fix: unify reasoning_effort to config.yaml only, remove HERMES_REASONING_EFFORT env var

Gateway and cron had inconsistent reasoning_effort resolution:
- CLI: config.yaml only (correct)
- Gateway: config.yaml first, env var fallback
- Cron: env var first, config.yaml fallback

All three now read exclusively from agent.reasoning_effort in config.yaml.
Removed HERMES_REASONING_EFFORT env var support entirely — .env is for
secrets only, not behavioral config.

.github/workflows/tests.yml

@@ -19,6 +19,9 @@ jobs:
       - name: Checkout code
         uses: actions/checkout@v4
 
+      - name: Install system dependencies
+        run: sudo apt-get update && sudo apt-get install -y ripgrep
+
       - name: Install uv
         uses: astral-sh/setup-uv@v5
 

agent/anthropic_adapter.py

@@ -1224,9 +1224,9 @@ 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 models do NOT support extended thinking at all — skip entirely.
+    # Haiku and MiniMax models do 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():
+        if reasoning_config.get("enabled") is not False and "haiku" not in model.lower() and "minimax" 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

@@ -59,13 +59,48 @@ from hermes_constants import OPENROUTER_BASE_URL
 
 logger = logging.getLogger(__name__)
 
+_PROVIDER_ALIASES = {
+    "google": "gemini",
+    "google-gemini": "gemini",
+    "google-ai-studio": "gemini",
+    "glm": "zai",
+    "z-ai": "zai",
+    "z.ai": "zai",
+    "zhipu": "zai",
+    "kimi": "kimi-coding",
+    "moonshot": "kimi-coding",
+    "minimax-china": "minimax-cn",
+    "minimax_cn": "minimax-cn",
+    "claude": "anthropic",
+    "claude-code": "anthropic",
+}
+
+
+def _normalize_aux_provider(provider: Optional[str], *, for_vision: bool = False) -> str:
+    normalized = (provider or "auto").strip().lower()
+    if normalized.startswith("custom:"):
+        suffix = normalized.split(":", 1)[1].strip()
+        if not suffix:
+            return "custom"
+        normalized = suffix if not for_vision else "custom"
+    if normalized == "codex":
+        return "openai-codex"
+    if normalized == "main":
+        # Resolve to the user's actual main provider so named custom providers
+        # and non-aggregator providers (DeepSeek, Alibaba, etc.) work correctly.
+        main_prov = _read_main_provider()
+        if main_prov and main_prov not in ("auto", "main", ""):
+            return main_prov
+        return "custom"
+    return _PROVIDER_ALIASES.get(normalized, normalized)
+
 # Default auxiliary models for direct API-key providers (cheap/fast for side tasks)
 _API_KEY_PROVIDER_AUX_MODELS: Dict[str, str] = {
     "gemini": "gemini-3-flash-preview",
     "zai": "glm-4.5-flash",
     "kimi-coding": "kimi-k2-turbo-preview",
-    "minimax": "MiniMax-M2.7-highspeed",
-    "minimax-cn": "MiniMax-M2.7-highspeed",
+    "minimax": "MiniMax-M2.7",
+    "minimax-cn": "MiniMax-M2.7",
     "anthropic": "claude-haiku-4-5-20251001",
     "ai-gateway": "google/gemini-3-flash",
     "opencode-zen": "gemini-3-flash",
@@ -92,6 +127,7 @@ auxiliary_is_nous: bool = False
 _OPENROUTER_MODEL = "google/gemini-3-flash-preview"
 _NOUS_MODEL = "google/gemini-3-flash-preview"
 _NOUS_FREE_TIER_VISION_MODEL = "xiaomi/mimo-v2-omni"
+_NOUS_FREE_TIER_AUX_MODEL = "xiaomi/mimo-v2-pro"
 _NOUS_DEFAULT_BASE_URL = "https://inference-api.nousresearch.com/v1"
 _ANTHROPIC_DEFAULT_BASE_URL = "https://api.anthropic.com"
 _AUTH_JSON_PATH = get_hermes_home() / "auth.json"
@@ -105,6 +141,23 @@ _CODEX_AUX_MODEL = "gpt-5.2-codex"
 _CODEX_AUX_BASE_URL = "https://chatgpt.com/backend-api/codex"
 
 
+def _to_openai_base_url(base_url: str) -> str:
+    """Normalize an Anthropic-style base URL to OpenAI-compatible format.
+
+    Some providers (MiniMax, MiniMax-CN) expose an ``/anthropic`` endpoint for
+    the Anthropic Messages API and a separate ``/v1`` endpoint for OpenAI chat
+    completions.  The auxiliary client uses the OpenAI SDK, so it must hit the
+    ``/v1`` surface.  Passing the raw ``inference_base_url`` causes requests to
+    land on ``/anthropic/chat/completions`` — a 404.
+    """
+    url = str(base_url or "").strip().rstrip("/")
+    if url.endswith("/anthropic"):
+        rewritten = url[: -len("/anthropic")] + "/v1"
+        logger.debug("Auxiliary client: rewrote base URL %s → %s", url, rewritten)
+        return rewritten
+    return url
+
+
 def _select_pool_entry(provider: str) -> Tuple[bool, Optional[Any]]:
     """Return (pool_exists_for_provider, selected_entry)."""
     try:
@@ -634,7 +687,9 @@ def _resolve_api_key_provider() -> Tuple[Optional[OpenAI], Optional[str]]:
             if not api_key:
                 continue
 
-            base_url = _pool_runtime_base_url(entry, pconfig.inference_base_url) or pconfig.inference_base_url
+            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")
             logger.debug("Auxiliary text client: %s (%s) via pool", pconfig.name, model)
             extra = {}
@@ -651,7 +706,9 @@ def _resolve_api_key_provider() -> Tuple[Optional[OpenAI], Optional[str]]:
         if not api_key:
             continue
 
-        base_url = str(creds.get("base_url", "")).strip().rstrip("/") or pconfig.inference_base_url
+        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")
         logger.debug("Auxiliary text client: %s (%s)", pconfig.name, model)
         extra = {}
@@ -713,7 +770,7 @@ def _try_openrouter() -> Tuple[Optional[OpenAI], Optional[str]]:
                    default_headers=_OR_HEADERS), _OPENROUTER_MODEL
 
 
-def _try_nous() -> Tuple[Optional[OpenAI], Optional[str]]:
+def _try_nous(vision: bool = False) -> Tuple[Optional[OpenAI], Optional[str]]:
     nous = _read_nous_auth()
     if not nous:
         return None, None
@@ -725,12 +782,13 @@ def _try_nous() -> Tuple[Optional[OpenAI], Optional[str]]:
     else:
         model = _NOUS_MODEL
     # Free-tier users can't use paid auxiliary models — use the free
-    # multimodal model instead so vision/browser-vision still works.
+    # models instead: mimo-v2-omni for vision, mimo-v2-pro for text tasks.
     try:
         from hermes_cli.models import check_nous_free_tier
         if check_nous_free_tier():
-            model = _NOUS_FREE_TIER_VISION_MODEL
-            logger.debug("Free-tier Nous account — using %s for auxiliary/vision", model)
+            model = _NOUS_FREE_TIER_VISION_MODEL if vision else _NOUS_FREE_TIER_AUX_MODEL
+            logger.debug("Free-tier Nous account — using %s for auxiliary/%s",
+                         model, "vision" if vision else "text")
     except Exception:
         pass
     return (
@@ -776,7 +834,7 @@ def _read_main_provider() -> str:
         if isinstance(model_cfg, dict):
             provider = model_cfg.get("provider", "")
             if isinstance(provider, str) and provider.strip():
-                return provider.strip().lower()
+                return _normalize_aux_provider(provider)
     except Exception:
         pass
     return ""
@@ -1138,11 +1196,7 @@ def resolve_provider_client(
         (client, resolved_model) or (None, None) if auth is unavailable.
     """
     # Normalise aliases
-    provider = (provider or "auto").strip().lower()
-    if provider == "codex":
-        provider = "openai-codex"
-    if provider == "main":
-        provider = "custom"
+    provider = _normalize_aux_provider(provider)
 
     # ── Auto: try all providers in priority order ────────────────────
     if provider == "auto":
@@ -1238,6 +1292,28 @@ def resolve_provider_client(
                        "but no endpoint credentials found")
         return None, None
 
+    # ── Named custom providers (config.yaml custom_providers list) ───
+    try:
+        from hermes_cli.runtime_provider import _get_named_custom_provider
+        custom_entry = _get_named_custom_provider(provider)
+        if custom_entry:
+            custom_base = custom_entry.get("base_url", "").strip()
+            custom_key = custom_entry.get("api_key", "").strip() or "no-key-required"
+            if custom_base:
+                final_model = model or _read_main_model() or "gpt-4o-mini"
+                client = OpenAI(api_key=custom_key, base_url=custom_base)
+                logger.debug(
+                    "resolve_provider_client: named custom provider %r (%s)",
+                    provider, final_model)
+                return (_to_async_client(client, final_model) if async_mode
+                        else (client, final_model))
+            logger.warning(
+                "resolve_provider_client: named custom provider %r has no base_url",
+                provider)
+            return None, None
+    except ImportError:
+        pass
+
     # ── API-key providers from PROVIDER_REGISTRY ─────────────────────
     try:
         from hermes_cli.auth import PROVIDER_REGISTRY, resolve_api_key_provider_credentials
@@ -1270,7 +1346,9 @@ def resolve_provider_client(
                          provider, ", ".join(tried_sources))
             return None, None
 
-        base_url = str(creds.get("base_url", "")).strip().rstrip("/") or pconfig.inference_base_url
+        base_url = _to_openai_base_url(
+            str(creds.get("base_url", "")).strip().rstrip("/") or pconfig.inference_base_url
+        )
 
         default_model = _API_KEY_PROVIDER_AUX_MODELS.get(provider, "")
         final_model = model or default_model
@@ -1347,19 +1425,11 @@ def get_async_text_auxiliary_client(task: str = ""):
 _VISION_AUTO_PROVIDER_ORDER = (
     "openrouter",
     "nous",
-    "openai-codex",
-    "anthropic",
-    "custom",
 )
 
 
 def _normalize_vision_provider(provider: Optional[str]) -> str:
-    provider = (provider or "auto").strip().lower()
-    if provider == "codex":
-        return "openai-codex"
-    if provider == "main":
-        return "custom"
-    return provider
+    return _normalize_aux_provider(provider, for_vision=True)
 
 
 def _resolve_strict_vision_backend(provider: str) -> Tuple[Optional[Any], Optional[str]]:
@@ -1367,7 +1437,7 @@ def _resolve_strict_vision_backend(provider: str) -> Tuple[Optional[Any], Option
     if provider == "openrouter":
         return _try_openrouter()
     if provider == "nous":
-        return _try_nous()
+        return _try_nous(vision=True)
     if provider == "openai-codex":
         return _try_codex()
     if provider == "anthropic":
@@ -1400,17 +1470,20 @@ def _preferred_main_vision_provider() -> Optional[str]:
 def get_available_vision_backends() -> List[str]:
     """Return the currently available vision backends in auto-selection order.
 
-    This is the single source of truth for setup, tool gating, and runtime
-    auto-routing of vision tasks. The selected main provider is preferred when
-    it is also a known-good vision backend; otherwise Hermes falls back through
-    the standard conservative order.
+    Order: OpenRouter → Nous → active provider.  This is the single source
+    of truth for setup, tool gating, and runtime auto-routing of vision tasks.
     """
-    ordered = list(_VISION_AUTO_PROVIDER_ORDER)
-    preferred = _preferred_main_vision_provider()
-    if preferred in ordered:
-        ordered.remove(preferred)
-        ordered.insert(0, preferred)
-    return [provider for provider in ordered if _strict_vision_backend_available(provider)]
+    available = [p for p in _VISION_AUTO_PROVIDER_ORDER
+                 if _strict_vision_backend_available(p)]
+    # Also check the user's active provider (may be DeepSeek, Alibaba, named
+    # custom, etc.) — resolve_provider_client handles all provider types.
+    main_provider = _read_main_provider()
+    if (main_provider and main_provider not in ("auto", "")
+            and main_provider not in available):
+        client, _ = resolve_provider_client(main_provider, _read_main_model())
+        if client is not None:
+            available.append(main_provider)
+    return available
 
 
 def resolve_vision_provider_client(
@@ -1455,16 +1528,30 @@ def resolve_vision_provider_client(
         return "custom", client, final_model
 
     if requested == "auto":
-        ordered = list(_VISION_AUTO_PROVIDER_ORDER)
-        preferred = _preferred_main_vision_provider()
-        if preferred in ordered:
-            ordered.remove(preferred)
-            ordered.insert(0, preferred)
-
-        for candidate in ordered:
+        # Vision auto-detection order:
+        #   1. OpenRouter  (known vision-capable default model)
+        #   2. Nous Portal (known vision-capable default model)
+        #   3. Active provider + model (user's main chat config)
+        #   4. Stop
+        for candidate in _VISION_AUTO_PROVIDER_ORDER:
             sync_client, default_model = _resolve_strict_vision_backend(candidate)
             if sync_client is not None:
                 return _finalize(candidate, sync_client, default_model)
+
+        # Fall back to the user's active provider + model.
+        main_provider = _read_main_provider()
+        main_model = _read_main_model()
+        if main_provider and main_provider not in ("auto", ""):
+            sync_client, resolved_model = resolve_provider_client(
+                main_provider, main_model)
+            if sync_client is not None:
+                logger.info(
+                    "Vision auto-detect: using active provider %s (%s)",
+                    main_provider, resolved_model or main_model,
+                )
+                return _finalize(
+                    main_provider, sync_client, resolved_model or main_model)
+
         logger.debug("Auxiliary vision client: none available")
         return None, None, None
 

agent/model_metadata.py

@@ -113,8 +113,15 @@ DEFAULT_CONTEXT_LENGTHS = {
     "llama": 131072,
     # Qwen
     "qwen": 131072,
-    # MiniMax
-    "minimax": 204800,
+    # 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,
     # GLM
     "glm": 202752,
     # Kimi
@@ -127,7 +134,7 @@ DEFAULT_CONTEXT_LENGTHS = {
     "deepseek-ai/DeepSeek-V3.2": 65536,
     "moonshotai/Kimi-K2.5": 262144,
     "moonshotai/Kimi-K2-Thinking": 262144,
-    "MiniMaxAI/MiniMax-M2.5": 204800,
+    "minimaxai/minimax-m2.5": 1048576,
     "XiaomiMiMo/MiMo-V2-Flash": 32768,
     "mimo-v2-pro": 1048576,
     "mimo-v2-omni": 1048576,
@@ -611,6 +618,59 @@ def _model_id_matches(candidate_id: str, lookup_model: str) -> bool:
     return False
 
 
+def query_ollama_num_ctx(model: str, base_url: str) -> Optional[int]:
+    """Query an Ollama server for the model's context length.
+
+    Returns the model's maximum context from GGUF metadata via ``/api/show``,
+    or the explicit ``num_ctx`` from the Modelfile if set.  Returns None if
+    the server is unreachable or not Ollama.
+
+    This is the value that should be passed as ``num_ctx`` in Ollama chat
+    requests to override the default 2048.
+    """
+    import httpx
+
+    bare_model = _strip_provider_prefix(model)
+    server_url = base_url.rstrip("/")
+    if server_url.endswith("/v1"):
+        server_url = server_url[:-3]
+
+    try:
+        server_type = detect_local_server_type(base_url)
+    except Exception:
+        return None
+    if server_type != "ollama":
+        return None
+
+    try:
+        with httpx.Client(timeout=3.0) as client:
+            resp = client.post(f"{server_url}/api/show", json={"name": bare_model})
+            if resp.status_code != 200:
+                return None
+            data = resp.json()
+
+            # Prefer explicit num_ctx from Modelfile parameters (user override)
+            params = data.get("parameters", "")
+            if "num_ctx" in params:
+                for line in params.split("\n"):
+                    if "num_ctx" in line:
+                        parts = line.strip().split()
+                        if len(parts) >= 2:
+                            try:
+                                return int(parts[-1])
+                            except ValueError:
+                                pass
+
+            # Fall back to GGUF model_info context_length (training max)
+            model_info = data.get("model_info", {})
+            for key, value in model_info.items():
+                if "context_length" in key and isinstance(value, (int, float)):
+                    return int(value)
+    except Exception:
+        pass
+    return None
+
+
 def _query_local_context_length(model: str, base_url: str) -> Optional[int]:
     """Query a local server for the model's context length."""
     import httpx

agent/retry_utils.py

@@ -0,0 +1,57 @@
+"""Retry utilities — jittered backoff for decorrelated retries.
+
+Replaces fixed exponential backoff with jittered delays to prevent
+thundering-herd retry spikes when multiple sessions hit the same
+rate-limited provider concurrently.
+"""
+
+import random
+import threading
+import time
+
+# Monotonic counter for jitter seed uniqueness within the same process.
+# Protected by a lock to avoid race conditions in concurrent retry paths
+# (e.g. multiple gateway sessions retrying simultaneously).
+_jitter_counter = 0
+_jitter_lock = threading.Lock()
+
+
+def jittered_backoff(
+    attempt: int,
+    *,
+    base_delay: float = 5.0,
+    max_delay: float = 120.0,
+    jitter_ratio: float = 0.5,
+) -> float:
+    """Compute a jittered exponential backoff delay.
+
+    Args:
+        attempt: 1-based retry attempt number.
+        base_delay: Base delay in seconds for attempt 1.
+        max_delay: Maximum delay cap in seconds.
+        jitter_ratio: Fraction of computed delay to use as random jitter
+            range.  0.5 means jitter is uniform in [0, 0.5 * delay].
+
+    Returns:
+        Delay in seconds: min(base * 2^(attempt-1), max_delay) + jitter.
+
+    The jitter decorrelates concurrent retries so multiple sessions
+    hitting the same provider don't all retry at the same instant.
+    """
+    global _jitter_counter
+    with _jitter_lock:
+        _jitter_counter += 1
+        tick = _jitter_counter
+
+    exponent = max(0, attempt - 1)
+    if exponent >= 63 or base_delay <= 0:
+        delay = max_delay
+    else:
+        delay = min(base_delay * (2 ** exponent), max_delay)
+
+    # Seed from time + counter for decorrelation even with coarse clocks.
+    seed = (time.time_ns() ^ (tick * 0x9E3779B9)) & 0xFFFFFFFF
+    rng = random.Random(seed)
+    jitter = rng.uniform(0, jitter_ratio * delay)
+
+    return delay + jitter

cli.py

@@ -63,7 +63,7 @@ from agent.usage_pricing import (
     format_duration_compact,
     format_token_count_compact,
 )
-from hermes_cli.banner import _format_context_length
+from hermes_cli.banner import _format_context_length, format_banner_version_label
 
 _COMMAND_SPINNER_FRAMES = ("⠋", "⠙", "⠹", "⠸", "⠼", "⠴", "⠦", "⠧", "⠇", "⠏")
 
@@ -1036,21 +1036,44 @@ COMPACT_BANNER = """
 
 def _build_compact_banner() -> str:
     """Build a compact banner that fits the current terminal width."""
-    w = min(shutil.get_terminal_size().columns - 2, 64)
+    try:
+        from hermes_cli.skin_engine import get_active_skin
+        _skin = get_active_skin()
+    except Exception:
+        _skin = None
+
+    skin_name = getattr(_skin, "name", "default") if _skin else "default"
+    border_color = _skin.get_color("banner_border", "#FFD700") if _skin else "#FFD700"
+    title_color = _skin.get_color("banner_title", "#FFBF00") if _skin else "#FFBF00"
+    dim_color = _skin.get_color("banner_dim", "#B8860B") if _skin else "#B8860B"
+
+    if skin_name == "default":
+        line1 = "⚕ NOUS HERMES - AI Agent Framework"
+        tiny_line = "⚕ NOUS HERMES"
+    else:
+        agent_name = _skin.get_branding("agent_name", "Hermes Agent") if _skin else "Hermes Agent"
+        line1 = f"{agent_name} - AI Agent Framework"
+        tiny_line = agent_name
+
+    version_line = format_banner_version_label()
+
+    w = min(shutil.get_terminal_size().columns - 2, 88)
     if w < 30:
-        return "\n[#FFBF00]⚕ NOUS HERMES[/] [dim #B8860B]- Nous Research[/]\n"
+        return f"\n[{title_color}]{tiny_line}[/] [dim {dim_color}]- Nous Research[/]\n"
+
     inner = w - 2  # inside the box border
     bar = "═" * w
-    line1 = "⚕ NOUS HERMES - AI Agent Framework"
-    line2 = "Messenger of the Digital Gods  ·  Nous Research"
+    content_width = inner - 2
+
     # Truncate and pad to fit
-    line1 = line1[:inner - 2].ljust(inner - 2)
-    line2 = line2[:inner - 2].ljust(inner - 2)
+    line1 = line1[:content_width].ljust(content_width)
+    line2 = version_line[:content_width].ljust(content_width)
+
     return (
-        f"\n[bold #FFD700]╔{bar}╗[/]\n"
-        f"[bold #FFD700]║[/] [#FFBF00]{line1}[/] [bold #FFD700]║[/]\n"
-        f"[bold #FFD700]║[/] [dim #B8860B]{line2}[/] [bold #FFD700]║[/]\n"
-        f"[bold #FFD700]╚{bar}╝[/]\n"
+        f"\n[bold {border_color}]╔{bar}╗[/]\n"
+        f"[bold {border_color}]║[/] [{title_color}]{line1}[/] [bold {border_color}]║[/]\n"
+        f"[bold {border_color}]║[/] [dim {dim_color}]{line2}[/] [bold {border_color}]║[/]\n"
+        f"[bold {border_color}]╚{bar}╝[/]\n"
     )
 
 
@@ -2163,7 +2186,7 @@ class HermesCLI:
             )
         except Exception as exc:
             message = format_runtime_provider_error(exc)
-            self.console.print(f"[bold red]{message}[/]")
+            ChatConsole().print(f"[bold red]{message}[/]")
             return False
 
         api_key = runtime.get("api_key")
@@ -2378,7 +2401,7 @@ class HermesCLI:
                     self._pending_title = None
             return True
         except Exception as e:
-            self.console.print(f"[bold red]Failed to initialize agent: {e}[/]")
+            ChatConsole().print(f"[bold red]Failed to initialize agent: {e}[/]")
             return False
     
     def show_banner(self):
@@ -4530,13 +4553,13 @@ class HermesCLI:
                             if output:
                                 self.console.print(_rich_text_from_ansi(output))
                             else:
-                                self.console.print("[dim]Command returned no output[/]")
+                                ChatConsole().print("[dim]Command returned no output[/]")
                         except subprocess.TimeoutExpired:
-                            self.console.print("[bold red]Quick command timed out (30s)[/]")
+                            ChatConsole().print("[bold red]Quick command timed out (30s)[/]")
                         except Exception as e:
-                            self.console.print(f"[bold red]Quick command error: {e}[/]")
+                            ChatConsole().print(f"[bold red]Quick command error: {e}[/]")
                     else:
-                        self.console.print(f"[bold red]Quick command '{base_cmd}' has no command defined[/]")
+                        ChatConsole().print(f"[bold red]Quick command '{base_cmd}' has no command defined[/]")
                 elif qcmd.get("type") == "alias":
                     target = qcmd.get("target", "").strip()
                     if target:
@@ -4545,9 +4568,9 @@ class HermesCLI:
                         aliased_command = f"{target} {user_args}".strip()
                         return self.process_command(aliased_command)
                     else:
-                        self.console.print(f"[bold red]Quick command '{base_cmd}' has no target defined[/]")
+                        ChatConsole().print(f"[bold red]Quick command '{base_cmd}' has no target defined[/]")
                 else:
-                    self.console.print(f"[bold red]Quick command '{base_cmd}' has unsupported type (supported: 'exec', 'alias')[/]")
+                    ChatConsole().print(f"[bold red]Quick command '{base_cmd}' has unsupported type (supported: 'exec', 'alias')[/]")
             # Check for plugin-registered slash commands
             elif base_cmd.lstrip("/") in _get_plugin_cmd_handler_names():
                 from hermes_cli.plugins import get_plugin_command_handler
@@ -4572,7 +4595,7 @@ class HermesCLI:
                     if hasattr(self, '_pending_input'):
                         self._pending_input.put(msg)
                 else:
-                    self.console.print(f"[bold red]Failed to load skill for {base_cmd}[/]")
+                    ChatConsole().print(f"[bold red]Failed to load skill for {base_cmd}[/]")
             else:
                 # Prefix matching: if input uniquely identifies one command, execute it.
                 # Matches against both built-in COMMANDS and installed skill commands so
@@ -4633,14 +4656,14 @@ class HermesCLI:
         )
 
         if not msg:
-            self.console.print("[bold red]Failed to load the bundled /plan skill[/]")
+            ChatConsole().print("[bold red]Failed to load the bundled /plan skill[/]")
             return
 
         _cprint(f"  📝 Plan mode queued via skill. Markdown plan target: {plan_path}")
         if hasattr(self, '_pending_input'):
             self._pending_input.put(msg)
         else:
-            self.console.print("[bold red]Plan mode unavailable: input queue not initialized[/]")
+            ChatConsole().print("[bold red]Plan mode unavailable: input queue not initialized[/]")
     
     def _handle_background_command(self, cmd: str):
         """Handle /background <prompt> — run a prompt in a separate background session.

cron/jobs.py

@@ -574,12 +574,16 @@ def remove_job(job_id: str) -> bool:
     return False
 
 
-def mark_job_run(job_id: str, success: bool, error: Optional[str] = None):
+def mark_job_run(job_id: str, success: bool, error: Optional[str] = None,
+                 delivery_error: Optional[str] = None):
     """
     Mark a job as having been run.
     
     Updates last_run_at, last_status, increments completed count,
     computes next_run_at, and auto-deletes if repeat limit reached.
+
+    ``delivery_error`` is tracked separately from the agent error — a job
+    can succeed (agent produced output) but fail delivery (platform down).
     """
     jobs = load_jobs()
     for i, job in enumerate(jobs):
@@ -588,6 +592,8 @@ def mark_job_run(job_id: str, success: bool, error: Optional[str] = None):
             job["last_run_at"] = now
             job["last_status"] = "ok" if success else "error"
             job["last_error"] = error if not success else None
+            # Track delivery failures separately — cleared on successful delivery
+            job["last_delivery_error"] = delivery_error
             
             # Increment completed count
             if job.get("repeat"):

cron/scheduler.py

@@ -196,7 +196,7 @@ def _send_media_via_adapter(adapter, chat_id: str, media_files: list, metadata:
             logger.warning("Job '%s': failed to send media %s: %s", job.get("id", "?"), media_path, e)
 
 
-def _deliver_result(job: dict, content: str, adapters=None, loop=None) -> None:
+def _deliver_result(job: dict, content: str, adapters=None, loop=None) -> Optional[str]:
     """
     Deliver job output to the configured target (origin chat, specific platform, etc.).
 
