Skip to content

Claude Deflake E2E

Claude Deflake E2E #79

name: Claude Deflake E2E
on:
schedule:
# Weekdays at 10:00 UTC (2 AM PST / 3 AM PDT due to DST)
- cron: "0 10 * * 1-5"
workflow_dispatch:
inputs:
commit_count:
description: "Number of recent commits on main to scan for flaky tests"
required: false
default: "10"
type: string
jobs:
deflake:
environment: ai-bots
runs-on:
- self-hosted
- macOS
- ARM64
permissions: {}
steps:
- name: Create GitHub App token
id: app-token
uses: actions/create-github-app-token@v2
with:
app-id: ${{ vars.DYAD_GITHUB_APP_ID }}
private-key: ${{ secrets.DYAD_GITHUB_APP_PRIVATE_KEY }}
permission-actions: write
permission-contents: write
permission-issues: write
permission-pull-requests: write
- name: Checkout repository
uses: actions/checkout@v5
with:
fetch-depth: 0
- name: Initialize environment
uses: actions/setup-node@v4
with:
node-version-file: package.json
cache: npm
cache-dependency-path: package-lock.json
- name: Install npm 11.8.0
run: npm install -g npm@11.8.0
- name: Install node modules
run: npm ci --no-audit --no-fund --progress=false
env:
GITHUB_TOKEN: ${{ steps.app-token.outputs.token }}
- name: Setup pnpm
uses: pnpm/action-setup@a7487c7e89a18df4991f7f222e4898a00d66ddda # v4.1.0
with:
version: 10.33.2
- name: Clone nextjs-template
run: git clone --depth 1 https://github.com/dyad-sh/nextjs-template.git nextjs-template
- name: Install scaffold dependencies
run: cd scaffold && pnpm install
- name: Install nextjs-template dependencies
run: cd nextjs-template && pnpm install
- name: Install Chromium browser for Playwright
run: npx playwright install chromium --with-deps
- name: Build fake LLM server
run: cd testing/fake-llm-server && npm install && npm run build
- name: Deflake E2E tests
uses: anthropics/claude-code-action@v1.0.96
env:
GH_TOKEN: ${{ steps.app-token.outputs.token }}
CLAUDE_CODE_MAX_OUTPUT_TOKENS: 48000
with:
claude_code_oauth_token: ${{ secrets.CLAUDE_CODE_OAUTH_TOKEN }}
github_token: ${{ steps.app-token.outputs.token }}
claude_args: --model claude-opus-4-6
display_report: true
prompt: |
/dyad:deflake-e2e-recent-commits ${{ inputs.commit_count || '10' }}
- name: Cleanup (self-hosted macOS)
if: always()
run: bash scripts/ci-cleanup-macos.sh