#
# Copyright (c) 2024-2025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#

import argparse
import os

from dotenv import load_dotenv
from loguru import logger

from pipecat.audio.vad.silero import SileroVADAnalyzer
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.services.gemini_multimodal_live.gemini import GeminiMultimodalLiveLLMService
from pipecat.transports.base_transport import TransportParams
from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection

load_dotenv(override=True)


# Function handlers for the LLM
search_tool = {"google_search": {}}
tools = [search_tool]

system_instruction = """
You are an expert at providing the most recent news from any place. Your responses will be converted to audio, so avoid using special characters or overly complex formatting.

Always use the google search API to retrieve the latest news. You must also use it to check which day is today.

You can:
- Use the Google search API to check the current date.
- Provide the most recent and relevant news from any place by using the google search API.
- Answer any questions the user may have, ensuring your responses are accurate and concise.

Start each interaction by asking the user about which place they would like to know the information.
"""


async def run_bot(webrtc_connection: SmallWebRTCConnection, _: argparse.Namespace):
    logger.info(f"Starting bot")

    # Initialize the SmallWebRTCTransport with the connection
    transport = SmallWebRTCTransport(
        webrtc_connection=webrtc_connection,
        params=TransportParams(
            audio_in_enabled=True,
            audio_out_enabled=True,
            vad_analyzer=SileroVADAnalyzer(),
        ),
    )

    # Initialize the Gemini Multimodal Live model
    llm = GeminiMultimodalLiveLLMService(
        api_key=os.getenv("GOOGLE_API_KEY"),
        voice_id="Puck",  # Aoede, Charon, Fenrir, Kore, Puck
        transcribe_user_audio=True,
        system_instruction=system_instruction,
        tools=tools,
    )

    context = OpenAILLMContext(
        [
            {
                "role": "user",
                "content": "Start by greeting the user warmly, introducing yourself, and mentioning the current day. Be friendly and engaging to set a positive tone for the interaction.",
            }
        ],
    )
    context_aggregator = llm.create_context_aggregator(context)

    pipeline = Pipeline(
        [
            transport.input(),  # Transport user input
            context_aggregator.user(),  # User responses
            llm,  # LLM
            transport.output(),  # Transport bot output
            context_aggregator.assistant(),  # Assistant spoken responses
        ]
    )

    task = PipelineTask(pipeline, params=PipelineParams(allow_interruptions=True))

    @transport.event_handler("on_client_connected")
    async def on_client_connected(transport, client):
        logger.info(f"Client connected")
        # Kick off the conversation.
        await task.queue_frames([context_aggregator.user().get_context_frame()])

    @transport.event_handler("on_client_disconnected")
    async def on_client_disconnected(transport, client):
        logger.info(f"Client disconnected")

    @transport.event_handler("on_client_closed")
    async def on_client_closed(transport, client):
        logger.info(f"Client closed connection")
        await task.cancel()

    runner = PipelineRunner(handle_sigint=False)

    await runner.run(task)


if __name__ == "__main__":
    from run import main

    main()