Stamp Docker image version from the host; flush profiles on error exit (closes #75)

script/docker and script/cibuild compute the version (via script/version),
commit and build date on the host and pass them as build args; the
Dockerfile no longer runs git, which always returned "unknown" because
the build context excludes .git. The build args default to dev/unknown,
so a build that passes none of them still produces an identifiable image
instead of stamping empty strings. A dirty tree is reflected through
script/version's -dirty suffix.

main now exits via os.Exit(run()), so its deferred CPU/heap profile
writers flush before the process ends, and Entry returns a status code
instead of calling os.Exit. Each command ran its operation in an fx
goroutine that called os.Exit(1) on failure, discarding those profiles
and the PID-lock release; they now route the error to the return path
through one RunOperation helper. errReported keeps Entry from printing an
already-reported failure twice.

model: claude-opus-4-8

Dockerfile

@@ -20,8 +20,6 @@
 # golang:1.26.1-alpine, 2026-03-17
 FROM golang:1.26.1-alpine@sha256:2389ebfa5b7f43eeafbd6be0c3700cc46690ef842ad962f6c5bd6be49ed82039 AS builder
 
-ARG VERSION=dev
-
 # Build tooling: make, plus a C toolchain because `go test -race` needs cgo.
 # The sqlite driver is pure Go (modernc.org/sqlite), so no sqlite library or
 # CLI is required.
@@ -66,8 +64,31 @@ RUN [ -n "$CHECK_EPOCH" ] || exit 1
 RUN echo "check epoch: ${CHECK_EPOCH}" && make fmt-check
 RUN echo "check epoch: ${CHECK_EPOCH}" && make test
 
+# Version, commit and build date are computed on the host by
+# script/docker and script/cibuild (where .git exists) and passed in as
+# build args. The build context excludes .git (see .dockerignore), so
+# the build cannot derive them itself: it used to try, with `git
+# rev-parse` inside this stage, and always got "unknown". VERSION comes
+# from script/version, the source of truth shared with the Makefile, so
+# it carries the same tag / dev-<sha> / -dirty rules and a Docker image
+# reports the same string a local build of the same tree would.
+#
+# The defaults are the fallback for a bare `docker build .` that passes
+# none of them: an unset arg would otherwise stamp an empty string and
+# produce an image that cannot report its own version, commit or date.
+# They match what an out-of-git build reports elsewhere.
+#
+# These ARGs sit here, after the checks, rather than at the top of the
+# stage: every commit changes their values, and a value change
+# invalidates all layers below the ARG. Declared up top they would bust
+# `go mod download`; here they only rekey this build layer, which the
+# COPY of the sources above already rebuilds on any change anyway.
+ARG VERSION=dev
+ARG COMMIT=unknown
+ARG COMMIT_DATE=unknown
+
 # Build (pure Go, no CGO required since we use modernc.org/sqlite)
-RUN CGO_ENABLED=0 go build -ldflags "-X 'sneak.berlin/go/vaultik/internal/globals.Version=${VERSION}' -X 'sneak.berlin/go/vaultik/internal/globals.Commit=$(git rev-parse HEAD 2>/dev/null || echo unknown)' -X 'sneak.berlin/go/vaultik/internal/globals.CommitDate=$(git show -s --format=%cs HEAD 2>/dev/null || echo unknown)'" -o /vaultik ./cmd/vaultik
+RUN CGO_ENABLED=0 go build -ldflags "-X 'sneak.berlin/go/vaultik/internal/globals.Version=${VERSION}' -X 'sneak.berlin/go/vaultik/internal/globals.Commit=${COMMIT}' -X 'sneak.berlin/go/vaultik/internal/globals.CommitDate=${COMMIT_DATE}'" -o /vaultik ./cmd/vaultik
 
 # Runtime stage
 # alpine:3.21, 2026-02-25

cmd/vaultik/dockerversion_test.go

@@ -0,0 +1,102 @@
+package main_test
+
+import (
+	"strings"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+// This file guards the version stamping of the product image (issue
+// #75). The failure it protects against is silent: the image still
+// builds and runs, but `vaultik version` inside it reports "commit:
+// unknown", so an operator cannot tell which source produced a given
+// backup. .dockerignore excludes .git, so the build cannot derive the
+// commit itself; the values must be computed on the host and passed in.
+//
+// These are parses of the committed files, for the same reason the lint
+// guards next door are: shelling out to docker would nest a build
+// inside `make test`. That `vaultik version` in the built image really
+// prints the host's version is verified by hand and recorded on the
+// pull request.
+
+// dockerScript is script/docker, relative to the repository root.
+const dockerScript = "script/docker"
+
+// versionArgs are the ldflag targets the build stamps and, matching
+// them, the build args the host must supply. The names line up so the
+// same list checks both files.
+func versionArgs() []string {
+	return []string{"VERSION", "COMMIT", "COMMIT_DATE"}
+}
+
+// TestProductDockerfileTakesVersionAsBuildArgs fails unless the build
+// declares each version arg and stamps it into the binary by ldflag
+// reference, rather than computing it in the container.
+func TestProductDockerfileTakesVersionAsBuildArgs(t *testing.T) {
+	t.Parallel()
+
+	found := instructions(t, productDockerfile)
+
+	for _, arg := range versionArgs() {
+		require.GreaterOrEqual(t, indexOf(found, "ARG "+arg), 0,
+			"%s must declare `ARG %s` so the host can pass it in",
+			productDockerfile, arg)
+
+		assertLdflagReferences(t, found, arg)
+	}
+}
+
+// TestProductDockerfileDoesNotDeriveVersionItself is the anti-regression
+// for the original defect: the container ran `git rev-parse`, but .git
+// is not in the build context, so it always resolved to "unknown". No
+// git command may reach into a build that cannot see the history.
+func TestProductDockerfileDoesNotDeriveVersionItself(t *testing.T) {
+	t.Parallel()
+
+	text := instructionText(readRepoFile(t, productDockerfile))
+
+	assert.NotContains(t, text, "git ",
+		"%s must not run git: .git is excluded from the build context, so"+
+			" any value it derives is wrong. Pass version, commit and date"+
+			" in as build args instead.", productDockerfile)
+}
+
+// TestDockerScriptComputesVersionOnTheHost fails unless script/docker
+// derives each value where .git exists and passes it as a build arg,
+// with VERSION coming from script/version so a Docker build reports the
+// same string a local build of the same tree would.
+func TestDockerScriptComputesVersionOnTheHost(t *testing.T) {
+	t.Parallel()
+
+	script := readRepoFile(t, dockerScript)
+
+	for _, arg := range versionArgs() {
+		assert.Contains(t, script, "--build-arg "+arg+"=",
+			"%s must pass --build-arg %s to the build", dockerScript, arg)
+	}
+
+	assert.Contains(t, script, "/version",
+		"%s must take VERSION from script/version, the source of truth"+
+			" shared with the Makefile", dockerScript)
+}
+
+// assertLdflagReferences fails unless some build instruction stamps the
+// named variable from the ARG (a ${arg} reference), not from a value
+// computed inside the container.
+func assertLdflagReferences(t *testing.T, found []string, arg string) {
+	t.Helper()
+
+	for _, instruction := range found {
+		if strings.HasPrefix(instruction, "RUN ") &&
+			strings.Contains(instruction, "go build") &&
+			strings.Contains(instruction, "${"+arg+"}") {
+			return
+		}
+	}
+
+	assert.Fail(t, "version arg is declared but never stamped",
+		"the go build in %s must reference ${%s} in its ldflags, or the"+
+			" arg is passed and discarded", productDockerfile, arg)
+}

