch.setenv("MATRIX_AUTO_THREAD", "false")
 
     adapter = _make_adapter()
-    room = _make_room(member_count=2)
+    _set_dm(adapter)
     event = _make_event("hello without mention", event_id="$dm1")
 
-    await adapter._on_room_message(room, event)
+    await adapter._on_room_message(event)
     adapter.handle_message.assert_awaited_once()
     msg = adapter.handle_message.await_args.args[0]
     assert msg.source.thread_id is None
@@ -499,11 +479,11 @@ async def test_dm_mention_thread_preserves_existing_thread(monkeypatch):
     monkeypatch.setenv("MATRIX_AUTO_THREAD", "false")
 
     adapter = _make_adapter()
+    _set_dm(adapter)
     adapter._bot_participated_threads.add("$existing_thread")
-    room = _make_room(member_count=2)
     event = _make_event("@hermes:example.org help me", thread_id="$existing_thread")
 
-    await adapter._on_room_message(room, event)
+    await adapter._on_room_message(event)
     adapter.handle_message.assert_awaited_once()
     msg = adapter.handle_message.await_args.args[0]
     assert msg.source.thread_id == "$existing_thread"
@@ -516,11 +496,11 @@ async def test_dm_mention_thread_tracks_participation(monkeypatch):
     monkeypatch.setenv("MATRIX_AUTO_THREAD", "false")
 
     adapter = _make_adapter()
-    room = _make_room(member_count=2)
+    _set_dm(adapter)
     event = _make_event("@hermes:example.org help", event_id="$dm1")
 
     with patch.object(adapter, "_save_participated_threads"):
-        await adapter._on_room_message(room, event)
+        await adapter._on_room_message(event)
 
     assert "$dm1" in adapter._bot_participated_threads
 

tests/gateway/test_matrix_voice.py

@@ -1,18 +1,23 @@
-"""Tests for Matrix voice message support (MSC3245)."""
+"""Tests for Matrix voice message support (MSC3245).
+
+Updated for the mautrix-python SDK (no more matrix-nio / nio imports).
+"""
 import io
+import os
+import tempfile
 import types
+from types import SimpleNamespace
 
 import pytest
 from unittest.mock import AsyncMock, MagicMock, patch
 
-# Try importing real nio; skip entire file if not available.
-# A MagicMock in sys.modules (from another test) is not the real package.
+# Try importing mautrix; skip entire file if not available.
 try:
-    import nio as _nio_probe
-    if not isinstance(_nio_probe, types.ModuleType) or not hasattr(_nio_probe, "__file__"):
-        pytest.skip("nio in sys.modules is a mock, not the real package", allow_module_level=True)
+    import mautrix as _mautrix_probe
+    if not isinstance(_mautrix_probe, types.ModuleType) or not hasattr(_mautrix_probe, "__file__"):
+        pytest.skip("mautrix in sys.modules is a mock, not the real package", allow_module_level=True)
 except ImportError:
-    pytest.skip("matrix-nio not installed", allow_module_level=True)
+    pytest.skip("mautrix not installed", allow_module_level=True)
 
 from gateway.platforms.base import MessageType
 
@@ -25,7 +30,7 @@ def _make_adapter():
     """Create a MatrixAdapter with mocked config."""
     from gateway.platforms.matrix import MatrixAdapter
     from gateway.config import PlatformConfig
-    
+
     config = PlatformConfig(
         enabled=True,
         token="***",
@@ -38,32 +43,26 @@ def _make_adapter():
     return adapter
 
 
-def _make_room(room_id: str = "!test:example.org", member_count: int = 2):
-    """Create a mock Matrix room."""
-    room = MagicMock()
-    room.room_id = room_id
-    room.member_count = member_count
-    return room
-
-
 def _make_audio_event(
     event_id: str = "$audio_event",
     sender: str = "@alice:example.org",
+    room_id: str = "!test:example.org",
     body: str = "Voice message",
     url: str = "mxc://example.org/abc123",
     is_voice: bool = False,
     mimetype: str = "audio/ogg",
-    timestamp: float = 9999999999000,  # ms
+    timestamp: int = 9999999999000,  # ms
 ):
     """
-    Create a mock RoomMessageAudio event that passes isinstance checks.
-    
+    Create a mock mautrix room message event.
+
+    In mautrix, the handler receives a single event object with attributes
+    ``room_id``, ``sender``, ``event_id``, ``timestamp``, and ``content``
+    (a dict-like or serializable object).
+
     Args:
-        is_voice: If True, adds org.matrix.msc3245.voice field to content
+        is_voice: If True, adds org.matrix.msc3245.voice field to content.
     """
-    import nio
-    
-    # Build the source dict that nio events expose via .source
     content = {
         "msgtype": "m.audio",
         "body": body,
@@ -72,39 +71,35 @@ def _make_audio_event(
             "mimetype": mimetype,
         },
     }
-    
+
     if is_voice:
         content["org.matrix.msc3245.voice"] = {}
-    
-    # Create a real nio RoomMessageAudio-like object
-    # We use MagicMock but configure __class__ to pass isinstance check
-    event = MagicMock(spec=nio.RoomMessageAudio)
-    event.event_id = event_id
-    event.sender = sender
-    event.body = body
-    event.url = url
-    event.server_timestamp = timestamp
-    event.source = {
-        "type": "m.room.message",
-        "content": content,
-    }
-    # For MIME type extraction - needs to be a dict
-    event.content = content
-    
+
+    event = SimpleNamespace(
+        event_id=event_id,
+        sender=sender,
+        room_id=room_id,
+        timestamp=timestamp,
+        content=content,
+    )
     return event
 
 
-def _make_download_response(body: bytes = b"fake audio data"):
-    """Create a mock nio.MemoryDownloadResponse."""
-    import nio
-    resp = MagicMock()
-    resp.body = body
-    resp.__class__ = nio.MemoryDownloadResponse
-    return resp
+def _make_state_store(member_count: int = 2):
+    """Create a mock state store with get_members/get_member support."""
+    store = MagicMock()
+    # get_members returns a list of member user IDs
+    members = [MagicMock() for _ in range(member_count)]
+    store.get_members = AsyncMock(return_value=members)
+    # get_member returns a single member info object
+    member = MagicMock()
+    member.displayname = "Alice"
+    store.get_member = AsyncMock(return_value=member)
+    return store
 
 
 # ---------------------------------------------------------------------------
-# Tests: MSC3245 Voice Detection (RED -> GREEN)
+# Tests: MSC3245 Voice Detection
 # ---------------------------------------------------------------------------
 
 class TestMatrixVoiceMessageDetection:
@@ -118,27 +113,28 @@ class TestMatrixVoiceMessageDetection:
         self.adapter._message_handler = AsyncMock()
         # Mock _mxc_to_http to return a fake HTTP URL
         self.adapter._mxc_to_http = lambda url: f"https://matrix.example.org/_matrix/media/v3/download/{url[6:]}"
-        # Mock client for authenticated download
+        # Mock client for authenticated download — download_media returns bytes directly
         self.adapter._client = MagicMock()
-        self.adapter._client.download = AsyncMock(return_value=_make_download_response())
+        self.adapter._client.download_media = AsyncMock(return_value=b"fake audio data")
+        # State store for DM detection
+        self.adapter._client.state_store = _make_state_store()
 
     @pytest.mark.asyncio
     async def test_voice_message_has_type_voice(self):
         """Voice messages (with MSC3245 field) should be MessageType.VOICE."""
-        room = _make_room()
         event = _make_audio_event(is_voice=True)
-        
+
         # Capture the MessageEvent passed to handle_message
         captured_event = None
-        
+
         async def capture(msg_event):
             nonlocal captured_event
             captured_event = msg_event
-        
+
         self.adapter.handle_message = capture
-        
-        await self.adapter._on_room_message_media(room, event)
-        
+
+        await self.adapter._on_room_message(event)
+
         assert captured_event is not None, "No event was captured"
         assert captured_event.message_type == MessageType.VOICE, \
             f"Expected MessageType.VOICE, got {captured_event.message_type}"
@@ -146,44 +142,43 @@ class TestMatrixVoiceMessageDetection:
     @pytest.mark.asyncio
     async def test_voice_message_has_local_path(self):
         """Voice messages should have a local cached path in media_urls."""
-        room = _make_room()
         event = _make_audio_event(is_voice=True)
-        
+
         captured_event = None
-        
+
         async def capture(msg_event):
             nonlocal captured_event
             captured_event = msg_event
-        
+
         self.adapter.handle_message = capture
-        
-        await self.adapter._on_room_message_media(room, event)
-        
+
+        await self.adapter._on_room_message(event)
+
         assert captured_event is not None
         assert captured_event.media_urls is not None
         assert len(captured_event.media_urls) > 0
         # Should be a local path, not an HTTP URL
         assert not captured_event.media_urls[0].startswith("http"), \
             f"media_urls should contain local path, got {captured_event.media_urls[0]}"
-        self.adapter._client.download.assert_awaited_once_with(mxc=event.url)
+        # download_media is called with a ContentURI wrapping the mxc URL
+        self.adapter._client.download_media.assert_awaited_once()
         assert captured_event.media_types == ["audio/ogg"]
 
     @pytest.mark.asyncio
     async def test_audio_without_msc3245_stays_audio_type(self):
         """Regular audio uploads (no MSC3245 field) should remain MessageType.AUDIO."""
-        room = _make_room()
         event = _make_audio_event(is_voice=False)  # NOT a voice message
-        
+
         captured_event = None
-        
+
         async def capture(msg_event):
             nonlocal captured_event
             captured_event = msg_event
-        
+
         self.adapter.handle_message = capture
-        
-        await self.adapter._on_room_message_media(room, event)
-        
+
+        await self.adapter._on_room_message(event)
+
         assert captured_event is not None
         assert captured_event.message_type == MessageType.AUDIO, \
             f"Expected MessageType.AUDIO for non-voice, got {captured_event.message_type}"
@@ -191,25 +186,24 @@ class TestMatrixVoiceMessageDetection:
     @pytest.mark.asyncio
     async def test_regular_audio_has_http_url(self):
         """Regular audio uploads should keep HTTP URL (not cached locally)."""
-        room = _make_room()
         event = _make_audio_event(is_voice=False)
-        
+
         captured_event = None
-        
+
         async def capture(msg_event):
             nonlocal captured_event
             captured_event = msg_event
-        
+
         self.adapter.handle_message = capture
-        
-        await self.adapter._on_room_message_media(room, event)
-        
+
+        await self.adapter._on_room_message(event)
+
         assert captured_event is not None
         assert captured_event.media_urls is not None
         # Should be HTTP URL, not local path
         assert captured_event.media_urls[0].startswith("http"), \
             f"Non-voice audio should have HTTP URL, got {captured_event.media_urls[0]}"
-        self.adapter._client.download.assert_not_awaited()
+        self.adapter._client.download_media.assert_not_awaited()
         assert captured_event.media_types == ["audio/ogg"]
 
 
@@ -224,29 +218,26 @@ class TestMatrixVoiceCacheFallback:
         self.adapter._message_handler = AsyncMock()
         self.adapter._mxc_to_http = lambda url: f"https://matrix.example.org/_matrix/media/v3/download/{url[6:]}"
         self.adapter._client = MagicMock()
+        self.adapter._client.state_store = _make_state_store()
 
     @pytest.mark.asyncio
     async def test_voice_cache_failure_falls_back_to_http_url(self):
-        """If caching fails, voice message should still be delivered with HTTP URL."""
-        room = _make_room()
+        """If caching fails (download returns None), voice message should still be delivered with HTTP URL."""
         event = _make_audio_event(is_voice=True)
-        
-        # Make download fail
-        import nio
-        error_resp = MagicMock()
-        error_resp.__class__ = nio.DownloadError
-        self.adapter._client.download = AsyncMock(return_value=error_resp)
-        
+
+        # download_media returns None on failure
+        self.adapter._client.download_media = AsyncMock(return_value=None)
+
         captured_event = None
-        
+
         async def capture(msg_event):
             nonlocal captured_event
             captured_event = msg_event
-        
+
         self.adapter.handle_message = capture
-        
-        await self.adapter._on_room_message_media(room, event)
-        
+
+        await self.adapter._on_room_message(event)
+
         assert captured_event is not None
         assert captured_event.media_urls is not None
         # Should fall back to HTTP URL
@@ -256,10 +247,9 @@ class TestMatrixVoiceCacheFallback:
     @pytest.mark.asyncio
     async def test_voice_cache_exception_falls_back_to_http_url(self):
         """Unexpected download exceptions should also fall back to HTTP URL."""
-        room = _make_room()
         event = _make_audio_event(is_voice=True)
 
-        self.adapter._client.download = AsyncMock(side_effect=RuntimeError("boom"))
+        self.adapter._client.download_media = AsyncMock(side_effect=RuntimeError("boom"))
 
         captured_event = None
 
@@ -269,7 +259,7 @@ class TestMatrixVoiceCacheFallback:
 
         self.adapter.handle_message = capture
 
-        await self.adapter._on_room_message_media(room, event)
+        await self.adapter._on_room_message(event)
 
         assert captured_event is not None
         assert captured_event.media_urls is not None
@@ -278,7 +268,7 @@ class TestMatrixVoiceCacheFallback:
 
 
 # ---------------------------------------------------------------------------
-# Tests: send_voice includes MSC3245 field (RED -> GREEN)
+# Tests: send_voice includes MSC3245 field
 # ---------------------------------------------------------------------------
 
 class TestMatrixSendVoiceMSC3245:
@@ -287,62 +277,52 @@ class TestMatrixSendVoiceMSC3245:
     def setup_method(self):
         self.adapter = _make_adapter()
         self.adapter._user_id = "@bot:example.org"
-        # Mock client with successful upload
+        # Mock client — upload_media returns a ContentURI string
         self.adapter._client = MagicMock()
         self.upload_call = None
 
-        async def mock_upload(*args, **kwargs):
-            self.upload_call = (args, kwargs)
-            import nio
-            resp = MagicMock()
-            resp.content_uri = "mxc://example.org/uploaded"
-            resp.__class__ = nio.UploadResponse
-            return resp, None
+        async def mock_upload_media(data, mime_type=None, filename=None, **kwargs):
+            self.upload_call = {"data": data, "mime_type": mime_type, "filename": filename}
+            return "mxc://example.org/uploaded"
 
-        self.adapter._client.upload = mock_upload
+        self.adapter._client.upload_media = mock_upload_media
 
