"""ML device selection (#872 — GPU enablement for the ml-worker).

The ml-worker is GPU-capable but must run unchanged on CPU (CI, non-GPU hosts).
Selection is a per-worker-HOST bootstrap concern (the GPU host runs CUDA, others
CPU), so it's an env var, not a DB setting — different workers need different
values. Each framework still ANDs this intent with its OWN runtime availability
(onnxruntime providers / torch.cuda), so "want GPU but none present" falls back
to CPU cleanly.

Env:
  FC_ML_DEVICE            auto (default) | cuda | gpu  -> try GPU;  cpu -> force CPU
  FC_ML_ONNX_GPU_MEM_GB   ONNX CUDA arena cap, GB (default 3) — the P4 is 8GB
                          total and torch shares it, so keep headroom.
  FC_ML_TORCH_MEM_FRACTION fraction of total VRAM torch may use (default 0.6).
"""

import os


def gpu_requested() -> bool:
    return os.environ.get("FC_ML_DEVICE", "auto").strip().lower() in (
        "auto", "cuda", "gpu",
    )


def onnx_gpu_mem_bytes() -> int:
    return int(float(os.environ.get("FC_ML_ONNX_GPU_MEM_GB", "3")) * 1024 ** 3)


def torch_mem_fraction() -> float:
    return float(os.environ.get("FC_ML_TORCH_MEM_FRACTION", "0.6"))