fix(agent): set the override owner on the temp file before the rename (#24)

CLAUDE.md

@@ -98,9 +98,6 @@ DATABASE_URL=postgres://... go test -tags integration ./internal/master/store/
   without the other has caused a fix commit already.
 - **`<summary>` C# convention from global CLAUDE.md does not apply here** — this
   is Go. Use idiomatic GoDoc (`// FuncName does X.`).
-- **The override file gets the owner of the existing override, else of the stack's first
-  compose file.** The agent runs as root and renames a new file into place; it chowns it
-  afterwards. A failure is a `warning:` line in the job output, never a failed job.
 - **Compose loads only one override file.** Of `compose.override.yml`,
   `compose.override.yaml`, `docker-compose.override.yml`, `docker-compose.override.yaml`
   only the first that exists is read. Hence the refusal described above.
@@ -108,6 +105,12 @@ DATABASE_URL=postgres://... go test -tags integration ./internal/master/store/
   agent's own jobs always pass it explicitly.
 - **Override entries are never pruned.** A service deleted from the stack file keeps its
   `image:` line in `compose.override.yaml`.
+- **The override file gets the owner of the existing override, else of the stack's first
+  compose file.** The exception is a root-owned existing override (written before this
+  fix): then the compose file's owner is used, so it stops being root-owned. The agent runs
+  as root, so `WriteOverride` chowns the open temp file before the rename (never the path
+  afterwards: a symlink could be swapped in). A failure is a `warning:` line in the job
+  output, never a failed job.
 - **There is no `STACKS_ROOT`.** Stack directories must be mounted read-write at the host
   path (`/path:/path`), and `SELF_ID` must resolve to the agent's own container. On Docker
   Desktop/OrbStack bind sources are translated, so Compose jobs fail there.

internal/agent/updater/compose.go

@@ -2,15 +2,11 @@ package updater
 
 import (
 	"context"
-	"errors"
 	"fmt"
 	"io"
-	"io/fs"
 	"os"
 	"os/exec"
-	"path/filepath"
 	"strings"
-	"syscall"
 	"time"
 
 	"github.com/docker/docker/api/types/container"
@@ -31,26 +27,6 @@ const (
 // job's error message; the full output is in the job log.
 const errorOutputTail = 2 << 10
 
-// chown is os.Chown; tests replace it.
-var chown = os.Chown
-
-// stackOwner returns the uid and gid the override file should have: those of
-// the existing override if there is one, else those of the stack's compose file.
-func stackOwner(overridePath, composeFile string) (uid, gid int, err error) {
-	fi, err := os.Stat(overridePath)
-	if errors.Is(err, fs.ErrNotExist) {
-		fi, err = os.Stat(composeFile)
-	}
-	if err != nil {
-		return 0, 0, err
-	}
-	st, ok := fi.Sys().(*syscall.Stat_t)
-	if !ok {
-		return 0, 0, errors.New("file owner is not available on this platform")
-	}
-	return int(st.Uid), int(st.Gid), nil
-}
-
 // tailWriter adapts a tailBuffer to io.Writer.
 type tailWriter struct{ b *tailBuffer }
 
@@ -176,18 +152,14 @@ func (e *ComposeExecutor) Execute(ctx context.Context, job protocol.JobStart, ou
 	}
 	fmt.Fprintln(out, resolveNote(job.Ref, pinned))
 
-	// The agent runs as root and WriteOverride renames a new file into place,
-	// so the override would end up root-owned. Hand it back to the stack's
-	// owner. A failure here is only a warning: the update itself is fine.
-	overridePath := filepath.Join(dir, OverrideName)
-	uid, gid, ownerErr := stackOwner(overridePath, files[0])
-	if _, err := WriteOverride(dir, service, pinned); err != nil {
+	// Giving the override the stack's owner is best effort: a failure is only
+	// a warning, the update itself is fine.
+	_, ownerErr, err := WriteOverride(dir, service, pinned, files[0])
+	if err != nil {
 		return "", err
 	}
 	if ownerErr != nil {
-		fmt.Fprintf(out, "warning: could not read the owner of %s or %s to give it to %s: %v\n", overridePath, files[0], overridePath, ownerErr)
-	} else if err := chown(overridePath, uid, gid); err != nil {
-		fmt.Fprintf(out, "warning: could not give %s the owner %d:%d: %v\n", overridePath, uid, gid, err)
+		fmt.Fprintf(out, "warning: could not give the override the stack's owner: %v\n", ownerErr)
 	}
 
 	base := composeBase(project, workingDir, files, envs)

internal/agent/updater/compose_test.go

@@ -7,7 +7,6 @@ import (
 	"os"
 	"path/filepath"
 	"strings"
-	"syscall"
 	"testing"
 
