feat(agent): configurable timeouts for auxiliary LLM calls via config.yaml (#3597)

Add per-task timeout settings under auxiliary.{task}.timeout in config.yaml
instead of hardcoded values. Users with slow local models (Ollama, llama.cpp)
can now increase timeouts for compression, vision, session search, etc.

Defaults:
  - auxiliary.compression.timeout: 120s (was hardcoded 45s)
  - auxiliary.vision.timeout: 30s (unchanged)
  - all other aux tasks: 30s (was hardcoded 30s)
  - title_generator: 30s (was hardcoded 15s)

call_llm/async_call_llm now auto-resolve timeout from config when not
explicitly passed. Callers can still override with an explicit timeout arg.

Based on PR #3406 by alanfwilliams. Converted from env vars to config.yaml
per project conventions.

Co-authored-by: alanfwilliams <alanfwilliams@users.noreply.github.com>

agent/auxiliary_client.py

@@ -1458,6 +1458,29 @@ def _resolve_task_provider_model(
     return "auto", resolved_model, None, None
 
 
+_DEFAULT_AUX_TIMEOUT = 30.0
+
+
+def _get_task_timeout(task: str, default: float = _DEFAULT_AUX_TIMEOUT) -> float:
+    """Read timeout from auxiliary.{task}.timeout in config, falling back to *default*."""
+    if not task:
+        return default
+    try:
+        from hermes_cli.config import load_config
+        config = load_config()
+    except ImportError:
+        return default
+    aux = config.get("auxiliary", {}) if isinstance(config, dict) else {}
+    task_config = aux.get(task, {}) if isinstance(aux, dict) else {}
+    raw = task_config.get("timeout")
+    if raw is not None:
+        try:
+            return float(raw)
+        except (ValueError, TypeError):
+            pass
+    return default
+
+
 def _build_call_kwargs(
     provider: str,
     model: str,
@@ -1515,7 +1538,7 @@ def call_llm(
     temperature: float = None,
     max_tokens: int = None,
     tools: list = None,
-    timeout: float = 30.0,
+    timeout: float = None,
     extra_body: dict = None,
 ) -> Any:
     """Centralized synchronous LLM call.
@@ -1533,7 +1556,7 @@ def call_llm(
         temperature: Sampling temperature (None = provider default).
         max_tokens: Max output tokens (handles max_tokens vs max_completion_tokens).
         tools: Tool definitions (for function calling).
-        timeout: Request timeout in seconds.
+        timeout: Request timeout in seconds (None = read from auxiliary.{task}.timeout config).
         extra_body: Additional request body fields.
 
     Returns:
@@ -1598,10 +1621,12 @@ def call_llm(
                 f"No LLM provider configured for task={task} provider={resolved_provider}. "
                 f"Run: hermes setup")
 
+    effective_timeout = timeout if timeout is not None else _get_task_timeout(task)
+
     kwargs = _build_call_kwargs(
         resolved_provider, final_model, messages,
         temperature=temperature, max_tokens=max_tokens,
-        tools=tools, timeout=timeout, extra_body=extra_body,
+        tools=tools, timeout=effective_timeout, extra_body=extra_body,
         base_url=resolved_base_url)
 
     # Handle max_tokens vs max_completion_tokens retry
@@ -1683,7 +1708,7 @@ async def async_call_llm(
     temperature: float = None,
     max_tokens: int = None,
     tools: list = None,
-    timeout: float = 30.0,
+    timeout: float = None,
     extra_body: dict = None,
 ) -> Any:
     """Centralized asynchronous LLM call.
@@ -1744,10 +1769,12 @@ async def async_call_llm(
                 f"No LLM provider configured for task={task} provider={resolved_provider}. "
                 f"Run: hermes setup")
 
+    effective_timeout = timeout if timeout is not None else _get_task_timeout(task)
+
     kwargs = _build_call_kwargs(
         resolved_provider, final_model, messages,
         temperature=temperature, max_tokens=max_tokens,
-        tools=tools, timeout=timeout, extra_body=extra_body,
+        tools=tools, timeout=effective_timeout, extra_body=extra_body,
         base_url=resolved_base_url)
 
     try:

agent/context_compressor.py

@@ -347,7 +347,7 @@ Write only the summary body. Do not include any preamble or prefix."""
                 "messages": [{"role": "user", "content": prompt}],
                 "temperature": 0.3,
                 "max_tokens": summary_budget * 2,
-                "timeout": 45.0,
+                # timeout resolved from auxiliary.compression.timeout config by call_llm
             }
             if self.summary_model:
                 call_kwargs["model"] = self.summary_model

agent/title_generator.py

@@ -19,7 +19,7 @@ _TITLE_PROMPT = (
 )
 
 
-def generate_title(user_message: str, assistant_response: str, timeout: float = 15.0) -> Optional[str]:
+def generate_title(user_message: str, assistant_response: str, timeout: float = 30.0) -> Optional[str]:
     """Generate a session title from the first exchange.
 
     Uses the auxiliary LLM client (cheapest/fastest available model).