app.py

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

from smolagents import CodeAgent, ToolCallingAgent, WebSearchTool, InferenceClientModel, VisitWebpageTool, GoogleSearchTool, WikipediaSearchTool, OpenAIServerModel
from tools import analyze_image, transcribe_audio
from langfuse import get_client
from openinference.instrumentation.smolagents import SmolagentsInstrumentor

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

# --- Agent Definition ---
# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------

class ReasoningAgent:
    """Powerful reasoning agent that can double check answers or provide better context. Uses the deepseek R1 model"""
    def __init__(self):
        model=InferenceClientModel("deepseek-ai/DeepSeek-R1", max_tokens=16192, provider='together')

        with open("prompts/toolcalling_agent.yaml", 'r') as stream:
            prompt_templates = yaml.safe_load(stream)
        
        self.agent = ToolCallingAgent(
            tools=[
                VisitWebpageTool(),
                WebSearchTool()
            ],
            model=model,
            add_base_tools=True,
            planning_interval=5,
            max_steps=10,
            name="thinker_agent",
            description="Uses the deepseek R1 model to perform more in depth reasoning. Also has access to basic search tools. Use this agent to double check complex logic or check for things you might have missed.",
            prompt_templates=prompt_templates,
        )

    def __call__(self, prompt: str) -> str:
            agent_answer = self.thinker_agent.run(prompt)
            print(f"Managed agent answer: {agent_answer}")
            return agent_answer
        
    
class MasterAgent:
    def __init__(self):
        
        model = OpenAIServerModel(
            model_id='Qwen/Qwen2.5-Coder-7B-Instruct-GPTQ-Int4',  # Match vLLM model
            api_base='http://localhost:8000/v1',  # vLLM container endpoint
            api_key='c9d522a59f485fee4355d8b27135d73f888c94020f1b8c9ed55146237e1c2feb',  # vLLM API key
            max_tokens=2096,  # Pass as kwargs for OpenAI client
            temperature=0.5,  # Pass as kwargs
            custom_role_conversions=None,
            client_kwargs=None  # Avoid unexpected parameters
        )
        with open("prompts/code_agent.yaml", 'r') as stream:
            prompt_templates = yaml.safe_load(stream)
        
        custom_instructions = """
        Call the thinker managed agent to double check any answer and formatting before calling final answer. Change formatting to anything it suggests.
        """

        try:
            thinker=ReasoningAgent()
        except Exception as e:
            print(f"Error instantiating agent: {e}")
            return f"Error initializing agent: {e}", None

        print("Starting instantiation of master")
        self.master_agent = CodeAgent(
            tools=[
                VisitWebpageTool(),
                #WebSearchTool(),
                WikipediaSearchTool(),
                analyze_image,
                transcribe_audio,
                GoogleSearchTool("serpapi")
            ],
            model=model,
            planning_interval=6,
            max_steps=20,
            managed_agents=[thinker.agent],
            prompt_templates=prompt_templates,
            additional_authorized_imports=[
                "json",
                "pandas",
                "numpy",
            ],
            instructions=custom_instructions,
        )
        
        print("MasterAgent initialized.")
    
    def __call__(self, question: str, attached_file: str) -> str:
        """"""
        print(f"Agent received question (first 50 chars): {question[:50]}...")

        additional_args = {}
        if attached_file:
            additional_args = {
                "attached_file": attached_file
            }
            question = question + f" attached_file can be accessed locally at './file_cache/{attached_file}' or at the public URL {DEFAULT_API_URL}/files/{os.path.splitext(attached_file)[0]}"
            
        agent_answer = self.master_agent.run(question, additional_args=additional_args)
        print(f"Agent answer: {agent_answer}")
        return agent_answer

        
def run_and_submit_all( profile: gr.OAuthProfile | None):
    """
    Fetches all questions, runs the MasterAgent 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"
    #questions_url = f"{api_url}/random-question"
    submit_url = f"{api_url}/submit"

    # 1. Instantiate Agent ( modify this part to create your agent)
    try:
        agent = MasterAgent()
    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 ( useful 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() # REMOVE BRACKETS WHEN SWITCHING TO ALL QUESTIONS
        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...")

    cache_dir = "file_cache"
    if not os.path.exists(cache_dir):
        os.makedirs(cache_dir)

    answers_dir = "answers_cache"
    if not os.path.exists(answers_dir):
        os.makedirs(answers_dir)
    
    for item in questions_data:
        task_id = item.get("task_id")
        question_text = item.get("question")
        submitted_answer = None

        task_answer_path = os.path.join(answers_dir, task_id + '.yaml')
        if os.path.exists(task_answer_path):
            print(f"Found existing answer for task {task_id}, loading")
            with open(task_answer_path, 'r') as stream:
                task_answer = yaml.safe_load(stream)

            try:
                submitted_answer = task_answer.get("submitted_answer")
            except Exception as e:
                print(f"Existing answer for task {task_id} is invalid.")
        
        attached_file = item.get("file_name")
        if attached_file != "":
            local_file_path = os.path.join(cache_dir, attached_file)
            if not os.path.exists(local_file_path):
                file_name_no_ext = os.path.splitext(attached_file)[0]  # e.g., 'document' from 'document.pdf'
                download_url = f"{api_url}/files/{file_name_no_ext}"

                try:
                    print(f"Downloading from {download_url}")
                    response = requests.get(download_url, stream=True)
                    response.raise_for_status()  # Raises an HTTPError for bad responses
                    with open(local_file_path, 'wb') as f:
                        for chunk in response.iter_content(chunk_size=8192):
                            if chunk:
                                f.write(chunk)
                    print(f"File downloaded and cached: {local_file_path}")
                
                except requests.exceptions.HTTPError as e:
                    print(f"HTTP error downloading {download_url}: {e}")
                except requests.exceptions.RequestException as e:
                    print(f"Error downloading {download_url}: {e}")
                except OSError as e:
                    print(f"Error saving file to {local_file_path}: {e}")
        
        if not task_id or question_text is None:
            print(f"Skipping item with missing task_id or question: {item}")
            continue
        try:
            if not submitted_answer:
                agent_text = agent(question_text, attached_file)
                submitted_answer = str(agent_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})

            with open(task_answer_path, 'w') as file:
                yaml.dump({"task_id": task_id, "question_text": question_text, "submitted_answer": submitted_answer}, file)
            
        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("# 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

    # Instrumentation
    langfuse = get_client()
    if langfuse.auth_check():
        print("Langfuse client is authenticated and ready!")
    else:
        print("Authentication failed. Please check your credentials and host.")
    SmolagentsInstrumentor().instrument()


    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 Agent Evaluation...")
    demo.launch(debug=True, share=False)