fix: revert accidental summary_target_tokens change + add docs for context_length config

- Revert summary_target_tokens from 2500 back to 500 (accidental change
  during patching)
- Add 'Context Length Detection' section to Custom & Self-Hosted docs
  explaining model.context_length config override

agent/auxiliary_client.py

@@ -654,10 +654,23 @@ def _try_anthropic() -> Tuple[Optional[Any], Optional[str]]:
     if not token:
         return None, None
 
+    # Allow base URL override from config.yaml model.base_url
+    base_url = _ANTHROPIC_DEFAULT_BASE_URL
+    try:
+        from hermes_cli.config import load_config
+        cfg = load_config()
+        model_cfg = cfg.get("model")
+        if isinstance(model_cfg, dict):
+            cfg_base_url = (model_cfg.get("base_url") or "").strip().rstrip("/")
+            if cfg_base_url:
+                base_url = cfg_base_url
+    except Exception:
+        pass
+
     model = _API_KEY_PROVIDER_AUX_MODELS.get("anthropic", "claude-haiku-4-5-20251001")
-    logger.debug("Auxiliary client: Anthropic native (%s)", model)
-    real_client = build_anthropic_client(token, _ANTHROPIC_DEFAULT_BASE_URL)
-    return AnthropicAuxiliaryClient(real_client, model, token, _ANTHROPIC_DEFAULT_BASE_URL), model
+    logger.debug("Auxiliary client: Anthropic native (%s) at %s", model, base_url)
+    real_client = build_anthropic_client(token, base_url)
+    return AnthropicAuxiliaryClient(real_client, model, token, base_url), model
 
 
 def _resolve_forced_provider(forced: str) -> Tuple[Optional[OpenAI], Optional[str]]:

agent/context_compressor.py

@@ -46,6 +46,7 @@ class ContextCompressor:
         summary_model_override: str = None,
         base_url: str = "",
         api_key: str = "",
+        config_context_length: int | None = None,
     ):
         self.model = model
         self.base_url = base_url
@@ -56,7 +57,10 @@ class ContextCompressor:
         self.summary_target_tokens = summary_target_tokens
         self.quiet_mode = quiet_mode
 
-        self.context_length = get_model_context_length(model, base_url=base_url, api_key=api_key)
+        self.context_length = get_model_context_length(
+            model, base_url=base_url, api_key=api_key,
+            config_context_length=config_context_length,
+        )
         self.threshold_tokens = int(self.context_length * threshold_percent)
         self.compression_count = 0
         self._context_probed = False  # True after a step-down from context error

agent/model_metadata.py

@@ -136,6 +136,8 @@ _CONTEXT_LENGTH_KEYS = (
     "max_input_tokens",
     "max_sequence_length",
     "max_seq_len",
+    "n_ctx_train",
+    "n_ctx",
 )
 
 _MAX_COMPLETION_KEYS = (
@@ -342,6 +344,25 @@ def fetch_endpoint_model_metadata(
                     entry["pricing"] = pricing
                 _add_model_aliases(cache, model_id, entry)
 
+            # If this is a llama.cpp server, query /props for actual allocated context
+            is_llamacpp = any(
+                m.get("owned_by") == "llamacpp"
+                for m in payload.get("data", []) if isinstance(m, dict)
+            )
+            if is_llamacpp:
+                try:
+                    props_url = candidate.rstrip("/").replace("/v1", "") + "/props"
+                    props_resp = requests.get(props_url, headers=headers, timeout=5)
+                    if props_resp.ok:
+                        props = props_resp.json()
+                        gen_settings = props.get("default_generation_settings", {})
+                        n_ctx = gen_settings.get("n_ctx")
+                        model_alias = props.get("model_alias", "")
+                        if n_ctx and model_alias and model_alias in cache:
+                            cache[model_alias]["context_length"] = n_ctx
+                except Exception:
+                    pass
+
             _endpoint_model_metadata_cache[normalized] = cache
             _endpoint_model_metadata_cache_time[normalized] = time.time()
             return cache
@@ -439,16 +460,26 @@ def parse_context_limit_from_error(error_msg: str) -> Optional[int]:
     return None
 
 
-def get_model_context_length(model: str, base_url: str = "", api_key: str = "") -> int:
+def get_model_context_length(
+    model: str,
+    base_url: str = "",
+    api_key: str = "",
+    config_context_length: int | None = None,
+) -> int:
     """Get the context length for a model.
 
     Resolution order:
+    0. Explicit config override (model.context_length in config.yaml)
     1. Persistent cache (previously discovered via probing)
     2. Active endpoint metadata (/models for explicit custom endpoints)
     3. OpenRouter API metadata
     4. Hardcoded DEFAULT_CONTEXT_LENGTHS (fuzzy match for hosted routes only)
     5. First probe tier (2M) — will be narrowed on first context error
     """
+    # 0. Explicit config override — user knows best
+    if config_context_length is not None and isinstance(config_context_length, int) and config_context_length > 0:
+        return config_context_length
+
     # 1. Check persistent cache (model+provider)
     if base_url:
         cached = get_cached_context_length(model, base_url)
@@ -458,13 +489,30 @@ def get_model_context_length(model: str, base_url: str = "", api_key: str = "")
     # 2. Active endpoint metadata for explicit custom routes
     if _is_custom_endpoint(base_url):
         endpoint_metadata = fetch_endpoint_model_metadata(base_url, api_key=api_key)
-        if model in endpoint_metadata:
-            context_length = endpoint_metadata[model].get("context_length")
+        matched = endpoint_metadata.get(model)
+        if not matched:
+            # Single-model servers: if only one model is loaded, use it
+            if len(endpoint_metadata) == 1:
+                matched = next(iter(endpoint_metadata.values()))
+            else:
+                # Fuzzy match: substring in either direction
+                for key, entry in endpoint_metadata.items():
+                    if model in key or key in model:
+                        matched = entry
+                        break
+        if matched:
+            context_length = matched.get("context_length")
             if isinstance(context_length, int):
                 return context_length
         if not _is_known_provider_base_url(base_url):
             # Explicit third-party endpoints should not borrow fuzzy global
             # defaults from unrelated providers with similarly named models.
+            logger.info(
+                "Could not detect context length for model %r at %s — "
+                "defaulting to %s tokens (probe-down). Set model.context_length "
+                "in config.yaml to override.",
+                model, base_url, f"{CONTEXT_PROBE_TIERS[0]:,}",
+            )
             return CONTEXT_PROBE_TIERS[0]
 
     # 3. OpenRouter API metadata

cli.py

@@ -1046,6 +1046,14 @@ class HermesCLI:
         _config_model = _model_config.get("default", "") if isinstance(_model_config, dict) else (_model_config or "")
         _FALLBACK_MODEL = "anthropic/claude-opus-4.6"
         self.model = model or _config_model or _FALLBACK_MODEL
+        # Auto-detect model from local server if still on fallback
+        if self.model == _FALLBACK_MODEL:
+            _base_url = _model_config.get("base_url", "") if isinstance(_model_config, dict) else ""
+            if "localhost" in _base_url or "127.0.0.1" in _base_url:
+                from hermes_cli.runtime_provider import _auto_detect_local_model
+                _detected = _auto_detect_local_model(_base_url)
+                if _detected:
+                    self.model = _detected
         # Track whether model was explicitly chosen by the user or fell back
         # to the global default.  Provider-specific normalisation may override
         # the default silently but should warn when overriding an explicit choice.
@@ -1251,6 +1259,8 @@ class HermesCLI:
     def _get_status_bar_snapshot(self) -> Dict[str, Any]:
         model_name = self.model or "unknown"
         model_short = model_name.split("/")[-1] if "/" in model_name else model_name
+        if model_short.endswith(".gguf"):
+            model_short = model_short[:-5]
         if len(model_short) > 26:
             model_short = f"{model_short[:23]}..."
 

