Update app/core/model_loader.py

app/core/model_loader.py

@@ -146,7 +146,7 @@ class LLMSingleton:
         # Check daily quota before sending (Gemini 3 Flash Limit)
         if self.stats["daily_requests_count"] >= 500:
              logger.error("❌ Daily Quota Exceeded (500 requests). Request blocked.")
-             return ""
+             raise RuntimeError("QUOTA_EXCEEDED")
 
         # Track attempt
         self.requests_this_minute += 1
@@ -203,7 +203,7 @@ class LLMSingleton:
         self.stats["errors"] += 1
         self._save_stats()
         logger.error("❌ Max retries reached. Request failed.")
-        return ""
+        raise RuntimeError("RATE_LIMIT_EXCEEDED")
 
     def generate_text(self, prompt: str) -> str:
         """