Stop snapshot purge when a snapshot cannot leave the local index (closes #337)

snapshot purge, and the purge step of snapshot create --prune, logged a
failed local index delete, then deleted that snapshot's metadata from
the destination store anyway and exited 0, leaving a local record whose
metadata was gone. It now stops at that snapshot with an error, before
touching its metadata, so the command exits non-zero; snapshots already
purged stay purged. This matches how the same loop already handles a
failed metadata delete.

Model: opus-5-5

Dockerfile

@@ -5,7 +5,16 @@
 FROM golangci/golangci-lint:v2.14.0@sha256:ad862ba6b3798cbe0fd9fd7408d498fd74fbd2623a92406b2fd3898faf0bf98f AS lint
 WORKDIR /src
 COPY go.mod go.sum ./
-RUN go mod download
+# Without the time limit a stalled connection to the module proxy holds
+# this step, and every build on the host sharing it, until the kernel
+# drops the connection, which can take an hour. The limit is well above
+# the three minutes a working download can take on a busy build host.
+RUN for attempt in 1 2 3; do \
+        timeout 300 go mod download && exit 0; \
+        echo "go mod download attempt $attempt failed or ran over 300s" >&2; \
+    done; \
+    echo "module download failed: giving up after 3 attempts" >&2; \
+    exit 1
 COPY . .
 # `golangci-lint run` silently ignores an unknown top-level key in
 # .golangci.yml, such as a misspelt `linters:`; `config verify` fails on it.
@@ -18,7 +27,13 @@ RUN golangci-lint run --config .golangci.yml ./...
 FROM golang:1.26.1@sha256:cd78d88e00afadbedd272f977d375a6247455f3a4b1178f8ae8bbcb201743a8a AS test
 WORKDIR /src
 COPY go.mod go.sum ./
-RUN go mod download
+# Limited and retried as in the lint phase above.
+RUN for attempt in 1 2 3; do \
+        timeout 300 go mod download && exit 0; \
+        echo "go mod download attempt $attempt failed or ran over 300s" >&2; \
+    done; \
+    echo "module download failed: giving up after 3 attempts" >&2; \
+    exit 1
 COPY . .
 RUN go test -timeout 90s -race -cover ./... || \
     { echo "--- Rerunning with -v for details ---"; \
@@ -36,7 +51,13 @@ RUN apk add --no-cache git
 RUN git config --system --add safe.directory /src
 WORKDIR /src
 COPY go.mod go.sum ./
-RUN go mod download
+# Limited and retried as in the lint phase above.
+RUN for attempt in 1 2 3; do \
+        timeout 300 go mod download && exit 0; \
+        echo "go mod download attempt $attempt failed or ran over 300s" >&2; \
+    done; \
+    echo "module download failed: giving up after 3 attempts" >&2; \
+    exit 1
 COPY . .
 
 # The VERSION build arg when one is given, otherwise

README.md

@@ -271,17 +271,8 @@ existing file. Created with mode `0600` since it will contain credentials.
 **`config set`**: Set a scalar config value by dotted YAML path
 (e.g. `vaultik config set compression_level 9`,
 `vaultik config set storage_url "file:///mnt/backups"`). Comments and
-formatting in the file are preserved. Missing keys along the path are
+formatting in the file are preserved; intermediate maps are created as
-created: as a list when the next path element is a number (so
+needed.
-`vaultik config set age_recipients.0 age1...` works on a file without
-`age_recipients`), otherwise as a map. If the config loads, a change
-after which it would not, such as `vaultik config set compression_level 99`,
-is refused and the file is left unchanged. A config that does not load,
-such as the one `config init` writes before `storage_url` is set or one
-with a `${ENV:...}` reference to a variable not set in this shell, is
-checked one setting at a time: only a change after which the changed
-setting cannot be read, such as one giving it the wrong type (a single
-value where a list belongs or a word where a number belongs), is refused.
 
 **`snapshot create`**: Perform incremental backup of configured snapshots.
 * Optional snapshot names argument to create specific snapshots (default: all)
@@ -348,7 +339,9 @@ local index alone, and still exits zero.
 
 **`snapshot purge`**: Remove old snapshots based on criteria. Retention is
 per-snapshot-name (`--keep-latest` keeps the latest of each name, not the
-latest globally).
+latest globally). If a snapshot cannot be removed from the local index, the
+command stops there, leaves that snapshot's metadata on the destination store
+and exits non-zero; `snapshot create --prune` fails the same way.
 * `--keep-latest`: Keep only the most recent snapshot of each name
 * `--older-than <duration>`: Remove snapshots older than duration (e.g. `30d`,
   `4w`, `6mo`, `1y`; `m` is minutes, `mo` is months)

cmd/vaultik/dockermoddownload_test.go

@@ -0,0 +1,45 @@
+package main_test
+
+import (
+	"strings"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+// TestDockerfileBoundsEveryModuleDownload fails unless every
+// `go mod download` in the Dockerfile runs under a time limit, is tried
+// a fixed number of times, and then fails the build with a message that
+// names the module download (issue #351). Like the version tests, this
+// parses the Dockerfile; that a stalled download really is cut off and
+// retried was checked by hand.
+func TestDockerfileBoundsEveryModuleDownload(t *testing.T) {
+	t.Parallel()
+
+	var downloads []string
+
+	for _, instruction := range instructions(t, productDockerfile) {
+		if strings.Contains(instruction, "go mod download") {
+			downloads = append(downloads, instruction)
+		}
+	}
+
+	require.NotEmpty(t, downloads, "%s must download modules",
+		productDockerfile)
+
+	for _, download := range downloads {
+		assert.Contains(t, download, "timeout 300 go mod download",
+			"%s: a module download must have a time limit: %s",
+			productDockerfile, download)
+		assert.Contains(t, download, "for attempt in 1 2 3",
+			"%s: a module download must be retried: %s",
+			productDockerfile, download)
+		assert.Contains(t, download, "module download failed",
+			"%s: a module download that never succeeds must say so: %s",
+			productDockerfile, download)
+		assert.True(t, strings.HasSuffix(download, "exit 1"),
+			"%s: a module download that never succeeds must fail the"+
+				" build: %s", productDockerfile, download)
+	}
+}

