Game detection: foreign GPU holders take an external lock hold (GAME_PROCS, GPU_FOREIGN_VRAM_MB)

internal/config/config.go

@@ -61,6 +61,17 @@ type Config struct {
 	ComfyIdleTimeout  time.Duration
 	ComfyStartTimeout time.Duration
 
+	// GameProcs (GAME_PROCS) is a watch list of process names; while any of
+	// them runs, the GPU is treated as held by a foreign process. The
+	// nvidia-smi path (GPUForeignVRAMMB, GPU_FOREIGN_VRAM_MB) does the same
+	// when a process not in GPUIgnoreProcs (GPU_IGNORE_PROCS) holds more than
+	// that many MiB of VRAM. GamePollInterval (GAME_POLL_INTERVAL) is how
+	// often both checks run.
+	GameProcs        []string
+	GPUForeignVRAMMB int
+	GPUIgnoreProcs   []string
+	GamePollInterval time.Duration
+
 	WarmModel string
 	LogLevel  slog.Level
 	LogJSON   bool
@@ -102,6 +113,11 @@ func Defaults() Config {
 		ComfyIdleTimeout:  5 * time.Minute,
 		ComfyStartTimeout: 2 * time.Minute,
 
+		// ComfyUI runs under python; excluding it (and Ollama) by name keeps
+		// our own consumers from tripping the foreign-VRAM check.
+		GPUIgnoreProcs:   []string{"ollama", "ollama app", "ollama_llama_server", "python", "pythonw"},
+		GamePollInterval: 5 * time.Second,
+
 		LogLevel: slog.LevelWarn,
 	}
 }
@@ -137,6 +153,17 @@ func ParseEnvFile(r io.Reader) (map[string]string, error) {
 	return values, scanner.Err()
 }
 
+// splitList parses a comma-separated setting into trimmed, non-empty items.
+func splitList(v string) []string {
+	var out []string
+	for _, item := range strings.Split(v, ",") {
+		if item = strings.TrimSpace(item); item != "" {
+			out = append(out, item)
+		}
+	}
+	return out
+}
+
 func envDuration(getenv func(string) string, name string, dst *time.Duration) error {
 	v := getenv(name)
 	if v == "" {
@@ -192,11 +219,25 @@ func Load(getenv func(string) string) (Config, error) {
 		{"COMFY_IDLE_TIMEOUT", &cfg.ComfyIdleTimeout},
 		{"COMFY_START_TIMEOUT", &cfg.ComfyStartTimeout},
 		{"UPDATE_INTERVAL", &cfg.UpdateInterval},
+		{"GAME_POLL_INTERVAL", &cfg.GamePollInterval},
 	} {
 		if err := envDuration(getenv, e.name, e.dst); err != nil {
 			return cfg, err
 		}
 	}
+	if v := getenv("GAME_PROCS"); v != "" {
+		cfg.GameProcs = splitList(v)
+	}
+	if v := getenv("GPU_IGNORE_PROCS"); v != "" {
+		cfg.GPUIgnoreProcs = splitList(v)
+	}
+	if v := getenv("GPU_FOREIGN_VRAM_MB"); v != "" {
+		n, err := strconv.Atoi(v)
+		if err != nil || n < 0 {
+			return cfg, fmt.Errorf("GPU_FOREIGN_VRAM_MB: must be a non-negative integer (MiB, 0 = disabled)")
+		}
+		cfg.GPUForeignVRAMMB = n
+	}
 	if v := getenv("PROMPT_CAPTURE_LIMIT"); v != "" {
 		n, err := strconv.ParseInt(v, 10, 64)
 		if err != nil || n < 0 {