"""
XGBoost Busy Detector — HF Space App (FastAPI)
Wraps the EndpointHandler in a FastAPI server for HF Spaces deployment.
"""

from fastapi import FastAPI
from fastapi.middleware.cors import CORSMiddleware
from pydantic import BaseModel
from typing import Dict, Optional
import os

app = FastAPI(title="XGBoost Busy Detector", version="1.0.0")


def _cors_origins_from_env() -> list[str]:
    raw = (os.getenv("ALLOWED_ORIGINS") or "").strip()
    if not raw:
        return ["*"]
    return [o.strip() for o in raw.split(",") if o.strip()]


_cors_origins = _cors_origins_from_env()
app.add_middleware(
    CORSMiddleware,
    allow_origins=_cors_origins,
    # Browsers reject: Access-Control-Allow-Origin="*" with credentials=true.
    allow_credentials=("*" not in _cors_origins),
    allow_methods=["*"], allow_headers=["*"],
)

# Load handler on startup
from handler import EndpointHandler
handler = EndpointHandler(path=".")


class PredictRequest(BaseModel):
    inputs: Dict  # { "audio_features": {...}, "text_features": {...} }


@app.get("/")
async def root():
    return {
        "service": "XGBoost Busy Detector",
        "version": "1.0.0",
        "endpoints": ["/predict", "/health"],
    }


@app.get("/health")
async def health():
    return {"status": "healthy", "model_loaded": handler.model is not None}


@app.post("/predict")
async def predict(request: PredictRequest):
    """Run XGBoost inference with evidence accumulation scoring."""
    result = handler({"inputs": request.inputs})
    return result


if __name__ == "__main__":
    import uvicorn
    import os
    port = int(os.environ.get("PORT", 7860))
    uvicorn.run(app, host="0.0.0.0", port=port)