app.py

import os
import gradio as gr
import requests
import inspect
import pandas as pd
import json
import threading

# Import our custom tools from their modules
from huggingface_hub import login
from smolagents import CodeAgent, InferenceClientModel, OpenAIServerModel
from tools import web_search, visit_webpage, final_answer, wiki_search
# from tools import web_search, visit_webpage, final_answer, go_back, close_popups, search_item_ctrl_f
from retriever import load_guest_dataset
from functools import lru_cache

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

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

        # Get API key automatically from Space environment
        api_key = os.getenv("HF_API_KEY")

        # Login to Hugging Face with the token
        login(token=api_key)
        
        # Create the search tool
        self.web_search = web_search

        self.visit_webpage = visit_webpage

        self.final_answer = final_answer
        
        self.wiki_search = wiki_search

        # self.go_back = go_back 
        
        # self.close_popups = close_popups
        
        # self.search_item_ctrl_f = search_item_ctrl_f
        
        # Create the model
        self.model = InferenceClientModel(model_id="Qwen/Qwen2.5-72B-Instruct")
        # self.model = InferenceClientModel(model_id="Qwen/Qwen2.5-7B-Instruct") #smaller/faster
        # self.model = OpenAIServerModel(model_id="gpt-4o")

        # Define your system prompt
        self.system_prompt = """You are a general AI assistant. I will ask you a question. Finish your answer with only 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.
        
        If visit_webpage fails with a 403 error, fetch the page directly using requests with a User-Agent header: import requests 
        headers = {"User-Agent": "Mozilla/5.0 (compatible; MyAgent/1.0)"} 
        response = requests.get(url, headers=headers) 
        text = response.text

        When fetching pages with requests, always parse with BeautifulSoup to extract readable text instead of raw HTML: 
        from bs4 import BeautifulSoup 
        soup = BeautifulSoup(response.text, 'html.parser') 
        text = soup.get_text() 
        print(text[:3000])

        To read downloaded files, use io.BytesIO instead of open(). Example for Excel: 
        import requests, io, pandas as pd 
        response = requests.get(url)
        df = pd.read_excel(io.BytesIO(response.content))

        To read downloaded files, never use open(). Use io.BytesIO instead:
        import requests, io, pandas as pd
        response = requests.get(url)
        df = pd.read_excel(io.BytesIO(response.content))
        
        YouTube URLs cannot be accessed directly. For YouTube questions, search for the video title or topic using web_search to find the answer indirectly.
        """
        
        # Create the agent with tools
        self.agent = CodeAgent(
            tools=[web_search, self.visit_webpage, self.final_answer, wiki_search],
            # tools=[self.web_search, self.visit_webpage, self.final_answer, go_back, close_popups, search_item_ctrl_f],
            model=self.model,
            additional_authorized_imports=["pandas", "openpyxl", "yt_dlp", "requests", "io", "json", "whisper", "bs4"],
            max_steps=10  # Limit reasoning steps
        )

    def __call__(self, question: str) -> str:
        print(f"Agent received question (first 50 chars): {question[:50]}...")
        #fixed_answer = "This is a default answer."
        #print(f"Agent returning fixed answer: {fixed_answer}")

        try:
            # Run the agent with the question
            # formatted_question = f"{question}\n\nOnly return the exact answer, no explanation." 
            formatted_question = f"{self.system_prompt}\n\nQuestion: {question}\n\n"
            answer = self.agent.run(formatted_question)
            answer = str(answer).strip() if answer is not None else "No answer produced."

            # Detect raw scratchpad instead of clean answer
            if "Thought:" in answer or "```" in answer or "Calling tools:" in answer:
                print("Warning: agent returned scratchpad, extracting final answer...")
                if "YOUR FINAL ANSWER" in answer:
                    answer = answer.split("YOUR FINAL ANSWER")[-1].strip().lstrip(":").strip()
                else:
                    answer = "Agent did not produce a final answer."
            
            # answer = self.agent.run(question)
            print(f"Agent returning answer: {answer[:100]}...")
            fixed_answer = answer
        except Exception as e:
            print(f"Agent error: {e}")
            fixed_answer = f"I encountered an error: {str(e)}"
        
        return fixed_answer

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
    
    from concurrent.futures import ThreadPoolExecutor, as_completed, TimeoutError
    cache_lock = threading.Lock()
    results_log = []
    answers_payload = []
    print(f"Running agent on {len(questions_data)} questions...")

    CACHE_FILE = "answer_cache.json"
    cache = json.load(open(CACHE_FILE)) if os.path.exists(CACHE_FILE) else {}

    def process_question(item):
        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}")
            return None, None, None

        # Return cached answer if available
        if task_id in cache:
            print(f"Cache hit for task {task_id}")
            return task_id, question_text, cache[task_id]
        
        try:
            question_with_context = f"""Task ID: {task_id}
If this question refers to an attached file, download it first from:
https://agents-course-unit4-scoring.hf.space/files/{task_id}
{question_text}"""
            submitted_answer = agent(question_with_context)
            # Save to cache
            with cache_lock:
                cache[task_id] = submitted_answer
                json.dump(cache, open(CACHE_FILE, "w"))
            return task_id, question_text, submitted_answer
        except Exception as e:
            print(f"Error running agent on task {task_id}: {e}")
            return task_id, question_text, f"AGENT ERROR: {e}"
    
    with ThreadPoolExecutor(max_workers=3) as executor:
        futures = {executor.submit(process_question, item): item for item in questions_data}
        for future in as_completed(futures):
            item = futures[future]
            task_id = item.get("task_id")
            question_text = item.get("question")
            try:
                result_task_id, result_question, submitted_answer = future.result(timeout=300)
                if result_task_id is None:
                    continue
                answers_payload.append({"task_id": result_task_id, "submitted_answer": submitted_answer})
                results_log.append({"Task ID": result_task_id, "Question": result_question, "Submitted Answer": submitted_answer})
            except TimeoutError:
                print(f"Task {task_id} timed out, skipping.")
                answers_payload.append({"task_id": task_id, "submitted_answer": "TIMEOUT"})
                results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": "TIMEOUT"})
            except Exception as e:
                print(f"Task {task_id} raised an exception: {e}")
                answers_payload.append({"task_id": task_id, "submitted_answer": f"AGENT ERROR: {e}"})
                results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT ERROR: {e}"})
    
    # 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
    #     try:
    #         # submitted_answer = agent(question_text)
    #         question_with_context = f"""Task ID: {task_id}
    #         If this question refers to an attached file, download it first from:
    #         https://agents-course-unit4-scoring.hf.space/files/{task_id}
    #         {question_text}"""
    #         submitted_answer = agent(question_with_context) # for Excel and audio questions
    #         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}"})

    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)