"""
Speechmatics STT factory for voice-agent.

Creates a livekit-plugins-speechmatics STT instance configured for
Mandarin-English bilingual recognition with speaker diarization support.

The SPEECHMATICS_API_KEY environment variable is read automatically
by the livekit-plugins-speechmatics package.
"""
import logging

from livekit.plugins import speechmatics

logger = logging.getLogger(__name__)


# Map Whisper language codes to Speechmatics language codes
_LANG_MAP = {
    "zh": "cmn",
    "en": "en",
    "ja": "ja",
    "ko": "ko",
    "de": "de",
    "fr": "fr",
}


def create_speechmatics_stt(language: str = "cmn") -> speechmatics.STT:
    """Create a Speechmatics STT instance for the voice pipeline.

    Args:
        language: Language code (Whisper or Speechmatics). Whisper codes like
                  'zh' are automatically mapped to Speechmatics equivalents.

    Returns:
        Configured speechmatics.STT instance.
    """
    sm_lang = _LANG_MAP.get(language, language)
    stt = speechmatics.STT(
        language=sm_lang,
        include_partials=True,
    )
    logger.info("Speechmatics STT created: language=%s (input=%s)", sm_lang, language)
    return stt