Fix endpoint model preservation for tasks

routes/model_routes.py

@@ -1402,12 +1402,18 @@ def setup_model_routes(model_discovery):
         return sess in variants or sess.startswith(base + "/")
 
     def _clear_sessions_for_endpoint(db, base_url: str) -> int:
+        """Drop stored auth for sessions using an endpoint being deleted.
+
+        Keep the session's endpoint URL and model intact. If the admin is
+        replacing an endpoint with the same URL, clearing those fields leaves
+        the UI looking selected while chat requests arrive with an empty model.
+        The chat-time orphan guard still clears truly dead endpoints when no
+        matching enabled endpoint exists.
+        """
         cleared = 0
         rows = db.query(DbSession).filter(DbSession.endpoint_url.isnot(None)).all()
         for row in rows:
             if _session_uses_endpoint_url(row.endpoint_url or "", base_url):
-                row.endpoint_url = ""
-                row.model = ""
                 row.headers = {}
                 row.updated_at = datetime.utcnow()
                 cleared += 1
@@ -1425,8 +1431,6 @@ def setup_model_routes(model_discovery):
         try:
             for sess in list(getattr(manager, "sessions", {}).values()):
                 if _session_uses_endpoint_url(getattr(sess, "endpoint_url", "") or "", base_url):
-                    sess.endpoint_url = ""
-                    sess.model = ""
                     sess.headers = {}
                     cleared += 1
         except Exception:

src/endpoint_resolver.py

@@ -35,6 +35,18 @@ def _first_chat_model(models) -> Optional[str]:
     return (models[0] if models else None)
 
 
+def _endpoint_cached_models(ep) -> list:
+    """Return cached model ids from the current or legacy endpoint field."""
+    raw = getattr(ep, "cached_models", None) or getattr(ep, "models", None)
+    if not raw:
+        return []
+    try:
+        models = json.loads(raw) if isinstance(raw, str) else raw
+    except Exception:
+        return []
+    return models if isinstance(models, list) else []
+
+
 # Cache for Tailscale hostname → IP resolution
 _tailscale_cache: Dict[str, Optional[str]] = {}
 
@@ -236,14 +248,9 @@ def resolve_endpoint(
         chat_url = build_chat_url(base)
         headers = build_headers(ep.api_key, base)
 
-        # If no model specified, try to pick the first from endpoint's cached list
-        if not model and hasattr(ep, 'models') and ep.models:
-            try:
-                models = json.loads(ep.models) if isinstance(ep.models, str) else ep.models
-                if models:
-                    model = _first_chat_model(models)
-            except Exception:
-                pass
+        # If no model specified, try to pick the first from endpoint's cached list.
+        if not model:
+            model = _first_chat_model(_endpoint_cached_models(ep)) or ""
 
         return chat_url, model or fallback_model, headers
     except Exception as e:
@@ -275,13 +282,8 @@ def resolve_endpoint_by_id(
         chat_url = build_chat_url(base)
         headers = build_headers(ep.api_key, base)
         m = (model or "").strip()
-        if not m and getattr(ep, "models", None):
-            try:
-                models = json.loads(ep.models) if isinstance(ep.models, str) else ep.models
-                if models:
-                    m = _first_chat_model(models) or ""
-            except Exception:
-                pass
+        if not m:
+            m = _first_chat_model(_endpoint_cached_models(ep)) or ""
         if not m:
             return None
         return chat_url, m, headers