feat(deploy): add the production container image

Add deploy/Dockerfile and .dockerignore (ADR 0044): one image for the
api service and every operator-run CLI, built from an already-assembled
workspace (the platform plus whatever modules/<id> the context holds).

- node:24.18.0-trixie-slim pinned by index digest; pnpm via Corepack at
  the root packageManager version.
- Build stage: frozen install, modules:validate, migrations:validate,
  build. Runtime: production-only node_modules plus every dist/, core
  migrations, and each module directory, in the repository layout the
  API and CLIs resolve paths from; root-owned, run as node.
- NODE_ENV=production and EKKLESIA_API_HOST=0.0.0.0 inside the image
  only; the platform default stays 127.0.0.1. Configuration comes only
  from the environment; no .env enters the context or any layer.
- HEALTHCHECK on /api/v1/health/ready with Node's fetch; OCI labels for
  source, revision, and version.
- CI builds the image without modules: build only, no credentials, no
  push.
- deploy/README.md documents the image, the read-only production
  posture (verified), init: true, and the exact CLI commands.

Co-Authored-By: Claude Opus 5.5 <[email protected]>
This commit is contained in:
ekklesia
2026-10-01 20:00:43 -05:00
co-authored by Claude Opus 5.5
parent ef1383d080
commit 756e9b821c
5 changed files with 396 additions and 3 deletions
+129
View File
@@ -0,0 +1,129 @@
# Ekklesia's one production image (ADR 0044): the `api` service and every operator-run CLI, from one
# build. See deploy/README.md for how to build and run it.
#
# The build context is an already-assembled workspace: the platform, zero or more module packages in
# `modules/<id>`, and the `pnpm-lock.yaml` that describes exactly that set. This file clones nothing
# and chooses no modules. With an empty or absent `modules/`, it builds the platform alone.
#
# No `# syntax=` directive, deliberately: it would make BuildKit pull an unpinned frontend image.
# The built-in frontend supports everything below, including cache mounts.
# Node.js 24.18.0 (matching `.node-version`) on Debian 13 slim, pinned by its multi-architecture
# index digest. glibc rather than musl, because module dependencies such as sharp ship glibc
# prebuilt binaries. Every stage starts from this exact image.
FROM node:24.18.0-trixie-slim@sha256:ae91dcc111a68c9d2d81ff2a17bda61be126426176fde6fe7d08ab13b7f50573 AS base
# ---------------------------------------------------------------------------------------------------
# toolchain: pnpm through Corepack, at exactly the root `packageManager` version.
# ---------------------------------------------------------------------------------------------------
FROM base AS toolchain
ENV COREPACK_ENABLE_DOWNLOAD_PROMPT=0 \
PNPM_HOME=/pnpm \
TURBO_TELEMETRY_DISABLED=1 \
DO_NOT_TRACK=1
WORKDIR /opt/ekklesia
COPY package.json ./
# Corepack reads `packageManager` (pnpm@<exact version>) from the root manifest, so the version is
# declared once, in the repository, and never restated here.
RUN corepack enable && corepack install
# ---------------------------------------------------------------------------------------------------
# manifests: the lockfile, workspace configuration, and every workspace package.json, at their
# repository paths. Dependency installation keys on these alone, so a source-only change reuses the
# installed layers.
# ---------------------------------------------------------------------------------------------------
FROM base AS manifests
WORKDIR /context
COPY . .
RUN set -eu; \
mkdir /manifests; \
cp package.json pnpm-lock.yaml pnpm-workspace.yaml .npmrc /manifests/; \
for manifest in apps/*/package.json builders/*/package.json core/package.json \
modules/*/package.json packages/*/package.json surfaces/*/package.json \
templates/*/package.json; do \
if [ -f "$manifest" ]; then install -D -m 0644 "$manifest" "/manifests/$manifest"; fi; \
done
# ---------------------------------------------------------------------------------------------------
# build: full install, validation, build, then the exact runtime file set.
# ---------------------------------------------------------------------------------------------------
FROM toolchain AS build
