fix(auxiliary): custom provider URL rewrite + main_runtime model for title gen

- auxiliary_client: apply _to_openai_base_url() to custom base_url
  (fixes /anthropic → /v1 rewrite missing for provider="custom")
- auxiliary_client: use main_runtime.get("model") instead of _read_main_model()
  so auxiliary tasks follow system default model changes
- title_generator: thread main_runtime through generate_title → auto_title_session → maybe_auto_title
- cli.py / gateway/run.py: pass main_runtime to maybe_auto_title
- tests: update mock assertions for new main_runtime parameter

agent/auxiliary_client.py

@@ -1834,7 +1834,7 @@ def resolve_provider_client(
     # ── Custom endpoint (OPENAI_BASE_URL + OPENAI_API_KEY) ───────────
     if provider == "custom":
         if explicit_base_url:
-            custom_base = explicit_base_url.strip()
+            custom_base = _to_openai_base_url(explicit_base_url).strip()
             custom_key = (
                 (explicit_api_key or "").strip()
                 or os.getenv("OPENAI_API_KEY", "").strip()
@@ -1847,7 +1847,7 @@ def resolve_provider_client(
                 )
                 return None, None
             final_model = _normalize_resolved_model(
-                model or _read_main_model() or "gpt-4o-mini",
+                model or (main_runtime.get("model") if main_runtime else None) or "gpt-4o-mini",
                 provider,
             )
             extra = {}

agent/title_generator.py

@@ -30,10 +30,12 @@ def generate_title(
     assistant_response: str,
     timeout: float = 30.0,
     failure_callback: Optional[FailureCallback] = None,
+    main_runtime: dict = None,
 ) -> Optional[str]:
     """Generate a session title from the first exchange.
 
-    Uses the auxiliary LLM client (cheapest/fastest available model).
+    Uses the main runtime's model when available, falling back to the
+    auxiliary LLM client (cheapest/fastest available model).
     Returns the title string or None on failure.
 
     ``failure_callback`` is invoked with ``(task, exception)`` when the
@@ -57,6 +59,7 @@ def generate_title(
             max_tokens=500,
             temperature=0.3,
             timeout=timeout,
+            main_runtime=main_runtime,
         )
         title = (response.choices[0].message.content or "").strip()
         # Clean up: remove quotes, trailing punctuation, prefixes like "Title: "
@@ -86,6 +89,7 @@ def auto_title_session(
     user_message: str,
     assistant_response: str,
     failure_callback: Optional[FailureCallback] = None,
+    main_runtime: dict = None,
 ) -> None:
     """Generate and set a session title if one doesn't already exist.
 
@@ -107,7 +111,7 @@ def auto_title_session(
         return
 
     title = generate_title(
-        user_message, assistant_response, failure_callback=failure_callback
+        user_message, assistant_response, failure_callback=failure_callback, main_runtime=main_runtime
     )
     if not title:
         return
@@ -126,6 +130,7 @@ def maybe_auto_title(
     assistant_response: str,
     conversation_history: list,
     failure_callback: Optional[FailureCallback] = None,
+    main_runtime: dict = None,
 ) -> None:
     """Fire-and-forget title generation after the first exchange.
 
@@ -147,7 +152,7 @@ def maybe_auto_title(
     thread = threading.Thread(
         target=auto_title_session,
         args=(session_db, session_id, user_message, assistant_response),
-        kwargs={"failure_callback": failure_callback},
+        kwargs={"failure_callback": failure_callback, "main_runtime": main_runtime},
         daemon=True,
         name="auto-title",
     )

cli.py

@@ -8835,6 +8835,13 @@ class HermesCLI:
                         response,
                         self.conversation_history,
                         failure_callback=_title_failure_cb,
+                        main_runtime={
+                            "model": self.model,
+                            "provider": self.provider,
+                            "base_url": self.base_url,
+                            "api_key": self.api_key,
+                            "api_mode": self.api_mode,
+                        },
                     )
                 except Exception:
                     pass

gateway/run.py

@@ -10700,6 +10700,13 @@ class GatewayRunner:
                         final_response,
                         all_msgs,
                         failure_callback=_title_failure_cb,
+                        main_runtime={
+                            "model": getattr(agent, "model", None),
+                            "provider": getattr(agent, "provider", None),
+                            "base_url": getattr(agent, "base_url", None),
+                            "api_key": getattr(agent, "api_key", None),
+                            "api_mode": getattr(agent, "api_mode", None),
+                        } if agent else None,
                     )
                 except Exception:
                     pass

tests/agent/test_title_generator.py

@@ -182,7 +182,7 @@ class TestMaybeAutoTitle:
             import time
             time.sleep(0.3)
             mock_auto.assert_called_once_with(
-                db, "sess-1", "hello", "hi there", failure_callback=None
+                db, "sess-1", "hello", "hi there", failure_callback=None, main_runtime=None
             )
 
     def test_forwards_failure_callback_to_worker(self):
@@ -202,7 +202,7 @@ class TestMaybeAutoTitle:
             import time
             time.sleep(0.3)
             mock_auto.assert_called_once_with(
-                db, "sess-1", "hello", "hi there", failure_callback=_cb
+                db, "sess-1", "hello", "hi there", failure_callback=_cb, main_runtime=None
             )
 
     def test_skips_if_no_response(self):