     @pytest.mark.asyncio
-    async def test_send_voice_includes_msc3245_field(self):
+    @patch("mimetypes.guess_type", return_value=("audio/ogg", None))
+    async def test_send_voice_includes_msc3245_field(self, _mock_guess):
         """send_voice should include org.matrix.msc3245.voice in message content."""
-        import tempfile
-        import os
-        
         # Create a temp audio file
         with tempfile.NamedTemporaryFile(suffix=".ogg", delete=False) as f:
             f.write(b"fake audio data")
             temp_path = f.name
-        
+
         try:
-            # Capture the message content sent to room_send
+            # Capture the message content sent via send_message_event
             sent_content = None
-            
-            async def mock_room_send(room_id, event_type, content):
+
+            async def mock_send_message_event(room_id, event_type, content):
                 nonlocal sent_content
                 sent_content = content
-                resp = MagicMock()
-                resp.event_id = "$sent_event"
-                import nio
-                resp.__class__ = nio.RoomSendResponse
-                return resp
-            
-            self.adapter._client.room_send = mock_room_send
-            
+                # send_message_event returns an EventID string
+                return "$sent_event"
+
+            self.adapter._client.send_message_event = mock_send_message_event
+
             await self.adapter.send_voice(
                 chat_id="!room:example.org",
                 audio_path=temp_path,
                 caption="Test voice",
             )
-            
+
             assert sent_content is not None, "No message was sent"
             assert "org.matrix.msc3245.voice" in sent_content, \
                 f"MSC3245 voice field missing from content: {sent_content.keys()}"
             assert sent_content["msgtype"] == "m.audio"
             assert sent_content["info"]["mimetype"] == "audio/ogg"
-            assert self.upload_call is not None, "Expected upload() to be called"
-            args, kwargs = self.upload_call
-            assert isinstance(args[0], io.BytesIO)
-            assert kwargs["content_type"] == "audio/ogg"
-            assert kwargs["filename"].endswith(".ogg")
+            assert self.upload_call is not None, "Expected upload_media() to be called"
+            assert isinstance(self.upload_call["data"], bytes)
+            assert self.upload_call["mime_type"] == "audio/ogg"
+            assert self.upload_call["filename"].endswith(".ogg")
 
         finally:
             os.unlink(temp_path)

tests/gateway/test_restart_drain.py

@@ -0,0 +1,160 @@
+import asyncio
+import shutil
+import subprocess
+from unittest.mock import AsyncMock, MagicMock
+
+import pytest
+
+import gateway.run as gateway_run
+from gateway.platforms.base import MessageEvent, MessageType
+from gateway.restart import DEFAULT_GATEWAY_RESTART_DRAIN_TIMEOUT
+from gateway.session import build_session_key
+from tests.gateway.restart_test_helpers import make_restart_runner, make_restart_source
+
+
+@pytest.mark.asyncio
+async def test_restart_command_while_busy_requests_drain_without_interrupt():
+    runner, _adapter = make_restart_runner()
+    runner.request_restart = MagicMock(return_value=True)
+    event = MessageEvent(
+        text="/restart",
+        message_type=MessageType.TEXT,
+        source=make_restart_source(),
+        message_id="m1",
+    )
+    session_key = build_session_key(event.source)
+    running_agent = MagicMock()
+    runner._running_agents[session_key] = running_agent
+
+    result = await runner._handle_message(event)
+
+    assert result == "⏳ Draining 1 active agent(s) before restart..."
+    running_agent.interrupt.assert_not_called()
+    runner.request_restart.assert_called_once_with(detached=True, via_service=False)
+
+
+@pytest.mark.asyncio
+async def test_drain_queue_mode_queues_follow_up_without_interrupt():
+    runner, adapter = make_restart_runner()
+    runner._draining = True
+    runner._restart_requested = True
+    runner._busy_input_mode = "queue"
+
+    event = MessageEvent(
+        text="follow up",
+        message_type=MessageType.TEXT,
+        source=make_restart_source(),
+        message_id="m2",
+    )
+    session_key = build_session_key(event.source)
+    adapter._active_sessions[session_key] = asyncio.Event()
+
+    await adapter.handle_message(event)
+
+    assert session_key in adapter._pending_messages
+    assert adapter._pending_messages[session_key].text == "follow up"
+    assert not adapter._active_sessions[session_key].is_set()
+    assert any("queued for the next turn" in message for message in adapter.sent)
+
+
+@pytest.mark.asyncio
+async def test_draining_rejects_new_session_messages():
+    runner, _adapter = make_restart_runner()
+    runner._draining = True
+    runner._restart_requested = True
+
+    event = MessageEvent(
+        text="hello",
+        message_type=MessageType.TEXT,
+        source=make_restart_source("fresh"),
+        message_id="m3",
+    )
+
+    result = await runner._handle_message(event)
+
+    assert result == "⏳ Gateway is restarting and is not accepting new work right now."
+
+
+def test_load_busy_input_mode_prefers_env_then_config_then_default(tmp_path, monkeypatch):
+    monkeypatch.setattr(gateway_run, "_hermes_home", tmp_path)
+    monkeypatch.delenv("HERMES_GATEWAY_BUSY_INPUT_MODE", raising=False)
+
+    assert gateway_run.GatewayRunner._load_busy_input_mode() == "interrupt"
+
+    (tmp_path / "config.yaml").write_text(
+        "display:\n  busy_input_mode: queue\n", encoding="utf-8"
+    )
+    assert gateway_run.GatewayRunner._load_busy_input_mode() == "queue"
+
+    monkeypatch.setenv("HERMES_GATEWAY_BUSY_INPUT_MODE", "interrupt")
+    assert gateway_run.GatewayRunner._load_busy_input_mode() == "interrupt"
+
+
+def test_load_restart_drain_timeout_prefers_env_then_config_then_default(
+    tmp_path, monkeypatch, caplog
+):
+    monkeypatch.setattr(gateway_run, "_hermes_home", tmp_path)
+    monkeypatch.delenv("HERMES_RESTART_DRAIN_TIMEOUT", raising=False)
+
+    assert (
+        gateway_run.GatewayRunner._load_restart_drain_timeout()
+        == DEFAULT_GATEWAY_RESTART_DRAIN_TIMEOUT
+    )
+
+    (tmp_path / "config.yaml").write_text(
+        "agent:\n  restart_drain_timeout: 12\n", encoding="utf-8"
+    )
+    assert gateway_run.GatewayRunner._load_restart_drain_timeout() == 12.0
+
+    monkeypatch.setenv("HERMES_RESTART_DRAIN_TIMEOUT", "7")
+    assert gateway_run.GatewayRunner._load_restart_drain_timeout() == 7.0
+
+    monkeypatch.setenv("HERMES_RESTART_DRAIN_TIMEOUT", "invalid")
+    assert (
+        gateway_run.GatewayRunner._load_restart_drain_timeout()
+        == DEFAULT_GATEWAY_RESTART_DRAIN_TIMEOUT
+    )
+    assert "Invalid restart_drain_timeout" in caplog.text
+
+
+@pytest.mark.asyncio
+async def test_request_restart_is_idempotent():
+    runner, _adapter = make_restart_runner()
+    runner.stop = AsyncMock()
+
+    assert runner.request_restart(detached=True, via_service=False) is True
+    first_task = next(iter(runner._background_tasks))
+    assert runner.request_restart(detached=True, via_service=False) is False
+
+    await first_task
+
+    runner.stop.assert_awaited_once_with(
+        restart=True, detached_restart=True, service_restart=False
+    )
+
+
+@pytest.mark.asyncio
+async def test_launch_detached_restart_command_uses_setsid(monkeypatch):
+    runner, _adapter = make_restart_runner()
+    popen_calls = []
+
+    monkeypatch.setattr(gateway_run, "_resolve_hermes_bin", lambda: ["/usr/bin/hermes"])
+    monkeypatch.setattr(gateway_run.os, "getpid", lambda: 321)
+    monkeypatch.setattr(shutil, "which", lambda cmd: "/usr/bin/setsid" if cmd == "setsid" else None)
+
+    def fake_popen(cmd, **kwargs):
+        popen_calls.append((cmd, kwargs))
+        return MagicMock()
+
+    monkeypatch.setattr(subprocess, "Popen", fake_popen)
+
+    await runner._launch_detached_restart_command()
+
+    assert len(popen_calls) == 1
+    cmd, kwargs = popen_calls[0]
+    assert cmd[:2] == ["/usr/bin/setsid", "bash"]
+    assert "gateway restart" in cmd[-1]
+    assert "kill -0 321" in cmd[-1]
+    assert kwargs["start_new_session"] is True
+    assert kwargs["stdout"] is subprocess.DEVNULL
+    assert kwargs["stderr"] is subprocess.DEVNULL

tests/gateway/test_resume_command.py

@@ -221,5 +221,6 @@ class TestHandleResumeCommand:
 
         runner._async_flush_memories.assert_called_once_with(
             "current_session_001",
+            "agent:main:telegram:dm:67890",
         )
         db.close()

tests/gateway/test_session_boundary_hooks.py

@@ -127,6 +127,16 @@ async def test_shutdown_fires_finalize_for_active_agents(mock_invoke_hook):
     runner._shutdown_event = MagicMock()
     runner.adapters = {}
     runner._exit_reason = "test"
+    runner._exit_code = None
+    runner._draining = False
+    runner._restart_requested = False
+    runner._restart_task_started = False
+    runner._restart_detached = False
+    runner._restart_via_service = False
+    runner._restart_drain_timeout = 0.0
+    runner._stop_task = None
+    runner._running_agents_ts = {}
+    runner._update_runtime_status = MagicMock()
 
     agent1 = MagicMock()
     agent1.session_id = "sess-a"

tests/gateway/test_session_model_override_routing.py

@@ -0,0 +1,160 @@
+"""Regression tests for session-scoped model/provider overrides in gateway agents.
+
+These cover the bug where `/model ...` stored a session override, but fresh
+agent constructions still resolved model/provider from global config/runtime.
+That let helper agents (and cache-miss main agents) route GPT-5.4 to the wrong
+provider, e.g. Nous instead of OpenAI Codex.
+"""
+
+import asyncio
+import sys
+import threading
+import types
+from unittest.mock import AsyncMock, MagicMock
+
+import pytest
+
+import gateway.run as gateway_run
+from gateway.config import Platform
+from gateway.session import SessionSource
+
+
+class _CapturingAgent:
+    """Fake agent that records init kwargs for assertions."""
+
+    last_init = None
+
+    def __init__(self, *args, **kwargs):
+        type(self).last_init = dict(kwargs)
+        self.tools = []
+
+    def run_conversation(self, user_message: str, conversation_history=None, task_id=None):
+        return {
+            "final_response": "ok",
+            "messages": [],
+            "api_calls": 1,
+        }
+
+
+def _make_runner():
+    runner = object.__new__(gateway_run.GatewayRunner)
+    runner.adapters = {}
+    runner.session_store = None
+    runner.config = None
+    runner._voice_mode = {}
+    runner._ephemeral_system_prompt = ""
+    runner._prefill_messages = []
+    runner._reasoning_config = None
+    runner._show_reasoning = False
+    runner._provider_routing = {}
+    runner._fallback_model = None
+    runner._service_tier = None
+    runner._running_agents = {}
+    runner._running_agents_ts = {}
+    runner._background_tasks = set()
+    runner._session_db = None
+    runner._session_model_overrides = {}
+    runner._pending_model_notes = {}
+    runner._pending_approvals = {}
+    runner._agent_cache = {}
+    runner._agent_cache_lock = threading.Lock()
+    runner._get_or_create_gateway_honcho = lambda session_key: (None, None)
+    runner.hooks = MagicMock()
+    runner.hooks.emit = AsyncMock()
+    runner.hooks.loaded_hooks = []
+    return runner
+
+
+def _codex_override():
+    return {
+        "model": "gpt-5.4",
+        "provider": "openai-codex",
+        "api_key": "***",
+        "base_url": "https://chatgpt.com/backend-api/codex",
+        "api_mode": "codex_responses",
+    }
+
+
+def _explode_runtime_resolution():
+    raise AssertionError(
+        "global runtime resolution should not run when a complete session override exists"
+    )
+
+
+def test_run_agent_prefers_session_override_over_global_runtime(monkeypatch):
+    monkeypatch.setattr(gateway_run, "_load_gateway_config", lambda: {})
+    monkeypatch.setattr(gateway_run, "load_dotenv", lambda *args, **kwargs: None)
+    monkeypatch.setattr(gateway_run, "_resolve_runtime_agent_kwargs", _explode_runtime_resolution)
+
+    fake_run_agent = types.ModuleType("run_agent")
+    fake_run_agent.AIAgent = _CapturingAgent
+    monkeypatch.setitem(sys.modules, "run_agent", fake_run_agent)
+
+    _CapturingAgent.last_init = None
+    runner = _make_runner()
+
+    source = SessionSource(
+        platform=Platform.LOCAL,
+        chat_id="cli",
+        chat_name="CLI",
+        chat_type="dm",
+        user_id="user-1",
+    )
+    session_key = "agent:main:local:dm"
+    runner._session_model_overrides[session_key] = _codex_override()
+
+    result = asyncio.run(
+        runner._run_agent(
+            message="ping",
+            context_prompt="",
+            history=[],
+            source=source,
+            session_id="session-1",
+            session_key=session_key,
+        )
+    )
+
+    assert result["final_response"] == "ok"
+    assert _CapturingAgent.last_init is not None
+    assert _CapturingAgent.last_init["model"] == "gpt-5.4"
+    assert _CapturingAgent.last_init["provider"] == "openai-codex"
+    assert _CapturingAgent.last_init["api_mode"] == "codex_responses"
+    assert _CapturingAgent.last_init["base_url"] == "https://chatgpt.com/backend-api/codex"
+    assert _CapturingAgent.last_init["api_key"] == "***"
+
+
+@pytest.mark.asyncio
+async def test_background_task_prefers_session_override_over_global_runtime(monkeypatch):
+    monkeypatch.setattr(gateway_run, "_load_gateway_config", lambda: {})
+    monkeypatch.setattr(gateway_run, "_resolve_runtime_agent_kwargs", _explode_runtime_resolution)
+
+    fake_run_agent = types.ModuleType("run_agent")
+    fake_run_agent.AIAgent = _CapturingAgent
+    monkeypatch.setitem(sys.modules, "run_agent", fake_run_agent)
+
+    _CapturingAgent.last_init = None
+    runner = _make_runner()
+
+    adapter = AsyncMock()
+    adapter.send = AsyncMock()
+    adapter.extract_media = MagicMock(return_value=([], "ok"))
+    adapter.extract_images = MagicMock(return_value=([], "ok"))
+    runner.adapters[Platform.TELEGRAM] = adapter
+
+    source = SessionSource(
+        platform=Platform.TELEGRAM,
+        user_id="12345",
+        chat_id="67890",
+        user_name="testuser",
+    )
+    session_key = runner._session_key_for_source(source)
+    runner._session_model_overrides[session_key] = _codex_override()
+
+    await runner._run_background_task("say hello", source, "bg_test")
+
+    assert _CapturingAgent.last_init is not None
+    assert _CapturingAgent.last_init["model"] == "gpt-5.4"
+    assert _CapturingAgent.last_init["provider"] == "openai-codex"
+    assert _CapturingAgent.last_init["api_mode"] == "codex_responses"
+    assert _CapturingAgent.last_init["base_url"] == "https://chatgpt.com/backend-api/codex"
+    assert _CapturingAgent.last_init["api_key"] == "***"

tests/gateway/test_session_race_guard.py

@@ -41,6 +41,15 @@ def _make_runner():
     runner._pending_approvals = {}
     runner._voice_mode = {}
     runner._background_tasks = set()
+    runner._draining = False
+    runner._restart_requested = False
+    runner._restart_task_started = False
+    runner._restart_detached = False
+    runner._restart_via_service = False
+    runner._restart_drain_timeout = 0.0
+    runner._stop_task = None
+    runner._exit_code = None
+    runner._update_runtime_status = MagicMock()
     runner._is_user_authorized = lambda _source: True
     runner.hooks = MagicMock()
     runner.hooks.emit = AsyncMock()

tests/gateway/test_weixin.py

@@ -62,15 +62,15 @@ class TestWeixinFormatting:
 
 
 class TestWeixinChunking:
-    def test_split_text_sends_top_level_newlines_as_separate_messages(self):
+    def test_split_text_keeps_short_multiline_message_in_single_chunk(self):
         adapter = _make_adapter()
 
         content = adapter.format_message("第一行\n第二行\n第三行")
         chunks = adapter._split_text(content)
 
-        assert chunks == ["第一行", "第二行", "第三行"]
+        assert chunks == ["第一行\n第二行\n第三行"]
 
-    def test_split_text_keeps_indented_followup_with_previous_line(self):
+    def test_split_text_keeps_short_reformatted_table_in_single_chunk(self):
         adapter = _make_adapter()
 
         content = adapter.format_message(
@@ -81,10 +81,7 @@ class TestWeixinChunking:
         )
         chunks = adapter._split_text(content)
 
