Record the stored size of a blob a backup finds already stored (closes #300)

When a finished blob already existed at the destination, the upload was
skipped but the blob row, and so the manifest, kept the size of the
local copy. That copy differs from the stored object when
compression_level or the recipients changed since it was written, so
shallow and deep verify failed on a good snapshot. Marking a blob
uploaded now records the size of the object in storage: for an existing
blob, the size Stat reports.

Judgement call: the test adds a recipient rather than changing the
compression level, because an extra age recipient always makes the
local copy larger, while two zstd levels need not compress the test
data differently.

Model: opus-5-5

ARCHITECTURE.md

@@ -279,8 +279,8 @@ Key methods:
 - `Scan(ctx, path, snapshotID)` → Main scan operation
 
 Scan phases:
-1. **Phase 1**: Walk directory, identify files needing processing
-2. **Phase 1b**: Count as deleted the files that the previous snapshot of the same name lists and the walk did not find; an excluded file is not counted
+1. **Phase 0**: Detect deleted files from previous snapshots
+2. **Phase 1**: Walk directory, identify files needing processing
 3. **Phase 2**: Process files (chunk → pack → upload)
 
 #### SnapshotManager
@@ -320,13 +320,13 @@ CreateSnapshot(opts)
     │       │
     │       ├─► scanner.Scan(ctx, path, snapshotID)
     │       │       │
+    │       │       ├─► Phase 0: detectDeletedFiles()
+    │       │       │
     │       │       ├─► Phase 1: scanPhase()
     │       │       │       Walk directory
     │       │       │       Check file metadata changes
     │       │       │       Build list of files to process
     │       │       │
-    │       │       ├─► Phase 1b: detectDeletedFiles()
-    │       │       │
     │       │       └─► Phase 2: processPhase()
     │       │               For each file:
     │       │                   chunker.ChunkReaderStreaming()

TODO.md

@@ -22,17 +22,15 @@ the tag exists and is exercised; what is left is merging `next` to
 
 # Completed Steps
 
-- 2026-10-13: Counted a file as deleted only when the previous snapshot
-  of the same name had it
-  ([issue #304](https://git.eeqj.de/sneak/vaultik/issues/304)). The
-  deleted figure of a backup counted every file in the local index under
-  the source path that the walk did not find. That took in files the
-  snapshot excludes but another snapshot backs up, and files deleted
-  long ago, which every later backup, and the first backup of another
-  name over the same path, reported as deleted again. A file is now
-  counted only when the previous completed snapshot of the same name
-  lists it and the walk did not find it, and an excluded file is never
-  counted.
+- 2026-10-13: Recorded the size of the stored object for a blob a backup
+  found already stored
+  ([issue #300](https://git.eeqj.de/sneak/vaultik/issues/300)). When the
+  upload was skipped, the blob row and the manifest kept the size of the
+  local copy, which differs from the stored object's when
+  `compression_level` or the recipients changed since it was written.
+  `snapshot verify` then failed on a good snapshot, shallow and deep,
+  and the listed sizes were wrong. Marking the blob uploaded now records
+  the size of the object in storage.
 
 - 2026-10-13: Made `snapshot remove` fail for a snapshot that does not
   exist ([issue #293](https://git.eeqj.de/sneak/vaultik/issues/293)).

docs/DATAMODEL.md

@@ -90,7 +90,7 @@ Stores information about packed, compressed, and encrypted blob files.
 - `created_ts` (INTEGER NOT NULL) - Creation timestamp
 - `finished_ts` (INTEGER) - Finalization timestamp (NULL if in progress)
 - `uncompressed_size` (INTEGER NOT NULL DEFAULT 0) - Total size of chunks before compression
-- `compressed_size` (INTEGER NOT NULL DEFAULT 0) - Size after compression and encryption
+- `compressed_size` (INTEGER NOT NULL DEFAULT 0) - Size after compression and encryption. Once uploaded, the size of the object in storage: when the blob was already stored, under another compression level or other recipients, this differs from the size of the local copy
 - `uploaded_ts` (INTEGER) - Upload completion timestamp (NULL if not uploaded)
 
 **Purpose:** Tracks blob lifecycle from creation through upload. The UUID primary key allows immediate association of chunks with blobs.
@@ -183,7 +183,7 @@ Tracks blob upload metrics.
    - `UPDATE blobs SET blob_hash = ?, finished_ts = ?` - Finalize blob after packing
 
