Keep unlocker list working when unlocker metadata is corrupt (closes #42)

PGPUnlocker.GetID() panicked when its metadata could not be read or
parsed, which took down `secret unlocker list` for every unlocker. It
now warns with the unlocker's directory and returns `pgp-unknown`;
metadata with an empty GPG key ID counts as corrupt too.
ListUnlockers now skips, with a warning, an unlocker whose metadata
file is unreadable or not JSON, as it already did for a missing one.

This is the first half of the issue only. Passing the mnemonic in
memory moved to #60.

Model: opus-5-5

.dockerignore

@@ -1,3 +1,9 @@
+# .git is sent without its config. Without a VERSION build argument the
+# stage that compiles runs `git describe --tags --always` on .git, which
+# does not need .git/config; that file can hold a credential, such as a
+# password in a remote URL or the token the CI checkout step stores there.
+.git/config
+
 # Build artifacts
 secret
 coverage.out

Dockerfile

@@ -27,7 +27,20 @@ RUN go mod download
 COPY . .
 
 RUN make test
-RUN make build
+
+# The version stamped into the binary: the VERSION build argument when one
+# is given, otherwise `git describe --tags --always` of the .git the build
+# context carries: the tag on a tagged commit, tag-N-gHASH on a commit after
+# one, the short commit when no tag is reachable. A context that carries .git
+# and still yields no version fails the build.
+ARG VERSION
+RUN version="${VERSION:-$(git describe --tags --always)}"; \
+    if [ -e .git ] && { [ -z "$version" ] || [ "$version" = dev ] || \
+        [ "$version" = unknown ]; }; then \
+        echo "no version could be derived although the build context carries .git" >&2; \
+        exit 1; \
+    fi; \
+    make build VERSION="${version:-dev}"
 
 # Runtime stage
 # alpine 3.23 (2026-03-10)

Makefile

@@ -2,7 +2,7 @@ export CGO_ENABLED=1
 export DOCKER_HOST := ssh://root@ber1app1.local
 
 # Version information
-VERSION := 0.1.0
+VERSION := $(shell git describe --tags --always --dirty 2>/dev/null || echo "dev")
 GIT_COMMIT := $(shell git rev-parse HEAD 2>/dev/null || echo "unknown")
 LDFLAGS := -X 'git.eeqj.de/sneak/secret/internal/cli.Version=$(VERSION)' \
            -X 'git.eeqj.de/sneak/secret/internal/cli.GitCommit=$(GIT_COMMIT)'

TODO.md

@@ -25,6 +25,19 @@ Bring the repo into policy compliance in one commit:
 
 # Completed Steps
 
+- 2026-10-03: A PGP unlocker whose metadata has no usable GPG key ID
+  no longer panics: `GetID()` warns with the unlocker's directory and
+  returns `pgp-unknown`. `ListUnlockers` skips, with a warning, an
+  unlocker whose metadata file cannot be read or parsed instead of
+  failing, so `secret unlocker list` still lists the others.
+- 2026-10-02: A plain `docker build .` builds again: the size tests
+  skip a case that needs more locked memory than the process can
+  lock, and run every case under `script/cibuild`. The image stamps the
+  `VERSION` build argument, else `git describe --tags --always`, into
+  `Version`, and fails if `.git` is present but yields no version;
+  `make build` stamps `git describe` too, not a fixed `0.1.0`.
+  `.dockerignore` keeps `.git/config` out; `script/docker` is the
+  canonical copy.
 - 2026-08-07: Updated golangci-lint to v2.12.2 with the canonical
   `.golangci.yml` (all linters enabled minus the standard disable
   list, `lll` 88, tests linted); bumped the `Dockerfile` lint-stage
@@ -93,8 +106,6 @@ Bring the repo into policy compliance in one commit:
     - Timing attacks: bytes.Equal passphrase compare (cli/init.go:
       209-216); non-constant-time public key compare (vault.go:95-100).
 - High priority:
-    - Return errors instead of panicking on corrupted metadata
-      (pgpunlocker.go:116, keychainunlocker.go:141).
     - Secure temporary file handling and cleanup.
     - Print cobra usage only for argument errors, not internal
       failures.