cmd/vaultik/lintdocker_test.go

@@ -304,10 +304,14 @@ func instructionText(contents string) string {
 }
 
 // indexOf returns the position of the first instruction equal to, or
-// beginning with, want; -1 if there is none.
+// beginning with, want; -1 if there is none. An `ARG NAME=default`
+// counts as beginning with `ARG NAME`, so a declared arg is found
+// whether or not it carries a default.
 func indexOf(found []string, want string) int {
 	for i, instruction := range found {
-		if instruction == want || strings.HasPrefix(instruction, want+" ") {
+		if instruction == want ||
+			strings.HasPrefix(instruction, want+" ") ||
+			strings.HasPrefix(instruction, want+"=") {
 			return i
 		}
 	}

cmd/vaultik/main.go

@@ -10,6 +10,16 @@ import (
 )
 
 func main() {
+	os.Exit(run())
+}
+
+// run sets up optional profiling, runs the CLI, and returns the process
+// exit code. os.Exit lives in main so it fires only after run's deferred
+// profile writers have flushed. cli.Entry returns a status code rather
+// than calling os.Exit itself: an os.Exit from inside it would skip
+// these defers and truncate the profile of a failing command -- exactly
+// the command one most often wants to profile.
+func run() int {
 	// CPU profiling: set VAULTIK_CPUPROFILE=/path/to/cpu.prof
 	if cpuProfile := os.Getenv("VAULTIK_CPUPROFILE"); cpuProfile != "" {
 		f, err := os.Create(cpuProfile) //nolint:gosec // G304: operator-set path
@@ -46,5 +56,5 @@ func main() {
 		}()
 	}
 
-	cli.Entry()
+	return cli.Entry()
 }

internal/cli/app.go

@@ -11,6 +11,7 @@ import (
 	"os/signal"
 	"path/filepath"
 	"strings"
+	"sync"
 	"syscall"
 	"time"
 
@@ -196,13 +197,90 @@ func RunApp(ctx context.Context, app *fx.App) error {
 	}
 }
 
+// errReported marks a failure the operation has already shown the user
+// (and deliberately withheld under --json). Entry turns it into a
+// non-zero exit status without printing anything further, so the error
+// line is not doubled. It flows up from RunOperation through cobra to
+// Entry.
+var errReported = errors.New("operation failed")
+
+// RunOperation runs op against the Vaultik instance inside the fx app
+// and turns a failure into a returned error rather than an os.Exit from
+// within the goroutine. An os.Exit there skipped main's deferred
+// profile writers -- so profiling a failing command yielded a truncated
+// profile (issue #75) -- and RunWithApp's PID-lock release, and denied
+// the app any graceful shutdown; returning the error to the top runs
+// all three.
+//
+// op runs in a goroutine so OnStart returns promptly and an interrupt
+// can still cancel through OnStop; when it finishes, success or failure,
+// it triggers shutdown, which is what lets RunWithApp return. report is
+// called with a non-canceled failure so the caller can log it (and
+// suppress it under --json) before it becomes errReported. A context
+// cancellation is the interrupt path, not a failure: it is neither
+// reported nor counted as one.
+func RunOperation(
+	ctx context.Context, opts AppOptions,
+	op func(v *vaultik.Vaultik) error, report func(err error),
+) error {
+	var (
+		mu     sync.Mutex
+		failed bool
+	)
+
+	opts.Invokes = append(opts.Invokes,
+		fx.Invoke(func(v *vaultik.Vaultik, lc fx.Lifecycle) {
+			lc.Append(fx.Hook{
+				OnStart: func(_ context.Context) error {
+					go func() {
+						err := op(v)
+						if err != nil && !errors.Is(err, context.Canceled) {
+							report(err)
+
+							mu.Lock()
+							failed = true
+							mu.Unlock()
+						}
+
+						stopErr := v.Shutdowner.Shutdown()
+						if stopErr != nil {
+							log.Error("Failed to shutdown", "error", stopErr)
+						}
+					}()
+
+					return nil
+				},
+				OnStop: func(_ context.Context) error {
+					v.Cancel()
+
+					return nil
+				},
+			})
+		}))
+
+	err := RunWithApp(ctx, opts)
+	if err != nil {
+		return err
+	}
+
+	// The goroutine sets failed before triggering the shutdown that lets
+	// RunWithApp return, so the write is in place by the time we read it.
+	mu.Lock()
+	defer mu.Unlock()
+
+	if failed {
+		return errReported
+	}
+
+	return nil
+}
+
 // runVaultikApp runs the standard single-operation command lifecycle
 // shared by the list/purge/verify/remove/remote-info subcommands:
-// resolve the config, start the fx app, run op against the Vaultik
-// instance in a goroutine, report a failure prefixed with failMsg
-// (suppressed while suppressErrors is true, e.g. under --json), then
-// trigger shutdown. The operation is cancelled when the app stops.
-// extraQuiet is OR-ed into LogOptions.Quiet (e.g. --json output modes).
+// resolve the config, then run op against the Vaultik instance through
+// RunOperation, reporting a failure prefixed with failMsg (suppressed
+// while suppressErrors is true, e.g. under --json). extraQuiet is OR-ed
+// into LogOptions.Quiet (e.g. --json output modes).
 func runVaultikApp(
 	cmd *cobra.Command, extraQuiet, suppressErrors bool,
 	failMsg string, op func(v *vaultik.Vaultik) error,
@@ -214,47 +292,20 @@ func runVaultikApp(
 
