Monitor: show Ollama's loaded models, their VRAM footprint, and busy state

The status snapshot now queries /api/ps (2s timeout so a wedged Ollama
cannot stall the channel) and the ollama line renders e.g.
'UP · llama3.1:8b (4.8 GiB VRAM) · busy'; comfy gets the busy marker
too while an image job runs.

cmd/gpu-turnstile/main.go

@@ -813,7 +813,7 @@ 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, gw),
+			statusProvider(cfg, lk, comfySup, health, started, gw, ollamaClient),
 			reloadHandler(cfg, configPath, restartWhenIdle))
 	}
 
@@ -1106,6 +1106,16 @@ type statusDownstream struct {
 	URL     string `json:"url"`
 	Up      bool   `json:"up"`
 	Managed string `json:"managed,omitempty"`
+	// Models lists Ollama's loaded models with their VRAM footprint. Null
+	// when unknown (query failed / not applicable); [] means none loaded —
+	// deliberately no omitempty so the two stay distinguishable.
+	Models []statusModel `json:"models"`
+}
+
+// statusModel is one loaded Ollama model.
+type statusModel struct {
+	Name   string `json:"name"`
+	VRAMMB int64  `json:"vram_mb"` // 0 = resident in RAM, not VRAM
 }
 
 type statusLock struct {
@@ -1183,8 +1193,10 @@ func diffConfig(a, b config.Config) []string {
 	return out
 }
 
-// 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, gw *gpuWatch) func() string {
+// statusProvider assembles the one-line JSON snapshot for CmdStatus. The
+// loaded-model query to Ollama gets a short timeout so a wedged upstream
+// cannot stall the status channel for long.
+func statusProvider(cfg config.Config, lk *lock.Lock, comfySup *supervise.Process, health *healthTracker, started time.Time, gw *gpuWatch, ollamaClient *ollama.Client) func() string {
 	return func() string {
 		snap := statusSnapshot{
 			Version: version,
@@ -1197,9 +1209,21 @@ func statusProvider(cfg config.Config, lk *lock.Lock, comfySup *supervise.Proces
 			Foreign: foreign, AgeS: ageS,
 		}
 		if cfg.OllamaURL != "" {
-			snap.Downstreams = append(snap.Downstreams, statusDownstream{
+			d := statusDownstream{
 				Name: "ollama", URL: cfg.OllamaURL, Up: health.get("ollama"),
-			})
+			}
+			if ollamaClient != nil {
+				mctx, cancel := context.WithTimeout(context.Background(), 2*time.Second)
+				models, err := ollamaClient.LoadedModelDetails(mctx)
+				cancel()
+				if err == nil {
+					d.Models = make([]statusModel, 0, len(models))
+					for _, m := range models {
+						d.Models = append(d.Models, statusModel{Name: m.Name, VRAMMB: m.SizeVRAM / (1024 * 1024)})
+					}
+				}
+			}
+			snap.Downstreams = append(snap.Downstreams, d)
 		}
 		if cfg.ComfyURL != "" {
 			d := statusDownstream{Name: "comfy", URL: cfg.ComfyURL, Up: health.get("comfy")}