nightly.yml

# SPDX-License-Identifier: AGPL-3.0-or-later
name: Nightly Tests

# Nightly workflow runs expensive cross-Python and integration tests.
# Results are recorded as commit statuses so release.yml can skip them
# when the release SHA was already covered by nightly.

on:
  schedule:
    - cron: '30 5 * * *'  # 5:30 AM UTC daily
  workflow_dispatch:

concurrency:
  group: nightly-singleton
  cancel-in-progress: false

jobs:
  # ─────────────────────────────────────────────────────────────
  # Test matrix (Python versions on Linux)
  # Uses container images to guarantee Python availability —
  # setup-python@v5 can't find pre-built binaries for Debian 12
  # (the versions manifest only ships Ubuntu builds).
  # ─────────────────────────────────────────────────────────────
  test-matrix:
    strategy:
      matrix:
        python-version: ['3.10', '3.11', '3.12', '3.13']
      fail-fast: false

    runs-on: self-hosted
    container: python:${{ matrix.python-version }}-bookworm
    timeout-minutes: 15
    env:
      SEGMENT_DOWNLOAD_TIMEOUT_MINS: "1"

    steps:
      # Forgejo runner needs Node.js in the container to execute
      # JS-based actions. python:*-bookworm images don't ship it.
      - name: Install Node.js for JS-based actions
        run: apt-get update && apt-get install -y nodejs

      - uses: actions/checkout@v4

      - name: Install dependencies
        run: |
          pip install --upgrade pip
          if [ -d "packages/hypergumbo-core" ]; then
            pip install -e packages/hypergumbo-core \
                        -e packages/hypergumbo-lang-mainstream \
                        -e packages/hypergumbo-lang-common \
                        -e packages/hypergumbo-lang-extended1 \
                        -e packages/hypergumbo-lang-rust-analyzer \
                        -e "packages/hypergumbo-tracker[dev,tui]" \
                        -e packages/hypergumbo \
                        jsonschema
          else
            pip install -e .[dev]
          fi

      - name: Build source-only grammars
        run: ./scripts/build-source-grammars

      - name: Check for sentence-transformers
        run: |
          if python -c "import sentence_transformers" 2>/dev/null; then
            echo "sentence-transformers available"
            echo "EMBEDDINGS_AVAILABLE=true" >> "$GITHUB_ENV"
          else
            echo "sentence-transformers not installed, embedding tests will be skipped"
            echo "EMBEDDINGS_AVAILABLE=false" >> "$GITHUB_ENV"
          fi

      - name: Run tests with coverage
        run: |
          if [ -d "packages/hypergumbo-core" ]; then
            COV_PATHS="--cov=packages/hypergumbo-core/src --cov=packages/hypergumbo-lang-mainstream/src --cov=packages/hypergumbo-lang-common/src --cov=packages/hypergumbo-lang-extended1/src --cov=packages/hypergumbo-lang-rust-analyzer/src --cov=packages/hypergumbo-tracker/src"
            TEST_PATHS="packages/*/tests/"
          else
            COV_PATHS="--cov=src"
            TEST_PATHS=""
          fi

          # Detect available CPUs from cgroup limits
          if [ -f /sys/fs/cgroup/cpu.max ]; then
            read quota period < /sys/fs/cgroup/cpu.max
            if [ "$quota" != "max" ]; then
              WORKERS=$((quota / period))
            else
              WORKERS=$(nproc)
            fi
          else
            WORKERS=$(nproc)
          fi

          if [ "$EMBEDDINGS_AVAILABLE" = "true" ]; then
            pytest -n "$WORKERS" $COV_PATHS --cov-report=term-missing --cov-fail-under=100 $TEST_PATHS
          else
            pytest -n "$WORKERS" $COV_PATHS --cov-report=term-missing --cov-fail-under=100 \
              --cov-config=.coveragerc.no-embeddings $TEST_PATHS
          fi

      - name: Mark version as passed
        if: success()
        run: |
          mkdir -p /tmp/matrix-result
          echo "passed" > /tmp/matrix-result/py${{ matrix.python-version }}

      - name: Upload pass marker
        if: success()
        uses: actions/upload-artifact@v3
        with:
          name: matrix-pass-py${{ matrix.python-version }}
          path: /tmp/matrix-result/py${{ matrix.python-version }}
          retention-days: 1