 4. **Upload**
-   - `UPDATE blobs SET uploaded_ts = ?` - Mark blob as uploaded
+   - `UPDATE blobs SET uploaded_ts = ?, compressed_size = ?` - Mark blob as uploaded, with the size of the object in storage (the upload is skipped when the blob is already stored)
    - `INSERT INTO uploads` - Record upload metrics with snapshot_id
    - `INSERT INTO snapshot_blobs` - Associate blob with snapshot
 

internal/database/blobs.go

@@ -159,13 +159,16 @@ func (r *BlobRepository) UpdateFinished(
 	return nil
 }
 
-// UpdateUploaded marks a blob as uploaded
+// UpdateUploaded marks a blob as uploaded and records the size of the
+// stored object as its compressed size. That size can differ from the
+// local copy's when an identical blob was already stored with another
+// compression level or other recipients.
 func (r *BlobRepository) UpdateUploaded(
-	ctx context.Context, tx *sql.Tx, id string,
+	ctx context.Context, tx *sql.Tx, id string, storedSize int64,
 ) error {
 	query := `
-		UPDATE blobs 
-		SET uploaded_ts = ?
+		UPDATE blobs
+		SET uploaded_ts = ?, compressed_size = ?
 		WHERE id = ?
 	`
 
@@ -173,9 +176,9 @@ func (r *BlobRepository) UpdateUploaded(
 
 	var err error
 	if tx != nil {
-		_, err = tx.ExecContext(ctx, query, now, id)
+		_, err = tx.ExecContext(ctx, query, now, storedSize, id)
 	} else {
-		_, err = r.db.ExecWithLog(ctx, query, now, id)
+		_, err = r.db.ExecWithLog(ctx, query, now, storedSize, id)
 	}
 
 	if err != nil {

internal/database/blobs_test.go

@@ -122,8 +122,8 @@ func TestBlobRepositoryUpdates(t *testing.T) {
 		t.Errorf("expected compressed size 500, got %d", updated.CompressedSize)
 	}
 
-	// Test UpdateUploaded
-	err = repo.UpdateUploaded(ctx, nil, blob.ID.String())
+	// Test UpdateUploaded, with a stored object larger than the local copy
+	err = repo.UpdateUploaded(ctx, nil, blob.ID.String(), 600)
 	if err != nil {
 		t.Fatalf("failed to update blob as uploaded: %v", err)
 	}
@@ -141,6 +141,10 @@ func TestBlobRepositoryUpdates(t *testing.T) {
 	if uploaded.UploadedTS.Before(now.Add(-1 * time.Second)) {
 		t.Error("uploaded timestamp should be around test time")
 	}
+
+	if uploaded.CompressedSize != 600 {
+		t.Errorf("expected the stored size 600, got %d", uploaded.CompressedSize)
+	}
 }
 
 func TestBlobRepositoryDuplicate(t *testing.T) {

internal/database/files.go

@@ -277,50 +277,6 @@ func (r *FileRepository) ListUnderPath(
 	return files, rows.Err()
 }
 
-// ListUnderPathInSnapshot returns the files that ListUnderPath returns
-// for path and that the snapshot lists, in no particular order.
-func (r *FileRepository) ListUnderPathInSnapshot(
-	ctx context.Context, path, snapshotID string,
-) ([]*File, error) {
-	path = strings.TrimRight(path, "/")
-	dirPrefix := path + "/"
-
-	query := `
-		SELECT f.id, f.path, f.source_path, f.mtime, f.mtime_nsec, f.size,
-			f.mode, f.uid, f.gid, f.link_target
-		FROM files f
-		JOIN snapshot_files sf ON sf.file_id = f.id
-		WHERE sf.snapshot_id = ?
-		  AND (f.path = ? OR substr(f.path, 1, length(?)) = ?)
-	`
-
-	rows, err := r.db.conn.QueryContext(ctx, query,
-		snapshotID, path, dirPrefix, dirPrefix)
-	if err != nil {
-		return nil, fmt.Errorf("querying files: %w", err)
-	}
-
-	defer func() {
-		err := rows.Close()
-		if err != nil {
-			Fatalf("failed to close rows: %v", err)
-		}
-	}()
-
-	var files []*File
-
-	for rows.Next() {
-		file, err := r.scanFileRows(rows)
-		if err != nil {
-			return nil, fmt.Errorf("scanning file: %w", err)
-		}
-
-		files = append(files, file)
-	}
-
-	return files, rows.Err()
-}
-
 // ListIDsWithChunksNotInUploadedBlobs returns the IDs of the files whose
 // path starts with prefix and that list at least one chunk held by no
 // blob whose upload has completed (uploaded_ts set). A new snapshot