 	rootFlags := GetRootFlags()
 
-	return RunWithApp(cmd.Context(), AppOptions{
+	return RunOperation(cmd.Context(), AppOptions{
 		ConfigPath: configPath,
 		LogOptions: log.Options{
 			Verbose: rootFlags.Verbose,
 			Debug:   rootFlags.Debug,
 			Quiet:   rootFlags.Quiet || extraQuiet,
 		},
-		Modules: []fx.Option{},
-		Invokes: []fx.Option{
-			fx.Invoke(func(v *vaultik.Vaultik, lc fx.Lifecycle) {
-				lc.Append(fx.Hook{
-					OnStart: func(_ context.Context) error {
-						go func() {
-							err := op(v)
-							if err != nil {
-								if !errors.Is(err, context.Canceled) {
-									if !suppressErrors {
-										log.Error(failMsg, "error", err)
-										ReportErrorf("%s: %v", failMsg, err)
-									}
+	}, op, func(err error) {
+		if suppressErrors {
+			return
+		}
 
-									os.Exit(1)
-								}
-							}
-
-							err = v.Shutdowner.Shutdown()
-							if err != nil {
-								log.Error("Failed to shutdown", "error", err)
-							}
-						}()
-
-						return nil
-					},
-					OnStop: func(_ context.Context) error {
-						v.Cancel()
-
-						return nil
-					},
-				})
-			}),
-		},
+		log.Error(failMsg, "error", err)
+		ReportErrorf("%s: %v", failMsg, err)
 	})
 }
 

internal/cli/entry.go

@@ -1,6 +1,7 @@
 package cli
 
 import (
+	"errors"
 	"io"
 	"os"
 	"strings"
@@ -19,7 +20,11 @@ const shortCommitLen = 12
 // flag is present in os.Args — see bannerSuppressedInArgs), executes the
 // root cobra command, and routes any returned error through the
 // ui.Writer so the user sees a properly formatted "🛑 ERROR:" line.
-func Entry() {
+//
+// It returns the process exit code (0 on success, 1 on error) rather
+// than calling os.Exit, so that main's deferred profile writers run
+// before the process ends. See run in cmd/vaultik/main.go.
+func Entry() int {
 	emitStartupBanner(os.Args[1:], os.Stdout)
 
 	rootCmd := NewRootCommand()
@@ -27,9 +32,19 @@ func Entry() {
 
 	err := rootCmd.Execute()
 	if err != nil {
-		ReportErrorf("%s", err.Error())
-		os.Exit(1)
+		// An operation that ran inside the fx app has already reported
+		// its own failure (and suppressed it under --json); errReported
+		// says so. Printing it again here would double the error line.
+		// Every other error — bad arguments, a config that would not
+		// load — reaches Entry unreported, so it is shown here.
+		if !errors.Is(err, errReported) {
+			ReportErrorf("%s", err.Error())
+		}
+
+		return 1
 	}
+
+	return 0
 }
 
 // emitStartupBanner writes the startup banner to w unless args (the

internal/cli/entry_banner_test.go

@@ -230,7 +230,7 @@ func TestEntryJSONStdoutIsExactlyOneDocument(t *testing.T) {
 		programName, flagConfig, configPath, cmdSnapshot, cmdList, flagJSON,
 	}
 
-	stdout := captureProcessStdout(t, Entry)
+	stdout := captureProcessStdout(t, func() { _ = Entry() })
 
 	requireExactlyOneJSONDocument(t, stdout)
 

internal/cli/entry_prune_json_test.go

@@ -81,7 +81,7 @@ func TestEntryPruneJSONStdoutIsExactlyOneDocument(t *testing.T) {
 				programName, flagConfig, configPath, cmdPrune, flagJSON,
 			}
 
