Add normalize configuration contract

internal/config/normalize.go

@@ -0,0 +1,54 @@
+package config
+
+import (
+	"fmt"
+
+	"gopkg.in/yaml.v3"
+)
+
+const (
+	defaultNormalizeOutputPath   = "transcripts/normalized.json"
+	defaultNormalizeOutputSchema = "seriatim-intermediate"
+)
+
+// UnmarshalYAML tracks explicit normalize.output_path presence so validation can
+// distinguish omitted vs explicitly empty values.
+func (cfg *NormalizeConfig) UnmarshalYAML(node *yaml.Node) error {
+	if node.Kind != yaml.MappingNode {
+		return fmt.Errorf("normalize must be a mapping")
+	}
+	allowedKeys := map[string]struct{}{
+		"output_path":   {},
+		"output_schema": {},
+		"report":        {},
+	}
+	for i := 0; i+1 < len(node.Content); i += 2 {
+		key := node.Content[i].Value
+		if _, ok := allowedKeys[key]; !ok {
+			return fmt.Errorf("field %q not found in type config.NormalizeConfig", key)
+		}
+	}
+
+	type rawNormalize NormalizeConfig
+	var raw rawNormalize
+	if err := node.Decode(&raw); err != nil {
+		return err
+	}
+	*cfg = NormalizeConfig(raw)
+	for i := 0; i+1 < len(node.Content); i += 2 {
+		if node.Content[i].Value == "output_path" {
+			cfg.outputPathSet = true
+			break
+		}
+	}
+	return nil
+}
+
+// outputPathSet records whether normalize.output_path appeared in YAML.
+// This is intentionally unexported and not serialized.
+func (cfg *NormalizeConfig) outputPathWasSet() bool {
+	if cfg == nil {
+		return false
+	}
+	return cfg.outputPathSet
+}