.github/workflows/evaluation.yml

name: Evaluation Run

on:
  workflow_dispatch: {}

jobs:
  run-evaluation:
    runs-on: ubuntu-latest
    steps:
      - name: Check out
        uses: actions/checkout@v4

      - name: Set up Python
        uses: actions/setup-python@v4
        with:
          python-version: "3.11"

      - name: Install dependencies
        run: |
          python -m pip install --upgrade pip
          if [ -f requirements.txt ]; then pip install -r requirements.txt; fi

      - name: Run evaluation and archive
        env:
          EVAL_TARGET_URL: ${{ secrets.EVAL_TARGET_URL }}
        run: |
          bash evaluation/run_and_archive.sh

      - name: Upload evaluation results
        uses: actions/upload-artifact@v4
        with:
          name: evaluation_results
          path: evaluation_results/