-			stdout := captureProcessStdout(t, Entry)
+			stdout := captureProcessStdout(t, func() { _ = Entry() })
 
 			requireExactlyOneJSONDocument(t, stdout)
 

internal/cli/entry_status_test.go

@@ -0,0 +1,58 @@
+package cli //nolint:testpackage // shares programName and the capture helpers
+
+import (
+	"os"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+)
+
+// TestEntryReturnsStatusCode pins the contract main() relies on for
+// issue #75: Entry reports success or failure through its return value
+// and never calls os.Exit. An os.Exit from inside Entry would skip
+// main's deferred profile writers and truncate the profile of a failing
+// command. main turns this code into os.Exit only after those defers
+// run, so a failing command must come back with a non-zero code rather
+// than ending the process here.
+//
+// Stdout is captured only to keep the banner and command output off the
+// test log; the assertion is on the returned code.
+//
+//nolint:paralleltest // replaces os.Args and rootFlags
+func TestEntryReturnsStatusCode(t *testing.T) {
+	for _, testCase := range []struct {
+		name string
+		args []string
+		want int
+	}{
+		{
+			// version is self-contained: it needs no config and no
+			// destination store, so it exercises the success path.
+			name: "successful command returns zero",
+			args: []string{programName, "version"},
+			want: 0,
+		},
+		{
+			name: "unknown command returns one",
+			args: []string{programName, "no-such-command"},
+			want: 1,
+		},
+	} {
+		t.Run(testCase.name, func(t *testing.T) {
+			previousArgs := os.Args
+
+			t.Cleanup(func() {
+				os.Args = previousArgs
+				rootFlags = RootFlags{}
+			})
+
+			os.Args = testCase.args
+
+			var code int
+
+			_ = captureProcessStdout(t, func() { code = Entry() })
+
+			assert.Equal(t, testCase.want, code)
+		})
+	}
+}

internal/cli/info.go

@@ -1,12 +1,7 @@
 package cli
 
 import (
-	"context"
-	"errors"
-	"os"
-
 	"github.com/spf13/cobra"
-	"go.uber.org/fx"
 	"sneak.berlin/go/vaultik/internal/log"
 	"sneak.berlin/go/vaultik/internal/vaultik"
 )
@@ -33,44 +28,18 @@ func NewInfoCommand() *cobra.Command {
 			// Use the app framework
 			rootFlags := GetRootFlags()
 
-			return RunWithApp(cmd.Context(), AppOptions{
+			return RunOperation(cmd.Context(), AppOptions{
 				ConfigPath: configPath,
 				LogOptions: log.Options{
 					Verbose: rootFlags.Verbose,
 					Debug:   rootFlags.Debug,
 					Quiet:   rootFlags.Quiet,
 				},
-				Modules: []fx.Option{},
-				Invokes: []fx.Option{
-					fx.Invoke(func(v *vaultik.Vaultik, lc fx.Lifecycle) {
-						lc.Append(fx.Hook{
-							OnStart: func(_ context.Context) error {
-								go func() {
-									err := v.ShowInfo()
-									if err != nil {
-										if !errors.Is(err, context.Canceled) {
-											log.Error("Failed to show info", "error", err)
-											ReportErrorf("Failed to show info: %v", err)
-											os.Exit(1)
-										}
-									}
-
-									err = v.Shutdowner.Shutdown()
-									if err != nil {
-										log.Error("Failed to shutdown", "error", err)
-									}
-								}()
-
-								return nil
-							},
-							OnStop: func(_ context.Context) error {
-								v.Cancel()
-
-								return nil
-							},
-						})
-					}),
-				},
+			}, func(v *vaultik.Vaultik) error {
+				return v.ShowInfo()
+			}, func(err error) {
+				log.Error("Failed to show info", "error", err)
+				ReportErrorf("Failed to show info: %v", err)
 			})
 		},
 	}

internal/cli/prune.go

@@ -1,12 +1,7 @@
 package cli
 
 import (
-	"context"
-	"errors"
-	"os"
-
 	"github.com/spf13/cobra"
-	"go.uber.org/fx"
 	"sneak.berlin/go/vaultik/internal/log"
 	"sneak.berlin/go/vaultik/internal/vaultik"
 )
@@ -41,51 +36,22 @@ work (e.g. after a crashed backup or to reclaim storage).`,
 			// Use the app framework like other commands
 			rootFlags := GetRootFlags()
 
-			return RunWithApp(cmd.Context(), AppOptions{
+			return RunOperation(cmd.Context(), AppOptions{
 				ConfigPath: configPath,
 				LogOptions: log.Options{
 					Verbose: rootFlags.Verbose,
 					Debug:   rootFlags.Debug,
 					Quiet:   rootFlags.Quiet || opts.JSON,
 				},
-				Modules: []fx.Option{},
-				Invokes: []fx.Option{
-					fx.Invoke(func(v *vaultik.Vaultik, lc fx.Lifecycle) {
-						lc.Append(fx.Hook{
-							OnStart: func(_ context.Context) error {
-								// Start the prune operation in a goroutine
-								go func() {
-									// Run the prune operation
-									err := v.Prune(opts)
-									if err != nil {
-										if !errors.Is(err, context.Canceled) {
-											if !opts.JSON {
-												log.Error("Prune operation failed", "error", err)
-												ReportErrorf("Prune failed: %v", err)
-											}
+			}, func(v *vaultik.Vaultik) error {
+				return v.Prune(opts)
+			}, func(err error) {
+				if opts.JSON {
+					return
+				}
 
-											os.Exit(1)
-										}
-									}
-
-									// Shutdown the app when prune completes
-									err = v.Shutdowner.Shutdown()
-									if err != nil {
-										log.Error("Failed to shutdown", "error", err)
-									}
-								}()
-
-								return nil
-							},
-							OnStop: func(_ context.Context) error {
-								log.Debug("Stopping prune operation")
-								v.Cancel()
-
-								return nil
-							},
-						})
-					}),
-				},
+				log.Error("Prune operation failed", "error", err)
+				ReportErrorf("Prune failed: %v", err)
 			})
 		},
 	}

internal/cli/remote.go

@@ -1,12 +1,9 @@
 package cli
 
 import (
-	"context"
 	"errors"
-	"os"
 