gateway/run.py

@@ -1441,6 +1441,12 @@ class GatewayRunner:
         if canonical == "reload-mcp":
             return await self._handle_reload_mcp_command(event)
 
+        if canonical == "approve":
+            return await self._handle_approve_command(event)
+
+        if canonical == "deny":
+            return await self._handle_deny_command(event)
+
         if canonical == "update":
             return await self._handle_update_command(event)
 
@@ -1518,32 +1524,9 @@ class GatewayRunner:
             except Exception as e:
                 logger.debug("Skill command check failed (non-fatal): %s", e)
         
-        # Check for pending exec approval responses
-        session_key_preview = self._session_key_for_source(source)
-        if session_key_preview in self._pending_approvals:
-            user_text = event.text.strip().lower()
-            if user_text in ("yes", "y", "approve", "ok", "go", "do it"):
-                approval = self._pending_approvals.pop(session_key_preview)
-                cmd = approval["command"]
-                pattern_keys = approval.get("pattern_keys", [])
-                if not pattern_keys:
-                    pk = approval.get("pattern_key", "")
-                    pattern_keys = [pk] if pk else []
-                logger.info("User approved dangerous command: %s...", cmd[:60])
-                from tools.terminal_tool import terminal_tool
-                from tools.approval import approve_session
-                for pk in pattern_keys:
-                    approve_session(session_key_preview, pk)
-                result = terminal_tool(command=cmd, force=True)
-                return f"✅ Command approved and executed.\n\n```\n{result[:3500]}\n```"
-            elif user_text in ("no", "n", "deny", "cancel", "nope"):
-                self._pending_approvals.pop(session_key_preview)
-                return "❌ Command denied."
-            elif user_text in ("full", "show", "view", "show full", "view full"):
-                # Show full command without consuming the approval
-                cmd = self._pending_approvals[session_key_preview]["command"]
-                return f"Full command:\n\n```\n{cmd}\n```\n\nReply yes/no to approve or deny."
-            # If it's not clearly an approval/denial, fall through to normal processing
+        # Pending exec approvals are handled by /approve and /deny commands above.
+        # No bare text matching — "yes" in normal conversation must not trigger
+        # execution of a dangerous command.
         
         # Get or create session
         session_entry = self.session_store.get_or_create_session(source)
@@ -2059,9 +2042,22 @@ class GatewayRunner:
             # Check if the agent encountered a dangerous command needing approval
             try:
                 from tools.approval import pop_pending
+                import time as _time
                 pending = pop_pending(session_key)
                 if pending:
+                    pending["timestamp"] = _time.time()
                     self._pending_approvals[session_key] = pending
+                    # Append structured instructions so the user knows how to respond
+                    cmd_preview = pending.get("command", "")
+                    if len(cmd_preview) > 200:
+                        cmd_preview = cmd_preview[:200] + "..."
+                    approval_hint = (
+                        f"\n\n⚠️ **Dangerous command requires approval:**\n"
+                        f"```\n{cmd_preview}\n```\n"
+                        f"Reply `/approve` to execute, `/approve session` to approve this pattern "
+                        f"for the session, or `/deny` to cancel."
+                    )
+                    response = (response or "") + approval_hint
             except Exception as e:
                 logger.debug("Failed to check pending approvals: %s", e)
             
@@ -3696,6 +3692,78 @@ class GatewayRunner:
             logger.warning("MCP reload failed: %s", e)
             return f"❌ MCP reload failed: {e}"
 
+    # ------------------------------------------------------------------
+    # /approve & /deny — explicit dangerous-command approval
+    # ------------------------------------------------------------------
+
+    _APPROVAL_TIMEOUT_SECONDS = 300  # 5 minutes
+
+    async def _handle_approve_command(self, event: MessageEvent) -> str:
+        """Handle /approve command — execute a pending dangerous command.
+
+        Usage:
+            /approve          — approve and execute the pending command
+            /approve session  — approve and remember for this session
+            /approve always   — approve this pattern permanently
+        """
+        source = event.source
+        session_key = self._session_key_for_source(source)
+
+        if session_key not in self._pending_approvals:
+            return "No pending command to approve."
+
+        import time as _time
+        approval = self._pending_approvals[session_key]
+
+        # Check for timeout
+        ts = approval.get("timestamp", 0)
+        if _time.time() - ts > self._APPROVAL_TIMEOUT_SECONDS:
+            self._pending_approvals.pop(session_key, None)
+            return "⚠️ Approval expired (timed out after 5 minutes). Ask the agent to try again."
+
+        self._pending_approvals.pop(session_key)
+        cmd = approval["command"]
+        pattern_keys = approval.get("pattern_keys", [])
+        if not pattern_keys:
+            pk = approval.get("pattern_key", "")
+            pattern_keys = [pk] if pk else []
+
+        # Determine approval scope from args
+        args = event.get_command_args().strip().lower()
+        from tools.approval import approve_session, approve_permanent
+
+        if args in ("always", "permanent", "permanently"):
+            for pk in pattern_keys:
+                approve_permanent(pk)
+            scope_msg = " (pattern approved permanently)"
+        elif args in ("session", "ses"):
+            for pk in pattern_keys:
+                approve_session(session_key, pk)
+            scope_msg = " (pattern approved for this session)"
+        else:
+            # One-time approval — just approve for session so the immediate
+            # replay works, but don't advertise it as session-wide
+            for pk in pattern_keys:
+                approve_session(session_key, pk)
+            scope_msg = ""
+
+        logger.info("User approved dangerous command via /approve: %s...%s", cmd[:60], scope_msg)
+        from tools.terminal_tool import terminal_tool
+        result = terminal_tool(command=cmd, force=True)
+        return f"✅ Command approved and executed{scope_msg}.\n\n```\n{result[:3500]}\n```"
+
+    async def _handle_deny_command(self, event: MessageEvent) -> str:
+        """Handle /deny command — reject a pending dangerous command."""
+        source = event.source
+        session_key = self._session_key_for_source(source)
+
+        if session_key not in self._pending_approvals:
+            return "No pending command to deny."
+
+        self._pending_approvals.pop(session_key)
+        logger.info("User denied dangerous command via /deny")
+        return "❌ Command denied."
+
     async def _handle_update_command(self, event: MessageEvent) -> str:
         """Handle /update command — update Hermes Agent to the latest version.
 

hermes_cli/banner.py

@@ -289,6 +289,8 @@ def build_welcome_banner(console: Console, model: str, cwd: str,
         _hero = HERMES_CADUCEUS
     left_lines = ["", _hero, ""]
     model_short = model.split("/")[-1] if "/" in model else model
+    if model_short.endswith(".gguf"):
+        model_short = model_short[:-5]
     if len(model_short) > 28:
         model_short = model_short[:25] + "..."
     ctx_str = f" [dim {dim}]·[/] [dim {dim}]{_format_context_length(context_length)} context[/]" if context_length else ""

hermes_cli/commands.py

@@ -61,6 +61,10 @@ COMMAND_REGISTRY: list[CommandDef] = [
     CommandDef("rollback", "List or restore filesystem checkpoints", "Session",
                args_hint="[number]"),
     CommandDef("stop", "Kill all running background processes", "Session"),
+    CommandDef("approve", "Approve a pending dangerous command", "Session",
+               gateway_only=True, args_hint="[session|always]"),
+    CommandDef("deny", "Deny a pending dangerous command", "Session",
+               gateway_only=True),
     CommandDef("background", "Run a prompt in the background", "Session",
                aliases=("bg",), args_hint="<prompt>"),
     CommandDef("status", "Show session info", "Session",

hermes_cli/runtime_provider.py

@@ -24,11 +24,41 @@ def _normalize_custom_provider_name(value: str) -> str:
     return value.strip().lower().replace(" ", "-")
 