@@ -204,16 +204,16 @@ def _deliver_result(job: dict, content: str, adapters=None, loop=None) -> None:
     use the live adapter first — this supports E2EE rooms (e.g. Matrix) where
     the standalone HTTP path cannot encrypt.  Falls back to standalone send if
     the adapter path fails or is unavailable.
+
+    Returns None on success, or an error string on failure.
     """
     target = _resolve_delivery_target(job)
     if not target:
         if job.get("deliver", "local") != "local":
-            logger.warning(
-                "Job '%s' deliver=%s but no concrete delivery target could be resolved",
-                job["id"],
-                job.get("deliver", "local"),
-            )
-        return
+            msg = f"no delivery target resolved for deliver={job.get('deliver', 'local')}"
+            logger.warning("Job '%s': %s", job["id"], msg)
+            return msg
+        return None  # local-only jobs don't deliver — not a failure
 
     platform_name = target["platform"]
     chat_id = target["chat_id"]
@@ -239,19 +239,22 @@ def _deliver_result(job: dict, content: str, adapters=None, loop=None) -> None:
     }
     platform = platform_map.get(platform_name.lower())
     if not platform:
-        logger.warning("Job '%s': unknown platform '%s' for delivery", job["id"], platform_name)
-        return
+        msg = f"unknown platform '{platform_name}'"
+        logger.warning("Job '%s': %s", job["id"], msg)
+        return msg
 
     try:
         config = load_gateway_config()
     except Exception as e:
-        logger.error("Job '%s': failed to load gateway config for delivery: %s", job["id"], e)
-        return
+        msg = f"failed to load gateway config: {e}"
+        logger.error("Job '%s': %s", job["id"], msg)
+        return msg
 
     pconfig = config.platforms.get(platform)
     if not pconfig or not pconfig.enabled:
-        logger.warning("Job '%s': platform '%s' not configured/enabled", job["id"], platform_name)
-        return
+        msg = f"platform '{platform_name}' not configured/enabled"
+        logger.warning("Job '%s': %s", job["id"], msg)
+        return msg
 
     # Optionally wrap the content with a header/footer so the user knows this
     # is a cron delivery.  Wrapping is on by default; set cron.wrap_response: false
@@ -307,7 +310,7 @@ def _deliver_result(job: dict, content: str, adapters=None, loop=None) -> None:
 
             if adapter_ok:
                 logger.info("Job '%s': delivered to %s:%s via live adapter", job["id"], platform_name, chat_id)
-                return
+                return None
         except Exception as e:
             logger.warning(
                 "Job '%s': live adapter delivery to %s:%s failed (%s), falling back to standalone",
@@ -329,13 +332,17 @@ def _deliver_result(job: dict, content: str, adapters=None, loop=None) -> None:
             future = pool.submit(asyncio.run, _send_to_platform(platform, pconfig, chat_id, cleaned_delivery_content, thread_id=thread_id, media_files=media_files))
             result = future.result(timeout=30)
     except Exception as e:
-        logger.error("Job '%s': delivery to %s:%s failed: %s", job["id"], platform_name, chat_id, e)
-        return
+        msg = f"delivery to {platform_name}:{chat_id} failed: {e}"
+        logger.error("Job '%s': %s", job["id"], msg)
+        return msg
 
     if result and result.get("error"):
-        logger.error("Job '%s': delivery error: %s", job["id"], result["error"])
-    else:
-        logger.info("Job '%s': delivered to %s:%s", job["id"], platform_name, chat_id)
+        msg = f"delivery error: {result['error']}"
+        logger.error("Job '%s': %s", job["id"], msg)
+        return msg
+
+    logger.info("Job '%s': delivered to %s:%s", job["id"], platform_name, chat_id)
+    return None
 
 
 _SCRIPT_TIMEOUT = 120  # seconds
@@ -578,11 +585,9 @@ def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:
         except Exception as e:
             logger.warning("Job '%s': failed to load config.yaml, using defaults: %s", job_id, e)
 
-        # Reasoning config from env or config.yaml
+        # Reasoning config from config.yaml
         from hermes_constants import parse_reasoning_effort
-        effort = os.getenv("HERMES_REASONING_EFFORT", "")
-        if not effort:
-            effort = str(_cfg.get("agent", {}).get("reasoning_effort", "")).strip()
+        effort = str(_cfg.get("agent", {}).get("reasoning_effort", "")).strip()
         reasoning_config = parse_reasoning_effort(effort)
 
         # Prefill messages from env or config.yaml
@@ -868,13 +873,15 @@ def tick(verbose: bool = True, adapters=None, loop=None) -> int:
                     logger.info("Job '%s': agent returned %s — skipping delivery", job["id"], SILENT_MARKER)
                     should_deliver = False
 
+                delivery_error = None
                 if should_deliver:
                     try:
-                        _deliver_result(job, deliver_content, adapters=adapters, loop=loop)
+                        delivery_error = _deliver_result(job, deliver_content, adapters=adapters, loop=loop)
                     except Exception as de:
+                        delivery_error = str(de)
                         logger.error("Delivery failed for job %s: %s", job["id"], de)
 
-                mark_job_run(job["id"], success, error)
+                mark_job_run(job["id"], success, error, delivery_error=delivery_error)
                 executed += 1
 
             except Exception as e:

environments/agent_loop.py

@@ -21,6 +21,8 @@ from dataclasses import dataclass, field
 from typing import Any, Dict, List, Optional, Set
 
 from model_tools import handle_function_call
+from tools.terminal_tool import get_active_env
+from tools.tool_result_storage import maybe_persist_tool_result, enforce_turn_budget
 
 # Thread pool for running sync tool calls that internally use asyncio.run()
 # (e.g., the Modal/Docker/Daytona terminal backends). Running them in a separate
@@ -138,6 +140,7 @@ class HermesAgentLoop:
         temperature: float = 1.0,
         max_tokens: Optional[int] = None,
         extra_body: Optional[Dict[str, Any]] = None,
+        budget_config: Optional["BudgetConfig"] = None,
     ):
         """
         Initialize the agent loop.
@@ -154,7 +157,11 @@ class HermesAgentLoop:
             extra_body: Extra parameters passed to the OpenAI client's create() call.
                         Used for OpenRouter provider preferences, transforms, etc.
                         e.g. {"provider": {"ignore": ["DeepInfra"]}}
+            budget_config: Tool result persistence budget. Controls per-tool
+                        thresholds, per-turn aggregate budget, and preview size.
+                        If None, uses DEFAULT_BUDGET (current hardcoded values).
         """
+        from tools.budget_config import DEFAULT_BUDGET
         self.server = server
         self.tool_schemas = tool_schemas
         self.valid_tool_names = valid_tool_names
@@ -163,6 +170,7 @@ class HermesAgentLoop:
         self.temperature = temperature
         self.max_tokens = max_tokens
         self.extra_body = extra_body
+        self.budget_config = budget_config or DEFAULT_BUDGET
 
     async def run(self, messages: List[Dict[str, Any]]) -> AgentResult:
         """
@@ -446,8 +454,15 @@ class HermesAgentLoop:
                         except (json.JSONDecodeError, TypeError):
                             pass
 
-                    # Add tool response to conversation
                     tc_id = tc.get("id", "") if isinstance(tc, dict) else tc.id
+                    tool_result = maybe_persist_tool_result(
+                        content=tool_result,
+                        tool_name=tool_name,
+                        tool_use_id=tc_id,
+                        env=get_active_env(self.task_id),
+                        config=self.budget_config,
+                    )
+
                     messages.append(
                         {
                             "role": "tool",
@@ -456,6 +471,14 @@ class HermesAgentLoop:
                         }
                     )
 
+                num_tcs = len(assistant_msg.tool_calls)
+                if num_tcs > 0:
+                    enforce_turn_budget(
+                        messages[-num_tcs:],
+                        env=get_active_env(self.task_id),
+                        config=self.budget_config,
+                    )
+
                 turn_elapsed = _time.monotonic() - turn_start
                 logger.info(
                     "[%s] turn %d: api=%.1fs, %d tools, turn_total=%.1fs",

environments/agentic_opd_env.py

@@ -1048,6 +1048,7 @@ class AgenticOPDEnv(HermesAgentBaseEnv):
                     temperature=0.0,
                     max_tokens=self.config.max_token_length,
                     extra_body=self.config.extra_body,
+                    budget_config=self.config.build_budget_config(),
                 )
                 result = await agent.run(messages)
 

environments/benchmarks/terminalbench_2/terminalbench2_env.py

@@ -44,7 +44,7 @@ import tempfile
 import time
 import uuid
 from collections import defaultdict
-from pathlib import Path
+from pathlib import Path, PurePosixPath, PureWindowsPath
 from typing import Any, Dict, List, Optional, Tuple, Union
 
 # Ensure repo root is on sys.path for imports
@@ -148,6 +148,62 @@ MODAL_INCOMPATIBLE_TASKS = {
 # Tar extraction helper
 # =============================================================================
 
+def _normalize_tar_member_parts(member_name: str) -> list:
+    """Return safe path components for a tar member or raise ValueError."""
+    normalized_name = member_name.replace("\\", "/")
+    posix_path = PurePosixPath(normalized_name)
+    windows_path = PureWindowsPath(member_name)
+
+    if (
+        not normalized_name
+        or posix_path.is_absolute()
+        or windows_path.is_absolute()
+        or windows_path.drive
+    ):
+        raise ValueError(f"Unsafe archive member path: {member_name}")
+
+    parts = [part for part in posix_path.parts if part not in ("", ".")]
+    if not parts or any(part == ".." for part in parts):
+        raise ValueError(f"Unsafe archive member path: {member_name}")
+    return parts
+
+
+def _safe_extract_tar(tar: tarfile.TarFile, target_dir: Path) -> None:
+    """Extract a tar archive without allowing traversal or link entries."""
+    target_dir.mkdir(parents=True, exist_ok=True)
+    target_root = target_dir.resolve()
+
+    for member in tar.getmembers():
+        parts = _normalize_tar_member_parts(member.name)
+        target = target_dir.joinpath(*parts)
+        target_real = target.resolve(strict=False)
+
+        try:
+            target_real.relative_to(target_root)
+        except ValueError as exc:
+            raise ValueError(f"Unsafe archive member path: {member.name}") from exc
+
+        if member.isdir():
+            target_real.mkdir(parents=True, exist_ok=True)
+            continue
+
+        if not member.isfile():
+            raise ValueError(f"Unsupported archive member type: {member.name}")
+
+        target_real.parent.mkdir(parents=True, exist_ok=True)
+        extracted = tar.extractfile(member)
+        if extracted is None:
+            raise ValueError(f"Cannot read archive member: {member.name}")
+
+        with extracted, open(target_real, "wb") as dst:
+            shutil.copyfileobj(extracted, dst)
+
+        try:
+            os.chmod(target_real, member.mode & 0o777)
+        except OSError:
+            pass
+
+
 def _extract_base64_tar(b64_data: str, target_dir: Path):
     """Extract a base64-encoded tar.gz archive into target_dir."""
     if not b64_data:
@@ -155,7 +211,7 @@ def _extract_base64_tar(b64_data: str, target_dir: Path):
     raw = base64.b64decode(b64_data)
     buf = io.BytesIO(raw)
     with tarfile.open(fileobj=buf, mode="r:gz") as tar:
-        tar.extractall(path=str(target_dir))
+        _safe_extract_tar(tar, target_dir)
 
 
 # =============================================================================
@@ -485,6 +541,7 @@ class TerminalBench2EvalEnv(HermesAgentBaseEnv):
                         temperature=self.config.agent_temperature,
                         max_tokens=self.config.max_token_length,
                         extra_body=self.config.extra_body,
+                        budget_config=self.config.build_budget_config(),
                     )
                     result = await agent.run(messages)
             else:
@@ -497,6 +554,7 @@ class TerminalBench2EvalEnv(HermesAgentBaseEnv):
                     temperature=self.config.agent_temperature,
                     max_tokens=self.config.max_token_length,
                     extra_body=self.config.extra_body,
+                    budget_config=self.config.build_budget_config(),
                 )
                 result = await agent.run(messages)
 

environments/benchmarks/yc_bench/yc_bench_env.py

@@ -549,6 +549,7 @@ class YCBenchEvalEnv(HermesAgentBaseEnv):
                 temperature=self.config.agent_temperature,
                 max_tokens=self.config.max_token_length,
                 extra_body=self.config.extra_body,
+                budget_config=self.config.build_budget_config(),
             )
             result = await agent.run(messages)
 

environments/hermes_base_env.py

@@ -62,6 +62,11 @@ from atroposlib.type_definitions import Item
 
 from environments.agent_loop import AgentResult, HermesAgentLoop
 from environments.tool_context import ToolContext
+from tools.budget_config import (
+    DEFAULT_RESULT_SIZE_CHARS,
+    DEFAULT_TURN_BUDGET_CHARS,
+    DEFAULT_PREVIEW_SIZE_CHARS,
+)
 
 # Import hermes-agent toolset infrastructure
 from model_tools import get_tool_definitions
@@ -160,6 +165,32 @@ class HermesAgentEnvConfig(BaseEnvConfig):
         "Options: hermes, mistral, llama3_json, qwen, deepseek_v3, etc.",
     )
 
+    # --- Tool result budget ---
+    # Defaults imported from tools.budget_config (single source of truth).
+    default_result_size_chars: int = Field(
+        default=DEFAULT_RESULT_SIZE_CHARS,
+        description="Default per-tool threshold (chars) for persisting large results "
+        "to sandbox. Results exceeding this are written to /tmp/hermes-results/ "
+        "and replaced with a preview. Per-tool registry values take precedence "
+        "unless overridden via tool_result_overrides.",
+    )
+    turn_budget_chars: int = Field(
+        default=DEFAULT_TURN_BUDGET_CHARS,
+        description="Aggregate char budget per assistant turn. If all tool results "
+        "in a single turn exceed this, the largest are persisted to disk first.",
+    )
+    preview_size_chars: int = Field(
+        default=DEFAULT_PREVIEW_SIZE_CHARS,
+        description="Size of the inline preview shown after a tool result is persisted.",
+    )
+    tool_result_overrides: Optional[Dict[str, int]] = Field(
+        default=None,
+        description="Per-tool threshold overrides (chars). Keys are tool names, "
+        "values are char thresholds. Overrides both the default and registry "
+        "per-tool values. Example: {'terminal': 10000, 'search_files': 5000}. "
+        "Note: read_file is pinned to infinity and cannot be overridden.",
+    )
+
     # --- Provider-specific parameters ---
     # Passed as extra_body to the OpenAI client's chat.completions.create() call.
     # Useful for OpenRouter provider preferences, transforms, route settings, etc.
@@ -176,6 +207,16 @@ class HermesAgentEnvConfig(BaseEnvConfig):
         "transforms, and other provider-specific settings.",
     )
 
+    def build_budget_config(self):
+        """Build a BudgetConfig from env config fields."""
+        from tools.budget_config import BudgetConfig
+        return BudgetConfig(
+            default_result_size=self.default_result_size_chars,
+            turn_budget=self.turn_budget_chars,
+            preview_size=self.preview_size_chars,
+            tool_overrides=dict(self.tool_result_overrides) if self.tool_result_overrides else {},
+        )
+
 
 class HermesAgentBaseEnv(BaseEnv):
     """
@@ -490,6 +531,7 @@ class HermesAgentBaseEnv(BaseEnv):
                         temperature=self.config.agent_temperature,
                         max_tokens=self.config.max_token_length,
                         extra_body=self.config.extra_body,
+                        budget_config=self.config.build_budget_config(),
                     )
                     result = await agent.run(messages)
             except NotImplementedError:
@@ -507,6 +549,7 @@ class HermesAgentBaseEnv(BaseEnv):
                     temperature=self.config.agent_temperature,
                     max_tokens=self.config.max_token_length,
                     extra_body=self.config.extra_body,
+                    budget_config=self.config.build_budget_config(),
                 )
                 result = await agent.run(messages)
         else:
@@ -520,6 +563,7 @@ class HermesAgentBaseEnv(BaseEnv):
                 temperature=self.config.agent_temperature,
                 max_tokens=self.config.max_token_length,
                 extra_body=self.config.extra_body,
+                budget_config=self.config.build_budget_config(),
             )
             result = await agent.run(messages)
 

environments/web_research_env.py

@@ -472,6 +472,7 @@ class WebResearchEnv(HermesAgentBaseEnv):
                     temperature=0.0,  # Deterministic for eval
                     max_tokens=self.config.max_token_length,
                     extra_body=self.config.extra_body,
+                    budget_config=self.config.build_budget_config(),
                 )
                 result = await agent.run(messages)
 

gateway/config.py

@@ -556,6 +556,18 @@ def load_gateway_config() -> GatewayConfig:
                     os.environ["DISCORD_AUTO_THREAD"] = str(discord_cfg["auto_thread"]).lower()
                 if "reactions" in discord_cfg and not os.getenv("DISCORD_REACTIONS"):
                     os.environ["DISCORD_REACTIONS"] = str(discord_cfg["reactions"]).lower()
+                # ignored_channels: channels where bot never responds (even when mentioned)
+                ic = discord_cfg.get("ignored_channels")
+                if ic is not None and not os.getenv("DISCORD_IGNORED_CHANNELS"):
+                    if isinstance(ic, list):
+                        ic = ",".join(str(v) for v in ic)
+                    os.environ["DISCORD_IGNORED_CHANNELS"] = str(ic)
+                # no_thread_channels: channels where bot responds directly without creating thread
+                ntc = discord_cfg.get("no_thread_channels")
+                if ntc is not None and not os.getenv("DISCORD_NO_THREAD_CHANNELS"):
+                    if isinstance(ntc, list):
+                        ntc = ",".join(str(v) for v in ntc)
+                    os.environ["DISCORD_NO_THREAD_CHANNELS"] = str(ntc)
 
             # Telegram settings → env vars (env vars take precedence)
             telegram_cfg = yaml_cfg.get("telegram", {})
@@ -570,6 +582,8 @@ def load_gateway_config() -> GatewayConfig:
                     if isinstance(frc, list):
                         frc = ",".join(str(v) for v in frc)
                     os.environ["TELEGRAM_FREE_RESPONSE_CHATS"] = str(frc)
+                if "reactions" in telegram_cfg and not os.getenv("TELEGRAM_REACTIONS"):
+                    os.environ["TELEGRAM_REACTIONS"] = str(telegram_cfg["reactions"]).lower()
 
             whatsapp_cfg = yaml_cfg.get("whatsapp", {})
             if isinstance(whatsapp_cfg, dict):

gateway/platforms/api_server.py

@@ -20,6 +20,7 @@ Requires:
 """
 
 import asyncio
+import hmac
 import json
 import logging
 import os
@@ -370,7 +371,7 @@ class APIServerAdapter(BasePlatformAdapter):
         auth_header = request.headers.get("Authorization", "")
         if auth_header.startswith("Bearer "):
             token = auth_header[7:].strip()
-            if token == self._api_key:
+            if hmac.compare_digest(token, self._api_key):
                 return None  # Auth OK
 
         return web.json_response(
@@ -563,8 +564,10 @@ class APIServerAdapter(BasePlatformAdapter):
                 if delta is not None:
                     _stream_q.put(delta)
 
-            def _on_tool_progress(name, preview, args):
+            def _on_tool_progress(event_type, name, preview, args, **kwargs):
                 """Inject tool progress into the SSE stream for Open WebUI."""
+                if event_type != "tool.started":
+                    return  # Only show tool start events in chat stream
                 if name.startswith("_"):
                     return  # Skip internal events (_thinking)
                 from agent.display import get_tool_emoji
@@ -815,9 +818,29 @@ class APIServerAdapter(BasePlatformAdapter):
         else:
             return web.json_response(_openai_error("'input' must be a string or array"), status=400)
 
-        # Reconstruct conversation history from previous_response_id
+        # Accept explicit conversation_history from the request body.
+        # This lets stateless clients supply their own history instead of
+        # relying on server-side response chaining via previous_response_id.
+        # Precedence: explicit conversation_history > previous_response_id.
         conversation_history: List[Dict[str, str]] = []
-        if previous_response_id:
+        raw_history = body.get("conversation_history")
+        if raw_history:
+            if not isinstance(raw_history, list):
+                return web.json_response(
+                    _openai_error("'conversation_history' must be an array of message objects"),
+                    status=400,
+                )
+            for i, entry in enumerate(raw_history):
+                if not isinstance(entry, dict) or "role" not in entry or "content" not in entry:
+                    return web.json_response(
+                        _openai_error(f"conversation_history[{i}] must have 'role' and 'content' fields"),
+                        status=400,
+                    )
+                conversation_history.append({"role": str(entry["role"]), "content": str(entry["content"])})
+            if previous_response_id:
+                logger.debug("Both conversation_history and previous_response_id provided; using conversation_history")
+
+        if not conversation_history and previous_response_id:
             stored = self._response_store.get(previous_response_id)
             if stored is None:
                 return web.json_response(_openai_error(f"Previous response not found: {previous_response_id}"), status=404)
@@ -1403,14 +1426,49 @@ class APIServerAdapter(BasePlatformAdapter):
 
         instructions = body.get("instructions")
         previous_response_id = body.get("previous_response_id")
+
+        # Accept explicit conversation_history from the request body.
+        # Precedence: explicit conversation_history > previous_response_id.
         conversation_history: List[Dict[str, str]] = []
-        if previous_response_id:
+        raw_history = body.get("conversation_history")
+        if raw_history:
+            if not isinstance(raw_history, list):
+                return web.json_response(
+                    _openai_error("'conversation_history' must be an array of message objects"),
+                    status=400,
+                )
+            for i, entry in enumerate(raw_history):
+                if not isinstance(entry, dict) or "role" not in entry or "content" not in entry:
+                    return web.json_response(
+                        _openai_error(f"conversation_history[{i}] must have 'role' and 'content' fields"),
+                        status=400,
+                    )
+                conversation_history.append({"role": str(entry["role"]), "content": str(entry["content"])})
+            if previous_response_id:
+                logger.debug("Both conversation_history and previous_response_id provided; using conversation_history")
+
+        if not conversation_history and previous_response_id:
             stored = self._response_store.get(previous_response_id)
             if stored:
                 conversation_history = list(stored.get("conversation_history", []))
                 if instructions is None:
                     instructions = stored.get("instructions")
 
+        # When input is a multi-message array, extract all but the last
+        # message as conversation history (the last becomes user_message).
+        # Only fires when no explicit history was provided.
+        if not conversation_history and isinstance(raw_input, list) and len(raw_input) > 1:
+            for msg in raw_input[:-1]:
+                if isinstance(msg, dict) and msg.get("role") and msg.get("content"):
+                    content = msg["content"]
+                    if isinstance(content, list):
+                        # Flatten multi-part content blocks to text
+                        content = " ".join(
+                            part.get("text", "") for part in content
+                            if isinstance(part, dict) and part.get("type") == "text"
+                        )
+                    conversation_history.append({"role": msg["role"], "content": str(content)})
+
         session_id = body.get("session_id") or run_id
         ephemeral_system_prompt = instructions
 

gateway/platforms/base.py

@@ -124,7 +124,14 @@ async def cache_image_from_url(url: str, ext: str = ".jpg", retries: int = 2) ->
 
     Returns:
         Absolute path to the cached image file as a string.
+
+    Raises:
+        ValueError: If the URL targets a private/internal network (SSRF protection).
     """
+    from tools.url_safety import is_safe_url
+    if not is_safe_url(url):
+        raise ValueError(f"Blocked unsafe URL (SSRF protection): {_safe_url_for_log(url)}")
+
     import asyncio
     import httpx
     import logging as _logging
@@ -232,7 +239,14 @@ async def cache_audio_from_url(url: str, ext: str = ".ogg", retries: int = 2) ->
 
     Returns:
         Absolute path to the cached audio file as a string.
+
+    Raises:
+        ValueError: If the URL targets a private/internal network (SSRF protection).
     """
+    from tools.url_safety import is_safe_url
+    if not is_safe_url(url):
+        raise ValueError(f"Blocked unsafe URL (SSRF protection): {_safe_url_for_log(url)}")
+
     import asyncio
     import httpx
     import logging as _logging
@@ -1105,6 +1119,22 @@ class BasePlatformAdapter(ABC):
             logger.error("[%s] Fallback send also failed: %s", self.name, fallback_result.error)
         return fallback_result
 
+    @staticmethod
+    def _merge_caption(existing_text: Optional[str], new_text: str) -> str:
+        """Merge a new caption into existing text, avoiding duplicates.
+
+        Uses line-by-line exact match (not substring) to prevent false positives
+        where a shorter caption is silently dropped because it appears as a
+        substring of a longer one (e.g. "Meeting" inside "Meeting agenda").
+        Whitespace is normalised for comparison.
+        """
+        if not existing_text:
+            return new_text
+        existing_captions = [c.strip() for c in existing_text.split("\n\n")]
+        if new_text.strip() not in existing_captions:
+            return f"{existing_text}\n\n{new_text}".strip()
+        return existing_text
+
     async def handle_message(self, event: MessageEvent) -> None:
         """
         Process an incoming message.
@@ -1164,10 +1194,7 @@ class BasePlatformAdapter(ABC):
                     existing.media_urls.extend(event.media_urls)
                     existing.media_types.extend(event.media_types)
                     if event.text:
-                        if not existing.text:
-                            existing.text = event.text
-                        elif event.text not in existing.text:
-                            existing.text = f"{existing.text}\n\n{event.text}".strip()
+                        existing.text = self._merge_caption(existing.text, event.text)
                 else:
                     self._pending_messages[session_key] = event
                 return  # Don't interrupt now - will run after current task completes

gateway/platforms/discord.py

@@ -55,6 +55,7 @@ from gateway.platforms.base import (
     cache_document_from_bytes,
     SUPPORTED_DOCUMENT_TYPES,
 )
+from tools.url_safety import is_safe_url
 
 
 def _clean_discord_id(entry: str) -> str:
@@ -1285,6 +1286,10 @@ class DiscordAdapter(BasePlatformAdapter):
         if not self._client:
             return SendResult(success=False, error="Not connected")
 
+        if not is_safe_url(image_url):
+            logger.warning("[%s] Blocked unsafe image URL during Discord send_image", self.name)
+            return await super().send_image(chat_id, image_url, caption, reply_to, metadata=metadata)
+
         try:
             import aiohttp
 
@@ -2188,9 +2193,11 @@ class DiscordAdapter(BasePlatformAdapter):
         # UNLESS the channel is in the free-response list or the message is
         # in a thread where the bot has already participated.
         #
-        # Config (all settable via discord.* in config.yaml):
+        # Config (all settable via discord.* in config.yaml or DISCORD_* env vars):
         #   discord.require_mention: Require @mention in server channels (default: true)
         #   discord.free_response_channels: Channel IDs where bot responds without mention
+        #   discord.ignored_channels: Channel IDs where bot NEVER responds (even when mentioned)
+        #   discord.no_thread_channels: Channel IDs where bot responds directly without creating thread
         #   discord.auto_thread: Auto-create thread on @mention in channels (default: true)
 
         thread_id = None
@@ -2201,9 +2208,18 @@ class DiscordAdapter(BasePlatformAdapter):
             parent_channel_id = self._get_parent_channel_id(message.channel)
 
         if not isinstance(message.channel, discord.DMChannel):
+            # Check ignored channels first - never respond even when mentioned
+            ignored_channels_raw = os.getenv("DISCORD_IGNORED_CHANNELS", "")
+            ignored_channels = {ch.strip() for ch in ignored_channels_raw.split(",") if ch.strip()}
+            channel_ids = {str(message.channel.id)}
+            if parent_channel_id:
+                channel_ids.add(parent_channel_id)
+            if channel_ids & ignored_channels:
+                logger.debug("[%s] Ignoring message in ignored channel: %s", self.name, channel_ids)
+                return
+
             free_channels_raw = os.getenv("DISCORD_FREE_RESPONSE_CHANNELS", "")
             free_channels = {ch.strip() for ch in free_channels_raw.split(",") if ch.strip()}
-            channel_ids = {str(message.channel.id)}
             if parent_channel_id:
                 channel_ids.add(parent_channel_id)
 
@@ -2225,10 +2241,14 @@ class DiscordAdapter(BasePlatformAdapter):
         # Auto-thread: when enabled, automatically create a thread for every
         # @mention in a text channel so each conversation is isolated (like Slack).
         # Messages already inside threads or DMs are unaffected.
+        # no_thread_channels: channels where bot responds directly without thread.
         auto_threaded_channel = None
         if not is_thread and not isinstance(message.channel, discord.DMChannel):
+            no_thread_channels_raw = os.getenv("DISCORD_NO_THREAD_CHANNELS", "")
+            no_thread_channels = {ch.strip() for ch in no_thread_channels_raw.split(",") if ch.strip()}
+            skip_thread = bool(channel_ids & no_thread_channels)
             auto_thread = os.getenv("DISCORD_AUTO_THREAD", "true").lower() in ("true", "1", "yes")
-            if auto_thread:
+            if auto_thread and not skip_thread:
                 thread = await self._auto_create_thread(message)
                 if thread:
                     is_thread = True

gateway/platforms/feishu.py

@@ -20,6 +20,7 @@ from __future__ import annotations
 import asyncio
 import hashlib
 import hmac
+import itertools
 import json
 import logging
 import mimetypes
@@ -1052,6 +1053,9 @@ class FeishuAdapter(BasePlatformAdapter):
         self._media_batch_state = FeishuBatchState()
         self._pending_media_batches = self._media_batch_state.events
         self._pending_media_batch_tasks = self._media_batch_state.tasks
+        # Exec approval button state (approval_id → {session_key, message_id, chat_id})
+        self._approval_state: Dict[int, Dict[str, str]] = {}
+        self._approval_counter = itertools.count(1)
         self._load_seen_message_ids()
 