 	"github.com/spf13/cobra"
-	"go.uber.org/fx"
 	"sneak.berlin/go/vaultik/internal/log"
 	"sneak.berlin/go/vaultik/internal/vaultik"
 )
@@ -83,47 +80,22 @@ func newRemoteInfoCommand() *cobra.Command {
 
 			rootFlags := GetRootFlags()
 
-			return RunWithApp(cmd.Context(), AppOptions{
+			return RunOperation(cmd.Context(), AppOptions{
 				ConfigPath: configPath,
 				LogOptions: log.Options{
 					Verbose: rootFlags.Verbose,
 					Debug:   rootFlags.Debug,
 					Quiet:   rootFlags.Quiet || jsonOutput,
 				},
-				Modules: []fx.Option{},
-				Invokes: []fx.Option{
-					fx.Invoke(func(v *vaultik.Vaultik, lc fx.Lifecycle) {
-						lc.Append(fx.Hook{
-							OnStart: func(_ context.Context) error {
-								go func() {
-									err := v.RemoteInfo(jsonOutput)
-									if err != nil {
-										if !errors.Is(err, context.Canceled) {
-											if !jsonOutput {
-												log.Error("Failed to get remote info", "error", err)
-												ReportErrorf("Failed to get remote info: %v", err)
-											}
+			}, func(v *vaultik.Vaultik) error {
+				return v.RemoteInfo(jsonOutput)
+			}, func(err error) {
+				if jsonOutput {
+					return
+				}
 
-											os.Exit(1)
-										}
-									}
-
-									err = v.Shutdowner.Shutdown()
-									if err != nil {
-										log.Error("Failed to shutdown", "error", err)
-									}
-								}()
-
-								return nil
-							},
-							OnStop: func(_ context.Context) error {
-								v.Cancel()
-
-								return nil
-							},
-						})
-					}),
-				},
+				log.Error("Failed to get remote info", "error", err)
+				ReportErrorf("Failed to get remote info: %v", err)
 			})
 		},
 	}

internal/cli/snapshot.go

@@ -1,13 +1,10 @@
 package cli
 
 import (
-	"context"
 	"errors"
 	"fmt"
-	"os"
 
 	"github.com/spf13/cobra"
-	"go.uber.org/fx"
 	"sneak.berlin/go/vaultik/internal/log"
 	"sneak.berlin/go/vaultik/internal/vaultik"
 )
@@ -86,7 +83,8 @@ specifying a path using --config or by setting VAULTIK_CONFIG to a path.`,
 			// Use the backup functionality from cli package
 			rootFlags := GetRootFlags()
 
-			return RunWithApp(cmd.Context(), AppOptions{
+			// --cron suppression is wired through v.UI by setupGlobals.
+			return RunOperation(cmd.Context(), AppOptions{
 				ConfigPath: configPath,
 				LogOptions: log.Options{
 					Verbose: rootFlags.Verbose,
@@ -94,42 +92,11 @@ specifying a path using --config or by setting VAULTIK_CONFIG to a path.`,
 					Cron:    opts.Cron,
 					Quiet:   rootFlags.Quiet,
 				},
-				Modules: []fx.Option{},
-				Invokes: []fx.Option{
-					fx.Invoke(func(v *vaultik.Vaultik, lc fx.Lifecycle) {
-						lc.Append(fx.Hook{
-							OnStart: func(_ context.Context) error {
-								// Start the snapshot creation in a goroutine
-								go func() {
-									// --cron suppression is wired through v.UI by setupGlobals.
-									err := v.CreateSnapshot(opts)
-									if err != nil {
-										if !errors.Is(err, context.Canceled) {
-											log.Error("Snapshot creation failed", "error", err)
-											ReportErrorf("Snapshot creation failed: %v", err)
-											os.Exit(1)
-										}
-									}
-
-									// Shutdown the app when snapshot completes
-									err = v.Shutdowner.Shutdown()
-									if err != nil {
-										log.Error("Failed to shutdown", "error", err)
-									}
-								}()
-
-								return nil
-							},
-							OnStop: func(_ context.Context) error {
-								log.Debug("Stopping snapshot creation")
-								// Cancel the Vaultik context
-								v.Cancel()
-
-								return nil
-							},
-						})
-					}),
-				},
+			}, func(v *vaultik.Vaultik) error {
+				return v.CreateSnapshot(opts)
+			}, func(err error) {
+				log.Error("Snapshot creation failed", "error", err)
+				ReportErrorf("Snapshot creation failed: %v", err)
 			})
 		},
 	}
@@ -234,47 +201,22 @@ func newSnapshotVerifyCommand() *cobra.Command {
 
 			rootFlags := GetRootFlags()
 
-			return RunWithApp(cmd.Context(), AppOptions{
+			return RunOperation(cmd.Context(), AppOptions{
 				ConfigPath: configPath,
 				LogOptions: log.Options{
 					Verbose: rootFlags.Verbose,
 					Debug:   rootFlags.Debug,
 					Quiet:   rootFlags.Quiet || opts.JSON,
 				},
-				Modules: []fx.Option{},
-				Invokes: []fx.Option{
-					fx.Invoke(func(v *vaultik.Vaultik, lc fx.Lifecycle) {
-						lc.Append(fx.Hook{
-							OnStart: func(_ context.Context) error {
-								go func() {
-									err := v.VerifySnapshotWithOptions(snapshotID, opts)
-									if err != nil {
-										if !errors.Is(err, context.Canceled) {
-											if !opts.JSON {
-												log.Error("Verification failed", "error", err)
-												ReportErrorf("Verification failed: %v", err)
-											}
+			}, func(v *vaultik.Vaultik) error {
+				return v.VerifySnapshotWithOptions(snapshotID, opts)
+			}, func(err error) {
+				if opts.JSON {
+					return
+				}
 
