Aggregate test results. (#16581)

This commit is contained in:
Christian Gunderman
2026-01-14 07:08:05 +00:00
committed by GitHub
parent 8030404b08
commit 66e7b479ae
6 changed files with 295 additions and 9 deletions

View File

@@ -13,11 +13,16 @@ on:
permissions:
contents: 'read'
checks: 'write'
actions: 'read'
jobs:
evals:
name: 'Evals (USUALLY_PASSING) nightly run'
runs-on: 'gemini-cli-ubuntu-16-core'
strategy:
fail-fast: false
matrix:
run_attempt: [1, 2, 3]
steps:
- name: 'Checkout'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
@@ -34,8 +39,38 @@ jobs:
- name: 'Build project'
run: 'npm run build'
- name: 'Create logs directory'
run: 'mkdir -p evals/logs'
- name: 'Run Evals'
env:
GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
RUN_EVALS: "${{ github.event.inputs.run_all != 'false' }}"
run: 'npm run test:all_evals'
- name: 'Upload Logs'
if: 'always()'
uses: 'actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02' # ratchet:actions/upload-artifact@v4
with:
name: 'eval-logs-${{ matrix.run_attempt }}'
path: 'evals/logs'
retention-days: 7
aggregate-results:
name: 'Aggregate Results'
needs: ['evals']
if: 'always()'
runs-on: 'gemini-cli-ubuntu-16-core'
steps:
- name: 'Checkout'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
- name: 'Download Logs'
uses: 'actions/download-artifact@cc203385981b70ca67e1cc392babf9cc229d5806' # ratchet:actions/download-artifact@v4
with:
path: 'artifacts'
- name: 'Generate Summary'
env:
GH_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
run: 'node scripts/aggregate_evals.js artifacts >> "$GITHUB_STEP_SUMMARY"'