internal/cli/config.go

@@ -44,9 +44,6 @@ var (
 	errNeedNumericIndex = errors.New("key is a list; use a numeric index")
 	errIndexOutOfRange  = errors.New("index out of range")
 	errNotMapOrList     = errors.New("key is not a map or list")
-	errWouldNotLoad     = errors.New(
-		"vaultik would not load the config after this change, " +
-			"so the file was not changed")
 )
 
 const defaultConfigTemplate = `# vaultik configuration
@@ -394,17 +391,8 @@ func newConfigSetCommand() *cobra.Command {
 		Use:   "set <key> <value>",
 		Short: "Set a config value by dotted path (e.g. compression_level 5)",
 		Long: `Sets a scalar config value addressed by dotted YAML path and writes
-the file back, preserving comments and formatting. Missing keys along
+the file back, preserving comments and formatting. Intermediate maps
-the path are created: as a list when the next path element is a
+are created as needed.
-number, otherwise as a map.
-
-If the config loads, a change after which it would not, such as
-compression_level 99, is refused and the file is left unchanged. A
-config that does not load, such as the one config init writes before
-storage_url is set or one with a ${ENV:...} reference to a variable
-not set here, is checked one setting at a time: only a change after
-which the changed setting cannot be read, such as one giving it the
-wrong type, is refused.
 
 Examples:
   vaultik config set storage_url "file:///mnt/backups"
@@ -434,14 +422,7 @@ func writeConfigSet(out *ui.Writer, path, key, value string) error {
 		return err
 	}
 
-	oldData, err := marshalConfigYAML(root)
+	err = yamlPathSet(root, strings.Split(key, "."), value)
-	if err != nil {
-		return fmt.Errorf("marshaling config: %w", err)
-	}
-
-	keys := strings.Split(key, ".")
-
-	err = yamlPathSet(root, keys, value)
 	if err != nil {
 		return err
 	}
@@ -451,21 +432,6 @@ func writeConfigSet(out *ui.Writer, path, key, value string) error {
 		return fmt.Errorf("marshaling config: %w", err)
 	}
 
-	setting, err := yamlPathOnly(root, keys)
-	if err != nil {
-		return err
-	}
-
-	settingData, err := marshalConfigYAML(setting)
-	if err != nil {
-		return fmt.Errorf("marshaling config: %w", err)
-	}
-
-	err = checkConfigChange(oldData, data, settingData)
-	if err != nil {
-		return fmt.Errorf("%w: %w", errWouldNotLoad, err)
-	}
-
 	err = os.WriteFile(path, data, configFileMode)
 	if err != nil {
 		return fmt.Errorf("writing config file: %w", err)
@@ -487,58 +453,6 @@ func writeConfigSet(out *ui.Writer, path, key, value string) error {
 	return nil
 }
 
-// checkConfigChange returns the reason vaultik would not load newData, the
-// config after a change, if the change brings that failure in. If oldData,
-// the config before it, loads, the new one must load too. A config that
-// does not load, such as one still being filled in or one with a ${...}
-// reference that cannot be filled in here, is checked one setting at a
-// time: settingData, the changed setting on its own, must decode into the
-// config type.
-func checkConfigChange(oldData, newData, settingData []byte) error {
-	oldCfg, err := config.Parse(oldData)
-	if err == nil && oldCfg.Validate() == nil {
-		newCfg, err := config.Parse(newData)
-		if err != nil {
-			return err
-		}
-
-		return newCfg.Validate()
-	}
-
-	_, err = config.Parse(settingData)
-
-	return err
-}
-
-// yamlPathOnly returns a document holding only the value at the dotted key
-// path in root, inside the maps and lists that lead to it there.
-func yamlPathOnly(root *yaml.Node, keys []string) (*yaml.Node, error) {
-	node, err := yamlPathGet(root, keys)
-	if err != nil {
-		return nil, err
-	}
-
-	for i := len(keys) - 1; i >= 0; i-- {
-		parent, err := yamlPathGet(root, keys[:i])
-		if err != nil {
-			return nil, err
-		}
-
-		if parent.Kind == yaml.SequenceNode {
-			node = &yaml.Node{
-				Kind: yaml.SequenceNode, Content: []*yaml.Node{node},
-			}
-		} else {
-			key := &yaml.Node{Kind: yaml.ScalarNode, Value: keys[i]}
-			node = &yaml.Node{
-				Kind: yaml.MappingNode, Content: []*yaml.Node{key, node},
-			}
-		}
-	}
-
-	return &yaml.Node{Kind: yaml.DocumentNode, Content: []*yaml.Node{node}}, nil
-}
-
 // marshalConfigYAML renders a config document tree with 2-space indentation,
 // matching defaultConfigTemplate. yaml.Marshal defaults to 4 spaces, which
 // would reindent the whole file on the first `config set` despite the promise
@@ -645,8 +559,8 @@ func yamlPathGet(root *yaml.Node, keys []string) (*yaml.Node, error) {
 	return node, nil
 }
 
-// yamlPathSet navigates a dotted key path, creating missing keys as needed,
+// yamlPathSet navigates a dotted key path, creating intermediate maps as
-// and sets the final key to the given scalar value. Numeric path
+// needed, and sets the final key to the given scalar value. Numeric path
 // components index into sequences; an index equal to the sequence length
 // appends a new element (e.g. "age_recipients.1" on a 1-element list).
 func yamlPathSet(root *yaml.Node, keys []string, value string) error {
@@ -659,12 +573,12 @@ func yamlPathSet(root *yaml.Node, keys []string, value string) error {
 		node = node.Content[0]
 	}
 
