fix: resolve three travel agent UI issues

- Connection error: wrap sync get_llm_api_key() in sync_to_async in
  stream_chat_completion() to fix SynchronousOnlyOperation raised when
  the async SSE generator calls a synchronous Django ORM function
- Models not loading: add opencode_zen handler to models endpoint
  returning its default model; fix frontend to show 'Default' instead
  of 'Loading...' indefinitely when no model list is returned
- Location in header: remove destination subtitle from Travel Assistant
  header — collection-wide chat has no single meaningful location

backend/server/chat/llm_client.py

@@ -2,6 +2,7 @@ import json
 import logging
 
 import litellm
+from asgiref.sync import sync_to_async
 from django.conf import settings
 
 from integrations.models import UserAPIKey
@@ -371,7 +372,7 @@ async def stream_chat_completion(user, messages, provider, tools=None, model=Non
         yield f"data: {json.dumps(payload)}\n\n"
         return
 
-    api_key = get_llm_api_key(user, normalized_provider)
+    api_key = await sync_to_async(get_llm_api_key)(user, normalized_provider)
 
     if provider_config["needs_api_key"] and not api_key:
         payload = {

backend/server/chat/views/__init__.py

@@ -414,6 +414,9 @@ class ChatProviderCatalogViewSet(viewsets.ViewSet):
                     pass
                 return Response({"models": []})
 
+            if provider in ["opencode_zen"]:
+                return Response({"models": ["openai/gpt-5-nano"]})
+
             return Response({"models": []})
         except Exception as exc:
             logger.error("Failed to fetch models for %s: %s", provider, exc)