Update app.py

app.py

@@ -2,202 +2,181 @@ import os
 import traceback
 import gradio as gr
 import requests
-import inspect
 import pandas as pd
 from smolagents import CodeAgent, DuckDuckGoSearchTool, PythonInterpreterTool, HfApiModel, LiteLLMModel, WikipediaSearchTool
 from huggingface_hub import login
 import time
 
-# (Keep Constants as is)
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
-#HF_TOKEN = os.getenv("HF_TOKEN")
-#login(HF_TOKEN)
 HF_TOKEN = os.getenv("HF_TOKEN")
-#login(HF_TOKEN)
+# login(HF_TOKEN) # Recommended via Space secrets
+
 model = LiteLLMModel(model_id="deepseek/deepseek-chat",
                      api_key=os.getenv("DEEPSEEK_API_KEY"),
                      base_url="https://api.deepseek.com")
 
 # --- Basic Agent Definition ---
-# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
 class BasicAgent:
     def __init__(self):
-        print("BasicAgent initialized.")
-        # Set up model
+        # print("BasicAgent initialized.") # Removed
         self.model = model
-
-        # Initialize custom tools
         self.tools = [
             PythonInterpreterTool(),
             DuckDuckGoSearchTool(),
             WikipediaSearchTool(),
         ]
-
-        # Create agent
         self.agent = CodeAgent(
             model=self.model,
             tools=self.tools,
             add_base_tools=True
         )
-        
-    def answer_question(self, question: str) -> str:
-        """Process a question and return the answer"""
-        print(f"Processing question: {question[:50]}..." if len(question) > 50 else question)
 
+    def answer_question(self, question: str) -> str:
+        # print(f"Processing question (first 50 chars): {question[:50]}...") # Removed
         try:
             result = self.agent.run(question)
-            # Ensure result is always a string
             if not isinstance(result, str):
                 result = str(result)
-             # 提取最终答案 - 如果结果包含"Final answer:"格式
             if "Final answer:" in result:
-                # 只提取最终答案部分
-                final_answer_part = result.split("Final answer:")[1].strip()
+                final_answer_part = result.split("Final answer:", 1)[1].strip()
                 return final_answer_part
             return result
-        except Exception as e:
-            print(traceback.format_exc())
-            error_msg = f"Error running agent: {str(e)}"
-            return f"I encountered an issue while processing your question: {str(e)}"
+        except Exception as e: # Capture exception object
+            print(f"Error in agent.run for question '{question[:50]}...':\n{traceback.format_exc()}")
+            return f"I encountered an issue processing your question: {str(e)}"
 
 
+# Global variables
+processed_questions_cache = {}
+submission_has_been_completed = False
 
-# 添加全局变量来存储已经处理过的问题和答案
-processed_questions = {}
-submission_completed = False
-def run_and_submit_all( profile: gr.OAuthProfile | None):
-    """
-    Fetches all questions, runs the BasicAgent on them, submits all answers,
-    and displays the results.
-    """
+def run_and_submit_all(profile: gr.OAuthProfile | None):
+    global processed_questions_cache, submission_has_been_completed
 
-    global processed_questions, submission_completed
-    
-    # 如果已经完成提交，直接返回之前的结果
-    if submission_completed and processed_questions:
-        results_log = []
-        for task_id, data in processed_questions.items():
-            results_log.append({"Task ID": task_id, "Question": data["question"], "Submitted Answer": data["answer"]})
-        return "已经完成提交，请刷新页面重新开始。", pd.DataFrame(results_log)
+    # print(f"--- run_and_submit_all triggered. Submission completed: {submission_has_been_completed} ---") # Removed
 
-    # --- 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 submission_has_been_completed and processed_questions_cache:
+        # print("--- Submission previously completed. Displaying cached results. ---") # Removed
+        results_log_display = []
+        for task_id, data in processed_questions_cache.items():
+            results_log_display.append({"Task ID": task_id, "Question": data["question"], "Submitted Answer": data["answer"]})
+        return "评估已完成并提交。如果需要重新运行，请刷新页面。", pd.DataFrame(results_log_display if results_log_display else [{}])
 
-    if profile:
-        username= f"{profile.username}"
-        print(f"User logged in: {username}")
-    else:
-        print("User not logged in.")
-        return "Please Login to Hugging Face with the button.", None
+    if not profile:
+        # print("--- User not logged in. ---") # Removed
+        return "请先使用 Hugging Face 账号登录。", None
+
+    username = profile.username
+    print(f"--- User: {username}. Starting new submission process. ---") # Kept for context
 
     api_url = DEFAULT_API_URL
     questions_url = f"{api_url}/questions"
     submit_url = f"{api_url}/submit"
+    space_id = os.getenv("SPACE_ID")
+    agent_code_url = f"https://huggingface.co/spaces/{space_id}/tree/main" if space_id else "N/A (SPACE_ID not set)"
 
-    # 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)
+        print(f"Fatal: Error instantiating agent: {e}\n{traceback.format_exc()}")
+        return f"初始化 Agent 失败: {e}", None
 
