app.py

import os
import gradio as gr
import requests
import inspect
import pandas as pd
from langgraph.prebuilt import ToolNode, create_react_agent
from tools import web_search, parse_excel, ocr_image

# from typing import Any, Dict
# from typing import TypedDict, Annotated

from langchain_openai import ChatOpenAI
from langgraph.graph import StateGraph, START, END
from langgraph.graph.message import add_messages
from langchain.schema import HumanMessage, AIMessage, SystemMessage
# Create a ToolNode that knows about your web_search function
import json

def parse_tool_json(text: str) -> dict | None:
    """
    Given a string like '{"tool":"web_search","query":"..."}'
    or '"{\"tool\":\"web_search\",\"query\":\"...\"}"', return
    the parsed dict. Otherwise, return None.
    """
    t = text.strip()
    # If it’s wrapped in single or double quotes, remove them:
    if (t.startswith('"') and t.endswith('"')) or (t.startswith("'") and t.endswith("'")):
        t = t[1:-1]
    try:
        obj = json.loads(t)
        if isinstance(obj, dict) and "tool" in obj:
            return obj
    except Exception:
        return None
    return None


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


llm = ChatOpenAI(model_name="gpt-4.1-mini", temperature=0.0)
tool_node = ToolNode([ocr_image, parse_excel, web_search])
agent = create_react_agent(model=llm, tools=tool_node)

# 2) Build a two‐edge graph:
graph = StateGraph(dict)
graph.add_node("agent", agent)
graph.add_edge(START, "agent")
graph.add_edge("agent", END)
compiled_graph = graph.compile()

def respond_to_input(user_input: str) -> str:
    """
    Wrap compiled_graph.invoke(…) (and the “second pass”) in a try/except
    so that if the agent ever returns something unparsable (a plain str),
    we catch it and avoid the `'str' object has no attribute 'items'` error.
    """

    # A) Build a SystemMessage that forces the model to emit bare JSON if it calls a tool:
    system_msg = SystemMessage(
        content=(
            "You are an assistant with access to exactly these tools:\n"
            "  1) web_search(query:str)\n"
            "  2) parse_excel(path:str,sheet_name:str)\n"
            "  3) ocr_image(path:str)\n\n"
            "⚠️ **IMPORTANT** ⚠️: If (and only if) you need to call a tool, "
            "output exactly one JSON object and nothing else. For example:\n"
            "```json\n"
            '{"tool":"web_search","query":"Mercedes Sosa albums 2000-2009"}\n'
            "```\n"
            "That JSON must start at the very first character of your response and end at the very last character—"
            "no quotes, no code fences, and no extra explanation.\n\n"
            "If you do NOT need any tool, simply reply with your final answer as plain text."
        )
    )

    # B) Initialize state with just that SystemMessage. We'll pass user_input separately below:
    initial_state = { "messages": [system_msg] }

    try:
        # C) First pass: invoke the graph with the user’s question:
        final_state = compiled_graph.invoke(initial_state, user_input)

        # D) Log every AIMessage for debugging (optional—remove in production):
        print("===== AGENT MESSAGES (First Pass) =====")
        for i, msg in enumerate(final_state["messages"]):
            if isinstance(msg, AIMessage):
                print(f"[AIMessage #{i}]: {repr(msg.content)}")
        print("=========================================")

        # E) Find the very last AIMessage the agent produced:
        last_msg = None
        for msg in reversed(final_state["messages"]):
            if isinstance(msg, AIMessage):
                last_msg = msg.content
                break

        # F) Try to parse that last_msg as a tool‐call JSON:
        tool_dict = parse_tool_json(last_msg or "")
        if tool_dict:
            # G) If valid JSON, run the tool:
            print(">> Parsed tool call:", tool_dict)
            tool_result = tool_node.run(tool_dict)

            # H) Log output of the tool (optional):
            print(f">> Tool '{tool_dict['tool']}' returned: {repr(tool_result)}")

            # I) Second pass: feed the tool’s result back into the graph,
            #    with an empty user_input because we’re continuing the same turn.
            continuation_state = {
                "messages": [
                    *final_state["messages"],
                    AIMessage(content=tool_result)
                ]
            }
            second_pass = compiled_graph.invoke(continuation_state, "")

            # J) Log every AIMessage from the second pass (optional):
            print("===== AGENT MESSAGES (Second Pass) =====")
            for i, msg in enumerate(second_pass["messages"]):
                if isinstance(msg, AIMessage):
                    print(f"[AIMessage2 #{i}]: {repr(msg.content)}")
            print("=========================================")

            # K) Return the last AIMessage from the second pass as the final answer:
            for msg in reversed(second_pass["messages"]):
                if isinstance(msg, AIMessage):
                    return msg.content or ""
            return ""

        else:
            # L) If it wasn’t valid JSON, just treat last_msg as plain‐text final answer:
            return last_msg or ""

    except Exception as e:
        # M) If *any* part of the above raises (e.g. because the LLM returned a string
        #    that the routing layer tried to treat as a dict), we catch it here:
        print(f"‼️ respond_to_input error: {repr(e)}")
        return ""  # or return a default fallback string if you prefer


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 respond_to_input(question)
        # return fixed_answer






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("LangGraph version:", langgraph.__version__) 
    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
    # import langgraph
    # print("▶︎ LangGraph version:", langgraph.__version__)
    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)