qwen-code/.github/workflows/e2e.yml
易良 d1787a2280
ci: quarantine cron-interactive from push E2E to nightly-only (#6986)
cron-interactive.test.ts is inherently timing-flaky: it relies on
wall-clock cron fire (*/1 at minute boundary) + real model latency,
with a 90s waitForScreen window. On slower macOS runners this
occasionally exceeds the timeout, turning push CI red and triggering
wasteful autofix attempts (~50min).

Changes:
- Exclude cron-interactive from push-triggered Linux and macOS jobs
  via vitest --exclude
- Add new cron-interactive-nightly job: runs only on schedule/
  workflow_dispatch, with continue-on-error so flakes are visible
  but do not fail the workflow
- Mirrors the existing web-shell-browser-regression pattern

Coverage is preserved: cron regressions are still caught by nightly
runs within ~24h. The root fix (injectable clock seam in
CronScheduler) is tracked separately in #6487/#6982.

Closes #6982
2026-07-15 17:18:28 +00:00

239 lines
8.8 KiB
YAML

name: 'E2E Tests'
on:
# E2E is slow and currently flaky, so it is NOT in the merge queue (gating the
# serial queue on it would stall every merge). It runs post-merge on `main`,
# plus a nightly full regression and on-demand. Promote it to `merge_group` +
# required once a stable subset is carved out.
push:
branches:
- 'main'
- 'feat/e2e/**'
schedule:
- cron: '0 4 * * *' # nightly full regression (~04:00 UTC), guaranteed signal
workflow_dispatch:
concurrency:
# Scope the group by event so back-to-back pushes to `main` cancel superseded
# runs (no pile-up when PRs merge in quick succession), without ever cancelling
# the nightly schedule or a manual dispatch — they share the ref but not the
# event. feat/e2e/** pushes still cancel their own superseded runs.
group: |-
${{ github.workflow }}-${{ github.event_name }}-${{ github.head_ref || github.ref_name }}
# Cancel superseded pushes (main included now — only the latest tree matters,
# and it covers every merged change). The nightly run always finishes, so a
# busy merge window that keeps cancelling the push run still gets a signal.
cancel-in-progress: |-
${{ github.event_name == 'push' }}
jobs:
e2e-test-linux:
name: 'E2E Test (Linux) - ${{ matrix.sandbox }}'
runs-on: 'ubuntu-latest'
# Skip on fork PRs: forks have no access to repository secrets
# (OPENAI_*, DOCKERHUB_*), so the matrix would fail unconditionally
# and show misleading red status. Same-repo PRs run normally.
if: |-
${{ github.event_name != 'pull_request' || github.event.pull_request.head.repo.full_name == github.repository }}
strategy:
matrix:
sandbox:
- 'sandbox:none'
- 'sandbox:docker'
node-version:
- '22.x'
steps:
- name: 'Checkout'
uses: 'actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10' # v6.0.3
- name: 'Set up Node.js ${{ matrix.node-version }}'
uses: 'actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e' # v6.4.0
with:
node-version: '${{ matrix.node-version }}'
cache: 'npm'
cache-dependency-path: 'package-lock.json'
registry-url: 'https://registry.npmjs.org/'
- name: 'Configure npm for rate limiting'
run: |-
npm config set fetch-retry-mintimeout 20000
npm config set fetch-retry-maxtimeout 120000
npm config set fetch-retries 5
npm config set fetch-timeout 300000
- name: 'Install dependencies'
run: |-
npm ci --prefer-offline --no-audit --progress=false
- name: 'Build project'
run: |-
npm run build
- name: 'Bundle CLI for E2E tests'
run: |-
npm run bundle
- name: 'Set up Docker'
if: |-
${{ matrix.sandbox == 'sandbox:docker' }}
uses: 'docker/setup-buildx-action@d7f5e7f509e45cec5c76c4d5afdd7de93d0b3df5' # ratchet:docker/setup-buildx-action@v4
- name: 'Set up Podman'
if: |-
${{ matrix.sandbox == 'sandbox:podman' }}
uses: 'redhat-actions/podman-login@4934294ad0449894bcd1e9f191899d7292469603' # ratchet:redhat-actions/podman-login@v1
with:
registry: 'docker.io'
username: '${{ secrets.DOCKERHUB_USERNAME }}'
password: '${{ secrets.DOCKERHUB_TOKEN }}'
- name: 'Run E2E tests'
env:
OPENAI_API_KEY: '${{ secrets.OPENAI_API_KEY }}'
OPENAI_BASE_URL: '${{ secrets.OPENAI_BASE_URL }}'
OPENAI_MODEL: '${{ secrets.OPENAI_MODEL }}'
KEEP_OUTPUT: 'true'
VERBOSE: 'true'
run: |-
if [[ "${{ matrix.sandbox }}" == "sandbox:docker" ]]; then
npm run test:integration:sandbox:docker -- --exclude '**/interactive/cron-interactive.test.ts'