 	"github.com/docker/docker/api/types/container"
@@ -65,53 +64,12 @@ func (r *recorder) run(_ context.Context, dir string, out io.Writer, args ...str
 	return nil
 }
 
-// stubChown replaces chown for the test. Tests that use it must not run in parallel.
-func stubChown(t *testing.T, f func(path string, uid, gid int) error) {
-	t.Helper()
-	orig := chown
-	chown = f
-	t.Cleanup(func() { chown = orig })
-}
-
-func TestStackOwner(t *testing.T) {
-	dir := t.TempDir()
-	override := filepath.Join(dir, OverrideName)
-	compose := filepath.Join(dir, "compose.yaml")
-
-	t.Run("falls back to the compose file when there is no override", func(t *testing.T) {
-		require.NoError(t, os.WriteFile(compose, nil, 0o644))
-		uid, gid, err := stackOwner(override, compose)
-		require.NoError(t, err)
-		assert.Equal(t, os.Getuid(), uid)
-		assert.Equal(t, os.Getgid(), gid)
-	})
-	t.Run("prefers the existing override", func(t *testing.T) {
-		require.NoError(t, os.WriteFile(override, nil, 0o644))
-		require.NoError(t, os.Remove(compose))
-		uid, _, err := stackOwner(override, compose)
-		require.NoError(t, err, "the compose file is not consulted")
-		assert.Equal(t, os.Getuid(), uid)
-	})
-	t.Run("fails when neither file exists", func(t *testing.T) {
-		require.NoError(t, os.Remove(override))
-		_, _, err := stackOwner(override, compose)
-		assert.Error(t, err)
-	})
-}
-
-func TestChown_RealToOwnIDs(t *testing.T) {
-	f := filepath.Join(t.TempDir(), "f")
-	require.NoError(t, os.WriteFile(f, nil, 0o644))
-	uid, gid, err := stackOwner(f, f)
-	require.NoError(t, err)
-	assert.NoError(t, chown(f, uid, gid))
-}
-
 func TestComposeExecutor(t *testing.T) {
 	const d = "sha256:d1d1d1d1d1d1d1d1d1d1d1d1d1d1d1d1d1d1d1d1d1d1d1d1d1d1d1d1d1d1d1d1"
 	root, _ := filepath.EvalSymlinks(t.TempDir())
 	stack := filepath.Join(root, "slusk")
 	require.NoError(t, os.MkdirAll(stack, 0o755))
+	composeFile := stackFile(t, stack)
 	job := protocol.JobStart{Kind: protocol.KindCompose, ComposeProject: "slusk", ComposeService: "web", Ref: "gitea.shcizo.se/shcizo/slusk:1.4"}
 	pinned := job.Ref + "@" + d
 
