feat(providers): add per-provider and per-model request_timeout_seconds config

Adds optional providers.<id>.request_timeout_seconds and
providers.<id>.models.<model>.timeout_seconds config, resolved via a new
hermes_cli/timeouts.py helper and applied where client_kwargs is built
in run_agent.py. Zero default behavior change: when both keys are unset,
the openai SDK default takes over.

Mirrors the existing _get_task_timeout pattern in agent/auxiliary_client.py
for auxiliary tasks - the primary turn path just never got the equivalent
knob.

Cross-project demand: openclaw/openclaw#43946 (17 reactions) asks for
exactly this config - specifically calls out Ollama cold-start hanging
the client.

hermes_cli/timeouts.py

@@ -0,0 +1,42 @@
+from __future__ import annotations
+
+
+def _coerce_timeout(raw: object) -> float | None:
+    try:
+        timeout = float(raw)
+    except (TypeError, ValueError):
+        return None
+    if timeout <= 0:
+        return None
+    return timeout
+
+
+def get_provider_request_timeout(
+    provider_id: str, model: str | None = None
+) -> float | None:
+    """Return a configured provider request timeout in seconds, if any."""
+    if not provider_id:
+        return None
+
+    try:
+        from hermes_cli.config import load_config
+    except ImportError:
+        return None
+
+    config = load_config()
+    providers = config.get("providers", {}) if isinstance(config, dict) else {}
+    provider_config = (
+        providers.get(provider_id, {}) if isinstance(providers, dict) else {}
+    )
+    if not isinstance(provider_config, dict):
+        return None
+
+    if model:
+        models = provider_config.get("models", {})
+        model_config = models.get(model, {}) if isinstance(models, dict) else {}
+        if isinstance(model_config, dict):
+            timeout = _coerce_timeout(model_config.get("timeout_seconds"))
+            if timeout is not None:
+                return timeout
+
+    return _coerce_timeout(provider_config.get("request_timeout_seconds"))