 
+def _auto_detect_local_model(base_url: str) -> str:
+    """Query a local server for its model name when only one model is loaded."""
+    if not base_url:
+        return ""
+    try:
+        import requests
+        url = base_url.rstrip("/")
+        if not url.endswith("/v1"):
+            url += "/v1"
+        resp = requests.get(url + "/models", timeout=5)
+        if resp.ok:
+            models = resp.json().get("data", [])
+            if len(models) == 1:
+                model_id = models[0].get("id", "")
+                if model_id:
+                    return model_id
+    except Exception:
+        pass
+    return ""
+
+
 def _get_model_config() -> Dict[str, Any]:
     config = load_config()
     model_cfg = config.get("model")
     if isinstance(model_cfg, dict):
-        return dict(model_cfg)
+        cfg = dict(model_cfg)
+        default = cfg.get("default", "").strip()
+        base_url = cfg.get("base_url", "").strip()
+        is_local = "localhost" in base_url or "127.0.0.1" in base_url
+        is_fallback = not default or default == "anthropic/claude-opus-4.6"
+        if is_local and is_fallback and base_url:
+            detected = _auto_detect_local_model(base_url)
+            if detected:
+                cfg["default"] = detected
+        return cfg
     if isinstance(model_cfg, str) and model_cfg.strip():
         return {"default": model_cfg.strip()}
     return {}
@@ -313,10 +343,14 @@ def resolve_runtime_provider(
                 "No Anthropic credentials found. Set ANTHROPIC_TOKEN or ANTHROPIC_API_KEY, "
                 "run 'claude setup-token', or authenticate with 'claude /login'."
             )
+        # Allow base URL override from config.yaml model.base_url
+        model_cfg = _get_model_config()
+        cfg_base_url = (model_cfg.get("base_url") or "").strip().rstrip("/")
+        base_url = cfg_base_url or "https://api.anthropic.com"
         return {
             "provider": "anthropic",
             "api_mode": "anthropic_messages",
-            "base_url": "https://api.anthropic.com",
+            "base_url": base_url,
             "api_key": token,
             "source": "env",
             "requested_provider": requested_provider,
@@ -340,13 +374,23 @@ def resolve_runtime_provider(
     if pconfig and pconfig.auth_type == "api_key":
         creds = resolve_api_key_provider_credentials(provider)
         model_cfg = _get_model_config()
+        base_url = creds.get("base_url", "").rstrip("/")
         api_mode = "chat_completions"
         if provider == "copilot":
             api_mode = _copilot_runtime_api_mode(model_cfg, creds.get("api_key", ""))
+        else:
+            # Check explicit api_mode from model config first
+            configured_mode = _parse_api_mode(model_cfg.get("api_mode"))
+            if configured_mode:
+                api_mode = configured_mode
+            # Auto-detect Anthropic-compatible endpoints by URL convention
+            # (e.g. https://api.minimax.io/anthropic, https://dashscope.../anthropic)
+            elif base_url.rstrip("/").endswith("/anthropic"):
+                api_mode = "anthropic_messages"
         return {
             "provider": provider,
             "api_mode": api_mode,
-            "base_url": creds.get("base_url", "").rstrip("/"),
+            "base_url": base_url,
             "api_key": creds.get("api_key", ""),
             "source": creds.get("source", "env"),
             "requested_provider": requested_provider,

run_agent.py

@@ -493,6 +493,11 @@ class AIAgent:
         elif self.provider == "anthropic" or (provider_name is None and "api.anthropic.com" in self._base_url_lower):
             self.api_mode = "anthropic_messages"
             self.provider = "anthropic"
+        elif self._base_url_lower.rstrip("/").endswith("/anthropic"):
+            # Third-party Anthropic-compatible endpoints (e.g. MiniMax, DashScope)
+            # use a URL convention ending in /anthropic. Auto-detect these so the
+            # Anthropic Messages API adapter is used instead of chat completions.
+            self.api_mode = "anthropic_messages"
         else:
             self.api_mode = "chat_completions"
 
@@ -964,6 +969,18 @@ class AIAgent:
         compression_threshold = float(_compression_cfg.get("threshold", 0.50))
         compression_enabled = str(_compression_cfg.get("enabled", True)).lower() in ("true", "1", "yes")
         compression_summary_model = _compression_cfg.get("summary_model") or None
+
+        # Read explicit context_length override from model config
+        _model_cfg = _agent_cfg.get("model", {})
+        if isinstance(_model_cfg, dict):
+            _config_context_length = _model_cfg.get("context_length")
+        else:
+            _config_context_length = None
+        if _config_context_length is not None:
+            try:
+                _config_context_length = int(_config_context_length)
+            except (TypeError, ValueError):
+                _config_context_length = None
         
         self.context_compressor = ContextCompressor(
             model=self.model,
@@ -975,6 +992,7 @@ class AIAgent:
             quiet_mode=self.quiet_mode,
             base_url=self.base_url,
             api_key=getattr(self, "api_key", ""),
+            config_context_length=_config_context_length,
         )
         self.compression_enabled = compression_enabled
         self._user_turn_count = 0
@@ -3474,11 +3492,11 @@ class AIAgent:
 
             # Determine api_mode from provider
             fb_api_mode = "chat_completions"
+            fb_base_url = str(fb_client.base_url)
             if fb_provider == "openai-codex":
                 fb_api_mode = "codex_responses"
-            elif fb_provider == "anthropic":
+            elif fb_provider == "anthropic" or fb_base_url.rstrip("/").lower().endswith("/anthropic"):
                 fb_api_mode = "anthropic_messages"
-            fb_base_url = str(fb_client.base_url)
 
             old_model = self.model
             self.model = fb_model

tests/agent/test_model_metadata.py

@@ -218,6 +218,79 @@ class TestGetModelContextLength:
 
         assert result == CONTEXT_PROBE_TIERS[0]
 
+    @patch("agent.model_metadata.fetch_model_metadata")
+    @patch("agent.model_metadata.fetch_endpoint_model_metadata")
+    def test_custom_endpoint_single_model_fallback(self, mock_endpoint_fetch, mock_fetch):
+        """Single-model servers: use the only model even if name doesn't match."""
+        mock_fetch.return_value = {}
+        mock_endpoint_fetch.return_value = {
+            "Qwen3.5-9B-Q4_K_M.gguf": {"context_length": 131072}
+        }
+
+        result = get_model_context_length(
+            "qwen3.5:9b",
+            base_url="http://myserver.example.com:8080/v1",
+            api_key="test-key",
+        )
+
+        assert result == 131072
+
+    @patch("agent.model_metadata.fetch_model_metadata")
+    @patch("agent.model_metadata.fetch_endpoint_model_metadata")
+    def test_custom_endpoint_fuzzy_substring_match(self, mock_endpoint_fetch, mock_fetch):
+        """Fuzzy match: configured model name is substring of endpoint model."""
+        mock_fetch.return_value = {}
+        mock_endpoint_fetch.return_value = {
+            "org/llama-3.3-70b-instruct-fp8": {"context_length": 131072},
+            "org/qwen-2.5-72b": {"context_length": 32768},
+        }
+
+        result = get_model_context_length(
+            "llama-3.3-70b-instruct",
+            base_url="http://myserver.example.com:8080/v1",
+            api_key="test-key",
+        )
+
+        assert result == 131072
+
+    @patch("agent.model_metadata.fetch_model_metadata")
+    def test_config_context_length_overrides_all(self, mock_fetch):
+        """Explicit config_context_length takes priority over everything."""
+        mock_fetch.return_value = {
+            "test/model": {"context_length": 200000}
+        }
+
+        result = get_model_context_length(
+            "test/model",
+            config_context_length=65536,
+        )
+
+        assert result == 65536
+
+    @patch("agent.model_metadata.fetch_model_metadata")
+    def test_config_context_length_zero_is_ignored(self, mock_fetch):
+        """config_context_length=0 should be treated as unset."""
+        mock_fetch.return_value = {}
+
+        result = get_model_context_length(
+            "anthropic/claude-sonnet-4",
+            config_context_length=0,
+        )
+
+        assert result == 200000
+
+    @patch("agent.model_metadata.fetch_model_metadata")
+    def test_config_context_length_none_is_ignored(self, mock_fetch):
+        """config_context_length=None should be treated as unset."""
+        mock_fetch.return_value = {}
+
+        result = get_model_context_length(
+            "anthropic/claude-sonnet-4",
+            config_context_length=None,
+        )
+
+        assert result == 200000
+
 
