app.py

import os
import gradio as gr
import requests
import inspect
import pandas as pd
import re
import math
import json
import unicodedata
from typing import TypedDict, Annotated, Any, List, Optional
 
from huggingface_hub import InferenceClient
 
from langchain_core.messages import AnyMessage, HumanMessage, SystemMessage, AIMessage, ToolMessage
from langchain_core.tools import tool
from langchain_community.tools import DuckDuckGoSearchRun
from langchain_community.utilities import WikipediaAPIWrapper
 
from langgraph.graph import START, StateGraph
from langgraph.graph.message import add_messages
from langgraph.prebuilt import ToolNode, tools_condition

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

@tool
def web_search(query: str) -> str:
    """Search the web using DuckDuckGo. Use for current events, facts, and general knowledge."""
    try:
        return DuckDuckGoSearchRun().run(query)
    except Exception as e:
        return f"Search error: {e}"
 
 
@tool
def wikipedia_search(query: str) -> str:
    """Search Wikipedia for encyclopedic knowledge, historical facts, biographies, science."""
    try:
        wiki = WikipediaAPIWrapper(top_k_results=2, doc_content_chars_max=3000)
        return wiki.run(query)
    except Exception as e:
        return f"Wikipedia error: {e}"
 
 
@tool
def python_repl(code: str) -> str:
    """
    Execute Python code for math calculations, data processing, logic.
    Always use print() to show the result.
    Example: print(2 + 2)
    """
    import io, sys
    old_stdout = sys.stdout
    sys.stdout = io.StringIO()
    try:
        exec(code, {"math": math, "json": json, "re": re,
                    "unicodedata": unicodedata, "__builtins__": __builtins__})
        output = sys.stdout.getvalue()
        return output.strip() if output.strip() else "Code executed with no output. Use print()."
    except Exception as e:
        return f"Code error: {e}"
    finally:
        sys.stdout = old_stdout
 
 
@tool
def calculator(expression: str) -> str:
    """
    Evaluate a simple math expression.
    Examples: '2 + 2', '100 * 1.07 ** 5', 'math.sqrt(144)'
    """
    try:
        return str(eval(expression, {"math": math, "__builtins__": {}}))
    except Exception as e:
        return f"Calculation error: {e}"
 
 
@tool
def get_task_file(task_id: str) -> str:
    """
    Fetch the file attached to a GAIA task by its task_id.
    Use this when the question mentions an attached file or document.
    """
    try:
        import requests as req
        url = f"https://agents-course-unit4-scoring.hf.space/files/{task_id}"
        response = req.get(url, timeout=15)
        if response.status_code == 200:
            ct = response.headers.get("Content-Type", "")
            if "text" in ct or "json" in ct:
                return response.text[:5000]
            return f"[Binary file - content-type: {ct}]"
        return f"No file found for task {task_id}"
    except Exception as e:
        return f"Error fetching task file: {e}"
 


class AgentState(TypedDict):
    messages: Annotated[list[AnyMessage], add_messages]

SYSTEM_PROMPT = """You are a precise expert AI solving GAIA benchmark questions.
 
## Answer Format (CRITICAL)
- Give ONLY the bare answer: a number, word, name, date, or short phrase.
- NO explanations, NO punctuation at the end, NO "The answer is...".
- Correct examples: `42`, `Marie Curie`, `Paris`, `1969`, `blue`
- For lists: `item1, item2, item3`
 
## Strategy
1. Read carefully — identify exactly what is asked.
2. Use tools to find and verify the answer.
3. Double-check calculations with calculator or python_repl.
4. If the question mentions a file or attachment, use get_task_file.
 
