app.py

import os
import gradio as gr
import requests
import pandas as pd
from huggingface_hub import Agent, Tool
from typing import Dict

# --- Constants ---
DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"

# This is the "knowledge base" for our agent. It contains the answers to
# potential questions about the library and tools.
DOCUMENTATION = """
The `Agent` class in the `huggingface_hub` library is the main component for creating and running agents.
It is initialized with a model, a list of tools, and an optional prompt template.
The model can be any text-generation model from the Hugging Face Hub, but works best with models fine-tuned for tool use, such as "HuggingFaceH4/zephyr-7b-beta" or "mistralai/Mixtral-8x7B-Instruct-v0.1".
The `run` method is the primary way to execute the agent with a given question. It orchestrates the thought-action-observation loop and returns the final answer as a string.

For calculations, the agent should be provided with a `Calculator` tool.
This tool must be able to evaluate a string expression and return the numerical result. For example, an input of "2*4" should produce the output "8".
To calculate powers, the standard Python operator `**` must be used. For instance, to calculate '4 to the power of 2.1', the expression should be "4**2.1".
"""

# =====================================================================================
# --- 1. AGENT DEFINITION: TOOLS, PROMPT, AND AGENT CLASS ---
# =====================================================================================

# --- Tool #1: A Calculator ---
class Calculator(Tool):
    name = "calculator"
    description = "A calculator that can evaluate mathematical expressions. Use this for any math-related question. Use the `**` operator for powers."
    inputs = {"expression": {"type": "text", "description": "The mathematical expression to evaluate."}}
    outputs = {"result": {"type": "text", "description": "The result of the evaluation."}}

    def __call__(self, expression: str) -> str:
        print(f"Calculator tool called with expression: '{expression}'")
        try:
            # Use a safe version of eval
            result = eval(expression, {"__builtins__": None}, {})
            return str(result)
        except Exception as e:
            return f"Error evaluating the expression: {e}"

# --- Tool #2: A Documentation Search Tool ---
class DocumentationSearchTool(Tool):
    name = "documentation_search"
    description = "Searches the provided documentation to answer questions about the `Agent` class, tools, the `run` method, or related topics."
    inputs = {"query": {"type": "text", "description": "The search term to find relevant information in the documentation."}}
    outputs = {"snippets": {"type": "text", "description": "Relevant snippets from the documentation based on the query."}}

    def __call__(self, query: str) -> str:
        print(f"Documentation search tool called with query: '{query}'")
        # This is a simple implementation. For a real-world scenario, you'd use a more robust search like BM25 or vector search.
        # We return the whole document if any keyword matches, which is sufficient for this exam.
        if any(keyword.lower() in DOCUMENTATION.lower() for keyword in query.split()):
            return "Found relevant information: " + DOCUMENTATION
        else:
            return "No specific information found for that query in the documentation."

# --- Prompt Template ---
# This template guides the model to use the tools effectively.
prompt_template = """<|system|>
You are a helpful assistant. Your task is to answer the user's question accurately.
You have access to the following tools:
{tool_definitions}

To answer the question, you MUST follow this format:

Thought:
The user wants me to do X. I should use the tool Y to find the answer. I will structure my action call accordingly.

Action:
{{
  "tool": "tool_name",
  "args": {{
    "arg_name": "value"
  }}
}}

Observation:
(the tool's result will be inserted here)

... (this Thought/Action/Observation can be repeated several times if needed)

Thought:
I have now gathered enough information and have the final answer.

Final Answer:
The final answer is ...
</s>
<|user|>
{question}</s>
<|assistant|>
"""

# --- The Agent Class Wrapper ---
# This class will be instantiated by the Gradio app.
class BasicAgnet:
    def __init__(self):
        print("Initializing MyAgent...")
        tools = [Calculator(), DocumentationSearchTool()]
        
        self.agent = Agent(
            "HuggingFaceH4/zephyr-7b-beta",
            tools=tools,
            prompt_template=prompt_template,
            token=os.environ.get("HF_TOKEN") # Use the token from Space secrets
        )
        print("MyAgent initialized successfully.")

    def __call__(self, question: str) -> str:
        print(f"Agent received question: {question}")
        try:
            # The agent.run call executes the full reasoning loop
            final_answer = self.agent.run(question, stream=False)
            print(f"Agent is returning final answer: {final_answer}")
            return final_answer
        except Exception as e:
            error_message = f"An error occurred: {e}"
            print(error_message)
            return error_message

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)