go.mod

@@ -16,6 +16,7 @@ require (
 	github.com/stretchr/testify v1.8.4
 	github.com/tyler-smith/go-bip39 v1.1.0
 	golang.org/x/crypto v0.38.0
+	golang.org/x/sys v0.33.0
 	golang.org/x/term v0.32.0
 )
 
@@ -31,7 +32,6 @@ require (
 	github.com/mattn/go-isatty v0.0.20 // indirect
 	github.com/pmezard/go-difflib v1.0.0 // indirect
 	github.com/spf13/pflag v1.0.6 // indirect
-	golang.org/x/sys v0.33.0 // indirect
 	golang.org/x/text v0.25.0 // indirect
 	gopkg.in/yaml.v3 v3.0.1 // indirect
 )

internal/cli/secrets_size_test.go

@@ -17,11 +17,51 @@ import (
 	"github.com/spf13/cobra"
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
+	"golang.org/x/sys/unix"
 )
 
 // testVaultName is the vault name used by the size tests.
 const testVaultName = "test-vault"
 
+// lockedBytesPerSecretByte bounds the locked memory that storing a secret
+// holds at once: the buffers it is read into reach up to 1.5 times its
+// size, and they are then copied into one more buffer of its size.
+const lockedBytesPerSecretByte = 3
+
+// skipIfLockedMemoryTooLow skips the test when this process cannot lock
+// the memory a secret of size bytes needs, found by locking a buffer of
+// that size and releasing it. memguard panics, ending the whole test run,
+// when it cannot lock a buffer, and a plain `docker build .` runs the
+// tests under an 8 MiB locked-memory limit (RLIMIT_MEMLOCK). A process
+// allowed to lock past that limit runs every case.
+func skipIfLockedMemoryTooLow(t *testing.T, size int) {
+	t.Helper()
+
+	need := lockedBytesPerSecretByte * size
+
+	buf, err := unix.Mmap(-1, 0, need,
+		unix.PROT_READ|unix.PROT_WRITE, unix.MAP_PRIVATE|unix.MAP_ANON)
+	require.NoError(t, err)
+
+	lockErr := unix.Mlock(buf)
+
+	// Unmapping the buffer also unlocks it.
+	err = unix.Munmap(buf)
+	require.NoError(t, err)
+
+	if lockErr != nil {
+		var limit unix.Rlimit
+
+		err = unix.Getrlimit(unix.RLIMIT_MEMLOCK, &limit)
+		require.NoError(t, err)
+
+		t.Skipf("a %d-byte secret needs up to %d bytes of locked memory, "+
+			"which could not be locked under the locked-memory limit "+
+			"(RLIMIT_MEMLOCK) of %d bytes: %v",
+			size, need, limit.Cur, lockErr)
+	}
+}
+
 // newSizeTestVault creates an in-memory vault unlocked with the test
 // mnemonic and returns the filesystem and vault.
 //
@@ -59,6 +99,7 @@ func newSizeTestVault(t *testing.T) (afero.Fs, *vault.Vault) {
 // verifies the outcome.
 func runAddSecretSizeCase(t *testing.T, size int, wantErr bool, errMsg string) {
 	t.Helper()
+	skipIfLockedMemoryTooLow(t, size)
 
 	fs, vlt := newSizeTestVault(t)
 
@@ -110,6 +151,7 @@ func runAddSecretSizeCase(t *testing.T, size int, wantErr bool, errMsg string) {
 // verifies the outcome.
 func runImportSecretSizeCase(t *testing.T, size int, wantErr bool, errMsg string) {
 	t.Helper()
+	skipIfLockedMemoryTooLow(t, size)
 
 	fs, vlt := newSizeTestVault(t)
 
