#
# Copyright (c) 2025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#

import os
import sys

from dotenv import load_dotenv
from loguru import logger
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.audio.vad.vad_analyzer import VADParams
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
from pipecat.processors.aggregators.llm_context import LLMContext
from pipecat.processors.aggregators.llm_response_universal import (
    LLMContextAggregatorPair,
    LLMUserAggregatorParams,
)
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import parse_telephony_websocket
from pipecat.serializers.twilio import TwilioFrameSerializer
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.google.llm import GoogleLLMService
from pipecat.transports.base_transport import BaseTransport
from pipecat.transports.websocket.fastapi import (
    FastAPIWebsocketParams,
    FastAPIWebsocketTransport,
)
from pipecat.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
from pipecat.turns.user_turn_strategies import UserTurnStrategies

load_dotenv(override=True)

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


async def run_bot(transport: BaseTransport, handle_sigint: bool):
    llm = GoogleLLMService(api_key=os.getenv("GOOGLE_API_KEY"))

    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))

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

    messages = [
        {
            "role": "system",
            "content": (
                "You are a friendly assistant making an outbound phone call. Your responses will be read aloud, "
                "so keep them concise and conversational. Avoid special characters or formatting. "
                "Begin by politely greeting the person and explaining why you're calling."
            ),
        },
    ]

    context = LLMContext(messages)
    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
        context,
        user_params=LLMUserAggregatorParams(
            user_turn_strategies=UserTurnStrategies(
                stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
            ),
        ),
    )

    pipeline = Pipeline(
        [
            transport.input(),  # Websocket input from client
            stt,  # Speech-To-Text
            user_aggregator,
            llm,  # LLM
            tts,  # Text-To-Speech
            transport.output(),  # Websocket output to client
            assistant_aggregator,
        ]
    )

    task = PipelineTask(
        pipeline,
        params=PipelineParams(
            audio_in_sample_rate=8000,
            audio_out_sample_rate=8000,
            enable_metrics=True,
            enable_usage_metrics=True,
        ),
    )

    @transport.event_handler("on_client_connected")
    async def on_client_connected(transport, client):
        # Kick off the outbound conversation, waiting for the user to speak first
        logger.info("Starting outbound call conversation")

    @transport.event_handler("on_client_disconnected")
    async def on_client_disconnected(transport, client):
        logger.info("Outbound call ended")
        await task.cancel()

    runner = PipelineRunner(handle_sigint=handle_sigint)

    await runner.run(task)


async def bot(runner_args: RunnerArguments):
    """Main bot entry point compatible with Pipecat Cloud."""
    transport_type, call_data = await parse_telephony_websocket(runner_args.websocket)
    logger.info(f"Auto-detected transport: {transport_type}")

    # Access custom stream parameters passed from TwiML
    # Use the body data to personalize the conversation
    # by loading customer data based on the to_number or from_number
    body_data = call_data.get("body", {})
    to_number = body_data.get("to_number")
    from_number = body_data.get("from_number")

    logger.info(f"Call metadata - To: {to_number}, From: {from_number}")

    serializer = TwilioFrameSerializer(
        stream_sid=call_data["stream_id"],
        call_sid=call_data["call_id"],
        account_sid=os.getenv("TWILIO_ACCOUNT_SID", ""),
        auth_token=os.getenv("TWILIO_AUTH_TOKEN", ""),
    )

    transport = FastAPIWebsocketTransport(
        websocket=runner_args.websocket,
        params=FastAPIWebsocketParams(
            audio_in_enabled=True,
            audio_out_enabled=True,
            add_wav_header=False,
            vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
            serializer=serializer,
        ),
    )

    handle_sigint = runner_args.handle_sigint

    await run_bot(transport, handle_sigint)