gstack/.github/workflows/evals-periodic.yml

name: Periodic Evals
on:
  schedule:
    - cron: '0 6 * * 1'  # Monday 6 AM UTC
  workflow_dispatch:

concurrency:
  group: evals-periodic
  cancel-in-progress: true

env:
  IMAGE: ghcr.io/${{ github.repository }}/ci
  EVALS_TIER: periodic
  EVALS_ALL: 1  # Ignore diff — run all periodic tests

jobs:
  build-image:
    runs-on: ubicloud-standard-2
    permissions:
      contents: read
      packages: write
    outputs:
      image-tag: ${{ steps.meta.outputs.tag }}
    steps:
      - uses: actions/checkout@v4

      - id: meta
        run: echo "tag=${{ env.IMAGE }}:${{ hashFiles('.github/docker/Dockerfile.ci', 'package.json') }}" >> "$GITHUB_OUTPUT"

      - uses: docker/login-action@v3
        with:
          registry: ghcr.io
          username: ${{ github.actor }}
          password: ${{ secrets.GITHUB_TOKEN }}

      - name: Check if image exists
        id: check
        run: |
          if docker manifest inspect ${{ steps.meta.outputs.tag }} > /dev/null 2>&1; then
            echo "exists=true" >> "$GITHUB_OUTPUT"
          else
            echo "exists=false" >> "$GITHUB_OUTPUT"
          fi

      - if: steps.check.outputs.exists == 'false'
        run: cp package.json .github/docker/

      - if: steps.check.outputs.exists == 'false'
        uses: docker/build-push-action@v6
        with:
          context: .github/docker
          file: .github/docker/Dockerfile.ci
          push: true
          tags: |
            ${{ steps.meta.outputs.tag }}
            ${{ env.IMAGE }}:latest

  evals:
    runs-on: ubicloud-standard-2
    needs: build-image
    container:
      image: ${{ needs.build-image.outputs.image-tag }}
      credentials:
        username: ${{ github.actor }}
        password: ${{ secrets.GITHUB_TOKEN }}
      options: --user runner
    timeout-minutes: 25
    strategy:
      fail-fast: false
      matrix:
        suite:
          - name: e2e-plan
            file: test/skill-e2e-plan.test.ts
          - name: e2e-design
            file: test/skill-e2e-design.test.ts
          - name: e2e-qa-bugs
            file: test/skill-e2e-qa-bugs.test.ts
          - name: e2e-qa-workflow
            file: test/skill-e2e-qa-workflow.test.ts
          - name: e2e-review
            file: test/skill-e2e-review.test.ts
          - name: e2e-workflow
            file: test/skill-e2e-workflow.test.ts
          - name: e2e-routing
            file: test/skill-routing-e2e.test.ts
          - name: e2e-codex
            file: test/codex-e2e.test.ts
          - name: e2e-gemini
            file: test/gemini-e2e.test.ts
    steps:
      - uses: actions/checkout@v4
        with:
          fetch-depth: 0

      - name: Fix bun temp
        run: |
          mkdir -p /home/runner/.cache/bun
          {
            echo "BUN_INSTALL_CACHE_DIR=/home/runner/.cache/bun"
            echo "BUN_TMPDIR=/home/runner/.cache/bun"
            echo "TMPDIR=/home/runner/.cache"
          } >> "$GITHUB_ENV"

      - name: Restore deps
        run: |
          if [ -d /opt/node_modules_cache ] && diff -q /opt/node_modules_cache/.package.json package.json >/dev/null 2>&1; then
            ln -s /opt/node_modules_cache node_modules
          else
            bun install
          fi

      - run: bun run build

      - name: Run ${{ matrix.suite.name }}
        env:
          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
          GEMINI_API_KEY: ${{ secrets.GEMINI_API_KEY }}
          EVALS_CONCURRENCY: "40"
          PLAYWRIGHT_BROWSERS_PATH: /opt/playwright-browsers
        run: EVALS=1 bun test --retry 2 --concurrent --max-concurrency 40 ${{ matrix.suite.file }}

      - name: Upload eval results
        if: always()
        uses: actions/upload-artifact@v4
        with:
          name: eval-periodic-${{ matrix.suite.name }}
          path: ~/.gstack-dev/evals/*.json
          retention-days: 90