@@ -150,41 +108,17 @@ func TestComposeExecutor(t *testing.T) {
 		_, doc := readOverride(t, stack)
 		assert.Equal(t, pinned, serviceImage(doc, "web"))
 		assert.Contains(t, out.String(), "resolved "+pinned)
-	})
-	t.Run("the override is chowned to the owner of the compose file", func(t *testing.T) {
-		t.Cleanup(cleanOverride)
-		composeFile := filepath.Join(stack, "compose.yaml")
-		require.NoError(t, os.WriteFile(composeFile, []byte("services: {}\n"), 0o644))
-		t.Cleanup(func() { os.Remove(composeFile) })
-		fi, err := os.Stat(composeFile)
-		require.NoError(t, err)
-		st := fi.Sys().(*syscall.Stat_t)
-		var gotPath string
-		var gotUID, gotGID int
-		stubChown(t, func(path string, uid, gid int) error {
-			gotPath, gotUID, gotGID = path, uid, gid
-			return nil
-		})
-		var out strings.Builder
-		_, err = setup(fakeCompose{rw, []container.Summary{ct}}, &fakeDist{digest: d}, &recorder{}).Execute(context.Background(), job, &out)
-		require.NoError(t, err)
-		assert.Equal(t, overridePath, gotPath)
-		assert.Equal(t, int(st.Uid), gotUID)
-		assert.Equal(t, int(st.Gid), gotGID)
 		assert.NotContains(t, out.String(), "warning")
 	})
-	t.Run("a chown failure is a warning and the job still succeeds", func(t *testing.T) {
+	t.Run("an unreadable owner is a warning and the job still succeeds", func(t *testing.T) {
 		t.Cleanup(cleanOverride)
-		composeFile := filepath.Join(stack, "compose.yaml")
-		require.NoError(t, os.WriteFile(composeFile, []byte("services: {}\n"), 0o644))
-		t.Cleanup(func() { os.Remove(composeFile) })
-		stubChown(t, func(string, int, int) error { return errors.New("operation not permitted") })
+		require.NoError(t, os.Rename(composeFile, composeFile+".bak"))
+		t.Cleanup(func() { os.Rename(composeFile+".bak", composeFile) })
 		var out strings.Builder
 		got, err := setup(fakeCompose{rw, []container.Summary{ct}}, &fakeDist{digest: d}, &recorder{}).Execute(context.Background(), job, &out)
 		require.NoError(t, err)
 		assert.Equal(t, pinned, got)
-		assert.Contains(t, out.String(), "warning: could not give "+overridePath+" the owner ")
-		assert.Contains(t, out.String(), "operation not permitted")
+		assert.Contains(t, out.String(), "warning: could not give the override the stack's owner: read owner: ")
 		_, doc := readOverride(t, stack)
 		assert.Equal(t, pinned, serviceImage(doc, "web"))
 	})

internal/agent/updater/override.go

@@ -8,6 +8,7 @@ import (
 	"os"
 	"path/filepath"
 	"strings"
+	"syscall"
 