-	for i := range keys {
+	for i, key := range keys {
 		last := i == len(keys)-1
 
 		switch node.Kind {
 		case yaml.MappingNode:
-			node = yamlSetInMapping(node, keys, i, value, last)
+			node = yamlSetInMapping(node, key, value, last)
 		case yaml.SequenceNode:
 			next, err := yamlSetInSequence(node, keys, i, value, last)
 			if err != nil {
@@ -733,16 +647,14 @@ func yamlField(typ reflect.Type, key string) (reflect.StructField, bool) {
 	return reflect.StructField{}, false
 }
 
-// yamlSetInMapping resolves (creating if needed) the value node for the
+// yamlSetInMapping resolves (creating if needed) the value node for key
-// path element keys[i] within a mapping node, setting it to value when it
+// within a mapping node, setting it to value when it is the final path
-// is the final path element, and returns the node to descend into.
+// element, and returns the node to descend into.
-func yamlSetInMapping(
+func yamlSetInMapping(node *yaml.Node, key, value string, last bool) *yaml.Node {
-	node *yaml.Node, keys []string, i int, value string, last bool,
-) *yaml.Node {
 	var valueNode *yaml.Node
 
 	for j := 0; j+1 < len(node.Content); j += 2 {
-		if node.Content[j].Value == keys[i] {
+		if node.Content[j].Value == key {
 			valueNode = node.Content[j+1]
 
 			break
@@ -750,8 +662,13 @@ func yamlSetInMapping(
 	}
 
 	if valueNode == nil {
-		keyNode := &yaml.Node{Kind: yaml.ScalarNode, Value: keys[i]}
+		keyNode := &yaml.Node{Kind: yaml.ScalarNode, Value: key}
-		valueNode = newPathNode(keys, i, value)
+
+		valueNode = &yaml.Node{Kind: yaml.MappingNode}
+		if last {
+			valueNode = &yaml.Node{Kind: yaml.ScalarNode, Value: value}
+		}
+
 		node.Content = append(node.Content, keyNode, valueNode)
 	} else if last {
 		setScalar(valueNode, value)
@@ -779,7 +696,12 @@ func yamlSetInSequence(
 	}
 
 	if idx == len(node.Content) {
-		node.Content = append(node.Content, newPathNode(keys, i, value))
+		newNode := &yaml.Node{Kind: yaml.MappingNode}
+		if last {
+			newNode = &yaml.Node{Kind: yaml.ScalarNode, Value: value}
+		}
+
+		node.Content = append(node.Content, newNode)
 	} else if last {
 		setScalar(node.Content[idx], value)
 	}
@@ -787,22 +709,6 @@ func yamlSetInSequence(
 	return node.Content[idx], nil
 }
 
-// newPathNode returns the node to create for the missing path element
-// keys[i]: the value when it is the final path element, otherwise an empty
-// list when the next path element is a number and an empty map when not.
-func newPathNode(keys []string, i int, value string) *yaml.Node {
-	if i == len(keys)-1 {
-		return &yaml.Node{Kind: yaml.ScalarNode, Value: value}
-	}
-
-	_, err := strconv.Atoi(keys[i+1])
-	if err == nil {
-		return &yaml.Node{Kind: yaml.SequenceNode}
-	}
-
-	return &yaml.Node{Kind: yaml.MappingNode}
-}
-
 // setScalar overwrites a node in place with a plain scalar value.
 func setScalar(n *yaml.Node, value string) {
 	n.Kind = yaml.ScalarNode

internal/cli/config_test.go

@@ -58,17 +58,14 @@ func TestDefaultConfigTemplateParses(t *testing.T) {
 	}
 }
 
-// testRecipient is a valid age public key.
-const testRecipient = "age1278m9q7dp3chsh2dcy82qk27v047zywyvtxwnj4cvt0z65jw6a7q5dqhfj"
-
 // TestConfigSetRecipientOnFreshConfig follows the README quickstart: on the
 // file `config init` writes, `config set age_recipients.0` and
 // `config set storage_url` give a config that loads with that recipient.
-// Neither is refused, although the config does not load until both are set;
-// once it loads, a recipient that is not a valid key is.
 func TestConfigSetRecipientOnFreshConfig(t *testing.T) {
 	t.Parallel()
 
+	const recipient = "age1278m9q7dp3chsh2dcy82qk27v047zywyvtxwnj4cvt0z65jw6a7q5dqhfj"
+
 	path := filepath.Join(t.TempDir(), "config.yml")
 
 	err := os.WriteFile(path, []byte(defaultConfigTemplate), configFileMode)
@@ -78,7 +75,7 @@ func TestConfigSetRecipientOnFreshConfig(t *testing.T) {
 
 	out := ui.NewWithColor(&bytes.Buffer{}, false)
 
-	err = writeConfigSet(out, path, "age_recipients.0", testRecipient)
+	err = writeConfigSet(out, path, "age_recipients.0", recipient)
 	if err != nil {
 		t.Fatalf("config set age_recipients.0: %v", err)
 	}
@@ -93,211 +90,8 @@ func TestConfigSetRecipientOnFreshConfig(t *testing.T) {
 		t.Fatalf("config.Load: %v", err)
 	}
 
