app.py

import os
import gradio as gr
import requests
import inspect
import pandas as pd
from bs4 import BeautifulSoup
import requests

# (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 ------


def web_search(query: str) -> list[dict]:
    """
    Performs a web search and returns relevant information.

    Args:
        query: The search query string.

    Returns:
        A list of dictionaries, where each dictionary represents a search result
        with keys 'title', 'snippet', and 'url'. Returns an empty list if no
        results are found or an error occurs.
    """
    search_url = f"https://www.google.com/search?q={requests.utils.quote(query)}"
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36"
    }
    results = []

    try:
        response = requests.get(search_url, headers=headers, timeout=10)
        response.raise_for_status() # Raise an HTTPError for bad responses (4xx or 5xx)

        soup = BeautifulSoup(response.text, 'html.parser')

        # Find search results - this is a basic example and might need adjustment
        # based on Google's ever-changing HTML structure.
        # 'div.tF2CMy' is a common class for result blocks as of certain dates.
        search_results = soup.select('div.tF2CMy')

        if not search_results:
             # Fallback or alternative selectors if the primary one fails
             search_results = soup.select('div.g') # Another common class

        for result in search_results:
            link = result.select_one('a')
            title = result.select_one('h3')
            snippet = result.select_one('span.aCOpNe') # Example snippet class

            if link and title:
                item = {
                    'title': title.get_text(),
                    'url': link['href'],
                    'snippet': snippet.get_text() if snippet else 'No snippet available'
                }
                results.append(item)

    except requests.exceptions.RequestException as e:
        print(f"Error during web search request: {e}")
    except Exception as e:
        print(f"An unexpected error occurred during web search: {e}")

    return results

# Example usage (optional, for testing)
# search_results = web_search("what is the capital of France?")
# for i, result in enumerate(search_results[:3]): # Print first 3 results
#     print(f"--- Result {i+1} ---")
#     print(f"Title: {result.get('title', 'N/A')}")
#     print(f"URL: {result.get('url', 'N/A')}")
#     print(f"Snippet: {result.get('snippet', 'N/A')}")
#     print("-" * 10)

class BasicAgent:
  def __init__(self):
        print("BasicAgent initialized.")

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

        # Simple logic to determine if a web search is needed
        question_lower = question.lower()
        search_keywords = ["what is", "how to", "where is", "who is", "when did", "define", "explain", "tell me about"]
        needs_search = any(keyword in question_lower for keyword in search_keywords) or "?" in question

        if needs_search:
            print(f"Question likely requires search. Searching for: {question}")
            search_results = web_search(question) # Call the web_search function

            if search_results:
                # Process search results to formulate an answer
                answer_parts = []
                for i, result in enumerate(search_results[:3]): # Use top 3 results
                    if result.get('snippet'):
                        answer_parts.append(f"Snippet {i+1}: {result['snippet']}")
                    elif result.get('title'):
                         answer_parts.append(f"Result {i+1} Title: {result['title']}")


                if answer_parts:
                    formulated_answer = "Based on web search:\n" + "\n".join(answer_parts)
                    print(f"Agent returning search-based answer: {formulated_answer[:100]}...")
                    return formulated_answer
                else:
                    print("Web search returned results but no useful snippets/titles found.")
                    return "I couldn't find a specific answer from the web search results."

            else:
                print("Web search returned no results.")
                return "I couldn't find any relevant information on the web for your question."
        else:
            # If no search is needed, return a default or simple response
            print("Question does not appear to require search. Returning fixed answer.")
            fixed_answer = "How can I help you?"
            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
    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
    
    def __init__(self):
        print("BasicAgent initialized.")
    def __call__(self, question: str) -> str:
        print(f"Agent received question (first 50 chars): {question[:50]}...")
        fixed_answer = "How i can help you?"
        print(f"Agent returning fixed answer: {fixed_answer}")
        return fixed_answer



# --- 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)7