Updated DefaultWordRunReorderWindow to 1.0

internal/cli/merge_test.go

@@ -8,6 +8,7 @@ import (
 	"strings"
 	"testing"
 
+	"gitea.maximumdirect.net/eric/seriatim/internal/config"
 	"gitea.maximumdirect.net/eric/seriatim/internal/model"
 	"gitea.maximumdirect.net/eric/seriatim/internal/report"
 	"gitea.maximumdirect.net/eric/seriatim/schema"
@@ -342,6 +343,8 @@ func TestMergeDetectsOverlapGroups(t *testing.T) {
 }
 
 func TestMergeResolvesOverlapGroupsWithWordRuns(t *testing.T) {
+	t.Setenv(config.WordRunReorderWindowEnv, "0.4")
+
 	dir := t.TempDir()
 	inputA := writeJSONFile(t, dir, "a.json", `{
 		"segments": [
@@ -1677,6 +1680,75 @@ func TestMergeResolveOverlapsAbsorbsNearbyContext(t *testing.T) {
 	}
 }
 
+func TestMergeResolveOverlapsPreservesAbsorbedContextPrefix(t *testing.T) {
+	dir := t.TempDir()
+	inputA := writeJSONFile(t, dir, "a.json", `{
+		"segments": [
+			{
+				"start": 7,
+				"end": 9.95,
+				"text": "full context prefix near",
+				"words": [
+					{"word": "full", "start": 7.1, "end": 7.2},
+					{"word": "context", "start": 7.3, "end": 7.4},
+					{"word": "prefix", "start": 7.5, "end": 7.6},
+					{"word": "near", "start": 9.7, "end": 9.9}
+				]
+			},
+			{
+				"start": 10,
+				"end": 11,
+				"text": "inside",
+				"words": [
+					{"word": "inside", "start": 10.5, "end": 10.7}
+				]
+			}
+		]
+	}`)
+	inputB := writeJSONFile(t, dir, "b.json", `{
+		"segments": [
+			{
+				"start": 10.2,
+				"end": 11,
+				"text": "bob",
+				"words": [
+					{"word": "bob", "start": 10.4, "end": 10.6}
+				]
+			}
+		]
+	}`)
+	speakers := writeYAMLFile(t, dir, "speakers.yml", `match:
+  - speaker: Alice
+    match: ["a.json"]
+  - speaker: Bob
+    match: ["b.json"]
+`)
+	output := filepath.Join(dir, "merged.json")
+
+	err := executeMerge(
+		"--input-file", inputA,
+		"--input-file", inputB,
+		"--speakers", speakers,
+		"--output-schema", "minimal",
+		"--output-file", output,
+	)
+	if err != nil {
+		t.Fatalf("merge failed: %v", err)
+	}
+
+	var transcript schema.MinimalTranscript
+	readJSON(t, output, &transcript)
+	aliceText := make([]string, 0)
+	for _, segment := range transcript.Segments {
+		if segment.Speaker == "Alice" {
+			aliceText = append(aliceText, segment.Text)
+		}
+	}
+	if strings.Join(aliceText, " ") != "full context prefix near inside" {
+		t.Fatalf("expected full absorbed context prefix in Alice output, got %#v", transcript.Segments)
+	}
+}
+
 func TestInvalidTimingFails(t *testing.T) {
 	tests := []struct {
 		name string