lmxopcua/.github/workflows/v2-ci.yml

# CI for the v2 branch — runs on every push + PR to the v2-akka-fuse / master
# branches. One job restores and builds once, then tests the WHOLE solution
# minus the env-gated tiers (self-maintaining).
#
# Skips E2E (Category=E2E) and LiveIntegration (needs a real gateway/PLC/VPN) — both
# are env-gated tiers with no hosted-runner fixtures. (The skip-gated *.IntegrationTests
# still run in the unit-tests leg and Assert.Skip when their fixtures are unreachable.)
#
# Compatible with both GitHub Actions and Gitea Actions (act_runner). The .NET 10
# SDK is pinned via global.json at the repo root; if no global.json exists, the
# setup-dotnet step falls back to dotnet-version below.

name: v2-ci

on:
  push:
    branches: [v2-akka-fuse, master]
  pull_request:
    branches: [v2-akka-fuse, master]
  workflow_dispatch: {}

# #707: one active run per repository across push/PR triggers. Gitea 1.26 supports
# workflow concurrency; newer pending runs can supersede an older pending run.
concurrency:
  group: lmxopcua-v2-ci
  cancel-in-progress: false

env:
  DOTNET_NOLOGO: "1"
  DOTNET_CLI_TELEMETRY_OPTOUT: "1"

jobs:

  unit-tests:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
      - uses: actions/setup-dotnet@v4
        with:
          dotnet-version: 10.0.x
      # #606: regenerated review summary must remain in sync with module findings.
      - name: code-reviews README drift check
        run: python3 code-reviews/regen-readme.py --check
      # #707: bound project workers and avoid concurrent NuGet restore work.
      - name: dotnet restore
        run: dotnet restore ZB.MOM.WW.OtOpcUa.slnx --disable-parallel -m:2
      - name: dotnet build
        run: dotnet build ZB.MOM.WW.OtOpcUa.slnx --no-restore --configuration Release -m:2
      # #606: the runner's size is the context every timing-sensitive failure needs and the log never
      # recorded it (load average included: the two Gitea runners may be running jobs side by side).
      - name: runner capacity
        run: |
          echo "nproc=$(nproc)"
          free -m || true
          uptime || true
      # 07/S-1: ONE whole-solution leg instead of a hand-maintained 5-project matrix that
      # silently dropped Client (388 tests), Analyzers (31), and every driver + most Core suite.
      # Self-maintaining — a new *.Tests project is covered automatically, no matrix to widen —
      # and matches CLAUDE.md's own `dotnet test ZB.MOM.WW.OtOpcUa.slnx` guidance. Excludes only
      # the env-gated tiers: E2E (nightly, needs the docker-dev fleet) and LiveIntegration (needs
      # a real gateway/PLC/VPN). Category=SlowUnit (Mqtt socket-timeout tests, #606) is deliberately NOT
      # excluded here — it is a local-dev-loop opt-out only. The skip-gated *.IntegrationTests Assert.Skip when their fixtures
      # are unreachable, so they run harmlessly here (and are counted by the skip-gate below).
      - name: dotnet test (whole solution, minus E2E + LiveIntegration)
        # #606: Akka TestKit time dilation for the Runtime + ControlPlane actor suites (read by their
        # harnesses, tests/Server/*/Harness/TestTimeFactor.cs). Their 2–8 s presence budgets
        # — sized on an idle dev box — failed in a long
        # tail, a different test per run. Dilation only stretches waits: a presence wait still fails if
        # the message never comes, and absence windows get longer (stricter). Local runs stay at 1.
        env:
          AKKA_TEST_TIMEFACTOR: "3"
        run: >
          dotnet test ZB.MOM.WW.OtOpcUa.slnx --configuration Release --no-build
          -m:1 -p:TestTfmsInParallel=false --settings scripts/ci/ci.runsettings
          --filter "Category!=E2E&Category!=LiveIntegration"
          --logger "trx" --results-directory artifacts/trx
      # 07/S-2 fail-on-skip: a whole-solution run that executed ZERO tests is a masked outage
      # (bad filter, broken discovery), not a pass — fail loudly. Runs even on test failure so
      # the diagnostic is always emitted.
      - name: assert not-all-skipped
        if: always()
        # #606: a whole-solution run executes ~13,000 tests; 12000 catches a project silently dropping out
        # of discovery, not just the all-skipped case. Raise it as the suite grows.
        env:
          MIN_EXECUTED: "12000"
        run: bash scripts/ci/assert-not-all-skipped.sh artifacts/trx/*.trx
      # #606: pinned to v3. Gitea's act_runner reports itself as GHES, and @actions/artifact v2+
      # (upload-artifact@v4+) refuses GHES outright ("GHESNotSupportedError") — so on Gitea the v4
      # step failed EVERY run and the job could never go green, independent of the tests. v3 speaks
      # the artifact API Gitea implements. continue-on-error because the trx upload is evidence, not a
      # gate: the test step and the skip-gate above decide the job, and an artifact-store hiccup must
      # not turn a green run red.
      - name: upload trx
        if: always()
        continue-on-error: true
        uses: actions/upload-artifact@v3
        with:
          name: unit-trx
          path: artifacts/trx/*.trx
          if-no-files-found: warn

  # NOTE (07/P-5): the former `integration` matrix job (Host.IntegrationTests +
  # OpcUaServer.IntegrationTests) was removed as fully redundant — the unit-tests leg
  # above already runs BOTH projects under the identical filter, fixtureless, and gates
  # them at MIN_EXECUTED=1. Its only unique output was a report-only skip tally the unit
  # leg's trx already contains. FOLLOW-UP (S-2 option #2): if a fixture-backed integration
  # leg is wanted, add it as a NEW job that starts the one public-image fixture as a
  # `services:` block (mcr.microsoft.com/iotedge/opc-plc; the modbus/S7/AB/FOCAS sims are
  # locally-built `otopcua-*` images not pullable here), sets OPCUA_SIM_ENDPOINT, and gates
  # at MIN_EXECUTED=1 so a fixture outage turns the job red — covering something the unit
  # leg cannot, rather than re-running the same fixtureless tests.