"""GPU load readout via nvidia-smi (present in the container thanks to the
NVIDIA Container Toolkit's `utility` capability). Returns None if unavailable —
the UI just shows n/a (e.g. CPU-fallback run).

Reads are CACHED and de-duplicated: the UI meter polls fast, /status reads it,
and the autoscaler samples it — if each spawned its own `nvidia-smi` (slow on a
busy GPU) those blocking subprocesses would pile up in the server's thread pool
and make the Start/Stop buttons feel dead. So a short TTL serves recent callers
from cache, and only ONE probe runs at a time (others get the last value)."""
import subprocess
import threading
import time

_TTL = 1.0                       # seconds a sample is reused before re-probing
_lock = threading.Lock()
_cache: dict | None = None
_cache_t = 0.0
_probing = False


def _probe() -> dict | None:
    try:
        out = subprocess.run(
            [
                "nvidia-smi",
                "--query-gpu=utilization.gpu,memory.used,memory.total,temperature.gpu",
                "--format=csv,noheader,nounits",
            ],
            capture_output=True, text=True, timeout=5, check=True,
        ).stdout.strip().splitlines()
    except (OSError, subprocess.SubprocessError):
        return None
    if not out:
        return None
    parts = [p.strip() for p in out[0].split(",")]
    try:
        return {
            "util_pct": int(float(parts[0])),
            "mem_used_mb": int(float(parts[1])),
            "mem_total_mb": int(float(parts[2])),
            "temp_c": int(float(parts[3])),
        }
    except (ValueError, IndexError):
        return None


def read_gpu(max_age: float = _TTL) -> dict | None:
    """Latest GPU reading, cached. Serves from cache when fresh; when stale,
    exactly one caller re-probes while the rest get the last value — so request
    threads never block behind more than one `nvidia-smi`."""
    global _cache, _cache_t, _probing
    now = time.monotonic()
    with _lock:
        fresh = _cache is not None and (now - _cache_t) < max_age
        if fresh or _probing:        # fresh, or a probe is already running
            return _cache
        _probing = True
    try:
        val = _probe()
    finally:
        with _lock:
            _cache = val
            _cache_t = time.monotonic()
            _probing = False
    return val