app.py

import os
import gradio as gr
import requests
import inspect
import pandas as pd
from smolagents import CodeAgent, HfApiModel
from smolagents.tools import PythonInterpreterTool, DuckDuckGoSearchTool
import subprocess
import sys

def install_package(package):
    subprocess.check_call([sys.executable, "-m", "pip", "install", package])

# 使用示例
install_package("smolagents")
# --- Constants ---
DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"

# --- SmolAgents Agent Definition ---
class SmolAgent:
    def __init__(self):
        print("SmolAgent initializing...")
        
        # 初始化模型 - 使用 HuggingFace API
        # 你需要设置你的 HF token
        hf_token = os.getenv("HF_TOKEN")
        if not hf_token:
            print("Warning: HF_TOKEN not found. Please set your HuggingFace token.")
        
        # 使用一个强大的模型，比如 Qwen2.5-72B-Instruct
        self.model = HfApiModel(
            model_id="Qwen/Qwen2.5-72B-Instruct",
            token=hf_token
        )
        
        # 初始化工具
        self.tools = [
            PythonInterpreterTool(),
            DuckDuckGoSearchTool(),
        ]
        
        # 创建代理
        self.agent = CodeAgent(
            tools=self.tools,
            model=self.model,
            max_steps=10,
            verbosity_level=2
        )
        
        print("SmolAgent initialized successfully.")
    
    def __call__(self, question: str) -> str:
        print(f"Agent received question (first 100 chars): {question[:100]}...")
        
        try:
            # 构建提示，强调需要精确答案
            enhanced_prompt = f"""
Please answer the following question accurately and precisely. 
Provide only the final answer without any additional text or explanation.
If the question requires calculations, use the Python tool to ensure accuracy.
If you need to search for information, use the search tool.

Question: {question}

Important: Your response should contain ONLY the final answer, nothing else.
"""
            
            # 运行代理
            result = self.agent.run(enhanced_prompt)
            
            # 提取最终答案
            if hasattr(result, 'content'):
                answer = result.content.strip()
            else:
                answer = str(result).strip()
            
            print(f"Agent returning answer: {answer}")
            return answer
            
        except Exception as e:
            print(f"Error in agent execution: {e}")
            return f"Error: {str(e)}"

def run_and_submit_all(profile: gr.OAuthProfile | None):
    """
    Fetches all questions, runs the SmolAgent on them, submits all answers,
    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

    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

    api_url = DEFAULT_API_URL
    questions_url = f"{api_url}/questions"
    submit_url = f"{api_url}/submit"

    # 1. Instantiate Agent
    try:
        agent = SmolAgent()
    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
    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
    print(f"Agent code link: {agent_code}")

    # 2. Fetch Questions
    print(f"Fetching questions from: {questions_url}")
    try:
        response = requests.get(questions_url, timeout=15)
        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.")
    except requests.exceptions.RequestException as e:
        print(f"Error fetching questions: {e}")
        return f"Error fetching questions: {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

    # 3. Run your Agent
    results_log = []
    answers_payload = []
    print(f"Running SmolAgent 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}")
            continue
            
        print(f"Processing question {i+1}/{len(questions_data)} (Task ID: {task_id})")
        
        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[:100] + "..." if len(question_text) > 100 else question_text, 
                "Submitted Answer": submitted_answer
            })
        except Exception as e:
             print(f"Error running agent on task {task_id}: {e}")
             error_answer = f"AGENT ERROR: {e}"
             answers_payload.append({"task_id": task_id, "submitted_answer": error_answer})
             results_log.append({
                 "Task ID": task_id, 
                 "Question": question_text[:100] + "..." if len(question_text) > 100 else question_text, 
                 "Submitted Answer": error_answer
             })

    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)

    # 4. Prepare Submission 
    submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers_payload}
    status_update = f"SmolAgent 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=120)  # 增加超时时间
        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.')}"
        )
        print("Submission successful.")
        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}"
        print(status_message)
        results_df = pd.DataFrame(results_log)
        return status_message, results_df
    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
    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
    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


# --- Build Gradio Interface using Blocks ---
with gr.Blocks() as demo:
    gr.Markdown("# SmolAgents GAIA Evaluation Runner")
    gr.Markdown(
        """
        **Instructions:**
        1. Make sure you have set your HF_TOKEN environment variable in your Space settings
        2. Log in to your Hugging Face account using the button below
        3. Click 'Run Evaluation & Submit All Answers' to start the evaluation
        
        **SmolAgent Features:**
        - Uses Qwen2.5-72B-Instruct model for reasoning
        - Python interpreter for calculations
        - DuckDuckGo search for information retrieval
        - Multi-step reasoning capabilities
        
        **Note:** This process may take several minutes as the agent processes each question thoroughly.
        """
    )

    gr.LoginButton()

    run_button = gr.Button("Run Evaluation & Submit All Answers", variant="primary")

    status_output = gr.Textbox(label="Run Status / Submission Result", lines=8, interactive=False)
    results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True)

    run_button.click(
        fn=run_and_submit_all,
        outputs=[status_output, results_table]
    )

if __name__ == "__main__":
    print("\n" + "-"*30 + " SmolAgent App Starting " + "-"*30)
    
    # Check for required environment variables
    space_host_startup = os.getenv("SPACE_HOST")
    space_id_startup = os.getenv("SPACE_ID")
    hf_token = os.getenv("HF_TOKEN")

    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(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.")
    
    if hf_token:
        print("✅ HF_TOKEN found.")
    else:
        print("⚠️  HF_TOKEN environment variable not found. Please set it in your Space settings.")

    print("-"*(60 + len(" SmolAgent App Starting ")) + "\n")

    print("Launching Gradio Interface for SmolAgent GAIA Evaluation...")
    demo.launch(debug=True, share=False)