test.yml

name: test

on:
  workflow_dispatch:
  # `develop` is the integration branch, so it has to be here for two reasons. It is the
  # branch releases are cut from, and — less obviously — GitHub scopes the Actions cache
  # to a branch and its base. A pull request can only restore a cache written by its base
  # branch, so a workflow that never runs on `develop` writes no cache a pull request can
  # read, and every run starts cold.
  push:
    branches: [develop, main]
  pull_request:

concurrency:
  # Keep every run on the long-lived branches so cancelled checks do not pollute their
  # commit history. PRs and other branches share a group and cancel stale runs.
  group: >-
    ${{ (github.ref == 'refs/heads/develop' || github.ref == 'refs/heads/main')
        && format('{0}-{1}', github.workflow, github.run_id)
        || format('{0}-{1}', github.workflow, github.event.pull_request.number || github.ref) }}
  cancel-in-progress: true

permissions:
  contents: read
  checks: write

env:
  FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: true

# The engine suite is sharded across JOBS rather than parallelised across workers inside
# one. The suite contains tests whose assertion is "this finished within N milliseconds",
# so their budget is really a statement about machine load: `bun test --parallel` passed on
# a 16-core idle host and failed in CI, where four workers sharing a runner's cores pushed
# a 3s wait past a 5s ceiling. A shard gets a runner to itself, so per-test wall clock stays
# what it was serially and only the total divides. See docs/TEST-PARALLELISM.md.
#
# `unit (linux)` is an aggregator that does no work. It exists so the required status check
# keeps a stable name while the jobs underneath it change shape — renaming a required check
# in the same pull request that introduces it is a deadlock, because the check the rule
# demands never reports.

jobs:
  engine:
    name: engine (linux ${{ matrix.shard }}/4)
    runs-on: ubuntu-latest
    timeout-minutes: 20
    strategy:
      # Every shard reports. Cancelling siblings on the first failure hides how much else
      # is broken, which is the thing you want to know from a red run.
      fail-fast: false
      matrix:
        shard: [1, 2, 3, 4]
    defaults:
      run:
        shell: bash
    steps:
      - name: Checkout repository
        uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4.3.1

      - name: Setup Node
        uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020 # v4.4.0
        with:
          node-version: "24"

      - name: Setup Bun
        uses: ./.github/actions/setup-bun

      # The ripgrep tests resolve `rg` from PATH, then a cache dir, and only then download
      # it from github.com. Relying on that download made tests hang to the harness timeout
      # with nothing in the log naming the cause, so it is provisioned up front.
      - name: Provision ripgrep
        run: |
          sudo apt-get update -qq && sudo apt-get install -y -qq ripgrep
          rg --version | head -1

      - name: Configure git identity
        run: |
          git config --global user.email "bot@code.redrob.ai"
          git config --global user.name "redrob"

      - name: Run engine tests
        run: ./scripts/test-shard.sh packages/redrob ${{ matrix.shard }} 4
        env:
          REDROB_EXPERIMENTAL_DISABLE_FILEWATCHER: "false"

  core:
    name: core (linux)
    runs-on: ubuntu-latest
    timeout-minutes: 20
    defaults:
      run:
        shell: bash
    steps:
      - name: Checkout repository
        uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4.3.1

      - name: Setup Node
        uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020 # v4.4.0
        with:
          node-version: "24"

      - name: Setup Bun
        uses: ./.github/actions/setup-bun

      - name: Provision ripgrep
        run: |
          sudo apt-get update -qq && sudo apt-get install -y -qq ripgrep
          rg --version | head -1

      - name: Configure git identity
        run: |
          git config --global user.email "bot@code.redrob.ai"
          git config --global user.name "redrob"

      # Not sharded: 933 tests in ~22s. Splitting it would cost more in runner setup than
      # it saves.
      - name: Run core tests
        working-directory: packages/core
        run: bun test --timeout 30000 --only-failures

      - name: Check generated client
        working-directory: packages/client
        run: bun run check:generated

  httpapi:
    name: httpapi (linux)
    runs-on: ubuntu-latest
    timeout-minutes: 20
    defaults:
      run:
        shell: bash
    steps:
      - name: Checkout repository
        uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4.3.1

