regression-tests.yml

# Regression Tests Workflow
# This workflow runs the NNV test suite with baseline comparison to detect regressions
# It runs separately from the main CI workflow to provide detailed regression analysis

name: Regression Tests

on:
  # Run on pull requests to master
  pull_request:
    branches: [ "master" ]

  # Allow manual triggering
  workflow_dispatch:
    inputs:
      update_baselines:
        description: 'Update baselines after tests'
        required: false
        default: false
        type: boolean
      run_cp:
        type: boolean
        required: false
        default: false

env:
  # Opt JS actions into Node 24 ahead of GitHub's forced 2026-06-16 default flip (Node 20
  # EOL on the runners), so any incompatibility surfaces in CI now rather than mid-competition.
  FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: 'true'

jobs:
  regression-test:
    runs-on: ubuntu-latest

    steps:
      - name: Checkout repository
        uses: actions/checkout@v4
        with:
          submodules: 'true'

      - name: Reclaim runner disk space
        # Free ~20-30 GB of preinstalled tooling so the ~5 GB MATLAB toolbox download
        # can't exhaust the runner disk ("No space left on device"). See test-matrix.yml.
        run: |
          echo "Disk before reclaim:"; df -h /
          sudo rm -rf /usr/share/dotnet /opt/ghc /usr/local/.ghcup /usr/local/lib/android \
                      /usr/share/swift /usr/local/share/powershell \
                      /opt/hostedtoolcache/CodeQL /usr/local/share/chromium /usr/local/share/boost || true
          sudo docker image prune --all --force >/dev/null 2>&1 || true
          echo "Disk after reclaim:"; df -h /

      - name: Setup MATLAB
        uses: matlab-actions/setup-matlab@v3
        with:
          release: R2024b
          products: >
            Computer_Vision_Toolbox
            Control_System_Toolbox
            Deep_Learning_Toolbox
            Image_Processing_Toolbox
            Optimization_Toolbox
            Parallel_Computing_Toolbox
            Statistics_and_Machine_Learning_Toolbox
            Symbolic_Math_Toolbox
            System_Identification_Toolbox
            Deep_Learning_Toolbox_Converter_for_ONNX_Model_Format
            Deep_Learning_Toolbox_Converter_for_PyTorch_Model_Format
            Deep_Learning_Toolbox_Converter_for_TensorFlow_models

      - name: Setup Python for CP
        uses: actions/setup-python@v5
        with:
          python-version: '3.12'

      - name: Install Python requirements
        if: github.event.inputs.run_cp == 'true'
        run: |
          python3 -m venv .venv
          source .venv/bin/activate
          pip install --upgrade pip
          pip install -r requirement.txt
        continue-on-error: true

      # Cache the tbxmanager toolboxes (MPT/glpk/sedumi/etc.) install.m downloads from the
      # ETH/tbxmanager server. OS/arch-keyed, MATLAB-release-independent; shared with the
      # matrix + legacy CI. startup_nnv's `tbxmanager restorepath` re-adds them, so a warm
      # cache turns install.m's downloads into no-ops. Restore/save split so we only persist a
      # COMPLETE install (gated on the last toolbox, sedumi), never a partial flaky download.
      # Force-refresh: run "CI (matrix-sharded)" with rebuild_cache=true (deletes
      # the repo-wide nnv-tbxmanager-* cache).
      - name: Restore NNV tbxmanager toolboxes
        id: tbxcache
        uses: actions/cache/restore@v4
        with:
          path: code/nnv/tbxmanager
          key: nnv-tbxmanager-${{ runner.os }}-${{ hashFiles('code/nnv/install.m') }}
          restore-keys: |
            nnv-tbxmanager-${{ runner.os }}-

      - name: Run regression tests
        uses: matlab-actions/run-command@v2
        env:
          NNV_TEST_COMPARE_BASELINES: '1'
          NNV_TEST_FAIL_ON_REGRESSION: '1'
        with:
          command: |
            disp('=== NNV Regression Test Suite ===');
            cd("code/nnv");
            install;

            % Add test utilities to path
            addpath(fullfile(pwd, 'tests', 'test_utils'));

            % Run tests with regression detection
            try
                [test_results, regression_results] = run_tests_with_regression("compare", true, "verbose", true);

                % Check for failures
                if ~isempty(test_results)
                    n_failed = sum([test_results.Failed]);
                    if n_failed > 0
                        error('Test failures detected: %d tests failed', n_failed);
                    end
                end

                % Check for regressions
                if isfield(regression_results, 'regressions') && ~isempty(regression_results.regressions)
                    error('Regressions detected: %d baseline mismatches', length(regression_results.regressions));
                end

                disp('All tests passed, no regressions detected.');
            catch ME
                disp(['Error: ' ME.message]);
                rethrow(ME);
            end

      - name: Save NNV tbxmanager cache (only a COMPLETE install, only on a miss)
        if: always() && steps.tbxcache.outputs.cache-hit != 'true' && hashFiles('code/nnv/tbxmanager/toolboxes/sedumi/**') != ''
        uses: actions/cache/save@v4
        with:
          path: code/nnv/tbxmanager
          key: nnv-tbxmanager-${{ runner.os }}-${{ hashFiles('code/nnv/install.m') }}

      - name: Upload test results
        if: always()
        uses: actions/upload-artifact@v4
        with:
          name: test-results
          path: |
            results/tests/data/
            results/tests/figures/
          retention-days: 30

      - name: Update baselines (manual trigger only)
        if: github.event_name == 'workflow_dispatch' && github.event.inputs.update_baselines == 'true'
        uses: matlab-actions/run-command@v2
        with:
          command: |
            cd("code/nnv");
            install;
            addpath(fullfile(pwd, 'tests', 'test_utils'));
            manage_baselines('save');
            disp('Baselines updated successfully.');

      - name: Commit updated baselines
        if: github.event_name == 'workflow_dispatch' && github.event.inputs.update_baselines == 'true'
        run: |
          git config --local user.email "action@github.com"
          git config --local user.name "GitHub Action"
          git add results/tests/baselines/
          git diff --staged --quiet || git commit -m "Update test baselines [skip ci]"
          git push