app.py

import os
import json
import gradio as gr
import requests
import inspect
import pandas as pd
from tools import search_tool, rag_chain, extract_final_answer, initialize_code_agent

# --- Constants ---
DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
SUBMISSION_FILE = "submission.jsonl"


def run_and_submit_all(profile: gr.OAuthProfile | None):
    """Fetches all questions, runs the CodeAgent 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 = initialize_code_agent()
        if not agent:
            raise Exception("Failed to initialize CodeAgent")
    except Exception as e:
        print(f"Error instantiating agent: {e}")
        return f"Error initializing agent: {e}", None

    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
        try:
            # Use imported search tool and RAG chain
            search_result = search_tool.run(question_text)
            if rag_chain:
                response = rag_chain.run(f"{question_text}\nSearch result: {search_result}")
                submitted_answer = extract_final_answer(response)
                # Format answer according to JSON-line submission requirements
                answers_payload.append({
                    "task_id": task_id,
                    "model_answer": submitted_answer,
                    "reasoning_trace": response
                })
            else:
                submitted_answer = agent.run(question_text)
                answers_payload.append({
                    "task_id": task_id,
                    "model_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)

    # Generate JSON-line submission file
    try:
        with open(SUBMISSION_FILE, "w") as f:
            for entry in answers_payload:
                json.dump(entry, f)
                f.write("\n")
        print(f"Successfully generated submission file: {SUBMISSION_FILE}")
    except Exception as e:
        print(f"Error generating submission file: {e}")
        return f"Error generating submission file: {e}", 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"Submission file generated: {SUBMISSION_FILE}\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}\nSubmission file generated: {SUBMISSION_FILE}"
        print(status_message)
        results_df = pd.DataFrame(results_log)
        return status_message, results_df
    except requests.exceptions.Timeout:
        status_message = f"Submission Failed: The request timed out.\nSubmission file generated: {SUBMISSION_FILE}"
        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}\nSubmission file generated: {SUBMISSION_FILE}"
        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}\nSubmission file generated: {SUBMISSION_FILE}"
        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("# Code Agent Evaluation Runner")
    gr.Markdown(
        """
        **Instructions:**

        1. Log in to your Hugging Face account using the button below.
        2. Make sure you have set up the required environment variables:
           - BING_API_KEY: For web search functionality
           - OPENAI_API_KEY: For GPT-3.5 model access
           - HUGGINGFACE_HUB_TOKEN: For GAIA dataset access
        3. Click 'Run Evaluation & Submit All Answers' to start the evaluation.

        The agent will:
        - Search the web for relevant information
        - Use RAG to process and retrieve context from GAIA dataset
        - Generate comprehensive answers
        - Create JSON-line submission file: submission.jsonl
        """
    )

    gr.LoginButton()
    run_button = gr.Button("Run Evaluation & Submit All Answers")
    status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, 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 + " App Starting " + "-"*30)
    space_host_startup = os.getenv("SPACE_HOST")
    space_id_startup = os.getenv("SPACE_ID")

    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.")

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

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