Add DefaultOnDemandStart configuration and update instance options

pkg/config/config.go

@@ -67,6 +67,9 @@ type InstancesConfig struct {
 	// Default restart delay for new instances (in seconds)
 	DefaultRestartDelay int `yaml:"default_restart_delay"`
 
+	// Default on-demand start setting for new instances
+	DefaultOnDemandStart bool `yaml:"default_on_demand_start"`
+
 	// Interval for checking instance timeouts (in minutes)
 	TimeoutCheckInterval int `yaml:"timeout_check_interval"`
 }
@@ -111,6 +114,7 @@ func LoadConfig(configPath string) (AppConfig, error) {
 			DefaultAutoRestart:   true,
 			DefaultMaxRestarts:   3,
 			DefaultRestartDelay:  5,
+			DefaultOnDemandStart: false,
 			TimeoutCheckInterval: 5, // Check timeouts every 5 minutes
 		},
 		Auth: AuthConfig{
@@ -221,6 +225,11 @@ func loadEnvVars(cfg *AppConfig) {
 			cfg.Instances.DefaultRestartDelay = seconds
 		}
 	}
+	if onDemandStart := os.Getenv("LLAMACTL_DEFAULT_ON_DEMAND_START"); onDemandStart != "" {
+		if b, err := strconv.ParseBool(onDemandStart); err == nil {
+			cfg.Instances.DefaultOnDemandStart = b
+		}
+	}
 	if timeoutCheckInterval := os.Getenv("LLAMACTL_TIMEOUT_CHECK_INTERVAL"); timeoutCheckInterval != "" {
 		if minutes, err := strconv.Atoi(timeoutCheckInterval); err == nil {
 			cfg.Instances.TimeoutCheckInterval = minutes

pkg/instance/instance.go

@@ -34,7 +34,9 @@ type CreateInstanceOptions struct {
 	AutoRestart  *bool `json:"auto_restart,omitempty"`
 	MaxRestarts  *int  `json:"max_restarts,omitempty"`
 	RestartDelay *int  `json:"restart_delay,omitempty"`
-	// Timeout
+	// On demand start
+	OnDemandStart *bool `json:"on_demand_start,omitempty"`
+	// Idle timeout
 	IdleTimeout *int `json:"idle_timeout,omitempty"`
 	// LlamaServerOptions contains the options for the llama server
 	llamacpp.LlamaServerOptions `json:",inline"`
@@ -49,6 +51,7 @@ func (c *CreateInstanceOptions) UnmarshalJSON(data []byte) error {
 		AutoRestart   *bool `json:"auto_restart,omitempty"`
 		MaxRestarts   *int  `json:"max_restarts,omitempty"`
 		RestartDelay  *int  `json:"restart_delay,omitempty"`
+		OnDemandStart *bool `json:"on_demand_start,omitempty"`
 		IdleTimeout   *int  `json:"idle_timeout,omitempty"`
 	}
 
@@ -61,6 +64,7 @@ func (c *CreateInstanceOptions) UnmarshalJSON(data []byte) error {
 	c.AutoRestart = temp.AutoRestart
 	c.MaxRestarts = temp.MaxRestarts
 	c.RestartDelay = temp.RestartDelay
+	c.OnDemandStart = temp.OnDemandStart
 	c.IdleTimeout = temp.IdleTimeout
 
 	// Now unmarshal the embedded LlamaServerOptions
@@ -138,6 +142,11 @@ func validateAndCopyOptions(name string, options *CreateInstanceOptions) *Create
 			optionsCopy.RestartDelay = &restartDelay
 		}
 
+		if options.OnDemandStart != nil {
+			onDemandStart := *options.OnDemandStart
+			optionsCopy.OnDemandStart = &onDemandStart
+		}
+
 		if options.IdleTimeout != nil {
 			idleTimeout := *options.IdleTimeout
 			if idleTimeout < 0 {
@@ -172,6 +181,11 @@ func applyDefaultOptions(options *CreateInstanceOptions, globalSettings *config.
 		options.RestartDelay = &defaultRestartDelay
 	}
 
+	if options.OnDemandStart == nil {
+		defaultOnDemandStart := globalSettings.DefaultOnDemandStart
+		options.OnDemandStart = &defaultOnDemandStart
+	}
+
 	if options.IdleTimeout == nil {
 		defaultIdleTimeout := 0
 		options.IdleTimeout = &defaultIdleTimeout