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

@@ -412,7 +412,8 @@ destination store.
 entirely. Remote storage is unaffected; the next backup will do a full
 scan and re-deduplicate against existing remote blobs, and the local
 index will re-bind to the currently configured storage destination.
-Use this after changing `storage_url` to a different destination.
+Use this after changing `storage_url`, or `s3.endpoint`, `s3.bucket` or
+`s3.prefix`, to a different destination.
 * `--force`: Skip confirmation prompt
 
 ---

TODO.md

@@ -22,15 +22,23 @@ the tag exists and is exercised; what is left is merging `next` to
 
 # Completed Steps
 
-- 2026-10-12: Made a `file://` destination list through a symlinked
-  directory ([issue #296](https://git.eeqj.de/sneak/vaultik/issues/296)).
-  A `metadata/` or `blobs/` directory that was a symlink to a directory
-  elsewhere was listed as one file, so the destination store listed as
-  empty while backups and restores still worked through the link.
-  `prune` then removed the local snapshot records and deleted every blob,
-  and `remote info` and `remote nuke` found no blobs. The listings now
-  read through the link as `Get` and `Stat` do; a link pointing back up
-  the tree makes them fail.
+- 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)).
+  Only `storage_url` was checked, so after `s3.bucket` or `s3.prefix`
+  changed, the next backup treated every chunk as already stored,
+  uploaded nothing, and completed a snapshot that could not be restored.
+  Without `storage_url`, the local index is now bound to `s3.endpoint`,
+  `s3.bucket` and `s3.prefix`, and a change is refused as a changed
+  `storage_url` is.
 
 - 2026-10-12: Rejected a retention duration longer than about 292 years
   ([issue #289](https://git.eeqj.de/sneak/vaultik/issues/289)). The

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/storage/file.go

@@ -120,9 +120,9 @@ func (f *FileStorer) Delete(_ context.Context, key string) error {
 	return nil
 }
 
-// List returns all keys with the given prefix, reading through symlinked
-// directories. It fails when the destination directory is missing; a
-// missing prefix under it is an empty listing.
+// List returns all keys with the given prefix. It fails when the
+// destination directory is missing; a missing prefix under it is an
+// empty listing.
 func (f *FileStorer) List(ctx context.Context, prefix string) ([]string, error) {
 	var keys []string
 
@@ -143,7 +143,7 @@ func (f *FileStorer) List(ctx context.Context, prefix string) ([]string, error)
 		return keys, nil // Empty list for non-existent prefix
 	}
 
-	err = f.walk(basePath, func(path string, info os.FileInfo, err error) error {
+	err = afero.Walk(f.fs, basePath, func(path string, info os.FileInfo, err error) error {
 		if err != nil {
 			return err
 		}
@@ -176,8 +176,7 @@ func (f *FileStorer) List(ctx context.Context, prefix string) ([]string, error)
 }
 
 // ListStream returns a channel of ObjectInfo for large result sets. Like
-// List, it reads through symlinked directories and sends an error when
-// the destination directory is missing.
+// List, it sends an error when the destination directory is missing.
 func (f *FileStorer) ListStream(ctx context.Context, prefix string) <-chan ObjectInfo {
 	ch := make(chan ObjectInfo)
 
@@ -205,7 +204,7 @@ func (f *FileStorer) ListStream(ctx context.Context, prefix string) <-chan Objec
 			return // Empty channel for non-existent prefix
 		}
 
-		_ = f.walk(basePath, func(path string, info os.FileInfo, err error) error {
+		_ = afero.Walk(f.fs, basePath, func(path string, info os.FileInfo, err error) error {
 			// Check context cancellation
 			select {
 			case <-ctx.Done():
@@ -353,17 +352,6 @@ func (f *FileStorer) writeAtomic(
 	return nil
 }
 
-// walk is afero.Walk, except that it reads through a symlinked directory
-// the way Get and Stat do, where afero.Walk reports the link as one file.
-// afero.Walk uses Lstat, which does not follow a link, whenever the
-// filesystem has one; the struct below carries only the afero.Fs methods,
-// so the walk uses Stat instead. A link back up the tree is followed until
-// the operating system refuses the path for too many levels of links, and
-// the walk then fails.
-func (f *FileStorer) walk(root string, fn filepath.WalkFunc) error {
-	return afero.Walk(struct{ afero.Fs }{f.fs}, root, fn)
-}
-
 // fullPath returns the full filesystem path for a key.
 func (f *FileStorer) fullPath(key string) string {
 	return filepath.Join(f.basePath, key)

internal/storage/file_backend_test.go

@@ -4,10 +4,7 @@ import (
 	"context"
 	"errors"
 	"io/fs"
-	"os"
 	"path/filepath"
-	"reflect"
-	"strings"
 	"testing"
 
