from smolagents import CodeAgent,DuckDuckGoSearchTool, HfApiModel,load_tool,tool, TransformersModel
from smolagents.models.base import Model
import datetime
import requests
import pytz
import yaml
from tools.final_answer import FinalAnswerTool
import os
from transformers import AutoTokenizer, AutoModelForCausalLM

from Gradio_UI import GradioUI

# Below is an example of a tool that does nothing. Amaze us with your creativity !
@tool
def my_custom_tool(arg1:str, arg2:int)-> str: #it's import to specify the return type
    #Keep this format for the description / args / args description but feel free to modify the tool
    """A tool that does nothing yet 
    Args:
        arg1: the first argument
        arg2: the second argument
    """
    return "What magic will you build ?"

@tool
def get_current_time_in_timezone(timezone: str) -> str:
    """A tool that fetches the current local time in a specified timezone.
    Args:
        timezone: A string representing a valid timezone (e.g., 'America/New_York').
    """
    try:
        # Create timezone object
        tz = pytz.timezone(timezone)
        # Get current time in that timezone
        local_time = datetime.datetime.now(tz).strftime("%Y-%m-%d %H:%M:%S")
        return f"The current local time in {timezone} is: {local_time}"
    except Exception as e:
        return f"Error fetching time for timezone '{timezone}': {str(e)}"


final_answer = FinalAnswerTool()

# If the agent does not answer, the model is overloaded, please use another model or the following Hugging Face Endpoint that also contains qwen2.5 coder:
# model_id='https://pflgm2locj2t89co.us-east-1.aws.endpoints.huggingface.cloud' 

with open("prompts.yaml", 'r') as stream:
    prompt_templates = yaml.safe_load(stream)
    
# Carga del modelo gratuito (no requiere token si es público y el Space también lo es)
model_name = "tiiuae/falcon-rw-1b"

tokenizer = AutoTokenizer.from_pretrained(model_name)
raw_model = AutoModelForCausalLM.from_pretrained(model_name)

# Wrapper para adaptarlo a smolagents
class FalconModel(Model):
    def __init__(self, raw_model, tokenizer, max_new_tokens=128):
        self.raw_model = raw_model
        self.tokenizer = tokenizer
        self.max_new_tokens = max_new_tokens

    def generate(self, messages, stop_sequences=None):
        # Combina el contenido de los mensajes en un prompt string
        prompt = ""
        for msg in messages:
            prompt += f"{msg['role']}: {msg['content']}\n"
        prompt += "assistant: "

        inputs = self.tokenizer(prompt, return_tensors="pt")
        outputs = self.raw_model.generate(
            **inputs,
            max_new_tokens=self.max_new_tokens,
            do_sample=True,
            top_p=0.95,
            temperature=0.8
        )
        text = self.tokenizer.decode(outputs[0], skip_special_tokens=True)

        # Si hay secuencias de parada, corta la salida ahí
        if stop_sequences:
            for stop_seq in stop_sequences:
                if stop_seq in text:
                    text = text.split(stop_seq)[0]

        # Retornar un objeto con .content
        class Response:
            def __init__(self, content):
                self.content = content

        return Response(text.strip())

model = FalconWrapper(raw_model, tokenizer)

# Instancia del agente
agent = CodeAgent(
    model=model,
    tools=[final_answer],
    max_steps=6,
    verbosity_level=1,
    grammar=None,
    planning_interval=None,
    name=None,
    description=None,
    prompt_templates=prompt_templates
)

# Interfaz de Gradio
GradioUI(agent).launch()