Centralize segment reference fallback in model

internal/model/model.go

@@ -1,5 +1,7 @@
 package model
 
+import "fmt"
+
 // RawTranscript is a loaded input document before canonical normalization.
 type RawTranscript struct {
 	Source   string       `json:"source"`
@@ -61,6 +63,17 @@ type Segment struct {
 	OverlapGroupID     int      `json:"overlap_group_id,omitempty"`
 }
 
+// SegmentReference returns the best available external reference for a segment.
+func SegmentReference(segment Segment) string {
+	if segment.Source != "" && segment.SourceSegmentIndex != nil {
+		return fmt.Sprintf("%s#%d", segment.Source, *segment.SourceSegmentIndex)
+	}
+	if segment.SourceRef != "" {
+		return segment.SourceRef
+	}
+	return ""
+}
+
 // Word preserves optional word-level timing data.
 type Word struct {
 	Text    string  `json:"text"`

internal/model/model_test.go

@@ -0,0 +1,41 @@
+package model
+
+import "testing"
+
+func TestSegmentReferenceUsesSourceAndIndexWhenAvailable(t *testing.T) {
+	index := 3
+	segment := Segment{
+		Source:             "input.json",
+		SourceSegmentIndex: &index,
+		SourceRef:          "word-run:1:2:3",
+	}
+
+	got := SegmentReference(segment)
+	want := "input.json#3"
+	if got != want {
+		t.Fatalf("reference = %q, want %q", got, want)
+	}
+}
+
+func TestSegmentReferenceFallsBackToSourceRef(t *testing.T) {
+	segment := Segment{
+		Source:    "input.json",
+		SourceRef: "coalesce:2",
+	}
+
+	got := SegmentReference(segment)
+	want := "coalesce:2"
+	if got != want {
+		t.Fatalf("reference = %q, want %q", got, want)
+	}
+}
+
+func TestSegmentReferenceReturnsEmptyWhenNoReferenceFieldsPresent(t *testing.T) {
+	segment := Segment{
+		Source: "input.json",
+	}
+
+	if got := SegmentReference(segment); got != "" {
+		t.Fatalf("reference = %q, want empty", got)
+	}
+}