 	"sneak.berlin/go/vaultik/internal/storage"
@@ -63,100 +60,3 @@ func TestFileStorerListMissingDestination(t *testing.T) {
 		t.Errorf("ListStream error = %v, want a not-exist error", streamErr)
 	}
 }
-
-// TestFileStorerListsThroughSymlinkedDirectory checks that List and
-// ListStream read through a symlinked metadata/ or blobs/ directory, as Get
-// and Stat do, instead of listing the link as one key. Listing the whole
-// destination meets the link part-way through the walk; listing its prefix
-// starts the walk at the link.
-func TestFileStorerListsThroughSymlinkedDirectory(t *testing.T) {
-	t.Parallel()
-
-	for _, dir := range []string{"metadata", "blobs"} {
-		t.Run(dir, func(t *testing.T) {
-			t.Parallel()
-
-			base := t.TempDir()
-			key := dir + "/aa/bb/object"
-
-			s, err := storage.NewFileStorer(base)
-			if err != nil {
-				t.Fatalf("NewFileStorer: %v", err)
-			}
-
-			err = s.Put(context.Background(), key, strings.NewReader("data"))
-			if err != nil {
-				t.Fatalf("Put: %v", err)
-			}
-
-			linkPath := filepath.Join(base, dir)
-			movedPath := filepath.Join(t.TempDir(), dir)
-
-			err = os.Rename(linkPath, movedPath)
-			if err != nil {
-				t.Fatalf("moving %s away: %v", dir, err)
-			}
-
-			err = os.Symlink(movedPath, linkPath)
-			if err != nil {
-				t.Fatalf("linking %s: %v", dir, err)
-			}
-
-			want := []string{key}
-
-			for _, prefix := range []string{"", dir + "/"} {
-				got := listSorted(t, s, prefix)
-				if !reflect.DeepEqual(got, want) {
-					t.Errorf("List(%q) = %v, want %v", prefix, got, want)
-				}
-
-				got = listStreamKeys(t, s, prefix)
-				if !reflect.DeepEqual(got, want) {
-					t.Errorf("ListStream(%q) = %v, want %v", prefix, got, want)
-				}
-			}
-		})
-	}
-}
-
-// TestFileStorerListFailsOnSymlinkLoop checks that a symlink pointing back
-// at the destination makes List and ListStream fail instead of walking it
-// forever.
-func TestFileStorerListFailsOnSymlinkLoop(t *testing.T) {
-	t.Parallel()
-
-	ctx := context.Background()
-	base := t.TempDir()
-
-	s, err := storage.NewFileStorer(base)
-	if err != nil {
-		t.Fatalf("NewFileStorer: %v", err)
-	}
-
-	err = s.Put(ctx, testBlobKey, strings.NewReader("data"))
-	if err != nil {
-		t.Fatalf("Put: %v", err)
-	}
-
-	err = os.Symlink(base, filepath.Join(base, "blobs", "loop"))
-	if err != nil {
-		t.Fatalf("Symlink: %v", err)
-	}
-
-	keys, err := s.List(ctx, "blobs/")
-	if err == nil {
-		t.Errorf("List = %d keys and no error, want an error", len(keys))
-	}
-
-	var streamErr error
-
-	for object := range s.ListStream(ctx, "blobs/") {
-		if object.Err != nil {
-			streamErr = object.Err
-		}
-	}
-
-	if streamErr == nil {
-		t.Error("ListStream sent no error, want one")
-	}
-}

internal/vaultik/storage_bind.go

@@ -9,7 +9,7 @@ import (
 )
 
 // errStorageBindingMismatch is returned when the local index database is
-// bound to a different destination than the configured storage_url.
+// bound to a different destination than the configured one.
 var errStorageBindingMismatch = errors.New(
 	"local index is bound to a different backup destination")
 
@@ -24,8 +24,9 @@ var errStorageBindingMismatch = errors.New(
 //
 // Behaviour:
 //   - On first use (empty stored value), record the configured
-//     storage_url and log the binding.
-//   - When the stored value matches the configured storage_url, do
+//     destination (storage_url, or the s3.* endpoint, bucket and
+//     prefix) and log the binding.
+//   - When the stored value matches the configured destination, do
 //     nothing and return nil.
 //   - When the two differ, refuse with an error that tells the user
 //     how to recover (revert the config, or run `vaultik database
@@ -46,12 +47,10 @@ func (v *Vaultik) EnsureStorageBinding() error {
 
 	configured := v.Config.StorageURL
 	if configured == "" {
-		// Some legacy configs still use the split s3.* keys instead of
-		// storage_url. Falling back to a synthetic URL for those would
-		// hide the fact that the binding is loose. Instead, treat
-		// unset as "nothing to bind against" — the check is
-		// necessarily best-effort for those configs.
-		return nil
+		// The s3.* form: bind on its endpoint, bucket and prefix,
+		// written the way storage_url would name the same destination.
+		s3 := v.Config.S3
+		configured = "s3://" + s3.Bucket + "/" + s3.Prefix + "?endpoint=" + s3.Endpoint
 	}
 
