import requests
import os
import gradio as gr
import inspect
import pandas as pd
import time
import re

# === TOOLS SECTION (scalone z helper.py) ===

from langchain_experimental.utilities import PythonREPL
from langchain.tools import Tool

# 1. Python REPL Tool
python_repl = PythonREPL()
repl_tool = Tool(
    name="python_repl",
    description="""
    A Python REPL (Read-Eval-Print Loop) for executing Python code.
    Use this tool for:
    - Performing accurate calculations (arithmetic, complex math).
    - Manipulating and analyzing data (e.g., lists, numbers).
    - Executing small, self-contained Python scripts.
    Input MUST be valid Python code, and all outputs must be printed.
    """,
    func=python_repl.run,
)

# 2. File Saver Tool
def download_and_save_file(args: dict) -> str:
    """
    Downloads a file from a given URL and saves it to a specified local filename.
    Input: JSON string with 'url' and 'local_filename' keys.
    Example: {"url": "https://example.com/data.xlsx", "local_filename": "data.xlsx"}
    """
    try:
        if isinstance(args, str):
            import json
            args = json.loads(args)
        url = args.get("url")
        local_filename = args.get("local_filename")
        if not url or not local_filename:
            return "Error: Both 'url' and 'local_filename' must be provided."
        response = requests.get(url, stream=True, timeout=30)
        response.raise_for_status()
        os.makedirs(os.path.dirname(local_filename) or '.', exist_ok=True)
        with open(local_filename, 'wb') as f:
            for chunk in response.iter_content(chunk_size=8192):
                f.write(chunk)
        return f"File downloaded successfully to {local_filename}"
    except Exception as e:
        return f"An unexpected error occurred: {e}"

file_saver_tool = Tool(
    name="file_saver",
    description="Downloads a file from a URL and saves it to a specified local filename. Input: JSON with 'url' and 'local_filename'.",
    func=download_and_save_file,
)

# 3. Audio Transcriber Tool
import speech_recognition as sr
from pydub import AudioSegment

def transcribe_audio_from_path(local_audio_path: str, language: str = "en-US") -> str:
    """
    Transcribes audio content from a local file path to text.
    Only local file paths. Converts to WAV if needed.
    """
    r = sr.Recognizer()
    temp_wav_path = "temp_audio_to_transcribe.wav"
    transcribed_text = ""
    try:
        if local_audio_path.startswith("http://") or local_audio_path.startswith("https://"):
            return "Error: This tool only accepts local file paths, not URLs. Please use 'file_saver' first."
        if not os.path.exists(local_audio_path):
            return f"Error: Local audio file not found at '{local_audio_path}'."
        audio = AudioSegment.from_file(local_audio_path)
        audio.export(temp_wav_path, format="wav")
        with sr.AudioFile(temp_wav_path) as source:
            audio_listened = r.record(source)
            try:
                transcribed_text = r.recognize_google(audio_listened, language=language)
            except sr.UnknownValueError:
                return "Could not understand audio (speech not clear or too short)."
            except sr.RequestError as e:
                return f"Could not request results from Google Speech Recognition service; {e}"
    except Exception as e:
        return f"An unexpected error occurred during audio processing or transcription: {e}"
    finally:
        if os.path.exists(temp_wav_path):
            os.remove(temp_wav_path)
    return transcribed_text.strip()

audio_transcriber_tool = Tool(
    name="audio_transcriber_tool",
    description=(
        "Transcribes audio content from a **local file path** to a text transcript. "
        "Use for extracting spoken information from audio recordings downloaded using 'file_saver'."
    ),
    func=transcribe_audio_from_path,
)

# 4. Gemini Multimodal Tool (for images)
import base64
from langchain.tools import Tool
from langchain_google_genai import ChatGoogleGenerativeAI
from langchain_core.messages import HumanMessage

def analyze_image_with_gemini(args: dict) -> str:
    """
    Analyzes an image using Gemini Multimodal LLM to answer a given question.
    Input: JSON with 'image_path' and 'question'.
    """
    try:
        if isinstance(args, str):
            import json
            args = json.loads(args)
        image_path = args.get("image_path")
        question = args.get("question")
        if not image_path or not question:
            return "Error: Both 'image_path' and 'question' must be provided."
        if not os.path.exists(image_path):
            return f"Error: Local image file not found at '{image_path}'."
        google_api_key = os.getenv("GOOGLE_API_KEY")
        if not google_api_key:
            return "Error: GOOGLE_API_KEY not found in environment variables for multimodal tool."
        llm = ChatGoogleGenerativeAI(
            model="gemini-2.0-flash",
            google_api_key=google_api_key,
            temperature=0.0
        )
        with open(image_path, "rb") as f:
            image_bytes = f.read()
            image_base64 = base64.b64encode(image_bytes).decode('utf-8')
        message = HumanMessage(
            content=[
                {"type": "text", "text": question},
                {"type": "image_url", "image_url": {"url": f"data:image/png;base64,{image_base64}"}},
            ]
        )
        response = llm.invoke([message])
        return response.content
    except Exception as e:
        return f"Error in gemini_multimodal_tool: {e}"

gemini_multimodal_tool = Tool(
    name="gemini_multimodal_tool",
    description="Analyze an image with Gemini LLM. Input: JSON with 'image_path' and 'question'.",
    func=analyze_image_with_gemini,
)