  # ─────────────────────────────────────────────────────────────
  # Test matrix retry (handles transient infra failures)
  # Only retries Python versions where the primary job failed.
  # ─────────────────────────────────────────────────────────────
  test-matrix-retry:
    needs: [test-matrix]
    if: >-
      always() &&
      (needs.test-matrix.result == 'failure' || needs.test-matrix.result == 'cancelled')
    strategy:
      matrix:
        python-version: ['3.10', '3.11', '3.12', '3.13']
      fail-fast: false

    runs-on: self-hosted
    container: python:${{ matrix.python-version }}-bookworm
    timeout-minutes: 15
    env:
      SEGMENT_DOWNLOAD_TIMEOUT_MINS: "1"

    steps:
      # Forgejo runner needs Node.js in the container to execute JS-based
      # actions like `actions/download-artifact@v3`. python:*-bookworm
      # images don't ship it. This MUST precede the download-artifact
      # step — if Node isn't on PATH, download-artifact fails with
      # `OCI runtime exec failed ... exec: "node": executable file not
      # found` under `continue-on-error: true`, the pass-marker file is
      # never written, and the skip-check then incorrectly reports
      # "Primary job failed ... retrying" for every Python version.
      # Observed 2026-04-21 on a nightly where the primary 3.10/3.11
      # passed but their retry ran anyway. The primary test-matrix job
      # solves this the same way (step "Install Node.js for JS-based
      # actions" at the top).
      - name: Install Node.js for JS-based actions
        run: apt-get update && apt-get install -y nodejs

      - name: Download pass marker
        id: check-primary
        uses: actions/download-artifact@v3
        with:
          name: matrix-pass-py${{ matrix.python-version }}
          path: /tmp/matrix-result
        continue-on-error: true

      - name: Skip if primary passed
        id: skip-check
        run: |
          if [ -f /tmp/matrix-result/py${{ matrix.python-version }} ]; then
            echo "Primary job passed for Python ${{ matrix.python-version }} — skipping retry"
            echo "should_skip=true" >> "$GITHUB_OUTPUT"
          else
            echo "Primary job failed for Python ${{ matrix.python-version }} — retrying"
            echo "should_skip=false" >> "$GITHUB_OUTPUT"
          fi

      - uses: actions/checkout@v4
        if: steps.skip-check.outputs.should_skip != 'true'

      - name: Install dependencies
        if: steps.skip-check.outputs.should_skip != 'true'
        run: |
          pip install --upgrade pip
          if [ -d "packages/hypergumbo-core" ]; then
            pip install -e packages/hypergumbo-core \
                        -e packages/hypergumbo-lang-mainstream \
                        -e packages/hypergumbo-lang-common \
                        -e packages/hypergumbo-lang-extended1 \
                        -e packages/hypergumbo-lang-rust-analyzer \
                        -e "packages/hypergumbo-tracker[dev,tui]" \
                        -e packages/hypergumbo \
                        jsonschema
          else
            pip install -e .[dev]
          fi

      - name: Build source-only grammars
        if: steps.skip-check.outputs.should_skip != 'true'
        run: ./scripts/build-source-grammars

      - name: Check for sentence-transformers
        if: steps.skip-check.outputs.should_skip != 'true'
        run: |
          if python -c "import sentence_transformers" 2>/dev/null; then
            echo "sentence-transformers available"
            echo "EMBEDDINGS_AVAILABLE=true" >> "$GITHUB_ENV"
          else
            echo "sentence-transformers not installed, embedding tests will be skipped"
            echo "EMBEDDINGS_AVAILABLE=false" >> "$GITHUB_ENV"
          fi

      - name: Run tests with coverage
        if: steps.skip-check.outputs.should_skip != 'true'
        run: |
          if [ -d "packages/hypergumbo-core" ]; then
            COV_PATHS="--cov=packages/hypergumbo-core/src --cov=packages/hypergumbo-lang-mainstream/src --cov=packages/hypergumbo-lang-common/src --cov=packages/hypergumbo-lang-extended1/src --cov=packages/hypergumbo-lang-rust-analyzer/src --cov=packages/hypergumbo-tracker/src"
            TEST_PATHS="packages/*/tests/"
          else
            COV_PATHS="--cov=src"
            TEST_PATHS=""
          fi