 # =========================================================================
 # fetch_model_metadata — caching, TTL, slugs, failures

tests/gateway/test_approve_deny_commands.py

@@ -0,0 +1,240 @@
+"""Tests for /approve and /deny gateway commands.
+
+Verifies that dangerous command approvals require explicit /approve or /deny
+slash commands, not bare "yes"/"no" text matching.
+"""
+
+import time
+from types import SimpleNamespace
+from unittest.mock import AsyncMock, MagicMock, patch
+
+import pytest
+
+from gateway.config import GatewayConfig, Platform, PlatformConfig
+from gateway.platforms.base import MessageEvent
+from gateway.session import SessionEntry, SessionSource, build_session_key
+
+
+def _make_source() -> SessionSource:
+    return SessionSource(
+        platform=Platform.TELEGRAM,
+        user_id="u1",
+        chat_id="c1",
+        user_name="tester",
+        chat_type="dm",
+    )
+
+
+def _make_event(text: str) -> MessageEvent:
+    return MessageEvent(
+        text=text,
+        source=_make_source(),
+        message_id="m1",
+    )
+
+
+def _make_runner():
+    from gateway.run import GatewayRunner
+
+    runner = object.__new__(GatewayRunner)
+    runner.config = GatewayConfig(
+        platforms={Platform.TELEGRAM: PlatformConfig(enabled=True, token="***")}
+    )
+    adapter = MagicMock()
+    adapter.send = AsyncMock()
+    runner.adapters = {Platform.TELEGRAM: adapter}
+    runner._voice_mode = {}
+    runner.hooks = SimpleNamespace(emit=AsyncMock(), loaded_hooks=False)
+    runner.session_store = MagicMock()
+    runner._running_agents = {}
+    runner._pending_messages = {}
+    runner._pending_approvals = {}
+    runner._session_db = None
+    runner._reasoning_config = None
+    runner._provider_routing = {}
+    runner._fallback_model = None
+    runner._show_reasoning = False
+    runner._is_user_authorized = lambda _source: True
+    runner._set_session_env = lambda _context: None
+    return runner
+
+
+def _make_pending_approval(command="sudo rm -rf /tmp/test", pattern_key="sudo"):
+    return {
+        "command": command,
+        "pattern_key": pattern_key,
+        "pattern_keys": [pattern_key],
+        "description": "sudo command",
+        "timestamp": time.time(),
+    }
+
+
+# ------------------------------------------------------------------
+# /approve command
+# ------------------------------------------------------------------
+
+
+class TestApproveCommand:
+
+    @pytest.mark.asyncio
+    async def test_approve_executes_pending_command(self):
+        """Basic /approve executes the pending command."""
+        runner = _make_runner()
+        source = _make_source()
+        session_key = runner._session_key_for_source(source)
+        runner._pending_approvals[session_key] = _make_pending_approval()
+
+        event = _make_event("/approve")
+        with patch("tools.terminal_tool.terminal_tool", return_value="done") as mock_term:
+            result = await runner._handle_approve_command(event)
+
+        assert "✅ Command approved and executed" in result
+        mock_term.assert_called_once_with(command="sudo rm -rf /tmp/test", force=True)
+        assert session_key not in runner._pending_approvals
+
+    @pytest.mark.asyncio
+    async def test_approve_session_remembers_pattern(self):
+        """/approve session approves the pattern for the session."""
+        runner = _make_runner()
+        source = _make_source()
+        session_key = runner._session_key_for_source(source)
+        runner._pending_approvals[session_key] = _make_pending_approval()
+
+        event = _make_event("/approve session")
+        with (
+            patch("tools.terminal_tool.terminal_tool", return_value="done"),
+            patch("tools.approval.approve_session") as mock_session,
+        ):
+            result = await runner._handle_approve_command(event)
+
+        assert "pattern approved for this session" in result
+        mock_session.assert_called_once_with(session_key, "sudo")
+
+    @pytest.mark.asyncio
+    async def test_approve_always_approves_permanently(self):
+        """/approve always approves the pattern permanently."""
+        runner = _make_runner()
+        source = _make_source()
+        session_key = runner._session_key_for_source(source)
+        runner._pending_approvals[session_key] = _make_pending_approval()
+
+        event = _make_event("/approve always")
+        with (
+            patch("tools.terminal_tool.terminal_tool", return_value="done"),
+            patch("tools.approval.approve_permanent") as mock_perm,
+        ):
+            result = await runner._handle_approve_command(event)
+
+        assert "pattern approved permanently" in result
+        mock_perm.assert_called_once_with("sudo")
+
+    @pytest.mark.asyncio
+    async def test_approve_no_pending(self):
+        """/approve with no pending approval returns helpful message."""
+        runner = _make_runner()
+        event = _make_event("/approve")
+        result = await runner._handle_approve_command(event)
+        assert "No pending command" in result
+
+    @pytest.mark.asyncio
+    async def test_approve_expired(self):
+        """/approve on a timed-out approval rejects it."""
+        runner = _make_runner()
+        source = _make_source()
+        session_key = runner._session_key_for_source(source)
+        approval = _make_pending_approval()
+        approval["timestamp"] = time.time() - 600  # 10 minutes ago
+        runner._pending_approvals[session_key] = approval
+
+        event = _make_event("/approve")
+        result = await runner._handle_approve_command(event)
+
+        assert "expired" in result
+        assert session_key not in runner._pending_approvals
+
+
+# ------------------------------------------------------------------
+# /deny command
+# ------------------------------------------------------------------
+
+
+class TestDenyCommand:
+
+    @pytest.mark.asyncio
+    async def test_deny_clears_pending(self):
+        """/deny clears the pending approval."""
+        runner = _make_runner()
+        source = _make_source()
+        session_key = runner._session_key_for_source(source)
+        runner._pending_approvals[session_key] = _make_pending_approval()
+
+        event = _make_event("/deny")
+        result = await runner._handle_deny_command(event)
+
+        assert "❌ Command denied" in result
+        assert session_key not in runner._pending_approvals
+
+    @pytest.mark.asyncio
+    async def test_deny_no_pending(self):
+        """/deny with no pending approval returns helpful message."""
+        runner = _make_runner()
+        event = _make_event("/deny")
+        result = await runner._handle_deny_command(event)
+        assert "No pending command" in result
+
+
+# ------------------------------------------------------------------
+# Bare "yes" must NOT trigger approval
+# ------------------------------------------------------------------
+
+
+class TestBareTextNoLongerApproves:
+
+    @pytest.mark.asyncio
+    async def test_yes_does_not_execute_pending_command(self):
+        """Saying 'yes' in normal conversation must not execute a pending command.
+
+        This is the core bug from issue #1888: bare text matching against
+        'yes'/'no' could intercept unrelated user messages.
+        """
+        runner = _make_runner()
+        source = _make_source()
+        session_key = runner._session_key_for_source(source)
+        runner._pending_approvals[session_key] = _make_pending_approval()
+
+        # Simulate the user saying "yes" as a normal message.
+        # The old code would have executed the pending command.
+        # Now it should fall through to normal processing (agent handles it).
+        event = _make_event("yes")
+
+        # The approval should still be pending — "yes" is not /approve
+        # We can't easily run _handle_message end-to-end, but we CAN verify
+        # the old text-matching block no longer exists by confirming the
+        # approval is untouched after the command dispatch section.
+        # The key assertion is that _pending_approvals is NOT consumed.
+        assert session_key in runner._pending_approvals
+
+
+# ------------------------------------------------------------------
+# Approval hint appended to response
+# ------------------------------------------------------------------
+
+
+class TestApprovalHint:
+
+    def test_approval_hint_appended_to_response(self):
+        """When a pending approval is collected, structured instructions
+        should be appended to the agent response."""
+        # This tests the approval collection logic at the end of _handle_message.
+        # We verify the hint format directly.
+        cmd = "sudo rm -rf /tmp/dangerous"
+        cmd_preview = cmd
+        hint = (
+            f"\n\n⚠️ **Dangerous command requires approval:**\n"
+            f"```\n{cmd_preview}\n```\n"
+            f"Reply `/approve` to execute, `/approve session` to approve this pattern "
+            f"for the session, or `/deny` to cancel."
+        )
+        assert "/approve" in hint
+        assert "/deny" in hint
+        assert cmd in hint