-    # 2. Fetch Questions
-    # print(f"Fetching questions from: {questions_url}")
+    # 1. Fetch Questions
+    # print(f"Fetching questions from: {questions_url}") # Removed
     try:
-        response = requests.get(questions_url, timeout=15)
+        response = requests.get(questions_url, timeout=20)
         response.raise_for_status()
         questions_data = response.json()
         if not questions_data:
-             print("Fetched questions list is empty.")
-             return "Fetched questions list is empty or invalid format.", None
-        # print(f"Fetched {len(questions_data)} questions.")
+            print("Warning: Fetched questions list is empty.")
+            return "获取到的问题列表为空。", None
+        # print(f"Fetched {len(questions_data)} questions.") # Removed
     except requests.exceptions.RequestException as e:
-        print(f"Error fetching questions: {e}")
-        return f"Error fetching questions: {e}", None
+        print(f"Fatal: Error fetching questions: {e}\n{traceback.format_exc()}")
+        return f"获取问题失败: {e}", None
     except requests.exceptions.JSONDecodeError as e:
-         print(f"Error decoding JSON response from questions endpoint: {e}")
-         print(f"Response text: {response.text[:500]}")
-         return f"Error decoding server response for questions: {e}", None
-    except Exception as e:
-        print(f"An unexpected error occurred fetching questions: {e}")
-        return f"An unexpected error occurred fetching questions: {e}", None
+        print(f"Fatal: Error decoding JSON from questions: {e}\nResponse text: {response.text[:500]}")
+        return f"解析问题数据失败: {e}", None
 
-    # 3. Run your Agent
     results_log = []
     answers_payload = []
-    # print(f"Running agent on {len(questions_data)} questions...")
-    for item in questions_data:
+
+    # 2. Run Agent on Questions
+    print(f"--- Running agent on {len(questions_data)} questions... ---")
+    for i, item in enumerate(questions_data):
         task_id = item.get("task_id")
         question_text = item.get("question")
+
         if not task_id or question_text is None:
-            # print(f"Skipping item with missing task_id or question: {item}")
+            print(f"Warning: Skipping item with missing task_id or question: {item}")
             continue
+
+        print(f"--- Processing question {i+1}/{len(questions_data)} (ID: {task_id}): \"{question_text[:70]}...\" ---")
+        submitted_answer = "AGENT_ERROR: Did not run or failed" # Default in case of early exit
         try:
             submitted_answer = agent.answer_question(question_text)
+            print(f"--- Answer for Q{i+1} (ID: {task_id}): \"{submitted_answer[:70]}...\" ---") # Print the answer
             answers_payload.append({"task_id": task_id, "submitted_answer": submitted_answer})
             results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": submitted_answer})
         except Exception as e:
-             print(f"Error running agent on task {task_id}: {e}")
-             results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT ERROR: {e}"})
+            # This specific exception handling might be redundant if agent.answer_question handles its own exceptions and returns a string
+            # However, keeping it as a fallback.
+            print(f"Error running agent on task {task_id} (Question: \"{question_text[:50]}...\"):\n{traceback.format_exc()}")
+            results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT_ERROR: {e}"})
 
-       
+        # CRITICAL: This sleep is likely causing timeouts.
+        # print(f"--- Waiting before next question... ---") # Removed
+        time.sleep(1) # MINIMAL SLEEP - ADJUST OR REMOVE FOR TESTING / BASED ON API LIMITS
 
     if not answers_payload:
-        # print("Agent did not produce any answers to submit.")
-        return "Agent did not produce any answers to submit.", pd.DataFrame(results_log)
+        print("Warning: Agent did not produce any answers to submit.")
+        return "Agent 未能生成任何答案用于提交。", 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)
+    # 3. Prepare and Submit
+    submission_data = {"username": username, "agent_code": agent_code_url, "answers": answers_payload}
+    # status_update = f"Agent finished. Submitting {len(answers_payload)} answers for user '{username}'..." # Removed
+    # print(status_update) # Removed
 
