Make a leading **/ in an exclude pattern match at the top level (closes #303)

An unanchored exclude pattern such as **/node_modules or **/*.pyc
needed a / before the name, so it excluded sub/node_modules and
sub/y.pyc but backed up node_modules/ and x.pyc directly under the
snapshot path. An unanchored pattern already matches at every depth,
so the leading **/ is now dropped when the pattern is compiled and,
as in gitignore, the pattern matches the top level too.

Judgement call: an anchored /**/x is left as it was; the issue covers
patterns that start with **/.

Model: opus-5-5

README.md

@@ -399,9 +399,7 @@ orphaned blob figures are reported as unknown; `--json` gives them as
 `null`, lists the remote key of each unreadable manifest in
 `unreadable_manifests` and counts the manifests under skipped names in
 `skipped_manifest_count`. An unreadable manifest also leaves its
-snapshot's blob count and blob size unknown, `null` in `--json`. A file
-under `blobs/` whose name is not a blob hash is not counted as a blob,
-since `prune` never deletes it.
+snapshot's blob count and blob size unknown, `null` in `--json`.
 * `--json`: Output as JSON
 
 **`remote nuke`**: Delete every snapshot's metadata and every blob from the

TODO.md

@@ -22,13 +22,14 @@ the tag exists and is exercised; what is left is merging `next` to
 
 # Completed Steps
 
-- 2026-10-13: Stopped `remote info` counting a file under `blobs/` that
-  is not a blob as an orphaned blob
-  ([issue #295](https://git.eeqj.de/sneak/vaultik/issues/295)). A stray
-  file such as `.DS_Store` was reported as an orphaned blob and the
-  report advised running `prune`, which skips such a file and deleted
-  nothing. `remote info` now takes its blob list from the same listing
-  `prune` uses, in the table and in `--json`.
+- 2026-10-13: Made an exclude pattern starting with `**/` also match
+  directly under the snapshot path
+  ([issue #303](https://git.eeqj.de/sneak/vaultik/issues/303)).
+  `**/node_modules` and `**/*.pyc`, the patterns `config.example.yml`
+  uses, excluded `sub/node_modules` and `sub/y.pyc` but backed up
+  `node_modules/` and `x.pyc` at the top of the path, since the pattern
+  required a `/` before the name. As in gitignore, such a pattern now
+  matches at every depth, the top included.
 
 - 2026-10-12: Bound the local index to the destination an `s3.*` config
   names ([issue #298](https://git.eeqj.de/sneak/vaultik/issues/298)).

internal/snapshot/exclude_test.go

@@ -531,3 +531,50 @@ func TestExcludePatterns_UnanchoredPatternFile(t *testing.T) {
 	require.Equal(t, 1, result.FilesScanned,
 		"Unanchored pattern for file should match anywhere")
 }
+
+func TestExcludePatterns_DoubleStarDirectoryAtEveryDepth(t *testing.T) {
+	t.Parallel()
+
+	// As in gitignore, a leading **/ also matches directly under the source dir
+	fs := setupAnchoredTestFS(t)
+
+	scanner, repos, cleanup := createTestScanner(t, fs, []string{"**/projectname"})
+	defer cleanup()
+
+	ctx := context.Background()
+	createSnapshotRecord(ctx, t, repos, "test-snapshot")
+
+	result, err := scanner.Scan(ctx, "/backup", "test-snapshot")
+	require.NoError(t, err)
+
+	// **/projectname should exclude BOTH:
+	// - /backup/projectname/file.txt
+	// - /backup/otherproject/projectname/file.txt
+	// Total files: 4, excluded: 2
+	require.Equal(t, 2, result.FilesScanned,
+		"**/ directory pattern should match at the top level and nested")
+}
+
+func TestExcludePatterns_DoubleStarFileAtEveryDepth(t *testing.T) {
+	t.Parallel()
+
+	// As in gitignore, a leading **/ also matches directly under the source dir
+	fs := setupAnchoredTestFS(t)
+
+	scanner, repos, cleanup := createTestScanner(t, fs, []string{"**/*.txt"})
+	defer cleanup()
+
+	ctx := context.Background()
+	createSnapshotRecord(ctx, t, repos, "test-snapshot")
+
+	result, err := scanner.Scan(ctx, "/backup", "test-snapshot")
+	require.NoError(t, err)
+
+	// **/*.txt should exclude ALL .txt files:
+	// - /backup/file.txt
+	// - /backup/projectname/file.txt
+	// - /backup/otherproject/projectname/file.txt
+	// Total files: 4, excluded: 3
+	require.Equal(t, 1, result.FilesScanned,
+		"**/ file pattern should match at the top level and nested")
+}

internal/snapshot/scanner.go

@@ -2013,6 +2013,14 @@ func compileExcludePatterns(patterns []string) []compiledPattern {
 		// Remove trailing slash if present (directory indicator)
 		pattern = strings.TrimSuffix(pattern, "/")
 
