app.py

import os
import gradio as gr
import requests
import inspect
import pandas as pd
from google import genai
from google.genai import types
import time
from smolagents import CodeAgent, DuckDuckGoSearchTool, WikipediaSearchTool, PythonInterpreterTool, FinalAnswerTool, LiteLLMModel, tool


# (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]}...")
#         fixed_answer = "This is a default answer."
#         print(f"Agent returning fixed answer: {fixed_answer}")
#         return fixed_answer

# class GeminiModel:
#     def __init__(self, model_name="gemini-2.0-flash-exp"):
#         api_key = os.getenv("GEMINI_API_KEY")
#         if not api_key:
#             raise ValueError("GEMINI_API_KEY is missing.")

#         os.environ["GOOGLE_API_KEY"] = api_key
#         self.client = genai.Client()
#         self.model_id = model_name

#         self.generation_config = types.GenerateContentConfig(
#             temperature=0.4,
#             top_p=0.9,
#             top_k=40,
#             candidate_count=1,
#             seed=42,
#             presence_penalty=0.0,
#             frequency_penalty=0.0,
#         )

#     def __call__(self, prompt: str, **kwargs) -> str:
#         """Send prompt to Gemini."""
#         try:
#             response = self.client.generate_content(
#                 model=self.model_id,
#                 contents=[{"role": "user", "parts": [{"text": prompt}]}],
#                 generation_config=self.generation_config
#             )
#             # Return a dictionary that CodeAgent expects
#             return {"content": response.candidates[0].content.parts[0].text.strip()}
#         except Exception as e:
#             return {"content": f"Error during Gemini call: {str(e)}"}

# # Define BasicAgent properly
# class BasicAgent:
#     def __init__(self):
#         print("Initializing CodeAgent with Gemini + tools.")

#         # Load tools
#         self.search_tool = DuckDuckGoSearchTool()

#         # Build the agent
#         self.agent = CodeAgent(
#             tools=[self.search_tool],
#             model=GeminiModel(),  # Our simple Gemini wrapper
#             planning_interval=3  # Activate planning
#         )

#     def __call__(self, question: str) -> str:
#         """Call the CodeAgent."""
#         print(f"Running agent for task: {question[:50]}...")
#         try:
#             result = self.agent.run(question)

#             # Sleep to respect rate limits
#             time.sleep(7)
#             return result
#         except Exception as e:
#             return f"Error running agent: {str(e)}"
            
# class BasicAgent(ReActAgent):
#     def __init__(self):
#         print("BasicAgent using local LLM initialized.")

#         # Load a small model from Hugging Face
#         model_name = "TinyLlama/TinyLlama-1.1B-Chat-v1.0"  
#         self.tokenizer = AutoTokenizer.from_pretrained(model_name)
#         self.model = AutoModelForCausalLM.from_pretrained(
#             model_name,
#             torch_dtype=torch.float16,
#             device_map="auto"  # Automatically choose GPU/CPU
#         )

#         super().__init__(tools=[])  # No tools for now

#     def call(self, task: str) -> str:
#         """Core method for answering a task."""
#         prompt = f"Answer the following question concisely:\n\n{task}\n\nAnswer:"
#         inputs = self.tokenizer(prompt, return_tensors="pt").to(self.model.device)

#         with torch.no_grad():
#             outputs = self.model.generate(
#                 **inputs,
#                 max_new_tokens=200,
#                 do_sample=True,
#                 temperature=0.7,
#                 top_p=0.95,
#                 top_k=50,
#             )
#         answer = self.tokenizer.decode(outputs[0], skip_special_tokens=True)

#         # Extract only the answer part
#         return answer.split("Answer:")[-1].strip()

# class BasicAgent:
#     def __init__(self):
#         print("BasicAgent using local LLM initialized.")

#         # Load a small Hugging Face model
#         model_name = "TinyLlama/TinyLlama-1.1B-Chat-v1.0"  # Change if you want
#         self.tokenizer = AutoTokenizer.from_pretrained(model_name)
#         self.model = AutoModelForCausalLM.from_pretrained(
#             model_name,
#             torch_dtype=torch.float16,
#             device_map="auto"  # Use GPU if available
#         )

#     def __call__(self, task: str) -> str:
#         """Answer a question."""
#         prompt = f"Answer the following question clearly and concisely:\n\n{task}\n\nAnswer:"
#         inputs = self.tokenizer(prompt, return_tensors="pt").to(self.model.device)

#         with torch.no_grad():
#             outputs = self.model.generate(
#                 **inputs,
#                 max_new_tokens=256,
#                 do_sample=True,
#                 temperature=0.7,
#                 top_p=0.9,
#                 top_k=50,
#             )
#         decoded = self.tokenizer.decode(outputs[0], skip_special_tokens=True)

#         # Extract the answer part
#         if "Answer:" in decoded:
#             return decoded.split("Answer:")[-1].strip()
#         return decoded.strip()



# # Setup Gemini Client
# api_key = os.getenv("GEMINI_API_KEY")
# if not api_key:
#     raise ValueError("GEMINI_API_KEY is missing.")
# os.environ["GOOGLE_API_KEY"] = api_key
# client = genai.Client()
# model_id = "gemini-2.0-flash-exp"

# generation_config = types.GenerateContentConfig(
#     temperature=0.4,
#     top_p=0.9,
#     top_k=40,
#     candidate_count=1,
#     seed=42,
#     presence_penalty=0.0,
#     frequency_penalty=0.0,
# )

@tool
def reverse_string(input_string: str) -> str:
    return input_string[::-1]
    
# Define the real agent
class BasicAgent:
    def __init__(self):
        print("Improved BasicAgent initialized with Gemini and enhanced tools.")

        # Load Gemini through LiteLLM (ensure GEMINI_API_TOKEN is set)
        self.model = LiteLLMModel(
            model_id="gemini/gemini-2.0-flash-lite",
            api_key=os.getenv("GEMINI_API_TOKEN"),
        )

        # Setup CodeAgent with tools
        self.agent = CodeAgent(
            tools=[
                DuckDuckGoSearchTool(),
                WikipediaSearchTool(),
                PythonInterpreterTool(),
                FinalAnswerTool(),
                reverse_string,
            ],
            model=self.model,
            max_steps=10,
            add_base_tools=True,
            additional_authorized_imports=["pandas", "*"]
        )

    def __call__(self, question: str) -> str:
        """Main callable for processing questions with rate limiting."""
        print(f"Running agent for task: {question[:50]}...")

        # Prompt with strict output formatting
        system_instruction = (
            "I will ask you a question. Report your thoughts step by step. "
            "Finish your answer only with the final answer. In the final answer don't write explanations. "
            "The answer should be a number OR as few words as possible OR a comma separated list of numbers and/or strings. "
            "Avoid units, abbreviations, or articles unless specified. "
            "Pay attention to each sentence in the question and verify the answer against every part. "
            "Try searching more sources if initial results are insufficient.\nQUESTION: "
        )

        prompt = system_instruction + question
        try:
            result = self.agent.run(prompt)
        except Exception as e:
            result = f"Error: {str(e)}"

        # Rate limiting to avoid 429 errors or API limits
        print("Waiting 3 seconds to respect rate limits...")
        time.sleep(3)

        return result
            
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)