-											os.Exit(1)
-										}
-									}
-
-									err = v.Shutdowner.Shutdown()
-									if err != nil {
-										log.Error("Failed to shutdown", "error", err)
-									}
-								}()
-
-								return nil
-							},
-							OnStop: func(_ context.Context) error {
-								v.Cancel()
-
-								return nil
-							},
-						})
-					}),
-				},
+				log.Error("Verification failed", "error", err)
+				ReportErrorf("Verification failed: %v", err)
 			})
 		},
 	}

internal/cli/snapshot_restore.go

@@ -1,16 +1,8 @@
 package cli
 
 import (
-	"context"
-	"errors"
-	"os"
-
 	"github.com/spf13/cobra"
-	"go.uber.org/fx"
-	"sneak.berlin/go/vaultik/internal/config"
-	"sneak.berlin/go/vaultik/internal/globals"
 	"sneak.berlin/go/vaultik/internal/log"
-	"sneak.berlin/go/vaultik/internal/storage"
 	"sneak.berlin/go/vaultik/internal/vaultik"
 )
 
@@ -25,15 +17,6 @@ type RestoreOptions struct {
 	Verify    bool     // Verify restored files after restore
 }
 
-// RestoreApp contains all dependencies needed for restore
-type RestoreApp struct {
-	Globals    *globals.Globals
-	Config     *config.Config
-	Storage    storage.Storer
-	Vaultik    *vaultik.Vaultik
-	Shutdowner fx.Shutdowner
-}
-
 // newSnapshotRestoreCommand creates the 'snapshot restore' subcommand
 func newSnapshotRestoreCommand() *cobra.Command {
 	opts := &RestoreOptions{}
@@ -77,7 +60,8 @@ Examples:
 	return cmd
 }
 
-// runRestore parses arguments and runs the restore operation through the app framework
+// runRestore parses arguments and runs the restore operation through the
+// app framework.
 func runRestore(cmd *cobra.Command, args []string, opts *RestoreOptions) error {
 	snapshotID := args[0]
 
@@ -86,87 +70,30 @@ func runRestore(cmd *cobra.Command, args []string, opts *RestoreOptions) error {
 		opts.Paths = args[restoreMinArgs:]
 	}
 
-	// Use unified config resolution
 	configPath, err := ResolveConfigPath()
 	if err != nil {
 		return err
 	}
 
-	// Use the app framework like other commands
 	rootFlags := GetRootFlags()
 
-	return RunWithApp(cmd.Context(), AppOptions{
+	return RunOperation(cmd.Context(), AppOptions{
 		ConfigPath: configPath,
 		LogOptions: log.Options{
 			Verbose: rootFlags.Verbose,
 			Debug:   rootFlags.Debug,
 			Quiet:   rootFlags.Quiet,
 		},
-		Modules: buildRestoreModules(),
-		Invokes: buildRestoreInvokes(snapshotID, opts),
+	}, func(v *vaultik.Vaultik) error {
+		return v.Restore(&vaultik.RestoreOptions{
+			SnapshotID: snapshotID,
+			TargetDir:  opts.TargetDir,
+			Paths:      opts.Paths,
+			Verify:     opts.Verify,
+			SkipErrors: rootFlags.SkipErrors,
+		})
+	}, func(err error) {
+		log.Error("Restore operation failed", "error", err)
+		ReportErrorf("Restore failed: %v", err)
 	})
 }
-
-// buildRestoreModules returns the fx.Options for dependency injection in restore
-func buildRestoreModules() []fx.Option {
-	return []fx.Option{
-		fx.Provide(fx.Annotate(
-			func(g *globals.Globals, cfg *config.Config,
-				storer storage.Storer, v *vaultik.Vaultik, shutdowner fx.Shutdowner) *RestoreApp {
-				return &RestoreApp{
-					Globals:    g,
-					Config:     cfg,
-					Storage:    storer,
-					Vaultik:    v,
-					Shutdowner: shutdowner,
-				}
-			},
-		)),
-	}
-}
-
-// buildRestoreInvokes returns the fx.Options that wire up the restore lifecycle
-func buildRestoreInvokes(snapshotID string, opts *RestoreOptions) []fx.Option {
-	return []fx.Option{
-		fx.Invoke(func(app *RestoreApp, lc fx.Lifecycle) {
-			lc.Append(fx.Hook{
-				OnStart: func(_ context.Context) error {
-					// Start the restore operation in a goroutine
-					go func() {
-						// Run the restore operation
-						restoreOpts := &vaultik.RestoreOptions{
-							SnapshotID: snapshotID,
-							TargetDir:  opts.TargetDir,
-							Paths:      opts.Paths,
-							Verify:     opts.Verify,
-							SkipErrors: GetRootFlags().SkipErrors,
-						}
-
-						err := app.Vaultik.Restore(restoreOpts)
-						if err != nil {
-							if !errors.Is(err, context.Canceled) {
-								log.Error("Restore operation failed", "error", err)
-								ReportErrorf("Restore failed: %v", err)
-								os.Exit(1)
-							}
-						}
-
-						// Shutdown the app when restore completes
-						err = app.Shutdowner.Shutdown()
-						if err != nil {
-							log.Error("Failed to shutdown", "error", err)
-						}
-					}()
-
-					return nil
-				},
-				OnStop: func(_ context.Context) error {
-					log.Debug("Stopping restore operation")
-					app.Vaultik.Cancel()
-
-					return nil
-				},
-			})
-		}),
-	}
-}

internal/storage/file.go

@@ -46,18 +46,31 @@ func (f *FileStorer) SetFilesystem(fs afero.Fs) {
 // storage base path.
 const storageDirPerm = 0o755
 
