from __future__ import annotations

from typing import Any

from yuxi.utils.logging_config import logger


async def describe_image(image_data: bytes, vision_api_url: str = "", vision_api_key: str = "") -> str:
    """通过外部 Vision API 描述图片内容。

    如果未配置 API URL，返回基本元数据描述。
    """
    if not vision_api_url:
        return f"Image attachment ({len(image_data)} bytes)"

    try:
        import base64

        import aiohttp

        encoded = base64.b64encode(image_data).decode("utf-8")
        payload = {
            "model": "gpt-4o-mini",
            "messages": [
                {
                    "role": "user",
                    "content": [
                        {"type": "text", "text": "Describe this image briefly in one sentence."},
                        {
                            "type": "image_url",
                            "image_url": {"url": f"data:image/jpeg;base64,{encoded}"},
                        },
                    ],
                }
            ],
            "max_tokens": 100,
        }
        headers = {"Authorization": f"Bearer {vision_api_key}"}
        async with aiohttp.ClientSession() as session:
            async with session.post(
                vision_api_url, json=payload, headers=headers, timeout=aiohttp.ClientTimeout(total=15)
            ) as resp:
                if resp.status == 200:
                    data = await resp.json()
                    return data["choices"][0]["message"]["content"]
                return f"Image attachment ({len(image_data)} bytes)"
    except Exception as e:
        logger.warning(f"[iMessage/AI] Vision API failed: {e}")
        return f"Image attachment ({len(image_data)} bytes)"


async def transcribe_audio(audio_data: bytes, transcription_api_url: str = "", transcription_api_key: str = "") -> str:
    """通过外部 API 转录音频内容。"""
    if not transcription_api_url:
        return f"Audio attachment ({len(audio_data)} bytes)"

    try:
        import aiohttp
        from aiohttp import FormData

        form = FormData()
        form.add_field("file", audio_data, filename="audio.caf", content_type="audio/x-caf")
        form.add_field("model", "whisper-1")

        headers = {"Authorization": f"Bearer {transcription_api_key}"}
        async with aiohttp.ClientSession() as session:
            async with session.post(
                transcription_api_url, data=form, headers=headers, timeout=aiohttp.ClientTimeout(total=30)
            ) as resp:
                if resp.status == 200:
                    data = await resp.json()
                    return data.get("text", "")
                return f"Audio attachment ({len(audio_data)} bytes)"
    except Exception as e:
        logger.warning(f"[iMessage/AI] Transcription API failed: {e}")
        return f"Audio attachment ({len(audio_data)} bytes)"


def is_vision_configured(config: dict[str, Any]) -> bool:
    return bool(config.get("vision_api_url") and config.get("vision_api_key"))


def is_transcription_configured(config: dict[str, Any]) -> bool:
    return bool(config.get("transcription_api_url") and config.get("transcription_api_key"))