tests/test_runtime_provider_resolution.py

@@ -438,10 +438,75 @@ def test_named_custom_provider_without_api_mode_defaults(monkeypatch):
         lambda p: {
             "name": "my-server",
             "base_url": "http://localhost:8000/v1",
-            "api_key": "sk-test",
+            "api_key": "***",
         },
     )
 
     resolved = rp.resolve_runtime_provider(requested="my-server")
 
     assert resolved["api_mode"] == "chat_completions"
+
+
+def test_anthropic_messages_in_valid_api_modes():
+    """anthropic_messages should be accepted by _parse_api_mode."""
+    assert rp._parse_api_mode("anthropic_messages") == "anthropic_messages"
+
+
+def test_api_key_provider_anthropic_url_auto_detection(monkeypatch):
+    """API-key providers with /anthropic base URL should auto-detect anthropic_messages mode."""
+    monkeypatch.setattr(rp, "resolve_provider", lambda *a, **k: "minimax")
+    monkeypatch.setattr(rp, "_get_model_config", lambda: {})
+    monkeypatch.setenv("MINIMAX_API_KEY", "test-minimax-key")
+    monkeypatch.setenv("MINIMAX_BASE_URL", "https://api.minimax.io/anthropic")
+
+    resolved = rp.resolve_runtime_provider(requested="minimax")
+
+    assert resolved["provider"] == "minimax"
+    assert resolved["api_mode"] == "anthropic_messages"
+    assert resolved["base_url"] == "https://api.minimax.io/anthropic"
+
+
+def test_api_key_provider_explicit_api_mode_config(monkeypatch):
+    """API-key providers should respect api_mode from model config."""
+    monkeypatch.setattr(rp, "resolve_provider", lambda *a, **k: "minimax")
+    monkeypatch.setattr(rp, "_get_model_config", lambda: {"api_mode": "anthropic_messages"})
+    monkeypatch.setenv("MINIMAX_API_KEY", "test-minimax-key")
+    monkeypatch.delenv("MINIMAX_BASE_URL", raising=False)
+
+    resolved = rp.resolve_runtime_provider(requested="minimax")
+
+    assert resolved["provider"] == "minimax"
+    assert resolved["api_mode"] == "anthropic_messages"
+
+
+def test_api_key_provider_default_url_stays_chat_completions(monkeypatch):
+    """API-key providers with default /v1 URL should stay on chat_completions."""
+    monkeypatch.setattr(rp, "resolve_provider", lambda *a, **k: "minimax")
+    monkeypatch.setattr(rp, "_get_model_config", lambda: {})
+    monkeypatch.setenv("MINIMAX_API_KEY", "test-minimax-key")
+    monkeypatch.delenv("MINIMAX_BASE_URL", raising=False)
+
+    resolved = rp.resolve_runtime_provider(requested="minimax")
+
+    assert resolved["provider"] == "minimax"
+    assert resolved["api_mode"] == "chat_completions"
+    assert resolved["base_url"] == "https://api.minimax.io/v1"
+
+
+def test_named_custom_provider_anthropic_api_mode(monkeypatch):
+    """Custom providers should accept api_mode: anthropic_messages."""
+    monkeypatch.setattr(rp, "resolve_provider", lambda *a, **k: "my-anthropic-proxy")
+    monkeypatch.setattr(
+        rp, "_get_named_custom_provider",
+        lambda p: {
+            "name": "my-anthropic-proxy",
+            "base_url": "https://proxy.example.com/anthropic",
+            "api_key": "test-key",
+            "api_mode": "anthropic_messages",
+        },
+    )
+
+    resolved = rp.resolve_runtime_provider(requested="my-anthropic-proxy")
+
+    assert resolved["api_mode"] == "anthropic_messages"
+    assert resolved["base_url"] == "https://proxy.example.com/anthropic"

website/docs/getting-started/quickstart.md

@@ -51,6 +51,8 @@ hermes setup       # Or configure everything at once
 | **MiniMax China** | China-region MiniMax endpoint | Set `MINIMAX_CN_API_KEY` |
 | **Alibaba Cloud** | Qwen models via DashScope | Set `DASHSCOPE_API_KEY` |
 | **Kilo Code** | KiloCode-hosted models | Set `KILOCODE_API_KEY` |
+| **OpenCode Zen** | Pay-as-you-go access to curated models | Set `OPENCODE_ZEN_API_KEY` |
+| **OpenCode Go** | $10/month subscription for open models | Set `OPENCODE_GO_API_KEY` |
 | **Vercel AI Gateway** | Vercel AI Gateway routing | Set `AI_GATEWAY_API_KEY` |
 | **Custom Endpoint** | VLLM, SGLang, or any OpenAI-compatible API | Set base URL + API key |
 

website/docs/reference/cli-commands.md

@@ -66,7 +66,7 @@ Common options:
 | `-q`, `--query "..."` | One-shot, non-interactive prompt. |
 | `-m`, `--model <model>` | Override the model for this run. |
 | `-t`, `--toolsets <csv>` | Enable a comma-separated set of toolsets. |
-| `--provider <provider>` | Force a provider: `auto`, `openrouter`, `nous`, `openai-codex`, `copilot`, `copilot-acp`, `anthropic`, `zai`, `kimi-coding`, `minimax`, `minimax-cn`. |
+| `--provider <provider>` | Force a provider: `auto`, `openrouter`, `nous`, `openai-codex`, `copilot`, `copilot-acp`, `anthropic`, `zai`, `kimi-coding`, `minimax`, `minimax-cn`, `opencode-zen`, `opencode-go`, `ai-gateway`, `kilocode`, `alibaba`. |
 | `-v`, `--verbose` | Verbose output. |
 | `-Q`, `--quiet` | Programmatic mode: suppress banner/spinner/tool previews. |
 | `--resume <session>` / `--continue [name]` | Resume a session directly from `chat`. |

