from abc import ABC, abstractmethod

from pydantic import BaseModel

from yuxi.utils.logging_config import logger


class VoiceSegment(BaseModel):
    audio_data: bytes
    sample_rate: int = 16000
    channels: int = 1
    encoding: str = "pcm_s16le"
    duration_ms: int = 0


class STTResult(BaseModel):
    text: str
    confidence: float = 0.0
    language: str | None = None


class STTProvider(ABC):
    @abstractmethod
    async def transcribe(self, segment: VoiceSegment) -> STTResult: ...


class TTSProvider(ABC):
    @abstractmethod
    async def synthesize(self, text: str, voice: str = "default") -> bytes: ...


class VoicePolicy:
    def __init__(self):
        self._stt_provider: STTProvider | None = None
        self._tts_provider: TTSProvider | None = None

    def configure_stt(self, provider: STTProvider) -> None:
        self._stt_provider = provider

    def configure_tts(self, provider: TTSProvider) -> None:
        self._tts_provider = provider

    async def process_voice(self, segment: VoiceSegment) -> str | None:
        if not self._stt_provider:
            return None
        try:
            result = await self._stt_provider.transcribe(segment)
        except Exception as e:
            logger.error(f"STT transcription failed: {e}")
            return None
        return result.text or None

    async def text_to_speech(self, text: str) -> bytes | None:
        if not self._tts_provider:
            return None
        try:
            return await self._tts_provider.synthesize(text)
        except Exception as e:
            logger.error(f"TTS synthesis failed: {e}")
            return None