Run normalization in process command

internal/cli/run.go

@@ -10,6 +10,7 @@ import (
 
 	"gitea.maximumdirect.net/eric/audita/internal/core/config"
 	"gitea.maximumdirect.net/eric/audita/internal/core/io"
+	"gitea.maximumdirect.net/eric/audita/internal/core/normalization"
 	"gitea.maximumdirect.net/eric/audita/internal/core/reporting"
 	"gitea.maximumdirect.net/eric/audita/internal/core/schema"
 )
@@ -45,8 +46,8 @@ var processRunner = func(inv processInvocation, stdout io.Writer) error {
 		return fmt.Errorf("invalid glossary: %w", err)
 	}
 
-	// Convert to canonical transcript format for output
-	outputTranscript := &schema.Transcript{
+	// Convert to canonical transcript format for normalization
+	normalizedTranscript := &schema.Transcript{
 		Segments: make([]schema.Segment, len(transcript.Segments)),
 	}
 	for i, s := range transcript.Segments {
@@ -54,7 +55,7 @@ var processRunner = func(inv processInvocation, stdout io.Writer) error {
 		if s.ID != nil {
 			id = *s.ID
 		}
-		outputTranscript.Segments[i] = schema.Segment{
+		normalizedTranscript.Segments[i] = schema.Segment{
 			ID:         id,
 			Speaker:    s.Speaker,
 			Start:      s.Start,
@@ -64,8 +65,18 @@ var processRunner = func(inv processInvocation, stdout io.Writer) error {
 		}
 	}
 
-	// Serialize output transcript to JSON
-	outputBytes, err := schema.TranscriptToJSON(outputTranscript)
+	// Apply deterministic normalization
+	normalizer := normalization.NewNormalizer(normalization.NormalizationConfig{
+		MaxSegmentGap:      inv.Config.Normalization.MaxSegmentGap,
+		EllipsisGap:        inv.Config.Normalization.EllipsisGap,
+		MaxSegmentDuration: inv.Config.Normalization.MaxSegmentDuration,
+		MaxSegmentTokens:   inv.Config.Normalization.MaxSegmentTokens,
+	})
+
+	normalizedTranscript, _ = normalizer.Normalize(normalizedTranscript)
+
+	// Serialize normalized transcript to JSON
+	outputBytes, err := schema.TranscriptToJSON(normalizedTranscript)
 	if err != nil {
 		return fmt.Errorf("failed to serialize transcript: %w", err)
 	}