Skip to content

Feature/example pack structure #9

Feature/example pack structure

Feature/example pack structure #9

Workflow file for this run

name: evals-workflow
on:
workflow_dispatch:
pull_request:
# push:
# branches: [ "main" ]
jobs:
run-evals:
runs-on: ubuntu-latest
steps:
- name: Checkout
uses: actions/checkout@v4
- name: Set up Python
uses: actions/setup-python@v5
with:
python-version: "3.12"
- name: Install dependencies
run: |
python3 -m pip install --upgrade pip
pip install -r requirements.txt
- name: Run evals (mock)
run: |
python3 runner.py --mode mock
- name: Compare to baseline (if exists)
run: |
if [ -f baselines/baseline_results.json ]; then
python3 regression_compare.py baselines/baseline_results.json results/latest_results.json --max-drop 0.3
else
echo "No baseline found. Skipping regression comparison."
fi
- name: Upload eval artifacts
uses: actions/upload-artifact@v4
with:
name: eval-results
path: |
results/latest_results.json
results/report.csv