Ekklesia/.github/workflows/ci.yml

name: CI

# IMPORTANT — the currently inventoried server is Gitea 1.24.2, which *ignores* several keys used
# below. Per https://docs.gitea.com/1.24/usage/actions/comparison, its unsupported workflow syntax
# includes `permissions` / `jobs.<job_id>.permissions`, `concurrency`, and
# `jobs.<job_id>.timeout-minutes`. They are declared here deliberately, so the workflow is already
# correct on a supported release and on GitHub Actions, but on this server they are inert:
#
#   * `permissions:` does NOT restrict the in-job `GITEA_TOKEN`. Job-token permission controls,
#     repository/owner defaults, and server-side maximum-permission clamping arrive in the 1.26
#     feature line (https://docs.gitea.com/1.26/usage/actions/token-permissions). Until the server
#     is upgraded and configured, the token's authority is whatever the server grants — not what
#     this file requests.
#   * `concurrency:` and `timeout-minutes:` are NOT bounded-execution guarantees here. Cancellation,
#     timeout, and teardown must be enforced by the trusted runner provisioner/reaper.
#
# `persist-credentials: false` below is unaffected by any of this and is enforced by the action
# itself. See docs/development/security.md.

on:
  pull_request:
  push:
    branches:
      - main

permissions:
  contents: read

concurrency:
  group: ci-${{ github.workflow }}-${{ github.ref }}
  cancel-in-progress: true

jobs:
  verify:
    runs-on: ubuntu-latest
    timeout-minutes: 15
    steps:
      - name: Check out repository
        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
        with:
          # `actions/checkout` defaults to leaving the job token in `.git/config`, where any later
          # step — including one a pull request added to this file — could read or reuse it. Nothing
          # in this workflow pushes, so the credential is never needed after checkout.
          persist-credentials: false

      - name: Set up Node.js
        uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6.4.0
        with:
          node-version-file: .node-version

      - name: Activate pinned pnpm
        run: |
          corepack enable
          corepack prepare [email protected] --activate

      - name: Install dependencies
        run: pnpm install --frozen-lockfile

      - name: Verify repository
        run: pnpm ci:verify

  infrastructure-smoke:
    needs: verify
    runs-on: ubuntu-latest
    timeout-minutes: 10
    env:
      # Names this job's stacks, so its final step removes exactly these (scripts/lib/ci-project.sh).
      EKKLESIA_CI_JOB_KEY: infrastructure-smoke
    steps:
      - name: Check out repository
        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
        with:
          # `actions/checkout` defaults to leaving the job token in `.git/config`, where any later
          # step — including one a pull request added to this file — could read or reuse it. Nothing
          # in this workflow pushes, so the credential is never needed after checkout.
          persist-credentials: false

      # A job the runner killed (cancelled, or past the runner's own time limit) never ran its
      # cleanup. Anything a CI job left on this shared daemon more than three hours ago goes first.
      - name: Sweep stale CI stacks from the runner
        run: bash scripts/ci-sweep.sh --stale

      - name: Prove the sweep removes exactly what it should, against real Docker resources
        run: bash scripts/test-ci-sweep.sh

      - name: Exercise PostgreSQL and S3 infrastructure
        run: bash scripts/smoke-infrastructure.sh

      # Whatever happened above, this job's own stacks do not outlive it.
      - name: Remove this job's CI stacks
        if: always()
        run: bash scripts/ci-sweep.sh --job

  migration-smoke:
    needs: verify
    runs-on: ubuntu-latest
    timeout-minutes: 15
    env:
      # Names this job's stacks, so its final step removes exactly these (scripts/lib/ci-project.sh).
      EKKLESIA_CI_JOB_KEY: migration-smoke
    steps:
      - name: Check out repository
        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
        with:
          # `actions/checkout` defaults to leaving the job token in `.git/config`, where any later
          # step — including one a pull request added to this file — could read or reuse it. Nothing
          # in this workflow pushes, so the credential is never needed after checkout.
          persist-credentials: false

      # A job the runner killed (cancelled, or past the runner's own time limit) never ran its
      # cleanup. Anything a CI job left on this shared daemon more than three hours ago goes first.
      - name: Sweep stale CI stacks from the runner
        run: bash scripts/ci-sweep.sh --stale

      - name: Set up Node.js
        uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6.4.0
        with:
          node-version-file: .node-version

      - name: Activate pinned pnpm
        run: |
          corepack enable
          corepack prepare [email protected] --activate

