wehub-resource-sync
74 lines
2.0 KiB
YAML
74 lines
2.0 KiB
YAML
name: Plugin Eval Report
|
|
|
|
on:
|
|
workflow_dispatch:
|
|
inputs:
|
|
depth:
|
|
description: 'Evaluation depth (quick = static only, standard = +LLM judge, deep = +Monte Carlo)'
|
|
required: true
|
|
default: 'quick'
|
|
type: choice
|
|
options:
|
|
- quick
|
|
- standard
|
|
- deep
|
|
only_changed:
|
|
description: 'Comma-separated plugin names to evaluate (blank = all)'
|
|
required: false
|
|
default: ''
|
|
type: string
|
|
schedule:
|
|
# Weekly full static sweep, Mondays at 06:00 UTC
|
|
- cron: '0 6 * * 1'
|
|
|
|
permissions:
|
|
contents: read
|
|
|
|
jobs:
|
|
eval:
|
|
name: Evaluate plugins (${{ inputs.depth || 'quick' }})
|
|
runs-on: ubuntu-latest
|
|
timeout-minutes: 180
|
|
env:
|
|
DEPTH: ${{ inputs.depth || 'quick' }}
|
|
ONLY_CHANGED: ${{ inputs.only_changed || '' }}
|
|
steps:
|
|
- uses: actions/checkout@v4
|
|
|
|
- name: Install uv
|
|
uses: astral-sh/setup-uv@v5
|
|
with:
|
|
enable-cache: true
|
|
|
|
- name: Sync plugin-eval dependencies
|
|
working-directory: plugins/plugin-eval
|
|
run: uv sync --all-extras
|
|
|
|
- name: Run eval sweep
|
|
working-directory: plugins/plugin-eval
|
|
env:
|
|
ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
|
|
run: |
|
|
args=( --depth "$DEPTH" --output-dir "$GITHUB_WORKSPACE/eval-reports" --concurrency 4 )
|
|
if [ -n "$ONLY_CHANGED" ]; then
|
|
args+=( --only-changed "$ONLY_CHANGED" )
|
|
fi
|
|
uv run python scripts/eval_all.py "${args[@]}"
|
|
|
|
- name: Post report to job summary
|
|
if: always()
|
|
run: |
|
|
if [ -f eval-reports/summary.md ]; then
|
|
cat eval-reports/summary.md >> "$GITHUB_STEP_SUMMARY"
|
|
else
|
|
echo "No summary produced." >> "$GITHUB_STEP_SUMMARY"
|
|
fi
|
|
|
|
- name: Upload reports artifact
|
|
if: always()
|
|
uses: actions/upload-artifact@v4
|
|
with:
|
|
name: eval-reports-${{ env.DEPTH }}-${{ github.run_id }}
|
|
path: eval-reports/
|
|
retention-days: 30
|