Add configurable transient retries for CLI execution

internal/config/config.go

@@ -33,12 +33,13 @@ var (
 
 // Config is the on-disk YAML shape for application-level settings.
 type Config struct {
-	PromptDir  string                   `yaml:"prompt_dir"`
-	ProfileDir string                   `yaml:"profile_dir"`
-	SchemaDir  string                   `yaml:"schema_dir"`
-	Server     ServerConfig             `yaml:"server"`
-	Defaults   DefaultsConfig           `yaml:"defaults"`
-	Backends   map[string]BackendConfig `yaml:"backends"`
+	PromptDir        string                   `yaml:"prompt_dir"`
+	ProfileDir       string                   `yaml:"profile_dir"`
+	SchemaDir        string                   `yaml:"schema_dir"`
+	TransientRetries *strictInteger           `yaml:"transient_retries"`
+	Server           ServerConfig             `yaml:"server"`
+	Defaults         DefaultsConfig           `yaml:"defaults"`
+	Backends         map[string]BackendConfig `yaml:"backends"`
 }
 
 type BackendConfig struct {
@@ -49,6 +50,20 @@ type BackendConfig struct {
 	QueueCapacity    *int           `yaml:"queue_capacity"`
 }
 
+type strictInteger int
+
+func (value *strictInteger) UnmarshalYAML(node *yaml.Node) error {
+	if node.Tag != "!!int" {
+		return fmt.Errorf("expected integer, got %s", node.Tag)
+	}
+	var decoded int
+	if err := node.Decode(&decoded); err != nil {
+		return err
+	}
+	*value = strictInteger(decoded)
+	return nil
+}
+
 type BackendSettings struct {
 	ID               string
 	Endpoint         string
@@ -82,6 +97,7 @@ type AppSettings struct {
 	MaxResponseBytes    int64
 	DefaultRenderFormat renderformat.PreparedRunOutputFormat
 	Backends            []BackendSettings
+	TransientRetries    *int
 }
 
 // CLIOverrides can be applied after config load to enforce precedence.
@@ -224,6 +240,13 @@ func decodeConfig(raw []byte) (Config, error) {
 
 func applyConfig(base AppSettings, cfg Config) (AppSettings, error) {
 	out := base
+	if cfg.TransientRetries != nil {
+		if *cfg.TransientRetries < 0 {
+			return AppSettings{}, fmt.Errorf("%w: transient_retries must be greater than or equal to 0", ErrInvalidConfig)
+		}
+		value := int(*cfg.TransientRetries)
+		out.TransientRetries = &value
+	}
 
 	if v := strings.TrimSpace(cfg.PromptDir); v != "" {
 		out.PromptDir = filepath.Clean(v)

internal/config/config_test.go

@@ -239,6 +239,44 @@ server:
 	}
 }
 
+func TestLoadConfigPreservesTransientRetryPresence(t *testing.T) {
+	for _, tc := range []struct {
+		name string
+		body string
+		want *int
+	}{
+		{name: "omitted", body: "prompt_dir: ./prompts\n"},
+		{name: "null", body: "transient_retries: null\n"},
+		{name: "zero", body: "transient_retries: 0\n", want: intPointer(0)},
+		{name: "positive", body: "transient_retries: 3\n", want: intPointer(3)},
+	} {
+		t.Run(tc.name, func(t *testing.T) {
+			settings, err := LoadConfig(writeConfigFile(t, "config.yml", tc.body), true)
+			if err != nil {
+				t.Fatal(err)
+			}
+			if !reflect.DeepEqual(settings.TransientRetries, tc.want) {
+				t.Fatalf("retry setting: got %v, want %v", settings.TransientRetries, tc.want)
+			}
+		})
+	}
+	for _, tc := range []struct {
+		body string
+		want error
+	}{
+		{body: "transient_retries: -1\n", want: ErrInvalidConfig},
+		{body: "transient_retries: wrong\n", want: ErrInvalidConfigYAML},
+		{body: "transient_retries: 1.5\n", want: ErrInvalidConfigYAML},
+	} {
+		_, err := LoadConfig(writeConfigFile(t, "config.yml", tc.body), true)
+		if !errors.Is(err, tc.want) {
+			t.Fatalf("body %q: expected %v, got %v", tc.body, tc.want, err)
+		}
+	}
+}
+
+func intPointer(value int) *int { return &value }
+
 func TestLoadConfigRejectsNegativeHTTPSizeLimits(t *testing.T) {
 	tests := []struct {
 		name string