eval.py

import os
import gradio as gr
import requests
import inspect
import pandas as pd
from dotenv import load_dotenv
from langchain_core.messages import HumanMessage
from agent import build_graph

load_dotenv()

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

# Debug Environment
print("--- Environment Debug ---")
print(f"SPACE_ID: {os.getenv('SPACE_ID')}")
print(f"SPACE_HOST: {os.getenv('SPACE_HOST')}")
print(f"HF_TOKEN present: {bool(os.getenv('HF_TOKEN'))}")
print(f"Gradio Version: {gr.__version__}")
print("-------------------------")

# CRITICAL FIX: Derive SPACE_ID from SPACE_HOST if not set
# HF Spaces sets SPACE_HOST (e.g., "vinhle-first-agent-template.hf.space")
# but not always SPACE_ID in Docker containers
if not os.getenv("SPACE_ID") and os.getenv("SPACE_HOST"):
    space_host = os.getenv("SPACE_HOST")
    # Parse: "username-spacename.hf.space" -> "username/spacename"
    if space_host.endswith(".hf.space"):
        space_slug = space_host.replace(".hf.space", "")
        # Convert "vinhle-first-agent-template" to "vinhle/first_agent_template"
        parts = space_slug.split("-", 1)  # Split on first hyphen only
        if len(parts) == 2:
            username, space_name = parts
            space_id = f"{username}/{space_name.replace('-', '_')}"
            os.environ["SPACE_ID"] = space_id
            print(f"✅ Derived SPACE_ID from SPACE_HOST: {space_id}")
        else:
            print(f"⚠️ Could not parse SPACE_HOST: {space_host}")


# Display configured model
try:
    import json
    with open("agent.json", "r") as f:
        config = json.load(f)
    model_config = config.get("model", {}).get("data", {})
    model_id = model_config.get("model_id", "Unknown")
    base_url = model_config.get("base_url", "Unknown")
    print(f"\n🤖 Configured Model: {model_id}")
    print(f"   Provider: {base_url}")
    print()
except Exception as e:
    print(f"⚠️ Could not load model config: {e}\n")


# --- Basic Agent Definition ---
class BasicAgent:
    def __init__(self):
        print("BasicAgent initialized.")
        # Initialize the graph with the desired provider. 
        # We default to 'google' which should be configured in agent.py
        try:
            self.graph = build_graph()
            print("Graph built successfully.")
        except Exception as e:
            print(f"Error building graph: {e}")
            self.graph = None

    def __call__(self, question: str) -> str:
        print(f"Agent received question (first 50 chars): {question[:50]}...")
        if not self.graph:
            return "Error: Agent graph not initialized."
        
        try:
            messages = [HumanMessage(content=question)]
            result = self.graph.invoke({"messages": messages})
            # content is the response from the agent
            content = result["messages"][-1].content
            
            # Clean up response if it's a list
            if isinstance(content, list):
                content = " ".join([str(item) for item in content])
            
            # DEBUG: Show full raw response (first 500 chars)
            print(f"Raw model response: {content[:500]}...")
            
            # Extract ONLY the final answer
            import re
            original_content = content
            
            # Strategy 1: Look for "FINAL ANSWER:" (case-insensitive) and extract everything after it
            final_answer_match = re.search(r'FINAL\s+ANSWER:\s*(.+?)(?:\s*</think>|$)', content, re.IGNORECASE | re.DOTALL)
            if final_answer_match:
                content = final_answer_match.group(1).strip()
                print("✅ Extracted using FINAL ANSWER pattern")
            else:
                # Strategy 2: If no "FINAL ANSWER:", try to extract text after </think> tag
                think_match = re.search(r'</think>\s*(.+)$', content, re.DOTALL)
                if think_match:
                    content = think_match.group(1).strip()
                    print("✅ Extracted text after </think> tag")
                else:
                    # Strategy 3: Remove all <think>...</think> blocks entirely
                    content = re.sub(r'<think>.*?</think>', '', content, flags=re.DOTALL).strip()
                    print("✅ Removed <think> blocks")
                    
                    # If nothing remains, the model didn't follow format - return error
                    if not content:
                        print("⚠️ Model output only contained reasoning, no answer found!")
                        return "ERROR: Model did not provide a final answer"
            
            # Remove any remaining XML-like tags
            content = re.sub(r'<[^>]+>', '', content).strip()
            
            # Remove any leading "Answer:" or "Final Answer:" that might remain
            content = re.sub(r'^(Final\s+)?Answer:\s*', '', content, flags=re.IGNORECASE).strip()
            
            print(f"📤 Submitting answer: '{content}'")
            return content
        except Exception as e:
            error_msg = str(e)
            # Check if it's a rate limit error
            if "429" in error_msg or "rate limit" in error_msg.lower():
                print(f"⚠️ Rate limit exceeded (429): {e}")
                return "ERROR: Rate limit exceeded"
            else:
                print(f"Error invoking agent: {e}")
                return f"Error: {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") 
    
    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...")
    
    # Add delay between requests to avoid rate limiting
    import time
    DELAY_BETWEEN_REQUESTS = 3  # seconds - adjust as needed
    
    for idx, item in enumerate(questions_data, 1):
        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
        
        print(f"\n📝 Processing question {idx}/{len(questions_data)}...")
        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}"})
        
        # Add delay between requests (except after the last one)
        if idx < len(questions_data):
            print(f"⏳ Waiting {DELAY_BETWEEN_REQUESTS}s before next request to avoid rate limiting...")
            time.sleep(DELAY_BETWEEN_REQUESTS)


    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(server_name="0.0.0.0", server_port=7860, debug=True)