-        assert chunks == [
-            "- Setting: Timeout\n  Value: 30s",
-            "- Setting: Retries\n  Value: 3",
-        ]
+        assert chunks == [content]
 
     def test_split_text_keeps_complete_code_block_together_when_possible(self):
         adapter = _make_adapter()
@@ -114,6 +111,23 @@ class TestWeixinChunking:
         assert all(len(chunk) <= adapter.MAX_MESSAGE_LENGTH for chunk in chunks)
         assert all(chunk.count("```") >= 2 for chunk in chunks)
 
+    def test_split_text_can_restore_legacy_multiline_splitting_via_config(self):
+        adapter = WeixinAdapter(
+            PlatformConfig(
+                enabled=True,
+                extra={
+                    "account_id": "acct",
+                    "token": "***",
+                    "split_multiline_messages": True,
+                },
+            )
+        )
+
+        content = adapter.format_message("第一行\n第二行\n第三行")
+        chunks = adapter._split_text(content)
+
+        assert chunks == ["第一行", "第二行", "第三行"]
+
 
 class TestWeixinConfig:
     def test_apply_env_overrides_configures_weixin(self):
@@ -127,6 +141,7 @@ class TestWeixinConfig:
                 "WEIXIN_BASE_URL": "https://ilink.example.com/",
                 "WEIXIN_CDN_BASE_URL": "https://cdn.example.com/c2c/",
                 "WEIXIN_DM_POLICY": "allowlist",
+                "WEIXIN_SPLIT_MULTILINE_MESSAGES": "true",
                 "WEIXIN_ALLOWED_USERS": "wxid_1,wxid_2",
                 "WEIXIN_HOME_CHANNEL": "wxid_1",
                 "WEIXIN_HOME_CHANNEL_NAME": "Primary DM",
@@ -142,6 +157,7 @@ class TestWeixinConfig:
         assert platform_config.extra["base_url"] == "https://ilink.example.com"
         assert platform_config.extra["cdn_base_url"] == "https://cdn.example.com/c2c"
         assert platform_config.extra["dm_policy"] == "allowlist"
+        assert platform_config.extra["split_multiline_messages"] == "true"
         assert platform_config.extra["allow_from"] == "wxid_1,wxid_2"
         assert platform_config.home_channel == HomeChannel(Platform.WEIXIN, "wxid_1", "Primary DM")
 

tests/hermes_cli/test_claw.py

@@ -289,12 +289,16 @@ class TestCmdMigrate:
             skill_conflict="skip", yes=False,
         )
 
+        mock_stdin = MagicMock()
+        mock_stdin.isatty.return_value = True
+
         with (
             patch.object(claw_mod, "_find_migration_script", return_value=tmp_path / "s.py"),
             patch.object(claw_mod, "_load_migration_module", return_value=fake_mod),
             patch.object(claw_mod, "get_config_path", return_value=config_path),
             patch.object(claw_mod, "prompt_yes_no", return_value=True),
             patch.object(claw_mod, "_offer_source_archival"),
+            patch("sys.stdin", mock_stdin),
         ):
             claw_mod._cmd_migrate(args)
 
@@ -377,6 +381,16 @@ class TestCmdMigrate:
         config_path = tmp_path / "config.yaml"
         config_path.write_text("")
 
+        # Preview must succeed before the confirmation prompt is shown
+        fake_mod = ModuleType("openclaw_to_hermes")
+        fake_mod.resolve_selected_options = MagicMock(return_value=set())
+        fake_migrator = MagicMock()
+        fake_migrator.migrate.return_value = {
+            "summary": {"migrated": 1, "skipped": 0, "conflict": 0, "error": 0},
+            "items": [{"kind": "soul", "status": "migrated", "source": "s", "destination": "d", "reason": ""}],
+        }
+        fake_mod.Migrator = MagicMock(return_value=fake_migrator)
+
         args = Namespace(
             source=str(openclaw_dir),
             dry_run=False, preset="full", overwrite=False,
@@ -384,9 +398,15 @@ class TestCmdMigrate:
             skill_conflict="skip", yes=False,
         )
 
+        mock_stdin = MagicMock()
+        mock_stdin.isatty.return_value = True
+
         with (
             patch.object(claw_mod, "_find_migration_script", return_value=tmp_path / "s.py"),
+            patch.object(claw_mod, "_load_migration_module", return_value=fake_mod),
+            patch.object(claw_mod, "get_config_path", return_value=config_path),
             patch.object(claw_mod, "prompt_yes_no", return_value=False),
+            patch("sys.stdin", mock_stdin),
         ):
             claw_mod._cmd_migrate(args)
 
@@ -448,7 +468,7 @@ class TestCmdMigrate:
             claw_mod._cmd_migrate(args)
 
         captured = capsys.readouterr()
-        assert "Migration failed" in captured.out
+        assert "Could not load migration script" in captured.out
 
     def test_full_preset_enables_secrets(self, tmp_path, capsys):
         """The 'full' preset should set migrate_secrets=True automatically."""
@@ -511,7 +531,13 @@ class TestOfferSourceArchival:
         source = tmp_path / ".openclaw"
         source.mkdir()
 
-        with patch.object(claw_mod, "prompt_yes_no", return_value=False):
+        mock_stdin = MagicMock()
+        mock_stdin.isatty.return_value = True
+
+        with (
+            patch.object(claw_mod, "prompt_yes_no", return_value=False),
+            patch("sys.stdin", mock_stdin),
+        ):
             claw_mod._offer_source_archival(source, auto_yes=False)
 
         captured = capsys.readouterr()
@@ -597,10 +623,14 @@ class TestCmdCleanup:
         openclaw = tmp_path / ".openclaw"
         openclaw.mkdir()
 
+        mock_stdin = MagicMock()
+        mock_stdin.isatty.return_value = True
+
         args = Namespace(source=None, dry_run=False, yes=False)
         with (
             patch.object(claw_mod, "_find_openclaw_dirs", return_value=[openclaw]),
             patch.object(claw_mod, "prompt_yes_no", return_value=False),
+            patch("sys.stdin", mock_stdin),
         ):
             claw_mod._cmd_cleanup(args)
 

tests/hermes_cli/test_clear_stale_base_url.py

@@ -0,0 +1,75 @@
+"""Tests for _clear_stale_openai_base_url() cleanup after provider switch (#5161)."""
+
+from __future__ import annotations
+
+from unittest.mock import patch
+
+from hermes_cli.config import load_config, save_config, save_env_value, get_env_value
+
+
+def _write_provider(provider: str, model: str = "test-model"):
+    """Helper: write a provider + model to config.yaml."""
+    cfg = load_config()
+    model_cfg = cfg.get("model", {})
+    if not isinstance(model_cfg, dict):
+        model_cfg = {}
+    model_cfg["provider"] = provider
+    model_cfg["default"] = model
+    cfg["model"] = model_cfg
+    save_config(cfg)
+
+
+class TestClearStaleOpenaiBaseUrl:
+    """_clear_stale_openai_base_url() removes OPENAI_BASE_URL when provider is not custom."""
+
+    def test_clears_when_provider_is_named(self, monkeypatch):
+        """OPENAI_BASE_URL is cleared when config provider is a named provider."""
+        from hermes_cli.main import _clear_stale_openai_base_url
+
+        _write_provider("openrouter")
+        save_env_value("OPENAI_BASE_URL", "http://localhost:11434/v1")
+
+        _clear_stale_openai_base_url()
+
+        result = get_env_value("OPENAI_BASE_URL")
+        assert not result, f"Expected OPENAI_BASE_URL to be cleared, got: {result!r}"
+
+    def test_preserves_when_provider_is_custom(self, monkeypatch):
+        """OPENAI_BASE_URL is NOT cleared when config provider is 'custom'."""
+        from hermes_cli.main import _clear_stale_openai_base_url
+
+        _write_provider("custom")
+        save_env_value("OPENAI_BASE_URL", "http://localhost:11434/v1")
+
+        _clear_stale_openai_base_url()
+
+        result = get_env_value("OPENAI_BASE_URL")
+        assert result == "http://localhost:11434/v1", \
+            f"Expected OPENAI_BASE_URL to be preserved, got: {result!r}"
+
+    def test_noop_when_no_openai_base_url(self, monkeypatch):
+        """No error when OPENAI_BASE_URL is not set."""
+        from hermes_cli.main import _clear_stale_openai_base_url
+
+        _write_provider("openrouter")
+        # Ensure it's not set
+        save_env_value("OPENAI_BASE_URL", "")
+        monkeypatch.delenv("OPENAI_BASE_URL", raising=False)
+
+        # Should not raise
+        _clear_stale_openai_base_url()
+
+    def test_noop_when_provider_empty(self, monkeypatch):
+        """No cleanup when provider is not set in config."""
+        from hermes_cli.main import _clear_stale_openai_base_url
+
+        cfg = load_config()
+        cfg.pop("model", None)
+        save_config(cfg)
+        save_env_value("OPENAI_BASE_URL", "http://localhost:11434/v1")
+
+        _clear_stale_openai_base_url()
+
+        result = get_env_value("OPENAI_BASE_URL")
+        assert result == "http://localhost:11434/v1", \
+            "Should not clear when provider is not configured"

tests/hermes_cli/test_gateway_service.py

@@ -5,6 +5,10 @@ from pathlib import Path
 from types import SimpleNamespace
 
 import hermes_cli.gateway as gateway_cli
+from gateway.restart import (
+    DEFAULT_GATEWAY_RESTART_DRAIN_TIMEOUT,
+    GATEWAY_SERVICE_RESTART_EXIT_CODE,
+)
 
 
 class TestSystemdServiceRefresh:
@@ -74,7 +78,7 @@ class TestSystemdServiceRefresh:
         assert unit_path.read_text(encoding="utf-8") == "new unit\n"
         assert calls[:2] == [
             ["systemctl", "--user", "daemon-reload"],
-            ["systemctl", "--user", "restart", gateway_cli.get_service_name()],
+            ["systemctl", "--user", "reload-or-restart", gateway_cli.get_service_name()],
         ]
 
 
@@ -84,6 +88,8 @@ class TestGeneratedSystemdUnits:
 
         assert "ExecStart=" in unit
         assert "ExecStop=" not in unit
+        assert "ExecReload=/bin/kill -USR1 $MAINPID" in unit
+        assert f"RestartForceExitStatus={GATEWAY_SERVICE_RESTART_EXIT_CODE}" in unit
         assert "TimeoutStopSec=60" in unit
 
     def test_user_unit_includes_resolved_node_directory_in_path(self, monkeypatch):
@@ -98,6 +104,8 @@ class TestGeneratedSystemdUnits:
 
         assert "ExecStart=" in unit
         assert "ExecStop=" not in unit
+        assert "ExecReload=/bin/kill -USR1 $MAINPID" in unit
+        assert f"RestartForceExitStatus={GATEWAY_SERVICE_RESTART_EXIT_CODE}" in unit
         assert "TimeoutStopSec=60" in unit
         assert "WantedBy=multi-user.target" in unit
 
@@ -157,6 +165,31 @@ class TestGatewayStopCleanup:
 
 
 class TestLaunchdServiceRecovery:
+    def test_get_restart_drain_timeout_prefers_env_then_config_then_default(self, monkeypatch):
+        monkeypatch.delenv("HERMES_RESTART_DRAIN_TIMEOUT", raising=False)
+        monkeypatch.setattr(gateway_cli, "read_raw_config", lambda: {})
+
+        assert (
+            gateway_cli._get_restart_drain_timeout()
+            == DEFAULT_GATEWAY_RESTART_DRAIN_TIMEOUT
+        )
+
+        monkeypatch.setattr(
+            gateway_cli,
+            "read_raw_config",
+            lambda: {"agent": {"restart_drain_timeout": 14}},
+        )
+        assert gateway_cli._get_restart_drain_timeout() == 14.0
+
+        monkeypatch.setenv("HERMES_RESTART_DRAIN_TIMEOUT", "9")
+        assert gateway_cli._get_restart_drain_timeout() == 9.0
+
+        monkeypatch.setenv("HERMES_RESTART_DRAIN_TIMEOUT", "invalid")
+        assert (
+            gateway_cli._get_restart_drain_timeout()
+            == DEFAULT_GATEWAY_RESTART_DRAIN_TIMEOUT
+        )
+
     def test_launchd_install_repairs_outdated_plist_without_force(self, tmp_path, monkeypatch):
         plist_path = tmp_path / "ai.hermes.gateway.plist"
         plist_path.write_text("<plist>old content</plist>", encoding="utf-8")
@@ -234,6 +267,55 @@ class TestLaunchdServiceRecovery:
             ["launchctl", "kickstart", target],
         ]
 
+    def test_launchd_restart_drains_running_gateway_before_kickstart(self, monkeypatch):
+        calls = []
+        target = f"{gateway_cli._launchd_domain()}/{gateway_cli.get_launchd_label()}"
+
+        monkeypatch.setattr(gateway_cli, "_get_restart_drain_timeout", lambda: 12.0)
+        monkeypatch.setattr(gateway_cli, "_request_gateway_self_restart", lambda pid: False)
+        monkeypatch.setattr(gateway_cli, "_wait_for_gateway_exit", lambda timeout, force_after=None: True)
+        monkeypatch.setattr(gateway_cli, "terminate_pid", lambda pid, force=False: calls.append(("term", pid, force)))
+        monkeypatch.setattr(
+            "gateway.status.get_running_pid",
+            lambda: 321,
+        )
+
+        def fake_run(cmd, check=False, **kwargs):
+            calls.append(cmd)
+            return SimpleNamespace(returncode=0, stdout="", stderr="")
+
+        monkeypatch.setattr(gateway_cli.subprocess, "run", fake_run)
+
+        gateway_cli.launchd_restart()
+
+        assert calls == [
+            ("term", 321, False),
+            ["launchctl", "kickstart", "-k", target],
+        ]
+
+    def test_launchd_restart_self_requests_graceful_restart_without_kickstart(self, monkeypatch, capsys):
+        calls = []
+
+        monkeypatch.setattr(
+            "gateway.status.get_running_pid",
+            lambda: 321,
+        )
+        monkeypatch.setattr(
+            gateway_cli,
+            "_request_gateway_self_restart",
+            lambda pid: calls.append(("self", pid)) or True,
+        )
+        monkeypatch.setattr(
+            gateway_cli.subprocess,
+            "run",
+            lambda *args, **kwargs: (_ for _ in ()).throw(AssertionError("launchctl should not run")),
+        )
+
+        gateway_cli.launchd_restart()
+
+        assert calls == [("self", 321)]
+        assert "restart requested" in capsys.readouterr().out.lower()
+
     def test_launchd_stop_uses_bootout_not_kill(self, monkeypatch):
         """launchd_stop must bootout the service so KeepAlive doesn't respawn it."""
         label = gateway_cli.get_launchd_label()
@@ -337,6 +419,31 @@ class TestGatewayServiceDetection:
 
 
 class TestGatewaySystemServiceRouting:
+    def test_systemd_restart_self_requests_graceful_restart_without_reload_or_restart(self, monkeypatch, capsys):
+        calls = []
+
+        monkeypatch.setattr(gateway_cli, "_select_systemd_scope", lambda system=False: False)
+        monkeypatch.setattr(gateway_cli, "refresh_systemd_unit_if_needed", lambda system=False: calls.append(("refresh", system)))
+        monkeypatch.setattr(
+            "gateway.status.get_running_pid",
+            lambda: 654,
+        )
+        monkeypatch.setattr(
+            gateway_cli,
+            "_request_gateway_self_restart",
+            lambda pid: calls.append(("self", pid)) or True,
+        )
+        monkeypatch.setattr(
+            gateway_cli.subprocess,
+            "run",
+            lambda *args, **kwargs: (_ for _ in ()).throw(AssertionError("systemctl should not run")),
+        )
+
+        gateway_cli.systemd_restart()
+
+        assert calls == [("refresh", False), ("self", 654)]
+        assert "restart requested" in capsys.readouterr().out.lower()
+
     def test_gateway_install_passes_system_flags(self, monkeypatch):
         monkeypatch.setattr(gateway_cli, "supports_systemd_services", lambda: True)
         monkeypatch.setattr(gateway_cli, "is_termux", lambda: False)

