solvecraft/.github/workflows/kernel-rig.yml

# The kernel rig and the complexity ladder as a regression gate. A plan job maps a pull request's
# changed files to the rig areas they can affect (scripts/ci/kernel_rig_plan.py): an area runs
# when a file its tests/kernel-cases/<area>/PATHS lists changes, or one of its cases; every area
# runs when the shared core in tests/kernel-cases/PATHS-ALL changes; the ladder runs whenever any
# area does. One job then builds solidcraft-cli once (release, SMLib prebuilt), checks that every
# registry command has a case or an exemption (tests/kernel-cases/EXEMPT), and hands the CLI to a
# matrix of shards as an artifact, one per selected area plus the ladder, in parallel, so the
# wall time is the build plus the slowest shard. See tests/kernel-cases/README.md.
#
# - An area fails on a regression (a case that fails and its tests/kernel-cases/<area>/KNOWN_FAILING
#   does not list) or on a listed case that passes (it is fixed: remove its line in the same pull
#   request, so the list only shrinks).
# - The ladder fails on any case whose status or counts differ from
#   tests/kernel-cases/ladder/golden.json; a right change is re-recorded (`--record "why"`).
#
# The trigger paths are whole folders that hold every area's PATHS (a self-test,
# scripts/ci/test_kernel_rig_plan.py, checks they do), so a pull request that touches none of
# them (the UI, docs, packaging) starts no runner at all, and a new area needs no edit here: the
# plan finds the areas from the folders. Pushes to main and develop on the same paths, merge groups
# (once the queue is on), the release gate (release-gate.yml, workflow_call) and a run by hand run
# every area; those pushes also commit the compiler cache (a Blacksmith sticky disk) that every
# other run mounts read-only.
name: Kernel rig

on:
  pull_request:
    types: [opened, synchronize, reopened, ready_for_review]
    paths:
      - "crates/kernel/**"
      - "crates/geom/**"
      - "crates/smlib/**"
      - "crates/step/**"
      - "crates/io/src/**"
      - "crates/doc/src/**"
      - "crates/engine/src/**"
      - "tests/kernel-cases/**"
      # The rig itself: the grading, the runner, the selection and this workflow.
      - "apps/solidcraft-cli/src/kernel_cases.rs"
      - "xtask/src/kernel_cases.rs"
      - "xtask/src/kernel_ladder.rs"
      - "scripts/fetch-smlib.sh"
      - "scripts/ci/kernel_rig_plan.py"
      - "scripts/ci/test_kernel_rig_plan.py"
      - ".github/workflows/kernel-rig.yml"
  push:
    branches: [main, develop]
    # The same paths as pull_request.
    paths:
      - "crates/kernel/**"
      - "crates/geom/**"
      - "crates/smlib/**"
      - "crates/step/**"
      - "crates/io/src/**"
      - "crates/doc/src/**"
      - "crates/engine/src/**"
      - "tests/kernel-cases/**"
      # The rig itself: the grading, the runner, the selection and this workflow.
      - "apps/solidcraft-cli/src/kernel_cases.rs"
      - "xtask/src/kernel_cases.rs"
      - "xtask/src/kernel_ladder.rs"
      - "scripts/fetch-smlib.sh"
      - "scripts/ci/kernel_rig_plan.py"
      - "scripts/ci/test_kernel_rig_plan.py"
      - ".github/workflows/kernel-rig.yml"
  merge_group:
  workflow_call:
  workflow_dispatch:

permissions:
  contents: read

concurrency:
  # A new push to a pull request replaces its old run.
  group: kernel-rig-${{ github.event_name }}-${{ github.ref }}
  cancel-in-progress: ${{ github.event_name == 'pull_request' }}

env:
  CARGO_TERM_COLOR: always

jobs:
  plan:
    name: Select the rig areas
    # Draft pull requests run no CI, as in ci.yml.
    if: github.event_name != 'pull_request' || !github.event.pull_request.draft
    runs-on: blacksmith-2vcpu-ubuntu-2404
    timeout-minutes: 5
    outputs:
      # The shard matrix (JSON list of areas and the ladder; [] when nothing is selected).
      shards: ${{ steps.plan.outputs.shards }}
      # Whether the build job, and with it the coverage check, runs.
      build: ${{ steps.plan.outputs.build }}
    steps:
      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
        with:
          # A pull request's diff needs its base's history.
          fetch-depth: ${{ github.event_name == 'pull_request' && '0' || '1' }}
      - name: Selection self-test
        run: python3 -I scripts/ci/test_kernel_rig_plan.py
      - id: plan
        name: Map the changed files to areas
        env:
          EVENT_NAME: ${{ github.event_name }}
          BASE_SHA: ${{ github.event.pull_request.base.sha }}
          HEAD_SHA: ${{ github.event.pull_request.head.sha }}
        run: |
          # Pull requests run the areas their diff reaches; pushes, merge groups, the release
          # gate and a run by hand run every area.
          if [ "$EVENT_NAME" = pull_request ]; then
            git diff --no-renames --name-only -z "$BASE_SHA...$HEAD_SHA" > "$RUNNER_TEMP/rig-paths"
            python3 -I scripts/ci/kernel_rig_plan.py --paths "$RUNNER_TEMP/rig-paths" --github-output "$GITHUB_OUTPUT"
          else
            python3 -I scripts/ci/kernel_rig_plan.py --all --github-output "$GITHUB_OUTPUT"
          fi

