solver/.gitea/workflows/ci.yaml

name: CI

on:
  push:
    branches: [main]
  pull_request:
    branches: [main]
  workflow_dispatch:
    inputs:
      run_datagen:
        description: "Run dataset generation"
        required: false
        type: boolean
        default: false
      num_assemblies:
        description: "Number of assemblies to generate"
        required: false
        type: string
        default: "100000"
      num_workers:
        description: "Parallel workers for datagen"
        required: false
        type: string
        default: "4"

env:
  PIP_CACHE_DIR: /tmp/pip-cache-solver
  TORCH_INDEX: https://download.pytorch.org/whl/cpu
  VIRTUAL_ENV: /tmp/solver-venv

jobs:
  # ---------------------------------------------------------------------------
  # Lint — fast, no torch required
  # ---------------------------------------------------------------------------
  lint:
    runs-on: ubuntu-latest
    env:
      PATH: /tmp/solver-venv/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin
    steps:
      - name: Trust internal CA
        run: |
          curl -sk https://ipa.kindred.internal/ipa/config/ca.crt \
            -o /usr/local/share/ca-certificates/kindred-internal.crt
          update-ca-certificates

      - name: Checkout
        uses: https://github.com/actions/checkout@v4

      - name: Set up venv
        run: python3 -m venv $VIRTUAL_ENV

      - name: Install lint tools
        run: pip install --cache-dir $PIP_CACHE_DIR ruff

      - name: Ruff check
        run: ruff check solver/ freecad/ tests/ scripts/

      - name: Ruff format check
        run: ruff format --check solver/ freecad/ tests/ scripts/

  # ---------------------------------------------------------------------------
  # Type check
  # ---------------------------------------------------------------------------
  type-check:
    runs-on: ubuntu-latest
    env:
      PATH: /tmp/solver-venv/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin
    steps:
      - name: Trust internal CA
        run: |
          curl -sk https://ipa.kindred.internal/ipa/config/ca.crt \
            -o /usr/local/share/ca-certificates/kindred-internal.crt
          update-ca-certificates

      - name: Checkout
        uses: https://github.com/actions/checkout@v4

      - name: Set up venv
        run: python3 -m venv $VIRTUAL_ENV

      - name: Install dependencies
        run: |
          pip install --cache-dir $PIP_CACHE_DIR \
            mypy numpy scipy \
            torch --index-url $TORCH_INDEX
          pip install --cache-dir $PIP_CACHE_DIR torch-geometric
          pip install --cache-dir $PIP_CACHE_DIR -e ".[dev]"

      - name: Mypy
        run: mypy solver/ freecad/

  # ---------------------------------------------------------------------------
  # Tests
  # ---------------------------------------------------------------------------
  test:
    runs-on: ubuntu-latest
    env:
      PATH: /tmp/solver-venv/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin
    steps:
      - name: Trust internal CA
        run: |
          curl -sk https://ipa.kindred.internal/ipa/config/ca.crt \
            -o /usr/local/share/ca-certificates/kindred-internal.crt
          update-ca-certificates

      - name: Checkout
        uses: https://github.com/actions/checkout@v4

      - name: Set up venv
        run: python3 -m venv $VIRTUAL_ENV

      - name: Install dependencies
        run: |
          pip install --cache-dir $PIP_CACHE_DIR \
            torch --index-url $TORCH_INDEX
          pip install --cache-dir $PIP_CACHE_DIR torch-geometric
          pip install --cache-dir $PIP_CACHE_DIR -e ".[train,dev]"

      - name: Run tests
        run: pytest tests/ freecad/tests/ -v --tb=short

  # ---------------------------------------------------------------------------
  # Dataset generation — manual trigger or on main push
  # ---------------------------------------------------------------------------
  datagen:
    runs-on: ubuntu-latest
    if: >-
      (github.event_name == 'workflow_dispatch' && inputs.run_datagen == true) ||
      (github.event_name == 'push' && github.ref == 'refs/heads/main')
    needs: [test]
    env:
      PATH: /tmp/solver-venv/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin
    steps:
      - name: Trust internal CA
        run: |
          curl -sk https://ipa.kindred.internal/ipa/config/ca.crt \
            -o /usr/local/share/ca-certificates/kindred-internal.crt
          update-ca-certificates

      - name: Checkout
        uses: https://github.com/actions/checkout@v4

      - name: Set up venv
        run: python3 -m venv $VIRTUAL_ENV

      - name: Install dependencies
        run: |
          pip install --cache-dir $PIP_CACHE_DIR \
            torch --index-url $TORCH_INDEX
          pip install --cache-dir $PIP_CACHE_DIR torch-geometric
          pip install --cache-dir $PIP_CACHE_DIR -e ".[train]"

      - name: Restore datagen checkpoint
        id: datagen-cache
        uses: https://github.com/actions/cache/restore@v4
        with:
          path: data/synthetic
          key: datagen-${{ github.sha }}
          restore-keys: |
            datagen-

      - name: Generate dataset
        run: |
          NUM=${INPUTS_NUM_ASSEMBLIES:-100000}
          WORKERS=${INPUTS_NUM_WORKERS:-4}
          echo "Generating ${NUM} assemblies with ${WORKERS} workers"
          python3 scripts/generate_synthetic.py \
            --num-assemblies "${NUM}" \
            --num-workers "${WORKERS}" \
            --output-dir data/synthetic
        env:
          INPUTS_NUM_ASSEMBLIES: ${{ inputs.num_assemblies }}
          INPUTS_NUM_WORKERS: ${{ inputs.num_workers }}

      - name: Save datagen checkpoint
        if: always()
        uses: https://github.com/actions/cache/save@v4
        with:
          path: data/synthetic
          key: datagen-${{ github.sha }}

      - name: Upload dataset
        uses: https://github.com/actions/upload-artifact@v3
        with:
          name: synthetic-dataset
          path: |
            data/synthetic/index.json
            data/synthetic/stats.json
            data/synthetic/shards/
          retention-days: 90

      - name: Print summary
        if: always()
        run: |
          echo "=== Dataset Generation Results ==="
          if [ -f data/synthetic/stats.json ]; then
            python3 -c "
          import json
          with open('data/synthetic/stats.json') as f:
              s = json.load(f)
          print(f'Total examples: {s[\"total_examples\"]}')
          print(f'Classification: {json.dumps(s[\"classification_distribution\"], indent=2)}')
          print(f'Rigid: {s[\"rigidity\"][\"rigid_fraction\"]*100:.1f}%')
          print(f'Degeneracy: {s[\"geometric_degeneracy\"][\"fraction_with_degeneracy\"]*100:.1f}%')
          "
          else
            echo "stats.json not found — generation may have failed"
            ls -la data/synthetic/ 2>/dev/null || echo "output dir missing"
          fi