internal/database/files_test.go

@@ -212,65 +212,6 @@ func TestFileRepositoryListUnderPath(t *testing.T) {
 	}
 }
 
-// ListUnderPathInSnapshot leaves out files outside path and files the
-// snapshot does not list, though another snapshot lists them.
-func TestFileRepositoryListUnderPathInSnapshot(t *testing.T) {
-	t.Parallel()
-
-	db, cleanup := setupTestDB(t)
-	defer cleanup()
-
-	ctx := context.Background()
-	files := database.NewFileRepository(db)
-	snapshots := database.NewSnapshotRepository(db)
-
-	listed := map[string][]string{
-		"one": {"/src/a.txt", "/src2/c.txt"},
-		"two": {"/src/b.txt"},
-	}
-
-	for snapshotID, paths := range listed {
-		err := snapshots.Create(ctx, nil, &database.Snapshot{
-			ID:        types.SnapshotID(snapshotID),
-			Hostname:  "host",
-			StartedAt: time.Now(),
-		})
-		if err != nil {
-			t.Fatalf("failed to create snapshot %s: %v", snapshotID, err)
-		}
-
-		for _, path := range paths {
-			err := files.Create(ctx, nil, &database.File{
-				Path:  types.FilePath(path),
-				MTime: time.Now().Truncate(time.Second),
-				Mode:  0644,
-			})
-			if err != nil {
-				t.Fatalf("failed to create %s: %v", path, err)
-			}
-
-			err = snapshots.AddFile(ctx, nil, snapshotID, path)
-			if err != nil {
-				t.Fatalf("failed to add %s to %s: %v", path, snapshotID, err)
-			}
-		}
-	}
-
-	found, err := files.ListUnderPathInSnapshot(ctx, "/src", "one")
-	if err != nil {
-		t.Fatalf("failed to list files: %v", err)
-	}
-
-	got := make([]string, 0, len(found))
-	for _, f := range found {
-		got = append(got, f.Path.String())
-	}
-
-	if !slices.Equal(got, []string{"/src/a.txt"}) {
-		t.Errorf("got %q, want only /src/a.txt", got)
-	}
-}
-
 func TestFileRepositorySymlink(t *testing.T) {
 	t.Parallel()
 

internal/snapshot/module.go

@@ -16,9 +16,6 @@ type ScannerParams struct {
 	Fs             afero.Fs
 	Exclude        []string // Exclude patterns (combined global + snapshot-specific)
 	SkipErrors     bool     // Skip file read errors (log loudly but continue)
-	// PreviousSnapshotID is the most recent completed snapshot of the
-	// same name, "" for none.
-	PreviousSnapshotID string
 }
 
 // Module exports backup functionality as an fx module.
@@ -47,18 +44,17 @@ func provideScannerFactory(
 		}
 
 		return NewScanner(ScannerConfig{
-			FS:                 params.Fs,
-			ChunkSize:          cfg.ChunkSize.Int64(),
-			Repositories:       repos,
-			Storage:            storer,
-			MaxBlobSize:        cfg.BlobSizeLimit.Int64(),
-			CompressionLevel:   cfg.CompressionLevel,
-			AgeRecipients:      cfg.AgeRecipients,
-			EnableProgress:     params.EnableProgress,
-			UI:                 params.UI,
-			Exclude:            excludes,
-			SkipErrors:         params.SkipErrors,
-			PreviousSnapshotID: params.PreviousSnapshotID,
+			FS:               params.Fs,
+			ChunkSize:        cfg.ChunkSize.Int64(),
+			Repositories:     repos,
+			Storage:          storer,
+			MaxBlobSize:      cfg.BlobSizeLimit.Int64(),
+			CompressionLevel: cfg.CompressionLevel,
+			AgeRecipients:    cfg.AgeRecipients,
+			EnableProgress:   params.EnableProgress,
+			UI:               params.UI,
+			Exclude:          excludes,
+			SkipErrors:       params.SkipErrors,
 		})
 	}
 }

internal/snapshot/scanner.go

@@ -58,10 +58,6 @@ type Scanner struct {
 	compressionLevel int
 	ageRecipient     string
 	snapshotID       string // Current snapshot being processed
-	// previousSnapshotID is the most recent completed snapshot of the
-	// same name, "" for none. Only a file it lists can be counted as
-	// deleted.
-	previousSnapshotID string
 	// currentSourcePath is the source directory being scanned, stored with
 	// each file record.
 	currentSourcePath string
@@ -133,9 +129,6 @@ type ScannerConfig struct {
 	// SkipErrors skips files that cannot be opened or read (log loudly but
 	// continue); packer, database, encryption, and upload errors still abort.
 	SkipErrors bool
-	// PreviousSnapshotID is the most recent completed snapshot of the
-	// same name, "" for none.
-	PreviousSnapshotID string
 }
 