## Final Answer
Always end with:
FINAL ANSWER: <your answer here>
"""

def _tool_to_openai_schema(t) -> dict:
    """Converte un LangChain tool nel formato tool OpenAI."""
    return {
        "type": "function",
        "function": {
            "name": t.name,
            "description": t.description,
            "parameters": t.args_schema.schema() if t.args_schema else {"type": "object", "properties": {}},
        }
    }

# --- Basic Agent Definition ---
# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
class BasicAgent:
    def __init__(self):
        print("Initializing agent with HF InferenceClient...")
 
        self.tools_list = [
            web_search,
            wikipedia_search,
            python_repl,
            calculator,
            get_task_file,
        ]
 
        # Mappa nome → funzione tool per esecuzione
        self.tools_by_name = {t.name: t for t in self.tools_list}
 
        # InferenceClient diretto — usa la Serverless Inference API HF
        self.client = InferenceClient(
            api_key=os.getenv("HF_TOKEN"),
        )
         
        # Schema OpenAI dei tool per passarli al client
        self.tools_schema = [_tool_to_openai_schema(t) for t in self.tools_list]
 
        # Grafo LangGraph per gestire il loop ReAct
        builder = StateGraph(AgentState)
        builder.add_node("assistant", self._assistant_node)
        builder.add_node("tools", ToolNode(self.tools_list))
        builder.add_edge(START, "assistant")
        builder.add_conditional_edges("assistant", tools_condition)
        builder.add_edge("tools", "assistant")
        self.graph = builder.compile()
 
        print("Agent ready.")
 
    def _messages_to_hf_format(self, messages: list) -> list:
        """Converte messaggi LangChain nel formato dict che InferenceClient si aspetta."""
        result = []
        for m in messages:
            if isinstance(m, SystemMessage):
                result.append({"role": "system", "content": m.content})
            elif isinstance(m, HumanMessage):
                result.append({"role": "user", "content": m.content})
            elif isinstance(m, AIMessage):
                msg = {"role": "assistant", "content": m.content or ""}
                # Includi tool_calls se presenti
                if m.tool_calls:
                    msg["tool_calls"] = [
                        {
                            "id": tc["id"],
                            "type": "function",
                            "function": {
                                "name": tc["name"],
                                "arguments": json.dumps(tc["args"]),
                            }
                        }
                        for tc in m.tool_calls
                    ]
                result.append(msg)
            elif isinstance(m, ToolMessage):
                result.append({
                    "role": "tool",
                    "tool_call_id": m.tool_call_id,
                    "content": m.content,
                })
        return result
 
    def _assistant_node(self, state: AgentState):
        """Nodo assistant: chiama InferenceClient con i tool e restituisce la risposta."""
        sys_msg = SystemMessage(content=SYSTEM_PROMPT)
        hf_messages = self._messages_to_hf_format([sys_msg] + state["messages"])
 
        response = self.client.chat_completion(
            model="Qwen/Qwen2.5-7B-Instruct",            
            messages=hf_messages,
            tools=self.tools_schema,
            tool_choice="auto",
            max_tokens=512,
            temperature=0,
        )
 
        choice = response.choices[0].message
 
        # Costruisci AIMessage compatibile con LangGraph
        tool_calls = []
        if choice.tool_calls:
            for tc in choice.tool_calls:
                tool_calls.append({
                    "id": tc.id,
                    "name": tc.function.name,
                    "args": json.loads(tc.function.arguments),
                    "type": "tool_call",
                })
 
        ai_message = AIMessage(
            content=choice.content or "",
            tool_calls=tool_calls,
        )
        return {"messages": [ai_message]}
 
    def __call__(self, question: str) -> str:
        print(f"Agent received question (first 50 chars): {question[:50]}...")
        try:
            result = self.graph.invoke({
                "messages": [HumanMessage(content=question)]
            })
            last_message = result["messages"][-1].content
            print(f"Agent raw output: {last_message[:200]}...")
 
            # Estrai FINAL ANSWER se presente, altrimenti ultima riga
            match = re.search(r"FINAL ANSWER:\s*(.+?)(?:\n|$)", last_message, re.IGNORECASE)
            answer = match.group(1).strip() if match else last_message.strip().split("\n")[-1]
 
            print(f"Agent returning answer: {answer}")
            return answer
        except Exception as e:
            print(f"Agent error: {e}")
            return f"AGENT 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") # 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)