# -*- coding: utf-8 -*-
"""NVIDIA GPU 推理后端实现（5090，Triton/ONNX）。

对应 PRD 5.6：5090 实现（Triton/ONNX）——通过 OpenAI 兼容接口
（vLLM / Triton Inference Server）对外提供推理，业务侧统一走
`InferenceBackend` 接口，不感知硬件。
"""
from inference_backend.base import InferenceBackend, InferRequest, InferResult


class NvidiaGpuBackend(InferenceBackend):
    """NVIDIA GPU 后端：面向 5090 服务器（Triton/ONNX，OpenAI 兼容）。"""

    backend_name = "gpu"

    def __init__(self, endpoint: str = "", model: str = "iaop-default",
                 timeout_seconds: float = 10.0, runtime: str = "vllm",
                 device: str = "nvidia-5090", **kwargs):
        super().__init__(endpoint, model, timeout_seconds)
        self.runtime = runtime          # vllm | triton
        self.device = device            # 硬件型号（默认 5090）
        self._loaded = False

    def load_model(self, model_name: str | None = None) -> dict:
        """加载模型到 GPU。无 endpoint 时仅维护本地状态（适配层就绪）。"""
        model_name = model_name or self.model
        if not self.endpoint:
            self._loaded = True
            return {"status": "ok", "backend": self.backend_name,
                    "model": model_name, "device": self.device,
                    "reason": "dry-run（未配置 endpoint）"}
        body = self._post_json("/v1/models/load",
                               {"model": model_name, "device": self.device})
        self._loaded = body.get("status") in ("ok", "loaded", "ready")
        return body

    def infer(self, request: InferRequest) -> InferResult:
        """OpenAI 兼容生成（/v1/chat/completions）。"""
        started = __import__("time").monotonic()
        payload = request.to_payload()
        payload["model"] = payload["model"] or self.model
        body = self._post_json("/v1/chat/completions", payload)
        latency_ms = round((__import__("time").monotonic() - started) * 1000, 2)
        try:
            text = body["choices"][0]["message"]["content"]
        except (KeyError, IndexError, TypeError):
            text = str(body)
        return InferResult(
            text=text,
            backend=self.backend_name,
            latency_ms=latency_ms,
            meta={"runtime": self.runtime, "device": self.device,
                  "model": self.model, "raw": body},
        )

    def health(self) -> dict:
        """健康巡检：探测 /health，返回后端/设备/运行时信息。"""
        base = self._healthz()
        base.update({
            "backend": self.backend_name,
            "runtime": self.runtime,
            "device": self.device,
            "model": self.model,
            "loaded": self._loaded,
        })
        return base

    def unload(self) -> dict:
        """卸载模型、释放显存。"""
        self._loaded = False
        if not self.endpoint:
            return {"status": "ok", "backend": self.backend_name,
                    "reason": "dry-run（未配置 endpoint）"}
        return self._post_json("/v1/models/unload", {"model": self.model})