Behavioral evals framework. (#16047)

This commit is contained in:
Christian Gunderman
2026-01-14 04:49:17 +00:00
committed by GitHub
parent 933bc5774f
commit 8030404b08
15 changed files with 1577 additions and 1413 deletions

View File

@@ -277,6 +277,37 @@ jobs:
shell: 'pwsh'
run: 'npm run test:integration:sandbox:none'
evals:
name: 'Evals (ALWAYS_PASSING)'
needs:
- 'merge_queue_skipper'
- 'parse_run_context'
runs-on: 'gemini-cli-ubuntu-16-core'
if: |
always() && (needs.merge_queue_skipper.result !='success' || needs.merge_queue_skipper.outputs.skip != 'true')
steps:
- name: 'Checkout'
uses: 'actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955' # ratchet:actions/checkout@v5
with:
ref: '${{ needs.parse_run_context.outputs.sha }}'
repository: '${{ needs.parse_run_context.outputs.repository }}'
- name: 'Set up Node.js 20.x'
uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions-node@v4
with:
node-version: '20.x'
- name: 'Install dependencies'
run: 'npm ci'
- name: 'Build project'
run: 'npm run build'
- name: 'Run Evals (Required to pass)'
env:
GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
run: 'npm run test:always_passing_evals'
e2e:
name: 'E2E'
if: |
@@ -284,13 +315,15 @@ jobs:
needs:
- 'e2e_linux'
- 'e2e_mac'
- 'evals'
- 'merge_queue_skipper'
runs-on: 'gemini-cli-ubuntu-16-core'
steps:
- name: 'Check E2E test results'
run: |
if [[ ${{ needs.e2e_linux.result }} != 'success' || \
${{ needs.e2e_mac.result }} != 'success' ]]; then
${{ needs.e2e_mac.result }} != 'success' || \
${{ needs.evals.result }} != 'success' ]]; then
echo "One or more E2E jobs failed."
exit 1
fi

41
.github/workflows/evals-nightly.yml vendored Normal file
View File

@@ -0,0 +1,41 @@
name: 'Evals: Nightly'
on:
schedule:
- cron: '0 1 * * *' # Runs at 1 AM every day
workflow_dispatch:
inputs:
run_all:
description: 'Run all evaluations (including usually passing)'
type: 'boolean'
default: true
permissions:
contents: 'read'
checks: 'write'
jobs:
evals:
name: 'Evals (USUALLY_PASSING) nightly run'
runs-on: 'gemini-cli-ubuntu-16-core'
steps:
- name: 'Checkout'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
- name: 'Set up Node.js'
uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4
with:
node-version-file: '.nvmrc'
cache: 'npm'
- name: 'Install dependencies'
run: 'npm ci'
- name: 'Build project'
run: 'npm run build'
- 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'