tests/hermes_cli/test_gateway_wsl.py

@@ -0,0 +1,279 @@
+"""Tests for WSL detection and WSL-aware gateway behavior."""
+
+import io
+import subprocess
+import sys
+from types import SimpleNamespace
+from unittest.mock import patch, MagicMock, mock_open
+
+import pytest
+
+import hermes_cli.gateway as gateway
+import hermes_constants
+
+
+# =============================================================================
+# is_wsl() in hermes_constants
+# =============================================================================
+
+class TestIsWsl:
+    """Test the shared is_wsl() utility."""
+
+    def setup_method(self):
+        # Reset cached value between tests
+        hermes_constants._wsl_detected = None
+
+    def test_detects_wsl2(self):
+        fake_content = (
+            "Linux version 5.15.146.1-microsoft-standard-WSL2 "
+            "(gcc (GCC) 11.2.0) #1 SMP Thu Jan 11 04:09:03 UTC 2024\n"
+        )
+        with patch("builtins.open", mock_open(read_data=fake_content)):
+            assert hermes_constants.is_wsl() is True
+
+    def test_detects_wsl1(self):
+        fake_content = (
+            "Linux version 4.4.0-19041-Microsoft "
+            "(Microsoft@Microsoft.com) (gcc version 5.4.0) #1\n"
+        )
+        with patch("builtins.open", mock_open(read_data=fake_content)):
+            assert hermes_constants.is_wsl() is True
+
+    def test_native_linux(self):
+        fake_content = (
+            "Linux version 6.5.0-44-generic (buildd@lcy02-amd64-015) "
+            "(x86_64-linux-gnu-gcc-12 (Ubuntu 12.3.0-1ubuntu1~22.04) 12.3.0) #44\n"
+        )
+        with patch("builtins.open", mock_open(read_data=fake_content)):
+            assert hermes_constants.is_wsl() is False
+
+    def test_no_proc_version(self):
+        with patch("builtins.open", side_effect=FileNotFoundError):
+            assert hermes_constants.is_wsl() is False
+
+    def test_result_is_cached(self):
+        """After first detection, subsequent calls return the cached value."""
+        hermes_constants._wsl_detected = True
+        # Even with open raising, cached value is returned
+        with patch("builtins.open", side_effect=FileNotFoundError):
+            assert hermes_constants.is_wsl() is True
+
+
+# =============================================================================
+# _wsl_systemd_operational() in gateway
+# =============================================================================
+
+class TestWslSystemdOperational:
+    """Test the WSL systemd check."""
+
+    def test_running(self, monkeypatch):
+        monkeypatch.setattr(
+            gateway.subprocess, "run",
+            lambda *a, **kw: SimpleNamespace(
+                returncode=0, stdout="running\n", stderr=""
+            ),
+        )
+        assert gateway._wsl_systemd_operational() is True
+
+    def test_degraded(self, monkeypatch):
+        monkeypatch.setattr(
+            gateway.subprocess, "run",
+            lambda *a, **kw: SimpleNamespace(
+                returncode=1, stdout="degraded\n", stderr=""
+            ),
+        )
+        assert gateway._wsl_systemd_operational() is True
+
+    def test_starting(self, monkeypatch):
+        monkeypatch.setattr(
+            gateway.subprocess, "run",
+            lambda *a, **kw: SimpleNamespace(
+                returncode=1, stdout="starting\n", stderr=""
+            ),
+        )
+        assert gateway._wsl_systemd_operational() is True
+
+    def test_offline_no_systemd(self, monkeypatch):
+        monkeypatch.setattr(
+            gateway.subprocess, "run",
+            lambda *a, **kw: SimpleNamespace(
+                returncode=1, stdout="offline\n", stderr=""
+            ),
+        )
+        assert gateway._wsl_systemd_operational() is False
+
+    def test_systemctl_not_found(self, monkeypatch):
+        monkeypatch.setattr(
+            gateway.subprocess, "run",
+            MagicMock(side_effect=FileNotFoundError),
+        )
+        assert gateway._wsl_systemd_operational() is False
+
+    def test_timeout(self, monkeypatch):
+        monkeypatch.setattr(
+            gateway.subprocess, "run",
+            MagicMock(side_effect=subprocess.TimeoutExpired("systemctl", 5)),
+        )
+        assert gateway._wsl_systemd_operational() is False
+
+
+# =============================================================================
+# supports_systemd_services() WSL integration
+# =============================================================================
+
+class TestSupportsSystemdServicesWSL:
+    """Test that supports_systemd_services() handles WSL correctly."""
+
+    def test_wsl_with_systemd(self, monkeypatch):
+        """WSL + working systemd → True."""
+        monkeypatch.setattr(gateway, "is_linux", lambda: True)
+        monkeypatch.setattr(gateway, "is_termux", lambda: False)
+        monkeypatch.setattr(gateway, "is_wsl", lambda: True)
+        monkeypatch.setattr(gateway, "_wsl_systemd_operational", lambda: True)
+        assert gateway.supports_systemd_services() is True
+
+    def test_wsl_without_systemd(self, monkeypatch):
+        """WSL + no systemd → False."""
+        monkeypatch.setattr(gateway, "is_linux", lambda: True)
+        monkeypatch.setattr(gateway, "is_termux", lambda: False)
+        monkeypatch.setattr(gateway, "is_wsl", lambda: True)
+        monkeypatch.setattr(gateway, "_wsl_systemd_operational", lambda: False)
+        assert gateway.supports_systemd_services() is False
+
+    def test_native_linux(self, monkeypatch):
+        """Native Linux (not WSL) → True without checking systemd."""
+        monkeypatch.setattr(gateway, "is_linux", lambda: True)
+        monkeypatch.setattr(gateway, "is_termux", lambda: False)
+        monkeypatch.setattr(gateway, "is_wsl", lambda: False)
+        assert gateway.supports_systemd_services() is True
+
+    def test_termux_still_excluded(self, monkeypatch):
+        """Termux → False regardless of WSL status."""
+        monkeypatch.setattr(gateway, "is_linux", lambda: True)
+        monkeypatch.setattr(gateway, "is_termux", lambda: True)
+        assert gateway.supports_systemd_services() is False
+
+
+# =============================================================================
+# WSL messaging in gateway commands
+# =============================================================================
+
+class TestGatewayCommandWSLMessages:
+    """Test that WSL users see appropriate guidance."""
+
+    def test_install_wsl_no_systemd(self, monkeypatch, capsys):
+        """hermes gateway install on WSL without systemd shows guidance."""
+        monkeypatch.setattr(gateway, "is_linux", lambda: True)
+        monkeypatch.setattr(gateway, "is_termux", lambda: False)
+        monkeypatch.setattr(gateway, "is_wsl", lambda: True)
+        monkeypatch.setattr(gateway, "supports_systemd_services", lambda: False)
+        monkeypatch.setattr(gateway, "is_macos", lambda: False)
+        monkeypatch.setattr(gateway, "is_managed", lambda: False)
+
+        args = SimpleNamespace(
+            gateway_command="install", force=False, system=False,
+            run_as_user=None,
+        )
+        with pytest.raises(SystemExit) as exc_info:
+            gateway.gateway_command(args)
+        assert exc_info.value.code == 1
+
+        out = capsys.readouterr().out
+        assert "WSL detected" in out
+        assert "systemd is not running" in out
+        assert "hermes gateway run" in out
+        assert "tmux" in out
+
+    def test_start_wsl_no_systemd(self, monkeypatch, capsys):
+        """hermes gateway start on WSL without systemd shows guidance."""
+        monkeypatch.setattr(gateway, "is_linux", lambda: True)
+        monkeypatch.setattr(gateway, "is_termux", lambda: False)
+        monkeypatch.setattr(gateway, "is_wsl", lambda: True)
+        monkeypatch.setattr(gateway, "supports_systemd_services", lambda: False)
+        monkeypatch.setattr(gateway, "is_macos", lambda: False)
+
+        args = SimpleNamespace(gateway_command="start", system=False)
+        with pytest.raises(SystemExit) as exc_info:
+            gateway.gateway_command(args)
+        assert exc_info.value.code == 1
+
+        out = capsys.readouterr().out
+        assert "WSL detected" in out
+        assert "hermes gateway run" in out
+        assert "wsl.conf" in out
+
+    def test_install_wsl_with_systemd_warns(self, monkeypatch, capsys):
+        """hermes gateway install on WSL with systemd shows warning but proceeds."""
+        monkeypatch.setattr(gateway, "is_linux", lambda: True)
+        monkeypatch.setattr(gateway, "is_termux", lambda: False)
+        monkeypatch.setattr(gateway, "is_wsl", lambda: True)
+        monkeypatch.setattr(gateway, "supports_systemd_services", lambda: True)
+        monkeypatch.setattr(gateway, "is_macos", lambda: False)
+        monkeypatch.setattr(gateway, "is_managed", lambda: False)
+
+        # Mock systemd_install to capture call
+        install_called = []
+        monkeypatch.setattr(
+            gateway, "systemd_install",
+            lambda **kwargs: install_called.append(kwargs),
+        )
+
+        args = SimpleNamespace(
+            gateway_command="install", force=False, system=False,
+            run_as_user=None,
+        )
+        gateway.gateway_command(args)
+
+        out = capsys.readouterr().out
+        assert "WSL detected" in out
+        assert "may not survive WSL restarts" in out
+        assert len(install_called) == 1  # install still proceeded
+
+    def test_status_wsl_running_manual(self, monkeypatch, capsys):
+        """hermes gateway status on WSL with manual process shows WSL note."""
+        monkeypatch.setattr(gateway, "supports_systemd_services", lambda: False)
+        monkeypatch.setattr(gateway, "is_macos", lambda: False)
+        monkeypatch.setattr(gateway, "is_termux", lambda: False)
+        monkeypatch.setattr(gateway, "is_wsl", lambda: True)
+        monkeypatch.setattr(gateway, "find_gateway_pids", lambda: [12345])
+        monkeypatch.setattr(gateway, "_runtime_health_lines", lambda: [])
+        # Stub out the systemd unit path check
+        monkeypatch.setattr(
+            gateway, "get_systemd_unit_path",
+            lambda system=False: SimpleNamespace(exists=lambda: False),
+        )
+        monkeypatch.setattr(
+            gateway, "get_launchd_plist_path",
+            lambda: SimpleNamespace(exists=lambda: False),
+        )
+
+        args = SimpleNamespace(gateway_command="status", deep=False, system=False)
+        gateway.gateway_command(args)
+
+        out = capsys.readouterr().out
+        assert "WSL note" in out
+        assert "tmux or screen" in out
+
+    def test_status_wsl_not_running(self, monkeypatch, capsys):
+        """hermes gateway status on WSL with no process shows WSL start advice."""
+        monkeypatch.setattr(gateway, "supports_systemd_services", lambda: False)
+        monkeypatch.setattr(gateway, "is_macos", lambda: False)
+        monkeypatch.setattr(gateway, "is_termux", lambda: False)
+        monkeypatch.setattr(gateway, "is_wsl", lambda: True)
+        monkeypatch.setattr(gateway, "find_gateway_pids", lambda: [])
+        monkeypatch.setattr(gateway, "_runtime_health_lines", lambda: [])
+        monkeypatch.setattr(
+            gateway, "get_systemd_unit_path",
+            lambda system=False: SimpleNamespace(exists=lambda: False),
+        )
+        monkeypatch.setattr(
+            gateway, "get_launchd_plist_path",
+            lambda: SimpleNamespace(exists=lambda: False),
+        )
+
+        args = SimpleNamespace(gateway_command="status", deep=False, system=False)
+        gateway.gateway_command(args)
+
+        out = capsys.readouterr().out
+        assert "hermes gateway run" in out
+        assert "tmux" in out

tests/hermes_cli/test_plugins_cmd.py

@@ -555,3 +555,103 @@ class TestPromptPluginEnvVars:
 
         # Should not crash, and not save anything
         mock_save.assert_not_called()
+
+
+# ── curses_radiolist ─────────────────────────────────────────────────────
+
+
+class TestCursesRadiolist:
+    """Test the curses_radiolist function (non-TTY fallback path)."""
+
+    def test_non_tty_returns_default(self):
+        from hermes_cli.curses_ui import curses_radiolist
+        with patch("sys.stdin") as mock_stdin:
+            mock_stdin.isatty.return_value = False
+            result = curses_radiolist("Pick one", ["a", "b", "c"], selected=1)
+            assert result == 1
+
+    def test_non_tty_returns_cancel_value(self):
+        from hermes_cli.curses_ui import curses_radiolist
+        with patch("sys.stdin") as mock_stdin:
+            mock_stdin.isatty.return_value = False
+            result = curses_radiolist("Pick", ["x", "y"], selected=0, cancel_returns=1)
+            assert result == 1
+
+
+# ── Provider discovery helpers ───────────────────────────────────────────
+
+
+class TestProviderDiscovery:
+    """Test provider plugin discovery and config helpers."""
+
+    def test_get_current_memory_provider_default(self, tmp_path, monkeypatch):
+        """Empty config returns empty string."""
+        monkeypatch.setenv("HERMES_HOME", str(tmp_path))
+        config_file = tmp_path / "config.yaml"
+        config_file.write_text("memory:\n  provider: ''\n")
+        from hermes_cli.plugins_cmd import _get_current_memory_provider
+        result = _get_current_memory_provider()
+        assert result == ""
+
+    def test_get_current_context_engine_default(self, tmp_path, monkeypatch):
+        """Default config returns 'compressor'."""
+        monkeypatch.setenv("HERMES_HOME", str(tmp_path))
+        config_file = tmp_path / "config.yaml"
+        config_file.write_text("context:\n  engine: compressor\n")
+        from hermes_cli.plugins_cmd import _get_current_context_engine
+        result = _get_current_context_engine()
+        assert result == "compressor"
+
+    def test_save_memory_provider(self, tmp_path, monkeypatch):
+        """Saving a memory provider persists to config.yaml."""
+        monkeypatch.setenv("HERMES_HOME", str(tmp_path))
+        config_file = tmp_path / "config.yaml"
+        config_file.write_text("memory:\n  provider: ''\n")
+        from hermes_cli.plugins_cmd import _save_memory_provider
+        _save_memory_provider("honcho")
+        content = yaml.safe_load(config_file.read_text())
+        assert content["memory"]["provider"] == "honcho"
+
+    def test_save_context_engine(self, tmp_path, monkeypatch):
+        """Saving a context engine persists to config.yaml."""
+        monkeypatch.setenv("HERMES_HOME", str(tmp_path))
+        config_file = tmp_path / "config.yaml"
+        config_file.write_text("context:\n  engine: compressor\n")
+        from hermes_cli.plugins_cmd import _save_context_engine
+        _save_context_engine("lcm")
+        content = yaml.safe_load(config_file.read_text())
+        assert content["context"]["engine"] == "lcm"
+
+    def test_discover_memory_providers_empty(self):
+        """Discovery returns empty list when import fails."""
+        with patch("plugins.memory.discover_memory_providers",
+                    side_effect=ImportError("no module")):
+            from hermes_cli.plugins_cmd import _discover_memory_providers
+            result = _discover_memory_providers()
+            assert result == []
+
+    def test_discover_context_engines_empty(self):
+        """Discovery returns empty list when import fails."""
+        with patch("plugins.context_engine.discover_context_engines",
+                    side_effect=ImportError("no module")):
+            from hermes_cli.plugins_cmd import _discover_context_engines
+            result = _discover_context_engines()
+            assert result == []
+
+
+# ── Auto-activation fix ──────────────────────────────────────────────────
+
+
+class TestNoAutoActivation:
+    """Verify that plugin engines don't auto-activate when config says 'compressor'."""
+
+    def test_compressor_default_ignores_plugin(self):
+        """When context.engine is 'compressor', a plugin-registered engine should NOT
+        be used — only explicit config triggers plugin engines."""
+        # This tests the run_agent.py logic indirectly by checking that the
+        # code path for default config doesn't call get_plugin_context_engine.
+        import run_agent as ra_module
+        source = open(ra_module.__file__).read()
+        # The old code had: "Even with default config, check if a plugin registered one"
+        # The fix removes this. Verify it's gone.
+        assert "Even with default config, check if a plugin registered one" not in source

