ci-macos-e2e.yml

name: ci-macos-e2e

# The e2e suite on macOS ARM64, called by ci.yml beside ci-macos.yml after the
# macOS build. Two shards, assigned by measured duration
# (tests/e2e/timings/macos.tsv, rule R4 of the 2026-10-02 CI record), each
# running the one binary build.yml produced (use-built-mcpp, rule R1), and
# each writing the per-test report the e2e-coverage job of ci.yml reads.
#
# The suite took about 3.5 minutes when this workflow was split out of
# ci-macos.yml, and it was not sharded for that reason. Measured on 2026-10-01
# it took 17 to 21 minutes in one job, and reached the 25-minute limit once.
#
# Paired workflows: ci-macos.yml, ci-linux-e2e.yml, ci-windows-e2e.yml.

on:
  workflow_call:
    inputs:
      known-red:
        description: >
          Include the legs that are known red (#669). ci.yml passes true on
          main, on dispatch and on a pull request labelled `macos-27` (rule R7).
        type: boolean
        required: false
        default: true

jobs:
  e2e:
    name: e2e suite ${{ matrix.shard }}/${{ matrix.shards }} (macOS ARM64, self-host, ${{ matrix.image }}${{ matrix.known_red != '' && format(', known red {0}', matrix.known_red) || '' }})
    # The same two images as ci-macos.yml; `xcode-27` is macOS 27 (see there).
    # KNOWN RED on xcode-27, along with ci-macos.yml's own job: the image's
    # Command Line Tools SDK ships an `arm64e.x1` .tbd stub ld64.lld 22.1.8
    # cannot parse (fixed upstream, llvm-project#222721, not yet in a
    # release). See mcpp-community/mcpp#669.
    strategy:
      fail-fast: false
      matrix:
        # macos-15 in two shards. The known-red leg is in the matrix only when
        # the caller asks for it, and as one shard: it fails at its first link
        # (#669), and two shards of it would hold two of the five macOS slots.
        include: ${{ fromJSON(inputs.known-red && '[{"image":"macos-15","known_red":"","shard":1,"shards":2},{"image":"macos-15","known_red":"","shard":2,"shards":2},{"image":"xcode-27","known_red":"#669","shard":1,"shards":1}]' || '[{"image":"macos-15","known_red":"","shard":1,"shards":2},{"image":"macos-15","known_red":"","shard":2,"shards":2}]') }}
    runs-on: ${{ matrix.image }}
    # KNOWN RED, MACHINE-READABLY (the 2026-09-28 design, WS7). A leg whose
    # failure has a tracked external cause carries that issue in `known_red`:
    # the leg may fail without failing the workflow, its own result and log
    # stay visible, and .github/tools/check_workflow_assertions.py requires
    # the issue to be open. The leg leaves the list when #669 closes.
    continue-on-error: ${{ matrix.known_red != '' }}
    timeout-minutes: 60
    env:
      E2E_SHARD: ${{ matrix.shard }}/${{ matrix.shards }}
      E2E_TIMINGS: tests/e2e/timings/macos.tsv
      E2E_REPORT: ${{ github.workspace }}/e2e-report-${{ matrix.image == 'macos-15' && 'macos' || matrix.image }}-${{ matrix.shard }}.tsv
    # NOTE: no MCPP_VERBOSE — the e2e suite asserts mcpp's default quiet
    # output (tests 48/53).
    steps:
      # `submodules: recursive` so tests/e2e/233_bench_matrix.sh can check that
      # each `hub`/`body` in bench/matrix.json exists in the tree it names --
      # the check reads "submodule not initialised" without them and reports
      # nothing, which is how a stale hub path survived (#599). Under 10 MB of
      # source across the three pins, and nothing here builds them.
      - uses: actions/checkout@v4
        with:
          submodules: recursive
      - uses: ./.github/actions/setup-macos-llvm
        with:
          image: ${{ matrix.image }}

      - uses: ./.github/actions/use-built-mcpp
        with:
          host: macos-arm64

      - name: E2E suite
        # Twice a shard's budget of about nine minutes (R4); the per-test 600 s
        # limit in run_all.sh names a test that hangs.
        timeout-minutes: 20
        run: |
          # MCPP is this commit's binary and MCPP_BOOT the released bootstrap
          # (use-built-mcpp); e2e 252 checks an older client against a package
          # this commit produces, so it needs a real old binary.
          export MCPP MCPP_BOOT MCPP_VENDORED_XLINGS
          test -x "$MCPP_VENDORED_XLINGS"
          export MCPP_E2E_TOOLCHAIN_MIRROR=GLOBAL
          "$MCPP" self config
          # macOS default toolchain is LLVM
          "$MCPP" toolchain default "llvm@${MCPP_LLVM_VER}"
          echo "MCPP=$MCPP" >> "$GITHUB_ENV"
          set -o pipefail
          bash tests/e2e/run_all.sh 2>&1 | tee "$RUNNER_TEMP/e2e-suite.log"

      # One file, no glob: the report the e2e-coverage job of ci.yml reads. A
      # glob upload once hung a macOS job for ten minutes, and cancelling it lost
      # the job's whole log.
      - name: Upload the shard's report
        if: always()
        timeout-minutes: 5
        uses: actions/upload-artifact@v4
        with:
          name: e2e-report-${{ matrix.image == 'macos-15' && 'macos' || matrix.image }}-${{ matrix.shard }}
          path: e2e-report-${{ matrix.image == 'macos-15' && 'macos' || matrix.image }}-${{ matrix.shard }}.tsv
          if-no-files-found: warn
          retention-days: 7

      # Measurement legs print READING lines and pass whatever they read; the
      # readings are what a decision is taken from (#646 F2: whether a C++
      # exception thrown in a dylib is caught by its class under the payload's
      # default runtime), so they are collected where a reader finds them.
      - name: Measurement readings
        if: always()
        shell: bash
        run: |
          {
            echo "### Measurement readings (macOS)"
            echo '```'
            grep -h '^READING' "$RUNNER_TEMP/e2e-suite.log" 2>/dev/null || echo "(none)"
            echo '```'
          } >> "$GITHUB_STEP_SUMMARY"

      # #647 E3: an Android row links on a macOS host. Its own step, because the
      # NDK is a large download the suite's per-test bound does not allow for,
      # and the shard does not carry it (the script declares android-ndk).
      - name: "Android row on a macOS host (721)"
        # Once per image, not once per shard: the step installs the NDK.
        if: matrix.shard == 1  # ci-lint: allow-r1: one NDK install per image; the shards share it
        timeout-minutes: 30
        shell: bash
        run: |
          set -o pipefail
          export MCPP_VENDORED_XLINGS="$XLINGS_BIN"
          export MCPP_E2E_TOOLCHAIN_MIRROR=GLOBAL
          "$MCPP" toolchain install android-ndk@30.0.16248370
          bash tests/e2e/721_*.sh 2>&1 | tee "$RUNNER_TEMP/721.log"
          grep -q '^PASS: 721' "$RUNNER_TEMP/721.log"