app.py

import os
from traceback import print_tb
import gradio as gr
import requests
import inspect
import pandas as pd
from smolagents import CodeAgent, DuckDuckGoSearchTool, InferenceClientModel, OpenAIServerModel, ToolCallingAgent, VisitWebpageTool
from dotenv import load_dotenv
from utils import detect_file_category
from tools import transcribe_audio
from PIL import Image

load_dotenv()
from smolagents import CodeAgent, DuckDuckGoSearchTool, InferenceClientModel

# (Keep Constants as is)
# --- Constants ---
DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
DASHSCOPE_API_BASE = os.getenv("DASHSCOPE_API_BASE")
DASHSCOPE_API_KEY = os.getenv("DASHSCOPE_API_KEY")  

# --- Basic Agent Definition ---
# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
class BasicAgent:
    def __init__(self):
        print("BasicAgent initialized.")

    def __call__(self, question: str, file_path: str) -> str:
        if not file_path or "ERROR" in file_path:
            file_path = None

        if file_path:
            category = detect_file_category(file_path)
        else:
            category = "none"

        if category == "none":
            agent = CodeAgent(tools=[DuckDuckGoSearchTool(), VisitWebpageTool()], model=OpenAIServerModel(
                model_id="qwen3-coder-flash",
                api_base=DASHSCOPE_API_BASE,
                api_key=DASHSCOPE_API_KEY,
            ))
            return agent.run(question)
        
        if category == "audio":
            agent = CodeAgent(
                tools=[DuckDuckGoSearchTool(), VisitWebpageTool(), transcribe_audio], 
                model=OpenAIServerModel(
                    model_id="qwen3-coder-flash",
                    api_base=DASHSCOPE_API_BASE,
                    api_key=DASHSCOPE_API_KEY,
            ))
            return agent.run(question + f"\n\nfile_path：{file_path}")

        if category == "image":
            agent = CodeAgent(
                model=OpenAIServerModel(
                    model_id="qwen3-vl-flash",
                    api_base=DASHSCOPE_API_BASE,
                    api_key=DASHSCOPE_API_KEY,
                ),
                max_steps=20,
                verbosity_level=2
            )
            # agent = CodeAgent(
            #     tools=[DuckDuckGoSearchTool(), VisitWebpageTool()], 
            #     model=OpenAIServerModel(
            #         model_id="qwen3-coder-flash",
            #         api_base=DASHSCOPE_API_BASE,
            #         api_key=DASHSCOPE_API_KEY,
            #     ),
            #     managed_agents=[image_agent])
            return agent.run(question, images=[Image.open(file_path).convert("RGB")])
        
        agent = CodeAgent(
            additional_authorized_imports=["pandas"],
            tools=[DuckDuckGoSearchTool(), VisitWebpageTool()], 
            model=OpenAIServerModel(
                model_id="qwen3-coder-flash",
                api_base=DASHSCOPE_API_BASE,
                api_key=DASHSCOPE_API_KEY,
        ))
        return agent.run(question + f"\n\nfile_path：{file_path}")

# 新增：下载与 task_id 关联的文件的辅助函数
import re

def download_task_file(api_url: str, task_id: str, output_dir: str = "downloads") -> str:
    files_url = f"{api_url}/files/{task_id}"
    try:
        os.makedirs(output_dir, exist_ok=True)

        # 快速预检：如果 downloads 里已存在以 task_id 命名的文件则直接返回
        try:
            for name in os.listdir(output_dir):
                base, _ext = os.path.splitext(name)
                candidate = os.path.join(output_dir, name)
                if base == task_id and os.path.isfile(candidate):
                    print(f"File for task {task_id} already exists: {candidate}")
                    return candidate
        except FileNotFoundError:
            pass

        with requests.get(files_url, stream=True, timeout=30) as r:
            r.raise_for_status()
            filename = None
            cd = r.headers.get("content-disposition")
            if cd:
                m = re.search('filename="?([^";]+)"?', cd)
                if m:
                    filename = m.group(1)
            if not filename:
                filename = r.headers.get("x-filename")
            if not filename:
                filename = f"{task_id}.download"
            dest_path = os.path.join(output_dir, filename)

            # 二次检查：若目标文件已存在则跳过重新下载
            if os.path.exists(dest_path):
                print(f"File for task {task_id} already exists: {dest_path}")
                return dest_path

            with open(dest_path, "wb") as f:
                for chunk in r.iter_content(chunk_size=8192):
                    if chunk:
                        f.write(chunk)
        print(f"Downloaded file for task {task_id} to: {dest_path}")
        return dest_path
    except requests.exceptions.HTTPError as e:
        status = getattr(e.response, 'status_code', 'unknown')
        print(f"File download HTTP error for task {task_id}: {e}")
        return f"ERROR: HTTP {status} for task {task_id}"
    except requests.exceptions.Timeout:
        print(f"File download timed out for task {task_id}")
        return f"ERROR: Timeout downloading task {task_id}"
    except requests.exceptions.RequestException as e:
        print(f"File download network error for task {task_id}: {e}")
        return f"ERROR: Network error downloading task {task_id}: {e}"
    except Exception as e:
        print(f"Unexpected error downloading file for task {task_id}: {e}")
        return f"ERROR: Unexpected error downloading task {task_id}: {e}"

def run_and_submit_all( profile: gr.OAuthProfile | None):
    """
    Fetches all questions, runs the BasicAgent 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 ( 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)
        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 agent on {len(questions_data)} questions...")
    for item in 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
        # 新增：下载与该 task_id 关联的文件
        downloaded_path = download_task_file(api_url, task_id)
        try:
            submitted_answer = agent(question_text, downloaded_path)
            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, "Downloaded File": downloaded_path})
        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}", "Downloaded File": downloaded_path})

    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"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)
        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("# Basic Agent Evaluation Runner")
    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.

        ---
        **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.
        """
    )

    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]
    )

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")

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