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
 	}

internal/config/config_test.go

@@ -74,6 +74,29 @@ func TestAppVersion(t *testing.T) {
 	}
 }
 
+func TestComfyCmdRequiresURL(t *testing.T) {
+	_, err := Load(func(k string) string {
+		if k == "COMFY_CMD" {
+			return "python main.py"
+		}
+		return ""
+	})
+	if err == nil || !strings.Contains(err.Error(), "COMFY_CMD requires COMFY_URL") {
+		t.Fatalf("err = %v, want COMFY_CMD/COMFY_URL validation error", err)
+	}
+	if _, err := Load(func(k string) string {
+		switch k {
+		case "COMFY_CMD":
+			return "python main.py"
+		case "COMFY_URL":
+			return "http://127.0.0.1:8188"
+		}
+		return ""
+	}); err != nil {
+		t.Fatalf("COMFY_CMD with COMFY_URL must load: %v", err)
+	}
+}
+
 func TestParseEnvFile(t *testing.T) {
 	input := `# comment
 OLLAMA_URL=http://host:11435

internal/config/sample.go

@@ -28,6 +28,10 @@ func sampleEntries(logFile string) []sampleEntry {
 		{"OLLAMA_URL", "http://127.0.0.1:11434", "Ollama upstream URL; setting it enables the Ollama consumer (default: empty = disabled)", false},
 		{"COMFY_URL", "http://127.0.0.1:8188", "ComfyUI upstream URL; setting it enables the ComfyUI consumer (default: empty = disabled)", false},
 		{"WARM_MODEL", "", "Optional model to reload after an image job (default: empty = none)", false},
+		{"COMFY_CMD", `"C:\ComfyUI\.venv\Scripts\python.exe" ComfyUI\main.py --port 8188`, "Spawn and supervise ComfyUI on demand: the first request starts it, it stops after COMFY_IDLE_TIMEOUT to free VRAM (default: empty = unmanaged)", false},
+		{"COMFY_DIR", `C:\ComfyUI`, "Working directory for COMFY_CMD (default: empty = inherit)", false},
+		{"COMFY_IDLE_TIMEOUT", "5m", "Stop the managed ComfyUI after this long without requests or jobs (frees VRAM)", false},
+		{"COMFY_START_TIMEOUT", "2m", "How long a request waits for the managed ComfyUI to come up", false},
 		{"UNLOAD_TIMEOUT", "60s", "How long to wait for Ollama to unload a model", false},
 		{"JOB_TIMEOUT", "15m", "Maximum time to wait for a ComfyUI job", false},
 		{"LLM_WAIT_TIMEOUT", "10m", "Max time an LLM request waits for the GPU before being answered 503 (wait mode)", false},