-	if len(cfg.AgeRecipients) != 1 || cfg.AgeRecipients[0] != testRecipient {
+	if len(cfg.AgeRecipients) != 1 || cfg.AgeRecipients[0] != recipient {
-		t.Errorf("age_recipients = %v, want [%s]", cfg.AgeRecipients, testRecipient)
+		t.Errorf("age_recipients = %v, want [%s]", cfg.AgeRecipients, recipient)
-	}
-
-	err = writeConfigSet(out, path, "age_recipients.0", "notakey")
-	if err == nil || !strings.Contains(err.Error(), "not a valid recipient") {
-		t.Errorf("config set age_recipients.0 notakey gives error %v, "+
-			"want one saying it is not a valid recipient", err)
-	}
-
-	_, err = config.Load(path)
-	if err != nil {
-		t.Errorf("config.Load after the refused change: %v", err)
-	}
-}
-
-// configWithoutRecipients loads, but has no age_recipients key and no
-// snapshot named work.
-const configWithoutRecipients = `storage_url: file:///mnt/backups
-snapshots:
-  home:
-    paths:
-      - "~"
-`
-
-// configWithUnsetReference loads only where VAULTIK_TEST_UNSET_SECRET is
-// set, as a backup job's environment might set it. No test sets it.
-const configWithUnsetReference = configWithoutRecipients + `s3:
-  secret_access_key: ${ENV:VAULTIK_TEST_UNSET_SECRET}
-`
-
-// configWithLevelReference returns configWithoutRecipients with a ${FILE:...}
-// reference on compression_level to a file holding 9, so that the config
-// loads once the reference is filled in.
-func configWithLevelReference(t *testing.T) string {
-	t.Helper()
-
-	levelPath := filepath.Join(t.TempDir(), "level")
-
-	err := os.WriteFile(levelPath, []byte("9"), configFileMode)
-	if err != nil {
-		t.Fatalf("write level: %v", err)
-	}
-
-	return configWithoutRecipients +
-		"compression_level: ${FILE:" + levelPath + "}\n"
-}
-
-// TestConfigSetIndexUnderMissingKey checks that a list index under a key
-// the file does not have creates a list, and that the result loads.
-func TestConfigSetIndexUnderMissingKey(t *testing.T) {
-	t.Parallel()
-
-	tests := []struct {
-		key   string
-		value string
-		field func(cfg *config.Config) []string
-	}{
-		{"age_recipients.0", testRecipient,
-			func(cfg *config.Config) []string { return cfg.AgeRecipients }},
-		{"snapshots.work.paths.0", "/srv/work",
-			func(cfg *config.Config) []string { return cfg.Snapshots["work"].Paths }},
-	}
-
-	for _, tt := range tests {
-		t.Run(tt.key, func(t *testing.T) {
-			t.Parallel()
-
-			path := filepath.Join(t.TempDir(), "config.yml")
-
-			err := os.WriteFile(path, []byte(configWithoutRecipients), configFileMode)
-			if err != nil {
-				t.Fatalf("write config: %v", err)
-			}
-
-			err = writeConfigSet(ui.NewWithColor(&bytes.Buffer{}, false),
-				path, tt.key, tt.value)
-			if err != nil {
-				t.Fatalf("config set %s: %v", tt.key, err)
-			}
-
-			cfg, err := config.Load(path)
-			if err != nil {
-				t.Fatalf("config.Load: %v", err)
-			}
-
-			got := tt.field(cfg)
-			if len(got) != 1 || got[0] != tt.value {
-				t.Errorf("%s gives %v, want [%s]", tt.key, got, tt.value)
-			}
-		})
-	}
-}
-
-// TestConfigSetKeepsFileThatWouldNotLoad checks that config set refuses a
-// change after which the config would not load, with an error giving the
-// reason, and leaves the file as it was. On the file `config init` writes,
-// which does not load until storage_url is set, and on one that cannot be
-// read here, only a value of the wrong type is refused.
-func TestConfigSetKeepsFileThatWouldNotLoad(t *testing.T) {
-	t.Parallel()
-
-	levelReference := configWithLevelReference(t)
-
-	tests := []struct {
-		config string
-		key    string
-		value  string
-		reason string
-	}{
-		// Index 1 of the empty list the missing key gives.
-		{configWithoutRecipients, "age_recipients.1", testRecipient,
-			"index out of range"},
-		// A list set to a single value.
-		{configWithoutRecipients, "snapshots.home.paths", "/srv",
-			"into []string"},
-		{configWithoutRecipients, "chunk_size", "fast",
-			"invalid size format"},
-		// Values of the right type that fail validation.
-		{configWithoutRecipients, "compression_level", "99",
-			"compression_level must be between 1 and 19"},
-		{configWithoutRecipients, "chunk_size", "1KB",
-			"chunk_size must be at least 1MB"},
-		// With its reference filled in, the config loads.
-		{levelReference, "chunk_size", "1KB",
-			"chunk_size must be at least 1MB"},
-		// The type check on a config that does not load yet.
-		{defaultConfigTemplate, "snapshots.apps.paths", "/srv",
-			"into []string"},
-		// The type check on a config that cannot be read here.
-		{configWithUnsetReference, "snapshots.home.paths", "/srv",
-			"into []string"},
-	}
-
-	for _, tt := range tests {
-		t.Run(tt.key+" "+tt.value, func(t *testing.T) {
-			t.Parallel()
-
-			path := filepath.Join(t.TempDir(), "config.yml")
-
-			err := os.WriteFile(path, []byte(tt.config), configFileMode)
-			if err != nil {
-				t.Fatalf("write config: %v", err)
-			}
-
-			err = writeConfigSet(ui.NewWithColor(&bytes.Buffer{}, false),
-				path, tt.key, tt.value)
-			if err == nil || !strings.Contains(err.Error(), tt.reason) {
-				t.Errorf("config set %s %s gives error %v, want one saying %q",
-					tt.key, tt.value, err, tt.reason)
-			}
-
-			data, err := os.ReadFile(path) //nolint:gosec // G304: test-controlled path
-			if err != nil {
-				t.Fatalf("read config: %v", err)
-			}
-
-			if string(data) != tt.config {
-				t.Errorf("config set %s changed the file to:\n%s",
-					tt.key, data)
-			}
-		})
-	}
-}
-
-// TestConfigSetRefusesOnlyItsOwnFailure checks that setting another key
-// works on a config with a ${...} reference on compression_level, which
-// loads because loading fills the reference in, on one whose
-// compression_level already fails to load, and on one with a reference
-// that cannot be filled in here.
-func TestConfigSetRefusesOnlyItsOwnFailure(t *testing.T) {
-	t.Parallel()
-
-	configs := map[string]string{
-		"reference":       configWithLevelReference(t),
-		"failing":         configWithoutRecipients + "compression_level: fast\n",
-		"unset reference": configWithUnsetReference,
-	}
-
-	for name, configYAML := range configs {
-		t.Run(name, func(t *testing.T) {
-			t.Parallel()
-
-			path := filepath.Join(t.TempDir(), "config.yml")
-
-			err := os.WriteFile(path, []byte(configYAML), configFileMode)
-			if err != nil {
-				t.Fatalf("write config: %v", err)
-			}
-
-			err = writeConfigSet(ui.NewWithColor(&bytes.Buffer{}, false),
-				path, "hostname", "myhost")
-			if err != nil {
-				t.Fatalf("config set hostname: %v", err)
-			}
-
-			data, err := os.ReadFile(path) //nolint:gosec // G304: test-controlled path
-			if err != nil {
-				t.Fatalf("read config: %v", err)
-			}
-
-			if !strings.Contains(string(data), "hostname: myhost") {
-				t.Errorf("config set hostname wrote:\n%s", data)
-			}
-		})
 	}
 }
 

