Repair stale transcription outputs when resuming

internal/stage/transcribe_checkpoint_test.go

@@ -222,6 +222,14 @@ func TestTranscribeResumeValidationUsesSpeakerEvidence(t *testing.T) {
 		t.Fatalf("Run() error = %v", err)
 	}
 	validation, err := (transcribeStage{}).ValidateResume(context.Background(), env, m)
+	if err != nil || validation.Resumable {
+		t.Fatalf("ValidateResume() = %#v, %v, want missing aggregate repaired", validation, err)
+	}
+	if len(m.Stages["transcribe"].Outputs) != 0 {
+		t.Fatal("resume inspection mutated aggregate outputs")
+	}
+	m.Stages["transcribe"].Outputs = []manifest.ArtifactRecord{m.Stages["transcribe"].TranscribeSpeakers["alice"].Output}
+	validation, err = (transcribeStage{}).ValidateResume(context.Background(), env, m)
 	if err != nil || !validation.Resumable {
 		t.Fatalf("ValidateResume() = %#v, %v, want resumable", validation, err)
 	}
@@ -280,6 +288,7 @@ func TestTranscribeReuseDoesNotDependOnRunDirectory(t *testing.T) {
 	if _, err := (transcribeStage{}).Run(context.Background(), env, m); err != nil {
 		t.Fatalf("Run() error = %v", err)
 	}
+	m.Stages["transcribe"].Outputs = []manifest.ArtifactRecord{m.Stages["transcribe"].TranscribeSpeakers["alice"].Output}
 	paths := sessionPathsForEnv(env, m.SessionID)
 	if err := os.RemoveAll(paths.RunsDir); err != nil {
 		t.Fatalf("remove run directory: %v", err)

internal/stage/transcribe_reconciliation_test.go

@@ -5,6 +5,7 @@ import (
 	"errors"
 	"os"
 	"path/filepath"
+	"reflect"
 	"slices"
 	"strings"
 	"testing"
@@ -44,6 +45,29 @@ func TestReconcileTranscribeSpeakersReusesUnchangedCompletedEvidence(t *testing.
 	}
 }
 
+func TestTranscribeResumeAcceptsEquivalentOutputsAndInspectsRemovalReadOnly(t *testing.T) {
+	env, m := setupCurrentTranscribeReconciliation(t, []string{"alice.flac", "bob.flac"})
+	record := m.Stages["transcribe"]
+	record.Status = manifest.StatusSucceeded
+	// Reverse speaker order and mix the supported local path representations.
+	bob := record.TranscribeSpeakers["bob"].Output
+	bob.LocalPath = filepath.Join(sessionPathsForEnv(env, m.SessionID).Root, filepath.FromSlash(bob.LocalPath))
+	record.Outputs = []manifest.ArtifactRecord{bob, record.TranscribeSpeakers["alice"].Output}
+	validation, err := (transcribeStage{}).ValidateResume(context.Background(), env, m)
+	if err != nil || !validation.Resumable {
+		t.Fatalf("equivalent aggregate: %#v, %v", validation, err)
+	}
+	m.Inputs = slices.DeleteFunc(m.Inputs, func(in manifest.InputRecord) bool { return filepath.Base(in.Path) == "bob.flac" })
+	before := cloneManifestForTranscribeCheckpoint(m)
+	validation, err = (transcribeStage{}).ValidateResume(context.Background(), env, m)
+	if err != nil || validation.Resumable {
+		t.Fatalf("removed speaker: %#v, %v", validation, err)
+	}
+	if !reflect.DeepEqual(m, before) {
+		t.Fatal("resume inspection mutated manifest")
+	}
+}
+
 func TestReconcileTranscribeSpeakersReplacesOnlyChangedAudio(t *testing.T) {
 	env, m := setupCurrentTranscribeReconciliation(t, []string{"alice.flac", "bob.flac"})
 	paths := sessionPathsForEnv(env, m.SessionID)

internal/stage/transcribe_resume.go

@@ -6,6 +6,7 @@ import (
 	"sort"
 	"strings"
 
+	"gitea.maximumdirect.net/eric/narratio/internal/artifacts"
 	"gitea.maximumdirect.net/eric/narratio/internal/manifest"
 )
 
@@ -19,6 +20,10 @@ func (transcribeStage) ValidateResume(
 		return ResumeValidation{}, fmt.Errorf("transcribe resume: reconcile speakers: %w", err)
 	}
 	if len(reconciliation.work) == 0 {
+		paths := sessionPathsForEnv(env, m.SessionID)
+		if !transcribeAggregateCurrent(m.Stages["transcribe"], reconciliation.current, paths) {
+			return NonResumable("speaker collection or aggregate outputs require reconciliation"), nil
+		}
 		return Resumable(), nil
 	}
 	speakers := make([]string, 0, len(reconciliation.work))
@@ -29,4 +34,27 @@ func (transcribeStage) ValidateResume(
 	return NonResumable("speaker transcripts require execution: " + strings.Join(speakers, ", ")), nil
 }
 
+// No HTTP work does not imply that the aggregate is current. The reconciled
+// collection is a subset of the stored records, so its cardinality also detects
+// removed speakers. Compare local output evidence independently of list order
+// and of the supported absolute/session-relative path representations.
+func transcribeAggregateCurrent(record *manifest.StageRecord, current map[string]manifest.TranscribeSpeakerRecord, paths artifacts.SessionPaths) bool {
+	if len(record.TranscribeSpeakers) != len(current) || len(record.Outputs) != len(current) {
+		return false
+	}
+	expected := make(map[string]manifest.ArtifactRecord, len(current))
+	for _, speaker := range current {
+		expected[artifacts.ResolveSessionLocalPathForRead(paths, speaker.Output.LocalPath)] = speaker.Output
+	}
+	for _, output := range record.Outputs {
+		path := artifacts.ResolveSessionLocalPathForRead(paths, output.LocalPath)
+		want, ok := expected[path]
+		if !ok || output.Kind != want.Kind || output.Checksum != want.Checksum || output.ProducerRunID != want.ProducerRunID {
+			return false
+		}
+		delete(expected, path)
+	}
+	return len(expected) == 0
+}
+
 var _ ResumeValidator = transcribeStage{}