 	"github.com/docker/docker/api/types/container"
 	"github.com/docker/docker/api/types/mount"
@@ -34,15 +35,68 @@ var overrideNames = []string{
 // keeping every other entry in the file, and returns the file's path. It
 // refuses when the file exists without the header, or when another
 // auto-loaded override file exists in dir. The write is atomic.
-func WriteOverride(dir, service, ref string) (string, error) {
+//
+// composeFile is the stack's first compose file. The new file gets the owner
+// of the existing override, or of composeFile when there is none or the
+// existing one is owned by root (see pickOwner). The agent runs as root and the
+// rename creates a new file, so without this the stack's owner would lose
+// control of the file. ownerErr reports that the owner could not be read or
+// set; the override is still written. err means it was not written.
+func WriteOverride(dir, service, ref, composeFile string) (path string, ownerErr error, err error) {
+	overridePath := filepath.Join(dir, OverrideName)
+	return writeOverride(dir, service, ref, func() (fileOwner, error) {
+		return resolveOwner(overridePath, composeFile)
+	})
+}
+
+// fileOwner is the uid and gid of a file.
+type fileOwner struct{ uid, gid int }
+
+// readOwner returns the owner of the file at path.
+func readOwner(path string) (fileOwner, error) {
+	fi, err := os.Stat(path)
+	if err != nil {
+		return fileOwner{}, fmt.Errorf("read owner: %w", err)
+	}
+	st, ok := fi.Sys().(*syscall.Stat_t)
+	if !ok {
+		return fileOwner{}, fmt.Errorf("read owner of %s: not available on this platform", path)
+	}
+	return fileOwner{int(st.Uid), int(st.Gid)}, nil
+}
+
+// pickOwner chooses the owner of a new override: the existing override's
+// (nil when there is none), unless that is root, then the compose file's.
+// Overrides written before the agent set owners are root-owned and would
+// otherwise stay so. compose is only called when needed.
+func pickOwner(override *fileOwner, compose func() (fileOwner, error)) (fileOwner, error) {
+	if override != nil && override.uid != 0 {
+		return *override, nil
+	}
+	return compose()
+}
+
+// resolveOwner applies pickOwner to the files on disk.
+func resolveOwner(overridePath, composeFile string) (fileOwner, error) {
+	var existing *fileOwner
+	if o, err := readOwner(overridePath); err == nil {
+		existing = &o
+	} else if !errors.Is(err, os.ErrNotExist) {
+		return fileOwner{}, err
+	}
+	return pickOwner(existing, func() (fileOwner, error) { return readOwner(composeFile) })
+}
+
+// writeOverride is WriteOverride with the owner lookup injected, for tests.
+func writeOverride(dir, service, ref string, owner func() (fileOwner, error)) (string, error, error) {
 	for _, name := range overrideNames {
 		if name == OverrideName {
 			continue
 		}
 		if _, err := os.Lstat(filepath.Join(dir, name)); err == nil {
-			return "", fmt.Errorf("refused: %s exists; the agent only manages %s and never edits operator files", name, OverrideName)
+			return "", nil, fmt.Errorf("refused: %s exists; the agent only manages %s and never edits operator files", name, OverrideName)
 		} else if !errors.Is(err, os.ErrNotExist) {
-			return "", fmt.Errorf("check %s: %w", name, err)
+			return "", nil, fmt.Errorf("check %s: %w", name, err)
 		}
 	}
 	path := filepath.Join(dir, OverrideName)
@@ -51,12 +105,12 @@ func WriteOverride(dir, service, ref string) (string, error) {
 	switch {
 	case errors.Is(err, os.ErrNotExist):
 	case err != nil:
-		return "", fmt.Errorf("read override: %w", err)
+		return "", nil, fmt.Errorf("read override: %w", err)
 	case !bytes.HasPrefix(raw, []byte(overrideHeader)):
-		return "", fmt.Errorf("refused: %s exists and was not written by package-updater", path)
+		return "", nil, fmt.Errorf("refused: %s exists and was not written by package-updater", path)
 	default:
 		if err := yaml.Unmarshal(raw, &doc); err != nil {
-			return "", fmt.Errorf("parse override: %w", err)
+			return "", nil, fmt.Errorf("parse override: %w", err)
 		}
 		if doc == nil {
 			doc = map[string]any{}
@@ -75,30 +129,38 @@ func WriteOverride(dir, service, ref string) (string, error) {
 	doc["services"] = services
 	body, err := yaml.Marshal(doc)
 	if err != nil {
-		return "", fmt.Errorf("encode override: %w", err)
+		return "", nil, fmt.Errorf("encode override: %w", err)
 	}
 	// Temp file in the same directory + rename: a crash never leaves a
 	// half-written override that compose would then load.
 	tmp, err := os.CreateTemp(dir, "."+OverrideName+".*")
 	if err != nil {
-		return "", fmt.Errorf("write override: %w", err)
+		return "", nil, fmt.Errorf("write override: %w", err)
 	}
 	defer os.Remove(tmp.Name()) // no-op after a successful rename
 	if _, err := tmp.WriteString(overrideHeader + string(body)); err != nil {
 		tmp.Close()
-		return "", fmt.Errorf("write override: %w", err)
+		return "", nil, fmt.Errorf("write override: %w", err)
 	}
 	if err := tmp.Chmod(0o644); err != nil {
 		tmp.Close()
-		return "", fmt.Errorf("write override: %w", err)
+		return "", nil, fmt.Errorf("write override: %w", err)
+	}
+	// Chown the open file, not the path after the rename: a path could have
+	// been swapped for a symlink by someone with write access to the stack.
+	var ownerErr error
+	if o, err := owner(); err != nil {
+		ownerErr = err
+	} else if err := tmp.Chown(o.uid, o.gid); err != nil {
+		ownerErr = fmt.Errorf("set owner %d:%d: %w", o.uid, o.gid, err)
 	}
 	if err := tmp.Close(); err != nil {
-		return "", fmt.Errorf("write override: %w", err)
+		return "", nil, fmt.Errorf("write override: %w", err)
 	}
 	if err := os.Rename(tmp.Name(), path); err != nil {
-		return "", fmt.Errorf("write override: %w", err)
+		return "", nil, fmt.Errorf("write override: %w", err)
 	}
-	return path, nil
+	return path, ownerErr, nil
 }
 
 // SelfInspector is the subset of the Docker SDK MountRoots needs.