     @staticmethod
@@ -1394,6 +1398,104 @@ class FeishuAdapter(BasePlatformAdapter):
             logger.error("[Feishu] Failed to edit message %s: %s", message_id, exc, exc_info=True)
             return SendResult(success=False, error=str(exc))
 
+    async def send_exec_approval(
+        self, chat_id: str, command: str, session_key: str,
+        description: str = "dangerous command",
+        metadata: Optional[Dict[str, Any]] = None,
+    ) -> SendResult:
+        """Send an interactive card with approval buttons.
+
+        The buttons carry ``hermes_action`` in their value dict so that
+        ``_handle_card_action_event`` can intercept them and call
+        ``resolve_gateway_approval()`` to unblock the waiting agent thread.
+        """
+        if not self._client:
+            return SendResult(success=False, error="Not connected")
+
+        try:
+            approval_id = next(self._approval_counter)
+            cmd_preview = command[:3000] + "..." if len(command) > 3000 else command
+
+            def _btn(label: str, action_name: str, btn_type: str = "default") -> dict:
+                return {
+                    "tag": "button",
+                    "text": {"tag": "plain_text", "content": label},
+                    "type": btn_type,
+                    "value": {"hermes_action": action_name, "approval_id": approval_id},
+                }
+
+            card = {
+                "config": {"wide_screen_mode": True},
+                "header": {
+                    "title": {"content": "⚠️ Command Approval Required", "tag": "plain_text"},
+                    "template": "orange",
+                },
+                "elements": [
+                    {
+                        "tag": "markdown",
+                        "content": f"```\n{cmd_preview}\n```\n**Reason:** {description}",
+                    },
+                    {
+                        "tag": "action",
+                        "actions": [
+                            _btn("✅ Allow Once", "approve_once", "primary"),
+                            _btn("✅ Session", "approve_session"),
+                            _btn("✅ Always", "approve_always"),
+                            _btn("❌ Deny", "deny", "danger"),
+                        ],
+                    },
+                ],
+            }
+
+            payload = json.dumps(card, ensure_ascii=False)
+            response = await self._feishu_send_with_retry(
+                chat_id=chat_id,
+                msg_type="interactive",
+                payload=payload,
+                reply_to=None,
+                metadata=metadata,
+            )
+
+            result = self._finalize_send_result(response, "send_exec_approval failed")
+            if result.success:
+                self._approval_state[approval_id] = {
+                    "session_key": session_key,
+                    "message_id": result.message_id or "",
+                    "chat_id": chat_id,
+                }
+            return result
+        except Exception as exc:
+            logger.warning("[Feishu] send_exec_approval failed: %s", exc)
+            return SendResult(success=False, error=str(exc))
+
+    async def _update_approval_card(
+        self, message_id: str, label: str, user_name: str, choice: str,
+    ) -> None:
+        """Replace the approval card with a resolved status card."""
+        if not self._client or not message_id:
+            return
+        icon = "❌" if choice == "deny" else "✅"
+        card = {
+            "config": {"wide_screen_mode": True},
+            "header": {
+                "title": {"content": f"{icon} {label}", "tag": "plain_text"},
+                "template": "red" if choice == "deny" else "green",
+            },
+            "elements": [
+                {
+                    "tag": "markdown",
+                    "content": f"{icon} **{label}** by {user_name}",
+                },
+            ],
+        }
+        try:
+            payload = json.dumps(card, ensure_ascii=False)
+            body = self._build_update_message_body(msg_type="interactive", content=payload)
+            request = self._build_update_message_request(message_id=message_id, request_body=body)
+            await asyncio.to_thread(self._client.im.v1.message.update, request)
+        except Exception as exc:
+            logger.warning("[Feishu] Failed to update approval card %s: %s", message_id, exc)
+
     async def send_voice(
         self,
         chat_id: str,
@@ -1820,6 +1922,52 @@ class FeishuAdapter(BasePlatformAdapter):
         action = getattr(event, "action", None)
         action_tag = str(getattr(action, "tag", "") or "button")
         action_value = getattr(action, "value", {}) or {}
+
+        # --- Exec approval button intercept ---
+        hermes_action = action_value.get("hermes_action") if isinstance(action_value, dict) else None
+        if hermes_action:
+            approval_id = action_value.get("approval_id")
+            state = self._approval_state.pop(approval_id, None)
+            if not state:
+                logger.debug("[Feishu] Approval %s already resolved or unknown", approval_id)
+                return
+
+            choice_map = {
+                "approve_once": "once",
+                "approve_session": "session",
+                "approve_always": "always",
+                "deny": "deny",
+            }
+            choice = choice_map.get(hermes_action, "deny")
+
+            label_map = {
+                "once": "Approved once",
+                "session": "Approved for session",
+                "always": "Approved permanently",
+                "deny": "Denied",
+            }
+            label = label_map.get(choice, "Resolved")
+
+            # Resolve sender name for the status card
+            sender_id = SimpleNamespace(open_id=open_id, user_id=None, union_id=None)
+            sender_profile = await self._resolve_sender_profile(sender_id)
+            user_name = sender_profile.get("user_name") or open_id
+
+            # Resolve the approval — unblocks the agent thread
+            try:
+                from tools.approval import resolve_gateway_approval
+                count = resolve_gateway_approval(state["session_key"], choice)
+                logger.info(
+                    "Feishu button resolved %d approval(s) for session %s (choice=%s, user=%s)",
+                    count, state["session_key"], choice, user_name,
+                )
+            except Exception as exc:
+                logger.error("Failed to resolve gateway approval from Feishu button: %s", exc)
+
+            # Update the card to show the decision
+            await self._update_approval_card(state.get("message_id", ""), label, user_name, choice)
+            return
+
         synthetic_text = f"/card {action_tag}"
         if action_value:
             try:
@@ -2065,10 +2213,7 @@ class FeishuAdapter(BasePlatformAdapter):
         existing.media_urls.extend(event.media_urls)
         existing.media_types.extend(event.media_types)
         if event.text:
-            if not existing.text:
-                existing.text = event.text
-            elif event.text not in existing.text.split("\n\n"):
-                existing.text = f"{existing.text}\n\n{event.text}"
+            existing.text = self._merge_caption(existing.text, event.text)
         existing.timestamp = event.timestamp
         if event.message_id:
             existing.message_id = event.message_id
@@ -2112,6 +2257,10 @@ class FeishuAdapter(BasePlatformAdapter):
         default_ext: str,
         preferred_name: str,
     ) -> tuple[str, str]:
+        from tools.url_safety import is_safe_url
+        if not is_safe_url(file_url):
+            raise ValueError(f"Blocked unsafe URL (SSRF protection): {file_url[:80]}")
+
         import httpx
 
         async with httpx.AsyncClient(timeout=30.0, follow_redirects=True) as client:

gateway/platforms/matrix.py

@@ -586,6 +586,11 @@ class MatrixAdapter(BasePlatformAdapter):
         metadata: Optional[Dict[str, Any]] = None,
     ) -> SendResult:
         """Download an image URL and upload it to Matrix."""
+        from tools.url_safety import is_safe_url
+        if not is_safe_url(image_url):
+            logger.warning("Matrix: blocked unsafe image URL (SSRF protection)")
+            return await super().send_image(chat_id, image_url, caption, reply_to, metadata=metadata)
+
         try:
             # Try aiohttp first (always available), fall back to httpx
             try:

gateway/platforms/mattermost.py

@@ -407,6 +407,11 @@ class MattermostAdapter(BasePlatformAdapter):
         kind: str = "file",
     ) -> SendResult:
         """Download a URL and upload it as a file attachment."""
+        from tools.url_safety import is_safe_url
+        if not is_safe_url(url):
+            logger.warning("Mattermost: blocked unsafe URL (SSRF protection)")
+            return await self.send(chat_id, f"{caption or ''}\n{url}".strip(), reply_to)
+
         import asyncio
         import aiohttp
 

gateway/platforms/slack.py

@@ -595,6 +595,11 @@ class SlackAdapter(BasePlatformAdapter):
         if not self._app:
             return SendResult(success=False, error="Not connected")
 
+        from tools.url_safety import is_safe_url
+        if not is_safe_url(image_url):
+            logger.warning("[Slack] Blocked unsafe image URL (SSRF protection)")
+            return await super().send_image(chat_id, image_url, caption, reply_to, metadata=metadata)
+
         try:
             import httpx
 

gateway/platforms/telegram.py

@@ -1632,7 +1632,12 @@ class TelegramAdapter(BasePlatformAdapter):
         """
         if not self._bot:
             return SendResult(success=False, error="Not connected")
-        
+
+        from tools.url_safety import is_safe_url
+        if not is_safe_url(image_url):
+            logger.warning("[%s] Blocked unsafe image URL (SSRF protection)", self.name)
+            return await super().send_image(chat_id, image_url, caption, reply_to, metadata=metadata)
+
         try:
             # Telegram can send photos directly from URLs (up to ~5MB)
             _photo_thread = metadata.get("thread_id") if metadata else None
@@ -2222,10 +2227,7 @@ class TelegramAdapter(BasePlatformAdapter):
             existing.media_urls.extend(event.media_urls)
             existing.media_types.extend(event.media_types)
             if event.text:
-                if not existing.text:
-                    existing.text = event.text
-                elif event.text not in existing.text:
-                    existing.text = f"{existing.text}\n\n{event.text}".strip()
+                existing.text = self._merge_caption(existing.text, event.text)
 
         prior_task = self._pending_photo_batch_tasks.get(batch_key)
         if prior_task and not prior_task.done():
@@ -2415,11 +2417,7 @@ class TelegramAdapter(BasePlatformAdapter):
             existing.media_urls.extend(event.media_urls)
             existing.media_types.extend(event.media_types)
             if event.text:
-                if existing.text:
-                    if event.text not in existing.text.split("\n\n"):
-                        existing.text = f"{existing.text}\n\n{event.text}"
-                else:
-                    existing.text = event.text
+                existing.text = self._merge_caption(existing.text, event.text)
 
         prior_task = self._media_group_tasks.get(media_group_id)
         if prior_task:
@@ -2675,3 +2673,46 @@ class TelegramAdapter(BasePlatformAdapter):
             auto_skill=topic_skill,
             timestamp=message.date,
         )
+
+    # ── Message reactions (processing lifecycle) ──────────────────────────
+
+    def _reactions_enabled(self) -> bool:
+        """Check if message reactions are enabled via config/env."""
+        return os.getenv("TELEGRAM_REACTIONS", "false").lower() not in ("false", "0", "no")
+
+    async def _set_reaction(self, chat_id: str, message_id: str, emoji: str) -> bool:
+        """Set a single emoji reaction on a Telegram message."""
+        if not self._bot:
+            return False
+        try:
+            await self._bot.set_message_reaction(
+                chat_id=int(chat_id),
+                message_id=int(message_id),
+                reaction=emoji,
+            )
+            return True
+        except Exception as e:
+            logger.debug("[%s] set_message_reaction failed (%s): %s", self.name, emoji, e)
+            return False
+
+    async def on_processing_start(self, event: MessageEvent) -> None:
+        """Add an in-progress reaction when message processing begins."""
+        if not self._reactions_enabled():
+            return
+        chat_id = getattr(event.source, "chat_id", None)
+        message_id = getattr(event, "message_id", None)
+        if chat_id and message_id:
+            await self._set_reaction(chat_id, message_id, "\U0001f440")
+
+    async def on_processing_complete(self, event: MessageEvent, success: bool) -> None:
+        """Swap the in-progress reaction for a final success/failure reaction.
+
+        Unlike Discord (additive reactions), Telegram's set_message_reaction
+        replaces all existing reactions in one call — no remove step needed.
+        """
+        if not self._reactions_enabled():
+            return
+        chat_id = getattr(event.source, "chat_id", None)
+        message_id = getattr(event, "message_id", None)
+        if chat_id and message_id:
+            await self._set_reaction(chat_id, message_id, "\u2705" if success else "\u274c")

gateway/platforms/webhook.py

@@ -76,8 +76,17 @@ class WebhookAdapter(BasePlatformAdapter):
         self._routes: Dict[str, dict] = dict(self._static_routes)
         self._runner = None
 
-        # Delivery info keyed by session chat_id — consumed by send()
+        # Delivery info keyed by session chat_id.
+        #
+        # Read by every send() invocation for the chat_id (status messages
+        # AND the final response).  Cleaned up via TTL on each POST so the
+        # dict stays bounded — see _prune_delivery_info().  Do NOT pop on
+        # send(), or interim status messages (e.g. fallback notifications,
+        # context-pressure warnings) will consume the entry before the
+        # final response arrives, causing the response to silently fall
+        # back to the "log" deliver type.
         self._delivery_info: Dict[str, dict] = {}
+        self._delivery_info_created: Dict[str, float] = {}
 
         # Reference to gateway runner for cross-platform delivery (set externally)
         self.gateway_runner = None
@@ -160,10 +169,14 @@ class WebhookAdapter(BasePlatformAdapter):
     ) -> SendResult:
         """Deliver the agent's response to the configured destination.
 
-        chat_id is ``webhook:{route}:{delivery_id}`` — we pop the delivery
-        info stored during webhook receipt so it doesn't leak memory.
+        chat_id is ``webhook:{route}:{delivery_id}``.  The delivery info
+        stored during webhook receipt is read with ``.get()`` (not popped)
+        so that interim status messages emitted before the final response
+        — fallback-model notifications, context-pressure warnings, etc. —
+        do not consume the entry and silently downgrade the final response
+        to the ``log`` deliver type.  TTL cleanup happens on POST.
         """
-        delivery = self._delivery_info.pop(chat_id, {})
+        delivery = self._delivery_info.get(chat_id, {})
         deliver_type = delivery.get("deliver", "log")
 
         if deliver_type == "log":
@@ -190,6 +203,23 @@ class WebhookAdapter(BasePlatformAdapter):
             success=False, error=f"Unknown deliver type: {deliver_type}"
         )
 
+    def _prune_delivery_info(self, now: float) -> None:
+        """Drop delivery_info entries older than the idempotency TTL.
+
+        Mirrors the cleanup pattern used for ``_seen_deliveries``.  Called
+        on each POST so the dict size is bounded by ``rate_limit * TTL``
+        even if many webhooks fire and never receive a final response.
+        """
+        cutoff = now - self._idempotency_ttl
+        stale = [
+            k
+            for k, t in self._delivery_info_created.items()
+            if t < cutoff
+        ]
+        for k in stale:
+            self._delivery_info.pop(k, None)
+            self._delivery_info_created.pop(k, None)
+
     async def get_chat_info(self, chat_id: str) -> Dict[str, Any]:
         return {"name": chat_id, "type": "webhook"}
 
@@ -382,7 +412,9 @@ class WebhookAdapter(BasePlatformAdapter):
         # same route get independent agent runs (not queued/interrupted).
         session_chat_id = f"webhook:{route_name}:{delivery_id}"
 
-        # Store delivery info for send() — consumed (popped) on delivery
+        # Store delivery info for send().  Read by every send() invocation
+        # for this chat_id (interim status messages and the final response),
+        # so we do NOT pop on send.  TTL-based cleanup keeps the dict bounded.
         deliver_config = {
             "deliver": route_config.get("deliver", "log"),
             "deliver_extra": self._render_delivery_extra(
@@ -391,6 +423,8 @@ class WebhookAdapter(BasePlatformAdapter):
             "payload": payload,
         }
         self._delivery_info[session_chat_id] = deliver_config
+        self._delivery_info_created[session_chat_id] = now
+        self._prune_delivery_info(now)
 
         # Build source and event
         source = self.build_source(

gateway/platforms/wecom.py

@@ -910,6 +910,10 @@ class WeComAdapter(BasePlatformAdapter):
         url: str,
         max_bytes: int,
     ) -> Tuple[bytes, Dict[str, str]]:
+        from tools.url_safety import is_safe_url
+        if not is_safe_url(url):
+            raise ValueError(f"Blocked unsafe URL (SSRF protection): {url[:80]}")
+
         if not HTTPX_AVAILABLE:
             raise RuntimeError("httpx is required for WeCom media download")
 

gateway/run.py

@@ -921,12 +921,11 @@ class GatewayRunner:
 
     @staticmethod
     def _load_reasoning_config() -> dict | None:
-        """Load reasoning effort from config with env fallback.
+        """Load reasoning effort from config.yaml.
 
-        Checks agent.reasoning_effort in config.yaml first, then
-        HERMES_REASONING_EFFORT as a fallback. Valid: "xhigh", "high",
-        "medium", "low", "minimal", "none". Returns None to use default
-        (medium).
+        Reads agent.reasoning_effort from config.yaml. Valid: "xhigh",
+        "high", "medium", "low", "minimal", "none". Returns None to use
+        default (medium).
         """
         from hermes_constants import parse_reasoning_effort
         effort = ""
@@ -939,8 +938,6 @@ class GatewayRunner:
                 effort = str(cfg.get("agent", {}).get("reasoning_effort", "") or "").strip()
         except Exception:
             pass
-        if not effort:
-            effort = os.getenv("HERMES_REASONING_EFFORT", "")
         result = parse_reasoning_effort(effort)
         if effort and effort.strip() and result is None:
             logger.warning("Unknown reasoning_effort '%s', using default (medium)", effort)
@@ -1987,10 +1984,7 @@ class GatewayRunner:
                             existing.media_urls.extend(event.media_urls)
                             existing.media_types.extend(event.media_types)
                             if event.text:
-                                if not existing.text:
-                                    existing.text = event.text
-                                elif event.text not in existing.text:
-                                    existing.text = f"{existing.text}\n\n{event.text}".strip()
+                                existing.text = BasePlatformAdapter._merge_caption(existing.text, event.text)
                         else:
                             adapter._pending_messages[_quick_key] = event
                     else:
@@ -3345,25 +3339,36 @@ class GatewayRunner:
         """Handle /status command."""
         source = event.source
         session_entry = self.session_store.get_or_create_session(source)
-        
+
         connected_platforms = [p.value for p in self.adapters.keys()]
-        
+
         # Check if there's an active agent
         session_key = session_entry.session_key
         is_running = session_key in self._running_agents
-        
+
+        title = None
+        if self._session_db:
+            try:
+                title = self._session_db.get_session_title(session_entry.session_id)
+            except Exception:
+                title = None
+
         lines = [
             "📊 **Hermes Gateway Status**",
             "",
-            f"**Session ID:** `{session_entry.session_id[:12]}...`",
+            f"**Session ID:** `{session_entry.session_id}`",
+        ]
+        if title:
+            lines.append(f"**Title:** {title}")
+        lines.extend([
             f"**Created:** {session_entry.created_at.strftime('%Y-%m-%d %H:%M')}",
             f"**Last Activity:** {session_entry.updated_at.strftime('%Y-%m-%d %H:%M')}",
             f"**Tokens:** {session_entry.total_tokens:,}",
             f"**Agent Running:** {'Yes ⚡' if is_running else 'No'}",
             "",
             f"**Connected Platforms:** {', '.join(connected_platforms)}",
-        ]
-        
+        ])
+
         return "\n".join(lines)
     
     async def _handle_stop_command(self, event: MessageEvent) -> str:
@@ -4913,8 +4918,8 @@ class GatewayRunner:
         cycle = ["off", "new", "all", "verbose"]
         descriptions = {
             "off": "⚙️ Tool progress: **OFF** — no tool activity shown.",
-            "new": "⚙️ Tool progress: **NEW** — shown when tool changes (short previews).",
-            "all": "⚙️ Tool progress: **ALL** — every tool call shown (short previews).",
+            "new": "⚙️ Tool progress: **NEW** — shown when tool changes (preview length: `display.tool_preview_length`, default 40).",
+            "all": "⚙️ Tool progress: **ALL** — every tool call shown (preview length: `display.tool_preview_length`, default 40).",
             "verbose": "⚙️ Tool progress: **VERBOSE** — every tool call with full arguments.",
         }
 
@@ -6036,6 +6041,11 @@ class GatewayRunner:
 
         if enriched_parts:
             prefix = "\n\n".join(enriched_parts)
+            # Strip the empty-content placeholder from the Discord adapter
+            # when we successfully transcribed the audio — it's redundant.
+            _placeholder = "(The user sent a message with no text content)"
+            if user_text and user_text.strip() == _placeholder:
+                return prefix
             if user_text:
                 return f"{prefix}\n\n{user_text}"
             return prefix
@@ -6327,10 +6337,15 @@ class GatewayRunner:
                 progress_queue.put(msg)
                 return
             
-            # "all" / "new" modes: short preview, always truncated (40 chars)
+            # "all" / "new" modes: short preview, respects tool_preview_length
+            # config (defaults to 40 chars when unset to keep gateway messages
+            # compact — unlike CLI spinners, these persist as permanent messages).
             if preview:
-                if len(preview) > 40:
-                    preview = preview[:37] + "..."
+                from agent.display import get_tool_preview_max_len
+                _pl = get_tool_preview_max_len()
+                _cap = _pl if _pl > 0 else 40
+                if len(preview) > _cap:
+                    preview = preview[:_cap - 3] + "..."
                 msg = f"{emoji} {tool_name}: \"{preview}\""
             else:
                 msg = f"{emoji} {tool_name}..."

gateway/stream_consumer.py

@@ -74,6 +74,8 @@ class GatewayStreamConsumer:
         self._edit_supported = True  # Disabled on first edit failure (Signal/Email/HA)
         self._last_edit_time = 0.0
         self._last_sent_text = ""   # Track last-sent text to skip redundant edits
+        self._fallback_final_send = False
+        self._fallback_prefix = ""
 
     @property
     def already_sent(self) -> bool:
@@ -138,12 +140,19 @@ class GatewayStreamConsumer:
                     while (
                         len(self._accumulated) > _safe_limit
                         and self._message_id is not None
+                        and self._edit_supported
                     ):
                         split_at = self._accumulated.rfind("\n", 0, _safe_limit)
                         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.
+                            break
                         self._accumulated = self._accumulated[split_at:].lstrip("\n")
                         self._message_id = None
                         self._last_sent_text = ""
@@ -156,9 +165,17 @@ class GatewayStreamConsumer:
                     self._last_edit_time = time.monotonic()
 
                 if got_done:
-                    # Final edit without cursor
-                    if self._accumulated and self._message_id:
-                        await self._send_or_edit(self._accumulated)
+                    # Final edit without cursor. If progressive editing failed
+                    # mid-stream, send a single continuation/fallback message
+                    # here instead of letting the base gateway path send the
+                    # full response again.
+                    if self._accumulated:
+                        if self._fallback_final_send:
+                            await self._send_fallback_final(self._accumulated)
+                        elif self._message_id:
+                            await self._send_or_edit(self._accumulated)
+                        elif not self._already_sent:
+                            await self._send_or_edit(self._accumulated)
                     return
 
                 # Tool boundary: the should_edit block above already flushed
@@ -169,6 +186,8 @@ class GatewayStreamConsumer:
                     self._message_id = None
                     self._accumulated = ""
                     self._last_sent_text = ""
+                    self._fallback_final_send = False
+                    self._fallback_prefix = ""
 
                 await asyncio.sleep(0.05)  # Small yield to not busy-loop
 
@@ -207,6 +226,86 @@ class GatewayStreamConsumer:
         # Strip trailing whitespace/newlines but preserve leading content
         return cleaned.rstrip()
 
+    def _visible_prefix(self) -> str:
+        """Return the visible text already shown in the streamed message."""
+        prefix = self._last_sent_text or ""
+        if self.cfg.cursor and prefix.endswith(self.cfg.cursor):
+            prefix = prefix[:-len(self.cfg.cursor)]
+        return self._clean_for_display(prefix)
+
+    def _continuation_text(self, final_text: str) -> str:
+        """Return only the part of final_text the user has not already seen."""
+        prefix = self._fallback_prefix or self._visible_prefix()
+        if prefix and final_text.startswith(prefix):
+            return final_text[len(prefix):].lstrip()
+        return final_text
+
+    @staticmethod
+    def _split_text_chunks(text: str, limit: int) -> list[str]:
+        """Split text into reasonably sized chunks for fallback sends."""
+        if len(text) <= limit:
+            return [text]
+        chunks: list[str] = []
+        remaining = text
+        while len(remaining) > limit:
+            split_at = remaining.rfind("\n", 0, limit)
+            if split_at < limit // 2:
+                split_at = limit
+            chunks.append(remaining[:split_at])
+            remaining = remaining[split_at:].lstrip("\n")
+        if remaining:
+            chunks.append(remaining)
+        return chunks
+
+    async def _send_fallback_final(self, text: str) -> None:
+        """Send the final continuation after streaming edits stop working."""
+        final_text = self._clean_for_display(text)
+        continuation = self._continuation_text(final_text)
+        self._fallback_final_send = False
+        if not continuation.strip():
+            # Nothing new to send — the visible partial already matches final text.
+            self._already_sent = True
+            return
+
+        raw_limit = getattr(self.adapter, "MAX_MESSAGE_LENGTH", 4096)
+        safe_limit = max(500, raw_limit - 100)
+        chunks = self._split_text_chunks(continuation, safe_limit)
+
+        last_message_id: Optional[str] = None
+        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:
+                if sent_any_chunk:
+                    # Some continuation text already reached the user. Suppress
+                    # the base gateway final-send path so we don't resend the
+                    # full response and create another duplicate.
+                    self._already_sent = True
+                    self._message_id = last_message_id
+                    self._last_sent_text = last_successful_chunk
+                    self._fallback_prefix = ""
+                    return
+                # No fallback chunk reached the user — allow the normal gateway
+                # final-send path to try one more time.
+                self._already_sent = False
+                self._message_id = None
+                self._last_sent_text = ""
+                self._fallback_prefix = ""
+                return
+            sent_any_chunk = True
+            last_successful_chunk = chunk
+            last_message_id = result.message_id or last_message_id
+
+        self._message_id = last_message_id
+        self._already_sent = True
+        self._last_sent_text = chunks[-1]
+        self._fallback_prefix = ""
+
     async def _send_or_edit(self, text: str) -> None:
         """Send or edit the streaming message."""
         # Strip MEDIA: directives so they don't appear as visible text.
@@ -232,14 +331,16 @@ class GatewayStreamConsumer:
                         self._last_sent_text = text
                     else:
                         # If an edit fails mid-stream (especially Telegram flood control),
-                        # stop progressive edits and let the normal final send path deliver
-                        # the complete answer instead of leaving the user with a partial.
+                        # stop progressive edits and send only the missing tail once the
+                        # final response is available.
                         logger.debug("Edit failed, disabling streaming for this adapter")
+                        self._fallback_prefix = self._visible_prefix()
+                        self._fallback_final_send = True
                         self._edit_supported = False
-                        self._already_sent = False
+                        self._already_sent = True
                 else:
                     # Editing not supported — skip intermediate updates.
-                    # The final response will be sent by the normal path.
+                    # The final response will be sent by the fallback path.
                     pass
             else:
                 # First message — send new

hermes_cli/auth.py

@@ -37,7 +37,7 @@ from typing import Any, Dict, List, Optional
 import httpx
 import yaml
 
-from hermes_cli.config import get_hermes_home, get_config_path
+from hermes_cli.config import get_hermes_home, get_config_path, read_raw_config
 from hermes_constants import OPENROUTER_BASE_URL
 
 logger = logging.getLogger(__name__)
@@ -2214,14 +2214,7 @@ def _update_config_for_provider(
     config_path = get_config_path()
     config_path.parent.mkdir(parents=True, exist_ok=True)
 
-    config: Dict[str, Any] = {}
-    if config_path.exists():
-        try:
-            loaded = yaml.safe_load(config_path.read_text()) or {}
-            if isinstance(loaded, dict):
-                config = loaded
-        except Exception:
-            config = {}
+    config = read_raw_config()
 
     current_model = config.get("model")
     if isinstance(current_model, dict):
@@ -2258,12 +2251,8 @@ def _reset_config_provider() -> Path:
     if not config_path.exists():
         return config_path
 
-    try:
-        config = yaml.safe_load(config_path.read_text()) or {}
-    except Exception:
-        return config_path
-
-    if not isinstance(config, dict):
+    config = read_raw_config()
+    if not config:
         return config_path
 
     model = config.get("model")

hermes_cli/banner.py

@@ -5,6 +5,7 @@ Pure display functions with no HermesCLI state dependency.
 
