Use user chat models for train of thought when no server chat settings

Update chat actors to use user's chat model for train of thought. This
requires passing the user info as argument to all the chat actors.

Whether the user is subscribed or not can be inferred from the user
info being passed, so it doesn't need to be passed as a separate
argument to chat actor functions

Let send_message_to_model function infer chat model instead of passing
it as an argument from some chat actors. Better if this logic can be
done in a single place.

src/khoj/processor/image/generate.py

@@ -25,7 +25,6 @@ async def text_to_image(
     location_data: LocationData,
     references: List[Dict[str, Any]],
     online_results: Dict[str, Any],
-    subscribed: bool = False,
     send_status_func: Optional[Callable] = None,
     uploaded_image_url: Optional[str] = None,
     agent: Agent = None,
@@ -66,8 +65,8 @@ async def text_to_image(
         note_references=references,
         online_results=online_results,
         model_type=text_to_image_config.model_type,
-        subscribed=subscribed,
         uploaded_image_url=uploaded_image_url,
+        user=user,
         agent=agent,
     )