Managed ComfyUI: COMFY_CMD starts it on demand, idle stop frees VRAM (internal/supervise)

internal/config/config.go

@@ -51,6 +51,16 @@ type Config struct {
 	LLMBusyStatus  int
 	BusyRetryAfter int
 
+	// ComfyCmd spawns and supervises a ComfyUI server on demand (empty =
+	// unmanaged, the current behavior). ComfyDir is its working directory.
+	// The managed server is stopped after ComfyIdleTimeout without
+	// requests, freeing its VRAM; ComfyStartTimeout bounds how long a
+	// request waits for it to come up.
+	ComfyCmd          string
+	ComfyDir          string
+	ComfyIdleTimeout  time.Duration
+	ComfyStartTimeout time.Duration
+
 	WarmModel string
 	LogLevel  slog.Level
 	LogJSON   bool
@@ -89,6 +99,9 @@ func Defaults() Config {
 		LLMBusyStatus:  503,
 		BusyRetryAfter: 30,
 
+		ComfyIdleTimeout:  5 * time.Minute,
+		ComfyStartTimeout: 2 * time.Minute,
+
 		LogLevel: slog.LevelWarn,
 	}
 }
@@ -150,6 +163,8 @@ func Load(getenv func(string) string) (Config, error) {
 		{"OLLAMA_URL", &cfg.OllamaURL},
 		{"COMFY_URL", &cfg.ComfyURL},
 		{"WARM_MODEL", &cfg.WarmModel},
+		{"COMFY_CMD", &cfg.ComfyCmd},
+		{"COMFY_DIR", &cfg.ComfyDir},
 		{"UPDATE_REPO", &cfg.UpdateRepo},
 		{"UPDATE_ASSET", &cfg.UpdateAsset},
 		{"LOG_FILE", &cfg.LogFile},
@@ -174,6 +189,8 @@ func Load(getenv func(string) string) (Config, error) {
 		{"SHUTDOWN_TIMEOUT", &cfg.ShutdownTimeout},
 		{"BACKOFF_INITIAL", &cfg.BackoffInitial},
 		{"BACKOFF_MAX", &cfg.BackoffMax},
+		{"COMFY_IDLE_TIMEOUT", &cfg.ComfyIdleTimeout},
+		{"COMFY_START_TIMEOUT", &cfg.ComfyStartTimeout},
 		{"UPDATE_INTERVAL", &cfg.UpdateInterval},
 	} {
 		if err := envDuration(getenv, e.name, e.dst); err != nil {
@@ -244,6 +261,9 @@ func Load(getenv func(string) string) (Config, error) {
 	default:
 		return cfg, fmt.Errorf("LOG_FORMAT: must be \"text\" or \"json\"")
 	}
+	if cfg.ComfyCmd != "" && cfg.ComfyURL == "" {
+		return cfg, fmt.Errorf("COMFY_CMD requires COMFY_URL to be set (the proxy needs somewhere to forward)")
+	}
 	if cfg.OllamaURL == "" && cfg.ComfyURL == "" {
 		return cfg, ErrNoConsumer
 	}