#
# Copyright (c) 2024–2025, 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 PIL import Image
from runner import configure

from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import (
    BotStartedSpeakingFrame,
    BotStoppedSpeakingFrame,
    Frame,
    OutputImageRawFrame,
    TextFrame,
)
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
from pipecat.services.cartesia import CartesiaTTSService
from pipecat.services.openai import OpenAILLMService
from pipecat.transports.services.daily import DailyParams, DailyTransport

load_dotenv(override=True)

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


class ImageSyncAggregator(FrameProcessor):
    def __init__(self, speaking_path: str, waiting_path: str):
        super().__init__()
        self._speaking_image = Image.open(speaking_path)
        self._speaking_image_format = self._speaking_image.format
        self._speaking_image_bytes = self._speaking_image.tobytes()

        self._waiting_image = Image.open(waiting_path)
        self._waiting_image_format = self._waiting_image.format
        self._waiting_image_bytes = self._waiting_image.tobytes()

    async def process_frame(self, frame: Frame, direction: FrameDirection):
        await super().process_frame(frame, direction)

        if isinstance(frame, BotStartedSpeakingFrame):
            await self.push_frame(
                OutputImageRawFrame(
                    image=self._speaking_image_bytes,
                    size=(1024, 1024),
                    format=self._speaking_image_format,
                )
            )

        elif isinstance(frame, BotStoppedSpeakingFrame):
            await self.push_frame(
                OutputImageRawFrame(
                    image=self._waiting_image_bytes,
                    size=(1024, 1024),
                    format=self._waiting_image_format,
                )
            )

        await self.push_frame(frame)


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

        transport = DailyTransport(
            room_url,
            token,
            "Respond bot",
            DailyParams(
                audio_out_enabled=True,
                camera_out_enabled=True,
                camera_out_width=1024,
                camera_out_height=1024,
                transcription_enabled=True,
                vad_enabled=True,
                vad_analyzer=SileroVADAnalyzer(),
            ),
        )

        tts = CartesiaTTSService(
            api_key=os.getenv("CARTESIA_API_KEY"),
            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
        )

        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")

        messages = [
            {
                "role": "system",
                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
            },
        ]

        context = OpenAILLMContext(messages)
        context_aggregator = llm.create_context_aggregator(context)

        image_sync_aggregator = ImageSyncAggregator(
            os.path.join(os.path.dirname(__file__), "assets", "speaking.png"),
            os.path.join(os.path.dirname(__file__), "assets", "waiting.png"),
        )

        pipeline = Pipeline(
            [
                transport.input(),
                context_aggregator.user(),
                llm,
                tts,
                image_sync_aggregator,
                transport.output(),
                context_aggregator.assistant(),
            ]
        )

        task = PipelineTask(
            pipeline,
            params=PipelineParams(
                allow_interruptions=True,
                enable_metrics=True,
                enable_usage_metrics=True,
                report_only_initial_ttfb=True,
            ),
        )

        @transport.event_handler("on_first_participant_joined")
        async def on_first_participant_joined(transport, participant):
            participant_name = participant.get("info", {}).get("userName", "")
            await transport.capture_participant_transcription(participant["id"])
            await task.queue_frames([TextFrame(f"Hi there {participant_name}!")])

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

        runner = PipelineRunner()

        await runner.run(task)


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