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

import os

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, TTSSpeakFrame, UserImageRequestFrame
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.frame_processor import FrameDirection
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import (
    create_transport,
    get_transport_client_id,
    maybe_capture_participant_camera,
)
from pipecat.services.aws.llm import AWSBedrockLLMService
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.llm_service import FunctionCallParams
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.workers.runner import WorkerRunner

load_dotenv(override=True)


async def fetch_user_image(params: FunctionCallParams, user_id: str, question: str):
    """Fetch the user image and push it to the LLM.

    When called, this function pushes a UserImageRequestFrame upstream to the
    transport. As a result, the transport will request the user image and push a
    UserImageRawFrame downstream which will be added to the context by the LLM
    assistant aggregator. The result_callback will be invoked once the image is
    retrieved and processed.

    Args:
        user_id: The ID of the user to grab the image from.
        question: The question that the user is asking about the image.
    """
    logger.debug(f"Requesting image with user_id={user_id}, question={question}")

    # Request a user image frame and indicate that it should be added to the
    # context. Also associate it to the function call. Pass the result_callback
    # so it can be invoked when the image is actually retrieved.
    await params.llm.push_frame(
        UserImageRequestFrame(
            user_id=user_id,
            text=question,
            append_to_context=True,
            function_name=params.function_name,
            tool_call_id=params.tool_call_id,
            result_callback=params.result_callback,
        ),
        FrameDirection.UPSTREAM,
    )


# 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,
        video_in_enabled=True,
    ),
    "webrtc": lambda: TransportParams(
        audio_in_enabled=True,
        audio_out_enabled=True,
        video_in_enabled=True,
    ),
}


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

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

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

    # AWS for vision analysis
    llm = AWSBedrockLLMService(
        aws_region="us-west-2",
        settings=AWSBedrockLLMService.Settings(
            model="us.anthropic.claude-sonnet-4-6",
            # Note: usually, prefer providing latency="optimized" param.
            # Here we can't because AWS Bedrock doesn't support it for Claude 3.7,
            # which we need for image input.
            temperature=0.8,
            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. You are able to describe images from the user camera.",
        ),
    )

    @llm.event_handler("on_function_calls_started")
    async def on_function_calls_started(service, function_calls):
        await tts.queue_frame(TTSSpeakFrame("Let me check on that."))

    context = LLMContext(tools=[fetch_user_image])
    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
        context,
        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
    )

    pipeline = Pipeline(
        [
            transport.input(),  # Transport user input
            stt,  # STT
            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,
        ),
        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(f"Client connected: {client}")

        await maybe_capture_participant_camera(transport, client)

        # Set the participant ID in the image requester
        client_id = get_transport_client_id(transport, client)

        # Kick off the conversation.
        context.add_message(
            {
                "role": "developer",
                "content": f"Please introduce yourself to the user briefly; don't mention the camera. Use '{client_id}' as the user ID during function calls.",
            }
        )
        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()

    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()