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

CLAUDE.md

@@ -122,8 +122,6 @@ DATABASE_URL=postgres://... go test -tags integration ./internal/master/store/
 - **Swarm updates need manager-node API access** for the agent doing the update.
 - **The image's default entrypoint is `updater-agent`.** The master overrides it with
   `updater-master`.
-- **The example stack runs the master as nobody (`user: "65534:65534"`).** Never add `USER`
-  to the Dockerfile: the agent uses the same image and needs root for the Docker socket.
 - **The webhook waits via a broker signal plus a store re-read, with a fallback poll**
   (the broker drops signals for slow subscribers). Marking and starting jobs runs on
   `context.WithoutCancel`, so a client that disconnects cannot leave a queued job no agent

README.md

@@ -28,16 +28,14 @@ a time per service, and one job at a time per agent.
 Use [`deploy/master.stack.yml`](deploy/master.stack.yml) as a starting point (Swarm stack;
 needs Postgres and an OIDC provider). The master listens for the UI on `PORT` (default
 `8080`, put it behind your reverse proxy) and for agents on `AGENT_PORT` (default `8090`,
-pinned TLS, reached directly on the internal network). The example runs the master as
-`nobody` (`65534`); it needs no root. The agent runs as root because access to the Docker
-socket is root on the host anyway.
+pinned TLS, reached directly on the internal network).
 
 | Variable | Required | Default | Purpose |
 |---|---|---|---|
 | `UPDATER_API_KEY` | no | — | Bearer token for `POST /update`. Without it the webhook answers `503` and the master logs `webhook_disabled`. |
 | `UPDATE_TIMEOUT` | no | `5m` | How long one `POST /update` waits for its auto jobs (Go duration). |
 | `POLL_INTERVAL` | no | `6h` | Time between registry polling cycles (Go duration, must be positive). The first cycle runs one minute after start. |
-| `DOCKER_CONFIG` | no | `~/.docker` | Directory with a `config.json` holding registry credentials for polling, readable by the master's user. Only inline `auths` entries work; see [Registry polling](#registry-polling). |
+| `DOCKER_CONFIG` | no | `~/.docker` | Directory with a `config.json` holding registry credentials for polling. Only inline `auths` entries work; see [Registry polling](#registry-polling). |
 
 The master's other settings (`DATABASE_URL`, `PUBLIC_URL`, `AGENT_URL`, `OIDC_*`,
 `ALLOWED_GROUP`, `AGENT_IMAGE`, `PORT`, `AGENT_PORT`, `LOG_LEVEL`) are shown in
@@ -148,14 +146,11 @@ multi-arch image the digest is the index digest, the same one `docker inspect` s
   tags continue. A later success clears it.
 - **Credentials.** The master reads `$DOCKER_CONFIG/config.json` (a file written by
   `docker login`), mounted read-only into the container; without it registries are accessed
-  anonymously. The directory and file must be readable by the master's user (`65534` in the
-  example stack) without being world-readable: `chown -R 65534:65534` the directory and keep
-  `0700`/`0600`. Only inline `auths` entries are supported. A `credsStore` or `credHelpers`
+  anonymously. Only inline `auths` entries are supported. A `credsStore` or `credHelpers`
   entry makes every lookup fail with `error getting credentials ... executable file not found
   in $PATH`, because the container has no credential helper binaries. The master logs
-  `registry_credentials` at startup with the directory, `config_json_found` and
-  `config_json_readable`, never the contents. If the file exists but cannot be opened it also
-  logs a `registry_credentials_unreadable` warning with the error.
+  `registry_credentials` at startup with the directory and whether `config.json` exists,
+  never its contents.
 - **Requests go wherever the image name points.** The master sends the lookup to the
   registry host in the image name, including a `GET /v2/` ping that follows redirects.
   Anyone who can start containers on a managed host can therefore make the master send

cmd/master/main.go

@@ -48,29 +48,19 @@ const pollFirstDelay = time.Minute
 const pollWorkers = 4
 
 // registryCredentialsDir returns the directory the registry client reads
-// credentials from (DOCKER_CONFIG, else ~/.docker), whether a config.json is
-// in it, and the error from opening it when it exists but cannot be read (for
-// example because the master runs as another user than the file owner). The
-// file is opened and closed, never read; only the path is logged.
-func registryCredentialsDir() (dir string, found bool, readErr error) {
+// credentials from (DOCKER_CONFIG, else ~/.docker) and whether a config.json
+// is in it. Only the path is logged, never the file.
+func registryCredentialsDir() (dir string, found bool) {
 	dir = os.Getenv("DOCKER_CONFIG")
 	if dir == "" {
 		home, err := os.UserHomeDir()
 		if err != nil {
-			return "", false, nil
+			return "", false
 		}
 		dir = filepath.Join(home, ".docker")
 	}
-	path := filepath.Join(dir, "config.json")
-	if _, err := os.Stat(path); err != nil {
-		return dir, false, nil
-	}
-	f, err := os.Open(path)
-	if err != nil {
-		return dir, true, err
-	}
-	_ = f.Close()
-	return dir, true, nil
+	_, err := os.Stat(filepath.Join(dir, "config.json"))
+	return dir, err == nil
 }
 
 func run() error {
@@ -164,12 +154,8 @@ func run() error {
 		BaseContext: baseContext,
 	}
 
