fix: auto-reload MCP tools when mcp_servers config changes without restart

Fixes #1036

After adding an MCP server to config.yaml, users had to restart Hermes
before the new tools became visible — even though /reload-mcp existed.

Add _check_config_mcp_changes() called from process_loop every 5s:
- stat() config.yaml for mtime changes (fast path, no YAML parse)
- On mtime change, parse and compare mcp_servers section
- If mcp_servers changed, auto-trigger _reload_mcp() and notify user
- Skip check while agent is running to avoid interrupting tool calls
- Throttled to CONFIG_WATCH_INTERVAL=5s to avoid busy-polling

/reload-mcp still works for manual force-reload.

Tests: 6 new tests in TestMCPConfigWatch, all passed

cli.py

@@ -1414,7 +1414,7 @@ class HermesCLI:
                 max_iterations=self.max_turns,
                 enabled_toolsets=self.enabled_toolsets,
                 verbose_logging=self.verbose,
-                quiet_mode=not self.verbose,
+                quiet_mode=True,
                 ephemeral_system_prompt=self.system_prompt if self.system_prompt else None,
                 prefill_messages=self.prefill_messages or None,
                 reasoning_config=self.reasoning_config,
@@ -1428,7 +1428,7 @@ class HermesCLI:
                 platform="cli",
                 session_db=self._session_db,
                 clarify_callback=self._clarify_callback,
-                reasoning_callback=self._on_reasoning if (self.show_reasoning or self.verbose) else None,
+                reasoning_callback=self._on_reasoning if self.show_reasoning else None,
                 honcho_session_key=None,  # resolved by run_agent via config sessions map / title
                 fallback_model=self._fallback_model,
                 thinking_callback=self._on_thinking,
@@ -3285,17 +3285,12 @@ class HermesCLI:
         if self.agent:
             self.agent.verbose_logging = self.verbose
             self.agent.quiet_mode = not self.verbose
-            # Auto-enable reasoning display in verbose mode
-            if self.verbose:
-                self.agent.reasoning_callback = self._on_reasoning
-            elif not self.show_reasoning:
-                self.agent.reasoning_callback = None
 
         labels = {
             "off": "[dim]Tool progress: OFF[/] — silent mode, just the final response.",
             "new": "[yellow]Tool progress: NEW[/] — show each new tool (skip repeats).",
             "all": "[green]Tool progress: ALL[/] — show every tool call.",
-            "verbose": "[bold green]Tool progress: VERBOSE[/] — full args, results, think blocks, and debug logs.",
+            "verbose": "[bold green]Tool progress: VERBOSE[/] — full args, results, and debug logs.",
         }
         self.console.print(labels.get(self.tool_progress_mode, ""))
 
@@ -3362,17 +3357,13 @@ class HermesCLI:
 
     def _on_reasoning(self, reasoning_text: str):
         """Callback for intermediate reasoning display during tool-call loops."""
-        if self.verbose:
-            # Verbose mode: show full reasoning text
-            _cprint(f"  {_DIM}[thinking] {reasoning_text.strip()}{_RST}")
+        lines = reasoning_text.strip().splitlines()
+        if len(lines) > 5:
+            preview = "\n".join(lines[:5])
+            preview += f"\n  ... ({len(lines) - 5} more lines)"
         else:
-            lines = reasoning_text.strip().splitlines()
-            if len(lines) > 5:
-                preview = "\n".join(lines[:5])
-                preview += f"\n  ... ({len(lines) - 5} more lines)"
-            else:
-                preview = reasoning_text.strip()
-            _cprint(f"  {_DIM}[thinking] {preview}{_RST}")
+            preview = reasoning_text.strip()
+        _cprint(f"  {_DIM}[thinking] {preview}{_RST}")
 
     def _manual_compress(self):
         """Manually trigger context compression on the current conversation."""

gateway/platforms/telegram.py

@@ -322,14 +322,6 @@ class TelegramAdapter(BasePlatformAdapter):
             # Format and split message if needed
             formatted = self.format_message(content)
             chunks = self.truncate_message(formatted, self.MAX_MESSAGE_LENGTH)
-            if len(chunks) > 1:
-                # truncate_message appends a raw " (1/2)" suffix. Escape the
-                # MarkdownV2-special parentheses so Telegram doesn't reject the
-                # chunk and fall back to plain text.
-                chunks = [
-                    re.sub(r" \((\d+)/(\d+)\)$", r" \\(\1/\2\\)", chunk)
-                    for chunk in chunks
-                ]
             
             message_ids = []
             thread_id = metadata.get("thread_id") if metadata else None

gateway/run.py

@@ -1114,9 +1114,6 @@ class GatewayRunner:
         # let the adapter-level batching/queueing logic absorb them.
         _quick_key = build_session_key(source)
         if _quick_key in self._running_agents:
-            if event.get_command() == "status":
-                return await self._handle_status_command(event)
-
             if event.message_type == MessageType.PHOTO:
                 logger.debug("PRIORITY photo follow-up for session %s — queueing without interrupt", _quick_key[:20])
                 adapter = self.adapters.get(source.platform)
@@ -1825,8 +1822,6 @@ class GatewayRunner:
             # Update session with actual prompt token count and model from the agent
             self.session_store.update_session(
                 session_entry.session_key,
-                input_tokens=agent_result.get("input_tokens", 0),
-                output_tokens=agent_result.get("output_tokens", 0),
                 last_prompt_tokens=agent_result.get("last_prompt_tokens", 0),
                 model=agent_result.get("model"),
             )
@@ -4176,15 +4171,11 @@ class GatewayRunner:
             # Return final response, or a message if something went wrong
             final_response = result.get("final_response")
 
