feat: support disabling image generation globally

- Added `disable-image-generation` configuration flag to disable the `image_generation` tool globally.
- Updated payload handling to remove `image_generation` tools from request payload arrays when the flag is enabled.
- Modified OpenAI image handlers (`ImagesGenerations`, `ImagesEdits`) to return 404 when the feature is disabled.
- Enhanced configuration diff logging to track changes for the `disable-image-generation` flag.
- Added accompanying unit tests for the new feature in payload helpers and image handler logic.

internal/config/config.go

@@ -610,6 +610,7 @@ func LoadConfigOptional(configFile string, optional bool) (*Config, error) {
 	cfg.ErrorLogsMaxFiles = 10
 	cfg.UsageStatisticsEnabled = false
 	cfg.DisableCooling = false
+	cfg.DisableImageGeneration = false
 	cfg.Pprof.Enable = false
 	cfg.Pprof.Addr = DefaultPprofAddr
 	cfg.AmpCode.RestrictManagementToLocalhost = false // Default to false: API key auth is sufficient

internal/config/sdk_config.go

@@ -9,6 +9,12 @@ type SDKConfig struct {
 	// ProxyURL is the URL of an optional proxy server to use for outbound requests.
 	ProxyURL string `yaml:"proxy-url" json:"proxy-url"`
 
+	// DisableImageGeneration disables the built-in image_generation tool when true.
+	// When enabled, the server will avoid injecting image_generation into request payloads,
+	// will remove any existing image_generation tool entries from tools arrays, and will
+	// return 404 for /v1/images/generations and /v1/images/edits.
+	DisableImageGeneration bool `yaml:"disable-image-generation" json:"disable-image-generation"`
+
 	// EnableGeminiCLIEndpoint controls whether Gemini CLI internal endpoints (/v1internal:*) are enabled.
 	// Default is false for safety; when false, /v1internal:* requests are rejected.
 	EnableGeminiCLIEndpoint bool `yaml:"enable-gemini-cli-endpoint" json:"enable-gemini-cli-endpoint"`