# 5. Wikipedia Search Tool
from langchain_community.document_loaders import WikipediaLoader

def wiki_search(query: str) -> str:
    """Search Wikipedia for a query and return up to 2 results."""
    search_docs = WikipediaLoader(query=query, load_max_docs=2).load()
    formatted_search_docs = "\n\n---\n\n".join(
        [
            f'<Document source="{doc.metadata.get("source", "")}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content}\n</Document>'
            for doc in search_docs
        ])
    return formatted_search_docs

wikipedia_search_tool2 = Tool(
    name="wikipedia_search_tool2",
    description="Search Wikipedia for a query and return up to 2 results.",
    func=wiki_search,
)

# ========== END TOOLS SECTION ==========

# --- AGENT SECTION ---
from langchain_google_genai import ChatGoogleGenerativeAI
from langchain.memory import ConversationSummaryMemory
from langchain.prompts import PromptTemplate
from langchain.agents import AgentExecutor, create_react_agent
from typing import List, Optional

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

# Set up LLM (Google Gemini - requires GOOGLE_API_KEY env variable)
google_api_key = os.getenv("GOOGLE_API_KEY")
if not google_api_key:
    raise RuntimeError("GOOGLE_API_KEY not found in environment. Please set it.")

gemini_model = "gemini-2.0-flash"
llm_client = ChatGoogleGenerativeAI(
    model=gemini_model,
    google_api_key=google_api_key,
    temperature=0,
)
summary_memory = ConversationSummaryMemory(llm=llm_client, memory_key="chat_history")

# Prompt
prompt = PromptTemplate(
    input_variables=["input", "agent_scratchpad", "chat_history", "tool_names"],
    template="""
You are a smart and helpful AI Agent/Assistant that excels at fact-based reasoning. You are allowed and encouraged to use one or more tools as needed to answer complex questions and perform tasks.
Your FINAL ANSWER must be one of these formats and ONLY the answer itself (no intro phrases):
- A number (e.g., '26', '1977', '519')
- As few words as possible (e.g., 'Paris', 'down', 'LUX')
- A comma-separated list of numbers and/or strings (e.g., '10,20,30', 'apple,banana,orange')
---
Previous conversation history:
{chat_history}
New input: {input}
---
{agent_scratchpad}
"""
)

tools = [repl_tool, file_saver_tool, audio_transcriber_tool, gemini_multimodal_tool, wikipedia_search_tool2]

summary_llm = ChatGoogleGenerativeAI(
    model=gemini_model,
    google_api_key=google_api_key,
    temperature=0,
    streaming=True
)

summary_react_agent = create_react_agent(
    llm=summary_llm,
    tools=tools,
    prompt=prompt
)

class BasicAgent:
    def __init__(
        self,
        agent,
        tools: List,
        verbose: bool = False,
        handle_parsing_errors: bool = True,
        max_iterations: int = 9,
        memory: Optional[ConversationSummaryMemory] = None
    ) -> None:
        self.agent = agent
        self.tools = tools
        self.verbose = verbose
        self.handle_parsing_errors = handle_parsing_errors
        self.max_iterations = max_iterations
        self.memory = memory
        self.agent_obj = AgentExecutor(
            agent=self.agent,
            tools=self.tools,
            verbose=self.verbose,
            handle_parsing_errors=self.handle_parsing_errors,
            max_iterations=self.max_iterations,
            memory=self.memory
        )
    def __call__(self, question: str) -> str:
        result = self.agent_obj.invoke(
            {"input": question},
            config={"configurable": {"session_id": "test-session"}},
        )
        return result['output']

def run_and_submit_all( profile: gr.OAuthProfile | None):
    space_id = os.getenv("SPACE_ID")
    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"

    agent = BasicAgent(summary_react_agent, tools, True, True, 30, summary_memory)
    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
    print(agent_code)

    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 Exception as e:
        return f"Error fetching questions: {e}", None

    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")
        file_name = item.get("file_name")
        full_question_for_agent = question_text
        if file_name:
            attachment_url = f"{api_url}/files/{task_id}"
            full_question_for_agent += f"\n\nAttachment '{file_name}' available at EXACT URL: {attachment_url}"
            print(f"Running agent on task {task_id}: {full_question_for_agent}",flush=True)
        try:
            submitted_answer = agent(full_question_for_agent)
            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})
            time.sleep(5)  # for demo, zmień na 60 przy real eval!
        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:
        return "Agent did not produce any answers to submit.", pd.DataFrame(results_log)

    submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers_payload}
    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.')}"
        )
        cleaned_final_status = re.sub(r'[^\x20-\x7E\n\r\t]+', '', final_status)
        cleaned_final_status = cleaned_final_status.strip()
        results_df = pd.DataFrame(results_log)
        return cleaned_final_status, results_df
    except Exception as e:
        status_message = f"An unexpected error occurred during submission: {e}"
        results_df = pd.DataFrame(results_log)
        return status_message, results_df

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.
        """
    )
    gr.LoginButton()
    run_button = gr.Button("Run Evaluation & Submit All Answers")
    status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
    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)
    space_host_startup = os.getenv("SPACE_HOST")
    space_id_startup = os.getenv("SPACE_ID")
    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(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)