@@ -300,6 +342,8 @@ func TestAddSecretBufferGrowth(t *testing.T) {
 
 	for _, size := range sizes {
 		t.Run(fmt.Sprintf("size_%d", size), func(t *testing.T) {
+			skipIfLockedMemoryTooLow(t, size)
+
 			fs, vlt := newSizeTestVault(t)
 
 			// Create test data of exactly the specified size

internal/cli/unlockers_list_test.go

@@ -1,13 +1,16 @@
 // Unlocker List Tests
 //
-// Tests for `secret unlocker list` behavior when the unlockers.d directory
-// cannot be read while the listing is being rendered:
+// Tests for `secret unlocker list` behavior when the unlockers.d directory,
+// or an unlocker's metadata in it, cannot be read while the listing is
+// being rendered:
 //
 //   - TestUnlockersListSkipsUnreadableUnlockersDir: an unreadable
 //     unlockers.d yields no rows rather than rows bearing synthesized IDs.
 //   - TestUnlockersListSkipsOnlyUnreadableEntries: a readable entry is
 //     still listed, with its real ID and its current-unlocker marker,
 //     when a later entry's scan fails.
+//   - TestUnlockersListToleratesCorruptMetadata: one unlocker's corrupt
+//     metadata does not stop the others from being listed.
 //
 // The listing resolves each unlocker's real ID by rescanning unlockers.d
 // after the vault has already enumerated it. If that rescan fails the ID
@@ -227,3 +230,56 @@ func TestUnlockersListReadableEntriesAreListed(t *testing.T) {
 	assert.True(t, unlockers[0].IsCurrent)
 	assert.False(t, unlockers[1].IsCurrent)
 }
+
+// TestUnlockersListToleratesCorruptMetadata asserts that one unlocker with
+// corrupt metadata does not stop the listing. Metadata that is not JSON
+// leaves that unlocker out; PGP metadata without a usable GPG key ID lists
+// it as "pgp-unknown". The healthy unlocker is listed with its real ID.
+func TestUnlockersListToleratesCorruptMetadata(t *testing.T) {
+	t.Parallel()
+
+	healthyID := "pgp-" + listTestGPGKeyID + "A"
+
+	tests := []struct {
+		name     string
+		metadata string
+		wantIDs  []string
+	}{
+		{
+			name:     "not JSON",
+			metadata: "not json",
+			wantIDs:  []string{healthyID},
+		},
+		{
+			name:     "GPG key ID of the wrong type",
+			metadata: `{"type": "pgp", "gpgKeyId": 42}`,
+			wantIDs:  []string{healthyID, "pgp-unknown"},
+		},
+		{
+			name:     "GPG key ID missing",
+			metadata: `{"type": "pgp"}`,
+			wantIDs:  []string{healthyID, "pgp-unknown"},
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			t.Parallel()
+
+			fs := newListTestVault(t, 2)
+			metadataPath := filepath.Join(listTestStateDir, "vaults.d",
+				listTestVaultName, listTestUnlockersDirName,
+				listTestUnlockerDirTwo, listTestMetadataFileName)
+			require.NoError(t, afero.WriteFile(
+				fs, metadataPath, []byte(tt.metadata), listTestFilePerm,
+			))
+
+			unlockers := listUnlockersJSON(t, fs)
+			require.Len(t, unlockers, len(tt.wantIDs))
+
+			for i, wantID := range tt.wantIDs {
+				assert.Equal(t, wantID, unlockers[i].ID)
+			}
+		})
+	}
+}

internal/secret/pgpunlocker.go

@@ -155,14 +155,18 @@ func (p *PGPUnlocker) GetDirectory() string {
 	return p.Directory
 }
 
