app.py

from __future__ import annotations


import os
import gradio as gr
import inspect
import pandas as pd
from agents import Agent, Runner, function_tool
from duckduckgo_search import DDGS
from agents import Agent, Runner
from markdownify import markdownify
from duckduckgo_search import DDGS
from bs4 import BeautifulSoup
from pydantic import BaseModel, Field
import nest_asyncio
import requests

#from agents.extensions.models.litellm_model import LitellmModel

os.getenv("OPENAI_API_KEY")
#os.getenv("GEMINI_API_KEY")
os.getenv("TAVILY_API_KEY")


# add this
nest_asyncio.apply()


#Tools

@function_tool
def tavily_search(query: str) -> str:
    """
    Perform a Tavily web search.
    Args:
        query (str): The search query string.
    Returns:
        str: Formatted search results.
    """
    try:
        client = TavilyClient(os.getenv("TAVILY_API_KEY"))
        results = client.search(query=query, max_results=5)

        formatted = []
        for result in results.get("results", []):
            formatted.append(f"**Title**: {result['title']}\n**URL**: {result['url']}\n**Content**: {result['content']}\n")

        return "\n\n".join(formatted) or "No results found."

    except Exception as e:
        return f"Error using Tavily Search: {e}"


@function_tool
def web_search(query: str) -> str:
    """
    Perform a web search.
    Args:
        query (str): The search query string.
    Returns:
        str: The search results formatted in markdown.
    """

    try:
        results = DDGS().text(query, max_results=10)

        if not results:
            raise Exception("No search results found.")

        formatted_results = []
        for i, result in enumerate(results, 1):
            title = result.get("title", "No title available.")
            link = result.get("href", "No link available.")
            snippet = result.get("body", "No description available.")

            entry = "  \n".join([
                f"**Title**: {title}",
                f"**Link**: {link}",
                f"**Snippet**: {snippet}"
            ])

            formatted_results.append(entry)

        return "\n\n".join(formatted_results)

    except Exception as e:
        return f"Error executing the query: {e}"

@function_tool
def visit_website(url: str) -> str:
    """
    Extract the contents of a website.
    Args:
        url (str): The URL of the website to visit.
    Returns:
        str: Formatted markdown ready for LLM consumption.
    """

    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"
    }

    try:
        response = requests.get(url, headers=headers, timeout=10)
        response.raise_for_status()

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

        for tag in soup(['script', 'style', 'nav', 'header', 'footer', 'aside', 'meta']):
            tag.decompose()

        main_content = soup.body
        markdown_text = markdownify(str(main_content), strip=['img', 'iframe', 'script', 'meta', 'button', 'input', 'svg'])

        max_length = 10000
        markdown_text = re.sub(r'\n\s*\n', '\n\n', markdown_text[:max_length])

        return markdown_text

    except requests.RequestException as e:
        return f"Error fetching the website: {e}"




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

        instructions = """
You are a ReAct (Reason-Act-Observe) agent that searches the internet to find accurate answers to questions.
## Available Tools
- **web_search**: Search the web for information
- **visit_website**: Visit specific webpages for detailed content
## Output Format Rules
Your final answer must be **exactly one** of these formats:
- **Single number**: No commas, units, or symbols (unless explicitly requested)
- **Single word/phrase**: No abbreviations (write "Los Angeles" not "LA")  
- **Comma-separated list**: Each item follows the above rules
**Important**: Provide ONLY the final answer - no explanations, markdown, or extra text.
## ReAct Process
Follow this cycle until you find the answer:
**Thought**: [Internal reasoning about your next step]
**Action**: [Single tool call]
**Observation**: [Tool result will appear here]
## Quality Guidelines
- Use multiple sources when possible to verify accuracy
- For recent events, prioritize newer sources
- If information conflicts between sources, use the most authoritative source
- For numerical data, ensure you're using the most current figures
## Before Final Answer
- Internally verify: "Does my answer violate format rules (extra text, wrong units, abbreviations)?"
- Before providing a final answer, always ensure it contains the minimal amount of text possible.
## Examples
- Q: What is 15 + 27? → 42
- Q: What is the capital of France? → Paris
- Q: What are the top 3 most populous US states? → California, Texas, Florida
"""

        my_agent = Agent(
            name="Expert Question Answering Agent",
            instructions=instructions,
            tools = [
                tavily_search,
                visit_website
            ],
            model="gpt-4o-mini"
        )

        result = Runner.run_sync(
            my_agent,
            input=question,
            max_turns=25
        )
        print(f"Agent gave reasons {result}")
        print(f"Agent gave answer (first 50 chars): {result.final_output[:50]}...")
        return result.final_output

#        result = Runner.run_sync(
#                my_agent,
#                input=question,
#               max_turns=25
#           )
#        print("\n--- Intermediate Reasoning ---")
#        for step in result.steps:
#            print("🧠 Thought:", step.thought)
#           print("⚙️ Action:", step.tool_call)
#            print("🔍 Observation:", step.observation)
#           print("-" * 50)

#        print(f"Agent returning fixed answer(first 50 chars): {result.final_output[:50]}...")
#       return result.final_output

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)