# Sources first, then one install: workspace packages publish `bin` commands from source files (the
# module UI builder's, which every module build invokes), and pnpm links a bin only when its target
# already exists. The store cache mount keeps a rebuild off the network all the same.
COPY . .
RUN --mount=type=cache,id=ekklesia-pnpm-store,target=/pnpm/store \
pnpm install --frozen-lockfile --store-dir /pnpm/store
# The same gates `pnpm verify` runs for modules and migrations, against exactly the module set in this
# context. Each script builds first; the final build is a Turbo cache hit that keeps the intent
# explicit.
RUN pnpm modules:validate && pnpm migrations:validate && pnpm build
# What the runtime resolves at startup, at the paths it resolves them from:
# - every workspace package's `dist/` (every package exports only from `dist/`), which includes
# the Dashboard and display host assets under `surfaces/shell/dist/browser/`;
# - Core's migrations, `core/drizzle/` with its `meta/` journal;
# - each module directory whole, minus `node_modules`, because each manifest names its own
# entrypoints, UI artifacts, and migrations directory.
# `node_modules` comes from the production-only install below, never from this stage.
RUN set -eu; \
mkdir -p /runtime/core /runtime/modules; \
for package in apps/* core packages/* surfaces/*; do \
if [ -d "$package/dist" ]; then \
mkdir -p "/runtime/$package"; \
cp -a "$package/dist" "/runtime/$package/dist"; \
fi; \
done; \
cp -a core/drizzle /runtime/core/drizzle; \
if [ -d modules ]; then \
tar -C modules --exclude='node_modules' -cf - . | tar -C /runtime/modules -xf -; \
fi
# ---------------------------------------------------------------------------------------------------
# prod-deps: the same lockfile, production dependencies only. No compiler, bundler, or test runner
# reaches the runtime image.
# ---------------------------------------------------------------------------------------------------
FROM toolchain AS prod-deps
COPY --from=manifests /manifests/ ./
RUN --mount=type=cache,id=ekklesia-pnpm-store,target=/pnpm/store \
pnpm install --frozen-lockfile --prod --store-dir /pnpm/store
# ---------------------------------------------------------------------------------------------------
# runtime
# ---------------------------------------------------------------------------------------------------
FROM base AS runtime
ARG VERSION=""
ARG REVISION=""
ARG SOURCE=""
LABEL org.opencontainers.image.title="Ekklesia" \
org.opencontainers.image.description="Ekklesia API, Dashboard, display host, and operator CLIs" \
org.opencontainers.image.version="${VERSION}" \
org.opencontainers.image.revision="${REVISION}" \
org.opencontainers.image.source="${SOURCE}" \
org.opencontainers.image.base.name="docker.io/library/node:24.18.0-trixie-slim" \
org.opencontainers.image.base.digest="sha256:ae91dcc111a68c9d2d81ff2a17bda61be126426176fde6fe7d08ab13b7f50573"
# Only the container's own listen address differs from the platform default: outside a container
# the API still binds 127.0.0.1. `production` is stated rather than relied on as the default.
ENV NODE_ENV=production \
EKKLESIA_API_HOST=0.0.0.0 \
EKKLESIA_API_PORT=3000
# The repository layout, preserved: the API finds the repository root three directories above
# `apps/api/dist/`, and every CLI uses its working directory as the root.
WORKDIR /opt/ekklesia
COPY --from=prod-deps /opt/ekklesia/ ./
COPY --from=build /runtime/ ./
# Files stay root-owned: the unprivileged runtime user can read the installation, never modify it.
USER node
EXPOSE 3000
# Readiness, not liveness: an instance whose database is unreachable or that is shutting down is
# unhealthy. Node's own fetch, so the image needs no curl.
HEALTHCHECK --interval=30s --timeout=5s --start-period=30s --retries=3 \
CMD ["node", "-e", "fetch('http://127.0.0.1:' + (process.env.EKKLESIA_API_PORT || '3000') + '/api/v1/health/ready', { signal: AbortSignal.timeout(4000) }).then((response) => process.exit(response.status === 200 ? 0 : 1), () => process.exit(1))"]
# `pnpm api:start` without its build step and without `--env-file`: configuration comes only from
# the container environment. The same image runs every CLI: `node core/dist/cli/<command>.js`.
CMD ["node", "apps/api/dist/server.js"]