from dotenv import load_dotenv
from livekit import agents, rtc
from livekit.agents import AgentServer, AgentSession, Agent, room_io
from livekit.plugins import noise_cancellation, silero
from livekit.plugins.turn_detector.multilingual import MultilingualModel

load_dotenv(".env.local")


class Assistant(Agent):
    def __init__(self) -> None:
        super().__init__(
            instructions="""You are a helpful voice AI assistant.
            You eagerly assist users with their questions by providing information from your extensive knowledge.
            Your responses are concise, to the point, and without any complex formatting or punctuation including emojis, asterisks, or other symbols.
            You are curious, friendly, and have a sense of humor.""",
        )


server = AgentServer()


@server.rtc_session(agent_name="my-agent")
async def my_agent(ctx: agents.JobContext):
    session = AgentSession(
        stt="deepgram/nova-3:multi",
        llm="openai/gpt-4.1-mini",
        tts="cartesia/sonic-3:9626c31c-bec5-4cca-baa8-f8ba9e84c8bc",
        vad=silero.VAD.load(),
        turn_detection=MultilingualModel(),
    )
    await session.start(
        room=ctx.room,
        agent=Assistant(),
        room_options=room_io.RoomOptions(
            audio_input=room_io.AudioInputOptions(
                noise_cancellation=lambda params: (
                    noise_cancellation.BVCTelephony()
                    if params.participant.kind == rtc.ParticipantKind.PARTICIPANT_KIND_SIP
                    else noise_cancellation.BVC()
                ),
            ),
        ),
    )
    await session.generate_reply(
        instructions="Greet the user and offer your assistance."
    )


if __name__ == "__main__":
    agents.cli.run_app(server)