chore: run containers as non-root, add HEALTHCHECK, npm ci

Backend: new `app` user (UID 10001), STORAGE_DIR pre-chowned so the
named volume inherits ownership, curl installed for the HEALTHCHECK
that pings /api/v1/health. The crawler's Chromium uses --no-sandbox
already so dropping privileges costs nothing operationally.

Frontend: switch `npm install` to `npm ci` (matches CI; deterministic
versions; refuses to silently rewrite package-lock.json mid-build).
Run as the built-in `node` user via --chown=node:node, add a busybox
wget HEALTHCHECK on port 3000.

Both images now expose container-level health so orchestrators can
take a wedged container out of rotation instead of letting it keep
serving timeouts.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

backend/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "mangalord"
-version = "0.35.0"
+version = "0.34.0"
 edition = "2021"
 default-run = "mangalord"
 

backend/Dockerfile

@@ -19,12 +19,49 @@ COPY migrations ./migrations
 RUN touch src/main.rs src/lib.rs && cargo build --locked --release
 
 FROM debian:bookworm-slim
+# `curl` is for the container HEALTHCHECK; `ca-certificates` is for
+# outbound HTTPS (crawler covers/pages).
 RUN apt-get update \
- && apt-get install -y --no-install-recommends ca-certificates \
+ && apt-get install -y --no-install-recommends ca-certificates curl \
  && rm -rf /var/lib/apt/lists/*
+
+# Non-root runtime user. The API binary doesn't need any root
+# privilege; the crawler daemon's Chromium launcher uses --no-sandbox
+# precisely because user-namespace sandboxing is fragile, so dropping
+# privileges costs nothing operationally and shrinks the blast radius
+# of any RCE.
+ARG APP_UID=10001
+ARG APP_GID=10001
+RUN groupadd --system --gid ${APP_GID} app \
+ && useradd --system --uid ${APP_UID} --gid app --home-dir /home/app --create-home --shell /usr/sbin/nologin app
+
 WORKDIR /app
 COPY --from=builder /app/target/release/mangalord /usr/local/bin/mangalord
 COPY --from=builder /app/migrations /app/migrations
+
 ENV STORAGE_DIR=/var/lib/mangalord/storage
+# Pre-create the storage dir so the entrypoint doesn't need to
+# mkdir-as-root and so the named volume mount inherits the right
+# ownership.
+#
+# UPGRADE NOTE for operators: if you're moving from an older image
+# that ran as root, the existing `storage-data` volume has files owned
+# by UID 0 and the new UID-10001 user can't write them. Run once
+# before the upgrade:
+#   docker compose run --rm --user 0 backend \
+#     chown -R 10001:10001 /var/lib/mangalord/storage
+# (Postgres is unaffected — that image's `postgres` user UID hasn't
+# changed.)
+RUN mkdir -p ${STORAGE_DIR} \
+ && chown -R app:app ${STORAGE_DIR} /app /home/app
+
+USER app
 EXPOSE 8080
+
+# `--start-period` is generous because first boot runs sqlx::migrate
+# against postgres which can take a few seconds; subsequent restarts
+# are sub-second.
+HEALTHCHECK --interval=30s --timeout=5s --start-period=20s --retries=3 \
+  CMD curl -fsS http://localhost:8080/api/v1/health > /dev/null || exit 1
+
 CMD ["mangalord"]

backend/src/main.rs

@@ -17,7 +17,10 @@ async fn main() -> anyhow::Result<()> {
     tracing::info!(%addr, "mangalord listening");
     let listener = tokio::net::TcpListener::bind(addr).await?;
     axum::serve(listener, router)
-        .with_graceful_shutdown(shutdown_signal())
+        .with_graceful_shutdown(async {
+            let _ = tokio::signal::ctrl_c().await;
+            tracing::info!("ctrl-c received; shutting down");
+        })
         .await?;
 
     // Drain background tasks (crawler daemon) before exiting so Chromium
@@ -27,33 +30,3 @@ async fn main() -> anyhow::Result<()> {
     }
     Ok(())
 }
-
-/// Wait for either Ctrl-C (interactive shell) or SIGTERM (Docker /
-/// Kubernetes / Podman / systemd stop) and log which arrived. Without
-/// the SIGTERM branch, `docker compose stop` runs out its grace period
-/// and skips straight to SIGKILL — the daemon never gets the
-/// `daemon.shutdown().await` path, leaking Chromium.
-async fn shutdown_signal() {
-    use tokio::signal::unix::{signal, SignalKind};
-    let mut sigterm = match signal(SignalKind::terminate()) {
-        Ok(s) => s,
-        Err(e) => {
-            // SignalKind::terminate() is supported on every Unix the
-            // tokio runtime runs on; if registration fails we still
-            // honour Ctrl-C so the process is at least
-            // interactive-shutdownable.
-            tracing::warn!(error = %e, "could not install SIGTERM handler; falling back to ctrl_c only");
-            let _ = tokio::signal::ctrl_c().await;
-            tracing::info!("ctrl-c received; shutting down");
-            return;
-        }
-    };
-    tokio::select! {
-        _ = tokio::signal::ctrl_c() => {
-            tracing::info!("ctrl-c received; shutting down");
-        }
-        _ = sigterm.recv() => {
-            tracing::info!("SIGTERM received; shutting down");
-        }
-    }
-}

frontend/Dockerfile

@@ -1,7 +1,11 @@
 FROM node:22-alpine AS builder
 WORKDIR /app
 COPY package.json package-lock.json* ./
-RUN npm install
+# `npm ci` installs the locked versions exactly; `npm install` would
+# silently rewrite package-lock.json mid-build. CI (.gitea/workflows)
+# also uses `npm ci`, so this keeps the image build deterministic and
+# matches what the test job validated.
+RUN npm ci
 COPY . .
 RUN npm run build
 
@@ -10,8 +14,20 @@ WORKDIR /app
 ENV NODE_ENV=production
 ENV HOST=0.0.0.0
 ENV PORT=3000
-COPY --from=builder /app/build ./build
+
-COPY --from=builder /app/node_modules ./node_modules
+# node:22-alpine ships a `node` user (UID 1000); use it instead of
-COPY --from=builder /app/package.json ./
+# running the SvelteKit server as root.
+COPY --from=builder --chown=node:node /app/build ./build
+COPY --from=builder --chown=node:node /app/node_modules ./node_modules
+COPY --from=builder --chown=node:node /app/package.json ./
+
+USER node
 EXPOSE 3000
+
+# Alpine's busybox `wget` is the canonical lightweight HTTP probe.
+# `--spider` doesn't follow redirects; `node build` serves a 200 on
+# `/` for the homepage so this works without a dedicated /health.
+HEALTHCHECK --interval=30s --timeout=5s --start-period=10s --retries=3 \
+  CMD wget -q --spider http://localhost:3000/ || exit 1
+
 CMD ["node", "build"]

frontend/package.json

@@ -1,6 +1,6 @@
 {
   "name": "mangalord-frontend",
-  "version": "0.35.0",
+  "version": "0.34.0",
   "private": true,
   "type": "module",
   "scripts": {