Update app.py

app.py

@@ -1,15 +1,12 @@
 import os
 import gradio as gr
 import requests
-import inspect
 import pandas as pd
 
 from smolagents import (
     ToolCallingAgent, 
     CodeAgent,
     DuckDuckGoSearchTool, 
-    InferenceClientModel, 
-    HfApiModel, 
     OpenAIServerModel
 )
 
@@ -30,24 +27,21 @@ class BasicAgent:
             add_base_tools=True
         )
 
+        # 修改系统提示词，允许更详细的回答
         self.agent.prompt_templates['system_prompt'] = """You are a general AI assistant. I will ask you a question.
-Your primary goal is to answer the question directly and concisely.
+Your primary goal is to answer the question accurately and thoroughly.
 The 'content' field of your response message, even if it's just your thought process before a tool call, MUST be a single string or null. It MUST NOT be a list or any other sequence.
 If you are providing a direct answer without using any tools, your response content MUST be a single string.
-Report your thoughts as a single block of text (a single string).
+
+For complex questions that require detailed explanations (like describing benchmarks, datasets, or technical concepts), provide a comprehensive answer with all relevant details.
+
 Finish your answer with the following template: FINAL ANSWER: [YOUR FINAL ANSWER].
-YOUR FINAL ANSWER should be a number OR as few words as possible OR a comma separated list of numbers and/or strings.
-If you are asked for a number, don't use comma to write your number neither use units such as $ or percent sign unless specified otherwise.
-If you are asked for a string, don't use articles, neither abbreviations (e.g. for cities), and write the digits in plain text unless specified otherwise.
-If you are asked for a comma separated list, apply the above rules depending of whether the element to be put in the list is a number or a string.
+YOUR FINAL ANSWER can be detailed and comprehensive when the question requires it, especially for questions about technical topics, benchmarks, datasets, or concepts that need thorough explanation.
 """
-        # 移除打印语句
-        
+    
     def __call__(self, question: str) -> str:
-        # 移除打印语句
-        fixed_answer = self.agent.run(question)
-        # 移除打印语句
-        return fixed_answer
+        # 移除所有打印语句，直接返回答案
+        return self.agent.run(question)
 
 def run_and_submit_all(profile: gr.OAuthProfile | None):
     """
@@ -55,132 +49,89 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
     and displays the results.
     """
     # --- Determine HF Space Runtime URL and Repo URL ---
-    space_id = os.getenv("SPACE_ID") # Get the SPACE_ID for sending link to the code
+    space_id = os.getenv("SPACE_ID")
 
     if profile:
-        username= f"{profile.username}"
-        # 移除打印语句
+        username = f"{profile.username}"
     else:
-        # 移除打印语句
-        return "Please Login to Hugging Face with the button.", None
+        return "请使用下方按钮登录Hugging Face。", None
 
     api_url = DEFAULT_API_URL
     questions_url = f"{api_url}/questions"
     submit_url = f"{api_url}/submit"
 
-    # 1. Instantiate Agent
+    # 1. 实例化代理
     try:
         agent = BasicAgent()
     except Exception as e:
-        # 移除打印语句
-        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
+        return f"初始化代理时出错: {e}", None
+    
     agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
-    # 移除打印语句
 
-    # 2. Fetch Questions
-    # 移除打印语句
+    # 2. 获取问题
     try:
         response = requests.get(questions_url, timeout=15)
         response.raise_for_status()
         questions_data = response.json()
         if not questions_data:
-             # 移除打印语句
-             return "Fetched questions list is empty or invalid format.", None
-        # 移除打印语句
-    except requests.exceptions.RequestException as e:
-        # 移除打印语句
-        return f"Error fetching questions: {e}", None
-    except requests.exceptions.JSONDecodeError as e:
-         # 移除打印语句
-         # 移除打印语句
-         return f"Error decoding server response for questions: {e}", None
+            return "获取的问题列表为空或格式无效。", None
     except Exception as e:
-        # 移除打印语句
-        return f"An unexpected error occurred fetching questions: {e}", None
+        return f"获取问题时出错: {e}", None
 
-    # 3. Run your Agent
+    # 3. 运行代理
     results_log = []
     answers_payload = []
-    # 移除打印语句
+    
     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:
-            # 移除打印语句
             continue
         try:
             submitted_answer = agent(question_text)
             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:
-             # 移除打印语句
-             results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT ERROR: {e}"})
-        
+            results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT ERROR: {e}"})
 
     if not answers_payload:
-        # 移除打印语句
-        return "Agent did not produce any answers to submit.", pd.DataFrame(results_log)
+        return "代理未能生成任何答案。", pd.DataFrame(results_log)
 
-    # 4. Prepare Submission 
+    # 4. 准备提交 
     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}'..."
-    # 移除打印语句
 
-    # 5. Submit
-    # 移除打印语句
+    # 5. 提交
     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', '未收到消息。')}"
         )
-        # 移除打印语句
         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}."
-        try:
-            error_json = e.response.json()
-            error_detail += f" Detail: {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}"
-        # 移除打印语句
-        results_df = pd.DataFrame(results_log)
-        return status_message, results_df
-    except requests.exceptions.Timeout:
-        status_message = "Submission Failed: The request timed out."
-        # 移除打印语句
-        results_df = pd.DataFrame(results_log)
-        return status_message, results_df
-    except requests.exceptions.RequestException as e:
-        status_message = f"Submission Failed: Network error - {e}"
-        # 移除打印语句
-        results_df = pd.DataFrame(results_log)
-        return status_message, results_df
     except Exception as e:
-        status_message = f"An unexpected error occurred during submission: {e}"
-        # 移除打印语句
+        status_message = f"提交失败: {e}"
         results_df = pd.DataFrame(results_log)
         return status_message, results_df
 
 
+
 # --- Build Gradio Interface using Blocks ---
 with gr.Blocks() as demo:
-    gr.Markdown("# Basic Agent Evaluation Runner")
+    gr.Markdown("# LangGraph Agent Evaluation Runner")  # Updated title
     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.  Please clone this space, then modify the code in `agent.py` and `app.py` to define your agent's logic, the tools, the necessary packages, etc ...
+        2.  **Make sure you have your `DEEPSEEK_API_KEY` set as a Space Secret.**
+        3.  Log in to your Hugging Face account using the button below. This uses your HF username for submission.
+        4.  Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see the score.
 
         ---
         **Disclaimers:**
@@ -202,5 +153,25 @@ with gr.Blocks() as demo:
     )
 
 if __name__ == "__main__":
-    # 移除所有启动时的打印语句
-    demo.launch(debug=False, share=False)
+    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")
+
+    print("Launching Gradio Interface for LangGraph Agent Evaluation...")  # Updated message
+    demo.launch(debug=True, share=False, auth=None)