update codes

app.py

@@ -10,24 +10,45 @@ from smolagents import CodeAgent, LiteLLMModel, DuckDuckGoSearchTool, VisitWebpa
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
+# --- RPM Guard: 프리 티어 버스트 방어형 커스텀 모델 어댑터 ---
+class PacedGeminiModel(LiteLLMModel):
+    def __init__(self, *args, **kwargs):
+        super().__init__(*args, **kwargs)
+        self.last_call_time = 0.0
+        self.min_interval = 10  # 15 RPM 제한을 안전하게 회피하기 위한 최소 초 단위 간격 고정
+
+    def __call__(self, *args, **kwargs):
+        # 마지막 API 호출 시점으로부터 경과한 시간을 계산하여 정밀 페이싱 락(Lock) 가동
+        now = time.time()
+        elapsed = now - self.last_call_time
+        if elapsed < self.min_interval:
+            sleep_needed = self.min_interval - elapsed
+            time.sleep(sleep_needed)
+            
+        try:
+            response = super().__call__(*args, **kwargs)
+            return response
+        finally:
+            # 실패하든 성공하든 타임스탬프를 갱신하여 연속 리트라이로 인한 버스트 폭증 차단
+            self.last_call_time = time.time()
+
 # --- Basic Agent Definition ---
 # ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
 class BasicAgent:
     def __init__(self):
         gemini_key = os.getenv("GEMINI_API_KEY") or os.getenv("GOOGLE_API_KEY")
         
-        # 일일 쿼터가 1,500회로 가장 넉넉한 2.0-flash 배정
-        # requests_per_minute 인자를 통해 프레임워크가 알아서 안전 가드레일을 잡도록 설정
-        self.model = LiteLLMModel(
-            model_id="gemini/gemini-2.0-flash",
+        # 기본 LiteLLMModel 대신 정밀 감속기가 내장된 PacedGeminiModel로 바인딩
+        self.model = PacedGeminiModel(
+            model_id="gemini/gemini-2.5-flash",
             api_key=gemini_key,
-            requests_per_minute=6  
+            requests_per_minute=6
         )
                 
         self.search_tool = DuckDuckGoSearchTool()
         self.visit_tool = VisitWebpageTool()
                 
-        # 45점 베이스라인의 다단계 계획 수립 및 내장 인터프리터 파라미터 완전 고정
+        # 계획 주기 가동 및 툴 가방 바인딩
         self.alfred = CodeAgent(
             tools=[self.search_tool, self.visit_tool], 
             model=self.model,
@@ -37,6 +58,8 @@ class BasicAgent:
 
     def __call__(self, question: str) -> str:
         try:
+            # 연속된 문제 풀이 사이에도 프리 티어 게이트웨이가 휴식할 수 있도록 5초 전처리 대기
+            time.sleep(5.0)
             result = self.alfred.run(question)
             if result is None:
                 return "unknown"
@@ -50,8 +73,8 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
     Fetches all questions, runs the BasicAgent on them, submits all answers,
     and displays the results.
     """
-    space_id = os.getenv("SPACE_ID") 
-
+    # --- Determine HF Space Runtime URL and Repo URL ---
+    space_id = os.getenv("SPACE_ID") # Get the SPACE_ID for sending link to the code
     if profile:
         username= f"{profile.username}"
         print(f"User logged in: {username}")
@@ -63,15 +86,17 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
     questions_url = f"{api_url}/questions"
     submit_url = f"{api_url}/submit"
 
+    # 1. Instantiate Agent ( modify this part to create your agent)
     try:
         agent = BasicAgent()
     except Exception as e:
         print(f"Error instantiating agent: {e}")
         return f"Error initializing agent: {e}", None
-        
+    # In the case of an app running as a hugging Face space, this link points toward your codebase ( usefull for others so please keep it public)
     agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
     print(agent_code)
 
+    # 2. Fetch Questions
     print(f"Fetching questions from: {questions_url}")
     try:
         response = requests.get(questions_url, timeout=15)
@@ -92,6 +117,7 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
         print(f"An unexpected error occurred fetching questions: {e}")
         return f"An unexpected error occurred fetching questions: {e}", None
 
+    # 3. Run your Agent
     results_log = []
     answers_payload = []
     print(f"Running agent on {len(questions_data)} questions...")
@@ -113,10 +139,12 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
         print("Agent did not produce any answers to submit.")
         return "Agent did not produce any answers to submit.", pd.DataFrame(results_log)
 
+    # 4. Prepare Submission 
     submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers_payload}
     status_update = f"Agent finished. Submitting {len(answers_payload)} answers for user '{username}'..."
     print(status_update)
 
+    # 5. Submit
     print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
     try:
         response = requests.post(submit_url, json=submission_data, timeout=60)