feat(docker): restore failed Compose updates and retain recent releases

README.md

@@ -182,11 +182,42 @@ cron entry with the absolute path of **your** checkout; keep logs in its `logs`
 directory. Do not configure both CI and Compose updates for the same instance.
 The updater refuses an active `epicnext-cms-app` CI-managed container.
 
-Logs: `logs/docker-update.log`. A failure after recreation leaves the candidate
-running for diagnosis and returns nonzero; this Compose updater does not promise
-automatic application or database rollback. Persistent volumes are preserved.
-Before production migrations, retain your normal database backup. The existing
-CI deploy continues to restore its previous container on failed verification.
+Logs: `logs/docker-update.log`. After cutover, a startup, image or HTTP check
+failure automatically recreates the CMS with its previous image and verifies its
+local HTTP release and database health. The command still returns nonzero: a
+rollback is not a successful update. Recovery uses the current Compose configuration
+and `.env`; it restores application code, not configuration edits or database migrations.
+The previous image must carry a valid release label. First installations have no
+previous release: a failed candidate remains available for diagnosis. A failed
+rollback is explicitly logged with a retained `epicnext-cms:rollback-...` recovery tag.
+Public routing must be checked separately after rollback. SIGKILL or host power loss
+cannot run the rollback handler.
+
+After success, the updater keeps the two most recent distinct releases tracked in
+`logs/docker-release-history.log`. Cleanup only removes older recorded CMS image
+tags, without force; images referenced by other containers (including stopped ones)
+are preserved and retried on later updates. Untracked historical images, build cache,
+other services and persistent volumes are not pruned. Retain the history file between
+updates. Before production migrations, retain your normal database backup.
+
+### Shared prebuilt image audit
+
+The current Docker build is installation-specific. A shared registry image needs
+these changes before it can safely replace local builds:
+
+| Configuration | Current source | Required preparation |
+| --- | --- | --- |
+| Avatar imager URL | `src/lib/imager.ts`, direct `NEXT_PUBLIC_IMAGER_URL` access | Supply public runtime configuration; remove the Epicnabbo-specific fallback for other installations. |
+| Badge URL | Admin user badge components, `NEXT_PUBLIC_BADGE_URL` | Pass runtime configuration from the server to client components. |
+| Public application URL | Diagnostics and photo helpers, `NEXT_PUBLIC_APP_URL` fallback | Use server runtime `APP_URL`; audit any generated absolute URLs. |
+| Release identity | `next.config.ts`, `NEXT_PUBLIC_CMS_RELEASE` | Keep baked into the image: one commit identifies the same application binary everywhere. |
+| Environment validation | `src/env.ts` requires database URL, hotel name and production auth secret | Build with isolated fixture configuration, then validate each installation at startup. Do not publish production environment files or builder images. |
+| Build context | `.dockerignore` currently includes `.env`; Dockerfile copies the context into the builder | Separate build inputs from runtime secrets; inspect final image and build layers before registry publication. |
+
+This is a source audit, not a validated portable image. The next verification is to
+run the **same image digest** for two installations with different names, domains,
+imager/badge URLs and credentials, then check rendered pages and browser requests.
+The registry publishing workflow is intentionally not enabled yet.
 