-            # Extract actual token counts from the agent instance used for this run
+            # Extract last actual prompt token count from the agent's compressor
             _last_prompt_toks = 0
-            _input_toks = 0
-            _output_toks = 0
             _agent = agent_holder[0]
             if _agent and hasattr(_agent, "context_compressor"):
                 _last_prompt_toks = getattr(_agent.context_compressor, "last_prompt_tokens", 0)
-                _input_toks = getattr(_agent, "session_prompt_tokens", 0)
-                _output_toks = getattr(_agent, "session_completion_tokens", 0)
             _resolved_model = getattr(_agent, "model", None) if _agent else None
 
             if not final_response:
@@ -4196,8 +4187,6 @@ class GatewayRunner:
                     "tools": tools_holder[0] or [],
                     "history_offset": len(agent_history),
                     "last_prompt_tokens": _last_prompt_toks,
-                    "input_tokens": _input_toks,
-                    "output_tokens": _output_toks,
                     "model": _resolved_model,
                 }
             
@@ -4261,8 +4250,6 @@ class GatewayRunner:
                 "tools": tools_holder[0] or [],
                 "history_offset": len(agent_history),
                 "last_prompt_tokens": _last_prompt_toks,
-                "input_tokens": _input_toks,
-                "output_tokens": _output_toks,
                 "model": _resolved_model,
                 "session_id": effective_session_id,
             }

hermes_cli/main.py

@@ -1112,32 +1112,8 @@ def _model_flow_custom(config):
 
     effective_key = api_key or current_key
 
-    from hermes_cli.models import probe_api_models
-
-    probe = probe_api_models(effective_key, effective_url)
-    if probe.get("used_fallback") and probe.get("resolved_base_url"):
-        print(
-            f"Warning: endpoint verification worked at {probe['resolved_base_url']}/models, "
-            f"not the exact URL you entered. Saving the working base URL instead."
-        )
-        effective_url = probe["resolved_base_url"]
-        if base_url:
-            base_url = effective_url
-    elif probe.get("models") is not None:
-        print(
-            f"Verified endpoint via {probe.get('probed_url')} "
-            f"({len(probe.get('models') or [])} model(s) visible)"
-        )
-    else:
-        print(
-            f"Warning: could not verify this endpoint via {probe.get('probed_url')}. "
-            f"Hermes will still save it."
-        )
-        if probe.get("suggested_base_url"):
-            print(f"  If this server expects /v1, try base URL: {probe['suggested_base_url']}")
-
     if base_url:
-        save_env_value("OPENAI_BASE_URL", effective_url)
+        save_env_value("OPENAI_BASE_URL", base_url)
     if api_key:
         save_env_value("OPENAI_API_KEY", api_key)
 

hermes_cli/models.py

@@ -308,62 +308,6 @@ def _fetch_anthropic_models(timeout: float = 5.0) -> Optional[list[str]]:
         return None
 
