Improve response detection timing and add delay for Gemini

- Added 2-second delay before response detection to allow Gemini to finish generating
- Enhanced JavaScript fallback logic to better handle response waiting
- Improved timing for response detection to avoid returning setup acknowledgments
- Better synchronization between prompt sending and response detection

olproxy.py

@@ -1278,6 +1278,9 @@ async def detect_progressive_response(page, container_selector, prompt, modified
             except Exception as e:
                 logging.error(f"Failed to save HTML content: {e}")
 
+        # Add a small delay to allow Gemini to finish generating the response
+        await asyncio.sleep(2)
+
         return await page.evaluate(
             """([containerSelector, prompt, modifiedPrompt, requestId, chatbotName]) => {
                 const container = document.querySelector(containerSelector);
@@ -1402,6 +1405,10 @@ async def detect_progressive_response(page, container_selector, prompt, modified
                                     }
                                 }
                             }
+
+                            // If no response found yet, wait a bit longer and try again
+                            console.log(`No response found for request ID ${requestId}, waiting longer...`);
+                            // This will cause the function to return undefined, triggering a retry
                         }
                         
                         // Fallback to selector-based detection