tests/hermes_cli/test_setup.py

@@ -4,6 +4,8 @@ import json
 import sys
 import types
 
+import pytest
+
 from hermes_cli.auth import get_active_provider
 from hermes_cli.config import load_config, save_config
 from hermes_cli.setup import setup_model_provider
@@ -362,3 +364,52 @@ def test_modal_setup_persists_direct_mode_when_user_chooses_their_own_account(tm
 
     assert config["terminal"]["backend"] == "modal"
     assert config["terminal"]["modal_mode"] == "direct"
+
+
+def test_resolve_hermes_chat_argv_prefers_which(monkeypatch):
+    from hermes_cli import setup as setup_mod
+
+    monkeypatch.setattr(setup_mod.shutil, "which", lambda name: "/usr/local/bin/hermes" if name == "hermes" else None)
+
+    assert setup_mod._resolve_hermes_chat_argv() == ["/usr/local/bin/hermes", "chat"]
+
+
+def test_resolve_hermes_chat_argv_falls_back_to_module(monkeypatch):
+    from hermes_cli import setup as setup_mod
+
+    monkeypatch.setattr(setup_mod.shutil, "which", lambda _name: None)
+    monkeypatch.setattr(setup_mod.importlib.util, "find_spec", lambda name: object() if name == "hermes_cli" else None)
+
+    assert setup_mod._resolve_hermes_chat_argv() == [sys.executable, "-m", "hermes_cli.main", "chat"]
+
+
+def test_offer_launch_chat_execs_fresh_process(monkeypatch):
+    from hermes_cli import setup as setup_mod
+
+    monkeypatch.setattr(setup_mod, "prompt_yes_no", lambda *_args, **_kwargs: True)
+    monkeypatch.setattr(setup_mod, "_resolve_hermes_chat_argv", lambda: ["/usr/local/bin/hermes", "chat"])
+
+    exec_calls = []
+
+    def fake_execvp(path, argv):
+        exec_calls.append((path, argv))
+        raise SystemExit(0)
+
+    monkeypatch.setattr(setup_mod.os, "execvp", fake_execvp)
+
+    with pytest.raises(SystemExit):
+        setup_mod._offer_launch_chat()
+
+    assert exec_calls == [("/usr/local/bin/hermes", ["/usr/local/bin/hermes", "chat"])]
+
+
+def test_offer_launch_chat_manual_fallback_when_unresolvable(monkeypatch, capsys):
+    from hermes_cli import setup as setup_mod
+
+    monkeypatch.setattr(setup_mod, "prompt_yes_no", lambda *_args, **_kwargs: True)
+    monkeypatch.setattr(setup_mod, "_resolve_hermes_chat_argv", lambda: None)
+
+    setup_mod._offer_launch_chat()
+
+    captured = capsys.readouterr()
+    assert "Run 'hermes chat' manually" in captured.out

tests/hermes_cli/test_setup_matrix_e2ee.py

@@ -22,7 +22,7 @@ def _parse_setup_imports():
 class TestSetupShutilImport:
     def test_shutil_imported_at_module_level(self):
         """shutil must be imported at module level so setup_gateway can use it
-        for the matrix-nio auto-install path (line ~2126)."""
+        for the mautrix auto-install path."""
         names = _parse_setup_imports()
         assert "shutil" in names, (
             "shutil is not imported at the top of hermes_cli/setup.py. "

tests/hermes_cli/test_tools_config.py

@@ -428,3 +428,31 @@ class TestPlatformToolsetConsistency:
                 f"Platform {platform!r} in tools_config but missing from "
                 f"skills_config PLATFORMS"
             )
+
+
+def test_numeric_mcp_server_name_does_not_crash_sorted():
+    """YAML parses bare numeric keys (e.g. ``12306:``) as int.
+
+    _get_platform_tools must normalise them to str so that sorted()
+    on the returned set never raises TypeError on mixed int/str.
+
+    Regression test for https://github.com/NousResearch/hermes-agent/issues/6901
+    """
+    config = {
+        "platform_toolsets": {"cli": ["web", 12306]},
+        "mcp_servers": {
+            12306: {"url": "https://example.com/mcp"},
+            "normal-server": {"url": "https://example.com/mcp2"},
+        },
+    }
+
+    enabled = _get_platform_tools(config, "cli")
+
+    # All names must be str — no int leaking through
+    assert all(isinstance(name, str) for name in enabled), (
+        f"Non-string toolset names found: {enabled}"
+    )
+    assert "12306" in enabled
+
+    # sorted() must not raise TypeError
+    sorted(enabled)

tests/hermes_cli/test_xiaomi_provider.py

@@ -0,0 +1,327 @@
+"""Tests for Xiaomi MiMo provider support."""
+
+import os
+import sys
+import types
+
+import pytest
+
+# Ensure dotenv doesn't interfere
+if "dotenv" not in sys.modules:
+    fake_dotenv = types.ModuleType("dotenv")
+    fake_dotenv.load_dotenv = lambda *args, **kwargs: None
+    sys.modules["dotenv"] = fake_dotenv
+
+from hermes_cli.auth import (
+    PROVIDER_REGISTRY,
+    resolve_provider,
+    get_api_key_provider_status,
+    resolve_api_key_provider_credentials,
+    AuthError,
+)
+
+
+# =============================================================================
+# Provider Registry
+# =============================================================================
+
+
+class TestXiaomiProviderRegistry:
+    """Verify Xiaomi is registered correctly in the PROVIDER_REGISTRY."""
+
+    def test_registered(self):
+        assert "xiaomi" in PROVIDER_REGISTRY
+
+    def test_name(self):
+        assert PROVIDER_REGISTRY["xiaomi"].name == "Xiaomi MiMo"
+
+    def test_auth_type(self):
+        assert PROVIDER_REGISTRY["xiaomi"].auth_type == "api_key"
+
+    def test_inference_base_url(self):
+        assert PROVIDER_REGISTRY["xiaomi"].inference_base_url == "https://api.xiaomimimo.com/v1"
+
+    def test_api_key_env_vars(self):
+        assert PROVIDER_REGISTRY["xiaomi"].api_key_env_vars == ("XIAOMI_API_KEY",)
+
+    def test_base_url_env_var(self):
+        assert PROVIDER_REGISTRY["xiaomi"].base_url_env_var == "XIAOMI_BASE_URL"
+
+
+# =============================================================================
+# Aliases
+# =============================================================================
+
+
+class TestXiaomiAliases:
+    """All aliases should resolve to 'xiaomi'."""
+
+    @pytest.mark.parametrize("alias", [
+        "xiaomi", "mimo", "xiaomi-mimo",
+    ])
+    def test_alias_resolves(self, alias, monkeypatch):
+        # Clear env to avoid auto-detection interfering
+        for key in ("XIAOMI_API_KEY",):
+            monkeypatch.delenv(key, raising=False)
+        monkeypatch.setenv("XIAOMI_API_KEY", "sk-test-key-12345678")
+        assert resolve_provider(alias) == "xiaomi"
+
+    def test_normalize_provider_models_py(self):
+        from hermes_cli.models import normalize_provider
+        assert normalize_provider("mimo") == "xiaomi"
+        assert normalize_provider("xiaomi-mimo") == "xiaomi"
+
+    def test_normalize_provider_providers_py(self):
+        from hermes_cli.providers import normalize_provider
+        assert normalize_provider("mimo") == "xiaomi"
+        assert normalize_provider("xiaomi-mimo") == "xiaomi"
+
+
+# =============================================================================
+# Auto-detection
+# =============================================================================
+
+
+class TestXiaomiAutoDetection:
+    """Setting XIAOMI_API_KEY should auto-detect the provider."""
+
+    def test_auto_detect(self, monkeypatch):
+        # Clear all other provider env vars
+        for var in ("OPENROUTER_API_KEY", "OPENAI_API_KEY", "ANTHROPIC_API_KEY",
+                     "DEEPSEEK_API_KEY", "GOOGLE_API_KEY", "GEMINI_API_KEY",
+                     "DASHSCOPE_API_KEY", "XAI_API_KEY", "KIMI_API_KEY",
+                     "MINIMAX_API_KEY", "AI_GATEWAY_API_KEY", "KILOCODE_API_KEY",
+                     "HF_TOKEN", "GLM_API_KEY", "COPILOT_GITHUB_TOKEN",
+                     "GH_TOKEN", "GITHUB_TOKEN", "MINIMAX_CN_API_KEY"):
+            monkeypatch.delenv(var, raising=False)
+        monkeypatch.setenv("XIAOMI_API_KEY", "sk-xiaomi-test-12345678")
+        provider = resolve_provider("auto")
+        assert provider == "xiaomi"
+
+
+# =============================================================================
+# Credentials
+# =============================================================================
+
+
+class TestXiaomiCredentials:
+    """Test credential resolution for the xiaomi provider."""
+
+    def test_status_configured(self, monkeypatch):
+        monkeypatch.setenv("XIAOMI_API_KEY", "sk-test-12345678")
+        status = get_api_key_provider_status("xiaomi")
+        assert status["configured"]
+
+    def test_status_not_configured(self, monkeypatch):
+        monkeypatch.delenv("XIAOMI_API_KEY", raising=False)
+        status = get_api_key_provider_status("xiaomi")
+        assert not status["configured"]
+
+    def test_resolve_credentials(self, monkeypatch):
+        monkeypatch.setenv("XIAOMI_API_KEY", "sk-test-12345678")
+        monkeypatch.delenv("XIAOMI_BASE_URL", raising=False)
+        creds = resolve_api_key_provider_credentials("xiaomi")
+        assert creds["api_key"] == "sk-test-12345678"
+        assert creds["base_url"] == "https://api.xiaomimimo.com/v1"
+
+    def test_custom_base_url_override(self, monkeypatch):
+        monkeypatch.setenv("XIAOMI_API_KEY", "sk-test-12345678")
+        monkeypatch.setenv("XIAOMI_BASE_URL", "https://custom.xiaomi.example/v1")
+        creds = resolve_api_key_provider_credentials("xiaomi")
+        assert creds["base_url"] == "https://custom.xiaomi.example/v1"
+
+
+# =============================================================================
+# Model catalog (dynamic — no static list)
+# =============================================================================
+
+
+class TestXiaomiModelCatalog:
+    """Xiaomi uses dynamic model discovery via models.dev."""
+
+    def test_models_dev_mapping(self):
+        from agent.models_dev import PROVIDER_TO_MODELS_DEV
+        assert PROVIDER_TO_MODELS_DEV["xiaomi"] == "xiaomi"
+
+    def test_static_model_list_fallback(self):
+        """Static _PROVIDER_MODELS fallback must exist for model picker."""
+        from hermes_cli.models import _PROVIDER_MODELS
+        assert "xiaomi" in _PROVIDER_MODELS
+        models = _PROVIDER_MODELS["xiaomi"]
+        assert "mimo-v2-pro" in models
+        assert "mimo-v2-omni" in models
+        assert "mimo-v2-flash" in models
+
+    def test_list_agentic_models_mock(self, monkeypatch):
+        """When models.dev returns Xiaomi data, list_agentic_models should return models."""
+        from agent import models_dev as md
+
+        fake_data = {
+            "xiaomi": {
+                "name": "Xiaomi",
+                "api": "https://api.xiaomimimo.com/v1",
+                "env": ["XIAOMI_API_KEY"],
+                "models": {
+                    "mimo-v2-pro": {
+                        "limit": {"context": 1000000},
+                        "tool_call": True,
+                    },
+                    "mimo-v2-omni": {
+                        "limit": {"context": 256000},
+                        "tool_call": True,
+                    },
+                    "mimo-v2-flash": {
+                        "limit": {"context": 256000},
+                        "tool_call": True,
+                    },
+                },
+            }
+        }
+        monkeypatch.setattr(md, "fetch_models_dev", lambda: fake_data)
+
+        result = md.list_agentic_models("xiaomi")
+        assert "mimo-v2-pro" in result
+        assert "mimo-v2-flash" in result
+
+
+# =============================================================================
+# Normalization
+# =============================================================================
+
+
+class TestXiaomiNormalization:
+    """Model name normalization — Xiaomi is a direct provider."""
+
+    def test_vendor_prefix_mapping(self):
+        from hermes_cli.model_normalize import _VENDOR_PREFIXES
+        assert _VENDOR_PREFIXES.get("mimo") == "xiaomi"
+
+    def test_matching_prefix_strip(self):
+        """xiaomi/mimo-v2-pro should normalize to mimo-v2-pro for direct API."""
+        from hermes_cli.model_normalize import _MATCHING_PREFIX_STRIP_PROVIDERS
+        assert "xiaomi" in _MATCHING_PREFIX_STRIP_PROVIDERS
+
+    def test_normalize_strips_provider_prefix(self):
+        from hermes_cli.model_normalize import normalize_model_for_provider
+        result = normalize_model_for_provider("xiaomi/mimo-v2-pro", "xiaomi")
+        assert result == "mimo-v2-pro"
+
+    def test_normalize_bare_name_unchanged(self):
+        from hermes_cli.model_normalize import normalize_model_for_provider
+        result = normalize_model_for_provider("mimo-v2-pro", "xiaomi")
+        assert result == "mimo-v2-pro"
+
+
+# =============================================================================
+# URL mapping
+# =============================================================================
+
+
+class TestXiaomiURLMapping:
+    """Test URL → provider inference for Xiaomi endpoints."""
+
+    def test_url_to_provider(self):
+        from agent.model_metadata import _URL_TO_PROVIDER
+        assert _URL_TO_PROVIDER.get("api.xiaomimimo.com") == "xiaomi"
+
+    def test_provider_prefixes(self):
+        from agent.model_metadata import _PROVIDER_PREFIXES
+        assert "xiaomi" in _PROVIDER_PREFIXES
+        assert "mimo" in _PROVIDER_PREFIXES
+        assert "xiaomi-mimo" in _PROVIDER_PREFIXES
+
+    def test_infer_from_url(self):
+        from agent.model_metadata import _infer_provider_from_url
+        assert _infer_provider_from_url("https://api.xiaomimimo.com/v1") == "xiaomi"
+
+    def test_infer_from_regional_urls(self):
+        """Regional token-plan endpoints should also resolve to xiaomi."""
+        from agent.model_metadata import _infer_provider_from_url
+        assert _infer_provider_from_url("https://token-plan-ams.xiaomimimo.com/v1") == "xiaomi"
+        assert _infer_provider_from_url("https://token-plan-cn.xiaomimimo.com/v1") == "xiaomi"
+        assert _infer_provider_from_url("https://token-plan-sgp.xiaomimimo.com/v1") == "xiaomi"
+
+
+# =============================================================================
+# providers.py
+# =============================================================================
+
+
+class TestXiaomiProvidersModule:
+    """Test Xiaomi in the unified providers module."""
+
+    def test_overlay_exists(self):
+        from hermes_cli.providers import HERMES_OVERLAYS
+        assert "xiaomi" in HERMES_OVERLAYS
+        overlay = HERMES_OVERLAYS["xiaomi"]
+        assert overlay.transport == "openai_chat"
+        assert overlay.base_url_env_var == "XIAOMI_BASE_URL"
+        assert not overlay.is_aggregator
+
+    def test_alias_resolves(self):
+        from hermes_cli.providers import normalize_provider
+        assert normalize_provider("mimo") == "xiaomi"
+        assert normalize_provider("xiaomi-mimo") == "xiaomi"
+
+    def test_label(self):
+        from hermes_cli.providers import get_label
+        assert get_label("xiaomi") == "Xiaomi MiMo"
+
+    def test_get_provider(self):
+        pdef = None
+        try:
+            from hermes_cli.providers import get_provider
+            pdef = get_provider("xiaomi")
+        except Exception:
+            pass
+        if pdef is not None:
+            assert pdef.id == "xiaomi"
+            assert pdef.transport == "openai_chat"
+
+
+# =============================================================================
+# Auxiliary client
+# =============================================================================
+
+
+class TestXiaomiAuxiliary:
+    """Xiaomi auxiliary routing: vision → omni, non-vision → user's main model, never flash."""
+
+    def test_no_flash_in_aux_models(self):
+        """mimo-v2-flash must NEVER be used for automatic aux routing."""
+        from agent.auxiliary_client import _API_KEY_PROVIDER_AUX_MODELS
+        assert "xiaomi" not in _API_KEY_PROVIDER_AUX_MODELS
+
+    def test_vision_model_override(self):
+        """Xiaomi vision tasks should use mimo-v2-omni (multimodal), not the main model."""
+        from agent.auxiliary_client import _PROVIDER_VISION_MODELS
+        assert "xiaomi" in _PROVIDER_VISION_MODELS
+        assert _PROVIDER_VISION_MODELS["xiaomi"] == "mimo-v2-omni"
+
+
+# =============================================================================
+# Agent init (no SyntaxError, correct api_mode)
+# =============================================================================
+
+
+class TestXiaomiDoctor:
+    """Verify hermes doctor recognizes Xiaomi env vars."""
+
+    def test_provider_env_hints(self):
+        from hermes_cli.doctor import _PROVIDER_ENV_HINTS
+        assert "XIAOMI_API_KEY" in _PROVIDER_ENV_HINTS
+
+
+class TestXiaomiAgentInit:
+    """Verify the agent can be constructed with xiaomi provider without errors."""
+
+    def test_no_syntax_errors(self):
+        """Importing run_agent with xiaomi should not raise."""
+        import importlib
+        importlib.import_module("run_agent")
+
+    def test_api_mode_is_chat_completions(self):
+        from hermes_cli.providers import HERMES_OVERLAYS, TRANSPORT_TO_API_MODE
+        overlay = HERMES_OVERLAYS["xiaomi"]
+        api_mode = TRANSPORT_TO_API_MODE[overlay.transport]
+        assert api_mode == "chat_completions"