-// GetID implements Unlocker interface - generates ID from GPG key ID
+// GetID implements Unlocker interface - generates ID from GPG key ID.
+// If the metadata has no usable GPG key ID, it warns with the unlocker's
+// directory and returns "pgp-unknown", so listing the other unlockers
+// still works.
 func (p *PGPUnlocker) GetID() string {
 	// Generate ID using GPG key ID: pgp-<keyid>
 	gpgKeyID, err := p.GetGPGKeyID()
 	if err != nil {
-		// The vault metadata is corrupt - this is a fatal error
-		// We cannot continue with a fallback ID as that would mask data corruption
-		panic(fmt.Sprintf("PGP unlocker metadata is corrupt or missing GPG key ID: %v", err))
+		Warn("PGP unlocker metadata is corrupt or missing its GPG key ID",
+			"directory", p.Directory, "error", err)
+
+		return "pgp-unknown"
 	}
 
 	return "pgp-" + gpgKeyID
@@ -197,6 +201,10 @@ func (p *PGPUnlocker) GetGPGKeyID() (string, error) {
 		return "", fmt.Errorf("failed to parse PGP metadata: %w", err)
 	}
 
+	if pgpMetadata.GPGKeyID == "" {
+		return "", fmt.Errorf("PGP metadata: %w", errGPGKeyIDEmpty)
+	}
+
 	return pgpMetadata.GPGKeyID, nil
 }
 

internal/vault/unlockers.go

@@ -247,16 +247,20 @@ func (v *Vault) ListUnlockers() ([]UnlockerMetadata, error) {
 
 			metadataBytes, err := afero.ReadFile(v.fs, metadataPath)
 			if err != nil {
-				return nil, fmt.Errorf(
-					"failed to read metadata for unlocker %s: %w", file.Name(), err)
+				secret.Warn("Skipping unlocker directory with unreadable metadata file",
+					"directory", file.Name(), "error", err)
+
+				continue
 			}
 
 			var metadata UnlockerMetadata
 
 			err = json.Unmarshal(metadataBytes, &metadata)
 			if err != nil {
-				return nil, fmt.Errorf(
-					"failed to parse metadata for unlocker %s: %w", file.Name(), err)
+				secret.Warn("Skipping unlocker directory with corrupt metadata file",
+					"directory", file.Name(), "error", err)
+
+				continue
 			}
 
 			unlockers = append(unlockers, metadata)

script/cibuild

@@ -1,8 +1,9 @@
 #!/bin/sh
 # script/cibuild: run the CI build. The Dockerfile runs script/check
 # (via make check), so a successful build implies all checks pass.
-# The Gitea workflow runs this on push. The memlock ulimit is required
-# because the test suite uses memguard, which mlocks memory.
+# The Gitea workflow runs this on push. The memlock ulimit lets the tests
+# that lock large secrets in memory (memguard mlocks them) run; under the
+# lower limit of a plain `docker build .` they are skipped.
 set -eu
 
 ROOT="$(cd "$(dirname "$0")/.." && pwd -P)"

script/docker

@@ -1,7 +1,8 @@
 #!/bin/sh
 # script/docker: build the Docker image tagged with the project name.
 # Identical in all repos; the tag comes from script/projectname.
-# Generic: needs no adaptation.
+# --no-cache because the gate phases the final stage depends on are RUN
+# steps, and a cached one is a check that did not run.
 set -eu
 
 SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd -P)"
@@ -9,7 +10,15 @@ ROOT="$(cd "$SCRIPT_DIR/.." && pwd -P)"
 
 main() {
     cd "$ROOT"
-    docker build -t "$("$SCRIPT_DIR/projectname")" .
+    # Own line: a failing command substitution inside an argument does
+    # not trip `set -e`, so the inline form degrades silently to an
+    # empty constant. The VERSION build argument takes precedence over
+    # the version a build stage derives from the .git in the context.
+    version="$(git describe --tags --always --dirty 2>/dev/null || true)"
+    [ -n "$version" ] || version="unknown"
+    docker build --no-cache \
+        --build-arg VERSION="$version" \
+        -t "$("$SCRIPT_DIR/projectname")" .
 }
 
 main "$@"