app.py

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

# LangChain & LangGraph imports
from langchain_core.messages import BaseMessage, HumanMessage, AIMessage, SystemMessage
from langchain_core.tools import tool
from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

# (Keep Constants as is)
# --- Constants ---
DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"

# --- Tool Definitions ---
@tool
def search_wikipedia(query: str) -> str:
    """Search Wikipedia for information. Use this for factual questions about people, places, events, etc."""
    try:
        import wikipediaapi
        wiki = wikipediaapi.Wikipedia(
            language='en',
            user_agent='MyLangGraphAgent/1.0 (contact: itay@razum.com)'
        )
        page = wiki.page(query)
        if page.exists():
            return page.summary[:500]
        else:
            return f"No Wikipedia page found for '{query}'. Try a different search term."
    except Exception as e:
        return f"Error searching Wikipedia: {str(e)}"

@tool
def web_search(query: str) -> str:
    """Search the web for general information. Use this when Wikipedia is not sufficient."""
    try:
        from ddgs import DDGS
        with DDGS() as ddgs:
            results = list(ddgs.text(query, max_results=3))
            if results:
                formatted = "\n\n".join([
                    f"Title: {r['title']}\nSnippet: {r['body']}\nURL: {r['href']}"
                    for r in results
                ])
                return formatted
            return "No results found."
    except Exception as e:
        return f"Error performing web search: {str(e)}"


@tool
def calculator(expression: str) -> str:
    """Evaluate mathematical expressions. Example: '15 + 27' or '2 * (3 + 4)'."""
    try:
        result = eval(expression, {"__builtins__": {}}, {})
        return str(result)
    except Exception as e:
        return f"Error calculating: {str(e)}"

@tool
def reverse_text(text: str) -> str:
    """Reverse a string of text. Useful for decoding reversed messages."""
    return text[::-1]

@tool
def visit_page(url: str, query: str = "") -> str:
    """Visit a specific URL and extract/summarize content based on a query.
    
    Args:
        url: The URL to visit and extract content from
        query: Optional focus query to guide what information to extract
    
    Returns:
        Summarized content relevant to the query, or full page summary if no query provided
    """
    try:
        from bs4 import BeautifulSoup
        
        headers = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36'
        }
        response = requests.get(url, headers=headers, timeout=10)
        response.raise_for_status()
        
        soup = BeautifulSoup(response.content, 'html.parser')
        
        for script in soup(["script", "style", "nav", "footer", "header"]):
            script.decompose()
        
        text = soup.get_text(separator=' ', strip=True)
        lines = (line.strip() for line in text.splitlines())
        chunks = (phrase.strip() for line in lines for phrase in line.split("  "))
        text = ' '.join(chunk for chunk in chunks if chunk)
        
        max_length = 3000
        if len(text) > max_length:
            text = text[:max_length]
        
        return f"Content from {url}:\n\n{text[:1000]}..."
            
    except requests.Timeout:
        return f"Error: Timeout while trying to access {url}"
    except requests.RequestException as e:
        return f"Error fetching {url}: {str(e)}"
    except Exception as e:
        return f"Error processing {url}: {str(e)}"

# --- LangGraph Agent Definition ---
# ----- THIS IS WHERE YOU CAN BUILD WHAT YOU WANT ------
class LangGraphAgent:
    """LangGraph ReAct agent with tools for question answering."""
    
    def __init__(self):
        print("Initializing LangGraph Agent...")
        
        # Configure LangSmith tracing if API key is available
        if os.getenv("LANGCHAIN_API_KEY"):
            os.environ["LANGCHAIN_TRACING_V2"] = "true"
            os.environ["LANGCHAIN_PROJECT"] = "agent-benchmark-production"
            print("🔍 LangSmith tracing enabled")
        
        # Set up OpenAI LLM
        api_key = os.getenv("OPENAI_API_KEY")
        if not api_key:
            raise ValueError("OPENAI_API_KEY environment variable not set!")
        
        self.llm = ChatOpenAI(
            model="gpt-4o-mini",
            temperature=0,
            api_key=api_key
        )
        
        # Define tools
        self.tools = [search_wikipedia, web_search, calculator, reverse_text, visit_page]
        
        # System prompt
        system_message = SystemMessage(
            content="""You are a helpful AI assistant that can answer questions by using various tools.

When answering questions:
1. Think step-by-step about what information you need
2. Use the appropriate tools to gather information
   - search_wikipedia: For factual questions about people, places, events
   - web_search: For general web searches
   - calculator: For mathematical calculations
   - reverse_text: For reversing text strings
   - visit_page: For extracting content from specific URLs
3. Provide clear, concise, and accurate answers
4. If you're not sure, say so rather than making up information
5. The answer should be short - for example, if asked how many awards someone won, answer with just the number
6. Write only the final answer without extra explanation
7. Simplify complex tasks into subtasks and think about which tool to use for each"""
        )
        
        # Create prompt template
        prompt = ChatPromptTemplate.from_messages([
            system_message,
            MessagesPlaceholder(variable_name="messages")
        ])
        
        # Create ReAct agent
        self.agent = create_react_agent(
            self.llm,
            self.tools,
            prompt=prompt
        )
        
        print(f"✅ Agent initialized with {len(self.tools)} tools")
        print("   Model: gpt-4o-mini")
    
    def __call__(self, question: str) -> str:
        """Process a question and return an answer."""
        print(f"Agent processing question: {question[:100]}...")
        
        try:
            result = self.agent.invoke({
                "messages": [HumanMessage(content=question)]
            })
            
            # Extract final answer
            final_message = result["messages"][-1]
            answer = final_message.content
            
            print(f"Agent answer: {answer[:100]}...")
            return answer
            
        except Exception as e:
            error_msg = f"Error processing question: {str(e)}"
            print(f"❌ {error_msg}")
            return error_msg

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 = LangGraphAgent()
    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)