tests/honcho_plugin/test_client.py

@@ -500,6 +500,48 @@ class TestObservationModeMigration:
         assert cfg.ai_observe_others is True
 
 
+class TestInitOnSessionStart:
+    """Tests for the initOnSessionStart config field."""
+
+    def test_default_is_false(self):
+        config = HonchoClientConfig()
+        assert config.init_on_session_start is False
+
+    def test_root_level_true(self, tmp_path):
+        cfg_file = tmp_path / "config.json"
+        cfg_file.write_text(json.dumps({
+            "apiKey": "k",
+            "initOnSessionStart": True,
+        }))
+        cfg = HonchoClientConfig.from_global_config(config_path=cfg_file)
+        assert cfg.init_on_session_start is True
+
+    def test_host_block_overrides_root(self, tmp_path):
+        cfg_file = tmp_path / "config.json"
+        cfg_file.write_text(json.dumps({
+            "apiKey": "k",
+            "initOnSessionStart": True,
+            "hosts": {"hermes": {"initOnSessionStart": False}},
+        }))
+        cfg = HonchoClientConfig.from_global_config(config_path=cfg_file)
+        assert cfg.init_on_session_start is False
+
+    def test_host_block_true_overrides_root_absent(self, tmp_path):
+        cfg_file = tmp_path / "config.json"
+        cfg_file.write_text(json.dumps({
+            "apiKey": "k",
+            "hosts": {"hermes": {"initOnSessionStart": True}},
+        }))
+        cfg = HonchoClientConfig.from_global_config(config_path=cfg_file)
+        assert cfg.init_on_session_start is True
+
+    def test_absent_everywhere_defaults_false(self, tmp_path):
+        cfg_file = tmp_path / "config.json"
+        cfg_file.write_text(json.dumps({"apiKey": "k"}))
+        cfg = HonchoClientConfig.from_global_config(config_path=cfg_file)
+        assert cfg.init_on_session_start is False
+
+
 class TestResetHonchoClient:
     def test_reset_clears_singleton(self):
         import plugins.memory.honcho.client as mod

tests/honcho_plugin/test_session.py

@@ -275,6 +275,97 @@ class TestPeerLookupHelpers:
 # ---------------------------------------------------------------------------
 
 
+# ---------------------------------------------------------------------------
+# Provider init behavior: lazy vs eager in tools mode
+# ---------------------------------------------------------------------------
+
+
+class TestToolsModeInitBehavior:
+    """Verify initOnSessionStart controls session init timing in tools mode."""
+
+    def _make_provider_with_config(self, recall_mode="tools", init_on_session_start=False,
+                                    peer_name=None, user_id=None):
+        """Create a HonchoMemoryProvider with mocked config and dependencies."""
+        from plugins.memory.honcho.client import HonchoClientConfig
+
+        cfg = HonchoClientConfig(
+            api_key="test-key",
+            enabled=True,
+            recall_mode=recall_mode,
+            init_on_session_start=init_on_session_start,
+            peer_name=peer_name,
+        )
+
+        provider = HonchoMemoryProvider()
+
+        # Patch the config loading and session init to avoid real Honcho calls
+        from unittest.mock import patch, MagicMock
+
+        mock_manager = MagicMock()
+        mock_session = MagicMock()
+        mock_session.messages = []
+        mock_manager.get_or_create.return_value = mock_session
+
+        init_kwargs = {}
+        if user_id:
+            init_kwargs["user_id"] = user_id
+
+        with patch("plugins.memory.honcho.client.HonchoClientConfig.from_global_config", return_value=cfg), \
+             patch("plugins.memory.honcho.client.get_honcho_client", return_value=MagicMock()), \
+             patch("plugins.memory.honcho.session.HonchoSessionManager", return_value=mock_manager), \
+             patch("hermes_constants.get_hermes_home", return_value=MagicMock()):
+            provider.initialize(session_id="test-session-001", **init_kwargs)
+
+        return provider, cfg
+
+    def test_tools_lazy_default(self):
+        """tools + initOnSessionStart=false → session NOT initialized after initialize()."""
+        provider, _ = self._make_provider_with_config(
+            recall_mode="tools", init_on_session_start=False,
+        )
+        assert provider._session_initialized is False
+        assert provider._manager is None
+        assert provider._lazy_init_kwargs is not None
+
+    def test_tools_eager_init(self):
+        """tools + initOnSessionStart=true → session IS initialized after initialize()."""
+        provider, _ = self._make_provider_with_config(
+            recall_mode="tools", init_on_session_start=True,
+        )
+        assert provider._session_initialized is True
+        assert provider._manager is not None
+
+    def test_tools_eager_prefetch_still_empty(self):
+        """tools mode with eager init still returns empty from prefetch() (no auto-injection)."""
+        provider, _ = self._make_provider_with_config(
+            recall_mode="tools", init_on_session_start=True,
+        )
+        assert provider.prefetch("test query") == ""
+
+    def test_tools_lazy_prefetch_empty(self):
+        """tools mode with lazy init also returns empty from prefetch()."""
+        provider, _ = self._make_provider_with_config(
+            recall_mode="tools", init_on_session_start=False,
+        )
+        assert provider.prefetch("test query") == ""
+
+    def test_explicit_peer_name_not_overridden_by_user_id(self):
+        """Explicit peerName in config must not be replaced by gateway user_id."""
+        _, cfg = self._make_provider_with_config(
+            recall_mode="tools", init_on_session_start=True,
+            peer_name="Kathie", user_id="8439114563",
+        )
+        assert cfg.peer_name == "Kathie"
+
+    def test_user_id_used_when_no_peer_name(self):
+        """Gateway user_id is used as peer_name when no explicit peerName configured."""
+        _, cfg = self._make_provider_with_config(
+            recall_mode="tools", init_on_session_start=True,
+            peer_name=None, user_id="8439114563",
+        )
+        assert cfg.peer_name == "8439114563"
+
+
 class TestChunkMessage:
     def test_short_message_single_chunk(self):
         result = HonchoMemoryProvider._chunk_message("hello world", 100)

tests/run_agent/test_compression_feasibility.py

@@ -0,0 +1,279 @@
+"""Tests for _check_compression_model_feasibility() — warns when the
+auxiliary compression model's context is smaller than the main model's
+compression threshold.
+
+Two-phase design:
+  1. __init__  → runs the check, prints via _vprint (CLI), stores warning
+  2. run_conversation (first call) → replays stored warning through
+     status_callback (gateway platforms)
+"""
+
+from unittest.mock import MagicMock, patch
+
+from run_agent import AIAgent
+from agent.context_compressor import ContextCompressor
+
+
+def _make_agent(
+    *,
+    compression_enabled: bool = True,
+    threshold_percent: float = 0.50,
+    main_context: int = 200_000,
+) -> AIAgent:
+    """Build a minimal AIAgent with a compressor, skipping __init__."""
+    agent = AIAgent.__new__(AIAgent)
+    agent.model = "test-main-model"
+    agent.provider = "openrouter"
+    agent.base_url = "https://openrouter.ai/api/v1"
+    agent.api_key = "sk-test"
+    agent.quiet_mode = True
+    agent.log_prefix = ""
+    agent.compression_enabled = compression_enabled
+    agent._print_fn = None
+    agent.suppress_status_output = False
+    agent._stream_consumers = []
+    agent._executing_tools = False
+    agent._mute_post_response = False
+    agent.status_callback = None
+    agent.tool_progress_callback = None
+    agent._compression_warning = None
+
+    compressor = MagicMock(spec=ContextCompressor)
+    compressor.context_length = main_context
+    compressor.threshold_tokens = int(main_context * threshold_percent)
+    agent.context_compressor = compressor
+
+    return agent
+
+
+# ── Core warning logic ──────────────────────────────────────────────
+
+
+@patch("agent.model_metadata.get_model_context_length", return_value=32_768)
+@patch("agent.auxiliary_client.get_text_auxiliary_client")
+def test_warns_when_aux_context_below_threshold(mock_get_client, mock_ctx_len):
+    """Warning emitted when aux model context < main model threshold."""
+    agent = _make_agent(main_context=200_000, threshold_percent=0.50)
+    # threshold = 100,000 — aux has only 32,768
+    mock_client = MagicMock()
+    mock_client.base_url = "https://openrouter.ai/api/v1"
+    mock_client.api_key = "sk-aux"
+    mock_get_client.return_value = (mock_client, "google/gemini-3-flash-preview")
+
+    messages = []
+    agent._emit_status = lambda msg: messages.append(msg)
+
+    agent._check_compression_model_feasibility()
+
+    assert len(messages) == 1
+    assert "Compression model" in messages[0]
+    assert "32,768" in messages[0]
+    assert "100,000" in messages[0]
+    assert "will not be possible" in messages[0]
+    # Actionable fix guidance included
+    assert "Fix options" in messages[0]
+    assert "auxiliary:" in messages[0]
+    assert "compression:" in messages[0]
+    assert "threshold:" in messages[0]
+    # Warning stored for gateway replay
+    assert agent._compression_warning is not None
+
+
+@patch("agent.model_metadata.get_model_context_length", return_value=200_000)
+@patch("agent.auxiliary_client.get_text_auxiliary_client")
+def test_no_warning_when_aux_context_sufficient(mock_get_client, mock_ctx_len):
+    """No warning when aux model context >= main model threshold."""
+    agent = _make_agent(main_context=200_000, threshold_percent=0.50)
+    # threshold = 100,000 — aux has 200,000 (sufficient)
+    mock_client = MagicMock()
+    mock_client.base_url = "https://openrouter.ai/api/v1"
+    mock_client.api_key = "sk-aux"
+    mock_get_client.return_value = (mock_client, "google/gemini-2.5-flash")
+
+    messages = []
+    agent._emit_status = lambda msg: messages.append(msg)
+
+    agent._check_compression_model_feasibility()
+
+    assert len(messages) == 0
+    assert agent._compression_warning is None
+
+
+@patch("agent.auxiliary_client.get_text_auxiliary_client")
+def test_warns_when_no_auxiliary_provider(mock_get_client):
+    """Warning emitted when no auxiliary provider is configured."""
+    agent = _make_agent()
+    mock_get_client.return_value = (None, None)
+
+    messages = []
+    agent._emit_status = lambda msg: messages.append(msg)
+
+    agent._check_compression_model_feasibility()
+
+    assert len(messages) == 1
+    assert "No auxiliary LLM provider" in messages[0]
+    assert agent._compression_warning is not None
+
+
+def test_skips_check_when_compression_disabled():
+    """No check performed when compression is disabled."""
+    agent = _make_agent(compression_enabled=False)
+
+    messages = []
+    agent._emit_status = lambda msg: messages.append(msg)
+
+    agent._check_compression_model_feasibility()
+
+    assert len(messages) == 0
+    assert agent._compression_warning is None
+
+
+@patch("agent.auxiliary_client.get_text_auxiliary_client")
+def test_exception_does_not_crash(mock_get_client):
+    """Exceptions in the check are caught — never blocks startup."""
+    agent = _make_agent()
+    mock_get_client.side_effect = RuntimeError("boom")
+
+    messages = []
+    agent._emit_status = lambda msg: messages.append(msg)
+
+    # Should not raise
+    agent._check_compression_model_feasibility()
+
+    # No user-facing message (error is debug-logged)
+    assert len(messages) == 0
+
+
+@patch("agent.model_metadata.get_model_context_length", return_value=100_000)
+@patch("agent.auxiliary_client.get_text_auxiliary_client")
+def test_exact_threshold_boundary_no_warning(mock_get_client, mock_ctx_len):
+    """No warning when aux context exactly equals the threshold."""
+    agent = _make_agent(main_context=200_000, threshold_percent=0.50)
+    mock_client = MagicMock()
+    mock_client.base_url = "https://openrouter.ai/api/v1"
+    mock_client.api_key = "sk-aux"
+    mock_get_client.return_value = (mock_client, "test-model")
+
+    messages = []
+    agent._emit_status = lambda msg: messages.append(msg)
+
+    agent._check_compression_model_feasibility()
+
+    assert len(messages) == 0
+
+
+@patch("agent.model_metadata.get_model_context_length", return_value=99_999)
+@patch("agent.auxiliary_client.get_text_auxiliary_client")
+def test_just_below_threshold_warns(mock_get_client, mock_ctx_len):
+    """Warning fires when aux context is one token below the threshold."""
+    agent = _make_agent(main_context=200_000, threshold_percent=0.50)
+    mock_client = MagicMock()
+    mock_client.base_url = "https://openrouter.ai/api/v1"
+    mock_client.api_key = "sk-aux"
+    mock_get_client.return_value = (mock_client, "small-model")
+
+    messages = []
+    agent._emit_status = lambda msg: messages.append(msg)
+
+    agent._check_compression_model_feasibility()
+
+    assert len(messages) == 1
+    assert "small-model" in messages[0]
+
+
+# ── Two-phase: __init__ + run_conversation replay ───────────────────
+
+
+@patch("agent.model_metadata.get_model_context_length", return_value=32_768)
+@patch("agent.auxiliary_client.get_text_auxiliary_client")
+def test_warning_stored_for_gateway_replay(mock_get_client, mock_ctx_len):
+    """__init__ stores the warning; _replay sends it through status_callback."""
+    agent = _make_agent(main_context=200_000, threshold_percent=0.50)
+    mock_client = MagicMock()
+    mock_client.base_url = "https://openrouter.ai/api/v1"
+    mock_client.api_key = "sk-aux"
+    mock_get_client.return_value = (mock_client, "google/gemini-3-flash-preview")
+
+    # Phase 1: __init__ — _emit_status prints (CLI) but callback is None
+    vprint_messages = []
+    agent._emit_status = lambda msg: vprint_messages.append(msg)
+    agent._check_compression_model_feasibility()
+
+    assert len(vprint_messages) == 1  # CLI got it
+    assert agent._compression_warning is not None  # stored for replay
+
+    # Phase 2: gateway wires callback post-init, then run_conversation replays
+    callback_events = []
+    agent.status_callback = lambda ev, msg: callback_events.append((ev, msg))
+    agent._replay_compression_warning()
+
+    assert any(
+        ev == "lifecycle" and "will not be possible" in msg
+        for ev, msg in callback_events
+    )
+
+
+@patch("agent.model_metadata.get_model_context_length", return_value=200_000)
+@patch("agent.auxiliary_client.get_text_auxiliary_client")
+def test_no_replay_when_no_warning(mock_get_client, mock_ctx_len):
+    """_replay_compression_warning is a no-op when there's no stored warning."""
+    agent = _make_agent(main_context=200_000, threshold_percent=0.50)
+    mock_client = MagicMock()
+    mock_client.base_url = "https://openrouter.ai/api/v1"
+    mock_client.api_key = "sk-aux"
+    mock_get_client.return_value = (mock_client, "big-model")
+
+    agent._emit_status = lambda msg: None
+    agent._check_compression_model_feasibility()
+
+    assert agent._compression_warning is None
+
+    callback_events = []
+    agent.status_callback = lambda ev, msg: callback_events.append((ev, msg))
+    agent._replay_compression_warning()
+
+    assert len(callback_events) == 0
+
+
+def test_replay_without_callback_is_noop():
+    """_replay_compression_warning doesn't crash when status_callback is None."""
+    agent = _make_agent()
+    agent._compression_warning = "some warning"
+    agent.status_callback = None
+
+    # Should not raise
+    agent._replay_compression_warning()
+
+
+@patch("agent.model_metadata.get_model_context_length", return_value=32_768)
+@patch("agent.auxiliary_client.get_text_auxiliary_client")
+def test_run_conversation_clears_warning_after_replay(mock_get_client, mock_ctx_len):
+    """After replay in run_conversation, _compression_warning is cleared
+    so the warning is not sent again on subsequent turns."""
+    agent = _make_agent(main_context=200_000, threshold_percent=0.50)
+    mock_client = MagicMock()
+    mock_client.base_url = "https://openrouter.ai/api/v1"
+    mock_client.api_key = "sk-aux"
+    mock_get_client.return_value = (mock_client, "small-model")
+
+    agent._emit_status = lambda msg: None
+    agent._check_compression_model_feasibility()
+
+    assert agent._compression_warning is not None
+
+    # Simulate what run_conversation does
+    callback_events = []
+    agent.status_callback = lambda ev, msg: callback_events.append((ev, msg))
+    if agent._compression_warning:
+        agent._replay_compression_warning()
+        agent._compression_warning = None  # as in run_conversation
+
+    assert len(callback_events) == 1
+
+    # Second turn — nothing replayed
+    callback_events.clear()
+    if agent._compression_warning:
+        agent._replay_compression_warning()
+        agent._compression_warning = None
+
+    assert len(callback_events) == 0