 
-def probe_api_models(
-    api_key: Optional[str],
-    base_url: Optional[str],
-    timeout: float = 5.0,
-) -> dict[str, Any]:
-    """Probe an OpenAI-compatible ``/models`` endpoint with light URL heuristics."""
-    normalized = (base_url or "").strip().rstrip("/")
-    if not normalized:
-        return {
-            "models": None,
-            "probed_url": None,
-            "resolved_base_url": "",
-            "suggested_base_url": None,
-            "used_fallback": False,
-        }
-
-    if normalized.endswith("/v1"):
-        alternate_base = normalized[:-3].rstrip("/")
-    else:
-        alternate_base = normalized + "/v1"
-
-    candidates: list[tuple[str, bool]] = [(normalized, False)]
-    if alternate_base and alternate_base != normalized:
-        candidates.append((alternate_base, True))
-
-    tried: list[str] = []
-    headers: dict[str, str] = {}
-    if api_key:
-        headers["Authorization"] = f"Bearer {api_key}"
-
-    for candidate_base, is_fallback in candidates:
-        url = candidate_base.rstrip("/") + "/models"
-        tried.append(url)
-        req = urllib.request.Request(url, headers=headers)
-        try:
-            with urllib.request.urlopen(req, timeout=timeout) as resp:
-                data = json.loads(resp.read().decode())
-                return {
-                    "models": [m.get("id", "") for m in data.get("data", [])],
-                    "probed_url": url,
-                    "resolved_base_url": candidate_base.rstrip("/"),
-                    "suggested_base_url": alternate_base if alternate_base != candidate_base else normalized,
-                    "used_fallback": is_fallback,
-                }
-        except Exception:
-            continue
-
-    return {
-        "models": None,
-        "probed_url": tried[-1] if tried else normalized.rstrip("/") + "/models",
-        "resolved_base_url": normalized,
-        "suggested_base_url": alternate_base if alternate_base != normalized else None,
-        "used_fallback": False,
-    }
-
-
 def fetch_api_models(
     api_key: Optional[str],
     base_url: Optional[str],
@@ -374,7 +318,22 @@ def fetch_api_models(
     Returns a list of model ID strings, or ``None`` if the endpoint could not
     be reached (network error, timeout, auth failure, etc.).
     """
-    return probe_api_models(api_key, base_url, timeout=timeout).get("models")
+    if not base_url:
+        return None
+
+    url = base_url.rstrip("/") + "/models"
+    headers: dict[str, str] = {}
+    if api_key:
+        headers["Authorization"] = f"Bearer {api_key}"
+
+    req = urllib.request.Request(url, headers=headers)
+    try:
+        with urllib.request.urlopen(req, timeout=timeout) as resp:
+            data = json.loads(resp.read().decode())
+            # Standard OpenAI format: {"data": [{"id": "model-name", ...}, ...]}
+            return [m.get("id", "") for m in data.get("data", [])]
+    except Exception:
+        return None
 
 
 def validate_requested_model(
@@ -417,53 +376,13 @@ def validate_requested_model(
             "message": "Model names cannot contain spaces.",
         }
 
+    # Custom endpoints can serve any model — skip validation
     if normalized == "custom":
-        probe = probe_api_models(api_key, base_url)
-        api_models = probe.get("models")
-        if api_models is not None:
-            if requested in set(api_models):
-                return {
-                    "accepted": True,
-                    "persist": True,
-                    "recognized": True,
-                    "message": None,
-                }
-
-            suggestions = get_close_matches(requested, api_models, n=3, cutoff=0.5)
-            suggestion_text = ""
-            if suggestions:
-                suggestion_text = "\n  Similar models: " + ", ".join(f"`{s}`" for s in suggestions)
-
-            message = (
-                f"Note: `{requested}` was not found in this custom endpoint's model listing "
-                f"({probe.get('probed_url')}). It may still work if the server supports hidden or aliased models."
-                f"{suggestion_text}"
-            )
-            if probe.get("used_fallback"):
-                message += (
-                    f"\n  Endpoint verification succeeded after trying `{probe.get('resolved_base_url')}`. "
-                    f"Consider saving that as your base URL."
-                )
-
-            return {
-                "accepted": True,
-                "persist": True,
-                "recognized": False,
-                "message": message,
-            }
-
-        message = (
-            f"Note: could not reach this custom endpoint's model listing at `{probe.get('probed_url')}`. "
-            f"Hermes will still save `{requested}`, but the endpoint should expose `/models` for verification."
-        )
-        if probe.get("suggested_base_url"):
-            message += f"\n  If this server expects `/v1`, try base URL: `{probe.get('suggested_base_url')}`"
-
         return {
             "accepted": True,
             "persist": True,
             "recognized": False,
-            "message": message,
+            "message": None,
         }
 
     # Probe the live API to check if the model actually exists

hermes_cli/setup.py

@@ -933,35 +933,11 @@ def setup_model_provider(config: dict):
 
         base_url = prompt(
             "  API base URL (e.g., https://api.example.com/v1)", current_url
-        ).strip()
+        )
         api_key = prompt("  API key", password=True)
         model_name = prompt("  Model name (e.g., gpt-4, claude-3-opus)", current_model)
 
         if base_url:
-            from hermes_cli.models import probe_api_models
-
-            probe = probe_api_models(api_key, base_url)
-            if probe.get("used_fallback") and probe.get("resolved_base_url"):
-                print_warning(
-                    f"Endpoint verification worked at {probe['resolved_base_url']}/models, "
-                    f"not the exact URL you entered. Saving the working base URL instead."
-                )
-                base_url = probe["resolved_base_url"]
-            elif probe.get("models") is not None:
-                print_success(
-                    f"Verified endpoint via {probe.get('probed_url')} "
-                    f"({len(probe.get('models') or [])} model(s) visible)"
-                )
-            else:
-                print_warning(
-                    f"Could not verify this endpoint via {probe.get('probed_url')}. "
-                    f"Hermes will still save it."
-                )
-                if probe.get("suggested_base_url"):
-                    print_info(
-                        f"  If this server expects /v1, try base URL: {probe['suggested_base_url']}"
-                    )
-
             save_env_value("OPENAI_BASE_URL", base_url)
         if api_key:
             save_env_value("OPENAI_API_KEY", api_key)