 import json
 import logging
+import os
 import shutil
 import subprocess
 import threading
@@ -189,6 +190,79 @@ def check_for_updates() -> Optional[int]:
     return behind
 
 
+def _resolve_repo_dir() -> Optional[Path]:
+    """Return the active Hermes git checkout, or None if this isn't a git install."""
+    hermes_home = get_hermes_home()
+    repo_dir = hermes_home / "hermes-agent"
+    if not (repo_dir / ".git").exists():
+        repo_dir = Path(__file__).parent.parent.resolve()
+    return repo_dir if (repo_dir / ".git").exists() else None
+
+
+def _git_short_hash(repo_dir: Path, rev: str) -> Optional[str]:
+    """Resolve a git revision to an 8-character short hash."""
+    try:
+        result = subprocess.run(
+            ["git", "rev-parse", "--short=8", rev],
+            capture_output=True,
+            text=True,
+            timeout=5,
+            cwd=str(repo_dir),
+        )
+    except Exception:
+        return None
+    if result.returncode != 0:
+        return None
+    value = (result.stdout or "").strip()
+    return value or None
+
+
+def get_git_banner_state(repo_dir: Optional[Path] = None) -> Optional[dict]:
+    """Return upstream/local git hashes for the startup banner."""
+    repo_dir = repo_dir or _resolve_repo_dir()
+    if repo_dir is None:
+        return None
+
+    upstream = _git_short_hash(repo_dir, "origin/main")
+    local = _git_short_hash(repo_dir, "HEAD")
+    if not upstream or not local:
+        return None
+
+    ahead = 0
+    try:
+        result = subprocess.run(
+            ["git", "rev-list", "--count", "origin/main..HEAD"],
+            capture_output=True,
+            text=True,
+            timeout=5,
+            cwd=str(repo_dir),
+        )
+        if result.returncode == 0:
+            ahead = int((result.stdout or "0").strip() or "0")
+    except Exception:
+        ahead = 0
+
+    return {"upstream": upstream, "local": local, "ahead": max(ahead, 0)}
+
+
+def format_banner_version_label() -> str:
+    """Return the version label shown in the startup banner title."""
+    base = f"Hermes Agent v{VERSION} ({RELEASE_DATE})"
+    state = get_git_banner_state()
+    if not state:
+        return base
+
+    upstream = state["upstream"]
+    local = state["local"]
+    ahead = int(state.get("ahead") or 0)
+
+    if ahead <= 0 or upstream == local:
+        return f"{base} · upstream {upstream}"
+
+    carried_word = "commit" if ahead == 1 else "commits"
+    return f"{base} · upstream {upstream} · local {local} (+{ahead} carried {carried_word})"
+
+
 # =========================================================================
 # Non-blocking update check
 # =========================================================================
@@ -448,7 +522,7 @@ def build_welcome_banner(console: Console, model: str, cwd: str,
     border_color = _skin_color("banner_border", "#CD7F32")
     outer_panel = Panel(
         layout_table,
-        title=f"[bold {title_color}]{agent_name} v{VERSION} ({RELEASE_DATE})[/]",
+        title=f"[bold {title_color}]{format_banner_version_label()}[/]",
         border_style=border_color,
         padding=(0, 2),
     )

hermes_cli/commands.py

@@ -293,14 +293,8 @@ def _resolve_config_gates() -> set[str]:
     if not gated:
         return set()
     try:
-        import yaml
-        from hermes_constants import get_hermes_home
-        config_path = str(get_hermes_home() / "config.yaml")
-        if os.path.exists(config_path):
-            with open(config_path, encoding="utf-8") as f:
-                cfg = yaml.safe_load(f) or {}
-        else:
-            cfg = {}
+        from hermes_cli.config import read_raw_config
+        cfg = read_raw_config()
     except Exception:
         return set()
     result: set[str] = set()

hermes_cli/config.py

@@ -416,6 +416,7 @@ DEFAULT_CONFIG = {
         "provider": "local",  # "local" (free, faster-whisper) | "groq" | "openai" (Whisper API)
         "local": {
             "model": "base",  # tiny, base, small, medium, large-v3
+            "language": "",  # auto-detect by default; set to "en", "es", "fr", etc. to force
         },
         "openai": {
             "model": "whisper-1",  # whisper-1, gpt-4o-mini-transcribe, gpt-4o-transcribe

hermes_cli/cron.py

@@ -93,6 +93,21 @@ def cron_list(show_all: bool = False):
         script = job.get("script")
         if script:
             print(f"    Script:    {script}")
+
+        # Execution history
+        last_status = job.get("last_status")
+        if last_status:
+            last_run = job.get("last_run_at", "?")
+            if last_status == "ok":
+                status_display = color("ok", Colors.GREEN)
+            else:
+                status_display = color(f"{last_status}: {job.get('last_error', '?')}", Colors.RED)
+            print(f"    Last run:  {last_run}  {status_display}")
+
+        delivery_err = job.get("last_delivery_error")
+        if delivery_err:
+            print(f"    {color('⚠ Delivery failed:', Colors.YELLOW)} {delivery_err}")
+
         print()
 
     from hermes_cli.gateway import find_gateway_pids

hermes_cli/gateway.py

@@ -267,6 +267,34 @@ def _profile_suffix() -> str:
     return hashlib.sha256(str(home).encode()).hexdigest()[:8]
 
 
+def _profile_arg(hermes_home: str | None = None) -> str:
+    """Return ``--profile <name>`` only when HERMES_HOME is a named profile.
+
+    For ``~/.hermes/profiles/<name>``, returns ``"--profile <name>"``.
+    For the default profile or hash-based custom paths, returns the empty string.
+
+    Args:
+        hermes_home: Optional explicit HERMES_HOME path. Defaults to the current
+            ``get_hermes_home()`` value. Should be passed when generating a
+            service definition for a different user (e.g. system service).
+    """
+    import re
+    from pathlib import Path as _Path
+    home = Path(hermes_home or str(get_hermes_home())).resolve()
+    default = (_Path.home() / ".hermes").resolve()
+    if home == default:
+        return ""
+    profiles_root = (default / "profiles").resolve()
+    try:
+        rel = home.relative_to(profiles_root)
+        parts = rel.parts
+        if len(parts) == 1 and re.match(r"^[a-z0-9][a-z0-9_-]{0,63}$", parts[0]):
+            return f"--profile {parts[0]}"
+    except ValueError:
+        pass
+    return ""
+
+
 def get_service_name() -> str:
     """Derive a systemd service name scoped to this HERMES_HOME.
 
@@ -626,6 +654,7 @@ def generate_systemd_unit(system: bool = False, run_as_user: str | None = None)
     if system:
         username, group_name, home_dir = _system_service_identity(run_as_user)
         hermes_home = _hermes_home_for_target_user(home_dir)
+        profile_arg = _profile_arg(hermes_home)
         path_entries.extend(_build_user_local_paths(Path(home_dir), path_entries))
         path_entries.extend(common_bin_paths)
         sane_path = ":".join(path_entries)
@@ -640,7 +669,7 @@ StartLimitBurst=5
 Type=simple
 User={username}
 Group={group_name}
-ExecStart={python_path} -m hermes_cli.main gateway run --replace
+ExecStart={python_path} -m hermes_cli.main{f" {profile_arg}" if profile_arg else ""} gateway run --replace
 WorkingDirectory={working_dir}
 Environment="HOME={home_dir}"
 Environment="USER={username}"
@@ -661,6 +690,7 @@ WantedBy=multi-user.target
 """
 
     hermes_home = str(get_hermes_home().resolve())
+    profile_arg = _profile_arg(hermes_home)
     path_entries.extend(_build_user_local_paths(Path.home(), path_entries))
     path_entries.extend(common_bin_paths)
     sane_path = ":".join(path_entries)
@@ -672,7 +702,7 @@ StartLimitBurst=5
 
 [Service]
 Type=simple
-ExecStart={python_path} -m hermes_cli.main gateway run --replace
+ExecStart={python_path} -m hermes_cli.main{f" {profile_arg}" if profile_arg else ""} gateway run --replace
 WorkingDirectory={working_dir}
 Environment="PATH={sane_path}"
 Environment="VIRTUAL_ENV={venv_dir}"
@@ -965,6 +995,7 @@ def generate_launchd_plist() -> str:
     log_dir = get_hermes_home() / "logs"
     log_dir.mkdir(parents=True, exist_ok=True)
     label = get_launchd_label()
+    profile_arg = _profile_arg(hermes_home)
     # Build a sane PATH for the launchd plist.  launchd provides only a
     # minimal default (/usr/bin:/bin:/usr/sbin:/sbin) which misses Homebrew,
     # nvm, cargo, etc.  We prepend venv/bin and node_modules/.bin (matching
@@ -986,21 +1017,32 @@ def generate_launchd_plist() -> str:
         dict.fromkeys(priority_dirs + [p for p in os.environ.get("PATH", "").split(":") if p])
     )
 
+    # Build ProgramArguments array, including --profile when using a named profile
+    prog_args = [
+        f"<string>{python_path}</string>",
+        "<string>-m</string>",
+        "<string>hermes_cli.main</string>",
+    ]
+    if profile_arg:
+        for part in profile_arg.split():
+            prog_args.append(f"<string>{part}</string>")
+    prog_args.extend([
+        "<string>gateway</string>",
+        "<string>run</string>",
+        "<string>--replace</string>",
+    ])
+    prog_args_xml = "\n        ".join(prog_args)
+
     return f"""<?xml version="1.0" encoding="UTF-8"?>
 <!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
 <plist version="1.0">
 <dict>
     <key>Label</key>
     <string>{label}</string>
-    
+
     <key>ProgramArguments</key>
     <array>
-        <string>{python_path}</string>
-        <string>-m</string>
-        <string>hermes_cli.main</string>
-        <string>gateway</string>
-        <string>run</string>
-        <string>--replace</string>
+        {prog_args_xml}
     </array>
     
     <key>WorkingDirectory</key>

hermes_cli/model_switch.py

@@ -791,12 +791,12 @@ def list_authenticated_providers(
         if overlay.auth_type in ("oauth_device_code", "oauth_external", "external_process"):
             # These use auth stores, not env vars — check for auth.json entries
             try:
-                from hermes_cli.auth import _read_auth_store
-                store = _read_auth_store()
-                if store and pid in store:
+                from hermes_cli.auth import _load_auth_store
+                store = _load_auth_store()
+                if store and (pid in store.get("providers", {}) or pid in store.get("credential_pool", {})):
                     has_creds = True
-            except Exception:
-                pass
+            except Exception as exc:
+                logger.debug("Auth store check failed for %s: %s", pid, exc)
         if not has_creds:
             continue
 

hermes_cli/models.py

@@ -144,18 +144,22 @@ _PROVIDER_MODELS: dict[str, list[str]] = {
         "kimi-k2-0905-preview",
     ],
     "minimax": [
-        "MiniMax-M2.7",
-        "MiniMax-M2.7-highspeed",
+        "MiniMax-M1",
+        "MiniMax-M1-40k",
+        "MiniMax-M1-80k",
+        "MiniMax-M1-128k",
+        "MiniMax-M1-256k",
         "MiniMax-M2.5",
-        "MiniMax-M2.5-highspeed",
-        "MiniMax-M2.1",
+        "MiniMax-M2.7",
     ],
     "minimax-cn": [
-        "MiniMax-M2.7",
-        "MiniMax-M2.7-highspeed",
+        "MiniMax-M1",
+        "MiniMax-M1-40k",
+        "MiniMax-M1-80k",
+        "MiniMax-M1-128k",
+        "MiniMax-M1-256k",
         "MiniMax-M2.5",
-        "MiniMax-M2.5-highspeed",
-        "MiniMax-M2.1",
+        "MiniMax-M2.7",
     ],
     "anthropic": [
         "claude-opus-4-6",

hermes_cli/runtime_provider.py

@@ -163,6 +163,16 @@ def _resolve_runtime_from_pool_entry(
         api_mode = _copilot_runtime_api_mode(model_cfg, getattr(entry, "runtime_api_key", ""))
     else:
         configured_provider = str(model_cfg.get("provider") or "").strip().lower()
+        # Honour model.base_url from config.yaml when the configured provider
+        # matches this provider — same pattern as the Anthropic branch above.
+        # Only override when the pool entry has no explicit base_url (i.e. it
+        # fell back to the hardcoded default).  Env var overrides win (#6039).
+        pconfig = PROVIDER_REGISTRY.get(provider)
+        pool_url_is_default = pconfig and base_url.rstrip("/") == pconfig.inference_base_url.rstrip("/")
+        if configured_provider == provider and pool_url_is_default:
+            cfg_base_url = str(model_cfg.get("base_url") or "").strip().rstrip("/")
+            if cfg_base_url:
+                base_url = cfg_base_url
         configured_mode = _parse_api_mode(model_cfg.get("api_mode"))
         if configured_mode and _provider_supports_explicit_api_mode(provider, configured_provider):
             api_mode = configured_mode
@@ -724,7 +734,15 @@ def resolve_runtime_provider(
     pconfig = PROVIDER_REGISTRY.get(provider)
     if pconfig and pconfig.auth_type == "api_key":
         creds = resolve_api_key_provider_credentials(provider)
-        base_url = creds.get("base_url", "").rstrip("/")
+        # Honour model.base_url from config.yaml when the configured provider
+        # matches this provider — mirrors the Anthropic path above.  Without
+        # this, users who set model.base_url to e.g. api.minimaxi.com/anthropic
+        # (China endpoint) still get the hardcoded api.minimax.io default (#6039).
+        cfg_provider = str(model_cfg.get("provider") or "").strip().lower()
+        cfg_base_url = ""
+        if cfg_provider == provider:
+            cfg_base_url = (model_cfg.get("base_url") or "").strip().rstrip("/")
+        base_url = cfg_base_url or creds.get("base_url", "").rstrip("/")
         api_mode = "chat_completions"
         if provider == "copilot":
             api_mode = _copilot_runtime_api_mode(model_cfg, creds.get("api_key", ""))

hermes_cli/setup.py

@@ -105,8 +105,8 @@ _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-M2.7", "MiniMax-M2.7-highspeed", "MiniMax-M2.5", "MiniMax-M2.5-highspeed", "MiniMax-M2.1"],
-    "minimax-cn": ["MiniMax-M2.7", "MiniMax-M2.7-highspeed", "MiniMax-M2.5", "MiniMax-M2.5-highspeed", "MiniMax-M2.1"],
+    "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"],
     "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"],
@@ -421,10 +421,22 @@ def _curses_prompt_choice(question: str, choices: list, default: int = 0) -> int
                 curses.init_pair(1, curses.COLOR_GREEN, -1)
                 curses.init_pair(2, curses.COLOR_YELLOW, -1)
             cursor = default
+            scroll_offset = 0
 
             while True:
                 stdscr.clear()
                 max_y, max_x = stdscr.getmaxyx()
+
+                # Rows available for list items: rows 2..(max_y-2) inclusive.
+                visible = max(1, max_y - 3)
+
+                # Scroll the viewport so the cursor is always visible.
+                if cursor < scroll_offset:
+                    scroll_offset = cursor
+                elif cursor >= scroll_offset + visible:
+                    scroll_offset = cursor - visible + 1
+                scroll_offset = max(0, min(scroll_offset, max(0, len(choices) - visible)))
+
                 try:
                     stdscr.addnstr(
                         0,
@@ -436,12 +448,12 @@ def _curses_prompt_choice(question: str, choices: list, default: int = 0) -> int
                 except curses.error:
                     pass
 
-                for i, choice in enumerate(choices):
-                    y = i + 2
+                for row, i in enumerate(range(scroll_offset, min(scroll_offset + visible, len(choices)))):
+                    y = row + 2
                     if y >= max_y - 1:
                         break
                     arrow = "→" if i == cursor else " "
-                    line = f" {arrow}  {choice}"
+                    line = f" {arrow}  {choices[i]}"
                     attr = curses.A_NORMAL
                     if i == cursor:
                         attr = curses.A_BOLD

hermes_cli/tools_config.py

@@ -554,6 +554,7 @@ def _get_platform_tools(
     # MCP servers are expected to be available on all platforms by default.
     # If the platform explicitly lists one or more MCP server names, treat that
     # as an allowlist. Otherwise include every globally enabled MCP server.
+    # Special sentinel: "no_mcp" in the toolset list disables all MCP servers.
     mcp_servers = config.get("mcp_servers") or {}
     enabled_mcp_servers = {
         name
@@ -561,10 +562,15 @@ def _get_platform_tools(
         if isinstance(server_cfg, dict)
         and _parse_enabled_flag(server_cfg.get("enabled", True), default=True)
     }
-    explicit_mcp_servers = explicit_passthrough & enabled_mcp_servers
-    enabled_toolsets.update(explicit_passthrough - enabled_mcp_servers)
+    # Allow "no_mcp" sentinel to opt out of all MCP servers for this platform
+    if "no_mcp" in toolset_names:
+        explicit_mcp_servers = set()
+        enabled_toolsets.update(explicit_passthrough - enabled_mcp_servers - {"no_mcp"})
+    else:
+        explicit_mcp_servers = explicit_passthrough & enabled_mcp_servers
+        enabled_toolsets.update(explicit_passthrough - enabled_mcp_servers)
     if include_default_mcp_servers:
-        if explicit_mcp_servers:
+        if explicit_mcp_servers or "no_mcp" in toolset_names:
             enabled_toolsets.update(explicit_mcp_servers)
         else:
             enabled_toolsets.update(enabled_mcp_servers)

plugins/memory/hindsight/__init__.py

@@ -23,6 +23,8 @@ import json
 import logging
 import os
 import threading
+
+from hermes_constants import get_hermes_home
 from typing import Any, Dict, List
 
 from agent.memory_provider import MemoryProvider
@@ -142,7 +144,6 @@ def _load_config() -> dict:
       3. Environment variables
     """
     from pathlib import Path
-    from hermes_constants import get_hermes_home
 
     # Profile-scoped path (preferred)
     profile_path = get_hermes_home() / "hindsight" / "config.json"

plugins/memory/supermemory/README.md

@@ -17,7 +17,7 @@ Or manually:
 
 ```bash
 hermes config set memory.provider supermemory
-echo 'SUPERMEMORY_API_KEY=your-key-here' >> ~/.hermes/.env
+echo 'SUPERMEMORY_API_KEY=***' >> ~/.hermes/.env
 ```
 
 ## Config
@@ -26,15 +26,23 @@ Config file: `$HERMES_HOME/supermemory.json`
 
 | Key | Default | Description |
 |-----|---------|-------------|
-| `container_tag` | `hermes` | Container tag used for search and writes |
+| `container_tag` | `hermes` | Container tag used for search and writes. Supports `{identity}` template for profile-scoped tags (e.g. `hermes-{identity}` → `hermes-coder`). |
 | `auto_recall` | `true` | Inject relevant memory context before turns |
 | `auto_capture` | `true` | Store cleaned user-assistant turns after each response |
 | `max_recall_results` | `10` | Max recalled items to format into context |
 | `profile_frequency` | `50` | Include profile facts on first turn and every N turns |
 | `capture_mode` | `all` | Skip tiny or trivial turns by default |
+| `search_mode` | `hybrid` | Search mode: `hybrid` (profile + memories), `memories` (memories only), `documents` (documents only) |
 | `entity_context` | built-in default | Extraction guidance passed to Supermemory |
 | `api_timeout` | `5.0` | Timeout for SDK and ingest requests |
 
+### Environment Variables
+
+| Variable | Description |
+|----------|-------------|
+| `SUPERMEMORY_API_KEY` | API key (required) |
+| `SUPERMEMORY_CONTAINER_TAG` | Override container tag (takes priority over config file) |
+
 ## Tools
 
 | Tool | Description |
@@ -52,3 +60,40 @@ When enabled, Hermes can:
 - store cleaned conversation turns after each completed response
 - ingest the full session on session end for richer graph updates
 - expose explicit tools for search, store, forget, and profile access
+
+## Profile-Scoped Containers
+
+Use `{identity}` in the `container_tag` to scope memories per Hermes profile:
+
+```json
+{
+  "container_tag": "hermes-{identity}"
+}
+```
+
+For a profile named `coder`, this resolves to `hermes-coder`. The default profile resolves to `hermes-default`. Without `{identity}`, all profiles share the same container.
+
+## Multi-Container Mode
+
+For advanced setups (e.g. OpenClaw-style multi-workspace), you can enable custom container tags so the agent can read/write across multiple named containers:
+
+```json
+{
+  "container_tag": "hermes",
+  "enable_custom_container_tags": true,
+  "custom_containers": ["project-alpha", "project-beta", "shared-knowledge"],
+  "custom_container_instructions": "Use project-alpha for coding tasks, project-beta for research, and shared-knowledge for team-wide facts."
+}
+```
+
+When enabled:
+- `supermemory_search`, `supermemory_store`, `supermemory_forget`, and `supermemory_profile` accept an optional `container_tag` parameter
+- The tag must be in the whitelist: primary container + `custom_containers`
+- Automatic operations (turn sync, prefetch, memory write mirroring, session ingest) always use the **primary** container only
+- Custom container instructions are injected into the system prompt
+
+## Support
+
+- [Supermemory Discord](https://supermemory.link/discord)
+- [support@supermemory.com](mailto:support@supermemory.com)
+- [supermemory.ai](https://supermemory.ai)

plugins/memory/supermemory/__init__.py

@@ -26,6 +26,8 @@ _DEFAULT_CONTAINER_TAG = "hermes"
 _DEFAULT_MAX_RECALL_RESULTS = 10
 _DEFAULT_PROFILE_FREQUENCY = 50
 _DEFAULT_CAPTURE_MODE = "all"
+_DEFAULT_SEARCH_MODE = "hybrid"
+_VALID_SEARCH_MODES = ("hybrid", "memories", "documents")
 _DEFAULT_API_TIMEOUT = 5.0
 _MIN_CAPTURE_LENGTH = 10
 _MAX_ENTITY_CONTEXT_LENGTH = 1500
@@ -59,8 +61,12 @@ def _default_config() -> dict:
         "max_recall_results": _DEFAULT_MAX_RECALL_RESULTS,
         "profile_frequency": _DEFAULT_PROFILE_FREQUENCY,
         "capture_mode": _DEFAULT_CAPTURE_MODE,
+        "search_mode": _DEFAULT_SEARCH_MODE,
         "entity_context": _DEFAULT_ENTITY_CONTEXT,
         "api_timeout": _DEFAULT_API_TIMEOUT,
+        "enable_custom_container_tags": False,
+        "custom_containers": [],
+        "custom_container_instructions": "",
     }
 
 
@@ -100,7 +106,10 @@ def _load_supermemory_config(hermes_home: str) -> dict:
         except Exception:
             logger.debug("Failed to parse %s", config_path, exc_info=True)
 
-    config["container_tag"] = _sanitize_tag(str(config.get("container_tag", _DEFAULT_CONTAINER_TAG)))
+    # Keep raw container_tag — template variables like {identity} are resolved
+    # in initialize(), and _sanitize_tag runs AFTER resolution.
+    raw_tag = str(config.get("container_tag", _DEFAULT_CONTAINER_TAG)).strip()
+    config["container_tag"] = raw_tag if raw_tag else _DEFAULT_CONTAINER_TAG
     config["auto_recall"] = _as_bool(config.get("auto_recall"), True)
     config["auto_capture"] = _as_bool(config.get("auto_capture"), True)
     try:
@@ -112,11 +121,23 @@ def _load_supermemory_config(hermes_home: str) -> dict:
     except Exception:
         config["profile_frequency"] = _DEFAULT_PROFILE_FREQUENCY
     config["capture_mode"] = "everything" if config.get("capture_mode") == "everything" else "all"
+    raw_search_mode = str(config.get("search_mode", _DEFAULT_SEARCH_MODE)).strip().lower()
+    config["search_mode"] = raw_search_mode if raw_search_mode in _VALID_SEARCH_MODES else _DEFAULT_SEARCH_MODE
     config["entity_context"] = _clamp_entity_context(str(config.get("entity_context", _DEFAULT_ENTITY_CONTEXT)))
     try:
         config["api_timeout"] = max(0.5, min(15.0, float(config.get("api_timeout", _DEFAULT_API_TIMEOUT))))
     except Exception:
         config["api_timeout"] = _DEFAULT_API_TIMEOUT
+
+    # Multi-container support
+    config["enable_custom_container_tags"] = _as_bool(config.get("enable_custom_container_tags"), False)
+    raw_containers = config.get("custom_containers", [])
+    if isinstance(raw_containers, list):
+        config["custom_containers"] = [_sanitize_tag(str(t)) for t in raw_containers if t]
+    else:
+        config["custom_containers"] = []
+    config["custom_container_instructions"] = str(config.get("custom_container_instructions", "")).strip()
+
     return config
 
 
@@ -240,28 +261,41 @@ def _is_trivial_message(text: str) -> bool:
 
 
 class _SupermemoryClient:
-    def __init__(self, api_key: str, timeout: float, container_tag: str):
+    def __init__(self, api_key: str, timeout: float, container_tag: str, search_mode: str = "hybrid"):
         from supermemory import Supermemory
 
         self._api_key = api_key
         self._container_tag = container_tag
+        self._search_mode = search_mode if search_mode in _VALID_SEARCH_MODES else _DEFAULT_SEARCH_MODE
         self._timeout = timeout
         self._client = Supermemory(api_key=api_key, timeout=timeout, max_retries=0)
 
-    def add_memory(self, content: str, metadata: Optional[dict] = None, *, entity_context: str = "") -> dict:
-        kwargs = {
+    def add_memory(self, content: str, metadata: Optional[dict] = None, *,
+                   entity_context: str = "", container_tag: Optional[str] = None,
+                   custom_id: Optional[str] = None) -> dict:
+        tag = container_tag or self._container_tag
+        kwargs: dict[str, Any] = {
             "content": content.strip(),
-            "container_tags": [self._container_tag],
+            "container_tags": [tag],
         }
         if metadata:
             kwargs["metadata"] = metadata
         if entity_context:
             kwargs["entity_context"] = _clamp_entity_context(entity_context)
+        if custom_id:
+            kwargs["custom_id"] = custom_id
         result = self._client.documents.add(**kwargs)
         return {"id": getattr(result, "id", "")}
 
-    def search_memories(self, query: str, *, limit: int = 5) -> list[dict]:
-        response = self._client.search.memories(q=query, container_tag=self._container_tag, limit=limit)
+    def search_memories(self, query: str, *, limit: int = 5,
+                        container_tag: Optional[str] = None,
+                        search_mode: Optional[str] = None) -> list[dict]:
+        tag = container_tag or self._container_tag
+        mode = search_mode or self._search_mode
+        kwargs: dict[str, Any] = {"q": query, "container_tag": tag, "limit": limit}
+        if mode in _VALID_SEARCH_MODES:
+            kwargs["search_mode"] = mode
+        response = self._client.search.memories(**kwargs)
         results = []
         for item in (getattr(response, "results", None) or []):
             results.append({
@@ -273,8 +307,10 @@ class _SupermemoryClient:
             })
         return results
 
-    def get_profile(self, query: Optional[str] = None) -> dict:
-        kwargs = {"container_tag": self._container_tag}
+    def get_profile(self, query: Optional[str] = None, *,
+                    container_tag: Optional[str] = None) -> dict:
+        tag = container_tag or self._container_tag
+        kwargs: dict[str, Any] = {"container_tag": tag}
         if query:
             kwargs["q"] = query
         response = self._client.profile(**kwargs)
@@ -296,18 +332,19 @@ class _SupermemoryClient:
                     })
         return {"static": static, "dynamic": dynamic, "search_results": search_results}
 
-    def forget_memory(self, memory_id: str) -> None:
-        self._client.memories.forget(container_tag=self._container_tag, id=memory_id)
+    def forget_memory(self, memory_id: str, *, container_tag: Optional[str] = None) -> None:
+        tag = container_tag or self._container_tag
+        self._client.memories.forget(container_tag=tag, id=memory_id)
 
-    def forget_by_query(self, query: str) -> dict:
-        results = self.search_memories(query, limit=5)
+    def forget_by_query(self, query: str, *, container_tag: Optional[str] = None) -> dict:
+        results = self.search_memories(query, limit=5, container_tag=container_tag)
         if not results:
             return {"success": False, "message": "No matching memory found to forget."}
         target = results[0]
         memory_id = target.get("id", "")
         if not memory_id:
             return {"success": False, "message": "Best matching memory has no id."}
-        self.forget_memory(memory_id)
+        self.forget_memory(memory_id, container_tag=container_tag)
         preview = (target.get("memory") or "")[:100]
         return {"success": True, "message": f'Forgot: "{preview}"', "id": memory_id}
 
