sync-hf.yml

name: Sync to HuggingFace

on:
  push:
    branches: [main]
    paths:
      - 'algorithmic/problems/**'
      - 'research/problems/**'
  release:
    types: [published]
  workflow_dispatch:  # Allow manual trigger

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

      - uses: actions/setup-python@v5
        with:
          python-version: '3.12'

      - name: Install huggingface_hub
        run: pip install huggingface_hub

      - name: Export dataset
        run: python scripts/export_hf_dataset.py

      - name: Upload to HuggingFace
        run: |
          python -c "
          from huggingface_hub import HfApi, CommitOperationAdd
          import os
          from pathlib import Path

          api = HfApi(token=os.environ['HF_TOKEN'])

          # Collect all files for single commit
          operations = []

          # Add data files
          data_dir = Path('hf_export/data')
          for f in data_dir.iterdir():
              operations.append(CommitOperationAdd(
                  path_in_repo=f'data/{f.name}',
                  path_or_fileobj=str(f)
              ))

          # Add README
          operations.append(CommitOperationAdd(
              path_in_repo='README.md',
              path_or_fileobj='hf_export/README.md'
          ))

          # Single commit with all files
          api.create_commit(
              repo_id='FrontierCS/Frontier-CS',
              repo_type='dataset',
              operations=operations,
              commit_message='Update dataset'
          )
          print(f'Uploaded {len(operations)} files')
          "
        env:
          HF_TOKEN: ${{ secrets.HF_TOKEN }}