wrap LiteLLMModel model to add rate limit logic

app.py

@@ -23,11 +23,19 @@ DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
 rate_limiter = RateLimiter()
 
+class LiteLLMModelWithRateLimit(LiteLLMModel):
+    """API呼び出し前にレート制限をチェックするLiteLLMModelのラッパー"""
+    def run(self, **kwargs) -> dict:
+        # APIを呼び出す直前に待機処理を挟む
+        limiter.wait_if_needed()
+        # 元のrunメソッドを呼び出してAPIアクセスを実行
+        return super().run(**kwargs)
+
 # --- Basic Agent Definition ---
 # ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
 class BasicAgent:
     def __init__(self):
-        model = LiteLLMModel(
+        model = LiteLLMModelWithRateLimit(
             model_id="gemini/gemini-2.5-flash", 
             api_key=os.getenv("GOOGLE_API_KEY")
         )
@@ -43,7 +51,6 @@ class BasicAgent:
         )
         print("BasicAgent initialized.")
     def __call__(self, question: str) -> str:
-        rate_limiter.sleep_if_needed()
         print(f"Agent received question (first 50 chars): {question[:50]}...")
         answer = self.agent.run(question)
         print(f"Agent returning answer: {answer}")