internal/agent/updater/override_test.go

@@ -29,11 +29,96 @@ func serviceImage(doc map[string]any, name string) any {
 	return entry["image"]
 }
 
+// stackFile creates dir/compose.yaml and returns its path.
+func stackFile(t *testing.T, dir string) string {
+	t.Helper()
+	p := filepath.Join(dir, "compose.yaml")
+	require.NoError(t, os.WriteFile(p, []byte("services: {}\n"), 0o644))
+	return p
+}
+
+func TestPickOwner(t *testing.T) {
+	compose := fileOwner{1000, 1000}
+	fromCompose := func() (fileOwner, error) { return compose, nil }
+	failing := func() (fileOwner, error) { return fileOwner{}, errors.New("boom") }
+	tests := []struct {
+		name     string
+		override *fileOwner
+		compose  func() (fileOwner, error)
+		want     fileOwner
+		wantErr  bool
+	}{
+		{"no override uses the compose file", nil, fromCompose, compose, false},
+		{"override owned by a user wins", &fileOwner{1001, 1002}, fromCompose, fileOwner{1001, 1002}, false},
+		{"root-owned override uses the compose file", &fileOwner{0, 0}, fromCompose, compose, false},
+		{"compose file is not read when the override decides", &fileOwner{1001, 1002}, failing, fileOwner{1001, 1002}, false},
+		{"unreadable compose file is an error", nil, failing, fileOwner{}, true},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			got, err := pickOwner(tt.override, tt.compose)
+			assert.Equal(t, tt.wantErr, err != nil)
+			assert.Equal(t, tt.want, got)
+		})
+	}
+}
+
+func TestResolveOwner(t *testing.T) {
+	me := fileOwner{os.Getuid(), os.Getgid()}
+	t.Run("no override uses the compose file", func(t *testing.T) {
+		dir := t.TempDir()
+		got, err := resolveOwner(filepath.Join(dir, OverrideName), stackFile(t, dir))
+		require.NoError(t, err)
+		assert.Equal(t, me, got)
+	})
+	t.Run("existing override is used without the compose file", func(t *testing.T) {
+		dir := t.TempDir()
+		require.NoError(t, os.WriteFile(filepath.Join(dir, OverrideName), nil, 0o644))
+		got, err := resolveOwner(filepath.Join(dir, OverrideName), filepath.Join(dir, "missing.yaml"))
+		require.NoError(t, err)
+		assert.Equal(t, me, got)
+	})
+	t.Run("neither file is an error", func(t *testing.T) {
+		dir := t.TempDir()
+		_, err := resolveOwner(filepath.Join(dir, OverrideName), filepath.Join(dir, "missing.yaml"))
+		assert.Error(t, err)
+	})
+}
+
+func TestWriteOverride_Owner(t *testing.T) {
+	t.Run("success sets no ownerErr", func(t *testing.T) {
+		dir := t.TempDir()
+		_, ownerErr, err := WriteOverride(dir, "web", "a:1@sha256:aa", stackFile(t, dir))
+		require.NoError(t, err)
+		assert.NoError(t, ownerErr)
+	})
+	t.Run("unreadable owner is reported and the file is still written", func(t *testing.T) {
+		dir := t.TempDir()
+		_, ownerErr, err := WriteOverride(dir, "web", "a:1@sha256:aa", filepath.Join(dir, "missing.yaml"))
+		require.NoError(t, err)
+		assert.ErrorContains(t, ownerErr, "read owner")
+		_, doc := readOverride(t, dir)
+		assert.Equal(t, "a:1@sha256:aa", serviceImage(doc, "web"))
+	})
+	t.Run("chown failure is reported and the file is still written", func(t *testing.T) {
+		if os.Getuid() == 0 {
+			t.Skip("root can chown to anyone")
+		}
+		dir := t.TempDir()
+		_, ownerErr, err := writeOverride(dir, "web", "a:1@sha256:aa", func() (fileOwner, error) { return fileOwner{0, 0}, nil })
+		require.NoError(t, err)
