Fix GeneratorExit exception in cancel generation by adding proper exception handling

app.py

@@ -567,6 +567,11 @@ def chat_response(user_msg, chat_history, system_prompt,
 
         gen_thread.join()
         yield history, debug + prompt_debug
+    except GeneratorExit:
+        # Handle cancellation gracefully
+        print("Chat response cancelled.")
+        # Don't yield anything - let the cancellation propagate
+        return
     except Exception as e:
         history.append({'role': 'assistant', 'content': f"Error: {e}"})
         yield history, debug
@@ -659,6 +664,11 @@ with gr.Blocks(title="LLM Inference with ZeroGPU") as demo:
                     chat: response_chunk[0],
                     dbg: response_chunk[1],
                 }
+        except GeneratorExit:
+            # Handle Gradio's cancellation signal gracefully
+            print("Generation cancelled by user.")
+            # Don't yield anything here - let the finally block handle UI reset
+            return
         except Exception as e:
             print(f"An error occurred during generation: {e}")
             # If an error happens, add it to the chat history to inform the user.