app.py

import os
import gradio as gr
import requests
import inspect
import pandas as pd
from dotenv import load_dotenv
from openai import OpenAI
from tenacity import retry, stop_after_attempt, wait_exponential

# Load environment variables
load_dotenv()

# (Keep Constants as is)
# --- Constants ---
DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
OPENAI_MODEL = "openai/gpt-4.1"  # or "gpt-3.5-turbo" based on your preference


# --- Basic Agent Definition ---
# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
class BasicAgent:
    def __init__(self):
        """Initialize the agent with OpenAI client and setup."""
        print("BasicAgent initializing...")
        self.client = OpenAI(
            api_key=os.environ["API_KEY"],
            base_url="https://models.github.ai/inference",
        )
        print("BasicAgent initialized successfully.")

    @retry(
        stop=stop_after_attempt(3), wait=wait_exponential(multiplier=1, min=4, max=10)
    )
    def _get_completion(self, prompt: str) -> str:
        """Get completion from OpenAI with retry logic."""
        try:
            response = self.client.chat.completions.create(
                model=OPENAI_MODEL,
                messages=[
                    {
                        "role": "developer",
                        "content": """
                        You are an expert research assistant that provides precise, accurate answers. Before responding, use this hidden planning phase (which will not be shown to users):
                        
                        ```
                        <planning>
                        1. Classify the question type:
                           - Arithmetic/mathematical calculation
                           - Factual lookup (dates, codes, definitions)
                           - Complex knowledge (requires synthesis of multiple facts)
                           - Subjective/opinion-based (requires reasoning with caveats)
                        
                        2. For each type:
                           - Arithmetic: Calculate step-by-step to ensure accuracy
                           - Factual lookup: Identify the specific data point needed
                           - Complex knowledge: Break down into key components and relationships
                           - Subjective: Note major perspectives and evidence for each
                        
                        3. Check for potential ambiguities or misinterpretations
                        4. Formulate the most precise answer possible
                        </planning>
                        ```
                        
                        ## Response Format
                        
                        After your planning, provide your answer in this format:
                        
                        **Answer:** [Your concise, precise answer]
                        
                        For factual questions, include only the exact information requested - no extra text.
                        For complex questions, provide a concise, well-structured response focused on accuracy.
                        
                        ## Examples
                        
                        **Q: What is 493 × 27?**
                        <planning>Arithmetic calculation: 493 × 27 = (493 × 20) + (493 × 7) = 9,860 + 3,451 = 13,311</planning>
                        **Answer:** 13,311
                        
                        **Q: Which country has the smallest land area in South America?**
                        <planning>Factual lookup: South American countries by land area. Smallest is Suriname at 63,251 square miles.</planning>
                        **Answer:** Suriname
                        
                        **Q: How does atmospheric carbon dioxide affect ocean acidity?**
                        <planning>Complex knowledge question requiring synthesis of chemistry concepts...</planning>
                        **Answer:** Atmospheric CO₂ dissolves in seawater forming carbonic acid (H₂CO₃), which releases hydrogen ions and lowers pH. This process, called ocean acidification, has increased ocean acidity by approximately 30% since the Industrial Revolution.""",
                    },
                    {"role": "user", "content": prompt},
                ],
                temperature=0.5,  # Lower temperature for more consistent outputs
                # max_tokens=1000,
            )
            return response.choices[0].message.content.strip()
        except Exception as e:
            print(f"Error in OpenAI API call: {e}")
            raise

    def _preprocess_question(self, question: str) -> str:
        """Preprocess the question to enhance clarity and context."""
        enhanced_prompt = f"""Please analyze and answer the following question from the GAIA benchmark.
        Question: {question}

        Provide a clear, specific answer that can be evaluated through exact matching.
        If the question requires multiple steps, please show your reasoning but ensure the final answer is clearly stated.
        """
        return enhanced_prompt

    def __call__(self, question: str) -> str:
        """Process the question and return an answer."""
        print(f"Agent received question (first 50 chars): {question[:50]}...")

        try:
            # Preprocess the question
            enhanced_prompt = self._preprocess_question(question)

            # Get completion from OpenAI
            response = self._get_completion(enhanced_prompt)

            # Extract the final answer
            # If the response contains multiple lines or explanations,
            # we'll try to extract just the final answer
            answer_lines = response.strip().split("\n")
            final_answer = answer_lines[-1].strip()

            # Log the response for debugging
            print(f"Agent generated answer: {final_answer[:100]}...")

            return final_answer

        except Exception as e:
            print(f"Error processing question: {e}")
            return f"Error: {str(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
        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,
                }
            )
        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)