Monitor: hotkeys (q quit, u update now) with footer line; show GPU VRAM usage

cmd/gpu-turnstile/main.go

@@ -728,9 +728,11 @@ func run(ctx context.Context, cfg config.Config, log *slog.Logger, logOut io.Wri
 
 	// Foreign GPU holders (games, other ML jobs) — enabled by GAME_PROCS
 	// and/or GPU_FOREIGN_VRAM_MB — hold the lock externally while they run.
+	// gw collects the VRAM reading for the status channel.
+	gw := &gpuWatch{}
 	if len(cfg.GameProcs) > 0 || cfg.GPUForeignVRAMMB > 0 {
 		det := game.New(cfg.GameProcs, cfg.GPUForeignVRAMMB, cfg.GPUIgnoreProcs, log)
-		go gameLoop(ctx, cfg, log, det, lk, ollamaClient, comfySup)
+		go gameLoop(ctx, cfg, log, det, lk, ollamaClient, comfySup, gw)
 	}
 
 	// Bind the listeners up front so a port conflict fails fast and the
@@ -809,7 +811,7 @@ func run(ctx context.Context, cfg config.Config, log *slog.Logger, logOut io.Wri
 	// AUTO_UPDATE.
 	if isService {
 		serveControl(ctx, log, u, exePath, applyStaged,
-			statusProvider(cfg, lk, comfySup, health, started),
+			statusProvider(cfg, lk, comfySup, health, started, gw),
 			reloadHandler(cfg, configPath, restartWhenIdle))
 	}
 
@@ -834,12 +836,34 @@ func run(ctx context.Context, cfg config.Config, log *slog.Logger, logOut io.Wri
 // (idle); health checks skip it instead of logging an outage.
 var errManagedDown = errors.New("managed upstream intentionally stopped")
 
+// gpuWatch records the latest VRAM reading from the game detector's poll
+// loop, for the status channel. Known stays false when game detection is
+// not configured (no nvidia-smi polling happens then).
+type gpuWatch struct {
+	mu     sync.Mutex
+	usedMB int
+	total  int
+	known  bool
+}
+
+func (g *gpuWatch) set(used, total int) {
+	g.mu.Lock()
+	g.usedMB, g.total, g.known = used, total, true
+	g.mu.Unlock()
+}
+
+func (g *gpuWatch) get() (used, total int, known bool) {
+	g.mu.Lock()
+	defer g.mu.Unlock()
+	return g.usedMB, g.total, g.known
+}
+
 // gameLoop polls for foreign GPU holders (a game, another ML job). While one
 // is detected it holds the lock externally so new LLM and image requests
 // wait (or are rejected per LLM_BUSY_MODE), and — once in-flight work has
 // drained — frees VRAM for it: the managed ComfyUI is stopped and Ollama's
 // resident models are unloaded.
-func gameLoop(ctx context.Context, cfg config.Config, log *slog.Logger, det *game.Detector, lk *lock.Lock, ollamaClient *ollama.Client, comfySup *supervise.Process) {
+func gameLoop(ctx context.Context, cfg config.Config, log *slog.Logger, det *game.Detector, lk *lock.Lock, ollamaClient *ollama.Client, comfySup *supervise.Process, gw *gpuWatch) {
 	ticker := time.NewTicker(cfg.GamePollInterval)
 	defer ticker.Stop()
 	held, freed := false, false
@@ -853,6 +877,9 @@ func gameLoop(ctx context.Context, cfg config.Config, log *slog.Logger, det *gam
 		if err != nil && ctx.Err() == nil {
 			log.Warn("game detection failed", "err", err)
 		}
+		if used, total, verr := game.QueryVRAMMB(ctx); verr == nil {
+			gw.set(used, total)
+		}
 		switch {
 		case len(holders) > 0 && !held:
 			held = true
@@ -1070,11 +1097,20 @@ type statusSnapshot struct {
 	UptimeS     int64              `json:"uptime_s"`
 	Downstreams []statusDownstream `json:"downstreams"`
 	Lock        statusLock         `json:"lock"`
+	// GPU carries the latest VRAM reading; Known is false when game
+	// detection (and with it nvidia-smi polling) is not configured.
+	GPU statusGPU `json:"gpu"`
 	// MonitorNote is set client-side (never over the wire) when the
 	// monitor's own binary differs from the service's version.
 	MonitorNote string `json:"-"`
 }
 
+type statusGPU struct {
+	UsedMB  int  `json:"used_mb"`
+	TotalMB int  `json:"total_mb"`
+	Known   bool `json:"known"`
+}
+
 // reloadHandler re-reads and validates the service's config file for
 // CmdReloadEnv. An invalid config is reported and the service keeps running
 // untouched; a valid, changed config triggers a GPU-idle-gated restart onto
@@ -1109,12 +1145,14 @@ func diffConfig(a, b config.Config) []string {
 }
 
 // statusProvider assembles the one-line JSON snapshot for CmdStatus.
-func statusProvider(cfg config.Config, lk *lock.Lock, comfySup *supervise.Process, health *healthTracker, started time.Time) func() string {
+func statusProvider(cfg config.Config, lk *lock.Lock, comfySup *supervise.Process, health *healthTracker, started time.Time, gw *gpuWatch) func() string {
 	return func() string {
 		snap := statusSnapshot{
 			Version: version,
 			UptimeS: int64(time.Since(started).Seconds()),
 		}
+		used, total, known := gw.get()
+		snap.GPU = statusGPU{UsedMB: used, TotalMB: total, Known: known}
 		if cfg.OllamaURL != "" {
 			snap.Downstreams = append(snap.Downstreams, statusDownstream{
 				Name: "ollama", URL: cfg.OllamaURL, Up: health.get("ollama"),