tests/run_agent/test_run_agent.py

@@ -953,14 +953,24 @@ class TestBuildApiKwargs:
         assert kwargs["messages"][0]["content"][0]["text"] == "hi"
         assert "cache_control" not in kwargs["messages"][0]["content"][0]
 
-    def test_qwen_portal_omits_max_tokens(self, agent):
+    def test_qwen_portal_sends_explicit_max_tokens(self, agent):
+        """When the user explicitly sets max_tokens, it should be sent to Qwen Portal."""
         agent.base_url = "https://portal.qwen.ai/v1"
         agent._base_url_lower = agent.base_url.lower()
         agent.max_tokens = 4096
         messages = [{"role": "system", "content": "sys"}, {"role": "user", "content": "hi"}]
         kwargs = agent._build_api_kwargs(messages)
-        assert "max_tokens" not in kwargs
-        assert "max_completion_tokens" not in kwargs
+        assert kwargs["max_tokens"] == 4096
+
+    def test_qwen_portal_default_max_tokens(self, agent):
+        """When max_tokens is None, Qwen Portal gets a default of 65536
+        to prevent reasoning models from exhausting their output budget."""
+        agent.base_url = "https://portal.qwen.ai/v1"
+        agent._base_url_lower = agent.base_url.lower()
+        agent.max_tokens = None
+        messages = [{"role": "system", "content": "sys"}, {"role": "user", "content": "hi"}]
+        kwargs = agent._build_api_kwargs(messages)
+        assert kwargs["max_tokens"] == 65536
 
 
 class TestBuildAssistantMessage:
@@ -1823,6 +1833,111 @@ class TestRunConversation:
         assert result["final_response"] == "Here is the actual answer."
         assert result["api_calls"] == 2  # 1 original + 1 nudge retry
 
+    def test_empty_response_triggers_fallback_provider(self, agent):
+        """After 3 empty retries, fallback provider is activated and produces content."""
+        self._setup_agent(agent)
+        agent.base_url = "http://127.0.0.1:1234/v1"
+        # Configure a fallback chain
+        agent._fallback_chain = [{"provider": "openrouter", "model": "anthropic/claude-sonnet-4"}]
+        agent._fallback_index = 0
+        agent._fallback_activated = False
+
+        empty_resp = _mock_response(content=None, finish_reason="stop")
+        content_resp = _mock_response(content="Fallback answer.", finish_reason="stop")
+        # 4 empty (1 orig + 3 retries), then fallback model answers
+        agent.client.chat.completions.create.side_effect = [
+            empty_resp, empty_resp, empty_resp, empty_resp, content_resp,
+        ]
+
+        fallback_called = {"called": False}
+
+        def _mock_fallback():
+            fallback_called["called"] = True
+            # Simulate what _try_activate_fallback does: just advance the
+            # index and set the flag (the client is already mocked).
+            agent._fallback_index = 1
+            agent._fallback_activated = True
+            agent.model = "anthropic/claude-sonnet-4"
+            agent.provider = "openrouter"
+            return True
+
+        with (
+            patch.object(agent, "_persist_session"),
+            patch.object(agent, "_save_trajectory"),
+            patch.object(agent, "_cleanup_task_resources"),
+            patch.object(agent, "_try_activate_fallback", side_effect=_mock_fallback),
+        ):
+            result = agent.run_conversation("answer me")
+        assert fallback_called["called"], "Fallback should have been triggered"
+        assert result["completed"] is True
+        assert result["final_response"] == "Fallback answer."
+
+    def test_empty_response_fallback_also_empty_returns_empty(self, agent):
+        """If fallback also returns empty, final response is (empty)."""
+        self._setup_agent(agent)
+        agent.base_url = "http://127.0.0.1:1234/v1"
+        agent._fallback_chain = [{"provider": "openrouter", "model": "anthropic/claude-sonnet-4"}]
+        agent._fallback_index = 0
+        agent._fallback_activated = False
+
+        empty_resp = _mock_response(content=None, finish_reason="stop")
+        # 4 empty from primary (1 + 3 retries), fallback activated,
+        # then 4 more empty from fallback (1 + 3 retries), no more fallbacks
+        agent.client.chat.completions.create.side_effect = [
+            empty_resp, empty_resp, empty_resp, empty_resp,  # primary exhausted
+            empty_resp, empty_resp, empty_resp, empty_resp,  # fallback exhausted
+        ]
+
+        def _mock_fallback():
+            if agent._fallback_index >= len(agent._fallback_chain):
+                return False
+            agent._fallback_index += 1
+            agent._fallback_activated = True
+            agent.model = "anthropic/claude-sonnet-4"
+            agent.provider = "openrouter"
+            return True
+
+        with (
+            patch.object(agent, "_persist_session"),
+            patch.object(agent, "_save_trajectory"),
+            patch.object(agent, "_cleanup_task_resources"),
+            patch.object(agent, "_try_activate_fallback", side_effect=_mock_fallback),
+        ):
+            result = agent.run_conversation("answer me")
+        assert result["completed"] is True
+        assert result["final_response"] == "(empty)"
+
+    def test_empty_response_emits_status_for_gateway(self, agent):
+        """_emit_status is called during empty retries so gateway users see feedback."""
+        self._setup_agent(agent)
+        agent.base_url = "http://127.0.0.1:1234/v1"
+
+        empty_resp = _mock_response(content=None, finish_reason="stop")
+        # 4 empty: 1 original + 3 retries, all empty, no fallback
+        agent.client.chat.completions.create.side_effect = [
+            empty_resp, empty_resp, empty_resp, empty_resp,
+        ]
+
+        status_messages = []
+
+        def _capture_status(msg):
+            status_messages.append(msg)
+
+        with (
+            patch.object(agent, "_persist_session"),
+            patch.object(agent, "_save_trajectory"),
+            patch.object(agent, "_cleanup_task_resources"),
+            patch.object(agent, "_emit_status", side_effect=_capture_status),
+        ):
+            result = agent.run_conversation("answer me")
+
+        assert result["final_response"] == "(empty)"
+        # Should have emitted retry statuses (3 retries) + final failure
+        retry_msgs = [m for m in status_messages if "retrying" in m.lower()]
+        assert len(retry_msgs) == 3, f"Expected 3 retry status messages, got {len(retry_msgs)}: {status_messages}"
+        failure_msgs = [m for m in status_messages if "no content" in m.lower() or "no fallback" in m.lower()]
+        assert len(failure_msgs) >= 1, f"Expected at least 1 failure status, got: {status_messages}"
+
     def test_nous_401_refreshes_after_remint_and_retries(self, agent):
         self._setup_agent(agent)
         agent.provider = "nous"

tests/run_agent/test_run_agent_codex_responses.py

@@ -222,6 +222,12 @@ def test_api_mode_normalizes_provider_case(monkeypatch):
 
 
 def test_api_mode_respects_explicit_openrouter_provider_over_codex_url(monkeypatch):
+    """GPT-5.x models need codex_responses even on OpenRouter.
+
+    OpenRouter rejects GPT-5 models on /v1/chat/completions with
+    ``unsupported_api_for_model``.  The model-level check overrides
+    the provider default.
+    """
     _patch_agent_bootstrap(monkeypatch)
     agent = run_agent.AIAgent(
         model="gpt-5-codex",
@@ -233,7 +239,7 @@ def test_api_mode_respects_explicit_openrouter_provider_over_codex_url(monkeypat
         skip_context_files=True,
         skip_memory=True,
     )
-    assert agent.api_mode == "chat_completions"
+    assert agent.api_mode == "codex_responses"
     assert agent.provider == "openrouter"
 
 

tests/test_project_metadata.py

@@ -12,10 +12,10 @@ def _load_optional_dependencies():
 
 
 def test_matrix_extra_linux_only_in_all():
-    """matrix-nio[e2e] depends on python-olm which is upstream-broken on modern
-    macOS (archived libolm, C++ errors with Clang 21+).  The [matrix] extra is
-    included in [all] but gated to Linux via a platform marker so that
-    ``hermes update`` doesn't fail on macOS."""
+    """mautrix[encryption] depends on python-olm which is upstream-broken on
+    modern macOS (archived libolm, C++ errors with Clang 21+).  The [matrix]
+    extra is included in [all] but gated to Linux via a platform marker so
+    that ``hermes update`` doesn't fail on macOS."""
     optional_dependencies = _load_optional_dependencies()
 
     assert "matrix" in optional_dependencies

tests/tools/test_approval.py

@@ -156,6 +156,8 @@ class TestSessionKeyContext:
         assert "reset_current_session_key" in called_names
 
 
+
+
 class TestRmFalsePositiveFix:
     """Regression tests: filenames starting with 'r' must NOT trigger recursive delete."""
 

tests/tools/test_budget_config.py

@@ -0,0 +1,176 @@
+"""Unit tests for tools/budget_config.py.
+
+Covers default values, resolve_threshold() priority chain
+(pinned > tool_overrides > registry > default), immutability,
+and the PINNED_THRESHOLDS escape-hatch for read_file.
+"""
+
+import dataclasses
+import math
+from unittest.mock import patch
+
+import pytest
+
+from tools.budget_config import (
+    DEFAULT_BUDGET,
+    DEFAULT_PREVIEW_SIZE_CHARS,
+    DEFAULT_RESULT_SIZE_CHARS,
+    DEFAULT_TURN_BUDGET_CHARS,
+    PINNED_THRESHOLDS,
+    BudgetConfig,
+)
+
+
+# ---------------------------------------------------------------------------
+# Module-level constants
+# ---------------------------------------------------------------------------
+
+
+class TestModuleConstants:
+    """Verify documented default values haven't drifted."""
+
+    def test_default_result_size(self):
+        assert DEFAULT_RESULT_SIZE_CHARS == 100_000
+
+    def test_default_turn_budget(self):
+        assert DEFAULT_TURN_BUDGET_CHARS == 200_000
+
+    def test_default_preview_size(self):
+        assert DEFAULT_PREVIEW_SIZE_CHARS == 1_500
+
+
+class TestPinnedThresholds:
+    """PINNED_THRESHOLDS – tools whose values must never be overridden."""
+
+    def test_read_file_is_inf(self):
+        assert PINNED_THRESHOLDS["read_file"] == float("inf")
+        assert math.isinf(PINNED_THRESHOLDS["read_file"])
+
+    def test_pinned_is_not_empty(self):
+        assert len(PINNED_THRESHOLDS) >= 1
+
+
+# ---------------------------------------------------------------------------
+# BudgetConfig defaults
+# ---------------------------------------------------------------------------
+
+
+class TestBudgetConfigDefaults:
+    """BudgetConfig() should match the module-level defaults exactly."""
+
+    def test_default_result_size(self):
+        cfg = BudgetConfig()
+        assert cfg.default_result_size == DEFAULT_RESULT_SIZE_CHARS
+
+    def test_default_turn_budget(self):
+        cfg = BudgetConfig()
+        assert cfg.turn_budget == DEFAULT_TURN_BUDGET_CHARS
+
+    def test_default_preview_size(self):
+        cfg = BudgetConfig()
+        assert cfg.preview_size == DEFAULT_PREVIEW_SIZE_CHARS
+
+    def test_default_tool_overrides_empty(self):
+        cfg = BudgetConfig()
+        assert cfg.tool_overrides == {}
+
+    def test_default_budget_singleton_matches(self):
+        """DEFAULT_BUDGET should equal a freshly constructed BudgetConfig."""
+        assert DEFAULT_BUDGET == BudgetConfig()
+
+
+# ---------------------------------------------------------------------------
+# Immutability (frozen=True)
+# ---------------------------------------------------------------------------
+
+
+class TestBudgetConfigFrozen:
+    """Frozen dataclass must reject attribute mutation."""
+
+    def test_cannot_set_default_result_size(self):
+        cfg = BudgetConfig()
+        with pytest.raises(dataclasses.FrozenInstanceError):
+            cfg.default_result_size = 999
+
+    def test_cannot_set_turn_budget(self):
+        cfg = BudgetConfig()
+        with pytest.raises(dataclasses.FrozenInstanceError):
+            cfg.turn_budget = 999
+
+    def test_cannot_set_preview_size(self):
+        cfg = BudgetConfig()
+        with pytest.raises(dataclasses.FrozenInstanceError):
+            cfg.preview_size = 999
+
+    def test_cannot_set_tool_overrides(self):
+        cfg = BudgetConfig()
+        with pytest.raises(dataclasses.FrozenInstanceError):
+            cfg.tool_overrides = {"foo": 1}
+
+
+# ---------------------------------------------------------------------------
+# Custom construction
+# ---------------------------------------------------------------------------
+
+
+class TestBudgetConfigCustom:
+    """BudgetConfig can be created with non-default values."""
+
+    def test_custom_values(self):
+        cfg = BudgetConfig(
+            default_result_size=50_000,
+            turn_budget=100_000,
+            preview_size=500,
+            tool_overrides={"my_tool": 42},
+        )
+        assert cfg.default_result_size == 50_000
+        assert cfg.turn_budget == 100_000
+        assert cfg.preview_size == 500
+        assert cfg.tool_overrides == {"my_tool": 42}
+
+
+# ---------------------------------------------------------------------------
+# resolve_threshold() priority chain
+# ---------------------------------------------------------------------------
+
+
+class TestResolveThreshold:
+    """Priority: pinned > tool_overrides > registry > default."""
+
+    def test_pinned_wins_over_override(self):
+        """Even if tool_overrides contains read_file, pinned value wins."""
+        cfg = BudgetConfig(tool_overrides={"read_file": 1})
+        result = cfg.resolve_threshold("read_file")
+        assert result == float("inf")
+
+    def test_tool_override_wins_over_default(self):
+        """tool_overrides should be returned before falling back to registry."""
+        cfg = BudgetConfig(tool_overrides={"my_tool": 42})
+        result = cfg.resolve_threshold("my_tool")
+        assert result == 42
+
+    @patch("tools.registry.registry")
+    def test_falls_back_to_registry(self, mock_registry):
+        """When not pinned and not in overrides, delegate to registry."""
+        mock_registry.get_max_result_size.return_value = 77_777
+        cfg = BudgetConfig()
+        result = cfg.resolve_threshold("some_tool")
+        mock_registry.get_max_result_size.assert_called_once_with(
+            "some_tool", default=DEFAULT_RESULT_SIZE_CHARS
+        )
+        assert result == 77_777
+
+    @patch("tools.registry.registry")
+    def test_registry_receives_custom_default(self, mock_registry):
+        """Custom default_result_size flows through to registry call."""
+        mock_registry.get_max_result_size.return_value = 50_000
+        cfg = BudgetConfig(default_result_size=50_000)
+        cfg.resolve_threshold("unknown_tool")
+        mock_registry.get_max_result_size.assert_called_once_with(
+            "unknown_tool", default=50_000
+        )
+
+    def test_pinned_read_file_returns_inf(self):
+        """Canonical case: read_file must always return inf."""
+        cfg = BudgetConfig()
+        assert cfg.resolve_threshold("read_file") == float("inf")