honcho_integration/session.py

@@ -927,11 +927,6 @@ class HonchoSessionManager:
             return False
 
         assistant_peer = self._get_or_create_peer(session.assistant_peer_id)
-        honcho_session = self._sessions_cache.get(session.honcho_session_id)
-        if not honcho_session:
-            logger.warning("No Honcho session cached for '%s', skipping AI seed", session_key)
-            return False
-
         try:
             wrapped = (
                 f"<ai_identity_seed>\n"
@@ -940,7 +935,7 @@ class HonchoSessionManager:
                 f"{content.strip()}\n"
                 f"</ai_identity_seed>"
             )
-            honcho_session.add_messages([assistant_peer.message(wrapped)])
+            assistant_peer.add_message("assistant", wrapped)
             logger.info("Seeded AI identity from '%s' into %s", source, session_key)
             return True
         except Exception as e:

run_agent.py

@@ -3301,7 +3301,8 @@ class AIAgent:
             extra_body["provider"] = provider_preferences
         _is_nous = "nousresearch" in self.base_url.lower()
 
-        if self._supports_reasoning_extra_body():
+        _is_mistral = "api.mistral.ai" in self.base_url.lower()
+        if (_is_openrouter or _is_nous) and not _is_mistral:
             if self.reasoning_config is not None:
                 rc = dict(self.reasoning_config)
                 # Nous Portal requires reasoning enabled — don't send
@@ -3325,32 +3326,6 @@ class AIAgent:
 
         return api_kwargs
 
-    def _supports_reasoning_extra_body(self) -> bool:
-        """Return True when reasoning extra_body is safe to send for this route/model.
-
-        OpenRouter forwards unknown extra_body fields to upstream providers.
-        Some providers/routes reject `reasoning` with 400s, so gate it to
-        known reasoning-capable model families and direct Nous Portal.
-        """
-        base_url = (self.base_url or "").lower()
-        if "nousresearch" in base_url:
-            return True
-        if "openrouter" not in base_url:
-            return False
-        if "api.mistral.ai" in base_url:
-            return False
-
-        model = (self.model or "").lower()
-        reasoning_model_prefixes = (
-            "deepseek/",
-            "anthropic/",
-            "openai/",
-            "x-ai/",
-            "google/gemini-2",
-            "qwen/qwen3",
-        )
-        return any(model.startswith(prefix) for prefix in reasoning_model_prefixes)
-
     def _build_assistant_message(self, assistant_message, finish_reason: str) -> dict:
         """Build a normalized assistant message dict from an API response message.
 
@@ -3370,7 +3345,8 @@ class AIAgent:
                 reasoning_text = combined or None
 
         if reasoning_text and self.verbose_logging:
-            logging.debug(f"Captured reasoning ({len(reasoning_text)} chars): {reasoning_text}")
+            preview = reasoning_text[:100] + "..." if len(reasoning_text) > 100 else reasoning_text
+            logging.debug(f"Captured reasoning ({len(reasoning_text)} chars): {preview}")
 
         if reasoning_text and self.reasoning_callback:
             try:
@@ -3847,12 +3823,8 @@ class AIAgent:
             print(f"  ⚡ Concurrent: {num_tools} tool calls — {tool_names_str}")
             for i, (tc, name, args) in enumerate(parsed_calls, 1):
                 args_str = json.dumps(args, ensure_ascii=False)
-                if self.verbose_logging:
-                    print(f"  📞 Tool {i}: {name}({list(args.keys())})")
-                    print(f"     Args: {args_str}")
-                else:
-                    args_preview = args_str[:self.log_prefix_chars] + "..." if len(args_str) > self.log_prefix_chars else args_str
-                    print(f"  📞 Tool {i}: {name}({list(args.keys())}) - {args_preview}")
+                args_preview = args_str[:self.log_prefix_chars] + "..." if len(args_str) > self.log_prefix_chars else args_str
+                print(f"  📞 Tool {i}: {name}({list(args.keys())}) - {args_preview}")
 
         for _, name, args in parsed_calls:
             if self.tool_progress_callback:
@@ -3917,20 +3889,17 @@ class AIAgent:
                     logger.warning("Tool %s returned error (%.2fs): %s", function_name, tool_duration, result_preview)
 
                 if self.verbose_logging:
+                    result_preview = function_result[:200] if len(function_result) > 200 else function_result
                     logging.debug(f"Tool {function_name} completed in {tool_duration:.2f}s")
-                    logging.debug(f"Tool result ({len(function_result)} chars): {function_result}")
+                    logging.debug(f"Tool result preview: {result_preview}...")
 
