Accept span deletions in structured responses

internal/framework/validators/llm_validators_test.go

@@ -2,6 +2,7 @@ package validators
 
 import (
 	"context"
+	"encoding/json"
 	"errors"
 	"strings"
 	"testing"
@@ -75,6 +76,43 @@ func mk(index int, orig, corr string) proposals.EnrichedCorrectionProposal {
 	}
 }
 
+func TestBuildLLMValidationRequestPreservesLiteralDeletionAndSpacing(t *testing.T) {
+	for _, tc := range []struct {
+		name, segment, original, replacement, result string
+	}{
+		{name: "deletion", segment: "uh hello", original: "uh ", replacement: "", result: "hello"},
+		{name: "spacing", segment: "hello  world", original: "  ", replacement: " ", result: "hello world"},
+	} {
+		t.Run(tc.name, func(t *testing.T) {
+			req := makeReq([]proposals.EnrichedCorrectionProposal{mk(7, tc.original, tc.replacement)})
+			req.WorkingTranscript.Segments[0].Text = tc.segment
+			payload, immediate := BuildLLMValidationRequest("editorial_review", LLMValidatorTypeEditorialReview, req)
+			if len(immediate) != 0 || len(payload.Items) != 1 {
+				t.Fatalf("expected previewable request: %+v, %+v", payload, immediate)
+			}
+			raw, err := json.Marshal(payload)
+			if err != nil {
+				t.Fatal(err)
+			}
+			var decoded struct {
+				ValidatorName string           `json:"validator_name"`
+				Corrections   []map[string]any `json:"corrections"`
+			}
+			if err := json.Unmarshal(raw, &decoded); err != nil {
+				t.Fatal(err)
+			}
+			if decoded.ValidatorName != "editorial_review" || len(decoded.Corrections) != 1 {
+				t.Fatalf("wrong validator identity or item count: %s", raw)
+			}
+			item := decoded.Corrections[0]
+			value, present := item["corrected_text"]
+			if !present || value != tc.replacement || item["original_text"] != tc.original || item["original_segment_text"] != tc.segment || item["corrected_segment_text"] != tc.result || item["correction_index"] != float64(7) {
+				t.Fatalf("literal spans or full segment text lost: %s", raw)
+			}
+		})
+	}
+}
+
 func TestChunkLLMValidationItemsOneSmallBatch(t *testing.T) {
 	items := []LLMValidationItem{{CorrectionIndex: 0, OriginalText: "a", CorrectedText: "b", OriginalSegmentText: "x", CorrectedSegmentText: "y"}}
 	batches, err := ChunkLLMValidationItems(items, 1000, chunking.NewSimpleTokenEstimator())