from google import genai
from google.genai import types

TRANSCRIPTION_MODEL = "gemini-3.1-flash-lite-preview"

async def transcribe_audio(audio_bytes: bytes, mime_type: str = "audio/mp4") -> str:
    """
    Transcribe audio bytes to text using Gemini.
    LINE 語音訊息固定是 m4a，MIME type 固定填 audio/mp4。
    """
    client = genai.Client(
        vertexai=True,
        project=os.getenv("GOOGLE_CLOUD_PROJECT"),
        location=os.getenv("GOOGLE_CLOUD_LOCATION", "us-central1"),
    )

    audio_part = types.Part.from_bytes(data=audio_bytes, mime_type=mime_type)

    response = await client.aio.models.generate_content(
        model=TRANSCRIPTION_MODEL,
        contents=[
            types.Content(
                role="user",
                parts=[
                    audio_part,
                    types.Part(text="請將以上語音內容完整轉錄成文字，保留原語言，不要加任何說明或前綴。"),
                ],
            )
        ],
    )

    return response.text or ""

async def handle_audio_message(event: MessageEvent):
    """Handle audio (voice) messages — transcribe and route through Orchestrator."""
    user_id = event.source.user_id
    replied = False  # 追蹤 reply token 是否已使用
    try:
        # 下載音訊
        message_content = await line_bot_api.get_message_content(event.message.id)
        audio_bytes = b""
        async for chunk in message_content.iter_content():
            audio_bytes += chunk

        # 轉錄
        transcription = await transcribe_audio(audio_bytes)

        # 空轉錄（無聲或太短）
        if not transcription.strip():
            await line_bot_api.reply_message(
                event.reply_token,
                [TextSendMessage(text="無法辨識語音內容，請重新錄製。")]
            )
            return

        # Reply #1：讓使用者確認轉錄結果（消耗 reply token）
        await line_bot_api.reply_message(
            event.reply_token,
            [TextSendMessage(text=f"你說的是：{transcription.strip()}")]
        )
        replied = True

        # Reply #2：送進 Orchestrator，用 push_message（token 已用掉）
        await handle_text_message_via_orchestrator(
            event, user_id,
            text=transcription.strip(),
            push_user_id=user_id,
        )

    except Exception as e:
        logger.error(f"Error handling audio for {user_id}: {e}", exc_info=True)
        error_text = LineService.format_error_message(e, "處理語音訊息")
        error_msg = TextSendMessage(text=error_text)
        if replied:
            # reply token 已消耗，改用 push
            await line_bot_api.push_message(user_id, [error_msg])
        else:
            await line_bot_api.reply_message(event.reply_token, [error_msg])

async def handle_text_message_via_orchestrator(
    event: MessageEvent,
    user_id: str,
    text: str = None,           # ← 外部傳入文字（語音轉錄）
    push_user_id: str = None,   # ← 設定時改用 push_message
):
    msg = text if text is not None else event.message.text.strip()
    try:
        result = await orchestrator.process_text(user_id=user_id, message=msg)
        response_text = format_orchestrator_response(result)
        reply_msg = TextSendMessage(text=response_text)

        if push_user_id:
            await line_bot_api.push_message(push_user_id, [reply_msg])
        else:
            await line_bot_api.reply_message(event.reply_token, [reply_msg])
    except Exception as e:
        error_msg = TextSendMessage(text=LineService.format_error_message(e, "處理您的問題"))
        if push_user_id:
            await line_bot_api.push_message(push_user_id, [error_msg])
        else:
            await line_bot_api.reply_message(event.reply_token, [error_msg])

# ❌ 錯誤（TypeError: Part.from_text() takes 1 positional argument but 2 were given）
types.Part.from_text(
    "請將以上語音內容完整轉錄成文字，保留原語言，不要加任何說明或前綴。"
)

# ✅ 正確
types.Part(text="請將以上語音內容完整轉錄成文字，保留原語言，不要加任何說明或前綴。")

LIVE_MODEL = "gemini-live-2.5-flash-native-audio"

async def text_to_speech(text: str) -> tuple[bytes, int]:
    client = genai.Client(vertexai=True, project=VERTEX_PROJECT, location="us-central1")
    config = {"response_modalities": ["AUDIO"]}

    async with client.aio.live.connect(model=LIVE_MODEL, config=config) as session:
        await session.send_client_content(
            turns=types.Content(role="user", parts=[types.Part(text=text)]),
            turn_complete=True,
        )
        pcm_chunks = []
        async for message in session.receive():
            if message.server_content and message.server_content.model_turn:
                for part in message.server_content.model_turn.parts:
                    if part.inline_data and part.inline_data.data:
                        pcm_chunks.append(part.inline_data.data)
            if message.server_content and message.server_content.turn_complete:
                break

    pcm_bytes = b"".join(pcm_chunks)
    duration_ms = int(len(pcm_bytes) / 32000 * 1000)  # 16kHz × 16-bit mono

    # PCM → m4a（temp file 模式，避免 moov atom 問題）
    with tempfile.NamedTemporaryFile(suffix=".pcm", delete=False) as f:
        f.write(pcm_bytes)
        pcm_path = f.name
    m4a_path = pcm_path.replace(".pcm", ".m4a")
    subprocess.run(
        ["ffmpeg", "-y", "-f", "s16le", "-ar", "16000", "-ac", "1",
         "-i", pcm_path, "-c:a", "aac", m4a_path],
        check=True, capture_output=True,
    )
    with open(m4a_path, "rb") as f:
        return f.read(), duration_ms

LIVE_MODEL = "gemini-3.1-flash-live-preview"

# ✅ 正確
LIVE_MODEL = "gemini-live-2.5-flash-native-audio"

# _api_client.py
self.location = location or env_location
if not self.location and not self.api_key:
    self.location = 'global'  # ← 這裡

# ❌ 受 GOOGLE_CLOUD_LOCATION=global 影響
VERTEX_LOCATION = os.getenv("GOOGLE_CLOUD_LOCATION", "us-central1")

# ✅ 硬寫，不受 env var 干擾
VERTEX_LOCATION = "us-central1"  # Live API 需要 regional endpoint