@@ -398,11 +435,17 @@ class SupermemoryMemoryProvider(MemoryProvider):
         self._max_recall_results = _DEFAULT_MAX_RECALL_RESULTS
         self._profile_frequency = _DEFAULT_PROFILE_FREQUENCY
         self._capture_mode = _DEFAULT_CAPTURE_MODE
+        self._search_mode = _DEFAULT_SEARCH_MODE
         self._entity_context = _DEFAULT_ENTITY_CONTEXT
         self._api_timeout = _DEFAULT_API_TIMEOUT
         self._hermes_home = ""
         self._write_enabled = True
         self._active = False
+        # Multi-container support
+        self._enable_custom_containers = False
+        self._custom_containers: List[str] = []
+        self._custom_container_instructions = ""
+        self._allowed_containers: List[str] = []
 
     @property
     def name(self) -> str:
@@ -419,16 +462,11 @@ class SupermemoryMemoryProvider(MemoryProvider):
             return False
 
     def get_config_schema(self):
+        # Only prompt for the API key during `hermes memory setup`.
+        # All other options are documented for $HERMES_HOME/supermemory.json
+        # or the SUPERMEMORY_CONTAINER_TAG env var.
         return [
             {"key": "api_key", "description": "Supermemory API key", "secret": True, "required": True, "env_var": "SUPERMEMORY_API_KEY", "url": "https://supermemory.ai"},
-            {"key": "container_tag", "description": "Container tag for reads and writes", "default": _DEFAULT_CONTAINER_TAG},
-            {"key": "auto_recall", "description": "Enable automatic recall before each turn", "default": "true", "choices": ["true", "false"]},
-            {"key": "auto_capture", "description": "Enable automatic capture after each completed turn", "default": "true", "choices": ["true", "false"]},
-            {"key": "max_recall_results", "description": "Maximum recalled items to inject", "default": str(_DEFAULT_MAX_RECALL_RESULTS)},
-            {"key": "profile_frequency", "description": "Include profile facts on first turn and every N turns", "default": str(_DEFAULT_PROFILE_FREQUENCY)},
-            {"key": "capture_mode", "description": "Capture mode", "default": _DEFAULT_CAPTURE_MODE, "choices": ["all", "everything"]},
-            {"key": "entity_context", "description": "Extraction guidance passed to Supermemory", "default": _DEFAULT_ENTITY_CONTEXT},
-            {"key": "api_timeout", "description": "Timeout in seconds for SDK and ingest calls", "default": str(_DEFAULT_API_TIMEOUT)},
         ]
 
     def save_config(self, values, hermes_home):
@@ -446,14 +484,29 @@ class SupermemoryMemoryProvider(MemoryProvider):
         self._turn_count = 0
         self._config = _load_supermemory_config(self._hermes_home)
         self._api_key = os.environ.get("SUPERMEMORY_API_KEY", "")
-        self._container_tag = self._config["container_tag"]
+
+        # Resolve container tag: env var > config > default.
+        # Supports {identity} template for profile-scoped containers.
+        env_tag = os.environ.get("SUPERMEMORY_CONTAINER_TAG", "").strip()
+        raw_tag = env_tag or self._config["container_tag"]
+        identity = kwargs.get("agent_identity", "default")
+        self._container_tag = _sanitize_tag(raw_tag.replace("{identity}", identity))
+
         self._auto_recall = self._config["auto_recall"]
         self._auto_capture = self._config["auto_capture"]
         self._max_recall_results = self._config["max_recall_results"]
         self._profile_frequency = self._config["profile_frequency"]
         self._capture_mode = self._config["capture_mode"]
+        self._search_mode = self._config["search_mode"]
         self._entity_context = self._config["entity_context"]
         self._api_timeout = self._config["api_timeout"]
+
+        # Multi-container setup
+        self._enable_custom_containers = self._config["enable_custom_container_tags"]
+        self._custom_containers = self._config["custom_containers"]
+        self._custom_container_instructions = self._config["custom_container_instructions"]
+        self._allowed_containers = [self._container_tag] + list(self._custom_containers)
+
         agent_context = kwargs.get("agent_context", "")
         self._write_enabled = agent_context not in ("cron", "flush", "subagent")
         self._active = bool(self._api_key)
@@ -464,6 +517,7 @@ class SupermemoryMemoryProvider(MemoryProvider):
                     api_key=self._api_key,
                     timeout=self._api_timeout,
                     container_tag=self._container_tag,
+                    search_mode=self._search_mode,
                 )
             except Exception:
                 logger.warning("Supermemory initialization failed", exc_info=True)
@@ -476,11 +530,18 @@ class SupermemoryMemoryProvider(MemoryProvider):
     def system_prompt_block(self) -> str:
         if not self._active:
             return ""
-        return (
-            "# Supermemory\n"
-            f"Active. Container: {self._container_tag}.\n"
-            "Use supermemory_search, supermemory_store, supermemory_forget, and supermemory_profile for explicit memory operations."
-        )
+        lines = [
+            "# Supermemory",
+            f"Active. Container: {self._container_tag}.",
+            "Use supermemory_search, supermemory_store, supermemory_forget, and supermemory_profile for explicit memory operations.",
+        ]
+        if self._enable_custom_containers and self._custom_containers:
+            tags_str = ", ".join(self._allowed_containers)
+            lines.append(f"\nMulti-container mode enabled. Available containers: {tags_str}.")
+            lines.append("Pass an optional container_tag to supermemory_search, supermemory_store, supermemory_forget, and supermemory_profile to target a specific container.")
+            if self._custom_container_instructions:
+                lines.append(f"\n{self._custom_container_instructions}")
+        return "\n".join(lines)
 
     def prefetch(self, query: str, *, session_id: str = "") -> str:
         if not self._active or not self._auto_recall or not self._client or not query.strip():
@@ -582,22 +643,62 @@ class SupermemoryMemoryProvider(MemoryProvider):
                 thread.join(timeout=5.0)
             setattr(self, attr_name, None)
 
+    def _resolve_tool_container_tag(self, args: dict) -> Optional[str]:
+        """Validate and resolve container_tag from tool call args.
+
+        Returns None (use primary) if multi-container is disabled or no tag provided.
+        Returns the validated tag if it's in the allowed list.
+        Raises ValueError if the tag is not whitelisted.
+        """
+        if not self._enable_custom_containers:
+            return None
+        tag = str(args.get("container_tag") or "").strip()
+        if not tag:
+            return None
+        sanitized = _sanitize_tag(tag)
+        if sanitized not in self._allowed_containers:
+            raise ValueError(
+                f"Container tag '{sanitized}' is not allowed. "
+                f"Allowed: {', '.join(self._allowed_containers)}"
+            )
+        return sanitized
+
     def get_tool_schemas(self) -> List[Dict[str, Any]]:
-        return [STORE_SCHEMA, SEARCH_SCHEMA, FORGET_SCHEMA, PROFILE_SCHEMA]
+        if not self._enable_custom_containers:
+            return [STORE_SCHEMA, SEARCH_SCHEMA, FORGET_SCHEMA, PROFILE_SCHEMA]
+
+        # When multi-container is enabled, add optional container_tag to relevant tools
+        container_param = {
+            "type": "string",
+            "description": f"Optional container tag. Allowed: {', '.join(self._allowed_containers)}. Defaults to primary ({self._container_tag}).",
+        }
+        schemas = []
+        for base in [STORE_SCHEMA, SEARCH_SCHEMA, FORGET_SCHEMA, PROFILE_SCHEMA]:
+            schema = json.loads(json.dumps(base))  # deep copy
+            schema["parameters"]["properties"]["container_tag"] = container_param
+            schemas.append(schema)
+        return schemas
 
     def _tool_store(self, args: dict) -> str:
         content = str(args.get("content") or "").strip()
         if not content:
             return tool_error("content is required")
+        try:
+            tag = self._resolve_tool_container_tag(args)
+        except ValueError as exc:
+            return tool_error(str(exc))
         metadata = args.get("metadata") or {}
         if not isinstance(metadata, dict):
             metadata = {}
         metadata.setdefault("type", _detect_category(content))
         metadata["source"] = "hermes_tool"
         try:
-            result = self._client.add_memory(content, metadata=metadata, entity_context=self._entity_context)
+            result = self._client.add_memory(content, metadata=metadata, entity_context=self._entity_context, container_tag=tag)
             preview = content[:80] + ("..." if len(content) > 80 else "")
-            return json.dumps({"saved": True, "id": result.get("id", ""), "preview": preview})
+            resp: dict[str, Any] = {"saved": True, "id": result.get("id", ""), "preview": preview}
+            if tag:
+                resp["container_tag"] = tag
+            return json.dumps(resp)
         except Exception as exc:
             return tool_error(f"Failed to store memory: {exc}")
 
@@ -605,22 +706,29 @@ class SupermemoryMemoryProvider(MemoryProvider):
         query = str(args.get("query") or "").strip()
         if not query:
             return tool_error("query is required")
+        try:
+            tag = self._resolve_tool_container_tag(args)
+        except ValueError as exc:
+            return tool_error(str(exc))
         try:
             limit = max(1, min(20, int(args.get("limit", 5) or 5)))
         except Exception:
             limit = 5
         try:
-            results = self._client.search_memories(query, limit=limit)
+            results = self._client.search_memories(query, limit=limit, container_tag=tag)
             formatted = []
             for item in results:
-                entry = {"id": item.get("id", ""), "content": item.get("memory", "")}
+                entry: dict[str, Any] = {"id": item.get("id", ""), "content": item.get("memory", "")}
                 if item.get("similarity") is not None:
                     try:
                         entry["similarity"] = round(float(item["similarity"]) * 100)
                     except Exception:
                         pass
                 formatted.append(entry)
-            return json.dumps({"results": formatted, "count": len(formatted)})
+            resp: dict[str, Any] = {"results": formatted, "count": len(formatted)}
+            if tag:
+                resp["container_tag"] = tag
+            return json.dumps(resp)
         except Exception as exc:
             return tool_error(f"Search failed: {exc}")
 
@@ -629,28 +737,39 @@ class SupermemoryMemoryProvider(MemoryProvider):
         query = str(args.get("query") or "").strip()
         if not memory_id and not query:
             return tool_error("Provide either id or query")
+        try:
+            tag = self._resolve_tool_container_tag(args)
+        except ValueError as exc:
+            return tool_error(str(exc))
         try:
             if memory_id:
-                self._client.forget_memory(memory_id)
+                self._client.forget_memory(memory_id, container_tag=tag)
                 return json.dumps({"forgotten": True, "id": memory_id})
-            return json.dumps(self._client.forget_by_query(query))
+            return json.dumps(self._client.forget_by_query(query, container_tag=tag))
         except Exception as exc:
             return tool_error(f"Forget failed: {exc}")
 
     def _tool_profile(self, args: dict) -> str:
         query = str(args.get("query") or "").strip() or None
         try:
-            profile = self._client.get_profile(query=query)
+            tag = self._resolve_tool_container_tag(args)
+        except ValueError as exc:
+            return tool_error(str(exc))
+        try:
+            profile = self._client.get_profile(query=query, container_tag=tag)
             sections = []
             if profile["static"]:
                 sections.append("## User Profile (Persistent)\n" + "\n".join(f"- {item}" for item in profile["static"]))
             if profile["dynamic"]:
                 sections.append("## Recent Context\n" + "\n".join(f"- {item}" for item in profile["dynamic"]))
-            return json.dumps({
+            resp: dict[str, Any] = {
                 "profile": "\n\n".join(sections),
                 "static_count": len(profile["static"]),
                 "dynamic_count": len(profile["dynamic"]),
-            })
+            }
+            if tag:
+                resp["container_tag"] = tag
+            return json.dumps(resp)
         except Exception as exc:
             return tool_error(f"Profile failed: {exc}")
 

run_agent.py

@@ -66,7 +66,8 @@ from model_tools import (
     handle_function_call,
     check_toolset_requirements,
 )
-from tools.terminal_tool import cleanup_vm
+from tools.terminal_tool import cleanup_vm, get_active_env
+from tools.tool_result_storage import maybe_persist_tool_result, enforce_turn_budget
 from tools.interrupt import set_interrupt as _set_interrupt
 from tools.browser_tool import cleanup_browser
 
@@ -75,6 +76,7 @@ from hermes_constants import OPENROUTER_BASE_URL
 
 # Agent internals extracted to agent/ package for modularity
 from agent.memory_manager import build_memory_context_block
+from agent.retry_utils import jittered_backoff
 from agent.prompt_builder import (
     DEFAULT_AGENT_IDENTITY, PLATFORM_HINTS,
     MEMORY_GUIDANCE, SESSION_SEARCH_GUIDANCE, SKILLS_GUIDANCE,
@@ -85,6 +87,7 @@ from agent.model_metadata import (
     estimate_tokens_rough, estimate_messages_tokens_rough, estimate_request_tokens_rough,
     get_next_probe_tier, parse_context_limit_from_error,
     save_context_length, is_local_endpoint,
+    query_ollama_num_ctx,
 )
 from agent.context_compressor import ContextCompressor
 from agent.subdirectory_hints import SubdirectoryHintTracker
@@ -409,63 +412,6 @@ def _strip_budget_warnings_from_history(messages: list) -> None:
 # Large tool result handler — save oversized output to temp file
 # =========================================================================
 
-# Threshold at which tool results are saved to a file instead of kept inline.
-# 100K chars ≈ 25K tokens — generous for any reasonable output but prevents
-# catastrophic context explosions.
-_LARGE_RESULT_CHARS = 100_000
-
-# How many characters of the original result to include as an inline preview
-# so the model has immediate context about what the tool returned.
-_LARGE_RESULT_PREVIEW_CHARS = 1_500
-
-
-def _save_oversized_tool_result(function_name: str, function_result: str) -> str:
-    """Replace oversized tool results with a file reference + preview.
-
-    When a tool returns more than ``_LARGE_RESULT_CHARS`` characters, the full
-    content is written to a temporary file under ``HERMES_HOME/cache/tool_responses/``
-    and the result sent to the model is replaced with:
-      • a brief head preview  (first ``_LARGE_RESULT_PREVIEW_CHARS`` chars)
-      • the file path so the model can use ``read_file`` / ``search_files``
-
-    Falls back to destructive truncation if the file write fails.
-    """
-    original_len = len(function_result)
-    if original_len <= _LARGE_RESULT_CHARS:
-        return function_result
-
-    # Build the target directory
-    try:
-        response_dir = os.path.join(get_hermes_home(), "cache", "tool_responses")
-        os.makedirs(response_dir, exist_ok=True)
-
-        timestamp = datetime.now().strftime("%Y%m%d_%H%M%S_%f")
-        # Sanitize tool name for use in filename
-        safe_name = re.sub(r"[^\w\-]", "_", function_name)[:40]
-        filename = f"{safe_name}_{timestamp}.txt"
-        filepath = os.path.join(response_dir, filename)
-
-        with open(filepath, "w", encoding="utf-8") as f:
-            f.write(function_result)
-
-        preview = function_result[:_LARGE_RESULT_PREVIEW_CHARS]
-        return (
-            f"{preview}\n\n"
-            f"[Large tool response: {original_len:,} characters total — "
-            f"only the first {_LARGE_RESULT_PREVIEW_CHARS:,} shown above. "
-            f"Full output saved to: {filepath}\n"
-            f"Use read_file or search_files on that path to access the rest.]"
-        )
-    except Exception as exc:
-        # Fall back to destructive truncation if file write fails
-        logger.warning("Failed to save large tool result to file: %s", exc)
-        return (
-            function_result[:_LARGE_RESULT_CHARS]
-            + f"\n\n[Truncated: tool response was {original_len:,} chars, "
-            f"exceeding the {_LARGE_RESULT_CHARS:,} char limit. "
-            f"File save failed: {exc}]"
-        )
-
 
 class AIAgent:
     """
@@ -1216,6 +1162,33 @@ class AIAgent:
         self.session_cost_status = "unknown"
         self.session_cost_source = "none"
         
+        # ── Ollama num_ctx injection ──
+        # Ollama defaults to 2048 context regardless of the model's capabilities.
+        # When running against an Ollama server, detect the model's max context
+        # and pass num_ctx on every chat request so the full window is used.
+        # User override: set model.ollama_num_ctx in config.yaml to cap VRAM use.
+        self._ollama_num_ctx: int | None = None
+        _ollama_num_ctx_override = None
+        if isinstance(_model_cfg, dict):
+            _ollama_num_ctx_override = _model_cfg.get("ollama_num_ctx")
+        if _ollama_num_ctx_override is not None:
+            try:
+                self._ollama_num_ctx = int(_ollama_num_ctx_override)
+            except (TypeError, ValueError):
+                logger.debug("Invalid ollama_num_ctx config value: %r", _ollama_num_ctx_override)
+        if self._ollama_num_ctx is None and self.base_url and is_local_endpoint(self.base_url):
+            try:
+                _detected = query_ollama_num_ctx(self.model, self.base_url)
+                if _detected and _detected > 0:
+                    self._ollama_num_ctx = _detected
+            except Exception as exc:
+                logger.debug("Ollama num_ctx detection failed: %s", exc)
+        if self._ollama_num_ctx and not self.quiet_mode:
+            logger.info(
+                "Ollama num_ctx: will request %d tokens (model max from /api/show)",
+                self._ollama_num_ctx,
+            )
+
         if not self.quiet_mode:
             if compression_enabled:
                 print(f"📊 Context limit: {self.context_compressor.context_length:,} tokens (compress at {int(compression_threshold*100)}% = {self.context_compressor.threshold_tokens:,})")
@@ -5456,6 +5429,15 @@ class AIAgent:
         if _is_nous:
             extra_body["tags"] = ["product=hermes-agent"]
 
+        # Ollama num_ctx: override the 2048 default so the model actually
+        # uses the context window it was trained for.  Passed via the OpenAI
+        # SDK's extra_body → options.num_ctx, which Ollama's OpenAI-compat
+        # endpoint forwards to the runner as --ctx-size.
+        if self._ollama_num_ctx:
+            options = extra_body.get("options", {})
+            options["num_ctx"] = self._ollama_num_ctx
+            extra_body["options"] = options
+
         if extra_body:
             api_kwargs["extra_body"] = extra_body
 
@@ -6224,15 +6206,17 @@ class AIAgent:
                 except Exception as cb_err:
                     logging.debug(f"Tool complete callback error: {cb_err}")
 
-            # Save oversized results to file instead of destructive truncation
-            function_result = _save_oversized_tool_result(name, function_result)
+            function_result = maybe_persist_tool_result(
+                content=function_result,
+                tool_name=name,
+                tool_use_id=tc.id,
+                env=get_active_env(effective_task_id),
+            )
 
-            # Discover subdirectory context files from tool arguments
             subdir_hints = self._subdirectory_hints.check_tool_call(name, args)
             if subdir_hints:
                 function_result += subdir_hints
 
-            # Append tool result message in order
             tool_msg = {
                 "role": "tool",
                 "content": function_result,
@@ -6240,6 +6224,12 @@ class AIAgent:
             }
             messages.append(tool_msg)
 
+        # ── Per-turn aggregate budget enforcement ─────────────────────────
+        num_tools = len(parsed_calls)
+        if num_tools > 0:
+            turn_tool_msgs = messages[-num_tools:]
+            enforce_turn_budget(turn_tool_msgs, env=get_active_env(effective_task_id))
+
         # ── Budget pressure injection ────────────────────────────────────
         budget_warning = self._get_budget_warning(api_call_count)
         if budget_warning and messages and messages[-1].get("role") == "tool":
@@ -6524,8 +6514,12 @@ class AIAgent:
                 except Exception as cb_err:
                     logging.debug(f"Tool complete callback error: {cb_err}")
 
-            # Save oversized results to file instead of destructive truncation
-            function_result = _save_oversized_tool_result(function_name, function_result)
+            function_result = maybe_persist_tool_result(
+                content=function_result,
+                tool_name=function_name,
+                tool_use_id=tool_call.id,
+                env=get_active_env(effective_task_id),
+            )
 
             # Discover subdirectory context files from tool arguments
             subdir_hints = self._subdirectory_hints.check_tool_call(function_name, function_args)
@@ -6563,6 +6557,11 @@ class AIAgent:
             if self.tool_delay > 0 and i < len(assistant_message.tool_calls):
                 time.sleep(self.tool_delay)
 
+        # ── Per-turn aggregate budget enforcement ─────────────────────────
+        num_tools_seq = len(assistant_message.tool_calls)
+        if num_tools_seq > 0:
+            enforce_turn_budget(messages[-num_tools_seq:], env=get_active_env(effective_task_id))
+
         # ── Budget pressure injection ─────────────────────────────────
         # After all tool calls in this turn are processed, check if we're
         # approaching max_iterations. If so, inject a warning into the LAST
@@ -7391,20 +7390,30 @@ class AIAgent:
                             response_invalid = True
                             error_details.append("response.output is not a list")
                         elif not output_items:
-                            # If we reach here, _run_codex_stream's backfill
-                            # from output_item.done events and text-delta
-                            # synthesis both failed to populate output.
-                            _resp_status = getattr(response, "status", None)
-                            _resp_incomplete = getattr(response, "incomplete_details", None)
-                            logging.warning(
-                                "Codex response.output is empty after stream backfill "
-                                "(status=%s, incomplete_details=%s, model=%s). %s",
-                                _resp_status, _resp_incomplete,
-                                getattr(response, "model", None),
-                                f"api_mode={self.api_mode} provider={self.provider}",
-                            )
-                            response_invalid = True
-                            error_details.append("response.output is empty")
+                            # Stream backfill may have failed, but
+                            # _normalize_codex_response can still recover
+                            # from response.output_text. Only mark invalid
+                            # when that fallback is also absent.
+                            _out_text = getattr(response, "output_text", None)
+                            _out_text_stripped = _out_text.strip() if isinstance(_out_text, str) else ""
+                            if _out_text_stripped:
+                                logger.debug(
+                                    "Codex response.output is empty but output_text is present "
+                                    "(%d chars); deferring to normalization.",
+                                    len(_out_text_stripped),
+                                )
+                            else:
+                                _resp_status = getattr(response, "status", None)
+                                _resp_incomplete = getattr(response, "incomplete_details", None)
+                                logger.warning(
+                                    "Codex response.output is empty after stream backfill "
+                                    "(status=%s, incomplete_details=%s, model=%s). %s",
+                                    _resp_status, _resp_incomplete,
+                                    getattr(response, "model", None),
+                                    f"api_mode={self.api_mode} provider={self.provider}",
+                                )
+                                response_invalid = True
+                                error_details.append("response.output is empty")
                     elif self.api_mode == "anthropic_messages":
                         content_blocks = getattr(response, "content", None) if response is not None else None
                         if response is None:
@@ -7494,7 +7503,8 @@ class AIAgent:
                             }
                         
                         # Longer backoff for rate limiting (likely cause of None choices)
-                        wait_time = min(5 * (2 ** (retry_count - 1)), 120)  # 5s, 10s, 20s, 40s, 80s, 120s
+                        # Jittered exponential: 5s base, 120s cap + random jitter
+                        wait_time = jittered_backoff(retry_count, base_delay=5.0, max_delay=120.0)
                         self._vprint(f"{self.log_prefix}⏳ Retrying in {wait_time}s (extended backoff for possible rate limit)...", force=True)
                         logging.warning(f"Invalid API response (retry {retry_count}/{max_retries}): {', '.join(error_details)} | Provider: {provider_name}")
                         
@@ -8351,7 +8361,7 @@ class AIAgent:
                                     _retry_after = min(int(_ra_raw), 120)  # Cap at 2 minutes
                                 except (TypeError, ValueError):
                                     pass
-                    wait_time = _retry_after if _retry_after else min(2 ** retry_count, 60)
+                    wait_time = _retry_after if _retry_after else jittered_backoff(retry_count, base_delay=2.0, max_delay=60.0)
                     if is_rate_limited:
                         self._emit_status(f"⏱️ Rate limit reached. Waiting {wait_time}s before retry (attempt {retry_count + 1}/{max_retries})...")
                     else:

tests/agent/test_auxiliary_client.py

@@ -471,6 +471,23 @@ class TestExplicitProviderRouting:
             client, model = resolve_provider_client("zai")
             assert client is not None
 
+    def test_explicit_google_alias_uses_gemini_credentials(self):
+        """provider='google' should route through the gemini API-key provider."""
+        with (
+            patch("hermes_cli.auth.resolve_api_key_provider_credentials", return_value={
+                "api_key": "gemini-key",
+                "base_url": "https://generativelanguage.googleapis.com/v1beta/openai",
+            }),
+            patch("agent.auxiliary_client.OpenAI") as mock_openai,
+        ):
+            mock_openai.return_value = MagicMock()
+            client, model = resolve_provider_client("google", model="gemini-3.1-pro-preview")
+
+        assert client is not None
+        assert model == "gemini-3.1-pro-preview"
+        assert mock_openai.call_args.kwargs["api_key"] == "gemini-key"
+        assert mock_openai.call_args.kwargs["base_url"] == "https://generativelanguage.googleapis.com/v1beta/openai"
+
     def test_explicit_unknown_returns_none(self, monkeypatch):
         """Unknown provider should return None."""
         client, model = resolve_provider_client("nonexistent-provider")
@@ -624,12 +641,15 @@ class TestVisionClientFallback:
         assert client is None
         assert model is None
 
-    def test_vision_auto_includes_anthropic_when_configured(self, monkeypatch):
-        monkeypatch.setenv("ANTHROPIC_API_KEY", "sk-ant-api03-key")
+    def test_vision_auto_includes_active_provider_when_configured(self, monkeypatch):
+        """Active provider appears in available backends when credentials exist."""
+        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="sk-ant-api03-key"),
+            patch("agent.anthropic_adapter.resolve_anthropic_token", return_value="***"),
         ):
             backends = get_available_vision_backends()
 
@@ -702,88 +722,50 @@ class TestAuxiliaryPoolAwareness:
         assert call_kwargs["base_url"] == "https://api.githubcopilot.com"
         assert call_kwargs["default_headers"]["Editor-Version"]
 
-    def test_vision_auto_uses_anthropic_when_no_higher_priority_backend(self, monkeypatch):
-        monkeypatch.setenv("ANTHROPIC_API_KEY", "sk-ant-api03-key")
+    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="sk-ant-api03-key"),
+            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"
-        assert model == "claude-haiku-4-5-20251001"
 
-    def test_selected_anthropic_provider_is_preferred_for_vision_auto(self, monkeypatch):
+    def test_vision_auto_prefers_openrouter_over_active_provider(self, monkeypatch):
+        """OpenRouter is tried before the active provider in vision auto."""
         monkeypatch.setenv("OPENROUTER_API_KEY", "or-key")
-        monkeypatch.setenv("ANTHROPIC_API_KEY", "sk-ant-api03-key")
-
-        def fake_load_config():
-            return {"model": {"provider": "anthropic", "default": "claude-sonnet-4-6"}}
+        monkeypatch.setenv("ANTHROPIC_API_KEY", "***")
 
         with (
             patch("agent.auxiliary_client._read_nous_auth", return_value=None),
-            patch("agent.anthropic_adapter.build_anthropic_client", return_value=MagicMock()),
-            patch("agent.anthropic_adapter.resolve_anthropic_token", return_value="sk-ant-api03-key"),
+            patch("agent.auxiliary_client._read_main_provider", return_value="anthropic"),
+            patch("agent.auxiliary_client._read_main_model", return_value="claude-sonnet-4"),
             patch("agent.auxiliary_client.OpenAI") as mock_openai,
-            patch("hermes_cli.config.load_config", fake_load_config),
-        ):
-            client, model = get_vision_auxiliary_client()
-
-        assert client is not None
-        assert client.__class__.__name__ == "AnthropicAuxiliaryClient"
-        assert model == "claude-haiku-4-5-20251001"
-
-    def test_selected_codex_provider_short_circuits_vision_auto(self, monkeypatch):
-        def fake_load_config():
-            return {"model": {"provider": "openai-codex", "default": "gpt-5.2-codex"}}
-
-        codex_client = MagicMock()
-        with (
-            patch("hermes_cli.config.load_config", fake_load_config),
-            patch("agent.auxiliary_client._try_codex", return_value=(codex_client, "gpt-5.2-codex")) as mock_codex,
-            patch("agent.auxiliary_client._try_openrouter") as mock_openrouter,
-            patch("agent.auxiliary_client._try_nous") as mock_nous,
-            patch("agent.auxiliary_client._try_anthropic") as mock_anthropic,
-            patch("agent.auxiliary_client._try_custom_endpoint") as mock_custom,
         ):
             provider, client, model = resolve_vision_provider_client()
 