internal/cli/entry_snapshot_purge_test.go

@@ -0,0 +1,90 @@
+package cli //nolint:testpackage // shares runEntry and the hermetic config helpers
+
+import (
+	"context"
+	"database/sql"
+	"os"
+	"path/filepath"
+	"testing"
+	"time"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+	"sneak.berlin/go/vaultik/internal/database"
+	"sneak.berlin/go/vaultik/internal/snapshot"
+	"sneak.berlin/go/vaultik/internal/types"
+)
+
+// The `snapshot purge` command word and flags used below.
+const (
+	cmdPurge       = "purge"
+	flagKeepLatest = "--keep-latest"
+	flagForce      = "--force"
+)
+
+// TestEntrySnapshotPurgeKeepsMetadataWhenLocalIndexDeleteFails makes
+// removing a snapshot from the local index fail and checks that
+// `snapshot purge` exits non-zero and leaves that snapshot's metadata on
+// the destination store. It used to log the error, delete the metadata
+// anyway and exit 0.
+//
+//nolint:paralleltest // replaces os.Args, os.Stdout, os.Stderr and the xdg globals
+func TestEntrySnapshotPurgeKeepsMetadataWhenLocalIndexDeleteFails(t *testing.T) {
+	ctx := context.Background()
+	configPath := writeHermeticPruneConfig(t, false)
+
+	// writeHermeticPruneConfig puts the index and the store directory
+	// beside the config file.
+	dir := filepath.Dir(configPath)
+
+	// Two snapshots of the same name: --keep-latest purges the older.
+	olderStart := time.Date(2026, 5, 1, 9, 0, 0, 0, time.UTC)
+	newerStart := olderStart.Add(time.Hour)
+	olderID := "test-host_test_" + olderStart.Format(time.RFC3339)
+	newerID := "test-host_test_" + newerStart.Format(time.RFC3339)
+
+	db, err := database.New(ctx, filepath.Join(dir, "index.sqlite"))
+	require.NoError(t, err)
+
+	repos := database.NewRepositories(db)
+
+	manifestPaths := make(map[string]string)
+
+	for id, startedAt := range map[string]time.Time{
+		olderID: olderStart,
+		newerID: newerStart,
+	} {
+		completedAt := startedAt.Add(time.Minute)
+		snap := &database.Snapshot{
+			ID:             types.SnapshotID(id),
+			Hostname:       "test-host",
+			VaultikVersion: "test",
+			StartedAt:      startedAt,
+			CompletedAt:    &completedAt,
+		}
+
+		err = repos.WithTx(ctx, func(ctx context.Context, tx *sql.Tx) error {
+			return repos.Snapshots.Create(ctx, tx, snap)
+		})
+		require.NoError(t, err)
+
+		manifestPaths[id] = filepath.Join(dir, "store", "metadata",
+			snapshot.RemoteSnapshotKey(id), "manifest.json.zst")
+		require.NoError(t, os.MkdirAll(filepath.Dir(manifestPaths[id]), 0o750))
+		require.NoError(t, os.WriteFile(manifestPaths[id], []byte("stub"), 0o600))
+	}
+
+	_, err = db.Conn().ExecContext(ctx, `
+		CREATE TRIGGER refuse_snapshot_delete BEFORE DELETE ON snapshots
+		BEGIN SELECT RAISE(ABORT, 'simulated index error'); END`)
+	require.NoError(t, err)
+	require.NoError(t, db.Close())
+
+	code, _, stderr := runEntry(t,
+		flagConfig, configPath, cmdSnapshot, cmdPurge, flagKeepLatest, flagForce)
+
+	assert.Equal(t, 1, code)
+	assert.Contains(t, stderr, "simulated index error")
+	assert.FileExists(t, manifestPaths[olderID],
+		"a snapshot still in the local index keeps its metadata")
+}

internal/config/config.go

@@ -4,7 +4,6 @@
 package config
 
 import (
-	"bytes"
 	"errors"
 	"fmt"
 	"os"
@@ -234,48 +233,14 @@ func New(path Path) (*Config, error) {
 	return cfg, nil
 }
 
