Add canonical source unit provenance

internal/modules/generic/chunk/units/chunker.go

@@ -243,6 +243,7 @@ func cloneUnits(units []source.SourceUnit) []source.SourceUnit {
 			ID:       unit.ID,
 			Kind:     unit.Kind,
 			Text:     unit.Text,
+			Ref:      unit.Ref,
 			Metadata: cloneMetadata(unit.Metadata),
 		})
 	}

internal/modules/generic/chunk/units/chunker_test.go

@@ -169,11 +169,15 @@ func TestChunkDefensivelyCopiesUnits(t *testing.T) {
 	}
 
 	doc.Units[0].ID = 99
+	doc.Units[0].Ref.SourceID = "changed"
 	doc.Units[0].Metadata["speaker"] = "changed"
 
 	if result.Chunks[0].Units[0].ID != 1 {
 		t.Fatalf("chunk unit ID changed after source mutation: %#v", result.Chunks[0].Units[0])
 	}
+	if got := result.Chunks[0].Units[0].Ref.SourceID; got != "source-1" {
+		t.Fatalf("chunk unit ref changed after source mutation: %#v", result.Chunks[0].Units[0].Ref)
+	}
 	if result.Chunks[0].Units[0].Metadata["speaker"] != "speaker-001" {
 		t.Fatalf("chunk unit metadata changed after source mutation: %#v", result.Chunks[0].Units[0].Metadata)
 	}
@@ -186,6 +190,7 @@ func testSource(count int) *source.SourceDocument {
 			ID:   i,
 			Kind: "unit",
 			Text: "Text for " + zeroPad3(i),
+			Ref:  source.SourceRef{SourceID: "source-1", StartUnitID: i, EndUnitID: i},
 			Metadata: map[string]any{
 				"speaker": "speaker-" + zeroPad3(i),
 			},