website/docs/reference/environment-variables.md

@@ -41,6 +41,12 @@ All variables go in `~/.hermes/.env`. You can also set them with `hermes config
 | `ANTHROPIC_TOKEN` | Manual or legacy Anthropic OAuth/setup-token override |
 | `DASHSCOPE_API_KEY` | Alibaba Cloud DashScope API key for Qwen models ([modelstudio.console.alibabacloud.com](https://modelstudio.console.alibabacloud.com/)) |
 | `DASHSCOPE_BASE_URL` | Custom DashScope base URL (default: international endpoint) |
+| `DEEPSEEK_API_KEY` | DeepSeek API key for direct DeepSeek access ([platform.deepseek.com](https://platform.deepseek.com/api_keys)) |
+| `DEEPSEEK_BASE_URL` | Custom DeepSeek API base URL |
+| `OPENCODE_ZEN_API_KEY` | OpenCode Zen API key — pay-as-you-go access to curated models ([opencode.ai](https://opencode.ai/auth)) |
+| `OPENCODE_ZEN_BASE_URL` | Override OpenCode Zen base URL |
+| `OPENCODE_GO_API_KEY` | OpenCode Go API key — $10/month subscription for open models ([opencode.ai](https://opencode.ai/auth)) |
+| `OPENCODE_GO_BASE_URL` | Override OpenCode Go base URL |
 | `CLAUDE_CODE_OAUTH_TOKEN` | Explicit Claude Code token override if you export one manually |
 | `HERMES_MODEL` | Preferred model name (checked before `LLM_MODEL`, used by gateway) |
 | `LLM_MODEL` | Default model name (fallback when not set in config.yaml) |
@@ -71,6 +77,7 @@ For native Anthropic auth, Hermes prefers Claude Code's own credential files whe
 | `PARALLEL_API_KEY` | AI-native web search ([parallel.ai](https://parallel.ai/)) |
 | `FIRECRAWL_API_KEY` | Web scraping ([firecrawl.dev](https://firecrawl.dev/)) |
 | `FIRECRAWL_API_URL` | Custom Firecrawl API endpoint for self-hosted instances (optional) |
+| `TAVILY_API_KEY` | Tavily API key for AI-native web search, extract, and crawl ([app.tavily.com](https://app.tavily.com/home)) |
 | `BROWSERBASE_API_KEY` | Browser automation ([browserbase.com](https://browserbase.com/)) |
 | `BROWSERBASE_PROJECT_ID` | Browserbase project ID |
 | `BROWSER_USE_API_KEY` | Browser Use cloud browser API key ([browser-use.com](https://browser-use.com/)) |
@@ -83,6 +90,7 @@ For native Anthropic auth, Hermes prefers Claude Code's own credential files whe
 | `GROQ_BASE_URL` | Override the Groq OpenAI-compatible STT endpoint |
 | `STT_OPENAI_MODEL` | Override the OpenAI STT model (default: `whisper-1`) |
 | `STT_OPENAI_BASE_URL` | Override the OpenAI-compatible STT endpoint |
+| `GITHUB_TOKEN` | GitHub token for Skills Hub (higher API rate limits, skill publish) |
 | `HONCHO_API_KEY` | Cross-session user modeling ([honcho.dev](https://honcho.dev/)) |
 | `TINKER_API_KEY` | RL training ([tinker-console.thinkingmachines.ai](https://tinker-console.thinkingmachines.ai/)) |
 | `WANDB_API_KEY` | RL training metrics ([wandb.ai](https://wandb.ai/)) |
@@ -211,7 +219,7 @@ For native Anthropic auth, Hermes prefers Claude Code's own credential files whe
 
 | Variable | Description |
 |----------|-------------|
-| `HERMES_MAX_ITERATIONS` | Max tool-calling iterations per conversation (default: 60) |
+| `HERMES_MAX_ITERATIONS` | Max tool-calling iterations per conversation (default: 90) |
 | `HERMES_TOOL_PROGRESS` | Deprecated compatibility variable for tool progress display. Prefer `display.tool_progress` in `config.yaml`. |
 | `HERMES_TOOL_PROGRESS_MODE` | Deprecated compatibility variable for tool progress mode. Prefer `display.tool_progress` in `config.yaml`. |
 | `HERMES_HUMAN_DELAY_MODE` | Response pacing: `off`/`natural`/`custom` |
@@ -221,6 +229,7 @@ For native Anthropic auth, Hermes prefers Claude Code's own credential files whe
 | `HERMES_API_TIMEOUT` | LLM API call timeout in seconds (default: `900`) |
 | `HERMES_EXEC_ASK` | Enable execution approval prompts in gateway mode (`true`/`false`) |
 | `HERMES_BACKGROUND_NOTIFICATIONS` | Background process notification mode in gateway: `all` (default), `result`, `error`, `off` |
+| `HERMES_EPHEMERAL_SYSTEM_PROMPT` | Ephemeral system prompt injected at API-call time (never persisted to sessions) |
 
 ## Session Settings
 

website/docs/reference/slash-commands.md

@@ -21,9 +21,8 @@ Type `/` in the CLI to open the autocomplete menu. Built-in commands are case-in
 
 | Command | Description |
 |---------|-------------|
-| `/new` | Start a new conversation (reset history) |
-| `/reset` | Reset conversation only (keep screen) |
-| `/clear` | Clear screen and reset conversation (fresh start) |
+| `/new` (alias: `/reset`) | Start a new session (fresh session ID + history) |
+| `/clear` | Clear screen and start a new session |
 | `/history` | Show conversation history |
 | `/save` | Save the current conversation |
 | `/retry` | Retry the last message (resend to agent) |
@@ -31,6 +30,7 @@ Type `/` in the CLI to open the autocomplete menu. Built-in commands are case-in
 | `/title` | Set a title for the current session (usage: /title My Session Name) |
 | `/compress` | Manually compress conversation context (flush memories + summarize) |
 | `/rollback` | List or restore filesystem checkpoints (usage: /rollback [number]) |
+| `/stop` | Kill all running background processes |
 | `/background <prompt>` | Run a prompt in a separate background session. The agent processes your prompt independently — your current session stays free for other work. Results appear as a panel when the task finishes. See [CLI Background Sessions](/docs/user-guide/cli#background-sessions). |
 | `/plan [request]` | Load the bundled `plan` skill to write a markdown plan instead of executing the work. Plans are saved under `.hermes/plans/` relative to the active workspace/backend working directory. |
 
@@ -58,6 +58,7 @@ Type `/` in the CLI to open the autocomplete menu. Built-in commands are case-in
 | `/skills` | Search, install, inspect, or manage skills from online registries |
 | `/cron` | Manage scheduled tasks (list, add/create, edit, pause, resume, run, remove) |
 | `/reload-mcp` | Reload MCP servers from config.yaml |
+| `/plugins` | List installed plugins and their status |
 
 ### Info
 
@@ -95,7 +96,7 @@ The messaging gateway supports the following built-in commands inside Telegram,
 | `/new` | Start a new conversation. |
 | `/reset` | Reset conversation history. |
 | `/status` | Show session info. |
-| `/stop` | Interrupt the running agent without queuing a follow-up prompt. |
+| `/stop` | Kill all running background processes and interrupt the running agent. |
 | `/model [provider:model]` | Show or change the model, including provider switches. |
 | `/provider` | Show provider availability and auth status. |
 | `/personality [name]` | Set a personality overlay for the session. |
@@ -119,7 +120,7 @@ The messaging gateway supports the following built-in commands inside Telegram,
 