 // ScanResult contains the results of a scan operation. Files and bytes
@@ -211,7 +204,6 @@ func NewScanner(cfg ScannerConfig) *Scanner {
 		compiledExclude:    compiledExclude,
 		progress:           progress,
 		skipErrors:         cfg.SkipErrors,
-		previousSnapshotID: cfg.PreviousSnapshotID,
 		ui:                 uiw,
 		pendingChunkHashes: make(map[string]struct{}),
 	}
@@ -263,9 +255,8 @@ func (s *Scanner) Scan(
 
 	filesToProcess := scanResult.FilesToProcess
 
-	// Phase 1b: Detect deleted files by comparing the previous snapshot
-	// of this name against scanned files
-	err = s.detectDeletedFiles(ctx, path, existingFiles, result)
+	// Phase 1b: Detect deleted files by comparing DB against scanned files
+	err = s.detectDeletedFilesFromMap(ctx, knownFiles, existingFiles, result)
 	if err != nil {
 		return nil, fmt.Errorf("detecting deleted files: %w", err)
 	}
@@ -445,8 +436,9 @@ func (s *Scanner) summarizeScanPhase(
 }
 
 // loadKnownFiles loads the known files at and beneath path from the
-// database into a map for fast lookup. This avoids per-file database
-// queries during the scan phase.
+// database into a map for fast lookup. Every loaded file the scan does
+// not find is counted as deleted. This avoids per-file database queries
+// during the scan phase.
 func (s *Scanner) loadKnownFiles(
 	ctx context.Context, path string,
 ) (map[string]*database.File, error) {
@@ -1517,7 +1509,8 @@ func (s *Scanner) finalizeProcessPhase(ctx context.Context, result *ScanResult)
 			// snapshot references has uploaded_ts set, so deduplication and
 			// interrupted-run repair treat these blobs as trustworthy.
 			err = s.repos.WithTx(ctx, func(ctx context.Context, tx *sql.Tx) error {
-				err := s.repos.Blobs.UpdateUploaded(ctx, tx, b.ID)
+				err := s.repos.Blobs.UpdateUploaded(
+					ctx, tx, b.ID, b.Compressed)
 				if err != nil {
 					return fmt.Errorf("marking blob uploaded: %w", err)
 				}
@@ -1553,7 +1546,7 @@ func (s *Scanner) handleBlobReady(
 	blobPath := fmt.Sprintf("blobs/%s/%s/%s",
 		finishedBlob.Hash[:2], finishedBlob.Hash[2:4], finishedBlob.Hash)
 
-	blobExists, err := s.uploadBlobIfNeeded(
+	storedSize, blobExists, err := s.uploadBlobIfNeeded(
 		ctx, blobPath, blobWithReader, startTime, result)
 	if err != nil {
 		s.cleanupBlobTempFile(blobWithReader)
@@ -1561,7 +1554,8 @@ func (s *Scanner) handleBlobReady(
 		return fmt.Errorf("uploading blob %s: %w", finishedBlob.Hash, err)
 	}
 
-	err = s.recordBlobMetadata(ctx, finishedBlob, blobExists, startTime)
+	err = s.recordBlobMetadata(
+		ctx, finishedBlob, storedSize, blobExists, startTime)
 	if err != nil {
 		s.cleanupBlobTempFile(blobWithReader)
 
@@ -1583,20 +1577,22 @@ func (s *Scanner) handleBlobReady(
 }
 
 // uploadBlobIfNeeded uploads the blob to storage if it doesn't already
-// exist, returns whether it existed
+// exist. It returns the size of the object in storage, which for an
+// existing object can differ from the local copy's, and whether it
+// already existed.
 func (s *Scanner) uploadBlobIfNeeded(
 	ctx context.Context,
 	blobPath string,
 	blobWithReader *blob.WithReader,
 	startTime time.Time,
 	result *ScanResult,
-) (bool, error) {
+) (int64, bool, error) {
 	finishedBlob := blobWithReader.FinishedBlob
 
