from datetime import datetime
from typing import List, Optional

from fastapi import APIRouter, Depends, HTTPException, Query
from sqlalchemy.orm import Session

from db.crud import (
    create_alarm,
    get_alarm_stats,
    get_alarms,
    update_alarm,
)
from db.models import get_db
from inference.pipeline import get_pipeline

router = APIRouter(prefix="/api/alarms", tags=["告警管理"])


@router.get("", response_model=List[dict])
def list_alarms(
    camera_id: Optional[int] = None,
    event_type: Optional[str] = None,
    limit: int = Query(default=100, le=1000),
    offset: int = Query(default=0, ge=0),
    db: Session = Depends(get_db),
):
    alarms = get_alarms(db, camera_id=camera_id, event_type=event_type, limit=limit, offset=offset)
    return [
        {
            "id": alarm.id,
            "camera_id": alarm.camera_id,
            "roi_id": alarm.roi_id,
            "event_type": alarm.event_type,
            "confidence": alarm.confidence,
            "snapshot_path": alarm.snapshot_path,
            "llm_checked": alarm.llm_checked,
            "llm_result": alarm.llm_result,
            "processed": alarm.processed,
            "created_at": alarm.created_at.isoformat() if alarm.created_at else None,
        }
        for alarm in alarms
    ]


@router.get("/stats")
def get_alarm_statistics(db: Session = Depends(get_db)):
    stats = get_alarm_stats(db)
    return stats


@router.get("/{alarm_id}", response_model=dict)
def get_alarm(alarm_id: int, db: Session = Depends(get_db)):
    from db.crud import get_alarms
    alarms = get_alarms(db, limit=1)
    alarm = next((a for a in alarms if a.id == alarm_id), None)
    if not alarm:
        raise HTTPException(status_code=404, detail="告警不存在")
    return {
        "id": alarm.id,
        "camera_id": alarm.camera_id,
        "roi_id": alarm.roi_id,
        "event_type": alarm.event_type,
        "confidence": alarm.confidence,
        "snapshot_path": alarm.snapshot_path,
        "llm_checked": alarm.llm_checked,
        "llm_result": alarm.llm_result,
        "processed": alarm.processed,
        "created_at": alarm.created_at.isoformat() if alarm.created_at else None,
    }


@router.put("/{alarm_id}")
def update_alarm_status(
    alarm_id: int,
    llm_checked: Optional[bool] = None,
    llm_result: Optional[str] = None,
    processed: Optional[bool] = None,
    db: Session = Depends(get_db),
):
    alarm = update_alarm(db, alarm_id, llm_checked=llm_checked, llm_result=llm_result, processed=processed)
    if not alarm:
        raise HTTPException(status_code=404, detail="告警不存在")
    return {"message": "更新成功"}


@router.post("/{alarm_id}/llm-check")
async def trigger_llm_check(alarm_id: int, db: Session = Depends(get_db)):
    from db.crud import get_alarms
    alarms = get_alarms(db, limit=1)
    alarm = next((a for a in alarms if a.id == alarm_id), None)
    if not alarm:
        raise HTTPException(status_code=404, detail="告警不存在")

    if not alarm.snapshot_path or not os.path.exists(alarm.snapshot_path):
        raise HTTPException(status_code=400, detail="截图不存在")

    try:
        from config import get_config
        config = get_config()
        if not config.llm.enabled:
            raise HTTPException(status_code=400, detail="大模型功能未启用")

        import base64
        with open(alarm.snapshot_path, "rb") as f:
            img_base64 = base64.b64encode(f.read()).decode("utf-8")

        from openai import OpenAI
        client = OpenAI(
            api_key=config.llm.api_key,
            base_url=config.llm.base_url,
        )

        prompt = """分析这张监控截图，判断是否存在异常行为。请简要说明：
1. 画面中是否有人
2. 人员位置和行为
3. 是否存在异常"""

        response = client.chat.completions.create(
            model=config.llm.model,
            messages=[
                {
                    "role": "user",
                    "content": [
                        {"type": "image_url", "image_url": {"url": f"data:image/jpeg;base64,{img_base64}"}},
                        {"type": "text", "text": prompt},
                    ],
                }
            ],
        )

        result = response.choices[0].message.content
        update_alarm(db, alarm_id, llm_checked=True, llm_result=result)

        return {"message": "大模型分析完成", "result": result}
    except Exception as e:
        raise HTTPException(status_code=500, detail=f"大模型调用失败: {str(e)}")


@router.get("/queue/size")
def get_event_queue_size():
    pipeline = get_pipeline()
    return {"size": len(pipeline.event_queue), "max_size": pipeline.config.inference.event_queue_maxlen}