fix(utility): use utility model for background tasks (auto-title, memory audit) instead of chat model (#4027)

routes/chat_helpers.py

@@ -159,9 +159,17 @@ async def auto_name_session(session_manager, sess):
             return
 
         owner = getattr(sess, "owner", None)
-        t_url, t_model, t_headers = resolve_task_endpoint(
+        t_url, t_model, t_headers = resolve_task_endpoint(owner=owner)
-            sess.endpoint_url, sess.model, sess.headers, owner=owner,
+        if not t_model:
-        )
+            # If no task/utility model is configured at all, fall back to
+            # the session's own model so auto-naming still works even on
+            # minimal setups.
+            from src.endpoint_resolver import resolve_endpoint
+            _fallback = resolve_endpoint("default", owner=owner)
+            if _fallback and _fallback[1]:
+                t_url, t_model, t_headers = _fallback
+            else:
+                t_url, t_model, t_headers = sess.endpoint_url, sess.model, sess.headers
         if not t_model:
             logger.debug("[auto-name] No model provided, skipping")
             return

routes/memory_routes.py

@@ -29,6 +29,7 @@ from src.llm_core import llm_call_async
 from services.memory.memory_extractor import audit_memories
 from src.auth_helpers import get_current_user, require_user
 from src.endpoint_resolver import resolve_endpoint
+from src.task_endpoint import resolve_task_endpoint
 from src.upload_limits import read_upload_limited, MEMORY_IMPORT_MAX_BYTES
 
 logger = logging.getLogger(__name__)
@@ -240,14 +241,18 @@ def setup_memory_routes(memory_manager: MemoryManager, session_manager: SessionM
         }
         messages = [system_msg] + sess.get_context_messages()
 
+        t_url, t_model, t_headers = resolve_task_endpoint(
+            sess.endpoint_url, sess.model, sess.headers, owner=_owner(request)
+        )
+
         try:
             suggestion_text = await llm_call_async(
-                sess.endpoint_url,
+                t_url,
-                sess.model,
+                t_model,
                 messages,
                 temperature=0.2,
                 max_tokens=500,
-                headers=sess.headers,
+                headers=t_headers,
             )
             try:
                 suggestions = json.loads(suggestion_text)
@@ -278,7 +283,15 @@ def setup_memory_routes(memory_manager: MemoryManager, session_manager: SessionM
         endpoint_url = model = None
         headers = {}
 
-        # Try default model from settings first
+        # Try utility model from settings first — memory audit is a background
+        # task and should prefer the lighter utility model over the main chat model.
+        from src.task_endpoint import resolve_task_endpoint
+        user = _owner(request)
+        t_url, t_model, t_headers = resolve_task_endpoint(owner=user)
+        if t_url and t_model:
+            endpoint_url, model, headers = t_url, t_model, t_headers
+        else:
+            # Fall back to default model if no task/utility model configured
             settings = _load_settings()
             ep_id = settings.get("default_endpoint_id", "")
             default_model = settings.get("default_model", "")
@@ -360,13 +373,13 @@ def setup_memory_routes(memory_manager: MemoryManager, session_manager: SessionM
             try:
                 sess = session_manager.get_session(session)
                 _assert_session_owner(sess, _owner(request))
-                endpoint_url = sess.endpoint_url
+                endpoint_url, model, headers = resolve_task_endpoint(
-                model = sess.model
+                    sess.endpoint_url, sess.model, sess.headers, owner=_owner(request)
-                headers = sess.headers
+                )
             except KeyError:
                  raise HTTPException(404, "Session not found — needed for LLM config")
         else:
-            endpoint_url, model, headers = resolve_endpoint("utility", owner=_owner(request))
+            endpoint_url, model, headers = resolve_task_endpoint(owner=_owner(request))
     
         if not endpoint_url or not model:
             raise HTTPException(400, "No LLM model configured. Set a default model in Settings.")

src/endpoint_resolver.py

@@ -265,23 +265,19 @@ def resolve_endpoint(
     ep_id = _stg(f"{setting_prefix}_endpoint_id")
     model = _stg(f"{setting_prefix}_model")
 
-    # If the specific endpoint is not configured, but the caller provided a
+    # Fall back to utility model for task/research/auto-naming if not specifically configured.
+    if not ep_id and setting_prefix not in ("utility", "default"):
+        ep_id = _stg("utility_endpoint_id")
+        model = _stg("utility_model")
+
+    # If the endpoint is STILL not configured, but the caller provided a
     # valid fallback (e.g. the active session model), use that immediately.
     # This prevents background tasks from jumping to the global default_model
     # when the user is mid-conversation with a different model.
     if not ep_id and fallback_url and fallback_model:
         return fallback_url, fallback_model, fallback_headers
 
-    # Unset Utility means "same as Default Chat Model".
+    # Unset Utility (or anything else that didn't have a fallback) means "same as Default Chat Model".
-    if setting_prefix == "utility" and not ep_id:
-        ep_id = _stg("default_endpoint_id")
-        model = _stg("default_model")
-
-    # Fall back to utility model for task/research/auto-naming if not specifically configured.
-    # If Utility itself is unset, the block above makes that resolve to Default Chat.
-    if not ep_id and setting_prefix != "utility":
-        ep_id = _stg("utility_endpoint_id")
-        model = _stg("utility_model")
     if not ep_id:
         ep_id = _stg("default_endpoint_id")
         model = _stg("default_model")