             # Print cute message per tool
             if self.quiet_mode:
                 cute_msg = _get_cute_tool_message_impl(name, args, tool_duration, result=function_result)
                 print(f"  {cute_msg}")
             elif not self.quiet_mode:
-                if self.verbose_logging:
-                    print(f"  ✅ Tool {i+1} completed in {tool_duration:.2f}s")
-                    print(f"     Result: {function_result}")
-                else:
-                    response_preview = function_result[:self.log_prefix_chars] + "..." if len(function_result) > self.log_prefix_chars else function_result
-                    print(f"  ✅ Tool {i+1} completed in {tool_duration:.2f}s - {response_preview}")
+                response_preview = function_result[:self.log_prefix_chars] + "..." if len(function_result) > self.log_prefix_chars else function_result
+                print(f"  ✅ Tool {i+1} completed in {tool_duration:.2f}s - {response_preview}")
 
             # Truncate oversized results
             MAX_TOOL_RESULT_CHARS = 100_000
@@ -4006,12 +3975,8 @@ class AIAgent:
 
             if not self.quiet_mode:
                 args_str = json.dumps(function_args, ensure_ascii=False)
-                if self.verbose_logging:
-                    print(f"  📞 Tool {i}: {function_name}({list(function_args.keys())})")
-                    print(f"     Args: {args_str}")
-                else:
-                    args_preview = args_str[:self.log_prefix_chars] + "..." if len(args_str) > self.log_prefix_chars else args_str
-                    print(f"  📞 Tool {i}: {function_name}({list(function_args.keys())}) - {args_preview}")
+                args_preview = args_str[:self.log_prefix_chars] + "..." if len(args_str) > self.log_prefix_chars else args_str
+                print(f"  📞 Tool {i}: {function_name}({list(function_args.keys())}) - {args_preview}")
 
             if self.tool_progress_callback:
                 try:
@@ -4167,9 +4132,7 @@ class AIAgent:
                     logger.error("handle_function_call raised for %s: %s", function_name, tool_error, exc_info=True)
                 tool_duration = time.time() - tool_start_time
 
-            result_preview = function_result if self.verbose_logging else (
-                function_result[:200] if len(function_result) > 200 else function_result
-            )
+            result_preview = function_result[:200] if len(function_result) > 200 else function_result
 
             # Log tool errors to the persistent error log so [error] tags
             # in the UI always have a corresponding detailed entry on disk.
@@ -4179,7 +4142,7 @@ class AIAgent:
 
             if self.verbose_logging:
                 logging.debug(f"Tool {function_name} completed in {tool_duration:.2f}s")
-                logging.debug(f"Tool result ({len(function_result)} chars): {function_result}")
+                logging.debug(f"Tool result preview: {result_preview}...")
 
             # Guard against tools returning absurdly large content that would
             # blow up the context window. 100K chars ≈ 25K tokens — generous
@@ -4202,12 +4165,8 @@ class AIAgent:
             messages.append(tool_msg)
 
             if not self.quiet_mode:
-                if self.verbose_logging:
-                    print(f"  ✅ Tool {i} completed in {tool_duration:.2f}s")
-                    print(f"     Result: {function_result}")
-                else:
-                    response_preview = function_result[:self.log_prefix_chars] + "..." if len(function_result) > self.log_prefix_chars else function_result
-                    print(f"  ✅ Tool {i} completed in {tool_duration:.2f}s - {response_preview}")
+                response_preview = function_result[:self.log_prefix_chars] + "..." if len(function_result) > self.log_prefix_chars else function_result
+                print(f"  ✅ Tool {i} completed in {tool_duration:.2f}s - {response_preview}")
 
             if self._interrupt_requested and i < len(assistant_message.tool_calls):
                 remaining = len(assistant_message.tool_calls) - i
@@ -4305,8 +4264,9 @@ class AIAgent:
                     api_messages.insert(sys_offset + idx, pfm.copy())
 
             summary_extra_body = {}
+            _is_openrouter = "openrouter" in self.base_url.lower()
             _is_nous = "nousresearch" in self.base_url.lower()
-            if self._supports_reasoning_extra_body():
+            if _is_openrouter or _is_nous:
                 if self.reasoning_config is not None:
                     summary_extra_body["reasoning"] = self.reasoning_config
                 else:
@@ -5458,10 +5418,7 @@ class AIAgent:
 
                 # Handle assistant response
                 if assistant_message.content and not self.quiet_mode:
-                    if self.verbose_logging:
-                        self._vprint(f"{self.log_prefix}🤖 Assistant: {assistant_message.content}")
-                    else:
-                        self._vprint(f"{self.log_prefix}🤖 Assistant: {assistant_message.content[:100]}{'...' if len(assistant_message.content) > 100 else ''}")
+                    self._vprint(f"{self.log_prefix}🤖 Assistant: {assistant_message.content[:100]}{'...' if len(assistant_message.content) > 100 else ''}")
 
                 # Notify progress callback of model's thinking (used by subagent
                 # delegation to relay the child's reasoning to the parent display).