 ## Notes
 
-- `/skin`, `/tools`, `/toolsets`, `/browser`, `/config`, `/prompt`, `/cron`, `/skills`, `/platforms`, `/paste`, and `/verbose` are **CLI-only** commands.
-- `/status`, `/stop`, `/sethome`, `/resume`, and `/update` are **messaging-only** commands.
+- `/skin`, `/tools`, `/toolsets`, `/browser`, `/config`, `/prompt`, `/cron`, `/skills`, `/platforms`, `/paste`, `/verbose`, and `/plugins` are **CLI-only** commands.
+- `/status`, `/sethome`, and `/update` are **messaging-only** commands.
 - `/background`, `/voice`, `/reload-mcp`, and `/rollback` work in **both** the CLI and the messaging gateway.
 - `/voice join`, `/voice channel`, and `/voice leave` are only meaningful on Discord.

website/docs/reference/tools-reference.md

@@ -141,6 +141,19 @@ This page documents the built-in Hermes tool registry as it exists in code. Avai
 |------|-------------|----------------------|
 | `todo` | Manage your task list for the current session. Use for complex tasks with 3+ steps or when the user provides multiple tasks. Call with no parameters to read the current list. Writing: - Provide 'todos' array to create/update items - merge=… | — |
 
+## `vision` toolset
+
+| Tool | Description | Requires environment |
+|------|-------------|----------------------|
+| `vision_analyze` | Analyze images using AI vision. Provides a comprehensive description and answers a specific question about the image content. | — |
+
+## `web` toolset
+
+| Tool | Description | Requires environment |
+|------|-------------|----------------------|
+| `web_search` | Search the web for information on any topic. Returns up to 5 relevant results with titles, URLs, and descriptions. | PARALLEL_API_KEY or FIRECRAWL_API_KEY or TAVILY_API_KEY |
+| `web_extract` | Extract content from web page URLs. Returns page content in markdown format. Also works with PDF URLs — pass the PDF link directly and it converts to markdown text. Pages under 5000 chars return full markdown; larger pages are LLM-summarized. | PARALLEL_API_KEY or FIRECRAWL_API_KEY or TAVILY_API_KEY |
+
 ## `tts` toolset
 
 | Tool | Description | Requires environment |

website/docs/reference/toolsets-reference.md

@@ -10,26 +10,29 @@ Toolsets are named bundles of tools that you can enable with `hermes chat --tool
 
 | Toolset | Kind | Resolves to |
 |---------|------|-------------|
-| `browser` | core | `browser_back`, `browser_click`, `browser_close`, `browser_get_images`, `browser_navigate`, `browser_press`, `browser_scroll`, `browser_snapshot`, `browser_type`, `browser_vision`, `web_search` |
+| `browser` | core | `browser_back`, `browser_click`, `browser_close`, `browser_console`, `browser_get_images`, `browser_navigate`, `browser_press`, `browser_scroll`, `browser_snapshot`, `browser_type`, `browser_vision`, `web_search` |
 | `clarify` | core | `clarify` |
 | `code_execution` | core | `execute_code` |
 | `cronjob` | core | `cronjob` |
 | `debugging` | composite | `patch`, `process`, `read_file`, `search_files`, `terminal`, `web_extract`, `web_search`, `write_file` |
 | `delegation` | core | `delegate_task` |
 | `file` | core | `patch`, `read_file`, `search_files`, `write_file` |
-| `hermes-cli` | platform | `browser_back`, `browser_click`, `browser_close`, `browser_get_images`, `browser_navigate`, `browser_press`, `browser_scroll`, `browser_snapshot`, `browser_type`, `browser_vision`, `clarify`, `delegate_task`, `execute_code`, `ha_call_service`, `ha_get_state`, `ha_list_entities`, `ha_list_services`, `honcho_conclude`, `honcho_context`, `honcho_profile`, `honcho_search`, `image_generate`, `cronjob`, `memory`, `mixture_of_agents`, `patch`, `process`, `read_file`, `search_files`, `send_message`, `session_search`, `skill_manage`, `skill_view`, `skills_list`, `terminal`, `text_to_speech`, `todo`, `vision_analyze`, `web_extract`, `web_search`, `write_file` |
-| `hermes-discord` | platform | `browser_back`, `browser_click`, `browser_close`, `browser_get_images`, `browser_navigate`, `browser_press`, `browser_scroll`, `browser_snapshot`, `browser_type`, `browser_vision`, `clarify`, `delegate_task`, `execute_code`, `ha_call_service`, `ha_get_state`, `ha_list_entities`, `ha_list_services`, `honcho_conclude`, `honcho_context`, `honcho_profile`, `honcho_search`, `image_generate`, `cronjob`, `memory`, `mixture_of_agents`, `patch`, `process`, `read_file`, `search_files`, `send_message`, `session_search`, `skill_manage`, `skill_view`, `skills_list`, `terminal`, `text_to_speech`, `todo`, `vision_analyze`, `web_extract`, `web_search`, `write_file` |
-| `hermes-email` | platform | `browser_back`, `browser_click`, `browser_close`, `browser_get_images`, `browser_navigate`, `browser_press`, `browser_scroll`, `browser_snapshot`, `browser_type`, `browser_vision`, `clarify`, `delegate_task`, `execute_code`, `ha_call_service`, `ha_get_state`, `ha_list_entities`, `ha_list_services`, `honcho_conclude`, `honcho_context`, `honcho_profile`, `honcho_search`, `image_generate`, `cronjob`, `memory`, `mixture_of_agents`, `patch`, `process`, `read_file`, `search_files`, `send_message`, `session_search`, `skill_manage`, `skill_view`, `skills_list`, `terminal`, `text_to_speech`, `todo`, `vision_analyze`, `web_extract`, `web_search`, `write_file` |
-| `hermes-gateway` | platform | `browser_back`, `browser_click`, `browser_close`, `browser_get_images`, `browser_navigate`, `browser_press`, `browser_scroll`, `browser_snapshot`, `browser_type`, `browser_vision`, `clarify`, `delegate_task`, `execute_code`, `ha_call_service`, `ha_get_state`, `ha_list_entities`, `ha_list_services`, `honcho_conclude`, `honcho_context`, `honcho_profile`, `honcho_search`, `image_generate`, `cronjob`, `memory`, `mixture_of_agents`, `patch`, `process`, `read_file`, `search_files`, `send_message`, `session_search`, `skill_manage`, `skill_view`, `skills_list`, `terminal`, `text_to_speech`, `todo`, `vision_analyze`, `web_extract`, `web_search`, `write_file` |
-| `hermes-homeassistant` | platform | `browser_back`, `browser_click`, `browser_close`, `browser_get_images`, `browser_navigate`, `browser_press`, `browser_scroll`, `browser_snapshot`, `browser_type`, `browser_vision`, `clarify`, `delegate_task`, `execute_code`, `ha_call_service`, `ha_get_state`, `ha_list_entities`, `ha_list_services`, `honcho_conclude`, `honcho_context`, `honcho_profile`, `honcho_search`, `image_generate`, `cronjob`, `memory`, `mixture_of_agents`, `patch`, `process`, `read_file`, `search_files`, `send_message`, `session_search`, `skill_manage`, `skill_view`, `skills_list`, `terminal`, `text_to_speech`, `todo`, `vision_analyze`, `web_extract`, `web_search`, `write_file` |
-| `hermes-signal` | platform | `browser_back`, `browser_click`, `browser_close`, `browser_get_images`, `browser_navigate`, `browser_press`, `browser_scroll`, `browser_snapshot`, `browser_type`, `browser_vision`, `clarify`, `delegate_task`, `execute_code`, `ha_call_service`, `ha_get_state`, `ha_list_entities`, `ha_list_services`, `honcho_conclude`, `honcho_context`, `honcho_profile`, `honcho_search`, `image_generate`, `cronjob`, `memory`, `mixture_of_agents`, `patch`, `process`, `read_file`, `search_files`, `send_message`, `session_search`, `skill_manage`, `skill_view`, `skills_list`, `terminal`, `text_to_speech`, `todo`, `vision_analyze`, `web_extract`, `web_search`, `write_file` |
-| `hermes-slack` | platform | `browser_back`, `browser_click`, `browser_close`, `browser_get_images`, `browser_navigate`, `browser_press`, `browser_scroll`, `browser_snapshot`, `browser_type`, `browser_vision`, `clarify`, `delegate_task`, `execute_code`, `ha_call_service`, `ha_get_state`, `ha_list_entities`, `ha_list_services`, `honcho_conclude`, `honcho_context`, `honcho_profile`, `honcho_search`, `image_generate`, `cronjob`, `memory`, `mixture_of_agents`, `patch`, `process`, `read_file`, `search_files`, `send_message`, `session_search`, `skill_manage`, `skill_view`, `skills_list`, `terminal`, `text_to_speech`, `todo`, `vision_analyze`, `web_extract`, `web_search`, `write_file` |
-| `hermes-telegram` | platform | `browser_back`, `browser_click`, `browser_close`, `browser_get_images`, `browser_navigate`, `browser_press`, `browser_scroll`, `browser_snapshot`, `browser_type`, `browser_vision`, `clarify`, `delegate_task`, `execute_code`, `ha_call_service`, `ha_get_state`, `ha_list_entities`, `ha_list_services`, `honcho_conclude`, `honcho_context`, `honcho_profile`, `honcho_search`, `image_generate`, `cronjob`, `memory`, `mixture_of_agents`, `patch`, `process`, `read_file`, `search_files`, `send_message`, `session_search`, `skill_manage`, `skill_view`, `skills_list`, `terminal`, `text_to_speech`, `todo`, `vision_analyze`, `web_extract`, `web_search`, `write_file` |
-| `hermes-whatsapp` | platform | `browser_back`, `browser_click`, `browser_close`, `browser_get_images`, `browser_navigate`, `browser_press`, `browser_scroll`, `browser_snapshot`, `browser_type`, `browser_vision`, `clarify`, `delegate_task`, `execute_code`, `ha_call_service`, `ha_get_state`, `ha_list_entities`, `ha_list_services`, `honcho_conclude`, `honcho_context`, `honcho_profile`, `honcho_search`, `image_generate`, `cronjob`, `memory`, `mixture_of_agents`, `patch`, `process`, `read_file`, `search_files`, `send_message`, `session_search`, `skill_manage`, `skill_view`, `skills_list`, `terminal`, `text_to_speech`, `todo`, `vision_analyze`, `web_extract`, `web_search`, `write_file` |
+| `hermes-acp` | platform | `browser_back`, `browser_click`, `browser_close`, `browser_console`, `browser_get_images`, `browser_navigate`, `browser_press`, `browser_scroll`, `browser_snapshot`, `browser_type`, `browser_vision`, `delegate_task`, `execute_code`, `memory`, `patch`, `process`, `read_file`, `search_files`, `session_search`, `skill_manage`, `skill_view`, `skills_list`, `terminal`, `todo`, `vision_analyze`, `web_extract`, `web_search`, `write_file` |
+| `hermes-cli` | platform | `browser_back`, `browser_click`, `browser_close`, `browser_console`, `browser_get_images`, `browser_navigate`, `browser_press`, `browser_scroll`, `browser_snapshot`, `browser_type`, `browser_vision`, `clarify`, `cronjob`, `delegate_task`, `execute_code`, `ha_call_service`, `ha_get_state`, `ha_list_entities`, `ha_list_services`, `honcho_conclude`, `honcho_context`, `honcho_profile`, `honcho_search`, `image_generate`, `memory`, `mixture_of_agents`, `patch`, `process`, `read_file`, `search_files`, `send_message`, `session_search`, `skill_manage`, `skill_view`, `skills_list`, `terminal`, `text_to_speech`, `todo`, `vision_analyze`, `web_extract`, `web_search`, `write_file` |
+| `hermes-discord` | platform | _(same as hermes-cli)_ |
+| `hermes-email` | platform | _(same as hermes-cli)_ |
+| `hermes-gateway` | composite | Union of all messaging platform toolsets |
+| `hermes-homeassistant` | platform | _(same as hermes-cli)_ |
+| `hermes-signal` | platform | _(same as hermes-cli)_ |
+| `hermes-slack` | platform | _(same as hermes-cli)_ |
+| `hermes-sms` | platform | _(same as hermes-cli)_ |
+| `hermes-telegram` | platform | _(same as hermes-cli)_ |
+| `hermes-whatsapp` | platform | _(same as hermes-cli)_ |
 | `homeassistant` | core | `ha_call_service`, `ha_get_state`, `ha_list_entities`, `ha_list_services` |
 | `honcho` | core | `honcho_conclude`, `honcho_context`, `honcho_profile`, `honcho_search` |
 | `image_gen` | core | `image_generate` |
 | `memory` | core | `memory` |
+| `messaging` | core | `send_message` |
 | `moa` | core | `mixture_of_agents` |
 | `rl` | core | `rl_check_status`, `rl_edit_config`, `rl_get_current_config`, `rl_get_results`, `rl_list_environments`, `rl_list_runs`, `rl_select_environment`, `rl_start_training`, `rl_stop_training`, `rl_test_inference` |
 | `safe` | composite | `image_generate`, `mixture_of_agents`, `vision_analyze`, `web_extract`, `web_search` |