 	// Check if blob already exists (deduplication after restart)
 	destination := s.storage.Info().Location
 
-	_, err := s.storage.Stat(ctx, blobPath)
+	stored, err := s.storage.Stat(ctx, blobPath)
 	if err == nil {
 		log.Info("Blob already exists in storage, skipping upload",
 			"hash", finishedBlob.Hash,
@@ -1605,7 +1601,7 @@ func (s *Scanner) uploadBlobIfNeeded(
 			s.ui.Hex(finishedBlob.Hash), s.ui.Size(finishedBlob.Compressed),
 			s.ui.Path(destination))
 
-		return true, nil
+		return stored.Size, true, nil
 	}
 
 	s.ui.Beginf("Uploading blob %s (%s) to %s.",
@@ -1619,7 +1615,7 @@ func (s *Scanner) uploadBlobIfNeeded(
 	if err != nil {
 		log.Error("Failed to upload blob", "hash", finishedBlob.Hash, "error", err)
 
-		return false, fmt.Errorf("uploading blob to storage: %w", err)
+		return 0, false, fmt.Errorf("uploading blob to storage: %w", err)
 	}
 
 	uploadDuration := time.Since(startTime)
@@ -1650,7 +1646,7 @@ func (s *Scanner) uploadBlobIfNeeded(
 		stats.BytesUploaded.Add(finishedBlob.Compressed)
 	}
 
-	return false, nil
+	return finishedBlob.Compressed, false, nil
 }
 
 // makeUploadProgressCallback creates a progress callback for blob uploads.
@@ -1720,6 +1716,7 @@ func (s *Scanner) makeUploadProgressCallback(
 func (s *Scanner) recordBlobMetadata(
 	ctx context.Context,
 	finishedBlob *blob.FinishedBlob,
+	storedSize int64,
 	blobExists bool,
 	startTime time.Time,
 ) error {
@@ -1731,7 +1728,8 @@ func (s *Scanner) recordBlobMetadata(
 	uploadDuration := time.Since(startTime)
 
 	return s.repos.WithTx(ctx, func(txCtx context.Context, tx *sql.Tx) error {
-		err := s.repos.Blobs.UpdateUploaded(txCtx, tx, finishedBlob.ID)
+		err := s.repos.Blobs.UpdateUploaded(
+			txCtx, tx, finishedBlob.ID, storedSize)
 		if err != nil {
 			return fmt.Errorf("updating blob upload timestamp: %w", err)
 		}
@@ -1941,28 +1939,21 @@ func (s *Scanner) queueFileForBatchInsert(
 	})
 }
 
-// detectDeletedFiles counts as deleted each file at or beneath path that
-// the previous snapshot of this name lists and the walk did not find.
-// An excluded file is not counted: the walk skips it whether or not it
-// is still on disk.
-func (s *Scanner) detectDeletedFiles(
+// detectDeletedFilesFromMap finds files that existed in previous snapshots
+// but no longer exist. Uses pre-loaded maps to avoid any filesystem or
+// database access.
+func (s *Scanner) detectDeletedFilesFromMap(
 	ctx context.Context,
-	path string,
+	knownFiles map[string]*database.File,
 	existingFiles map[string]struct{},
 	result *ScanResult,
 ) error {
-	if s.previousSnapshotID == "" {
+	if len(knownFiles) == 0 {
 		return nil
 	}
 
-	previousFiles, err := s.repos.Files.ListUnderPathInSnapshot(
-		ctx, path, s.previousSnapshotID)
-	if err != nil {
-		return fmt.Errorf("listing files of snapshot %s: %w",
-			s.previousSnapshotID, err)
-	}
-
-	for _, file := range previousFiles {
+	// Check each known file against the enumerated set (no filesystem access needed)
+	for path, file := range knownFiles {
 		// Check context cancellation periodically
 		select {
 		case <-ctx.Done():
@@ -1970,16 +1961,13 @@ func (s *Scanner) detectDeletedFiles(
 		default:
 		}
 
