register-referentie/.gitea/workflows/ci.yaml

name: CI

on:
  push:
    branches: [main]
  pull_request:
    branches: [main]

permissions:
  contents: read

# Supersede stale runs: a new push to the same branch/PR cancels the previous run, so the runner's
# concurrency slots aren't spent on commits nobody is waiting for (refs #127).
concurrency:
  group: ci-${{ github.workflow }}-${{ github.ref }}
  cancel-in-progress: true

# Self-hosted runner — see docs/runbooks/ci.md for the runner setup.
# `uses:` are absolute, tag-pinned URLs (CLAUDE.md §8.7 / §15).

# Each job calls a `make` target — the same one developers run locally
# (`make ci`). The Makefile is the single source of truth; see docs/runbooks/ci.md.

jobs:
  lint:
    runs-on: ubuntu-latest
    steps:
      - uses: https://github.com/actions/checkout@v4
      - uses: https://github.com/actions/setup-dotnet@v4
        with:
          dotnet-version: '10.0.x'
      # Cache the NuGet package store so each .NET job restores from disk, not the network. There are
      # no lock files (so setup-dotnet's built-in cache doesn't apply); key on the project files. @v3
      # avoids the GHES guard that breaks @v4 on Gitea (gitea-actions-gotchas.md); cache is best-effort
      # — a miss just restores from the network. See issue #73.
      - uses: https://github.com/actions/cache@v3
        with:
          path: ~/.nuget/packages
          key: nuget-${{ runner.os }}-${{ hashFiles('**/*.csproj') }}
          restore-keys: |
            nuget-${{ runner.os }}-
      - run: make lint

  build:
    runs-on: ubuntu-latest
    steps:
      - uses: https://github.com/actions/checkout@v4
      - uses: https://github.com/actions/setup-dotnet@v4
        with:
          dotnet-version: '10.0.x'
      - uses: https://github.com/actions/cache@v3
        with:
          path: ~/.nuget/packages
          key: nuget-${{ runner.os }}-${{ hashFiles('**/*.csproj') }}
          restore-keys: |
            nuget-${{ runner.os }}-
      - run: make build

  unit:
    runs-on: ubuntu-latest
    steps:
      - uses: https://github.com/actions/checkout@v4
      - uses: https://github.com/actions/setup-dotnet@v4
        with:
          dotnet-version: '10.0.x'
      - uses: https://github.com/actions/cache@v3
        with:
          path: ~/.nuget/packages
          key: nuget-${{ runner.os }}-${{ hashFiles('**/*.csproj') }}
          restore-keys: |
            nuget-${{ runner.os }}-
      - run: make unit

  # Frontend (Nx/Angular) lane: install with pnpm, then Nx lint + test + build.
  frontend:
    runs-on: ubuntu-latest
    steps:
      - uses: https://github.com/actions/checkout@v4
      - uses: https://github.com/pnpm/action-setup@v4
        with:
          version: 11
      - uses: https://github.com/actions/setup-node@v4
        with:
          node-version: '24'
          cache: 'pnpm'
      - run: make frontend