-        assert provider == "openai-codex"
-        assert client is codex_client
-        assert model == "gpt-5.2-codex"
-        mock_codex.assert_called_once()
-        mock_openrouter.assert_not_called()
-        mock_nous.assert_not_called()
-        mock_anthropic.assert_not_called()
-        mock_custom.assert_not_called()
+        # OpenRouter should win over anthropic active provider
+        assert provider == "openrouter"
 
-    def test_vision_auto_includes_codex(self, codex_auth_dir):
-        """Codex supports vision (gpt-5.3-codex), so auto mode should use it."""
-        with patch("agent.auxiliary_client._read_nous_auth", return_value=None), \
-             patch("agent.auxiliary_client.OpenAI"):
-            client, model = get_vision_auxiliary_client()
-        from agent.auxiliary_client import CodexAuxiliaryClient
-        assert isinstance(client, CodexAuxiliaryClient)
-        assert model == "gpt-5.2-codex"
-
-    def test_vision_auto_falls_back_to_custom_endpoint(self, monkeypatch):
-        """Custom endpoint is used as fallback in vision auto mode.
-
-        Many local models (Qwen-VL, LLaVA, etc.) support vision.
-        When no OpenRouter/Nous/Codex is available, try the custom endpoint.
-        """
+    def test_vision_auto_uses_named_custom_as_active_provider(self, monkeypatch):
+        """Named custom provider works as active provider fallback in vision auto."""
         monkeypatch.delenv("OPENROUTER_API_KEY", raising=False)
         monkeypatch.delenv("ANTHROPIC_API_KEY", raising=False)
         with patch("agent.auxiliary_client._read_nous_auth", return_value=None), \
              patch("agent.auxiliary_client._select_pool_entry", return_value=(False, None)), \
-             patch("agent.auxiliary_client._read_codex_access_token", return_value=None), \
-             patch("agent.auxiliary_client._resolve_custom_runtime",
-                   return_value=("http://localhost:1234/v1", "local-key")), \
-             patch("agent.auxiliary_client.OpenAI") as mock_openai:
-            client, model = get_vision_auxiliary_client()
-        assert client is not None  # Custom endpoint picked up as fallback
+             patch("agent.auxiliary_client._read_main_provider", return_value="custom:local"), \
+             patch("agent.auxiliary_client._read_main_model", return_value="my-local-model"), \
+             patch("agent.auxiliary_client.resolve_provider_client",
+                   return_value=(MagicMock(), "my-local-model")) as mock_resolve:
+            provider, client, model = resolve_vision_provider_client()
+        assert client is not None
+        assert provider == "custom:local"
 
     def test_vision_direct_endpoint_override(self, monkeypatch):
         monkeypatch.setenv("OPENROUTER_API_KEY", "or-key")
@@ -822,6 +804,31 @@ class TestAuxiliaryPoolAwareness:
         assert model == "google/gemini-3-flash-preview"
         assert client is not None
 
+    def test_vision_config_google_provider_uses_gemini_credentials(self, monkeypatch):
+        config = {
+            "auxiliary": {
+                "vision": {
+                    "provider": "google",
+                    "model": "gemini-3.1-pro-preview",
+                }
+            }
+        }
+        monkeypatch.setattr("hermes_cli.config.load_config", lambda: config)
+        with (
+            patch("hermes_cli.auth.resolve_api_key_provider_credentials", return_value={
+                "api_key": "gemini-key",
+                "base_url": "https://generativelanguage.googleapis.com/v1beta/openai",
+            }),
+            patch("agent.auxiliary_client.OpenAI") as mock_openai,
+        ):
+            resolved_provider, client, model = resolve_vision_provider_client()
+
+        assert resolved_provider == "gemini"
+        assert client is not None
+        assert model == "gemini-3.1-pro-preview"
+        assert mock_openai.call_args.kwargs["api_key"] == "gemini-key"
+        assert mock_openai.call_args.kwargs["base_url"] == "https://generativelanguage.googleapis.com/v1beta/openai"
+
     def test_vision_forced_main_uses_custom_endpoint(self, monkeypatch):
         """When explicitly forced to 'main', vision CAN use custom endpoint."""
         config = {
@@ -846,7 +853,14 @@ class TestAuxiliaryPoolAwareness:
         monkeypatch.setenv("AUXILIARY_VISION_PROVIDER", "main")
         monkeypatch.delenv("OPENAI_BASE_URL", raising=False)
         monkeypatch.delenv("OPENAI_API_KEY", raising=False)
+        # Clear client cache to avoid stale entries from previous tests
+        from agent.auxiliary_client import _client_cache
+        _client_cache.clear()
         with patch("agent.auxiliary_client._read_nous_auth", return_value=None), \
+             patch("agent.auxiliary_client._read_main_provider", return_value=""), \
+             patch("agent.auxiliary_client._read_main_model", return_value=""), \
+             patch("agent.auxiliary_client._select_pool_entry", return_value=(False, None)), \
+             patch("agent.auxiliary_client._resolve_custom_runtime", return_value=(None, None)), \
              patch("agent.auxiliary_client._read_codex_access_token", return_value=None), \
              patch("agent.auxiliary_client._resolve_api_key_provider", return_value=(None, None)):
             client, model = get_vision_auxiliary_client()

tests/agent/test_auxiliary_config_bridge.py

@@ -13,7 +13,7 @@ from unittest.mock import patch, MagicMock
 import pytest
 import yaml
 
-sys.path.insert(0, os.path.join(os.path.dirname(__file__), ".."))
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), "..", ".."))
 
 
 def _run_auxiliary_bridge(config_dict, monkeypatch):
@@ -199,7 +199,7 @@ class TestGatewayBridgeCodeParity:
 
     def test_gateway_has_auxiliary_bridge(self):
         """The gateway config bridge must include auxiliary.* bridging."""
-        gateway_path = Path(__file__).parent.parent / "gateway" / "run.py"
+        gateway_path = Path(__file__).parent.parent.parent / "gateway" / "run.py"
         content = gateway_path.read_text()
         # Check for key patterns that indicate the bridge is present
         assert "AUXILIARY_VISION_PROVIDER" in content
@@ -213,7 +213,7 @@ class TestGatewayBridgeCodeParity:
 
     def test_gateway_no_compression_env_bridge(self):
         """Gateway should NOT bridge compression config to env vars (config-only)."""
-        gateway_path = Path(__file__).parent.parent / "gateway" / "run.py"
+        gateway_path = Path(__file__).parent.parent.parent / "gateway" / "run.py"
         content = gateway_path.read_text()
         assert "CONTEXT_COMPRESSION_PROVIDER" not in content
         assert "CONTEXT_COMPRESSION_MODEL" not in content

tests/agent/test_auxiliary_named_custom_providers.py

@@ -0,0 +1,151 @@
+"""Tests for named custom provider and 'main' alias resolution in auxiliary_client."""
+
+import os
+from unittest.mock import patch, MagicMock
+
+import pytest
+
+
+@pytest.fixture(autouse=True)
+def _isolate(tmp_path, monkeypatch):
+    """Redirect HERMES_HOME and clear module caches."""
+    hermes_home = tmp_path / ".hermes"
+    hermes_home.mkdir()
+    monkeypatch.setenv("HERMES_HOME", str(hermes_home))
+    # Write a minimal config so load_config doesn't fail
+    (hermes_home / "config.yaml").write_text("model:\n  default: test-model\n")
+
+
+def _write_config(tmp_path, config_dict):
+    """Write a config.yaml to the test HERMES_HOME."""
+    import yaml
+    config_path = tmp_path / ".hermes" / "config.yaml"
+    config_path.write_text(yaml.dump(config_dict))
+
+
+class TestNormalizeVisionProvider:
+    """_normalize_vision_provider should resolve 'main' to actual main provider."""
+
+    def test_main_resolves_to_named_custom(self, tmp_path):
+        _write_config(tmp_path, {
+            "model": {"default": "my-model", "provider": "custom:beans"},
+            "custom_providers": [{"name": "beans", "base_url": "http://localhost/v1"}],
+        })
+        from agent.auxiliary_client import _normalize_vision_provider
+        assert _normalize_vision_provider("main") == "custom:beans"
+
+    def test_main_resolves_to_openrouter(self, tmp_path):
+        _write_config(tmp_path, {
+            "model": {"default": "anthropic/claude-sonnet-4", "provider": "openrouter"},
+        })
+        from agent.auxiliary_client import _normalize_vision_provider
+        assert _normalize_vision_provider("main") == "openrouter"
+
+    def test_main_resolves_to_deepseek(self, tmp_path):
+        _write_config(tmp_path, {
+            "model": {"default": "deepseek-chat", "provider": "deepseek"},
+        })
+        from agent.auxiliary_client import _normalize_vision_provider
+        assert _normalize_vision_provider("main") == "deepseek"
+
+    def test_main_falls_back_to_custom_when_no_provider(self, tmp_path):
+        _write_config(tmp_path, {"model": {"default": "gpt-4o"}})
+        from agent.auxiliary_client import _normalize_vision_provider
+        assert _normalize_vision_provider("main") == "custom"
+
+    def test_bare_provider_name_unchanged(self):
+        from agent.auxiliary_client import _normalize_vision_provider
+        assert _normalize_vision_provider("beans") == "beans"
+        assert _normalize_vision_provider("deepseek") == "deepseek"
+
+    def test_codex_alias_still_works(self):
+        from agent.auxiliary_client import _normalize_vision_provider
+        assert _normalize_vision_provider("codex") == "openai-codex"
+
+    def test_auto_unchanged(self):
+        from agent.auxiliary_client import _normalize_vision_provider
+        assert _normalize_vision_provider("auto") == "auto"
+        assert _normalize_vision_provider(None) == "auto"
+
+
+class TestResolveProviderClientMainAlias:
+    """resolve_provider_client('main', ...) should resolve to actual main provider."""
+
+    def test_main_resolves_to_named_custom_provider(self, tmp_path):
+        _write_config(tmp_path, {
+            "model": {"default": "my-model", "provider": "beans"},
+            "custom_providers": [
+                {"name": "beans", "base_url": "http://beans.local/v1", "api_key": "k"},
+            ],
+        })
+        from agent.auxiliary_client import resolve_provider_client
+        client, model = resolve_provider_client("main", "override-model")
+        assert client is not None
+        assert model == "override-model"
+        assert "beans.local" in str(client.base_url)
+
+    def test_main_with_custom_colon_prefix(self, tmp_path):
+        _write_config(tmp_path, {
+            "model": {"default": "my-model", "provider": "custom:beans"},
+            "custom_providers": [
+                {"name": "beans", "base_url": "http://beans.local/v1", "api_key": "k"},
+            ],
+        })
+        from agent.auxiliary_client import resolve_provider_client
+        client, model = resolve_provider_client("main", "test")
+        assert client is not None
+        assert "beans.local" in str(client.base_url)
+
+
+class TestResolveProviderClientNamedCustom:
+    """resolve_provider_client should resolve named custom providers directly."""
+
+    def test_named_custom_provider(self, tmp_path):
+        _write_config(tmp_path, {
+            "model": {"default": "test-model"},
+            "custom_providers": [
+                {"name": "beans", "base_url": "http://beans.local/v1", "api_key": "k"},
+            ],
+        })
+        from agent.auxiliary_client import resolve_provider_client
+        client, model = resolve_provider_client("beans", "my-model")
+        assert client is not None
+        assert model == "my-model"
+        assert "beans.local" in str(client.base_url)
+
+    def test_named_custom_provider_default_model(self, tmp_path):
+        _write_config(tmp_path, {
+            "model": {"default": "main-model"},
+            "custom_providers": [
+                {"name": "beans", "base_url": "http://beans.local/v1", "api_key": "k"},
+            ],
+        })
+        from agent.auxiliary_client import resolve_provider_client
+        client, model = resolve_provider_client("beans")
+        assert client is not None
+        # Should use _read_main_model() fallback
+        assert model == "main-model"
+
+    def test_named_custom_no_api_key_uses_fallback(self, tmp_path):
+        _write_config(tmp_path, {
+            "model": {"default": "test"},
+            "custom_providers": [
+                {"name": "local", "base_url": "http://localhost:8080/v1"},
+            ],
+        })
+        from agent.auxiliary_client import resolve_provider_client
+        client, model = resolve_provider_client("local", "test")
+        assert client is not None
+        # no-key-required should be used
+
+    def test_nonexistent_named_custom_falls_through(self, tmp_path):
+        _write_config(tmp_path, {
+            "model": {"default": "test"},
+            "custom_providers": [
+                {"name": "beans", "base_url": "http://beans.local/v1"},
+            ],
+        })
+        from agent.auxiliary_client import resolve_provider_client
+        # "coffee" doesn't exist in custom_providers
+        client, model = resolve_provider_client("coffee", "test")
+        assert client is None

tests/agent/test_minimax_auxiliary_url.py

@@ -0,0 +1,42 @@
+"""Tests for MiniMax auxiliary client URL normalization.
+
+MiniMax and MiniMax-CN set inference_base_url to the /anthropic path.
+The auxiliary client uses the OpenAI SDK, which needs /v1 instead.
+"""
+
+import sys
+import os
+
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), "..", ".."))
+
+from agent.auxiliary_client import _to_openai_base_url
+
+
+class TestToOpenaiBaseUrl:
+    def test_minimax_global_anthropic_suffix_replaced(self):
+        assert _to_openai_base_url("https://api.minimax.io/anthropic") == "https://api.minimax.io/v1"
+
+    def test_minimax_cn_anthropic_suffix_replaced(self):
+        assert _to_openai_base_url("https://api.minimaxi.com/anthropic") == "https://api.minimaxi.com/v1"
+
+    def test_trailing_slash_stripped_before_replace(self):
+        assert _to_openai_base_url("https://api.minimax.io/anthropic/") == "https://api.minimax.io/v1"
+
+    def test_v1_url_unchanged(self):
+        assert _to_openai_base_url("https://api.openai.com/v1") == "https://api.openai.com/v1"
+
+    def test_openrouter_url_unchanged(self):
+        assert _to_openai_base_url("https://openrouter.ai/api/v1") == "https://openrouter.ai/api/v1"
+
+    def test_anthropic_domain_unchanged(self):
+        """api.anthropic.com doesn't end with /anthropic — should be untouched."""
+        assert _to_openai_base_url("https://api.anthropic.com") == "https://api.anthropic.com"
+
+    def test_anthropic_in_subpath_unchanged(self):
+        assert _to_openai_base_url("https://example.com/anthropic/extra") == "https://example.com/anthropic/extra"
+
+    def test_empty_string(self):
+        assert _to_openai_base_url("") == ""
+
+    def test_none(self):
+        assert _to_openai_base_url(None) == ""

tests/agent/test_minimax_provider.py

@@ -0,0 +1,105 @@
+"""Tests for MiniMax provider hardening — context lengths, thinking guard, catalog."""
+
+
+class TestMinimaxContextLengths:
+    """Verify per-model context length entries for MiniMax models."""
+
+    def test_m1_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-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"
+
+    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
+
+
+
+class TestMinimaxThinkingGuard:
+    """Verify that build_anthropic_kwargs does NOT add thinking params for MiniMax models."""
+
+    def test_no_thinking_for_minimax_m27(self):
+        from agent.anthropic_adapter import build_anthropic_kwargs
+        kwargs = build_anthropic_kwargs(
+            model="MiniMax-M2.7",
+            messages=[{"role": "user", "content": "hello"}],
+            tools=None,
+            max_tokens=4096,
+            reasoning_config={"enabled": True, "effort": "medium"},
+        )
+        assert "thinking" not in kwargs
+        assert "output_config" not in kwargs
+
+    def test_no_thinking_for_minimax_m1(self):
+        from agent.anthropic_adapter import build_anthropic_kwargs
+        kwargs = build_anthropic_kwargs(
+            model="MiniMax-M1-128k",
+            messages=[{"role": "user", "content": "hello"}],
+            tools=None,
+            max_tokens=4096,
+            reasoning_config={"enabled": True, "effort": "high"},
+        )
+        assert "thinking" not in kwargs
+
+    def test_thinking_still_works_for_claude(self):
+        from agent.anthropic_adapter import build_anthropic_kwargs
+        kwargs = build_anthropic_kwargs(
+            model="claude-sonnet-4-20250514",
+            messages=[{"role": "user", "content": "hello"}],
+            tools=None,
+            max_tokens=4096,
+            reasoning_config={"enabled": True, "effort": "medium"},
+        )
+        assert "thinking" in kwargs
+
+
+class TestMinimaxAuxModel:
+    """Verify auxiliary model is standard (not highspeed)."""
+
+    def test_minimax_aux_is_standard(self):
+        from agent.auxiliary_client import _API_KEY_PROVIDER_AUX_MODELS
+        assert _API_KEY_PROVIDER_AUX_MODELS["minimax"] == "MiniMax-M2.7"
+        assert _API_KEY_PROVIDER_AUX_MODELS["minimax-cn"] == "MiniMax-M2.7"
+
+    def test_minimax_aux_not_highspeed(self):
+        from agent.auxiliary_client import _API_KEY_PROVIDER_AUX_MODELS
+        assert "highspeed" not in _API_KEY_PROVIDER_AUX_MODELS["minimax"]
+        assert "highspeed" not in _API_KEY_PROVIDER_AUX_MODELS["minimax-cn"]
+
+
+class TestMinimaxModelCatalog:
+    """Verify the model catalog includes M1 family and excludes deprecated models."""
+
+    def test_catalog_includes_m1_family(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
+
+    def test_catalog_excludes_deprecated(self):
+        from hermes_cli.models import _PROVIDER_MODELS
+        for provider in ("minimax", "minimax-cn"):
+            models = _PROVIDER_MODELS[provider]
+            assert "MiniMax-M2.1" not in models
+
+    def test_catalog_excludes_highspeed(self):
+        from hermes_cli.models import _PROVIDER_MODELS
+        for provider in ("minimax", "minimax-cn"):
+            models = _PROVIDER_MODELS[provider]
+            assert "MiniMax-M2.7-highspeed" not in models
+            assert "MiniMax-M2.5-highspeed" not in models

tests/cli/test_cli_provider_resolution.py

@@ -330,7 +330,7 @@ def test_model_flow_nous_prints_subscription_guidance_without_mutating_explicit_
         "hermes_cli.auth.fetch_nous_models",
         lambda *args, **kwargs: ["claude-opus-4-6"],
     )
-    monkeypatch.setattr("hermes_cli.auth._prompt_model_selection", lambda model_ids, current_model="", pricing=None: "claude-opus-4-6")
+    monkeypatch.setattr("hermes_cli.auth._prompt_model_selection", lambda model_ids, current_model="", pricing=None, **kw: "claude-opus-4-6")
     monkeypatch.setattr("hermes_cli.auth._save_model_choice", lambda model: None)
     monkeypatch.setattr("hermes_cli.auth._update_config_for_provider", lambda provider, url: None)
     monkeypatch.setattr(
@@ -368,7 +368,7 @@ def test_model_flow_nous_applies_managed_tts_default_when_unconfigured(monkeypat
         "hermes_cli.auth.fetch_nous_models",
         lambda *args, **kwargs: ["claude-opus-4-6"],
     )
-    monkeypatch.setattr("hermes_cli.auth._prompt_model_selection", lambda model_ids, current_model="", pricing=None: "claude-opus-4-6")
+    monkeypatch.setattr("hermes_cli.auth._prompt_model_selection", lambda model_ids, current_model="", pricing=None, **kw: "claude-opus-4-6")
     monkeypatch.setattr("hermes_cli.auth._save_model_choice", lambda model: None)
     monkeypatch.setattr("hermes_cli.auth._update_config_for_provider", lambda provider, url: None)
     monkeypatch.setattr(

tests/cli/test_cli_retry.py

@@ -1,6 +1,6 @@
 """Regression tests for CLI /retry history replacement semantics."""
 
-from tests.test_cli_init import _make_cli
+from tests.cli.test_cli_init import _make_cli
 
 
 def test_retry_last_truncates_history_before_requeueing_message():

tests/cli/test_cli_skin_integration.py

@@ -0,0 +1,98 @@
+from types import SimpleNamespace
+from unittest.mock import MagicMock, patch
+
+from cli import HermesCLI, _rich_text_from_ansi
+from hermes_cli.skin_engine import get_active_skin, set_active_skin
+
+
+def _make_cli_stub():
+    cli = HermesCLI.__new__(HermesCLI)
+    cli._sudo_state = None
+    cli._secret_state = None
+    cli._approval_state = None
+    cli._clarify_state = None
+    cli._clarify_freetext = False
+    cli._command_running = False
+    cli._agent_running = False
+    cli._voice_recording = False
+    cli._voice_processing = False
+    cli._voice_mode = False
+    cli._command_spinner_frame = lambda: "⟳"
+    cli._tui_style_base = {
+        "prompt": "#fff",
+        "input-area": "#fff",
+        "input-rule": "#aaa",
+        "prompt-working": "#888 italic",
+    }
+    cli._app = SimpleNamespace(style=None)
+    cli._invalidate = MagicMock()
+    return cli
+
+
+class TestCliSkinPromptIntegration:
+    def test_default_prompt_fragments_use_default_symbol(self):
+        cli = _make_cli_stub()
+
+        set_active_skin("default")
+        assert cli._get_tui_prompt_fragments() == [("class:prompt", "❯ ")]
+
+    def test_ares_prompt_fragments_use_skin_symbol(self):
+        cli = _make_cli_stub()
+
+        set_active_skin("ares")
+        assert cli._get_tui_prompt_fragments() == [("class:prompt", "⚔ ❯ ")]
+
+    def test_secret_prompt_fragments_preserve_secret_state(self):
+        cli = _make_cli_stub()
+        cli._secret_state = {"response_queue": object()}
+
+        set_active_skin("ares")
+        assert cli._get_tui_prompt_fragments() == [("class:sudo-prompt", "🔑 ❯ ")]
+
+    def test_icon_only_skin_symbol_still_visible_in_special_states(self):
+        cli = _make_cli_stub()
+        cli._secret_state = {"response_queue": object()}
+
+        with patch("hermes_cli.skin_engine.get_active_prompt_symbol", return_value="⚔ "):
+            assert cli._get_tui_prompt_fragments() == [("class:sudo-prompt", "🔑 ⚔ ")]
+
+    def test_build_tui_style_dict_uses_skin_overrides(self):
+        cli = _make_cli_stub()
+
+        set_active_skin("ares")
+        skin = get_active_skin()
+        style_dict = cli._build_tui_style_dict()
+
+        assert style_dict["prompt"] == skin.get_color("prompt")
+        assert style_dict["input-rule"] == skin.get_color("input_rule")
+        assert style_dict["prompt-working"] == f"{skin.get_color('banner_dim')} italic"
+        assert style_dict["approval-title"] == f"{skin.get_color('ui_warn')} bold"
+
+    def test_apply_tui_skin_style_updates_running_app(self):
+        cli = _make_cli_stub()
+
+        set_active_skin("ares")
+        assert cli._apply_tui_skin_style() is True
+        assert cli._app.style is not None
+        cli._invalidate.assert_called_once_with(min_interval=0.0)
+
+    def test_handle_skin_command_refreshes_live_tui(self, capsys):
+        cli = _make_cli_stub()
+
+        with patch("cli.save_config_value", return_value=True):
+            cli._handle_skin_command("/skin ares")
+
+        output = capsys.readouterr().out
+        assert "Skin set to: ares (saved)" in output
+        assert "Prompt + TUI colors updated." in output
+        assert cli._app.style is not None
+
+
+class TestAnsiRichTextHelper:
+    def test_preserves_literal_brackets(self):
+        text = _rich_text_from_ansi("[notatag] literal")
+        assert text.plain == "[notatag] literal"
+
+    def test_strips_ansi_but_keeps_plain_text(self):
+        text = _rich_text_from_ansi("\x1b[31mred\x1b[0m")
+        assert text.plain == "red"

tests/cron/test_jobs.py

@@ -339,6 +339,36 @@ class TestMarkJobRun:
         assert updated["last_status"] == "error"
         assert updated["last_error"] == "timeout"
 
+    def test_delivery_error_tracked_separately(self, tmp_cron_dir):
+        """Agent succeeds but delivery fails — both tracked independently."""
+        job = create_job(prompt="Report", schedule="every 1h")
+        mark_job_run(job["id"], success=True, delivery_error="platform 'telegram' not configured")
+        updated = get_job(job["id"])
+        assert updated["last_status"] == "ok"
+        assert updated["last_error"] is None
+        assert updated["last_delivery_error"] == "platform 'telegram' not configured"
+
+    def test_delivery_error_cleared_on_success(self, tmp_cron_dir):
+        """Successful delivery clears the previous delivery error."""
+        job = create_job(prompt="Report", schedule="every 1h")
+        mark_job_run(job["id"], success=True, delivery_error="network timeout")
+        updated = get_job(job["id"])
+        assert updated["last_delivery_error"] == "network timeout"
+        # Next run delivers successfully
+        mark_job_run(job["id"], success=True, delivery_error=None)
+        updated = get_job(job["id"])
+        assert updated["last_delivery_error"] is None
+
+    def test_both_agent_and_delivery_error(self, tmp_cron_dir):
+        """Agent fails AND delivery fails — both errors recorded."""
+        job = create_job(prompt="Report", schedule="every 1h")
+        mark_job_run(job["id"], success=False, error="model timeout",
+                     delivery_error="platform 'discord' not enabled")
+        updated = get_job(job["id"])
+        assert updated["last_status"] == "error"
+        assert updated["last_error"] == "model timeout"
+        assert updated["last_delivery_error"] == "platform 'discord' not enabled"
+
 
 class TestAdvanceNextRun:
     """Tests for advance_next_run() — crash-safety for recurring jobs."""

tests/cron/test_scheduler.py

@@ -508,6 +508,90 @@ class TestDeliverResultWrapping:
         assert send_mock.call_args.kwargs["thread_id"] == "17585"
 
