name: Validate Training Data

on:
  pull_request:
    paths:
      - 'training/data/**/*.jsonl'
      - 'training/data/**/schema.json'
      - 'training-data/*.jsonl'
      - 'training-data/schema.json'
      - 'scripts/validate-scene-data.py'

jobs:
  validate:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4

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

      - name: Validate scene descriptions (training-data/)
        run: |
          python3 scripts/validate-scene-data.py training-data/scene-descriptions-*.jsonl

      - name: Validate scene descriptions (training/data/)
        run: |
          cd training/data/scene-descriptions
          python3 validate.py *.jsonl