app.py

import os
import gradio as gr
import requests
import inspect
import pandas as pd
import mimetypes

#from langchain.agents import initialize_agent, AgentType
from agent.gaia_agent import create_langchain_agent

from tools.wikipedia_tool import wiki_search
from tools.youtube_tool import get_youtube_transcript
from tools.audio_transcriber import transcribe_audio
from tools.image_chess_solver import solve_chess_image
from tools.file_parser import parse_file_and_summarize

# (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("Initializing LangGraph Agent...")
        self.agent = create_langchain_agent()
        self.system_prompt = (
            "You are a highly capable AI assistant completing GAIA benchmark tasks.\n"
            "You MUST use the tools provided to answer the user's question. Do not answer from your own knowledge.\n"
            "If a tool fails, explain the reason for the failure instead of hallucinating an answer.\n"
            "Provide concise and direct answers as requested in the questions. Do not add extra information unless explicitly asked for.\n"
            "For example, if asked for a number, return only the number. If asked for a list, return only the exact requested list."
        )

    def __call__(self, question: str) -> str:
        try:
            # We call it ONCE. If it hits a rate limit, the native max_retries=6 
            # inside gaia_agent.py will handle the pausing silently.
            result = self.agent.invoke({
                "messages": [
                    ("system", self.system_prompt),
                    ("user", question)
                ]
            })
            return result["messages"][-1].content
            
        except Exception as e:
            return f"Agent error: {e}"


def manual_test(question):
    agent = BasicAgent()
    return agent(question)

def download_task_file(task_id: str) -> str:
    """Downloads the attached file for a task and returns the local file path."""
    file_url = f"{DEFAULT_API_URL}/files/{task_id}"
    try:
        response = requests.get(file_url, stream=True, timeout=15)
        # If a file exists, the server returns 200 OK
        if response.status_code == 200:
            os.makedirs("downloads", exist_ok=True)
            
            # Try to extract the original filename from the server headers
            content_disp = response.headers.get('content-disposition', '')
            if 'filename=' in content_disp:
                filename = content_disp.split('filename=')[1].strip('"\'')
            else:
                # Fallback: Guess the extension so pandas/whisper can read it
                content_type = response.headers.get('content-type', '')
                ext = mimetypes.guess_extension(content_type) or '.tmp'
                if 'spreadsheetml' in content_type: ext = '.xlsx'
                elif 'ms-excel' in content_type: ext = '.xls'
                filename = f"file_{task_id}{ext}"
            
            local_path = os.path.join("downloads", filename)
            
            # Save the file locally
            with open(local_path, 'wb') as f:
                for chunk in response.iter_content(chunk_size=8192):
                    f.write(chunk)
            return local_path
        return None
    except Exception as e:
        print(f"Failed to download file for {task_id}: {e}")
        return None

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
            
        # --- NEW: Download attached file and inject it into the prompt ---
        local_file_path = download_task_file(task_id)
        if local_file_path:
            print(f"Successfully downloaded file to: {local_file_path}")
            question_text += f"\n\n[System Note: A file is attached to this question. It has been downloaded to your local environment at path: {local_file_path}. Use your tools to read/analyze it if necessary.]"
        # -----------------------------------------------------------------

        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})
            print(f"✅ Solved! 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()
    
    manual_input = gr.Textbox(label="Try the Agent Manually", placeholder="How many studio albums where published by Mercedes Sosa between 2000 and 2009 (included)? You can use the latest v2022 version of wikipedia.")
    manual_output = gr.Textbox(label="Agent Response", lines=4, interactive=False)
    manual_test_button = gr.Button("Run Agent Locally")
    manual_test_button.click(fn=manual_test, inputs=[manual_input], outputs=[manual_output])
    
    print(manual_input.placeholder )
    

    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")
    
    #from tools.wikipedia_tool import wiki_search
    #print(wiki_search("Mercedes Sosa discography"))


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