-// Load reads the configuration file at path, parses it with Parse, warns
+// Load reads and parses the configuration file from the specified path.
-// when others can read the file, and validates the configuration.
+// It applies default values for optional fields, performs environment variable
-// Returns an error if the file cannot be read, parsed, or if validation
+// substitution using smartconfig, and validates the configuration.
-// fails.
+// The configuration file should be in YAML format. Returns an error if the file
+// cannot be read, parsed, or if validation fails.
 func Load(path string) (*Config, error) {
-	data, err := os.ReadFile(path) //nolint:gosec // G304: config path is operator-supplied
-	if err != nil {
-		return nil, fmt.Errorf("failed to load config file: %w", err)
-	}
-
-	cfg, err := Parse(data)
-	if err != nil {
-		return nil, err
-	}
-
-	// Check config file permissions (warn if world or group readable)
-	//nolint:gosec // G703: config path is operator-supplied by design
-	info, statErr := os.Stat(path)
-	if statErr == nil {
-		mode := info.Mode().Perm()
-		if mode&0044 != 0 { // group or world readable
-			log.Warn(cfg.readableByOthersWarning(),
-				"path", path,
-				"mode", fmt.Sprintf("%04o", mode),
-				"recommendation", "chmod 600 "+path)
-		}
-	}
-
-	err = cfg.Validate()
-	if err != nil {
-		return nil, fmt.Errorf("invalid config: %w", err)
-	}
-
-	return cfg, nil
-}
-
-// Parse reads YAML config data as Load does, without validating it. It
-// applies default values for optional fields, fills in ${...} references
-// using smartconfig, and expands ~ in paths.
-func Parse(data []byte) (*Config, error) {
 	// Load config using smartconfig for interpolation
-	sc, err := smartconfig.NewFromReader(bytes.NewReader(data))
+	sc, err := smartconfig.NewFromConfigPath(path)
 	if err != nil {
 		return nil, fmt.Errorf("failed to load config file: %w", err)
 	}
@@ -337,6 +302,24 @@ func Parse(data []byte) (*Config, error) {
 		cfg.S3.Region = "us-east-1"
 	}
 
+	// Check config file permissions (warn if world or group readable)
+	//nolint:gosec // G703: config path is operator-supplied by design
+	info, statErr := os.Stat(path)
+	if statErr == nil {
+		mode := info.Mode().Perm()
+		if mode&0044 != 0 { // group or world readable
+			log.Warn(cfg.readableByOthersWarning(),
+				"path", path,
+				"mode", fmt.Sprintf("%04o", mode),
+				"recommendation", "chmod 600 "+path)
+		}
+	}
+
+	err = cfg.Validate()
+	if err != nil {
+		return nil, fmt.Errorf("invalid config: %w", err)
+	}
+
 	return cfg, nil
 }
 

internal/vaultik/deep_verify_test.go

@@ -1,7 +1,9 @@
 package vaultik_test
 
 import (
+	"bytes"
 	"context"
+	"crypto/rand"
 	"io"
 	"os"
 	"path/filepath"
@@ -9,7 +11,9 @@ import (
 
 	"github.com/spf13/afero"
 	"github.com/stretchr/testify/require"
+	"sneak.berlin/go/vaultik/internal/config"
 	"sneak.berlin/go/vaultik/internal/log"
+	"sneak.berlin/go/vaultik/internal/storage"
 	"sneak.berlin/go/vaultik/internal/ui"
 	"sneak.berlin/go/vaultik/internal/vaultik"
 )
@@ -77,6 +81,174 @@ func TestDeepVerifyAcceptsHealthyAndRejectsCorruptBlob(t *testing.T) {
 		"deep verify should fail on a corrupted blob")
 }
 