      - name: Setup Node
        uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020 # v4.4.0
        with:
          node-version: "24"

      - name: Setup Bun
        uses: ./.github/actions/setup-bun

      - name: Provision ripgrep
        run: |
          sudo apt-get update -qq && sudo apt-get install -y -qq ripgrep
          rg --version | head -1

      - name: Configure git identity
        run: |
          git config --global user.email "bot@code.redrob.ai"
          git config --global user.name "redrob"

      # Its own job rather than a step after the tests: ~1m38s that has no reason to sit
      # behind anything else.
      - name: Run HttpApi exerciser gates
        working-directory: packages/redrob
        run: bun run test:httpapi

  unit:
    name: unit (linux)
    needs: [engine, core, httpapi]
    # `always()` so a failing dependency still reports here rather than leaving the required
    # check permanently "expected" — a skipped required check never resolves and blocks the
    # pull request with no visible failure to fix.
    if: always()
    runs-on: ubuntu-latest
    steps:
      - name: Report
        run: |
          set -euo pipefail
          printf 'engine  %s\ncore    %s\nhttpapi %s\n' \
            "${{ needs.engine.result }}" "${{ needs.core.result }}" "${{ needs.httpapi.result }}"
          # A matrix dependency reports one aggregated result, so a single red shard makes
          # `needs.engine.result` a failure.
          for result in "${{ needs.engine.result }}" "${{ needs.core.result }}" "${{ needs.httpapi.result }}"; do
            if [ "$result" != "success" ]; then
              echo "::error::a linux test job did not succeed"
              exit 1
            fi
          done
          echo "all linux test jobs succeeded"

  windows:
    name: unit (windows ${{ matrix.shard }}/4)
    runs-on: windows-latest
    timeout-minutes: 25
    strategy:
      fail-fast: false
      matrix:
        shard: [1, 2, 3, 4]
    # Windows runs and reports, but does not block. Two path-normalization tests were failing
    # here for a real reason — a drive-less rooted path resolved against the runner's D:
    # workspace instead of the C: temp directory — and that is fixed; whether anything else is
    # Windows-specific is not yet established, so this stays advisory until it has been green
    # for a while.
    #
    # Sharded now, which the earlier diagnosis said not to do. That diagnosis was wrong: the
    # job was not hanging after its tests. Turbo buffers each task's output until the task
    # ends, so `core` flushing at 88s and `redrob` flushing 14 minutes later read as a stall.
    # The engine suite genuinely takes 906s here against 381s on Linux, which is what nearly
    # hit the 20-minute limit. Splitting it is the fix, and it is the same mechanism already
    # proven on Linux.
    continue-on-error: true
    defaults:
      run:
        shell: bash
    steps:
      - name: Checkout repository
        uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4.3.1

      - name: Setup Node
        uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020 # v4.4.0
        with:
          node-version: "24"

      - name: Setup Bun
        uses: ./.github/actions/setup-bun

      - name: Provision ripgrep
        run: |
          choco install ripgrep -y --no-progress
          rg --version | head -1

      - name: Configure git identity
        run: |
          git config --global user.email "bot@code.redrob.ai"
          git config --global user.name "redrob"

      - name: Run engine tests
        run: ./scripts/test-shard.sh packages/redrob ${{ matrix.shard }} 4
        env:
          REDROB_EXPERIMENTAL_DISABLE_FILEWATCHER: "true"

  windows-core:
    name: unit (windows core)
    runs-on: windows-latest
    timeout-minutes: 25
    continue-on-error: true
    defaults:
      run:
        shell: bash
    steps:
      - name: Checkout repository
        uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4.3.1

      - name: Setup Node
        uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020 # v4.4.0
        with:
          node-version: "24"

      - name: Setup Bun
        uses: ./.github/actions/setup-bun

      - name: Provision ripgrep
        run: |
          choco install ripgrep -y --no-progress
          rg --version | head -1

      - name: Configure git identity
        run: |
          git config --global user.email "bot@code.redrob.ai"
          git config --global user.name "redrob"

      - name: Run core tests
        working-directory: packages/core
        run: bun test --timeout 30000 --only-failures
        env:
          REDROB_EXPERIMENTAL_DISABLE_FILEWATCHER: "true"