  mutation:
    runs-on: ubuntu-latest
    steps:
      - uses: https://github.com/actions/checkout@v4
      - uses: https://github.com/actions/setup-dotnet@v4
        with:
          dotnet-version: '10.0.x'
      - uses: https://github.com/actions/cache@v3
        with:
          path: ~/.nuget/packages
          key: nuget-${{ runner.os }}-${{ hashFiles('**/*.csproj') }}
          restore-keys: |
            nuget-${{ runner.os }}-
      - run: make mutation
      # Publish the Stryker HTML reports. `if: always()` uploads them even when the
      # ratchet fails — that is exactly when you want to inspect the survivors.
      # `continue-on-error` keeps the upload best-effort: the mutation *gate* is the
      # ratchet (make mutation's exit code), not the report, so a Gitea artifact-backend
      # 500 must not fail the job (gitea-actions-gotchas.md §4). Glob handles Stryker's
      # non-deterministic StrykerOutput/<timestamp>/ dir. Pinned @v3: @v4's bundled
      # @actions/artifact hard-aborts on non-github.com (GHES guard) — see the runbook.
      - uses: https://github.com/actions/upload-artifact@v3
        if: always()
        continue-on-error: true
        with:
          name: acl-mutation-report
          path: services/acl/StrykerOutput/**/reports/mutation-report.html
          if-no-files-found: warn
      - uses: https://github.com/actions/upload-artifact@v3
        if: always()
        continue-on-error: true
        with:
          name: event-subscriber-mutation-report
          path: services/event-subscriber/StrykerOutput/**/reports/mutation-report.html
          if-no-files-found: warn
      - uses: https://github.com/actions/upload-artifact@v3
        if: always()
        continue-on-error: true
        with:
          name: domain-mutation-report
          path: services/domain/StrykerOutput/**/reports/mutation-report.html
          if-no-files-found: warn
      - uses: https://github.com/actions/upload-artifact@v3
        if: always()
        continue-on-error: true
        with:
          name: bff-mutation-report
          path: services/bff/StrykerOutput/**/reports/mutation-report.html
          if-no-files-found: warn

  # One stage for every check that needs the live stack. Booting OpenZaak once (instead
  # of once per job) is the cheapest layout (issue #58). No setup-dotnet: the ACL test runs
  # in a built image and everything reaches services by container IP. Needs Docker + egress
  # (base images, nuget, selectielijst.openzaak.nl).
  #
  # `needs: [mutation]` is NOT a data dependency — it serialises the two memory-heavy jobs so
  # they never co-schedule now the runner has capacity >1. A concurrent Stryker run + full-stack
  # bring-up + Playwright browser on one host is what OOMs the e2e (commit d5e5fa2, #126). The
  # light .NET/frontend jobs have no `needs`, so they still parallelise up to runner capacity.
  # `if: !cancelled()` keeps verify-stack running even when the mutation ratchet fails (so we don't
  # lose its signal) while still honouring run cancellation from the concurrency group above.
  verify-stack:
    needs: [mutation]
    if: ${{ !cancelled() }}
    runs-on: ubuntu-latest
    steps:
      - uses: https://github.com/actions/checkout@v4
      # Bring the full stack up + wait for health — this also is the DoD "compose up
      # reaches green health" smoke (it replaces the old compose-smoke job).
      - name: Bring up the full stack & wait for health
        run: make verify-up
      - name: Observability backplane (Grafana + Tempo + Prometheus datasources)
        run: OBS_TIMEOUT=180 make verify-observability
      - name: ACL ↔ OpenZaak integration tests
        run: make verify-acl
      - name: OpenZaak → NRC notification delivery
        run: make verify-nrc
      - name: OpenZaak → NRC → Event Subscriber → projection-api
        run: make verify-projection
      - name: Domain → Flowable → ACL → OpenZaak
        run: make verify-domain
      - name: BFF → Keycloak + domain + projection
        run: make verify-bff
      - name: Distributed traces reach Tempo (one connected trace across services)
        run: TRACING_TIMEOUT=120 make verify-tracing
      - name: Golden-signal metrics scraped by Prometheus (/metrics on every service)
        run: METRICS_TIMEOUT=120 make verify-metrics
      - name: Self-service e2e (Playwright, login → submit → success)
        run: make verify-e2e
      # Log dump must precede teardown (which removes the containers).
      - name: Dump container logs on failure
        if: failure()
        run: docker compose -f infra/docker-compose.yml logs --no-color --tail=100 oz-init openzaak nrc-init nrc-web nrc-celery nrc-beat flowable-db flowable-rest flowable-init keycloak acl bff domain projection-db event-subscriber projection-api self-service openbaar behandel tempo prometheus grafana 2>&1 || true
      - name: Tear down
        if: always()
        run: make down