+// TestDeepVerifyJSONCountsBlobs checks the verified and missing counts
+// that deep verify reports under --json: on a healthy snapshot, with a
+// damaged blob, and with missing blobs. Deep verify stops at the first
+// damaged blob, so the blobs read before it are the ones verified; when
+// blobs are missing it reads no blob contents, but counts every missing
+// blob.
+func TestDeepVerifyJSONCountsBlobs(t *testing.T) {
+	log.Initialize(log.Config{})
+	t.Parallel()
+
+	fs := afero.NewOsFs()
+	ctx := context.Background()
+	storeDir := filepath.Join(t.TempDir(), "remote")
+
+	cfg, storer, snapshotID, keys := backUpSeveralBlobs(ctx, t, storeDir)
+
+	healthy, err := deepVerifyJSON(ctx, t, cfg, storer, snapshotID)
+	require.NoError(t, err)
+	require.Equal(t, "ok", healthy.Status)
+	require.Len(t, keys, healthy.BlobCount)
+	require.Equal(t, healthy.BlobCount, healthy.Verified)
+	require.Zero(t, healthy.Missing)
+
+	// Damage the last blob read, keeping its length, so every blob before
+	// it is read and passes first.
+	lastPath := filepath.Join(storeDir, keys[len(keys)-1])
+	blob, err := afero.ReadFile(fs, lastPath)
+	require.NoError(t, err)
+
+	blob[len(blob)/2] ^= 0xff
+	require.NoError(t, afero.WriteFile(fs, lastPath, blob, 0o600))
+
+	got, err := deepVerifyJSON(ctx, t, cfg, storer, snapshotID)
+	require.Error(t, err)
+	require.Equal(t, "failed", got.Status)
+	require.Equal(t, healthy.BlobCount-1, got.Verified)
+	require.Zero(t, got.Missing)
+
+	// Delete the first blob and the damaged last one: both must be
+	// counted as missing, not only the first one found.
+	var deletedSize int64
+
+	for _, key := range []string{keys[0], keys[len(keys)-1]} {
+		info, statErr := storer.Stat(ctx, key)
+		require.NoError(t, statErr)
+
+		deletedSize += info.Size
+
+		require.NoError(t, storer.Delete(ctx, key))
+	}
+
+	got, err = deepVerifyJSON(ctx, t, cfg, storer, snapshotID)
+	require.Error(t, err)
+	require.Equal(t, "failed", got.Status)
+	require.Equal(t, 2, got.Missing)
+	require.Equal(t, deletedSize, got.MissingSize)
+	require.Zero(t, got.Verified)
+}
+
+// TestDeepVerifyJSONCountsWrongSizeBlob checks that under --deep --json a
+// blob of the wrong size is counted in mismatched and fails the run, and
+// that the check goes on past it to count a missing blob after it.
+func TestDeepVerifyJSONCountsWrongSizeBlob(t *testing.T) {
+	log.Initialize(log.Config{})
+	t.Parallel()
+
+	fs := afero.NewOsFs()
+	ctx := context.Background()
+	storeDir := filepath.Join(t.TempDir(), "remote")
+
+	cfg, storer, snapshotID, keys := backUpSeveralBlobs(ctx, t, storeDir)
+
+	// Make the first blob checked longer, and delete the last one.
+	firstPath := filepath.Join(storeDir, keys[0])
+	blob, err := afero.ReadFile(fs, firstPath)
+	require.NoError(t, err)
+
+	blob = append(blob, []byte("extra")...)
+	require.NoError(t, afero.WriteFile(fs, firstPath, blob, 0o600))
+	require.NoError(t, storer.Delete(ctx, keys[len(keys)-1]))
+
+	got, err := deepVerifyJSON(ctx, t, cfg, storer, snapshotID)
+	require.Error(t, err)
+	require.Equal(t, "failed", got.Status)
+	require.Equal(t, 1, got.Mismatched)
+	require.Equal(t, 1, got.Missing)
+	require.Zero(t, got.Verified)
+}
+
+// TestDeepVerifyStopsOnBlobThatCannotBeChecked checks that a blob that is
+// present in storage but cannot be checked is not counted as missing:
+// deep verify stops and fails with the storage error.
+func TestDeepVerifyStopsOnBlobThatCannotBeChecked(t *testing.T) {
+	log.Initialize(log.Config{})
+	t.Parallel()
+
+	ctx := context.Background()
+	storeDir := filepath.Join(t.TempDir(), "remote")
+
+	cfg, storer, snapshotID, keys := backUpSeveralBlobs(ctx, t, storeDir)
+	failing := statFailingStorer{Storer: storer, failKeys: []string{keys[0]}}
+
+	got, err := deepVerifyJSON(ctx, t, cfg, failing, snapshotID)
+	require.Error(t, err)
+	require.Equal(t, "failed", got.Status)
+	require.Zero(t, got.Missing)
+	require.Contains(t, got.ErrorMessage, errStatDenied.Error())
+}
+
+// backUpSeveralBlobs backs up random data, which does not compress or
+// deduplicate, so it fills at least three blobs in a store on disk at
+// storeDir. It returns the blobs' storage keys sorted, which is hash
+// order, the order deep verify reads them in.
+func backUpSeveralBlobs(
+	ctx context.Context, t *testing.T, storeDir string,
+) (*config.Config, *storage.FileStorer, string, []string) {
+	t.Helper()
+
+	fs := afero.NewOsFs()
+	tempDir := t.TempDir()
+	dataDir := filepath.Join(tempDir, "source")
+	dbPath := filepath.Join(tempDir, "index.sqlite")
+
+	chunkSize := int64(32 * 1024)
+	maxBlobSize := int64(128 * 1024)
+
+	data := make([]byte, maxBlobSize*4)
+	_, err := rand.Read(data)
+	require.NoError(t, err)
+	require.NoError(t, fs.MkdirAll(dataDir, 0o755))
+	require.NoError(t, afero.WriteFile(fs,
+		filepath.Join(dataDir, "data.bin"), data, 0o644))
+
+	cfg, storer, snapshotID := runFileStorageBackup(
+		ctx, t, fs, dataDir, storeDir, dbPath, chunkSize, maxBlobSize)
+
+	keys := storedBlobKeys(t, storeDir)
+	require.GreaterOrEqual(t, len(keys), 3)
+
+	return cfg, storer, snapshotID, keys
+}
+
+// deepVerifyJSON runs deep verify with --json on snapshotID and returns
+// the decoded result and the error RunDeepVerify returned.
+func deepVerifyJSON(
+	ctx context.Context, t *testing.T,
+	cfg *config.Config, storer storage.Storer, snapshotID string,
+) (vaultik.VerifyResult, error) {
+	t.Helper()
+
+	var out bytes.Buffer
+
+	v := &vaultik.Vaultik{
+		Config:  cfg,
+		Storage: storer,
+		Fs:      afero.NewOsFs(),
+		Stdout:  &out,
+		Stderr:  io.Discard,
+		UI:      ui.NewWithColor(io.Discard, false),
+	}
+	v.SetContext(ctx)
+
+	err := v.RunDeepVerify(snapshotID,
+		&vaultik.VerifyOptions{Deep: true, JSON: true})
+
+	return decodeVerifyResult(t, out.Bytes()), err
+}
+
 // corruptOneBlob flips a middle byte of the first blob file found under
 // blobsDir, leaving the file length unchanged.
 func corruptOneBlob(t *testing.T, fs afero.Fs, blobsDir string) {

internal/vaultik/snapshot.go

@@ -627,7 +627,8 @@ func selectSnapshotsToPurge(
 }
 
 // confirmAndExecutePurge shows deletion candidates, confirms with the
-// user, and deletes snapshots.
+// user, and deletes snapshots. It stops with an error at the first
+// snapshot it cannot delete.
 func (v *Vaultik) confirmAndExecutePurge(
 	toDelete []SnapshotInfo, force, quiet bool,
 ) error {
@@ -669,10 +670,11 @@ func (v *Vaultik) confirmAndExecutePurge(
 		snapshotID := snap.ID.String()
 		log.Info("Deleting snapshot", "id", snapshotID)
 
+		// Stop before the remote delete: a snapshot still in the local
+		// index must keep its metadata on the destination store.
 		err := v.deleteSnapshotFromLocalDB(snapshotID)
 		if err != nil {
-			log.Error("Failed to delete from local database",
+			return fmt.Errorf("deleting snapshot %s from local index: %w", snapshotID, err)
-				"snapshot_id", snapshotID, "error", err)
 		}
 