 
+class TestDeliverResultErrorReturns:
+    """Verify _deliver_result returns error strings on failure, None on success."""
+
+    def test_returns_none_on_successful_delivery(self):
+        from gateway.config import Platform
+
+        pconfig = MagicMock()
+        pconfig.enabled = True
+        mock_cfg = MagicMock()
+        mock_cfg.platforms = {Platform.TELEGRAM: pconfig}
+
+        with patch("gateway.config.load_gateway_config", return_value=mock_cfg), \
+             patch("tools.send_message_tool._send_to_platform", new=AsyncMock(return_value={"success": True})):
+            job = {
+                "id": "ok-job",
+                "deliver": "origin",
+                "origin": {"platform": "telegram", "chat_id": "123"},
+            }
+            result = _deliver_result(job, "Output.")
+        assert result is None
+
+    def test_returns_none_for_local_delivery(self):
+        """local-only jobs don't deliver — not a failure."""
+        job = {"id": "local-job", "deliver": "local"}
+        result = _deliver_result(job, "Output.")
+        assert result is None
+
+    def test_returns_error_for_unknown_platform(self):
+        job = {
+            "id": "bad-platform",
+            "deliver": "origin",
+            "origin": {"platform": "fax", "chat_id": "123"},
+        }
+        with patch("gateway.config.load_gateway_config"):
+            result = _deliver_result(job, "Output.")
+        assert result is not None
+        assert "unknown platform" in result
+
+    def test_returns_error_when_platform_disabled(self):
+        from gateway.config import Platform
+
+        pconfig = MagicMock()
+        pconfig.enabled = False
+        mock_cfg = MagicMock()
+        mock_cfg.platforms = {Platform.TELEGRAM: pconfig}
+
+        with patch("gateway.config.load_gateway_config", return_value=mock_cfg):
+            job = {
+                "id": "disabled",
+                "deliver": "origin",
+                "origin": {"platform": "telegram", "chat_id": "123"},
+            }
+            result = _deliver_result(job, "Output.")
+        assert result is not None
+        assert "not configured" in result
+
+    def test_returns_error_on_send_failure(self):
+        from gateway.config import Platform
+
+        pconfig = MagicMock()
+        pconfig.enabled = True
+        mock_cfg = MagicMock()
+        mock_cfg.platforms = {Platform.TELEGRAM: pconfig}
+
+        with patch("gateway.config.load_gateway_config", return_value=mock_cfg), \
+             patch("tools.send_message_tool._send_to_platform", new=AsyncMock(return_value={"error": "rate limited"})):
+            job = {
+                "id": "rate-limited",
+                "deliver": "origin",
+                "origin": {"platform": "telegram", "chat_id": "123"},
+            }
+            result = _deliver_result(job, "Output.")
+        assert result is not None
+        assert "rate limited" in result
+
+    def test_returns_error_for_unresolved_target(self, monkeypatch):
+        """Non-local delivery with no resolvable target should return an error."""
+        monkeypatch.delenv("TELEGRAM_HOME_CHANNEL", raising=False)
+        job = {"id": "no-target", "deliver": "telegram"}
+        result = _deliver_result(job, "Output.")
+        assert result is not None
+        assert "no delivery target" in result
+
+
 class TestRunJobSessionPersistence:
     def test_run_job_passes_session_db_and_cron_platform(self, tmp_path):
         job = {

tests/environments/benchmarks/test_terminalbench2_env_security.py

@@ -0,0 +1,164 @@
+"""Security tests for Terminal-Bench 2 archive extraction."""
+
+import base64
+import importlib
+import io
+import sys
+import tarfile
+import types
+
+import pytest
+
+
+def _stub_module(name: str, **attrs):
+    module = types.ModuleType(name)
+    for key, value in attrs.items():
+        setattr(module, key, value)
+    return module
+
+
+def _load_terminalbench_module(monkeypatch):
+    class _EvalHandlingEnum:
+        STOP_TRAIN = "stop_train"
+
+    class _APIServerConfig:
+        def __init__(self, *args, **kwargs):
+            self.args = args
+            self.kwargs = kwargs
+
+    class _AgentResult:
+        pass
+
+    class _HermesAgentLoop:
+        pass
+
+    class _HermesAgentBaseEnv:
+        pass
+
+    class _HermesAgentEnvConfig:
+        pass
+
+    class _ToolContext:
+        pass
+
+    stub_modules = {
+        "atroposlib": _stub_module("atroposlib"),
+        "atroposlib.envs": _stub_module("atroposlib.envs"),
+        "atroposlib.envs.base": _stub_module(
+            "atroposlib.envs.base",
+            EvalHandlingEnum=_EvalHandlingEnum,
+        ),
+        "atroposlib.envs.server_handling": _stub_module("atroposlib.envs.server_handling"),
+        "atroposlib.envs.server_handling.server_manager": _stub_module(
+            "atroposlib.envs.server_handling.server_manager",
+            APIServerConfig=_APIServerConfig,
+        ),
+        "environments.agent_loop": _stub_module(
+            "environments.agent_loop",
+            AgentResult=_AgentResult,
+            HermesAgentLoop=_HermesAgentLoop,
+        ),
+        "environments.hermes_base_env": _stub_module(
+            "environments.hermes_base_env",
+            HermesAgentBaseEnv=_HermesAgentBaseEnv,
+            HermesAgentEnvConfig=_HermesAgentEnvConfig,
+        ),
+        "environments.tool_context": _stub_module(
+            "environments.tool_context",
+            ToolContext=_ToolContext,
+        ),
+        "tools.terminal_tool": _stub_module(
+            "tools.terminal_tool",
+            register_task_env_overrides=lambda *args, **kwargs: None,
+            clear_task_env_overrides=lambda *args, **kwargs: None,
+            cleanup_vm=lambda *args, **kwargs: None,
+        ),
+    }
+
+    stub_modules["atroposlib"].envs = stub_modules["atroposlib.envs"]
+    stub_modules["atroposlib.envs"].base = stub_modules["atroposlib.envs.base"]
+    stub_modules["atroposlib.envs"].server_handling = stub_modules["atroposlib.envs.server_handling"]
+    stub_modules["atroposlib.envs.server_handling"].server_manager = stub_modules[
+        "atroposlib.envs.server_handling.server_manager"
+    ]
+
+    for name, module in stub_modules.items():
+        monkeypatch.setitem(sys.modules, name, module)
+
+    module_name = "environments.benchmarks.terminalbench_2.terminalbench2_env"
+    sys.modules.pop(module_name, None)
+    return importlib.import_module(module_name)
+
+
+def _build_tar_b64(entries):
+    buf = io.BytesIO()
+    with tarfile.open(fileobj=buf, mode="w:gz") as tar:
+        for entry in entries:
+            kind = entry["kind"]
+            info = tarfile.TarInfo(entry["name"])
+
+            if kind == "dir":
+                info.type = tarfile.DIRTYPE
+                tar.addfile(info)
+                continue
+
+            if kind == "file":
+                data = entry["data"].encode("utf-8")
+                info.size = len(data)
+                tar.addfile(info, io.BytesIO(data))
+                continue
+
+            if kind == "symlink":
+                info.type = tarfile.SYMTYPE
+                info.linkname = entry["target"]
+                tar.addfile(info)
+                continue
+
+            raise ValueError(f"Unknown tar entry kind: {kind}")
+
+    return base64.b64encode(buf.getvalue()).decode("ascii")
+
+
+def test_extract_base64_tar_allows_safe_files(tmp_path, monkeypatch):
+    module = _load_terminalbench_module(monkeypatch)
+    archive = _build_tar_b64(
+        [
+            {"kind": "dir", "name": "nested"},
+            {"kind": "file", "name": "nested/hello.txt", "data": "hello"},
+        ]
+    )
+
+    target = tmp_path / "extract"
+    module._extract_base64_tar(archive, target)
+
+    assert (target / "nested" / "hello.txt").read_text(encoding="utf-8") == "hello"
+
+
+def test_extract_base64_tar_rejects_path_traversal(tmp_path, monkeypatch):
+    module = _load_terminalbench_module(monkeypatch)
+    archive = _build_tar_b64(
+        [
+            {"kind": "file", "name": "../escape.txt", "data": "owned"},
+        ]
+    )
+
+    target = tmp_path / "extract"
+    with pytest.raises(ValueError, match="Unsafe archive member path"):
+        module._extract_base64_tar(archive, target)
+
+    assert not (tmp_path / "escape.txt").exists()
+
+
+def test_extract_base64_tar_rejects_symlinks(tmp_path, monkeypatch):
+    module = _load_terminalbench_module(monkeypatch)
+    archive = _build_tar_b64(
+        [
+            {"kind": "symlink", "name": "link", "target": "../../escape.txt"},
+        ]
+    )
+
+    target = tmp_path / "extract"
+    with pytest.raises(ValueError, match="Unsupported archive member type"):
+        module._extract_base64_tar(archive, target)
+
+    assert not (target / "link").exists()

tests/gateway/test_api_server.py

@@ -439,7 +439,7 @@ class TestChatCompletionsEndpoint:
                 tp_cb = kwargs.get("tool_progress_callback")
                 # Simulate tool progress before streaming content
                 if tp_cb:
-                    tp_cb("terminal", "ls -la", {"command": "ls -la"})
+                    tp_cb("tool.started", "terminal", "ls -la", {"command": "ls -la"})
                 if cb:
                     await asyncio.sleep(0.05)
                     cb("Here are the files.")
@@ -476,8 +476,8 @@ class TestChatCompletionsEndpoint:
                 cb = kwargs.get("stream_delta_callback")
                 tp_cb = kwargs.get("tool_progress_callback")
                 if tp_cb:
-                    tp_cb("_thinking", "some internal state", {})
-                    tp_cb("web_search", "Python docs", {"query": "Python docs"})
+                    tp_cb("tool.started", "_thinking", "some internal state", {})
+                    tp_cb("tool.started", "web_search", "Python docs", {"query": "Python docs"})
                 if cb:
                     await asyncio.sleep(0.05)
                     cb("Found it.")

tests/gateway/test_discord_channel_controls.py

@@ -0,0 +1,343 @@
+"""Tests for Discord ignored_channels and no_thread_channels config."""
+
+from types import SimpleNamespace
+from datetime import datetime, timezone
+from unittest.mock import AsyncMock, MagicMock
+import sys
+
+import pytest
+
+from gateway.config import PlatformConfig
+
+
+def _ensure_discord_mock():
+    """Install a mock discord module when discord.py isn't available."""
+    if "discord" in sys.modules and hasattr(sys.modules["discord"], "__file__"):
+        return
+
+    discord_mod = MagicMock()
+    discord_mod.Intents.default.return_value = MagicMock()
+    discord_mod.Client = MagicMock
+    discord_mod.File = MagicMock
+    discord_mod.DMChannel = type("DMChannel", (), {})
+    discord_mod.Thread = type("Thread", (), {})
+    discord_mod.ForumChannel = type("ForumChannel", (), {})
+    discord_mod.ui = SimpleNamespace(View=object, button=lambda *a, **k: (lambda fn: fn), Button=object)
+    discord_mod.ButtonStyle = SimpleNamespace(success=1, primary=2, secondary=2, danger=3, green=1, grey=2, blurple=2, red=3)
+    discord_mod.Color = SimpleNamespace(orange=lambda: 1, green=lambda: 2, blue=lambda: 3, red=lambda: 4, purple=lambda: 5)
+    discord_mod.Interaction = object
+    discord_mod.Embed = MagicMock
+    discord_mod.app_commands = SimpleNamespace(
+        describe=lambda **kwargs: (lambda fn: fn),
+        choices=lambda **kwargs: (lambda fn: fn),
+        Choice=lambda **kwargs: SimpleNamespace(**kwargs),
+    )
+
+    ext_mod = MagicMock()
+    commands_mod = MagicMock()
+    commands_mod.Bot = MagicMock
+    ext_mod.commands = commands_mod
+
+    sys.modules.setdefault("discord", discord_mod)
+    sys.modules.setdefault("discord.ext", ext_mod)
+    sys.modules.setdefault("discord.ext.commands", commands_mod)
+
+
+_ensure_discord_mock()
+
+import gateway.platforms.discord as discord_platform  # noqa: E402
+from gateway.platforms.discord import DiscordAdapter  # noqa: E402
+
+
+class FakeDMChannel:
+    def __init__(self, channel_id: int = 1, name: str = "dm"):
+        self.id = channel_id
+        self.name = name
+
+
+class FakeTextChannel:
+    def __init__(self, channel_id: int = 1, name: str = "general", guild_name: str = "Hermes Server"):
+        self.id = channel_id
+        self.name = name
+        self.guild = SimpleNamespace(name=guild_name)
+        self.topic = None
+
+
+class FakeThread:
+    def __init__(self, channel_id: int = 1, name: str = "thread", parent=None, guild_name: str = "Hermes Server"):
+        self.id = channel_id
+        self.name = name
+        self.parent = parent
+        self.parent_id = getattr(parent, "id", None)
+        self.guild = getattr(parent, "guild", None) or SimpleNamespace(name=guild_name)
+        self.topic = None
+
+
+@pytest.fixture
+def adapter(monkeypatch):
+    monkeypatch.setattr(discord_platform.discord, "DMChannel", FakeDMChannel, raising=False)
+    monkeypatch.setattr(discord_platform.discord, "Thread", FakeThread, raising=False)
+
+    config = PlatformConfig(enabled=True, token="fake-token")
+    adapter = DiscordAdapter(config)
+    adapter._client = SimpleNamespace(user=SimpleNamespace(id=999))
+    adapter.handle_message = AsyncMock()
+    return adapter
+
+
+def make_message(*, channel, content: str, mentions=None):
+    author = SimpleNamespace(id=42, display_name="TestUser", name="TestUser")
+    return SimpleNamespace(
+        id=123,
+        content=content,
+        mentions=list(mentions or []),
+        attachments=[],
+        reference=None,
+        created_at=datetime.now(timezone.utc),
+        channel=channel,
+        author=author,
+    )
+
+
+# ── ignored_channels ─────────────────────────────────────────────────
+
+
+@pytest.mark.asyncio
+async def test_ignored_channel_blocks_message(adapter, monkeypatch):
+    """Messages in ignored channels are silently dropped."""
+    monkeypatch.setenv("DISCORD_REQUIRE_MENTION", "false")
+    monkeypatch.setenv("DISCORD_IGNORED_CHANNELS", "500")
+    monkeypatch.delenv("DISCORD_FREE_RESPONSE_CHANNELS", raising=False)
+
+    message = make_message(channel=FakeTextChannel(channel_id=500), content="hello")
+    await adapter._handle_message(message)
+
+    adapter.handle_message.assert_not_awaited()
+
+
+@pytest.mark.asyncio
+async def test_ignored_channel_blocks_even_with_mention(adapter, monkeypatch):
+    """Ignored channels take priority — even @mentions are dropped."""
+    monkeypatch.setenv("DISCORD_REQUIRE_MENTION", "true")
+    monkeypatch.setenv("DISCORD_IGNORED_CHANNELS", "500")
+
+    bot_user = adapter._client.user
+    message = make_message(
+        channel=FakeTextChannel(channel_id=500),
+        content=f"<@{bot_user.id}> hello",
+        mentions=[bot_user],
+    )
+    await adapter._handle_message(message)
+
+    adapter.handle_message.assert_not_awaited()
+
+
+@pytest.mark.asyncio
+async def test_non_ignored_channel_processes_normally(adapter, monkeypatch):
+    """Channels not in the ignored list process normally."""
+    monkeypatch.setenv("DISCORD_REQUIRE_MENTION", "false")
+    monkeypatch.setenv("DISCORD_IGNORED_CHANNELS", "500,600")
+    monkeypatch.delenv("DISCORD_FREE_RESPONSE_CHANNELS", raising=False)
+
+    message = make_message(channel=FakeTextChannel(channel_id=700), content="hello")
+    await adapter._handle_message(message)
+
+    adapter.handle_message.assert_awaited_once()
+
+
+@pytest.mark.asyncio
+async def test_ignored_channels_csv_parsing(adapter, monkeypatch):
+    """Multiple channel IDs are parsed correctly from CSV."""
+    monkeypatch.setenv("DISCORD_REQUIRE_MENTION", "false")
+    monkeypatch.setenv("DISCORD_IGNORED_CHANNELS", "500, 600 , 700")
+    monkeypatch.delenv("DISCORD_FREE_RESPONSE_CHANNELS", raising=False)
+
+    for ch_id in (500, 600, 700):
+        adapter.handle_message.reset_mock()
+        message = make_message(channel=FakeTextChannel(channel_id=ch_id), content="hello")
+        await adapter._handle_message(message)
+        adapter.handle_message.assert_not_awaited()
+
+
+@pytest.mark.asyncio
+async def test_ignored_channels_empty_string_ignores_nothing(adapter, monkeypatch):
+    """Empty DISCORD_IGNORED_CHANNELS means nothing is ignored."""
+    monkeypatch.setenv("DISCORD_REQUIRE_MENTION", "false")
+    monkeypatch.setenv("DISCORD_IGNORED_CHANNELS", "")
+    monkeypatch.delenv("DISCORD_FREE_RESPONSE_CHANNELS", raising=False)
+
+    message = make_message(channel=FakeTextChannel(channel_id=500), content="hello")
+    await adapter._handle_message(message)
+
+    adapter.handle_message.assert_awaited_once()
+
+
+@pytest.mark.asyncio
+async def test_ignored_channel_thread_parent_match(adapter, monkeypatch):
+    """Thread whose parent channel is ignored should also be ignored."""
+    monkeypatch.setenv("DISCORD_REQUIRE_MENTION", "false")
+    monkeypatch.setenv("DISCORD_IGNORED_CHANNELS", "500")
+    monkeypatch.delenv("DISCORD_FREE_RESPONSE_CHANNELS", raising=False)
+
+    parent = FakeTextChannel(channel_id=500, name="ignored-channel")
+    thread = FakeThread(channel_id=501, name="thread-in-ignored", parent=parent)
+    message = make_message(channel=thread, content="hello from thread")
+    await adapter._handle_message(message)
+
+    adapter.handle_message.assert_not_awaited()
+
+
+@pytest.mark.asyncio
+async def test_dms_unaffected_by_ignored_channels(adapter, monkeypatch):
+    """DMs should never be affected by ignored_channels."""
+    monkeypatch.setenv("DISCORD_IGNORED_CHANNELS", "500")
+    monkeypatch.delenv("DISCORD_FREE_RESPONSE_CHANNELS", raising=False)
+
+    message = make_message(channel=FakeDMChannel(channel_id=500), content="dm hello")
+    await adapter._handle_message(message)
+
+    adapter.handle_message.assert_awaited_once()
+
+
+# ── no_thread_channels ───────────────────────────────────────────────
+
+
+@pytest.mark.asyncio
+async def test_no_thread_channel_skips_auto_thread(adapter, monkeypatch):
+    """Channels in no_thread_channels should not auto-create threads."""
+    monkeypatch.setenv("DISCORD_REQUIRE_MENTION", "false")
+    monkeypatch.setenv("DISCORD_NO_THREAD_CHANNELS", "800")
+    monkeypatch.delenv("DISCORD_AUTO_THREAD", raising=False)
+    monkeypatch.delenv("DISCORD_IGNORED_CHANNELS", raising=False)
+    monkeypatch.delenv("DISCORD_FREE_RESPONSE_CHANNELS", raising=False)
+
+    adapter._auto_create_thread = AsyncMock(return_value=FakeThread(channel_id=999))
+
+    message = make_message(channel=FakeTextChannel(channel_id=800), content="hello")
+    await adapter._handle_message(message)
+
+    adapter._auto_create_thread.assert_not_awaited()
+    adapter.handle_message.assert_awaited_once()
+    event = adapter.handle_message.await_args.args[0]
+    assert event.source.chat_type == "group"
+
+
+@pytest.mark.asyncio
+async def test_normal_channel_still_auto_threads(adapter, monkeypatch):
+    """Channels NOT in no_thread_channels still get auto-threading."""
+    monkeypatch.setenv("DISCORD_REQUIRE_MENTION", "false")
+    monkeypatch.setenv("DISCORD_NO_THREAD_CHANNELS", "800")
+    monkeypatch.delenv("DISCORD_AUTO_THREAD", raising=False)
+    monkeypatch.delenv("DISCORD_IGNORED_CHANNELS", raising=False)
+    monkeypatch.delenv("DISCORD_FREE_RESPONSE_CHANNELS", raising=False)
+
+    fake_thread = FakeThread(channel_id=999, name="auto-thread")
+    adapter._auto_create_thread = AsyncMock(return_value=fake_thread)
+
+    message = make_message(channel=FakeTextChannel(channel_id=900), content="hello")
+    await adapter._handle_message(message)
+
+    adapter._auto_create_thread.assert_awaited_once()
+    adapter.handle_message.assert_awaited_once()
+    event = adapter.handle_message.await_args.args[0]
+    assert event.source.chat_type == "thread"
+
+
+@pytest.mark.asyncio
+async def test_no_thread_channels_csv_parsing(adapter, monkeypatch):
+    """Multiple no_thread channel IDs parsed from CSV."""
+    monkeypatch.setenv("DISCORD_REQUIRE_MENTION", "false")
+    monkeypatch.setenv("DISCORD_NO_THREAD_CHANNELS", "800, 900")
+    monkeypatch.delenv("DISCORD_AUTO_THREAD", raising=False)
+    monkeypatch.delenv("DISCORD_IGNORED_CHANNELS", raising=False)
+    monkeypatch.delenv("DISCORD_FREE_RESPONSE_CHANNELS", raising=False)
+
+    adapter._auto_create_thread = AsyncMock(return_value=FakeThread(channel_id=999))
+
+    for ch_id in (800, 900):
+        adapter._auto_create_thread.reset_mock()
+        adapter.handle_message.reset_mock()
+        message = make_message(channel=FakeTextChannel(channel_id=ch_id), content="hello")
+        await adapter._handle_message(message)
+        adapter._auto_create_thread.assert_not_awaited()
+
+
+@pytest.mark.asyncio
+async def test_no_thread_with_auto_thread_disabled_is_noop(adapter, monkeypatch):
+    """no_thread_channels is a no-op when auto_thread is globally disabled."""
+    monkeypatch.setenv("DISCORD_REQUIRE_MENTION", "false")
+    monkeypatch.setenv("DISCORD_AUTO_THREAD", "false")
+    monkeypatch.setenv("DISCORD_NO_THREAD_CHANNELS", "800")
+    monkeypatch.delenv("DISCORD_IGNORED_CHANNELS", raising=False)
+    monkeypatch.delenv("DISCORD_FREE_RESPONSE_CHANNELS", raising=False)
+
+    adapter._auto_create_thread = AsyncMock()
+
+    message = make_message(channel=FakeTextChannel(channel_id=800), content="hello")
+    await adapter._handle_message(message)
+
+    adapter._auto_create_thread.assert_not_awaited()
+    adapter.handle_message.assert_awaited_once()
+
+
+# ── config.py bridging ───────────────────────────────────────────────
+
+
+def test_config_bridges_ignored_channels(monkeypatch, tmp_path):
+    """gateway/config.py bridges discord.ignored_channels to env var."""
+    import yaml
+    config_file = tmp_path / "config.yaml"
+    config_file.write_text(yaml.dump({
+        "discord": {
+            "ignored_channels": ["111", "222"],
+        },
+    }))
+    monkeypatch.setenv("HERMES_HOME", str(tmp_path))
+    # Use setenv (not delenv) so monkeypatch registers cleanup even when
+    # the var doesn't exist yet — load_gateway_config will overwrite it.
+    monkeypatch.setenv("DISCORD_IGNORED_CHANNELS", "")
+
+    from gateway.config import load_gateway_config
+    load_gateway_config()
+
+    import os
+    assert os.getenv("DISCORD_IGNORED_CHANNELS") == "111,222"
+
+
+def test_config_bridges_no_thread_channels(monkeypatch, tmp_path):
+    """gateway/config.py bridges discord.no_thread_channels to env var."""
+    import yaml
+    config_file = tmp_path / "config.yaml"
+    config_file.write_text(yaml.dump({
+        "discord": {
+            "no_thread_channels": ["333"],
+        },
+    }))
+    monkeypatch.setenv("HERMES_HOME", str(tmp_path))
+    monkeypatch.setenv("DISCORD_NO_THREAD_CHANNELS", "")
+
+    from gateway.config import load_gateway_config
+    load_gateway_config()
+
+    import os
+    assert os.getenv("DISCORD_NO_THREAD_CHANNELS") == "333"
+
+
+def test_config_env_var_takes_precedence(monkeypatch, tmp_path):
+    """Env vars should take precedence over config.yaml values."""
+    import yaml
+    config_file = tmp_path / "config.yaml"
+    config_file.write_text(yaml.dump({
+        "discord": {
+            "ignored_channels": ["111"],
+        },
+    }))
+    monkeypatch.setenv("HERMES_HOME", str(tmp_path))
+    monkeypatch.setenv("DISCORD_IGNORED_CHANNELS", "999")
+
+    from gateway.config import load_gateway_config
+    load_gateway_config()
+
+    import os
+    # Env var should NOT be overwritten
+    assert os.getenv("DISCORD_IGNORED_CHANNELS") == "999"