-		filePath := file.Path.String()
-
-		_, exists := existingFiles[filePath]
-		if exists || s.shouldExclude(filePath, path) {
-			continue
+		// Check if the file exists in our enumerated set
+		if _, exists := existingFiles[path]; !exists {
+			// File has been deleted
+			result.FilesDeleted++
+			result.BytesDeleted += file.Size
+			log.Debug("Detected deleted file", "path", path, "size", file.Size)
 		}
-
-		result.FilesDeleted++
-		result.BytesDeleted += file.Size
-		log.Debug("Detected deleted file", "path", filePath, "size", file.Size)
 	}
 
 	if result.FilesDeleted > 0 {

internal/vaultik/fault_injection_test.go

@@ -661,18 +661,17 @@ func faultScannerFactory(
 ) snapshot.ScannerFactory {
 	return func(params snapshot.ScannerParams) *snapshot.Scanner {
 		return snapshot.NewScanner(snapshot.ScannerConfig{
-			FS:                 params.Fs,
-			Storage:            storer,
-			ChunkSize:          faultChunkSize,
-			MaxBlobSize:        faultMaxBlobSize,
-			CompressionLevel:   cfg.CompressionLevel,
-			AgeRecipients:      cfg.AgeRecipients,
-			Repositories:       repos,
-			EnableProgress:     params.EnableProgress,
-			UI:                 params.UI,
-			Exclude:            params.Exclude,
-			SkipErrors:         params.SkipErrors,
-			PreviousSnapshotID: params.PreviousSnapshotID,
+			FS:               params.Fs,
+			Storage:          storer,
+			ChunkSize:        faultChunkSize,
+			MaxBlobSize:      faultMaxBlobSize,
+			CompressionLevel: cfg.CompressionLevel,
+			AgeRecipients:    cfg.AgeRecipients,
+			Repositories:     repos,
+			EnableProgress:   params.EnableProgress,
+			UI:               params.UI,
+			Exclude:          params.Exclude,
+			SkipErrors:       params.SkipErrors,
 		})
 	}
 }

internal/vaultik/reused_blob_verify_test.go

@@ -0,0 +1,83 @@
+package vaultik_test
+
+import (
+	"context"
+	"io"
+	"path/filepath"
+	"testing"
+
+	"filippo.io/age"
+	"github.com/spf13/afero"
+	"github.com/stretchr/testify/require"
+	"sneak.berlin/go/vaultik/internal/log"
+	"sneak.berlin/go/vaultik/internal/ui"
+	"sneak.berlin/go/vaultik/internal/vaultik"
+)
+
+// TestVerifyPassesWhenBackupReusesStoredBlob backs up a file, then backs it
+// up again from an empty local index, as after `database delete`, with an
+// extra age recipient. The second backup builds the same blob, finds it
+// already stored and skips the upload, but its own copy is larger, because
+// age writes a header entry for each recipient. The second snapshot must
+// record the size of the stored object, so shallow and deep verify pass.
+func TestVerifyPassesWhenBackupReusesStoredBlob(t *testing.T) {
+	log.Initialize(log.Config{})
+	t.Parallel()
+
+	fs := afero.NewOsFs()
+	tempDir := t.TempDir()
+
+	dataDir := filepath.Join(tempDir, "source")
+	storeDir := filepath.Join(tempDir, "remote")
+	secondDBPath := filepath.Join(tempDir, "second.sqlite")
+
+	chunkSize := int64(64 * 1024)
+	maxBlobSize := int64(512 * 1024)
+
+	require.NoError(t, fs.MkdirAll(dataDir, 0o755))
+	require.NoError(t, afero.WriteFile(fs,
+		filepath.Join(dataDir, "data.bin"),
+		bytesPattern("reuse-", int(chunkSize*3)), 0o644))
+
+	ctx := context.Background()
+
+	runFileStorageBackup(ctx, t, fs, dataDir, storeDir,
+		filepath.Join(tempDir, "first.sqlite"), chunkSize, maxBlobSize)
+
+	env := setupDedupBackupEnv(
+		ctx, t, fs, storeDir, secondDBPath, chunkSize, maxBlobSize)
+
+	defer func() { _ = env.db.Close() }()
+
+	extra, err := age.GenerateX25519Identity()
+	require.NoError(t, err)
+
+	env.cfg.AgeRecipients = append(env.cfg.AgeRecipients,
+		extra.Recipient().String())
+
+	snapshotID, result := runDedupSnapshot(ctx, t, env.sm, env.makeScanner(),
+		env.cfg.Hostname, "second", dataDir, secondDBPath)
+	require.Positive(t, result.BlobsCreated)
+	require.Zero(t, result.BlobsUploaded,
+		"the second backup should find every blob already stored")
+
+	require.NoError(t, env.db.Close())
+
+	verifier := &vaultik.Vaultik{
+		Config:  env.cfg,
+		Storage: env.storer,
+		Fs:      fs,
+		Stdout:  io.Discard,
+		Stderr:  io.Discard,
+		UI:      ui.NewWithColor(io.Discard, false),
+	}
+	verifier.SetContext(ctx)
+
+	require.NoError(t,
+		verifier.VerifySnapshotWithOptions(snapshotID, &vaultik.VerifyOptions{}),
+		"shallow verify should pass")
+	require.NoError(t,
+		verifier.VerifySnapshotWithOptions(snapshotID,
+			&vaultik.VerifyOptions{Deep: true}),
+		"deep verify should pass")
+}