tests/gateway/test_status_command.py

@@ -1,133 +0,0 @@
-"""Tests for gateway /status behavior and token persistence."""
-
-from datetime import datetime
-from types import SimpleNamespace
-from unittest.mock import AsyncMock, MagicMock
-
-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(session_entry: SessionEntry):
-    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.session_store.get_or_create_session.return_value = session_entry
-    runner.session_store.load_transcript.return_value = []
-    runner.session_store.has_any_sessions.return_value = True
-    runner.session_store.append_to_transcript = MagicMock()
-    runner.session_store.rewrite_transcript = MagicMock()
-    runner.session_store.update_session = 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
-    runner._should_send_voice_reply = lambda *_args, **_kwargs: False
-    runner._send_voice_reply = AsyncMock()
-    runner._capture_gateway_honcho_if_configured = lambda *args, **kwargs: None
-    runner._emit_gateway_run_progress = AsyncMock()
-    return runner
-
-
-@pytest.mark.asyncio
-async def test_status_command_reports_running_agent_without_interrupt(monkeypatch):
-    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)
-    running_agent = MagicMock()
-    runner._running_agents[build_session_key(_make_source())] = running_agent
-
-    result = await runner._handle_message(_make_event("/status"))
-
-    assert "**Tokens:** 321" in result
-    assert "**Agent Running:** Yes ⚡" in result
-    running_agent.interrupt.assert_not_called()
-    assert runner._pending_messages == {}
-
-
-@pytest.mark.asyncio
-async def test_handle_message_persists_agent_token_counts(monkeypatch):
-    import gateway.run as gateway_run
-
-    session_entry = SessionEntry(
-        session_key=build_session_key(_make_source()),
-        session_id="sess-1",
-        created_at=datetime.now(),
-        updated_at=datetime.now(),
-        platform=Platform.TELEGRAM,
-        chat_type="dm",
-    )
-    runner = _make_runner(session_entry)
-    runner.session_store.load_transcript.return_value = [{"role": "user", "content": "earlier"}]
-    runner._run_agent = AsyncMock(
-        return_value={
-            "final_response": "ok",
-            "messages": [],
-            "tools": [],
-            "history_offset": 0,
-            "last_prompt_tokens": 80,
-            "input_tokens": 120,
-            "output_tokens": 45,
-            "model": "openai/test-model",
-        }
-    )
-
-    monkeypatch.setattr(gateway_run, "_resolve_runtime_agent_kwargs", lambda: {"api_key": "***"})
-    monkeypatch.setattr(
-        "agent.model_metadata.get_model_context_length",
-        lambda *_args, **_kwargs: 100000,
-    )
-
-    result = await runner._handle_message(_make_event("hello"))
-
-    assert result == "ok"
-    runner.session_store.update_session.assert_called_once_with(
-        session_entry.session_key,
-        input_tokens=120,
-        output_tokens=45,
-        last_prompt_tokens=80,
-        model="openai/test-model",
-    )

tests/gateway/test_telegram_format.py

@@ -7,7 +7,7 @@ or corrupt user-visible content.
 
 import re
 import sys
-from unittest.mock import AsyncMock, MagicMock
+from unittest.mock import MagicMock
 
 import pytest
 
@@ -392,27 +392,3 @@ class TestStripMdv2:
 
     def test_empty_string(self):
         assert _strip_mdv2("") == ""
-
-
-@pytest.mark.asyncio
-async def test_send_escapes_chunk_indicator_for_markdownv2(adapter):
-    adapter.MAX_MESSAGE_LENGTH = 80
-    adapter._bot = MagicMock()
-
-    sent_texts = []
-
-    async def _fake_send_message(**kwargs):
-        sent_texts.append(kwargs["text"])
-        msg = MagicMock()
-        msg.message_id = len(sent_texts)
-        return msg
-
-    adapter._bot.send_message = AsyncMock(side_effect=_fake_send_message)
-
-    content = ("**bold** chunk content " * 12).strip()
-    result = await adapter.send("123", content)
-
-    assert result.success is True
-    assert len(sent_texts) > 1
-    assert re.search(r" \\\([0-9]+/[0-9]+\\\)$", sent_texts[0])
-    assert re.search(r" \\\([0-9]+/[0-9]+\\\)$", sent_texts[-1])

tests/hermes_cli/test_model_validation.py

@@ -7,7 +7,6 @@ from hermes_cli.models import (
     fetch_api_models,
     normalize_provider,
     parse_model_input,
-    probe_api_models,
     provider_label,
     provider_model_ids,
     validate_requested_model,
@@ -27,15 +26,7 @@ FAKE_API_MODELS = [
 
 def _validate(model, provider="openrouter", api_models=FAKE_API_MODELS, **kw):
     """Shortcut: call validate_requested_model with mocked API."""
-    probe_payload = {
-        "models": api_models,
-        "probed_url": "http://localhost:11434/v1/models",
-        "resolved_base_url": kw.get("base_url", "") or "http://localhost:11434/v1",
-        "suggested_base_url": None,
-        "used_fallback": False,
-    }
-    with patch("hermes_cli.models.fetch_api_models", return_value=api_models), \
-         patch("hermes_cli.models.probe_api_models", return_value=probe_payload):
+    with patch("hermes_cli.models.fetch_api_models", return_value=api_models):
         return validate_requested_model(model, provider, **kw)
 