tests/tools/test_clipboard.py

@@ -205,9 +205,9 @@ class TestMacosOsascript:
 
 class TestIsWsl:
     def setup_method(self):
-        # Reset cached value before each test
-        import hermes_cli.clipboard as cb
-        cb._wsl_detected = None
+        # _is_wsl is now hermes_constants.is_wsl — reset its cache
+        import hermes_constants
+        hermes_constants._wsl_detected = None
 
     def test_wsl2_detected(self):
         content = "Linux version 5.15.0 (microsoft-standard-WSL2)"
@@ -229,6 +229,7 @@ class TestIsWsl:
             assert _is_wsl() is False
 
     def test_result_is_cached(self):
+        import hermes_constants
         content = "Linux version 5.15.0 (microsoft-standard-WSL2)"
         with patch("builtins.open", mock_open(read_data=content)) as m:
             assert _is_wsl() is True

tests/tools/test_delegate.py

@@ -1210,5 +1210,73 @@ class TestDelegateHeartbeat(unittest.TestCase):
             f"Heartbeat should include last_activity_desc: {touch_calls}")
 
 
+class TestDelegationReasoningEffort(unittest.TestCase):
+    """Tests for delegation.reasoning_effort config override."""
+
+    @patch("tools.delegate_tool._load_config")
+    @patch("run_agent.AIAgent")
+    def test_inherits_parent_reasoning_when_no_override(self, MockAgent, mock_cfg):
+        """With no delegation.reasoning_effort, child inherits parent's config."""
+        mock_cfg.return_value = {"max_iterations": 50, "reasoning_effort": ""}
+        MockAgent.return_value = MagicMock()
+        parent = _make_mock_parent()
+        parent.reasoning_config = {"enabled": True, "effort": "xhigh"}
+
+        _build_child_agent(
+            task_index=0, goal="test", context=None, toolsets=None,
+            model=None, max_iterations=50, parent_agent=parent,
+        )
+        call_kwargs = MockAgent.call_args[1]
+        self.assertEqual(call_kwargs["reasoning_config"], {"enabled": True, "effort": "xhigh"})
+
+    @patch("tools.delegate_tool._load_config")
+    @patch("run_agent.AIAgent")
+    def test_override_reasoning_effort_from_config(self, MockAgent, mock_cfg):
+        """delegation.reasoning_effort overrides the parent's level."""
+        mock_cfg.return_value = {"max_iterations": 50, "reasoning_effort": "low"}
+        MockAgent.return_value = MagicMock()
+        parent = _make_mock_parent()
+        parent.reasoning_config = {"enabled": True, "effort": "xhigh"}
+
+        _build_child_agent(
+            task_index=0, goal="test", context=None, toolsets=None,
+            model=None, max_iterations=50, parent_agent=parent,
+        )
+        call_kwargs = MockAgent.call_args[1]
+        self.assertEqual(call_kwargs["reasoning_config"], {"enabled": True, "effort": "low"})
+
+    @patch("tools.delegate_tool._load_config")
+    @patch("run_agent.AIAgent")
+    def test_override_reasoning_effort_none_disables(self, MockAgent, mock_cfg):
+        """delegation.reasoning_effort: 'none' disables thinking for subagents."""
+        mock_cfg.return_value = {"max_iterations": 50, "reasoning_effort": "none"}
+        MockAgent.return_value = MagicMock()
+        parent = _make_mock_parent()
+        parent.reasoning_config = {"enabled": True, "effort": "high"}
+
+        _build_child_agent(
+            task_index=0, goal="test", context=None, toolsets=None,
+            model=None, max_iterations=50, parent_agent=parent,
+        )
+        call_kwargs = MockAgent.call_args[1]
+        self.assertEqual(call_kwargs["reasoning_config"], {"enabled": False})
+
+    @patch("tools.delegate_tool._load_config")
+    @patch("run_agent.AIAgent")
+    def test_invalid_reasoning_effort_falls_back_to_parent(self, MockAgent, mock_cfg):
+        """Invalid delegation.reasoning_effort falls back to parent's config."""
+        mock_cfg.return_value = {"max_iterations": 50, "reasoning_effort": "banana"}
+        MockAgent.return_value = MagicMock()
+        parent = _make_mock_parent()
+        parent.reasoning_config = {"enabled": True, "effort": "medium"}
+
+        _build_child_agent(
+            task_index=0, goal="test", context=None, toolsets=None,
+            model=None, max_iterations=50, parent_agent=parent,
+        )
+        call_kwargs = MockAgent.call_args[1]
+        self.assertEqual(call_kwargs["reasoning_config"], {"enabled": True, "effort": "medium"})
+
+
 if __name__ == "__main__":
     unittest.main()

tests/tools/test_file_operations_edge_cases.py

@@ -0,0 +1,148 @@
+"""Tests for edge cases in tools/file_operations.py.
+
+Covers:
+- ``_is_likely_binary()`` content-analysis branch (dead-code removal regression guard)
+- ``_check_lint()`` robustness against file paths containing curly braces
+"""
+
+import pytest
+from unittest.mock import MagicMock, patch
+
+from tools.file_operations import ShellFileOperations
+
+
+# =========================================================================
+# _is_likely_binary edge cases
+# =========================================================================
+
+
+class TestIsLikelyBinary:
+    """Verify content-analysis logic after dead-code removal."""
+
+    @pytest.fixture()
+    def ops(self):
+        return ShellFileOperations.__new__(ShellFileOperations)
+
+    def test_binary_extension_returns_true(self, ops):
+        """Known binary extensions should short-circuit without content analysis."""
+        assert ops._is_likely_binary("image.png") is True
+        assert ops._is_likely_binary("archive.tar.gz", content_sample="hello") is True
+
+    def test_text_content_returns_false(self, ops):
+        """Normal printable text should not be classified as binary."""
+        sample = "Hello, world!\nThis is a normal text file.\n"
+        assert ops._is_likely_binary("unknown.xyz", content_sample=sample) is False
+
+    def test_binary_content_returns_true(self, ops):
+        """Content with >30% non-printable characters should be classified as binary."""
+        # 500 NUL bytes + 500 printable = 50% non-printable → binary
+        # Use .xyz extension (not in BINARY_EXTENSIONS) to ensure content analysis runs
+        sample = "\x00" * 500 + "a" * 500
+        assert ops._is_likely_binary("data.xyz", content_sample=sample) is True
+
+    def test_no_content_sample_returns_false(self, ops):
+        """When no content sample is provided and extension is unknown → not binary."""
+        assert ops._is_likely_binary("mystery_file") is False
+
+    def test_none_content_sample_returns_false(self, ops):
+        """Explicit ``None`` content_sample should behave the same as missing."""
+        assert ops._is_likely_binary("mystery_file", content_sample=None) is False
+
+    def test_empty_string_content_sample_returns_false(self, ops):
+        """Empty string is falsy, so content analysis should be skipped → not binary."""
+        assert ops._is_likely_binary("mystery_file", content_sample="") is False
+
+    def test_threshold_boundary(self, ops):
+        """Exactly 30% non-printable should NOT trigger binary classification (> 0.30, not >=)."""
+        # 300 NUL bytes + 700 printable = 30.0% → should be False (uses strict >)
+        sample = "\x00" * 300 + "a" * 700
+        assert ops._is_likely_binary("data.xyz", content_sample=sample) is False
+
+    def test_just_above_threshold(self, ops):
+        """301/1000 = 30.1% non-printable → should be binary."""
+        sample = "\x00" * 301 + "a" * 699
+        assert ops._is_likely_binary("data.xyz", content_sample=sample) is True
+
+    def test_tabs_and_newlines_excluded(self, ops):
+        """Tabs, carriage returns, and newlines should not count as non-printable."""
+        sample = "\t" * 400 + "\n" * 300 + "\r" * 200 + "a" * 100
+        assert ops._is_likely_binary("file.txt", content_sample=sample) is False
+
+    def test_content_sample_longer_than_1000(self, ops):
+        """Only the first 1000 characters should be analysed."""
+        # First 1000 chars: 200 NUL + 800 printable = 20% → not binary
+        # Remaining 1000 chars: all NUL → ignored by [:1000] slice
+        sample = "\x00" * 200 + "a" * 800 + "\x00" * 1000
+        assert ops._is_likely_binary("file.xyz", content_sample=sample) is False
+
+
+# =========================================================================
+# _check_lint edge cases
+# =========================================================================
+
+
+class TestCheckLintBracePaths:
+    """Verify _check_lint handles file paths with curly braces safely."""
+
+    @pytest.fixture()
+    def ops(self):
+        obj = ShellFileOperations.__new__(ShellFileOperations)
+        obj._command_cache = {}
+        return obj
+
+    def test_normal_path(self, ops):
+        """Normal path without braces should work as before."""
+        with patch.object(ops, "_has_command", return_value=True), \
+             patch.object(ops, "_exec") as mock_exec:
+            mock_exec.return_value = MagicMock(exit_code=0, stdout="")
+            result = ops._check_lint("/tmp/test_file.py")
+
+        assert result.success is True
+        # Verify the command was built correctly
+        cmd_arg = mock_exec.call_args[0][0]
+        assert "'/tmp/test_file.py'" in cmd_arg
+
+    def test_path_with_curly_braces(self, ops):
+        """Path containing ``{`` and ``}`` must not raise KeyError/ValueError."""
+        with patch.object(ops, "_has_command", return_value=True), \
+             patch.object(ops, "_exec") as mock_exec:
+            mock_exec.return_value = MagicMock(exit_code=0, stdout="")
+            # This would raise KeyError with .format() but works with .replace()
+            result = ops._check_lint("/tmp/{test}_file.py")
+
+        assert result.success is True
+        cmd_arg = mock_exec.call_args[0][0]
+        assert "{test}" in cmd_arg
+
+    def test_path_with_nested_braces(self, ops):
+        """Path with complex brace patterns like ``{{var}}`` should be safe."""
+        with patch.object(ops, "_has_command", return_value=True), \
+             patch.object(ops, "_exec") as mock_exec:
+            mock_exec.return_value = MagicMock(exit_code=0, stdout="")
+            result = ops._check_lint("/tmp/{{var}}.py")
+
+        assert result.success is True
+
+    def test_unsupported_extension_skipped(self, ops):
+        """Extensions without a linter should return a skipped result."""
+        result = ops._check_lint("/tmp/file.unknown_ext")
+        assert result.skipped is True
+
+    def test_missing_linter_skipped(self, ops):
+        """When the linter binary is not installed, skip gracefully."""
+        with patch.object(ops, "_has_command", return_value=False):
+            result = ops._check_lint("/tmp/test.py")
+        assert result.skipped is True
+
+    def test_lint_failure_returns_output(self, ops):
+        """When the linter exits non-zero, result should capture output."""
+        with patch.object(ops, "_has_command", return_value=True), \
+             patch.object(ops, "_exec") as mock_exec:
+            mock_exec.return_value = MagicMock(
+                exit_code=1,
+                stdout="SyntaxError: invalid syntax",
+            )
+            result = ops._check_lint("/tmp/bad.py")
+
+        assert result.success is False
+        assert "SyntaxError" in result.output

tests/tools/test_file_sync.py

@@ -255,3 +255,57 @@ class TestEdgeCases:
 
         mgr.sync(force=True)
         upload.assert_not_called()  # _file_mtime_key returns None, skipped
+
+
+class TestBulkUpload:
+    """Tests for the optional bulk_upload_fn callback."""
+
+    def test_bulk_upload_used_when_provided(self, tmp_files):
+        """When bulk_upload_fn is set, it's called instead of per-file upload_fn."""
+        upload = MagicMock()
+        bulk_upload = MagicMock()
+        mgr = FileSyncManager(
+            get_files_fn=_make_get_files(tmp_files),
+            upload_fn=upload,
+            delete_fn=MagicMock(),
+            bulk_upload_fn=bulk_upload,
+        )
+
+        mgr.sync(force=True)
+        upload.assert_not_called()
+        bulk_upload.assert_called_once()
+        # All 3 files passed as a list of (host, remote) tuples
+        files_arg = bulk_upload.call_args[0][0]
+        assert len(files_arg) == 3
+
+    def test_fallback_to_upload_fn_when_no_bulk(self, tmp_files):
+        """Without bulk_upload_fn, per-file upload_fn is used (backwards compat)."""
+        upload = MagicMock()
+        mgr = FileSyncManager(
+            get_files_fn=_make_get_files(tmp_files),
+            upload_fn=upload,
+            delete_fn=MagicMock(),
+            bulk_upload_fn=None,
+        )
+
+        mgr.sync(force=True)
+        assert upload.call_count == 3
+
+    def test_bulk_upload_rollback_on_failure(self, tmp_files):
+        """Bulk upload failure rolls back synced state so next sync retries."""
+        bulk_upload = MagicMock(side_effect=RuntimeError("upload failed"))
+        mgr = FileSyncManager(
+            get_files_fn=_make_get_files(tmp_files),
+            upload_fn=MagicMock(),
+            delete_fn=MagicMock(),
+            bulk_upload_fn=bulk_upload,
+        )
+
+        mgr.sync(force=True)  # fails, should rollback
+
+        # State rolled back: next sync should retry all files
+        bulk_upload.side_effect = None
+        bulk_upload.reset_mock()
+        mgr.sync(force=True)
+        bulk_upload.assert_called_once()
+        assert len(bulk_upload.call_args[0][0]) == 3