feat(model and app):

1. Increase support for visual models and multimodal models;
2. The application and workflow can input various multimodal files such as images, documents, audio, and videos.

api/app/controllers/app_controller.py

@@ -835,7 +835,8 @@ async def draft_run_compare(
         web_search=True,
         memory=True,
         parallel=payload.parallel,
-        timeout=payload.timeout or 60
+        timeout=payload.timeout or 60,
+        files=payload.files
     )
 
     logger.info(