internal/vaultik/snapshot.go

@@ -214,18 +214,12 @@ func (v *Vaultik) createNamedSnapshot(
 		return err
 	}
 
-	previousSnapshotID, err := v.previousSnapshotID(snapName)
-	if err != nil {
-		return err
-	}
-
 	scanner := v.ScannerFactory(snapshot.ScannerParams{
-		EnableProgress:     !opts.Cron,
-		UI:                 v.UI,
-		Fs:                 v.Fs,
-		Exclude:            v.Config.GetExcludes(snapName),
-		SkipErrors:         opts.SkipErrors,
-		PreviousSnapshotID: previousSnapshotID,
+		EnableProgress: !opts.Cron,
+		UI:             v.UI,
+		Fs:             v.Fs,
+		Exclude:        v.Config.GetExcludes(snapName),
+		SkipErrors:     opts.SkipErrors,
 	})
 
 	snapshotID, err := v.SnapshotManager.CreateSnapshotWithName(
@@ -260,24 +254,6 @@ func (v *Vaultik) createNamedSnapshot(
 	return nil
 }
 
-// previousSnapshotID returns the ID of the most recent completed snapshot
-// named snapName in the local index, or "" when there is none.
-func (v *Vaultik) previousSnapshotID(snapName string) (string, error) {
-	snapshots, err := v.Repositories.Snapshots.ListRecent(v.ctx, listRecentLimit)
-	if err != nil {
-		return "", fmt.Errorf("listing snapshots: %w", err)
-	}
-
-	for _, s := range snapshots {
-		if s.CompletedAt != nil &&
-			parseSnapshotName(s.ID.String(), s.Hostname.String()) == snapName {
-			return s.ID.String(), nil
-		}
-	}
-
-	return "", nil
-}
-
 // resolveSnapshotPaths resolves source directories to absolute paths
 // with symlink resolution.
 func (v *Vaultik) resolveSnapshotPaths(snapName string) ([]string, error) {