 	stored, err := v.Repositories.LocalMeta.Get(v.ctx, database.LocalMetaKeyStorageURL)
@@ -96,7 +95,8 @@ func buildBindingMismatchMessage(stored, configured string) string {
 		"future snapshots referencing blobs that don't exist at the new destination.\n" +
 		"\n" +
 		"To proceed, either:\n" +
-		"  - revert storage_url in your config to the bound destination, or\n" +
+		"  - revert storage_url (or the s3.* endpoint, bucket and prefix) in your\n" +
+		"    config to the bound destination, or\n" +
 		"  - run 'vaultik database delete' to discard the local index and rebuild it\n" +
 		"    from a fresh full backup against the new destination"
 }

internal/vaultik/storage_bind_test.go

@@ -76,3 +76,51 @@ func TestEnsureStorageBinding_MismatchRefuses(t *testing.T) {
 	assert.Contains(t, err.Error(), "file:///mnt/backups/new")
 	assert.Contains(t, err.Error(), "vaultik database delete")
 }
+
+// A config with no storage_url names its destination with s3.endpoint,
+// s3.bucket and s3.prefix; a change to any of them must be refused just
+// as a changed storage_url is.
+func TestEnsureStorageBinding_S3FieldsChangeRefuses(t *testing.T) {
+	log.Initialize(log.Config{})
+	t.Parallel()
+
+	bound := config.S3Config{
+		Endpoint: "https://s3.example.com",
+		Bucket:   "bucket-a",
+		Prefix:   "backups",
+	}
+
+	tests := []struct {
+		name    string
+		changed config.S3Config
+	}{
+		{"bucket", config.S3Config{
+			Endpoint: bound.Endpoint, Bucket: "bucket-b", Prefix: bound.Prefix,
+		}},
+		{"prefix", config.S3Config{
+			Endpoint: bound.Endpoint, Bucket: bound.Bucket, Prefix: "other",
+		}},
+		{"endpoint", config.S3Config{
+			Endpoint: "https://s3.other.com", Bucket: bound.Bucket, Prefix: bound.Prefix,
+		}},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			t.Parallel()
+
+			tv, _ := buildBindTestVaultik(t, "")
+
+			tv.Config.S3 = bound
+			require.NoError(t, tv.EnsureStorageBinding(), "first use binds")
+			require.NoError(t, tv.EnsureStorageBinding(), "same destination passes")
+
+			tv.Config.S3 = tt.changed
+			err := tv.EnsureStorageBinding()
+			require.Error(t, err)
+			assert.Contains(t, err.Error(),
+				"local index is bound to a different backup destination")
+			assert.Contains(t, err.Error(), "vaultik database delete")
+		})
+	}
+}

internal/vaultik/symlinked_destination_test.go

@@ -1,63 +0,0 @@
-package vaultik_test
-
-import (
-	"context"
-	"io/fs"
-	"os"
-	"path/filepath"
-	"testing"
-
-	"github.com/stretchr/testify/assert"
-	"github.com/stretchr/testify/require"
-	"sneak.berlin/go/vaultik/internal/log"
-	"sneak.berlin/go/vaultik/internal/vaultik"
-)
-
-// TestPruneDeletesNothingThroughSymlinkedDirectory checks that prune keeps
-// every blob and the local snapshot record when the metadata/ or blobs/
-// directory of a file:// destination is a symlink to a directory elsewhere
-// (https://git.eeqj.de/sneak/vaultik/issues/296). A backup writes through
-// such a link, so prune has to list through it too.
-func TestPruneDeletesNothingThroughSymlinkedDirectory(t *testing.T) {
-	log.Initialize(log.Config{})
-	t.Parallel()
-
-	for _, dir := range []string{"metadata", "blobs"} {
-		t.Run(dir, func(t *testing.T) {
-			t.Parallel()
-
-			ctx := context.Background()
-			storeDir := filepath.Join(t.TempDir(), "store")
-			v, repos, _ := backUpToFileDestination(ctx, t, storeDir)
-
-			var blobFiles []string
-
-			err := filepath.WalkDir(filepath.Join(storeDir, "blobs"),
-				func(path string, entry fs.DirEntry, err error) error {
-					if err == nil && !entry.IsDir() {
-						blobFiles = append(blobFiles, path)
-					}
-
-					return err
-				})
-			require.NoError(t, err)
-			require.NotEmpty(t, blobFiles)
-
-			linkPath := filepath.Join(storeDir, dir)
-			movedPath := filepath.Join(t.TempDir(), dir)
-			require.NoError(t, os.Rename(linkPath, movedPath))
-			require.NoError(t, os.Symlink(movedPath, linkPath))
-
-			require.NoError(t, v.Prune(&vaultik.PruneOptions{Force: true}))
-
-			// When blobs/ is the link, these paths run through it.
-			for _, blobFile := range blobFiles {
-				assert.FileExists(t, blobFile, "prune must delete no blob")
-			}
-
-			snapshots, err := repos.Snapshots.ListRecent(ctx, listRecentTestLimit)
-			require.NoError(t, err)
-			assert.Len(t, snapshots, 1, "prune must delete no local snapshot record")
-		})
-	}
-}