 
@@ -156,33 +147,6 @@ class TestFetchApiModels:
         with patch("hermes_cli.models.urllib.request.urlopen", side_effect=Exception("timeout")):
             assert fetch_api_models("key", "https://example.com/v1") is None
 
-    def test_probe_api_models_tries_v1_fallback(self):
-        class _Resp:
-            def __enter__(self):
-                return self
-
-            def __exit__(self, exc_type, exc, tb):
-                return False
-
-            def read(self):
-                return b'{"data": [{"id": "local-model"}]}'
-
-        calls = []
-
-        def _fake_urlopen(req, timeout=5.0):
-            calls.append(req.full_url)
-            if req.full_url.endswith("/v1/models"):
-                return _Resp()
-            raise Exception("404")
-
-        with patch("hermes_cli.models.urllib.request.urlopen", side_effect=_fake_urlopen):
-            probe = probe_api_models("key", "http://localhost:8000")
-
-        assert calls == ["http://localhost:8000/models", "http://localhost:8000/v1/models"]
-        assert probe["models"] == ["local-model"]
-        assert probe["resolved_base_url"] == "http://localhost:8000/v1"
-        assert probe["used_fallback"] is True
-
 
 # -- validate — format checks -----------------------------------------------
 
@@ -227,7 +191,6 @@ class TestValidateApiFound:
         )
         assert result["accepted"] is True
         assert result["persist"] is True
-        assert result["recognized"] is True
 
 
 # -- validate — API not found ------------------------------------------------
@@ -269,26 +232,3 @@ class TestValidateApiFallback:
         result = _validate("some-model", provider="totally-unknown", api_models=None)
         assert result["accepted"] is True
         assert result["persist"] is True
-
-    def test_custom_endpoint_warns_with_probed_url_and_v1_hint(self):
-        with patch(
-            "hermes_cli.models.probe_api_models",
-            return_value={
-                "models": None,
-                "probed_url": "http://localhost:8000/v1/models",
-                "resolved_base_url": "http://localhost:8000",
-                "suggested_base_url": "http://localhost:8000/v1",
-                "used_fallback": False,
-            },
-        ):
-            result = validate_requested_model(
-                "qwen3",
-                "custom",
-                api_key="local-key",
-                base_url="http://localhost:8000",
-            )
-
-        assert result["accepted"] is True
-        assert result["persist"] is True
-        assert "http://localhost:8000/v1/models" in result["message"]
-        assert "http://localhost:8000/v1" in result["message"]

tests/hermes_cli/test_setup_model_provider.py

@@ -75,58 +75,6 @@ def test_setup_keep_current_custom_from_config_does_not_fall_through(tmp_path, m
     assert calls["count"] == 1
 
 
-def test_setup_custom_endpoint_saves_working_v1_base_url(tmp_path, monkeypatch):
-    monkeypatch.setenv("HERMES_HOME", str(tmp_path))
-    _clear_provider_env(monkeypatch)
-
-    config = load_config()
-
-    def fake_prompt_choice(question, choices, default=0):
-        if question == "Select your inference provider:":
-            return 3  # Custom endpoint
-        if question == "Configure vision:":
-            return len(choices) - 1  # Skip
-        raise AssertionError(f"Unexpected prompt_choice call: {question}")
-
-    def fake_prompt(message, current=None, **kwargs):
-        if "API base URL" in message:
-            return "http://localhost:8000"
-        if "API key" in message:
-            return "local-key"
-        if "Model name" in message:
-            return "llm"
-        return ""
-
-    monkeypatch.setattr("hermes_cli.setup.prompt_choice", fake_prompt_choice)
-    monkeypatch.setattr("hermes_cli.setup.prompt", fake_prompt)
-    monkeypatch.setattr("hermes_cli.setup.prompt_yes_no", lambda *args, **kwargs: False)
-    monkeypatch.setattr("hermes_cli.auth.get_active_provider", lambda: None)
-    monkeypatch.setattr("hermes_cli.auth.detect_external_credentials", lambda: [])
-    monkeypatch.setattr("agent.auxiliary_client.get_available_vision_backends", lambda: [])
-    monkeypatch.setattr(
-        "hermes_cli.models.probe_api_models",
-        lambda api_key, base_url: {
-            "models": ["llm"],
-            "probed_url": "http://localhost:8000/v1/models",
-            "resolved_base_url": "http://localhost:8000/v1",
-            "suggested_base_url": "http://localhost:8000/v1",
-            "used_fallback": True,
-        },
-    )
-
-    setup_model_provider(config)
-    save_config(config)
-
-    env = _read_env(tmp_path)
-    reloaded = load_config()
-
-    assert env.get("OPENAI_BASE_URL") == "http://localhost:8000/v1"
-    assert env.get("OPENAI_API_KEY") == "local-key"
-    assert reloaded["model"]["provider"] == "custom"
-    assert reloaded["model"]["base_url"] == "http://localhost:8000/v1"
-    assert reloaded["model"]["default"] == "llm"
-
-
 def test_setup_keep_current_config_provider_uses_provider_specific_model_menu(tmp_path, monkeypatch):
     """Keep-current should respect config-backed providers, not fall back to OpenRouter."""
     monkeypatch.setenv("HERMES_HOME", str(tmp_path))