 		_, err = v.deleteRemoteSnapshotByKey(snapshot.RemoteSnapshotKey(snapshotID))

internal/vaultik/verify.go

@@ -17,6 +17,7 @@ import (
 	"sneak.berlin/go/vaultik/internal/database"
 	"sneak.berlin/go/vaultik/internal/log"
 	"sneak.berlin/go/vaultik/internal/snapshot"
+	"sneak.berlin/go/vaultik/internal/storage"
 )
 
 // Sentinel errors for snapshot verification failures.
@@ -32,7 +33,9 @@ var (
 	errManifestExtraBlob   = errors.New("manifest contains blob not in database")
 	errManifestMissingBlob = errors.New(
 		"manifest omits blob present in database")
-	errBlobSizeMismatch = errors.New("blob size mismatch")
+	errBlobSizeMismatch  = errors.New("blob size mismatch")
+	errBlobsNotInStorage = errors.New(
+		"blobs missing from storage or stored with the wrong size")
 )
 
 // verifyStatusFailed is the JSON status value for a failed verification.
@@ -149,7 +152,6 @@ func (v *Vaultik) RunDeepVerify(snapshotID string, opts *VerifyOptions) error {
 	}
 
 	result.Status = "ok"
-	result.Verified = len(dbBlobs)
 
 	if opts.JSON {
 		return v.outputVerifyJSON(result)
@@ -306,7 +308,7 @@ func (v *Vaultik) runVerificationSteps(
 		v.stdoutf("Checking blob existence in remote storage...\n")
 	}
 
-	err = v.verifyBlobExistenceFromDB(dbBlobs)
+	err = v.verifyBlobExistenceFromDB(dbBlobs, result)
 	if err != nil {
 		return v.deepVerifyFailure(result, opts, err.Error(), err)
 	}
@@ -317,7 +319,8 @@ func (v *Vaultik) runVerificationSteps(
 			len(dbBlobs), ubytes(totalSize))
 	}
 
-	err = v.performDeepVerificationFromDB(dbBlobs, tdb.db.Conn(), opts, identities)
+	err = v.performDeepVerificationFromDB(
+		dbBlobs, tdb.db.Conn(), opts, result, identities)
 	if err != nil {
 		return v.deepVerifyFailure(result, opts, err.Error(), err)
 	}
@@ -669,8 +672,14 @@ func (v *Vaultik) verifyManifestAgainstDatabase(
 	return nil
 }
 
-// verifyBlobExistenceFromDB checks that all blobs from database exist in S3
+// verifyBlobExistenceFromDB checks that every blob from the database is
-func (v *Vaultik) verifyBlobExistenceFromDB(blobs []snapshot.BlobInfo) error {
+// in storage with the size the database records. It checks them all,
+// counting the missing and wrong-size blobs in result, and fails if it
+// found any. Any storage error other than not found stops the check and
+// fails with that error.
+func (v *Vaultik) verifyBlobExistenceFromDB(
+	blobs []snapshot.BlobInfo, result *VerifyResult,
+) error {
 	log.Info("Verifying blob existence in S3", "blob_count", len(blobs))
 
 	for i, blob := range blobs {
@@ -683,17 +692,23 @@ func (v *Vaultik) verifyBlobExistenceFromDB(blobs []snapshot.BlobInfo) error {
 		// Construct blob path
 		blobPath := fmt.Sprintf("blobs/%s/%s/%s", blob.Hash[:2], blob.Hash[2:4], blob.Hash)
 
-		// Check blob exists
 		stat, err := v.Storage.Stat(v.ctx, blobPath)
-		if err != nil {
+		switch {
-			return fmt.Errorf("blob %s missing from storage: %w", blob.Hash, err)
+		case errors.Is(err, storage.ErrNotFound):
-		}
+			log.Warn("Blob missing from storage", "hash", blob.Hash)
 
-		// Verify size matches
+			result.Missing++
-		if stat.Size != blob.CompressedSize {
+			result.MissingSize += blob.CompressedSize
-			return fmt.Errorf(
+		case err != nil:
-				"%w: blob %s: S3 has %d bytes, database has %d bytes",
+			return fmt.Errorf("checking blob %s in storage: %w",
-				errBlobSizeMismatch, blob.Hash, stat.Size, blob.CompressedSize)
+				blob.Hash, err)
+		case stat.Size != blob.CompressedSize:
+			log.Warn("Blob has the wrong size in storage",
+				"hash", blob.Hash,
+				"storage_size", stat.Size,
+				"database_size", blob.CompressedSize)
+
+			result.Mismatched++
 		}
 
 		// Progress update every 100 blobs
@@ -707,16 +722,22 @@ func (v *Vaultik) verifyBlobExistenceFromDB(blobs []snapshot.BlobInfo) error {
 		}
 	}
 
+	if result.Missing > 0 || result.Mismatched > 0 {
+		return fmt.Errorf("%w: %d missing, %d with the wrong size",
+			errBlobsNotInStorage, result.Missing, result.Mismatched)
+	}
+
 	log.Info("✓ All blobs exist in storage")
 
 	return nil
 }
 
 // performDeepVerificationFromDB downloads and verifies the content of
-// each blob using the database as source.
+// each blob using the database as source, stopping at the first blob that
+// fails. Each blob that passes is counted in result.Verified.
 func (v *Vaultik) performDeepVerificationFromDB(
 	blobs []snapshot.BlobInfo, db *sql.DB, opts *VerifyOptions,
-	identities []age.Identity,
+	result *VerifyResult, identities []age.Identity,
 ) error {
 	// Calculate total bytes for ETA
 	var totalBytesExpected int64
@@ -739,6 +760,7 @@ func (v *Vaultik) performDeepVerificationFromDB(
 			return fmt.Errorf("blob %s verification failed: %w", blobInfo.Hash, err)
 		}
 
+		result.Verified++
 		bytesProcessed += blobInfo.CompressedSize
 		elapsed := time.Since(startTime)
 		remaining := len(blobs) - (i + 1)