#
# Copyright (c) 2024-2026, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#

import asyncio
import os
import sys

import aiohttp
from dotenv import load_dotenv
from loguru import logger

from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import LLMRunFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.worker import PipelineParams, PipelineWorker, ProcessorUnusablePolicy
from pipecat.processors.aggregators.llm_context import LLMContext
from pipecat.processors.aggregators.llm_response_universal import (
    LLMContextAggregatorPair,
    LLMUserAggregatorParams,
)
from pipecat.runner.daily import configure
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.daily.transport import DailyParams, DailyTransport
from pipecat.workers.runner import WorkerRunner

load_dotenv(override=True)

logger.remove(0)
logger.add(sys.stderr, level="DEBUG")


async def main():
    async with aiohttp.ClientSession() as session:
        (room_url, token) = await configure(session)

        transport = DailyTransport(
            room_url,
            token,
            "Respond bot",
            DailyParams(
                audio_in_enabled=True,
                audio_out_enabled=True,
                transcription_enabled=True,
            ),
        )

        tts = CartesiaTTSService(
            api_key=os.environ["CARTESIA_API_KEY"],
            settings=CartesiaTTSService.Settings(
                voice="86e30c1d-714b-4074-a1f2-1cb6b552fb49",
            ),
        )

        llm = OpenAILLMService(
            api_key=os.environ["OPENAI_API_KEY"],
            settings=OpenAILLMService.Settings(
                system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
            ),
        )

        context = LLMContext()
        user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
            context,
            user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
        )

        pipeline = Pipeline(
            [
                transport.input(),  # Transport user input
                user_aggregator,  # User responses
                llm,  # LLM
                tts,  # TTS
                transport.output(),  # Transport bot output
                assistant_aggregator,  # Assistant spoken responses
            ]
        )

        worker = PipelineWorker(
            pipeline,
            params=PipelineParams(
                enable_metrics=True,
                enable_usage_metrics=True,
            ),
            processor_unusable_policy=ProcessorUnusablePolicy.END,
        )

        runner = WorkerRunner()

        await runner.add_workers(worker)

        @transport.event_handler("on_first_participant_joined")
        async def on_first_participant_joined(transport, participant):
            await transport.capture_participant_transcription(participant["id"])
            # Kick off the conversation.
            context.add_message(
                {"role": "developer", "content": "Please introduce yourself to the user."}
            )
            await worker.queue_frames([LLMRunFrame()])

        @transport.event_handler("on_participant_left")
        async def on_participant_left(transport, participant, reason):
            await runner.cancel()

        await runner.run()


if __name__ == "__main__":
    asyncio.run(main())