          # Detect available CPUs from cgroup limits
          if [ -f /sys/fs/cgroup/cpu.max ]; then
            read quota period < /sys/fs/cgroup/cpu.max
            if [ "$quota" != "max" ]; then
              WORKERS=$((quota / period))
            else
              WORKERS=$(nproc)
            fi
          else
            WORKERS=$(nproc)
          fi

          if [ "$EMBEDDINGS_AVAILABLE" = "true" ]; then
            pytest -n "$WORKERS" $COV_PATHS --cov-report=term-missing --cov-fail-under=100 $TEST_PATHS
          else
            pytest -n "$WORKERS" $COV_PATHS --cov-report=term-missing --cov-fail-under=100 \
              --cov-config=.coveragerc.no-embeddings $TEST_PATHS
          fi

  # ─────────────────────────────────────────────────────────────
  # Integration tests
  # ─────────────────────────────────────────────────────────────
  integration-tests:
    runs-on: self-hosted
    timeout-minutes: 30
    env:
      SEGMENT_DOWNLOAD_TIMEOUT_MINS: "1"

    steps:
      - uses: actions/checkout@v4

      - name: Set up Python
        uses: actions/setup-python@v5
        with:
          python-version: '3.11'

      - name: Install dependencies
        run: |
          pip install --upgrade pip
          if [ -d "packages/hypergumbo-core" ]; then
            pip install -e packages/hypergumbo-core \
                        -e packages/hypergumbo-lang-mainstream \
                        -e packages/hypergumbo-lang-common \
                        -e packages/hypergumbo-lang-extended1 \
                        -e packages/hypergumbo-lang-rust-analyzer \
                        -e packages/hypergumbo
          else
            pip install -e .[dev]
          fi

      - name: Build source-only grammars
        run: ./scripts/build-source-grammars

      - name: Install jq
        run: |
          sudo apt-get update && sudo apt-get install -y jq || true

      - name: Run integration tests
        run: ./scripts/integration-test --quick

  # ─────────────────────────────────────────────────────────────
  # Report results as commit statuses
  # ─────────────────────────────────────────────────────────────
  report:
    needs: [test-matrix, test-matrix-retry, integration-tests]
    if: always()
    runs-on: self-hosted

    steps:
      - name: Set commit statuses
        env:
          FORGEJO_TOKEN: ${{ secrets.FORGEJO_TOKEN }}
        run: |
          SHA="${{ github.sha }}"
          REPO="${{ github.repository }}"
          API="https://codeberg.org/api/v1/repos/${REPO}/statuses/${SHA}"

          if [ -z "$FORGEJO_TOKEN" ]; then
            echo "::warning::FORGEJO_TOKEN not set, skipping commit status updates"
            exit 0
          fi

          # test-matrix passes if primary OR retry succeeded
          MATRIX_STATE="failure"
          if [ "${{ needs.test-matrix.result }}" = "success" ] || \
             [ "${{ needs.test-matrix-retry.result }}" = "success" ]; then
            MATRIX_STATE="success"
          fi
          curl -s -X POST \
            -H "Authorization: token $FORGEJO_TOKEN" \
            -H "Content-Type: application/json" \
            -d "{
              \"state\": \"${MATRIX_STATE}\",
              \"context\": \"nightly/test-matrix\",
              \"description\": \"Nightly Python 3.10-3.13 test matrix\",
              \"target_url\": \"${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}\"
            }" \
            "$API"
          echo "Set nightly/test-matrix status: $MATRIX_STATE"

          # Report integration-tests status
          INTEGRATION_STATE="success"
          if [ "${{ needs.integration-tests.result }}" != "success" ]; then
            INTEGRATION_STATE="failure"
          fi
          curl -s -X POST \
            -H "Authorization: token $FORGEJO_TOKEN" \
            -H "Content-Type: application/json" \
            -d "{
              \"state\": \"${INTEGRATION_STATE}\",
              \"context\": \"nightly/integration-tests\",
              \"description\": \"Nightly integration tests\",
              \"target_url\": \"${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}\"
            }" \
            "$API"
          echo "Set nightly/integration-tests status: $INTEGRATION_STATE"