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

"""Audio Recording Example with Pipecat.

This example demonstrates how to record audio from a conversation between a user and an AI assistant,
saving both merged and individual audio tracks. It showcases the AudioBufferProcessor's capabilities
to handle both combined and separate audio streams.

The example:
    1. Sets up a basic conversation with an AI assistant
    2. Records the entire conversation
    3. Saves three separate WAV files:
        - A merged recording of both participants
        - Individual recording of user audio
        - Individual recording of assistant audio

Requirements:
    - OpenAI API key (for GPT-4)
    - Cartesia API key (for text-to-speech)
    - Daily API key (for video/audio transport)

    Environment variables (.env file):
        OPENAI_API_KEY=your_openai_key
        CARTESIA_API_KEY=your_cartesia_key
        DAILY_API_KEY=your_daily_key
        DEEPGRAM_API_KEY=your_deepgram_key

The recordings will be saved in a 'recordings' directory with timestamps:
    recordings/
        merged_20240315_123456.wav  (Combined audio)
        user_20240315_123456.wav    (User audio only)
        bot_20240315_123456.wav     (Bot audio only)

Note:
    This example requires the AudioBufferProcessor with track-specific audio support,
    which provides both 'on_audio_data' and 'on_track_audio_data' events for
    handling merged and separate audio tracks respectively.
"""

import datetime
import io
import os
import wave

import aiofiles
from dotenv import load_dotenv
from loguru import logger

from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.evals.transport import EvalTransportParams
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.processors.audio.audio_buffer_processor import AudioBufferProcessor
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
from pipecat.workers.runner import WorkerRunner

load_dotenv(override=True)


async def save_audio_file(audio: bytes, filename: str, sample_rate: int, num_channels: int):
    """Save audio data to a WAV file."""
    if len(audio) > 0:
        with io.BytesIO() as buffer:
            with wave.open(buffer, "wb") as wf:
                wf.setsampwidth(2)
                wf.setnchannels(num_channels)
                wf.setframerate(sample_rate)
                wf.writeframes(audio)
            async with aiofiles.open(filename, "wb") as file:
                await file.write(buffer.getvalue())
        logger.info(f"Audio saved to {filename}")


# We use lambdas to defer transport parameter creation until the transport
# type is selected at runtime.
transport_params = {
    "eval": lambda: EvalTransportParams(
        audio_in_enabled=True,
        audio_out_enabled=True,
    ),
    "daily": lambda: DailyParams(
        audio_in_enabled=True,
        audio_out_enabled=True,
    ),
    "twilio": lambda: FastAPIWebsocketParams(
        audio_in_enabled=True,
        audio_out_enabled=True,
    ),
    "webrtc": lambda: TransportParams(
        audio_in_enabled=True,
        audio_out_enabled=True,
    ),
}


async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
    logger.info("Starting bot")

    stt = DeepgramSTTService(api_key=os.environ["DEEPGRAM_API_KEY"], audio_passthrough=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.",
        ),
    )

    # Create audio buffer processor. Recording starts automatically when the
    # pipeline starts; alternatively, push an AudioBufferStartRecordingFrame or
    # call start_recording() to start it on demand.
    audiobuffer = AudioBufferProcessor(auto_start_recording=True)

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

    pipeline = Pipeline(
        [
            transport.input(),
            stt,
            user_aggregator,
            llm,
            tts,
            transport.output(),
            audiobuffer,  # Add audio buffer to pipeline
            assistant_aggregator,
        ]
    )

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

    runner = WorkerRunner(handle_sigint=runner_args.handle_sigint)

    await runner.add_workers(worker)

    @transport.event_handler("on_client_connected")
    async def on_client_connected(transport, client):
        logger.info("Client connected")
        # 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_client_disconnected")
    async def on_client_disconnected(transport, client):
        logger.info("Client disconnected")
        await runner.cancel()

    @audiobuffer.event_handler("on_recording_started")
    async def on_recording_started(buffer):
        logger.info("Recording started")

    @audiobuffer.event_handler("on_recording_stopped")
    async def on_recording_stopped(buffer):
        logger.info("Recording stopped")

    # Handler for merged audio
    @audiobuffer.event_handler("on_audio_data")
    async def on_audio_data(buffer, audio, sample_rate, num_channels):
        timestamp = datetime.datetime.now().strftime("%Y%m%d_%H%M%S")
        filename = f"recordings/merged_{timestamp}.wav"
        os.makedirs("recordings", exist_ok=True)
        await save_audio_file(audio, filename, sample_rate, num_channels)

    # Handler for separate tracks
    @audiobuffer.event_handler("on_track_audio_data")
    async def on_track_audio_data(buffer, user_audio, bot_audio, sample_rate, num_channels):
        timestamp = datetime.datetime.now().strftime("%Y%m%d_%H%M%S")
        os.makedirs("recordings", exist_ok=True)

        # Save user audio
        user_filename = f"recordings/user_{timestamp}.wav"
        await save_audio_file(user_audio, user_filename, sample_rate, 1)

        # Save bot audio
        bot_filename = f"recordings/bot_{timestamp}.wav"
        await save_audio_file(bot_audio, bot_filename, sample_rate, 1)

    await runner.run()


async def bot(runner_args: RunnerArguments):
    """Main bot entry point compatible with Pipecat Cloud."""
    transport = await create_transport(runner_args, transport_params)
    await run_bot(transport, runner_args)


if __name__ == "__main__":
    from pipecat.runner.run import main

    main()