      - name: Install dependencies
        run: pnpm install --frozen-lockfile

      - name: Exercise transactional migrations against PostgreSQL
        run: pnpm test:migrations:integration

      # Whatever happened above, this job's own stacks do not outlive it.
      - name: Remove this job's CI stacks
        if: always()
        run: bash scripts/ci-sweep.sh --job

  image-build:
    needs: verify
    runs-on: ubuntu-latest
    timeout-minutes: 20
    env:
      # Names this job's stacks, so its final step removes exactly these (scripts/lib/ci-project.sh).
      EKKLESIA_CI_JOB_KEY: image-build
      # Cache mounts in deploy/Dockerfile need BuildKit; this selects it even where the Docker CLI
      # has no buildx plugin.
      DOCKER_BUILDKIT: "1"
    steps:
      - name: Check out repository
        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
        with:
          # `actions/checkout` defaults to leaving the job token in `.git/config`, where any later
          # step — including one a pull request added to this file — could read or reuse it. Nothing
          # in this workflow pushes, so the credential is never needed after checkout.
          persist-credentials: false

      # A job the runner killed (cancelled, or past the runner's own time limit) never ran its
      # cleanup. Anything a CI job left on this shared daemon more than three hours ago goes first.
      - name: Sweep stale CI stacks from the runner
        run: bash scripts/ci-sweep.sh --stale

      # The platform-only image (ADR 0044): a checkout has no `modules/`, so this proves the image
      # builds, validates, and assembles with zero modules. Build only — no registry login, no
      # credentials, no push, no tag anywhere but this runner's local image store.
      # Tagged per run and attempt, not only per commit: a pull request and a push of the same commit
      # can build at once on one runner's Docker daemon, and neither may remove the other's image.
      # Labeled like every CI stack, so this job's final step removes it even if the build is killed.
      - name: Build the production image without modules
        shell: bash
        run: |
          source scripts/lib/ci-project.sh
          docker build \
            --file deploy/Dockerfile \
            --build-arg REVISION="$GITHUB_SHA" \
            --label "${EKKLESIA_CI_LABEL}=$(ci_project_name image)" \
            --label "${EKKLESIA_CI_CREATED_LABEL}=$(date +%s)" \
            --tag ekklesia-ci:"$GITHUB_SHA-${GITHUB_RUN_ID:-0}-${GITHUB_RUN_ATTEMPT:-1}" \
            .

      # Whatever happened above, this job's own stacks do not outlive it.
      - name: Remove this job's CI stacks
        if: always()
        run: bash scripts/ci-sweep.sh --job

  deploy-smoke:
    needs: verify
    runs-on: ubuntu-latest
    timeout-minutes: 30
    # Both topologies (ADR 0045): same-origin, the default every installation gets, and split, which
    # adds a test-only module and drives a real headless browser across the two origins.
    strategy:
      fail-fast: false
      matrix:
        topology:
          - same-origin
          - split
    env:
      # Names this job's stacks, so its final step removes exactly these (scripts/lib/ci-project.sh).
      EKKLESIA_CI_JOB_KEY: deploy-smoke-${{ matrix.topology }}
      DOCKER_BUILDKIT: "1"
      EKKLESIA_SMOKE_TOPOLOGY: ${{ matrix.topology }}
    steps:
      - name: Check out repository
        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
        with:
          # `actions/checkout` defaults to leaving the job token in `.git/config`, where any later
          # step — including one a pull request added to this file — could read or reuse it. Nothing
          # in this workflow pushes, so the credential is never needed after checkout.
          persist-credentials: false

      # A job the runner killed (cancelled, or past the runner's own time limit) never ran its
      # cleanup. Anything a CI job left on this shared daemon more than three hours ago goes first.
      - name: Sweep stale CI stacks from the runner
        run: bash scripts/ci-sweep.sh --stale

      # The reference deployment end to end (ADR 0044): a platform-only image, base + proxy with
      # Caddy's internal CA (test-only), an explicit migration apply against this job's own fresh
      # PostgreSQL, then the API, Dashboard, storage delivery, client-address chain, and verify-full
      # database TLS through the proxy. Every secret is generated for this run and discarded with
      # it; nothing is pushed, published, or logged in to.
      - name: Smoke-test the reference deployment (${{ matrix.topology }})
        run: bash scripts/smoke-deploy.sh

      # Whatever happened above, this job's own stacks do not outlive it.
      - name: Remove this job's CI stacks
        if: always()
        run: bash scripts/ci-sweep.sh --job