+		assert.ErrorContains(t, ownerErr, "set owner 0:0")
+		_, doc := readOverride(t, dir)
+		assert.Equal(t, "a:1@sha256:aa", serviceImage(doc, "web"))
+	})
+}
+
 func TestWriteOverride(t *testing.T) {
 	t.Run("new file", func(t *testing.T) {
 		dir := t.TempDir()
-		path, err := WriteOverride(dir, "web", "a:1@sha256:aa")
+		path, ownerErr, err := WriteOverride(dir, "web", "a:1@sha256:aa", stackFile(t, dir))
 		require.NoError(t, err)
+		assert.NoError(t, ownerErr)
 		assert.Equal(t, filepath.Join(dir, OverrideName), path)
 		raw, doc := readOverride(t, dir)
 		assert.True(t, len(raw) > len(overrideHeader) && raw[:len(overrideHeader)] == overrideHeader)
@@ -42,7 +127,7 @@ func TestWriteOverride(t *testing.T) {
 	t.Run("keeps other services", func(t *testing.T) {
 		dir := t.TempDir()
 		require.NoError(t, os.WriteFile(filepath.Join(dir, OverrideName), []byte(overrideHeader+"services:\n  db:\n    image: db:1\n"), 0o644))
-		_, err := WriteOverride(dir, "web", "a:1@sha256:aa")
+		_, _, err := WriteOverride(dir, "web", "a:1@sha256:aa", stackFile(t, dir))
 		require.NoError(t, err)
 		_, doc := readOverride(t, dir)
 		assert.Equal(t, "db:1", serviceImage(doc, "db"))
@@ -51,7 +136,7 @@ func TestWriteOverride(t *testing.T) {
 	t.Run("replaces own entry", func(t *testing.T) {
 		dir := t.TempDir()
 		require.NoError(t, os.WriteFile(filepath.Join(dir, OverrideName), []byte(overrideHeader+"services:\n  web:\n    image: old\n"), 0o644))
-		_, err := WriteOverride(dir, "web", "a:2@sha256:bb")
+		_, _, err := WriteOverride(dir, "web", "a:2@sha256:bb", stackFile(t, dir))
 		require.NoError(t, err)
 		_, doc := readOverride(t, dir)
 		assert.Equal(t, "a:2@sha256:bb", serviceImage(doc, "web"))
@@ -60,7 +145,7 @@ func TestWriteOverride(t *testing.T) {
 		dir := t.TempDir()
 		const body = "services:\n  web:\n    environment: [A=1]\n"
 		require.NoError(t, os.WriteFile(filepath.Join(dir, OverrideName), []byte(body), 0o644))
-		_, err := WriteOverride(dir, "web", "a:1@sha256:aa")
+		_, _, err := WriteOverride(dir, "web", "a:1@sha256:aa", stackFile(t, dir))
 		assert.ErrorContains(t, err, "refused")
 		got, _ := os.ReadFile(filepath.Join(dir, OverrideName))
 		assert.Equal(t, body, string(got))
@@ -69,7 +154,7 @@ func TestWriteOverride(t *testing.T) {
 		t.Run("refuses next to "+other, func(t *testing.T) {
 			dir := t.TempDir()
 			require.NoError(t, os.WriteFile(filepath.Join(dir, other), []byte("services: {}\n"), 0o644))
-			_, err := WriteOverride(dir, "web", "a:1@sha256:aa")
+			_, _, err := WriteOverride(dir, "web", "a:1@sha256:aa", stackFile(t, dir))
 			assert.ErrorContains(t, err, other)
 			_, statErr := os.Stat(filepath.Join(dir, OverrideName))
 			assert.True(t, errors.Is(statErr, os.ErrNotExist))
@@ -77,12 +162,13 @@ func TestWriteOverride(t *testing.T) {
 	}
 	t.Run("leaves no temp files", func(t *testing.T) {
 		dir := t.TempDir()
-		_, err := WriteOverride(dir, "web", "a:1@sha256:aa")
+		_, _, err := WriteOverride(dir, "web", "a:1@sha256:aa", stackFile(t, dir))
 		require.NoError(t, err)
 		entries, err := os.ReadDir(dir)
 		require.NoError(t, err)
-		require.Len(t, entries, 1)
-		assert.Equal(t, OverrideName, entries[0].Name())
+		require.Len(t, entries, 2)
+		assert.Equal(t, "compose.override.yaml", entries[0].Name())
+		assert.Equal(t, "compose.yaml", entries[1].Name())
 	})
 }