tests/gateway/test_feishu_approval_buttons.py

@@ -0,0 +1,432 @@
+"""Tests for Feishu interactive card approval buttons."""
+
+import asyncio
+import json
+import os
+import sys
+from pathlib import Path
+from types import SimpleNamespace
+from unittest.mock import AsyncMock, MagicMock, Mock, patch
+
+import pytest
+
+# ---------------------------------------------------------------------------
+# Ensure the repo root is importable
+# ---------------------------------------------------------------------------
+_repo = str(Path(__file__).resolve().parents[2])
+if _repo not in sys.path:
+    sys.path.insert(0, _repo)
+
+
+# ---------------------------------------------------------------------------
+# Minimal Feishu mock so FeishuAdapter can be imported without lark-oapi
+# ---------------------------------------------------------------------------
+def _ensure_feishu_mocks():
+    """Provide stubs for lark-oapi / aiohttp.web so the import succeeds."""
+    if "lark_oapi" not in sys.modules:
+        mod = MagicMock()
+        for name in (
+            "lark_oapi", "lark_oapi.api.im.v1",
+            "lark_oapi.event", "lark_oapi.event.callback_type",
+        ):
+            sys.modules.setdefault(name, mod)
+    if "aiohttp" not in sys.modules:
+        aio = MagicMock()
+        sys.modules.setdefault("aiohttp", aio)
+        sys.modules.setdefault("aiohttp.web", aio.web)
+
+
+_ensure_feishu_mocks()
+
+from gateway.config import PlatformConfig
+from gateway.platforms.feishu import FeishuAdapter
+
+
+# ---------------------------------------------------------------------------
+# Helpers
+# ---------------------------------------------------------------------------
+
+def _make_adapter() -> FeishuAdapter:
+    """Create a FeishuAdapter with mocked internals."""
+    config = PlatformConfig(enabled=True)
+    adapter = FeishuAdapter(config)
+    adapter._client = MagicMock()
+    return adapter
+
+
+def _make_card_action_data(
+    action_value: dict,
+    chat_id: str = "oc_12345",
+    open_id: str = "ou_user1",
+    token: str = "tok_abc",
+) -> SimpleNamespace:
+    """Create a mock Feishu card action callback data object."""
+    return SimpleNamespace(
+        event=SimpleNamespace(
+            token=token,
+            context=SimpleNamespace(open_chat_id=chat_id),
+            operator=SimpleNamespace(open_id=open_id),
+            action=SimpleNamespace(
+                tag="button",
+                value=action_value,
+            ),
+        ),
+    )
+
+
+# ===========================================================================
+# send_exec_approval — interactive card with buttons
+# ===========================================================================
+
+class TestFeishuExecApproval:
+    """Test send_exec_approval sends an interactive card."""
+
+    @pytest.mark.asyncio
+    async def test_sends_interactive_card(self):
+        adapter = _make_adapter()
+
+        mock_response = SimpleNamespace(
+            success=lambda: True,
+            data=SimpleNamespace(message_id="msg_001"),
+        )
+        with patch.object(
+            adapter, "_feishu_send_with_retry", new_callable=AsyncMock,
+            return_value=mock_response,
+        ) as mock_send:
+            result = await adapter.send_exec_approval(
+                chat_id="oc_12345",
+                command="rm -rf /important",
+                session_key="agent:main:feishu:group:oc_12345",
+                description="dangerous deletion",
+            )
+
+        assert result.success is True
+        assert result.message_id == "msg_001"
+
+        mock_send.assert_called_once()
+        kwargs = mock_send.call_args[1]
+        assert kwargs["chat_id"] == "oc_12345"
+        assert kwargs["msg_type"] == "interactive"
+
+        # Verify card payload contains the command and buttons
+        card = json.loads(kwargs["payload"])
+        assert card["header"]["template"] == "orange"
+        assert "rm -rf /important" in card["elements"][0]["content"]
+        assert "dangerous deletion" in card["elements"][0]["content"]
+
+        # Check buttons
+        actions = card["elements"][1]["actions"]
+        assert len(actions) == 4
+        action_names = [a["value"]["hermes_action"] for a in actions]
+        assert action_names == [
+            "approve_once", "approve_session", "approve_always", "deny"
+        ]
+
+    @pytest.mark.asyncio
+    async def test_stores_approval_state(self):
+        adapter = _make_adapter()
+
+        mock_response = SimpleNamespace(
+            success=lambda: True,
+            data=SimpleNamespace(message_id="msg_002"),
+        )
+        with patch.object(
+            adapter, "_feishu_send_with_retry", new_callable=AsyncMock,
+            return_value=mock_response,
+        ):
+            await adapter.send_exec_approval(
+                chat_id="oc_12345",
+                command="echo test",
+                session_key="my-session-key",
+            )
+
+        assert len(adapter._approval_state) == 1
+        approval_id = list(adapter._approval_state.keys())[0]
+        state = adapter._approval_state[approval_id]
+        assert state["session_key"] == "my-session-key"
+        assert state["message_id"] == "msg_002"
+        assert state["chat_id"] == "oc_12345"
+
+    @pytest.mark.asyncio
+    async def test_not_connected(self):
+        adapter = _make_adapter()
+        adapter._client = None
+        result = await adapter.send_exec_approval(
+            chat_id="oc_12345", command="ls", session_key="s"
+        )
+        assert result.success is False
+
+    @pytest.mark.asyncio
+    async def test_truncates_long_command(self):
+        adapter = _make_adapter()
+
+        mock_response = SimpleNamespace(
+            success=lambda: True,
+            data=SimpleNamespace(message_id="msg_003"),
+        )
+        with patch.object(
+            adapter, "_feishu_send_with_retry", new_callable=AsyncMock,
+            return_value=mock_response,
+        ) as mock_send:
+            long_cmd = "x" * 5000
+            await adapter.send_exec_approval(
+                chat_id="oc_12345", command=long_cmd, session_key="s"
+            )
+
+        card = json.loads(mock_send.call_args[1]["payload"])
+        content = card["elements"][0]["content"]
+        assert "..." in content
+        assert len(content) < 5000
+
+    @pytest.mark.asyncio
+    async def test_multiple_approvals_get_unique_ids(self):
+        adapter = _make_adapter()
+
+        mock_response = SimpleNamespace(
+            success=lambda: True,
+            data=SimpleNamespace(message_id="msg_x"),
+        )
+        with patch.object(
+            adapter, "_feishu_send_with_retry", new_callable=AsyncMock,
+            return_value=mock_response,
+        ):
+            await adapter.send_exec_approval(
+                chat_id="oc_1", command="cmd1", session_key="s1"
+            )
+            await adapter.send_exec_approval(
+                chat_id="oc_2", command="cmd2", session_key="s2"
+            )
+
+        assert len(adapter._approval_state) == 2
+        ids = list(adapter._approval_state.keys())
+        assert ids[0] != ids[1]
+
+
+# ===========================================================================
+# _handle_card_action_event — approval button clicks
+# ===========================================================================
+
+class TestFeishuApprovalCallback:
+    """Test the approval intercept in _handle_card_action_event."""
+
+    @pytest.mark.asyncio
+    async def test_resolves_approval_on_click(self):
+        adapter = _make_adapter()
+        adapter._approval_state[1] = {
+            "session_key": "agent:main:feishu:group:oc_12345",
+            "message_id": "msg_001",
+            "chat_id": "oc_12345",
+        }
+
+        data = _make_card_action_data(
+            action_value={"hermes_action": "approve_once", "approval_id": 1},
+        )
+
+        with (
+            patch.object(
+                adapter, "_resolve_sender_profile", new_callable=AsyncMock,
+                return_value={"user_id": "ou_user1", "user_name": "Norbert", "user_id_alt": None},
+            ),
+            patch.object(adapter, "_update_approval_card", new_callable=AsyncMock) as mock_update,
+            patch("tools.approval.resolve_gateway_approval", return_value=1) as mock_resolve,
+        ):
+            await adapter._handle_card_action_event(data)
+
+        mock_resolve.assert_called_once_with("agent:main:feishu:group:oc_12345", "once")
+        mock_update.assert_called_once_with("msg_001", "Approved once", "Norbert", "once")
+
+        # State should be cleaned up
+        assert 1 not in adapter._approval_state
+
+    @pytest.mark.asyncio
+    async def test_deny_button(self):
+        adapter = _make_adapter()
+        adapter._approval_state[2] = {
+            "session_key": "some-session",
+            "message_id": "msg_002",
+            "chat_id": "oc_12345",
+        }
+
+        data = _make_card_action_data(
+            action_value={"hermes_action": "deny", "approval_id": 2},
+            token="tok_deny",
+        )
+
+        with (
+            patch.object(
+                adapter, "_resolve_sender_profile", new_callable=AsyncMock,
+                return_value={"user_id": "ou_alice", "user_name": "Alice", "user_id_alt": None},
+            ),
+            patch.object(adapter, "_update_approval_card", new_callable=AsyncMock) as mock_update,
+            patch("tools.approval.resolve_gateway_approval", return_value=1) as mock_resolve,
+        ):
+            await adapter._handle_card_action_event(data)
+
+        mock_resolve.assert_called_once_with("some-session", "deny")
+        mock_update.assert_called_once_with("msg_002", "Denied", "Alice", "deny")
+
+    @pytest.mark.asyncio
+    async def test_session_approval(self):
+        adapter = _make_adapter()
+        adapter._approval_state[3] = {
+            "session_key": "sess-3",
+            "message_id": "msg_003",
+            "chat_id": "oc_99",
+        }
+
+        data = _make_card_action_data(
+            action_value={"hermes_action": "approve_session", "approval_id": 3},
+            token="tok_ses",
+        )
+
+        with (
+            patch.object(
+                adapter, "_resolve_sender_profile", new_callable=AsyncMock,
+                return_value={"user_id": "ou_u", "user_name": "Bob", "user_id_alt": None},
+            ),
+            patch.object(adapter, "_update_approval_card", new_callable=AsyncMock) as mock_update,
+            patch("tools.approval.resolve_gateway_approval", return_value=1) as mock_resolve,
+        ):
+            await adapter._handle_card_action_event(data)
+
+        mock_resolve.assert_called_once_with("sess-3", "session")
+        mock_update.assert_called_once_with("msg_003", "Approved for session", "Bob", "session")
+
+    @pytest.mark.asyncio
+    async def test_always_approval(self):
+        adapter = _make_adapter()
+        adapter._approval_state[4] = {
+            "session_key": "sess-4",
+            "message_id": "msg_004",
+            "chat_id": "oc_55",
+        }
+
+        data = _make_card_action_data(
+            action_value={"hermes_action": "approve_always", "approval_id": 4},
+            token="tok_alw",
+        )
+
+        with (
+            patch.object(
+                adapter, "_resolve_sender_profile", new_callable=AsyncMock,
+                return_value={"user_id": "ou_u", "user_name": "Carol", "user_id_alt": None},
+            ),
+            patch.object(adapter, "_update_approval_card", new_callable=AsyncMock),
+            patch("tools.approval.resolve_gateway_approval", return_value=1) as mock_resolve,
+        ):
+            await adapter._handle_card_action_event(data)
+
+        mock_resolve.assert_called_once_with("sess-4", "always")
+
+    @pytest.mark.asyncio
+    async def test_already_resolved_drops_silently(self):
+        adapter = _make_adapter()
+        # No state for approval_id 99 — already resolved
+
+        data = _make_card_action_data(
+            action_value={"hermes_action": "approve_once", "approval_id": 99},
+            token="tok_gone",
+        )
+
+        with patch("tools.approval.resolve_gateway_approval") as mock_resolve:
+            await adapter._handle_card_action_event(data)
+
+        # Should NOT resolve — already handled
+        mock_resolve.assert_not_called()
+
+    @pytest.mark.asyncio
+    async def test_non_approval_actions_route_normally(self):
+        """Non-approval card actions should still become synthetic commands."""
+        adapter = _make_adapter()
+
+        data = _make_card_action_data(
+            action_value={"custom_action": "something_else"},
+            token="tok_normal",
+        )
+
+        with (
+            patch.object(
+                adapter, "_resolve_sender_profile", new_callable=AsyncMock,
+                return_value={"user_id": "ou_u", "user_name": "Dave", "user_id_alt": None},
+            ),
+            patch.object(adapter, "get_chat_info", new_callable=AsyncMock, return_value={"name": "Test Chat"}),
+            patch.object(adapter, "_handle_message_with_guards", new_callable=AsyncMock) as mock_handle,
+            patch("tools.approval.resolve_gateway_approval") as mock_resolve,
+        ):
+            await adapter._handle_card_action_event(data)
+
+        # Should NOT resolve any approval
+        mock_resolve.assert_not_called()
+        # Should have routed as synthetic command
+        mock_handle.assert_called_once()
+        event = mock_handle.call_args[0][0]
+        assert "/card button" in event.text
+
+
+# ===========================================================================
+# _update_approval_card — card replacement after resolution
+# ===========================================================================
+
+class TestFeishuUpdateApprovalCard:
+    """Test the card update after approval resolution."""
+
+    @pytest.mark.asyncio
+    async def test_updates_card_on_approve(self):
+        adapter = _make_adapter()
+
+        mock_update = AsyncMock()
+        adapter._client.im.v1.message.update = MagicMock()
+
+        with patch("asyncio.to_thread", new_callable=AsyncMock) as mock_thread:
+            await adapter._update_approval_card(
+                "msg_001", "Approved once", "Norbert", "once"
+            )
+
+        mock_thread.assert_called_once()
+        # Verify the update request was built
+        call_args = mock_thread.call_args
+        assert call_args[0][0] == adapter._client.im.v1.message.update
+
+    @pytest.mark.asyncio
+    async def test_updates_card_on_deny(self):
+        adapter = _make_adapter()
+
+        with patch("asyncio.to_thread", new_callable=AsyncMock) as mock_thread:
+            await adapter._update_approval_card(
+                "msg_002", "Denied", "Alice", "deny"
+            )
+
+        mock_thread.assert_called_once()
+
+    @pytest.mark.asyncio
+    async def test_skips_update_when_not_connected(self):
+        adapter = _make_adapter()
+        adapter._client = None
+
+        with patch("asyncio.to_thread", new_callable=AsyncMock) as mock_thread:
+            await adapter._update_approval_card(
+                "msg_001", "Approved", "Bob", "once"
+            )
+
+        mock_thread.assert_not_called()
+
+    @pytest.mark.asyncio
+    async def test_skips_update_when_no_message_id(self):
+        adapter = _make_adapter()
+
+        with patch("asyncio.to_thread", new_callable=AsyncMock) as mock_thread:
+            await adapter._update_approval_card(
+                "", "Approved", "Bob", "once"
+            )
+
+        mock_thread.assert_not_called()
+
+    @pytest.mark.asyncio
+    async def test_swallows_update_errors(self):
+        adapter = _make_adapter()
+
+        with patch("asyncio.to_thread", new_callable=AsyncMock, side_effect=Exception("API error")):
+            # Should not raise
+            await adapter._update_approval_card(
+                "msg_001", "Approved", "Bob", "once"
+            )

tests/gateway/test_mattermost.py

@@ -504,7 +504,8 @@ class TestMattermostFileUpload:
         self.adapter._session = MagicMock()
 
     @pytest.mark.asyncio
-    async def test_send_image_downloads_and_uploads(self):
+    @patch("tools.url_safety.is_safe_url", return_value=True)
+    async def test_send_image_downloads_and_uploads(self, _mock_safe):
         """send_image should download the URL, upload via /api/v4/files, then post."""
         # Mock the download (GET)
         mock_dl_resp = AsyncMock()

tests/gateway/test_media_download_retry.py

@@ -596,10 +596,11 @@ def _make_aiohttp_resp(status: int, content: bytes = b"file bytes",
     return resp
 
 
+@patch("tools.url_safety.is_safe_url", return_value=True)
 class TestMattermostSendUrlAsFile:
     """Tests for MattermostAdapter._send_url_as_file"""
 
-    def test_success_on_first_attempt(self):
+    def test_success_on_first_attempt(self, _mock_safe):
         """200 on first attempt → file uploaded and post created."""
         adapter = _make_mm_adapter()
         resp = _make_aiohttp_resp(200)
@@ -616,7 +617,7 @@ class TestMattermostSendUrlAsFile:
         adapter._upload_file.assert_called_once()
         adapter._api_post.assert_called_once()
 
-    def test_retries_on_429_then_succeeds(self):
+    def test_retries_on_429_then_succeeds(self, _mock_safe):
         """429 on first attempt is retried; 200 on second attempt succeeds."""
         adapter = _make_mm_adapter()
 
@@ -637,7 +638,7 @@ class TestMattermostSendUrlAsFile:
         assert adapter._session.get.call_count == 2
         mock_sleep.assert_called_once()
 
-    def test_retries_on_500_then_succeeds(self):
+    def test_retries_on_500_then_succeeds(self, _mock_safe):
         """5xx on first attempt is retried; 200 on second attempt succeeds."""
         adapter = _make_mm_adapter()
 
@@ -655,7 +656,7 @@ class TestMattermostSendUrlAsFile:
         assert result.success
         assert adapter._session.get.call_count == 2
 
-    def test_falls_back_to_text_after_max_retries_on_5xx(self):
+    def test_falls_back_to_text_after_max_retries_on_5xx(self, _mock_safe):
         """Three consecutive 500s exhaust retries; falls back to send() with URL text."""
         adapter = _make_mm_adapter()
 
@@ -674,7 +675,7 @@ class TestMattermostSendUrlAsFile:
         text_arg = adapter.send.call_args[0][1]
         assert "http://cdn.example.com/img.png" in text_arg
 
-    def test_falls_back_on_client_error(self):
+    def test_falls_back_on_client_error(self, _mock_safe):
         """aiohttp.ClientError on every attempt falls back to send() with URL."""
         import aiohttp
 
@@ -699,7 +700,7 @@ class TestMattermostSendUrlAsFile:
         text_arg = adapter.send.call_args[0][1]
         assert "http://cdn.example.com/img.png" in text_arg
 
-    def test_non_retryable_404_falls_back_immediately(self):
+    def test_non_retryable_404_falls_back_immediately(self, _mock_safe):
         """404 is non-retryable (< 500, != 429); send() is called right away."""
         adapter = _make_mm_adapter()
 

tests/gateway/test_reasoning_command.py

@@ -87,7 +87,6 @@ class TestReasoningCommand:
         )
 
         monkeypatch.setattr(gateway_run, "_hermes_home", hermes_home)
-        monkeypatch.delenv("HERMES_REASONING_EFFORT", raising=False)
 
         runner = _make_runner()
         runner._reasoning_config = {"enabled": True, "effort": "xhigh"}
@@ -108,7 +107,6 @@ class TestReasoningCommand:
         config_path.write_text("agent:\n  reasoning_effort: medium\n", encoding="utf-8")
 
         monkeypatch.setattr(gateway_run, "_hermes_home", hermes_home)
-        monkeypatch.delenv("HERMES_REASONING_EFFORT", raising=False)
 
         runner = _make_runner()
         runner._reasoning_config = {"enabled": True, "effort": "medium"}
@@ -138,7 +136,6 @@ class TestReasoningCommand:
                 "api_key": "test-key",
             },
         )
-        monkeypatch.delenv("HERMES_REASONING_EFFORT", raising=False)
         fake_run_agent = types.ModuleType("run_agent")
         fake_run_agent.AIAgent = _CapturingAgent
         monkeypatch.setitem(sys.modules, "run_agent", fake_run_agent)
@@ -170,55 +167,6 @@ class TestReasoningCommand:
         assert _CapturingAgent.last_init is not None
         assert _CapturingAgent.last_init["reasoning_config"] == {"enabled": True, "effort": "low"}
 
-    def test_run_agent_prefers_config_over_stale_reasoning_env(self, tmp_path, monkeypatch):
-        hermes_home = tmp_path / "hermes"
-        hermes_home.mkdir()
-        (hermes_home / "config.yaml").write_text("agent:\n  reasoning_effort: none\n", encoding="utf-8")
-
-        monkeypatch.setattr(gateway_run, "_hermes_home", hermes_home)
-        monkeypatch.setattr(gateway_run, "_env_path", hermes_home / ".env")
-        monkeypatch.setattr(gateway_run, "load_dotenv", lambda *args, **kwargs: None)
-        monkeypatch.setattr(
-            gateway_run,
-            "_resolve_runtime_agent_kwargs",
-            lambda: {
-                "provider": "openrouter",
-                "api_mode": "chat_completions",
-                "base_url": "https://openrouter.ai/api/v1",
-                "api_key": "test-key",
-            },
-        )
-        monkeypatch.setenv("HERMES_REASONING_EFFORT", "low")
-        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",
-        )
-
-        result = asyncio.run(
-            runner._run_agent(
-                message="ping",
-                context_prompt="",
-                history=[],
-                source=source,
-                session_id="session-1",
-                session_key="agent:main:local:dm",
-            )
-        )
-
-        assert result["final_response"] == "ok"
-        assert _CapturingAgent.last_init is not None
-        assert _CapturingAgent.last_init["reasoning_config"] == {"enabled": False}
-
     def test_run_agent_includes_enabled_mcp_servers_in_gateway_toolsets(self, tmp_path, monkeypatch):
         hermes_home = tmp_path / "hermes"
         hermes_home.mkdir()

tests/gateway/test_run_progress_topics.py

@@ -71,6 +71,24 @@ class FakeAgent:
         }
 
 
+class LongPreviewAgent:
+    """Agent that emits a tool call with a very long preview string."""
+    LONG_CMD = "cd /home/teknium/.hermes/hermes-agent/.worktrees/hermes-d8860339 && source .venv/bin/activate && python -m pytest tests/gateway/test_run_progress_topics.py -n0 -q"
+
+    def __init__(self, **kwargs):
+        self.tool_progress_callback = kwargs.get("tool_progress_callback")
+        self.tools = []
+
+    def run_conversation(self, message, conversation_history=None, task_id=None):
+        self.tool_progress_callback("tool.started", "terminal", self.LONG_CMD, {})
+        time.sleep(0.35)
+        return {
+            "final_response": "done",
+            "messages": [],
+            "api_calls": 1,
+        }
+
+
 def _make_runner(adapter):
     gateway_run = importlib.import_module("gateway.run")
     GatewayRunner = gateway_run.GatewayRunner
@@ -217,3 +235,102 @@ async def test_run_agent_progress_uses_event_message_id_for_slack_dm(monkeypatch
     assert adapter.sent
     assert adapter.sent[0]["metadata"] == {"thread_id": "1234567890.000001"}
     assert all(call["metadata"] == {"thread_id": "1234567890.000001"} for call in adapter.typing)
+
+
+# ---------------------------------------------------------------------------
+# Preview truncation tests (all/new mode respects tool_preview_length)
+# ---------------------------------------------------------------------------
+
+
+def _run_long_preview_helper(monkeypatch, tmp_path, preview_length=0):
+    """Shared setup for long-preview truncation tests.
+
+    Returns (adapter, result) after running the agent with LongPreviewAgent.
+    ``preview_length`` controls display.tool_preview_length in the config file
+    that _run_agent reads — so the gateway picks it up the same way production does.
+    """
+    import asyncio
+    import yaml
+
+    monkeypatch.setenv("HERMES_TOOL_PROGRESS_MODE", "all")
+
+    fake_dotenv = types.ModuleType("dotenv")
+    fake_dotenv.load_dotenv = lambda *args, **kwargs: None
+    monkeypatch.setitem(sys.modules, "dotenv", fake_dotenv)
+
+    fake_run_agent = types.ModuleType("run_agent")
+    fake_run_agent.AIAgent = LongPreviewAgent
+    monkeypatch.setitem(sys.modules, "run_agent", fake_run_agent)
+
+    # Write config.yaml so _run_agent picks up tool_preview_length
+    config = {"display": {"tool_preview_length": preview_length}}
+    (tmp_path / "config.yaml").write_text(yaml.dump(config), encoding="utf-8")
+
+    adapter = ProgressCaptureAdapter()
+    runner = _make_runner(adapter)
+    gateway_run = importlib.import_module("gateway.run")
+    monkeypatch.setattr(gateway_run, "_hermes_home", tmp_path)
+    monkeypatch.setattr(gateway_run, "_resolve_runtime_agent_kwargs", lambda: {"api_key": "***"})
+
+    source = SessionSource(
+        platform=Platform.TELEGRAM,
+        chat_id="12345",
+        chat_type="dm",
+        thread_id=None,
+    )
+
+    result = asyncio.get_event_loop().run_until_complete(
+        runner._run_agent(
+            message="hello",
+            context_prompt="",
+            history=[],
+            source=source,
+            session_id="sess-trunc",
+            session_key="agent:main:telegram:dm:12345",
+        )
+    )
+    return adapter, result
+
+
+def test_all_mode_default_truncation_40_chars(monkeypatch, tmp_path):
+    """When tool_preview_length is 0 (default), all/new mode truncates to 40 chars."""
+    adapter, result = _run_long_preview_helper(monkeypatch, tmp_path, preview_length=0)
+    assert result["final_response"] == "done"
+    assert adapter.sent
+    content = adapter.sent[0]["content"]
+    # The long command should be truncated — total preview <= 40 chars
+    assert "..." in content
+    # Extract the preview part between quotes
+    import re
+    match = re.search(r'"(.+)"', content)
+    assert match, f"No quoted preview found in: {content}"
+    preview_text = match.group(1)
+    assert len(preview_text) <= 40, f"Preview too long ({len(preview_text)}): {preview_text}"
+
+
+def test_all_mode_respects_custom_preview_length(monkeypatch, tmp_path):
+    """When tool_preview_length is explicitly set (e.g. 120), all/new mode uses that."""
+    adapter, result = _run_long_preview_helper(monkeypatch, tmp_path, preview_length=120)
+    assert result["final_response"] == "done"
+    assert adapter.sent
+    content = adapter.sent[0]["content"]
+    # With 120-char cap, the command (165 chars) should still be truncated but longer
+    import re
+    match = re.search(r'"(.+)"', content)
+    assert match, f"No quoted preview found in: {content}"
+    preview_text = match.group(1)
+    # Should be longer than the 40-char default
+    assert len(preview_text) > 40, f"Preview suspiciously short ({len(preview_text)}): {preview_text}"
+    # But still capped at 120
+    assert len(preview_text) <= 120, f"Preview too long ({len(preview_text)}): {preview_text}"
+
+
+def test_all_mode_no_truncation_when_preview_fits(monkeypatch, tmp_path):
+    """Short previews (under the cap) are not truncated."""
+    # Set a generous cap — the LongPreviewAgent's command is ~165 chars
+    adapter, result = _run_long_preview_helper(monkeypatch, tmp_path, preview_length=200)
+    assert result["final_response"] == "done"
+    assert adapter.sent
+    content = adapter.sent[0]["content"]
+    # With a 200-char cap, the 165-char command should NOT be truncated
+    assert "..." not in content, f"Preview was truncated when it shouldn't be: {content}"

tests/gateway/test_status_command.py

@@ -51,7 +51,8 @@ def _make_runner(session_entry: SessionEntry):
     runner._running_agents = {}
     runner._pending_messages = {}
     runner._pending_approvals = {}
-    runner._session_db = None
+    runner._session_db = MagicMock()
+    runner._session_db.get_session_title.return_value = None
     runner._reasoning_config = None
     runner._provider_routing = {}
     runner._fallback_model = None
@@ -82,12 +83,34 @@ async def test_status_command_reports_running_agent_without_interrupt(monkeypatc
 
     result = await runner._handle_message(_make_event("/status"))
 
+    assert "**Session ID:** `sess-1`" in result
     assert "**Tokens:** 321" in result
     assert "**Agent Running:** Yes ⚡" in result
+    assert "**Title:**" not in result
     running_agent.interrupt.assert_not_called()
     assert runner._pending_messages == {}
 
 
+@pytest.mark.asyncio
+async def test_status_command_includes_session_title_when_present():
+    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",
+        total_tokens=321,
+    )
+    runner = _make_runner(session_entry)
+    runner._session_db.get_session_title.return_value = "My titled session"
+
+    result = await runner._handle_message(_make_event("/status"))
+
+    assert "**Session ID:** `sess-1`" in result
+    assert "**Title:** My titled session" in result
+
+
 @pytest.mark.asyncio
 async def test_handle_message_persists_agent_token_counts(monkeypatch):
     import gateway.run as gateway_run

tests/gateway/test_stream_consumer.py

@@ -324,3 +324,91 @@ class TestSegmentBreakOnToolBoundary:
         await consumer.run()
 
         assert consumer.already_sent
+
+    @pytest.mark.asyncio
+    async def test_edit_failure_sends_only_unsent_tail_at_finish(self):
+        """If an edit fails mid-stream, send only the missing tail once at finish."""
+        adapter = MagicMock()
+        send_results = [
+            SimpleNamespace(success=True, message_id="msg_1"),
+            SimpleNamespace(success=True, message_id="msg_2"),
+        ]
+        adapter.send = AsyncMock(side_effect=send_results)
+        adapter.edit_message = AsyncMock(return_value=SimpleNamespace(success=False, error="flood_control:6"))
+        adapter.MAX_MESSAGE_LENGTH = 4096
+
+        config = StreamConsumerConfig(edit_interval=0.01, buffer_threshold=5, cursor=" ▉")
+        consumer = GatewayStreamConsumer(adapter, "chat_123", config)
+
+        consumer.on_delta("Hello")
+        task = asyncio.create_task(consumer.run())
+        await asyncio.sleep(0.08)
+        consumer.on_delta(" world")
+        await asyncio.sleep(0.08)
+        consumer.finish()
+        await task
+
+        assert adapter.send.call_count == 2
+        first_text = adapter.send.call_args_list[0][1]["content"]
+        second_text = adapter.send.call_args_list[1][1]["content"]
+        assert "Hello" in first_text
+        assert second_text.strip() == "world"
+        assert consumer.already_sent
+
+    @pytest.mark.asyncio
+    async def test_segment_break_clears_failed_edit_fallback_state(self):
+        """A tool boundary after edit failure must not duplicate the next segment."""
+        adapter = MagicMock()
+        send_results = [
+            SimpleNamespace(success=True, message_id="msg_1"),
+            SimpleNamespace(success=True, message_id="msg_2"),
+        ]
+        adapter.send = AsyncMock(side_effect=send_results)
+        adapter.edit_message = AsyncMock(return_value=SimpleNamespace(success=False, error="flood_control:6"))
+        adapter.MAX_MESSAGE_LENGTH = 4096
+
+        config = StreamConsumerConfig(edit_interval=0.01, buffer_threshold=5, cursor=" ▉")
+        consumer = GatewayStreamConsumer(adapter, "chat_123", config)
+
+        consumer.on_delta("Hello")
+        task = asyncio.create_task(consumer.run())
+        await asyncio.sleep(0.08)
+        consumer.on_delta(" world")
+        await asyncio.sleep(0.08)
+        consumer.on_delta(None)
+        consumer.on_delta("Next segment")
+        consumer.finish()
+        await task
+
+        sent_texts = [call[1]["content"] for call in adapter.send.call_args_list]
+        assert sent_texts == ["Hello ▉", "Next segment"]
+
+    @pytest.mark.asyncio
+    async def test_fallback_final_splits_long_continuation_without_dropping_text(self):
+        """Long continuation tails should be chunked when fallback final-send runs."""
+        adapter = MagicMock()
+        adapter.send = AsyncMock(side_effect=[
+            SimpleNamespace(success=True, message_id="msg_1"),
+            SimpleNamespace(success=True, message_id="msg_2"),
+            SimpleNamespace(success=True, message_id="msg_3"),
+        ])
+        adapter.edit_message = AsyncMock(return_value=SimpleNamespace(success=False, error="flood_control:6"))
+        adapter.MAX_MESSAGE_LENGTH = 610
+
+        config = StreamConsumerConfig(edit_interval=0.01, buffer_threshold=5, cursor=" ▉")
+        consumer = GatewayStreamConsumer(adapter, "chat_123", config)
+
+        prefix = "abc"
+        tail = "x" * 620
+        consumer.on_delta(prefix)
+        task = asyncio.create_task(consumer.run())
+        await asyncio.sleep(0.08)
+        consumer.on_delta(tail)
+        await asyncio.sleep(0.08)
+        consumer.finish()
+        await task
+
+        sent_texts = [call[1]["content"] for call in adapter.send.call_args_list]
+        assert len(sent_texts) == 3
+        assert sent_texts[0].startswith(prefix)
+        assert sum(len(t) for t in sent_texts[1:]) == len(tail)

tests/gateway/test_telegram_approval_buttons.py

@@ -33,8 +33,15 @@ def _ensure_telegram_mock():
     mod.constants.ChatType.GROUP = "group"
     mod.constants.ChatType.SUPERGROUP = "supergroup"
     mod.constants.ChatType.CHANNEL = "channel"
-    for name in ("telegram", "telegram.ext", "telegram.constants", "telegram.request", "telegram.error"):
+    # Provide real exception classes so ``except (NetworkError, ...)`` in
+    # connect() doesn't blow up under xdist when this mock leaks.
+    mod.error.NetworkError = type("NetworkError", (OSError,), {})
+    mod.error.TimedOut = type("TimedOut", (OSError,), {})
+    mod.error.BadRequest = type("BadRequest", (Exception,), {})
+
+    for name in ("telegram", "telegram.ext", "telegram.constants", "telegram.request"):
         sys.modules.setdefault(name, mod)
+    sys.modules.setdefault("telegram.error", mod.error)
 
 
 _ensure_telegram_mock()