website/docs/user-guide/configuration.md

@@ -74,7 +74,8 @@ You need at least one way to connect to an LLM. Use `hermes model` to switch pro
 | **MiniMax China** | `MINIMAX_CN_API_KEY` in `~/.hermes/.env` (provider: `minimax-cn`) |
 | **Alibaba Cloud** | `DASHSCOPE_API_KEY` in `~/.hermes/.env` (provider: `alibaba`, aliases: `dashscope`, `qwen`) |
 | **Kilo Code** | `KILOCODE_API_KEY` in `~/.hermes/.env` (provider: `kilocode`) |
-| **Alibaba Cloud** | `DASHSCOPE_API_KEY` in `~/.hermes/.env` (provider: `alibaba`) |
+| **OpenCode Zen** | `OPENCODE_ZEN_API_KEY` in `~/.hermes/.env` (provider: `opencode-zen`) |
+| **OpenCode Go** | `OPENCODE_GO_API_KEY` in `~/.hermes/.env` (provider: `opencode-go`) |
 | **Custom Endpoint** | `hermes model` (saved in `config.yaml`) or `OPENAI_BASE_URL` + `OPENAI_API_KEY` in `~/.hermes/.env` |
 
 :::info Codex Note
@@ -413,6 +414,29 @@ LLM_MODEL=meta-llama/Llama-3.1-70B-Instruct-Turbo
 
 ---
 
+### Context Length Detection
+
+Hermes automatically detects your model's context length by querying the endpoint's `/v1/models` response. For most setups this works out of the box. If detection fails (the model name doesn't match, the endpoint doesn't expose `/v1/models`, etc.), Hermes falls back to a high default and probes downward on context-length errors.
+
+To set the context length explicitly, add `context_length` to your model config:
+
+```yaml
+model:
+  default: "qwen3.5:9b"
+  base_url: "http://localhost:8080/v1"
+  context_length: 131072  # tokens
+```
+
+This takes highest priority — it overrides auto-detection, cached values, and hardcoded defaults.
+
+:::tip When to set this manually
+- Your model shows "2M context" in the status bar (detection failed)
+- You want to limit context below the model's maximum (e.g., 8k on a 128k model to save VRAM)
+- You're running behind a proxy that doesn't expose `/v1/models`
+:::
+
+---
+
 ### Choosing the Right Setup
 
 | Use Case | Recommended |