feat: add Generator return type hint to streaming inference endpoint

app.py

@@ -12,6 +12,7 @@ from gradio import Server
 from gradio.data_classes import FileData
 from fastapi.responses import HTMLResponse
 import spaces
+from typing import Generator
 
 # ---------- Globals & Model Loading ----------
 MODEL_ID = "openbmb/MiniCPM-V-4.6"
@@ -79,7 +80,7 @@ def predict(
     top_p: float = 0.8,
     top_k: int = 100,
     max_frames: int = 64
-):
+) -> Generator[str, None, None]:
     """
     Streaming inference endpoint with history support.
     """