-	credDir, credFound, credReadErr := registryCredentialsDir()
-	logger.Info("registry_credentials", "docker_config", credDir, "config_json_found", credFound,
-		"config_json_readable", credFound && credReadErr == nil)
-	if credReadErr != nil {
-		logger.Warn("registry_credentials_unreadable", "docker_config", credDir, "error", credReadErr)
-	}
+	credDir, credFound := registryCredentialsDir()
+	logger.Info("registry_credentials", "docker_config", credDir, "config_json_found", credFound)
 	pollCtx, stopPolling := context.WithCancel(ctx)
 	defer stopPolling()
 	registryPoller := poller.New(st, jobService, registry.New("package-updater-master/"+version, logger), broker, poller.Config{

cmd/master/main_test.go

@@ -1,42 +0,0 @@
-package main
-
-import (
-	"os"
-	"path/filepath"
-	"testing"
-
-	"github.com/stretchr/testify/assert"
-	"github.com/stretchr/testify/require"
-)
-
-func TestRegistryCredentialsDir(t *testing.T) {
-	t.Run("missing file", func(t *testing.T) {
-		dir := t.TempDir()
-		t.Setenv("DOCKER_CONFIG", dir)
-		got, found, readErr := registryCredentialsDir()
-		assert.Equal(t, dir, got)
-		assert.False(t, found)
-		assert.NoError(t, readErr)
-	})
-
-	t.Run("readable file", func(t *testing.T) {
-		dir := t.TempDir()
-		require.NoError(t, os.WriteFile(filepath.Join(dir, "config.json"), []byte("{}"), 0o600))
-		t.Setenv("DOCKER_CONFIG", dir)
-		_, found, readErr := registryCredentialsDir()
-		assert.True(t, found)
-		assert.NoError(t, readErr)
-	})
-
-	t.Run("unreadable file", func(t *testing.T) {
-		if os.Geteuid() == 0 {
-			t.Skip("root can read any file")
-		}
-		dir := t.TempDir()
-		require.NoError(t, os.WriteFile(filepath.Join(dir, "config.json"), []byte("{}"), 0o000))
-		t.Setenv("DOCKER_CONFIG", dir)
-		_, found, readErr := registryCredentialsDir()
-		assert.True(t, found)
-		assert.Error(t, readErr)
-	})
-}

deploy/master.stack.yml

@@ -12,17 +12,12 @@
 #      The reverse proxy must allow a read timeout longer than UPDATE_TIMEOUT (default 5m).
 #   5. Optional, for registry polling of private images: put a config.json written by
 #      `docker login` (inline "auths" only; no credsStore) in /path/to/docker-config and
-#      uncomment DOCKER_CONFIG and the volumes entry below. The master runs as 65534:65534, so
-#      the directory and config.json must be readable by that user while staying private:
-#      `chown -R 65534:65534 /path/to/docker-config` (keep 0700/0600), or set `user:` below
-#      to the owner's uid:gid. Do not make config.json world-readable; it holds registry
-#      passwords. The directory must exist on every manager node (the master is placed on a
-#      manager), or Swarm rejects the task. Without it registries are accessed anonymously.
+#      uncomment DOCKER_CONFIG and the volumes entry below. The directory must exist on every
+#      manager node (the master is placed on a manager), or Swarm rejects the task. Without
+#      it registries are accessed anonymously.
 services:
   master:
     image: gitea.shcizo.se/shcizo/package-updater:latest
-    # Runs as nobody: the master needs no root (the agent does, for the Docker socket).
-    user: "65534:65534"
     entrypoint: ["/bin/sh", "-c", "DATABASE_URL=$$(cat /run/secrets/pu_database_url) OIDC_CLIENT_SECRET=$$(cat /run/secrets/pu_oidc_client_secret) UPDATER_API_KEY=$$(cat /run/secrets/pu_updater_api_key) exec /usr/local/bin/updater-master"]
     environment:
       PUBLIC_URL: https://updater.example.com