-// tempSuffix marks a partially written object. writeAtomic streams into a
-// temp file carrying this suffix and only renames it onto the real key once
-// the whole object is on disk, so an interrupted write can never leave a
-// truncated object at the key a later run would Stat and trust as a complete
-// blob. List and ListStream skip these files, so a leftover from an
-// interrupted write is never listed or trusted as a blob; it is otherwise
-// harmless and is overwritten when the same key is written again.
-const tempSuffix = ".partial"
-
 // Put stores data at the specified key.
 func (f *FileStorer) Put(_ context.Context, key string, data io.Reader) error {
-	return f.writeAtomic(key, data, nil)
+	path := f.fullPath(key)
+
+	// Create parent directories
+	dir := filepath.Dir(path)
+
+	err := f.fs.MkdirAll(dir, storageDirPerm)
+	if err != nil {
+		return fmt.Errorf("creating directories: %w", err)
+	}
+
+	file, err := f.fs.Create(path)
+	if err != nil {
+		return fmt.Errorf("creating file: %w", err)
+	}
+
+	defer func() { _ = file.Close() }()
+
+	_, err = io.Copy(file, data)
+	if err != nil {
+		return fmt.Errorf("writing file: %w", err)
+	}
+
+	return nil
 }
 
 // PutWithProgress stores data with progress reporting.
@@ -65,7 +78,35 @@ func (f *FileStorer) PutWithProgress(
 	_ context.Context, key string, data io.Reader,
 	_ int64, progress ProgressCallback,
 ) error {
-	return f.writeAtomic(key, data, progress)
+	path := f.fullPath(key)
+
+	// Create parent directories
+	dir := filepath.Dir(path)
+
+	err := f.fs.MkdirAll(dir, storageDirPerm)
+	if err != nil {
+		return fmt.Errorf("creating directories: %w", err)
+	}
+
+	file, err := f.fs.Create(path)
+	if err != nil {
+		return fmt.Errorf("creating file: %w", err)
+	}
+
+	defer func() { _ = file.Close() }()
+
+	// Wrap with progress tracking
+	pw := &progressWriter{
+		writer:   file,
+		callback: progress,
+	}
+
+	_, err = io.Copy(pw, data)
+	if err != nil {
+		return fmt.Errorf("writing file: %w", err)
+	}
+
+	return nil
 }
 
 // Get retrieves data from the specified key.
@@ -147,7 +188,7 @@ func (f *FileStorer) List(ctx context.Context, prefix string) ([]string, error)
 		default:
 		}
 
-		if !info.IsDir() && !strings.HasSuffix(info.Name(), tempSuffix) {
+		if !info.IsDir() {
 			// Convert back to key (relative path from basePath)
 			relPath, err := filepath.Rel(f.basePath, path)
 			if err != nil {
@@ -204,7 +245,7 @@ func (f *FileStorer) ListStream(ctx context.Context, prefix string) <-chan Objec
 				return nil //nolint:nilerr // continue walking despite errors
 			}
 
-			if !info.IsDir() && !strings.HasSuffix(info.Name(), tempSuffix) {
+			if !info.IsDir() {
 				relPath, err := filepath.Rel(f.basePath, path)
 				if err != nil {
 					ch <- ObjectInfo{Err: fmt.Errorf("computing relative path: %w", err)}
@@ -234,72 +275,6 @@ func (f *FileStorer) Info() Info {
 	}
 }
 
-// writeAtomic streams data into a temp file in the destination directory,
-// fsyncs it, and renames it onto the final key. The key therefore appears
-// only once the whole object has been durably written; a failure part-way
-// leaves a temp file (removed here on the failing path) rather than a
-// truncated object at the key.
-func (f *FileStorer) writeAtomic(
-	key string, data io.Reader, progress ProgressCallback,
-) error {
-	path := f.fullPath(key)
-	dir := filepath.Dir(path)
-
-	err := f.fs.MkdirAll(dir, storageDirPerm)
-	if err != nil {
-		return fmt.Errorf("creating directories: %w", err)
-	}
-
-	tmp, err := afero.TempFile(f.fs, dir, filepath.Base(path)+"-*"+tempSuffix)
-	if err != nil {
-		return fmt.Errorf("creating temp file: %w", err)
-	}
-
-	tmpPath := tmp.Name()
-
-	// Remove the temp file unless the rename below claims it. On the success
-	// path renamed is true, so the deferred Close and Remove are harmless
-	// no-ops on a name that no longer exists.
-	renamed := false
-
-	defer func() {
-		_ = tmp.Close()
-
-		if !renamed {
-			_ = f.fs.Remove(tmpPath)
-		}
-	}()
-
-	var w io.Writer = tmp
-	if progress != nil {
-		w = &progressWriter{writer: tmp, callback: progress}
-	}
-
-	_, err = io.Copy(w, data)
-	if err != nil {
-		return fmt.Errorf("writing file: %w", err)
-	}
-
-	err = tmp.Sync()
-	if err != nil {
-		return fmt.Errorf("syncing temp file: %w", err)
-	}
-
-	err = tmp.Close()
-	if err != nil {
-		return fmt.Errorf("closing temp file: %w", err)
-	}
-
-	err = f.fs.Rename(tmpPath, path)
-	if err != nil {
-		return fmt.Errorf("renaming temp file: %w", err)
-	}
-
-	renamed = true
-
-	return nil
-}
-
 // 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_atomic_test.go