 ### Diagnose an update that is not visible
 

src/lib/docker-update.test.ts

@@ -29,6 +29,11 @@ function simulate(scenario: string) {
 	const dir = mkdtempSync(join(tmpdir(), "cms-compose-test-"));
 	try {
 		mkdirSync(join(dir, "scripts"));
+		mkdirSync(join(dir, "logs"));
+		writeFileSync(
+			join(dir, "logs/docker-release-history.log"),
+			`${"b".repeat(40)}\n${"c".repeat(40)}\n`,
+		);
 		copyFileSync(
 			resolve(root, "scripts/docker-update.sh"),
 			join(dir, "scripts/docker-update.sh"),
@@ -50,6 +55,7 @@ function simulate(scenario: string) {
 		if (result.error) throw result.error;
 		return {
 			status: result.status,
+			restored: existsSync(join(dir, "restored")),
 			output: result.stdout + result.stderr,
 			calls: existsSync(join(dir, "calls"))
 				? readFileSync(join(dir, "calls"), "utf8")
@@ -60,6 +66,32 @@ function simulate(scenario: string) {
 	}
 }
 describe("Docker clone updates", () => {
+	it("removes only historical release tags beyond the current and previous", () => {
+		const r = simulate("success");
+		expect(r.calls).toContain(`docker image rm epicnext-cms:${"c".repeat(40)}`);
+		expect(r.calls).not.toContain(
+			`docker image rm epicnext-cms:${"b".repeat(40)}`,
+		);
+	});
+	it("preserves older images used by another container", () => {
+		const r = simulate("retained-in-use");
+		expect(r.status, r.output).toBe(0);
+		expect(r.calls).not.toContain(
+			`docker image rm epicnext-cms:${"c".repeat(40)}`,
+		);
+	});
+	it("reports an unsuccessful rollback and retains the recovery image", () => {
+		const r = simulate("rollback-failure");
+		expect(r.status).not.toBe(0);
+		expect(r.output).toContain("rollback could not recreate CMS");
+		expect(r.calls).not.toContain("docker image rm epicnext-cms:rollback-");
+	});
+	it("handles first installation failures without claiming rollback", () => {
+		const r = simulate("first-failure");
+		expect(r.status).not.toBe(0);
+		expect(r.restored).toBe(false);
+		expect(r.output).toContain("no previous image exists");
+	});
 	it("builds the pulled commit, migrates before recreation and verifies local/public HTTP", () => {
 		const r = simulate("success");
 		expect(r.status, r.output).toBe(0);
@@ -91,6 +123,8 @@ describe("Docker clone updates", () => {
 			const r = simulate(scenario);
 			expect(r.status, r.output).not.toBe(0);
 			expect(r.output).not.toContain("Verified release");
+			expect(r.restored).toBe(true);
+			expect(r.output).toContain("Rollback verified locally");
 		},
 	);
 });

src/test/docker-update-harness.sh

@@ -15,15 +15,28 @@ docker() {
  case "$1 ${2:-}" in
   'inspect --format')
    if [ "${@: -1}" = epicnext-cms-app ]; then [ "$SCENARIO" = ci-active ] && echo true; return 0; fi
+   if [ "${@: -1}" = previous123 ] || [ -f "$TEST_DIR/restored" ]; then echo sha256:old; return 0; fi
    if [ "$SCENARIO" = wrong-image ]; then echo sha256:old; else echo sha256:new; fi ;;
   'image inspect')
+   if [[ "$*" = *org.opencontainers* ]] && [[ "$*" = *sha256:old* ]]; then printf 'b%.0s' {1..40}; echo; return 0; fi
    if [[ "$*" = *org.opencontainers* ]]; then echo "$TEST_SHA"; else echo sha256:new; fi ;;
   'compose config') return 0 ;;
   'compose build') [ "$SCENARIO" != build-failure ] ;;
-  'compose up') [ "$SCENARIO" != recreate-failure ] ;;
-  'compose ps') echo container123 ;;
+  'compose up')
+   if [[ "$CMS_RELEASE" = rollback-* ]]; then
+     [ "$SCENARIO" != rollback-failure ] || return 1
+     touch "$TEST_DIR/restored"; return 0
+   fi
+   touch "$TEST_DIR/cutover"
+   [ "$SCENARIO" != recreate-failure ] ;;
+  'compose ps')
+   if [ -f "$TEST_DIR/cutover" ]; then echo container123
+   elif [ "$SCENARIO" != first-failure ]; then echo previous123; fi ;;
   'run --rm') [ "$SCENARIO" != migration-failure ] ;;
+  'ps -aq') if [ "$SCENARIO" = retained-in-use ]; then echo other-container; fi ;;
   'exec container123')
+   if [ -f "$TEST_DIR/restored" ]; then return 0; fi
+   if [ "$SCENARIO" = first-failure ] || [ "$SCENARIO" = rollback-failure ]; then return 1; fi
    if [ "$SCENARIO" = wrong-release ]; then return 1; fi
    if [ "$SCENARIO" = wrong-public ] && [[ "$*" = *example.test* ]]; then return 1; fi ;;
   *) return 0 ;;