import requests
import os

import gradio as gr
import pandas as pd
from smolagents import CodeAgent, DuckDuckGoSearchTool, VisitWebpageTool, OpenAIServerModel, Tool
from youtube_transcript_api import YouTubeTranscriptApi
import whisper
from pytubefix import YouTube
from pytubefix.cli import on_progress
from bs4 import BeautifulSoup
import wikipediaapi
import cv2
import numpy as np


# (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 ImageLoaderTool(Tool):
    name = "image_loader"
    description = (
        "Loads an image from a given URL using cv2 and returns it as a numpy array. "
        "Input: URL of the image."
        "Output: Image as a numpy array."
        "Note: This tool requires the 'cv2' library to be installed."
    )
    inputs = {
        "image_url": {"type": "string", "description": "URL of the image."},
    }
    output_type = "numpy.ndarray"
    def forward(self, image_url: str) -> str:
        if not image_url.startswith("http"):
            raise ValueError(f"Invalid URL: {image_url}")
        try:
            response = requests.get(image_url)
            image = cv2.imdecode(np.frombuffer(response.content, np.uint8), cv2.IMREAD_COLOR)
            return image
        except Exception as e:
            raise ValueError(f"Error loading image: {e}")


class SpeechToTextTool(Tool):
    name = "speech_to_text"
    description = (
        "Converts an audio file to text. "
    )
    inputs = {
        "audio_file_path": {"type": "string", "description": "Path to the audio file."},
    }
    output_type = "string"
    
    def __init__(self):
        super().__init__()
        self.model = whisper.load_model("base")

    def forward(self, audio_file_path: str) -> str:
        if not os.path.exists(audio_file_path):
            raise ValueError(f"Audio file not found: {audio_file_path}")
        result = self.model.transcribe(audio_file_path)
        return result.get("text", "")


class YoutubeSubtitlesTranscriptTool(Tool):
    name = "youtube_subtitles_transcript"
    description = (
        "Fetches the transcript of a YouTube video. "
        "Input: YouTube video URL."
        "Output: Transcript text."
    )
    inputs = {
        "video_url": {"type": "string", "description": "YouTube video URL."},
    }
    output_type = "string"

    def forward(self, video_url: str) -> str:
        if not video_url.startswith("https://www.youtube.com/watch?v="):
            raise ValueError(f"Invalid YouTube URL: {video_url}")
        video_id = video_url.split("v=")[-1]
        try:
            transcript = YouTubeTranscriptApi.get_transcript(video_id)
            transcript_text = " ".join([entry["text"] for entry in transcript])
            return transcript_text
        except Exception as transcript_error:
            print(f"Transcript not available: {transcript_error}")
            try:
                # Fallback: Download audio for processing
                youtube_audio_transcript_tool = YoutubeAudioTranscriptTool()
                transcript_text = youtube_audio_transcript_tool.forward(video_url)
                print("Audio downloaded successfully.")
                return transcript_text  # Assuming the tool returns some text representation
            except Exception as e:
                raise ValueError(f"Error downloading audio or converting to text: {e}")


class YoutubeAudioTranscriptTool(Tool):
    name = "youtube_audio_transcript"
    description = (
        "Downloads the audio from a YouTube video and converts it to text. "
        "Input: YouTube video URL."
    )
    inputs = {
        "video_url": {"type": "string", "description": "YouTube video URL."},
    }
    output_type = "string"

    def forward(self, video_url: str) -> str:
        if not video_url.startswith("https://www.youtube.com/watch?v="):
            raise ValueError(f"Invalid YouTube URL: {video_url}")
        try:
            yt = YouTube(video_url, on_progress_callback=on_progress)
            audio_stream = yt.streams.filter(progressive=True, file_extension='mp4').first()
            audio_file_path = audio_stream.download(filename_prefix="audio_")
            speech_to_text_tool = SpeechToTextTool()
            transcript = speech_to_text_tool.forward(audio_file_path)
            os.remove(audio_file_path)  # Clean up the downloaded file
            return transcript
        except Exception as e:
            raise ValueError(f"Error downloading audio or converting to text: {e}")


class WikipediaSearchTool(Tool):
    name = "wikipedia_search"
    description = (
        "Searches Wikipedia for a given query and returns the summary of the first result."
        "Input: Search query."
        "Output: Wikipedia article."
    )
    inputs = {
        "query": {"type": "string", "description": "Search query."},
    }
    output_type = "string"

    def forward(self, query: str) -> str:
        wiki_wiki = wikipediaapi.Wikipedia(
            user_agent='wikipedia_agent',
            language='en',
            extract_format=wikipediaapi.ExtractFormat.WIKI
        )
        p_wiki = wiki_wiki.page(query)
        if not p_wiki.exists():
            raise ValueError(f"No Wikipedia page found for query: {query}")
        print(p_wiki.text)
        return p_wiki.text


class ParseURLTool(Tool):
    name = "parse_url"
    description = (
        "Parses a URL and returns the text content of the webpage."
        "Input: URL."
        "Output: Text content of the webpage."
    )
    inputs = {
        "url": {"type": "string", "description": "URL to parse."},
    }
    output_type = "string"

    def forward(self, url: str) -> str:
        if not url:
            raise ValueError("URL cannot be empty.")
        # Fetch the HTML content
        response = requests.get(url)
        # Retrieve the HTML content
        html = response.text
        # Create a BesutifulSoup Object
        soup = BeautifulSoup(html, 'html.parser')
        # Select all <p> tags
        paragraphs = soup.select("p")
        webpage_text_list = []
        for para in paragraphs:
            # Get the text content of each <p> tag
            text = para.text
            webpage_text_list.append(text)

        webpage_text = ",".join(webpage_text_list)
        print(f"Webpage text:\n {webpage_text}")
        return webpage_text


class BasicAgent:
    def __init__(self):
        print("BasicAgent initialized.")
        self.agent = CodeAgent(
            model=OpenAIServerModel(model_id="gpt-4o"),
            tools=[
                DuckDuckGoSearchTool(),
                VisitWebpageTool(),
                WikipediaSearchTool(),
                YoutubeSubtitlesTranscriptTool(),
                YoutubeAudioTranscriptTool(),
                SpeechToTextTool(),
                ParseURLTool(),
                ],
            add_base_tools=True,
            additional_authorized_imports=[
                "re",
                "requests",
                "bs4",
                "urllib",
                "pytubefix",
                "pytubefix.cli",
                "youtube_transcript_api",
                "wikipediaapi",
                "whisper",
                "pandas",
                "cv2",
                "numpy",
            ],
        )
    def __call__(self, question: str) -> str:
        print(f"Agent received question (first 50 chars): {question[:50]}...")
        answer = self.agent.run(question)
        print(f"Agent returning answer: {answer}")
        return 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", "sergiosampayo/Final_Assignment_Template") # 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)