+		// A leading "**/" demands a "/" before the name and so misses an
+		// entry directly under the source path. An unanchored pattern
+		// already matches at every depth, so drop the prefix: as in
+		// gitignore, "**/x" then also matches a top-level "x".
+		if !anchored {
+			pattern = strings.TrimPrefix(pattern, "**/")
+		}
+
 		// Compile the glob pattern
 		// For patterns without path separators, we need to match them as components
 		// e.g., ".git" should match ".git" anywhere in the path

internal/vaultik/info.go

@@ -167,6 +167,10 @@ const (
 	// metadataKeyParts is the minimum "/"-separated segment count of a
 	// metadata object key (metadata/<snapshot-id>/<filename>).
 	metadataKeyParts = 3
+
+	// blobKeyParts is the minimum "/"-separated segment count of a blob
+	// object key (blobs/<aa>/<bb>/<hash>).
+	blobKeyParts = 4
 )
 
 // SnapshotMetadataInfo contains information about a single snapshot's metadata
@@ -450,16 +454,23 @@ func (v *Vaultik) scanRemoteBlobStorage(
 		v.stdoutf("Scanning blobs...\n")
 	}
 
-	// Use prune's listing, so a file under blobs/ that prune would never
-	// delete is not counted as a blob, and so not as an orphaned one.
-	allBlobs, err := v.listAllRemoteBlobs()
-	if err != nil {
-		return err
-	}
+	blobCh := v.Storage.ListStream(v.ctx, "blobs/")
+	allBlobs := make(map[string]int64)
 
-	for _, size := range allBlobs {
+	for obj := range blobCh {
+		if obj.Err != nil {
+			return fmt.Errorf("listing blobs: %w", obj.Err)
+		}
+
+		parts := strings.Split(obj.Key, "/")
+		if len(parts) < blobKeyParts {
+			continue
+		}
+
+		hash := parts[3]
+		allBlobs[hash] = obj.Size
 		result.TotalBlobCount++
-		result.TotalBlobSize += size
+		result.TotalBlobSize += obj.Size
 	}
 
 	// A blob named only by a manifest that could not be read, or by one

internal/vaultik/prune.go

@@ -23,10 +23,6 @@ var errNukeRequiresForce = errors.New(
 // metadata.
 const metadataDirName = "metadata"
 
-// blobKeyParts is the "/"-separated segment count of a blob object key
-// (blobs/<aa>/<bb>/<hash>).
-const blobKeyParts = 4
-
 // NukeRemote deletes every snapshot's metadata and every blob from remote
 // storage, along with any object an upload cut off part-way left under a
 // temporary `.partial` name. After this returns successfully the bucket

internal/vaultik/remote_info_test.go

@@ -185,39 +185,6 @@ func TestRemoteInfo_SkipsNonConformingMetadataName(t *testing.T) {
 	assert.NotContains(t, doc, "unreadable_manifests")
 }
 
-// TestRemoteInfo_DoesNotCountNonBlobFileUnderBlobs checks that a file
-// under blobs/ whose name is not a blob hash is not counted as a blob.
-// prune never deletes such a file, so counting it as an orphaned blob
-// would advise a prune that removes nothing.
-func TestRemoteInfo_DoesNotCountNonBlobFileUnderBlobs(t *testing.T) {
-	log.Initialize(log.Config{})
-	t.Parallel()
-
-	env := newListEnv(t)
-	env.addRemote(t, listRemoteID, time.Date(2026, 3, 2, 0, 0, 0, 0, time.UTC))
-	addBlob(t, env.store.testStorer, testBlobHashA)
-	require.NoError(t, env.store.Put(context.Background(),
-		"blobs/"+testBlobHashA[:2]+"/"+testBlobHashA[2:4]+"/.DS_Store",
-		bytes.NewReader([]byte("junk"))))
-
-	require.NoError(t, env.v.RemoteInfo(false))
-
-	text := env.stdout.String()
-	assert.Contains(t, text, "Total blobs on remote:      1 (")
-	assert.Contains(t, text, "Orphaned (unreferenced):    0 (")
-	assert.NotContains(t, text, "vaultik prune")
-
-	env.stdout.Reset()
-	require.NoError(t, env.v.RemoteInfo(true))
-
-	var doc map[string]any
-
-	require.NoError(t, json.Unmarshal(env.stdout.Bytes(), &doc))
-	assert.InDelta(t, 1, doc["total_blob_count"], 0)
-	assert.InDelta(t, 0, doc["orphaned_blob_count"], 0)
-	assert.InDelta(t, 0, doc["orphaned_blob_size"], 0)
-}
-
 // TestRemoteInfo_DirectoryWithoutManifestLeavesOrphansKnown checks that
 // a directory under metadata/ holding no manifest.json.zst, such as one
 // left by a backup interrupted before its manifest upload, leaves the