ci.yml

name: CI

on:
  push:
    branches: ["**"]
  pull_request:
    branches: ["**"]

env:
  # Pin hash seed so tests that guard against hash()-based seeding are
  # deterministic and correctly distinguish hash() from hashlib.md5.
  PYTHONHASHSEED: "0"

jobs:
  test:
    name: pytest (Python 3.11)
    runs-on: ubuntu-latest

    steps:
      - name: Checkout aedt-mspe-experiments
        uses: actions/checkout@v4

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

      - name: Clone upstream toolkit (aedt-fairness-audit) at pinned SHA
        run: |
          PINNED_SHA="0951db99e3385fd235bd12fe5ba411251f4eba40"
          git clone https://github.com/chadmarkey/aedt-fairness-audit.git "$HOME/aedt-fairness-audit"
          git -C "$HOME/aedt-fairness-audit" fetch --depth 1 origin "$PINNED_SHA"
          git -C "$HOME/aedt-fairness-audit" checkout "$PINNED_SHA"
          # Verify the SHA actually landed where we expect (defensive).
          ACTUAL_SHA=$(git -C "$HOME/aedt-fairness-audit" rev-parse HEAD)
          if [ "$ACTUAL_SHA" != "$PINNED_SHA" ]; then
            echo "ERROR: toolkit checkout is at $ACTUAL_SHA, expected $PINNED_SHA" >&2
            exit 1
          fi
          echo "Upstream toolkit pinned at $PINNED_SHA"

      - name: Install dependencies
        run: |
          python -m pip install --upgrade pip
          pip install \
            numpy \
            pandas \
            scipy \
            scikit-learn \
            matplotlib \
            pytest
          # scikit-learn is required because the upstream toolkit's
          # audit/metrics.py imports sklearn.linear_model.LogisticRegression.
          # sentence-transformers is intentionally excluded — tests run offline
          # and do not require SBERT model downloads.

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