tests/test_cli_provider_resolution.py

@@ -336,42 +336,4 @@ def test_cmd_model_falls_back_to_auto_on_invalid_provider(monkeypatch, capsys):
 
     assert "Warning:" in output
     assert "falling back to auto provider detection" in output.lower()
-    assert "No change." in output
-
-
-def test_model_flow_custom_saves_verified_v1_base_url(monkeypatch, capsys):
-    monkeypatch.setattr(
-        "hermes_cli.config.get_env_value",
-        lambda key: "" if key in {"OPENAI_BASE_URL", "OPENAI_API_KEY"} else "",
-    )
-    saved_env = {}
-    monkeypatch.setattr("hermes_cli.config.save_env_value", lambda key, value: saved_env.__setitem__(key, value))
-    monkeypatch.setattr("hermes_cli.auth._save_model_choice", lambda model: saved_env.__setitem__("MODEL", model))
-    monkeypatch.setattr("hermes_cli.auth.deactivate_provider", lambda: None)
-    monkeypatch.setattr("hermes_cli.main._save_custom_provider", lambda *args, **kwargs: None)
-    monkeypatch.setattr(
-        "hermes_cli.models.probe_api_models",
-        lambda api_key, base_url: {
-            "models": ["llm"],
-            "probed_url": "http://localhost:8000/v1/models",
-            "resolved_base_url": "http://localhost:8000/v1",
-            "suggested_base_url": "http://localhost:8000/v1",
-            "used_fallback": True,
-        },
-    )
-    monkeypatch.setattr(
-        "hermes_cli.config.load_config",
-        lambda: {"model": {"default": "", "provider": "custom", "base_url": ""}},
-    )
-    monkeypatch.setattr("hermes_cli.config.save_config", lambda cfg: None)
-
-    answers = iter(["http://localhost:8000", "local-key", "llm"])
-    monkeypatch.setattr("builtins.input", lambda _prompt="": next(answers))
-
-    hermes_main._model_flow_custom({})
-    output = capsys.readouterr().out
-
-    assert "Saving the working base URL instead" in output
-    assert saved_env["OPENAI_BASE_URL"] == "http://localhost:8000/v1"
-    assert saved_env["OPENAI_API_KEY"] == "local-key"
-    assert saved_env["MODEL"] == "llm"
+    assert "No change." in output

tests/test_run_agent.py

@@ -612,25 +612,6 @@ class TestBuildApiKwargs:
         kwargs = agent._build_api_kwargs(messages)
         assert kwargs["extra_body"]["reasoning"] == {"enabled": False}
 
-    def test_reasoning_not_sent_for_unsupported_openrouter_model(self, agent):
-        agent.model = "minimax/minimax-m2.5"
-        messages = [{"role": "user", "content": "hi"}]
-        kwargs = agent._build_api_kwargs(messages)
-        assert "reasoning" not in kwargs.get("extra_body", {})
-
-    def test_reasoning_sent_for_supported_openrouter_model(self, agent):
-        agent.model = "qwen/qwen3.5-plus-02-15"
-        messages = [{"role": "user", "content": "hi"}]
-        kwargs = agent._build_api_kwargs(messages)
-        assert kwargs["extra_body"]["reasoning"]["effort"] == "medium"
-
-    def test_reasoning_sent_for_nous_route(self, agent):
-        agent.base_url = "https://inference-api.nousresearch.com/v1"
-        agent.model = "minimax/minimax-m2.5"
-        messages = [{"role": "user", "content": "hi"}]
-        kwargs = agent._build_api_kwargs(messages)
-        assert kwargs["extra_body"]["reasoning"]["effort"] == "medium"
-
     def test_max_tokens_injected(self, agent):
         agent.max_tokens = 4096
         messages = [{"role": "user", "content": "hi"}]
@@ -961,19 +942,6 @@ class TestHandleMaxIterations:
         assert "error" in result.lower()
         assert "API down" in result
 
-    def test_summary_skips_reasoning_for_unsupported_openrouter_model(self, agent):
-        agent.model = "minimax/minimax-m2.5"
-        resp = _mock_response(content="Summary")
-        agent.client.chat.completions.create.return_value = resp
-        agent._cached_system_prompt = "You are helpful."
-        messages = [{"role": "user", "content": "do stuff"}]
-
-        result = agent._handle_max_iterations(messages, 60)
-
-        assert result == "Summary"
-        kwargs = agent.client.chat.completions.create.call_args.kwargs
-        assert "reasoning" not in kwargs.get("extra_body", {})
-
 
 class TestRunConversation:
     """Tests for the main run_conversation method.