internal/vaultik/snapshot_deleted_count_test.go

@@ -1,149 +0,0 @@
-package vaultik_test
-
-import (
-	"bytes"
-	"context"
-	"fmt"
-	"os"
-	"path/filepath"
-	"testing"
-
-	"github.com/spf13/afero"
-	"github.com/stretchr/testify/assert"
-	"github.com/stretchr/testify/require"
-	"sneak.berlin/go/vaultik/internal/config"
-	"sneak.berlin/go/vaultik/internal/database"
-	"sneak.berlin/go/vaultik/internal/log"
-	"sneak.berlin/go/vaultik/internal/storage"
-	"sneak.berlin/go/vaultik/internal/ui"
-	"sneak.berlin/go/vaultik/internal/vaultik"
-)
-
-// These tests cover https://git.eeqj.de/sneak/vaultik/issues/304: a
-// backup counts a file as deleted only when the previous snapshot of
-// the same name had it and it is gone, and never counts an excluded
-// file.
-
-// deletedCountEnv is a backup setup over the source directory src whose
-// user-facing output is kept in out. Each test configures its snapshots
-// with setSnapshot.
-type deletedCountEnv struct {
-	v   *vaultik.Vaultik
-	out *bytes.Buffer
-	src string
-}
-
-// newDeletedCountEnv writes files, keyed by path relative to src.
-func newDeletedCountEnv(t *testing.T, files map[string][]byte) *deletedCountEnv {
-	t.Helper()
-
-	ctx := context.Background()
-	fs := afero.NewOsFs()
-	tempDir := t.TempDir()
-	srcDir := filepath.Join(tempDir, "src")
-
-	for rel, content := range files {
-		path := filepath.Join(srcDir, rel)
-		require.NoError(t, fs.MkdirAll(filepath.Dir(path), 0o755))
-		require.NoError(t, afero.WriteFile(fs, path, content, 0o644))
-	}
-
-	cfg := faultTestConfig()
-	cfg.IndexPath = filepath.Join(tempDir, "index.sqlite")
-	cfg.Snapshots = map[string]config.SnapshotConfig{}
-
-	store, err := storage.NewFileStorer(filepath.Join(tempDir, "remote"))
-	require.NoError(t, err)
-
-	db, err := database.New(ctx, cfg.IndexPath)
-	require.NoError(t, err)
-	t.Cleanup(func() { _ = db.Close() })
-
-	repos := database.NewRepositories(db)
-	out := &bytes.Buffer{}
-	v := newBackupVaultik(ctx, cfg, store, repos, db, fs)
-	v.UI = ui.NewWithColor(out, false)
-
-	return &deletedCountEnv{v: v, out: out, src: srcDir}
-}
-
-// setSnapshot configures the snapshot name to back up the path rel
-// beneath src, with the given excludes.
-func (e *deletedCountEnv) setSnapshot(name, rel string, exclude ...string) {
-	e.v.Config.Snapshots[name] = config.SnapshotConfig{
-		Paths:   []string{filepath.Join(e.src, rel)},
-		Exclude: exclude,
-	}
-}
-
-// backUp runs a backup of the named snapshot and returns its output.
-func (e *deletedCountEnv) backUp(t *testing.T, name string) string {
-	t.Helper()
-
-	e.out.Reset()
-	require.NoError(t, e.v.CreateSnapshot(&vaultik.SnapshotCreateOptions{
-		Snapshots: []string{name},
-	}))
-
-	return e.out.String()
-}
-
-// A file this snapshot excludes is not counted as deleted: neither one
-// that another snapshot backs up, nor one that the previous snapshot of
-// this name had before the exclude was added.
-func TestBackupDoesNotCountExcludedFileAsDeleted(t *testing.T) {
-	log.Initialize(log.Config{})
-	t.Parallel()
-
-	env := newDeletedCountEnv(t, map[string][]byte{
-		"top.txt":       []byte("top"),
-		"cache/tmp.bin": []byte("cache"),
-		"photos/a.jpg":  []byte("photo a"),
-		"photos/b.jpg":  []byte("photo b"),
-		"photos/c.jpg":  []byte("photo c"),
-	})
-	env.setSnapshot("photos", "photos")
-	env.setSnapshot("home", "", "/photos")
-
-	env.backUp(t, "photos")
-	assert.Contains(t, env.backUp(t, "home"), filesLine(2, 2, 0))
-
-	env.setSnapshot("home", "", "/photos", "/cache")
-	assert.Contains(t, env.backUp(t, "home"), filesLine(1, 0, 1))
-}
-
-// A file removed from disk is counted as deleted by the next backup of
-// the snapshot that had it, and not by any later backup of that
-// snapshot, nor by the first backup of another name over the same path.
-func TestBackupCountsDeletedFileOnce(t *testing.T) {
-	log.Initialize(log.Config{})
-	t.Parallel()
-
-	aContent := bytes.Repeat([]byte("a"), 1000)
-	bContent := bytes.Repeat([]byte("b"), 2000)
-	keptContent := bytes.Repeat([]byte("k"), 500)
-
-	env := newDeletedCountEnv(t, map[string][]byte{
-		"a.txt":    aContent,
-		"b.txt":    bContent,
-		"kept.txt": keptContent,
-	})
-	env.setSnapshot("home", "")
-	env.setSnapshot("other", "")
-
-	assert.Contains(t, env.backUp(t, "home"), filesLine(3, 3, 0))
-
-	require.NoError(t, os.Remove(filepath.Join(env.src, "a.txt")))
-	require.NoError(t, os.Remove(filepath.Join(env.src, "b.txt")))
-
-	summary := env.backUp(t, "home")
-	assert.Contains(t, summary,
-		"Files: 1 examined, 0 backed up, 1 unchanged, 2 deleted.")
-	assert.Contains(t, summary,
-		fmt.Sprintf("Data: %s total (%s backed up), %s deleted.",
-			env.v.UI.Size(int64(len(keptContent))), env.v.UI.Size(0),
-			env.v.UI.Size(int64(len(aContent)+len(bContent)))))
-
-	assert.Contains(t, env.backUp(t, "home"), filesLine(1, 0, 1))
-	assert.Contains(t, env.backUp(t, "other"), filesLine(1, 0, 1))
-}