  build:
    name: Build the CLI
    needs: plan
    if: needs.plan.outputs.build == 'true'
    runs-on: blacksmith-8vcpu-ubuntu-2404
    timeout-minutes: 60
    env:
      CARGO_INCREMENTAL: "0"
      RUSTC_WRAPPER: sccache
      SCCACHE_DIR: /home/runner/.cache/sccache
      SCCACHE_CACHE_SIZE: 10G
    steps:
      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
      - name: Size parallel compiles to the job's memory
        run: scripts/ci/build-jobs.sh
      - uses: dtolnay/rust-toolchain@stable
      # Only pushes to main and develop commit the cache; pull requests, merge groups and forks
      # mount a clone and never write back.
      - name: Mount the compiler cache
        uses: useblacksmith/stickydisk@3f6be1451e3cad893b778bc93495c80452a5da26 # v1.7.2
        continue-on-error: true
        with:
          key: ${{ github.repository }}-sccache-kernel-rig
          path: /home/runner/.cache/sccache
          commit: ${{ github.event_name == 'push' && (github.ref == 'refs/heads/main' || github.ref == 'refs/heads/develop') && 'on-change' || 'false' }}
      - uses: Swatinem/rust-cache@6323deb102c322ba6fcbdcafc7e3dddab59af2b6 # v2.9.2
        with:
          key: kernel-rig
          save-if: ${{ github.event_name == 'push' && (github.ref == 'refs/heads/main' || github.ref == 'refs/heads/develop') }}
      - name: Fetch SMLib (crates/smlib/SMLIB_REV)
        shell: bash
        run: scripts/fetch-smlib.sh
      - name: Set up compiler cache
        uses: mozilla-actions/sccache-action@fc920bf0ec8de6ee65d409111f7ec508035751ba # v0.0.11
        with:
          version: v0.16.0
      - name: Build the CLI (release, SMLib) and the rig's runner
        run: |
          cargo build --release --locked -p solidcraft-cli --features smlib
          cargo build --locked -p xtask
      # A tar keeps the executable bits, which an artifact drops. xtask finds the repository from
      # the path it was built in (CARGO_MANIFEST_DIR), which is the same checkout path in every
      # job of this workflow.
      # Every registry command is used by a case or listed in tests/kernel-cases/EXEMPT.
      - name: Every command has a case
        run: target/debug/xtask kernel-cases --coverage --cli target/release/solidcraft-cli
      # A coverage-only run (the registry or the cases changed, no area selected) runs no shard.
      - name: Pack the binaries
        if: needs.plan.outputs.shards != '[]'
        run: tar -cf "$RUNNER_TEMP/kernel-rig-bin.tar" -C target release/solidcraft-cli debug/xtask
      - uses: actions/upload-artifact@cf430e030ddbb5b0abf93d22962f4752f3646cd9 # v7.0.2
        if: needs.plan.outputs.shards != '[]'
        with:
          name: kernel-rig-bin
          path: ${{ runner.temp }}/kernel-rig-bin.tar
          retention-days: 1
      - name: Compiler cache statistics
        if: always()
        run: sccache --show-stats

  shard:
    name: Kernel rig (${{ matrix.shard }})
    needs: [plan, build]
    if: needs.plan.outputs.shards != '[]'
    runs-on: blacksmith-4vcpu-ubuntu-2404
    timeout-minutes: 30
    strategy:
      fail-fast: false
      matrix:
        # The areas of tests/kernel-cases/ the plan selected, and the ladder. On the build box
        # (aarch64, 4 cases at a time) the slowest areas took about 1 minute (booleans, 212 s of
        # cases with one of 84 s; threads, 161 s) and the ladder, one case at a time, 92 s: no area
        # needs splitting.
        shard: ${{ fromJSON(needs.plan.outputs.shards) }}
    steps:
      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
      - uses: actions/download-artifact@9000827ccba6bdab643e8b6fd33ac0654aef8333 # v8.0.2
        with:
          name: kernel-rig-bin
          path: ${{ runner.temp }}
      - name: Unpack the binaries
        run: mkdir -p target && tar -xf "$RUNNER_TEMP/kernel-rig-bin.tar" -C target
      - name: Run the cases against the known-failing list (the ladder against its golden)
        env:
          SHARD: ${{ matrix.shard }}
        run: |
          if [ "$SHARD" = ladder ]; then
            set -- --ladder --gate
          else
            set -- --area "$SHARD" --known-failing "tests/kernel-cases/$SHARD/KNOWN_FAILING"
          fi
          target/debug/xtask kernel-cases "$@" --cli target/release/solidcraft-cli --out "$RUNNER_TEMP/kernel-rig"
      - name: Keep the results
        if: always()
        uses: actions/upload-artifact@cf430e030ddbb5b0abf93d22962f4752f3646cd9 # v7.0.2
        with:
          name: kernel-rig-results-${{ matrix.shard }}
          path: ${{ runner.temp }}/kernel-rig/results.json
          if-no-files-found: ignore

  # One check for the whole gate, for branch protection and the merge queue.
  kernel-rig:
    name: kernel-rig
    needs: [plan, build, shard]
    if: always() && (github.event_name != 'pull_request' || !github.event.pull_request.draft)
    runs-on: blacksmith-2vcpu-ubuntu-2404
    steps:
      # A skipped build or shard counts as passed only when the plan selected none.
      - name: Every selected job passed
        env:
          PLAN: ${{ needs.plan.result }}
          WANT_BUILD: ${{ needs.plan.outputs.build }}
          WANT_SHARDS: ${{ needs.plan.outputs.shards }}
          BUILD: ${{ needs.build.result }}
          SHARDS: ${{ needs.shard.result }}
        run: |
          echo "plan=$PLAN build=$BUILD shards=$SHARDS selected=$WANT_SHARDS"
          test "$PLAN" = success
          if [ "$WANT_BUILD" = true ]; then test "$BUILD" = success; else test "$BUILD" = skipped; fi
          if [ "$WANT_SHARDS" != '[]' ]; then test "$SHARDS" = success; else test "$SHARDS" = skipped; fi