-    # 5. Submit
-    # print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
+    print(f"--- Submitting {len(answers_payload)} answers for user '{username}'... ---")
     try:
         response = requests.post(submit_url, json=submission_data, timeout=60)
         response.raise_for_status()
         result_data = response.json()
         final_status = (
-            f"Submission Successful!\n"
-            f"User: {result_data.get('username')}\n"
-            f"Overall Score: {result_data.get('score', 'N/A')}% "
-            f"({result_data.get('correct_count', '?')}/{result_data.get('total_attempted', '?')} correct)\n"
-            f"Message: {result_data.get('message', 'No message received.')}"
+            f"提交成功!\n"
+            f"用户: {result_data.get('username')}\n"
+            f"总分: {result_data.get('score', 'N/A')}% "
+            f"({result_data.get('correct_count', '?')}/{result_data.get('total_attempted', '?')} 正确)\n"
+            f"消息: {result_data.get('message', '无消息.')}"
         )
-        # print("Submission successful.")
-        submission_completed = True
+        print(f"--- Submission successful for {username}! Score: {result_data.get('score', 'N/A')}% ---")
+        submission_has_been_completed = True
+        for item_log in results_log:
+            processed_questions_cache[item_log["Task ID"]] = {
+                "question": item_log["Question"],
+                "answer": item_log["Submitted Answer"]
+            }
         results_df = pd.DataFrame(results_log)
         return final_status, results_df
     except requests.exceptions.HTTPError as e:
-        error_detail = f"Server responded with status {e.response.status_code}."
+        error_detail = f"服务器响应状态 {e.response.status_code}."
         try:
             error_json = e.response.json()
-            error_detail += f" Detail: {error_json.get('detail', e.response.text)}"
+            error_detail += f" 详情: {error_json.get('detail', e.response.text)}"
         except requests.exceptions.JSONDecodeError:
-            error_detail += f" Response: {e.response.text[:500]}"
-        status_message = f"Submission Failed: {error_detail}"
-        # print(status_message)
-        results_df = pd.DataFrame(results_log)
-        return status_message, results_df
+            error_detail += f" 响应内容: {e.response.text[:500]}"
+        status_message = f"提交失败: {error_detail}"
     except requests.exceptions.Timeout:
-        status_message = "Submission Failed: The request timed out."
-        # print(status_message)
-        results_df = pd.DataFrame(results_log)
-        return status_message, results_df
+        status_message = "提交失败: 请求超时."
     except requests.exceptions.RequestException as e:
-        status_message = f"Submission Failed: Network error - {e}"
-        # print(status_message)
-        results_df = pd.DataFrame(results_log)
-        return status_message, results_df
+        status_message = f"提交失败: 网络错误 - {e}"
     except Exception as e:
-        status_message = f"An unexpected error occurred during submission: {e}"
-        # print(status_message)
-        results_df = pd.DataFrame(results_log)
-        return status_message, results_df
+        status_message = f"提交过程中发生未知错误: {e}\n{traceback.format_exc()}"
+
+    print(f"--- Submission failed or an error occurred for {username}: {status_message} ---")
+    results_df = pd.DataFrame(results_log)
+    return status_message, results_df
 
 
 # --- Build Gradio Interface using Blocks ---
@@ -206,51 +185,29 @@ with gr.Blocks() as demo:
     gr.Markdown(
         """
         **Instructions:**
-
-        1.  Please clone this space, then modify the code to define your agent's logic, the tools, the necessary packages, etc ...
-        2.  Log in to your Hugging Face account using the button below. This uses your HF username for submission.
-        3.  Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see the score.
-
+        1.  Modify the code (if needed) to define your agent's logic.
+        2.  Log in to your Hugging Face account using the button below.
+        3.  Click 'Run Evaluation & Submit All Answers'.
         ---
         **Disclaimers:**
-        Once clicking on the "submit button, it can take quite some time ( this is the time for the agent to go through all the questions).
-        This space provides a basic setup and is intentionally sub-optimal to encourage you to develop your own, more robust solution. For instance for the delay process of the submit button, a solution could be to cache the answers and submit in a seperate action or even to answer the questions in async.
+        This process can take a significant amount of time.
+        If the process seems to restart, it might be due to platform timeouts.
+        Check the application logs on Hugging Face Spaces for more details.
         """
     )
 
     gr.LoginButton()
-
     run_button = gr.Button("Run Evaluation & Submit All Answers")
-
     status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
-    # Removed max_rows=10 from DataFrame constructor
     results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True)
 
     run_button.click(
         fn=run_and_submit_all,
-        outputs=[status_output, results_table]
+        outputs=[status_output, results_table],
     )
 
 if __name__ == "__main__":
     print("\n" + "-"*30 + " App Starting " + "-"*30)
-    # Check for SPACE_HOST and SPACE_ID at startup for information
-    space_host_startup = os.getenv("SPACE_HOST")
-    space_id_startup = os.getenv("SPACE_ID") # Get SPACE_ID at startup
-
-    if space_host_startup:
-        print(f"✅ SPACE_HOST found: {space_host_startup}")
-        print(f"   Runtime URL should be: https://{space_host_startup}.hf.space")
-    else:
-        print("ℹ️  SPACE_HOST environment variable not found (running locally?).")
-
-    if space_id_startup: # Print repo URLs if SPACE_ID is found
-        print(f"✅ SPACE_ID found: {space_id_startup}")
-        print(f"   Repo URL: https://huggingface.co/spaces/{space_id_startup}")
-        print(f"   Repo Tree URL: https://huggingface.co/spaces/{space_id_startup}/tree/main")
-    else:
-        print("ℹ️  SPACE_ID environment variable not found (running locally?). Repo URL cannot be determined.")
-
-    print("-"*(60 + len(" App Starting ")) + "\n")
-
+    # Minimal startup logs
     print("Launching Gradio Interface for Basic Agent Evaluation...")
-    demo.launch(debug=True, share=True)
+    demo.launch(debug=False, share=True) # debug=False for cleaner logs in production, True for local dev