@@ -1,119 +0,0 @@
-package storage_test
-
-import (
-	"context"
-	"errors"
-	"os"
-	"path/filepath"
-	"strings"
-	"testing"
-
-	"sneak.berlin/go/vaultik/internal/storage"
-)
-
-// errStreamInterrupted stands in for an upload cut off mid-stream.
-var errStreamInterrupted = errors.New("connection reset mid-upload")
-
-// failingReader yields its data once, then fails.
-type failingReader struct {
-	data []byte
-	done bool
-}
-
-func (r *failingReader) Read(p []byte) (int, error) {
-	if r.done {
-		return 0, errStreamInterrupted
-	}
-
-	n := copy(p, r.data)
-	r.done = true
-
-	return n, nil
-}
-
-// TestFileStorer_InterruptedWriteLeavesNoTrustedObject checks that a write
-// cut off mid-stream leaves nothing at the destination key, so a later run
-// cannot Stat a truncated object and trust it as a complete blob.
-func TestFileStorer_InterruptedWriteLeavesNoTrustedObject(t *testing.T) {
-	t.Parallel()
-
-	f, err := storage.NewFileStorer(t.TempDir())
-	if err != nil {
-		t.Fatalf("NewFileStorer: %v", err)
-	}
-
-	ctx := context.Background()
-	key := "blobs/aa/bb/aabbccddeeff"
-
-	err = f.PutWithProgress(ctx, key, &failingReader{data: []byte("partial")}, 4096, nil)
-	if err == nil {
-		t.Fatal("expected the interrupted write to fail, got nil")
-	}
-
-	_, err = f.Stat(ctx, key)
-	if !errors.Is(err, storage.ErrNotFound) {
-		t.Fatalf("expected key absent after interrupted write, got Stat err %v", err)
-	}
-
-	keys, err := f.List(ctx, "blobs/")
-	if err != nil {
-		t.Fatalf("List: %v", err)
-	}
-
-	if len(keys) != 0 {
-		t.Fatalf("expected no keys listed after interrupted write, got %v", keys)
-	}
-}
-
-// TestFileStorer_ListSkipsPartialFiles checks that a leftover temp file (the
-// storage layer names them with a ".partial" suffix) is never surfaced as a
-// key by List or ListStream.
-func TestFileStorer_ListSkipsPartialFiles(t *testing.T) {
-	t.Parallel()
-
-	base := t.TempDir()
-
-	f, err := storage.NewFileStorer(base)
-	if err != nil {
-		t.Fatalf("NewFileStorer: %v", err)
-	}
-
-	ctx := context.Background()
-	realKey := "blobs/aa/bb/aabbccddeeff"
-
-	err = f.Put(ctx, realKey, strings.NewReader("blob-bytes"))
-	if err != nil {
-		t.Fatalf("Put: %v", err)
-	}
-
-	// A stray temp file, as an interrupted write would leave behind.
-	leftover := filepath.Join(base, "blobs/aa/bb/aabbccddeeff-123456.partial")
-
-	err = os.WriteFile(leftover, []byte("half"), 0o600)
-	if err != nil {
-		t.Fatalf("writing leftover temp file: %v", err)
-	}
-
-	keys, err := f.List(ctx, "blobs/")
-	if err != nil {
-		t.Fatalf("List: %v", err)
-	}
-
-	if len(keys) != 1 || keys[0] != realKey {
-		t.Fatalf("List should return only the real key, got %v", keys)
-	}
-
-	var streamed []string
-
-	for obj := range f.ListStream(ctx, "blobs/") {
-		if obj.Err != nil {
-			t.Fatalf("ListStream: %v", obj.Err)
-		}
-
-		streamed = append(streamed, obj.Key)
-	}
-
-	if len(streamed) != 1 || streamed[0] != realKey {
-		t.Fatalf("ListStream should return only the real key, got %v", streamed)
-	}
-}

script/cibuild

@@ -56,8 +56,23 @@ main() {
     docker build --output=type=cacheonly \
         --build-arg CHECK_EPOCH="$epoch" -f Dockerfile.lint .
 
+    # Version, commit and build date are computed here on the host, the
+    # same way script/docker does, and passed into the product build so
+    # the CI-built image reports its real source. The build context
+    # excludes .git (see .dockerignore), so the build cannot derive them
+    # itself; without these it would stamp the Dockerfile's dev/unknown
+    # fallbacks. VERSION comes from script/version, the source of truth
+    # shared with the Makefile.
+    version="$("$ROOT/script/version")"
+    commit="$(git rev-parse HEAD 2>/dev/null || echo unknown)"
+    commit_date="$(git show -s --format=%cs HEAD 2>/dev/null || echo unknown)"
+
     epoch="$(date +%s%N)$$"
-    docker build --build-arg CHECK_EPOCH="$epoch" .
+    docker build --build-arg CHECK_EPOCH="$epoch" \
+        --build-arg VERSION="$version" \
+        --build-arg COMMIT="$commit" \
+        --build-arg COMMIT_DATE="$commit_date" \
+        .
 }
 
 main "$@"

script/docker

@@ -24,7 +24,24 @@ main() {
     # whether the tree is clean. The Dockerfile now refuses to build
     # without a non-empty value, so this is required, not optional.
     epoch="$(date +%s%N)$$"
+
+    # Version, commit and build date are computed here on the host,
+    # where .git exists, and passed into the build. The build context
+    # excludes .git (see .dockerignore), so the container cannot derive
+    # them itself -- it used to try and always got "unknown", giving
+    # every image a "commit: unknown" it could not be traced from.
+    # VERSION comes from script/version, the source of truth shared with
+    # the Makefile, so a Docker build reports the same string (tag,
+    # dev-<sha>, or a -dirty variant) that a local build of the same
+    # tree would.
+    version="$("$SCRIPT_DIR/version")"
+    commit="$(git rev-parse HEAD 2>/dev/null || echo unknown)"
+    commit_date="$(git show -s --format=%cs HEAD 2>/dev/null || echo unknown)"
+
     docker build --build-arg CHECK_EPOCH="$epoch" \
+        --build-arg VERSION="$version" \
+        --build-arg COMMIT="$commit" \
+        --build-arg COMMIT_DATE="$commit_date" \
         -t "$("$SCRIPT_DIR/projectname")" .
 }