from smolagents import CodeAgent, LiteLLMModel, DuckDuckGoSearchTool, PythonInterpreterTool, FinalAnswerTool, VisitWebpageTool, tool
import os
import wikipediaapi
from youtubesearchpython import VideosSearch
from youtube_transcript_api import YouTubeTranscriptApi, NoTranscriptFound, TranscriptsDisabled
import pandas as pd

wiki_api = wikipediaapi.Wikipedia(
    language='en',
    user_agent="MyAgent/1.0 (contact@example.com)"
)

@tool
def search_youtube_video(query: str) -> str:
    """
    Searches YouTube and returns the title and URL of the top result.

    Args:
        query (str): The search term to look up on YouTube.

    Returns:
        str: The title and URL of the top video result.

    """
    print(f"--- Executing Youtube with query: '{query}' ---")
    try:
        search = VideosSearch(query, limit=1)
        top_result = search.result()['result'][0]
        video_id = top_result['id']
        video_title = top_result['title']
        video_url = f"https://www.youtube.com/watch?v={video_id}"
        return f"Title: {video_title}\nURL: {video_url}"
    except IndexError:
        return "Error: No YouTube videos found for that query."
    except Exception as e:
        return f"An unknown error occurred during Youtube: {e}"

@tool
def get_youtube_transcript(video_url: str) -> str:
    """
    Extracts and returns the full transcript of a YouTube video.

    Args:
        video_url (str): The full URL of the YouTube video.

    Returns:
        str: The transcript text, or an error message if unavailable.
    """
    print(f"--- Executing YouTube Transcript Tool for URL: '{video_url}' ---")
    try:
        # Extract video ID from URL
        if "watch?v=" in video_url:
            video_id = video_url.split("watch?v=")[1].split("&")[0]
        elif "youtu.be/" in video_url:
            video_id = video_url.split("youtu.be/")[1].split("?")[0]
        else:
            return "Error: Invalid YouTube URL format."
            
        # Fetch the transcript
        transcript_list = YouTubeTranscriptApi.get_transcript(video_id)
        
        # Combine transcript segments into a single block of text
        full_transcript = " ".join([item['text'] for item in transcript_list])
        
        return full_transcript
    except NoTranscriptFound:
        return "Error: No transcript could be found for this video."
    except TranscriptsDisabled:
        return "Error: Transcripts are disabled for this video."
    except Exception as e:
        return f"An unknown error occurred while fetching the transcript: {e}"
    
@tool
def get_wikipedia_summary(query: str) -> str:
    """
    Fetches and returns the summary of a Wikipedia article.

    Args:
        query (str): The title or topic of the Wikipedia article to search.

    Returns:
        str: The summary text of the article, or an error message if not found.
    """
    print(f"--- Executing Wikipedia Tool with query: '{query}' ---")
    page = wiki_api.page(query)
    if not page.exists():
        return f"Error: The Wikipedia page for '{query}' could not be found."
    return f"Title: {page.title}\n\nSummary:\n{page.summary}"

@tool
def analyze_excel_file(file_path: str, query: str) -> str:
    """
    Analyze an Excel file using pandas and answer a question about it.
    Args:
        file_path (str): the path to the Excel file.
        query (str): Question about the data
    """
    try:
        # Read the Excel file
        df = pd.read_excel(file_path)

        # Run various analyses based on the query
        result = (
            f"Excel file loaded with {len(df)} rows and {len(df.columns)} columns.\n"
        )
        result += f"Columns: {', '.join(df.columns)}\n\n"

        # Add summary statistics
        result += "Summary statistics:\n"
        result += str(df.describe())

        return result

    except Exception as e:
        return f"Error analyzing Excel file: {str(e)}"

class BasicAgent:
    def __init__(self):


        model = LiteLLMModel(model_id="gpt-4.1-2025-04-14")


        self.agent = CodeAgent(
            model=model,
            tools=[DuckDuckGoSearchTool(), 
                   PythonInterpreterTool(), 
                   FinalAnswerTool(), 
                   VisitWebpageTool(),
                   search_youtube_video,
                   get_youtube_transcript,
                   get_wikipedia_summary,
                   analyze_excel_file],
            additional_authorized_imports=['numpy','csv','xlrd','openpyxl','pandas','markdownify','requests'],       
            add_base_tools=False,
            max_steps=10,
        )


    

    def __call__(self, question: str) -> str:

        custom_prompt = ("""
                        __CONSTRAINTS__
                        - DO NOT start with an intro or include an outro.
                        """)
    
        print(f"Agent received question (first 50 chars): {question[:50]}...")
        result = self.agent.run(custom_prompt + question)

        print("Raw result:", result)

        if isinstance(result, dict) and "output" in result:
            final_str = str(result["output"]).strip()
        elif hasattr(result, "output"):
            final_str = str(result.output).strip()
        else:
            final_str = str(result).strip()

        return final_str