else
npm run test:integration:sandbox:none -- --exclude '**/interactive/cron-interactive.test.ts'
fi
e2e-test-macos:
name: 'E2E Test - macOS'
runs-on: 'macos-latest'
# Skip on fork PRs (no secrets) — see e2e-test-linux above.
if: |-
${{ github.event_name != 'pull_request' || github.event.pull_request.head.repo.full_name == github.repository }}
steps:
- name: 'Checkout'
uses: 'actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10' # v6.0.3
- name: 'Set up Node.js'
uses: 'actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e' # v6.4.0
with:
node-version-file: '.nvmrc'
cache: 'npm'
cache-dependency-path: 'package-lock.json'
registry-url: 'https://registry.npmjs.org/'
- name: 'Configure npm for rate limiting'
run: |-
npm config set fetch-retry-mintimeout 20000
npm config set fetch-retry-maxtimeout 120000
npm config set fetch-retries 5
npm config set fetch-timeout 300000
- name: 'Install dependencies'
run: |-
npm ci --prefer-offline --no-audit --progress=false
- name: 'Build project'
run: |-
npm run build
- name: 'Bundle CLI for E2E tests'
run: |-
npm run bundle
- name: 'Run E2E tests'
env:
OPENAI_API_KEY: '${{ secrets.OPENAI_API_KEY }}'
OPENAI_BASE_URL: '${{ secrets.OPENAI_BASE_URL }}'
OPENAI_MODEL: '${{ secrets.OPENAI_MODEL }}'
run: 'npx cross-env VERBOSE=true KEEP_OUTPUT=true QWEN_SANDBOX=false vitest run --root ./integration-tests --exclude "**/interactive/cron-interactive.test.ts"'
cron-interactive-nightly:
name: 'cron-interactive E2E (nightly)'
runs-on: 'ubuntu-latest'
if: |-
${{ github.event_name == 'schedule' || github.event_name == 'workflow_dispatch' }}
# This test is inherently timing-flaky (wall-clock cron fire + real model
# latency). Run it nightly only so flakes do not turn push CI red.
# continue-on-error prevents this job from marking the workflow as failed.
continue-on-error: true
steps:
- name: 'Checkout'
uses: 'actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10' # v6.0.3
- name: 'Set up Node.js'
uses: 'actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e' # v6.4.0
with:
node-version-file: '.nvmrc'
cache: 'npm'
cache-dependency-path: 'package-lock.json'
registry-url: 'https://registry.npmjs.org/'
- name: 'Configure npm for rate limiting'
run: |-
npm config set fetch-retry-mintimeout 20000
npm config set fetch-retry-maxtimeout 120000
npm config set fetch-retries 5
npm config set fetch-timeout 300000
- name: 'Install dependencies'
run: |-
npm ci --prefer-offline --no-audit --progress=false
- name: 'Build project'
run: |-
npm run build
- name: 'Bundle CLI for E2E tests'
run: |-
npm run bundle
- name: 'Run cron-interactive E2E tests'
env:
OPENAI_API_KEY: '${{ secrets.OPENAI_API_KEY }}'
OPENAI_BASE_URL: '${{ secrets.OPENAI_BASE_URL }}'
OPENAI_MODEL: '${{ secrets.OPENAI_MODEL }}'
KEEP_OUTPUT: 'true'
VERBOSE: 'true'
run: 'npx cross-env QWEN_SANDBOX=false vitest run --root ./integration-tests interactive/cron-interactive.test.ts'
web-shell-browser-regression:
name: 'web-shell Browser Regression'
runs-on: 'ubuntu-latest'
if: |-
${{ github.event_name == 'schedule' || github.event_name == 'workflow_dispatch' }}
steps:
- name: 'Checkout'
uses: 'actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd' # v6.0.2
- name: 'Set up Node.js'
uses: 'actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e' # v6.4.0
with:
node-version-file: '.nvmrc'
cache: 'npm'
cache-dependency-path: 'package-lock.json'
registry-url: 'https://registry.npmjs.org/'
- name: 'Configure npm for rate limiting'
run: |-
npm config set fetch-retry-mintimeout 20000
npm config set fetch-retry-maxtimeout 120000
npm config set fetch-retries 5
npm config set fetch-timeout 300000
- name: 'Install dependencies'
run: |-
npm ci --prefer-offline --no-audit --progress=false
- name: 'Install Playwright Chromium'
run: 'npx playwright install --with-deps chromium'
- name: 'Run web-shell browser regression'
run: 'npm run test:e2e --workspace=packages/web-shell'
- name: 'Upload web-shell Playwright artifacts'
if: '${{ always() }}'
uses: 'actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a' # v7.0.1
with:
name: 'web-shell-browser-regression'
path: |-
packages/web-shell/client/e2e/test-results
packages/web-shell/client/e2e/playwright-report
if-no-files-found: 'ignore'