gstack/.github/workflows/evals.yml

name: E2E Evals
on:
  pull_request:
    branches: [main]
  workflow_dispatch:

concurrency:
  group: evals-${{ github.head_ref }}
  cancel-in-progress: true

env:
  IMAGE: ghcr.io/${{ github.repository }}/ci

jobs:
  # Build Docker image with pre-baked toolchain (cached — only rebuilds on Dockerfile/lockfile change)
  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: ${{ matrix.suite.runner || '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: 20
    strategy:
      fail-fast: false
      matrix:
        suite:
          - name: llm-judge
            file: test/skill-llm-eval.test.ts
          - name: e2e-browse
            file: test/skill-e2e-bws.test.ts
            runner: ubicloud-standard-8
          - name: e2e-plan
            file: test/skill-e2e-plan.test.ts
          - name: e2e-deploy
            file: test/skill-e2e-deploy.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

      # Restore pre-installed node_modules from Docker image via symlink (~0s vs ~15s install)
      # If package.json changed since image was built, fall back to fresh install
      - 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

      # Verify Playwright can launch Chromium (fails fast if sandbox/deps are broken)
      - name: Verify Chromium
        if: matrix.suite.name == 'e2e-browse'
        run: bun -e "import {chromium} from 'playwright';const b=await chromium.launch({args:['--no-sandbox']});console.log('Chromium OK');await b.close()"

      - 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-${{ matrix.suite.name }}
          path: ~/.gstack-dev/evals/*.json
          retention-days: 90

  report:
    runs-on: ubicloud-standard-2
    needs: evals
    if: always() && github.event_name == 'pull_request'
    timeout-minutes: 5
    permissions:
      contents: read
      pull-requests: write
    steps:
      - uses: actions/checkout@v4
        with:
          fetch-depth: 1

      - name: Download all eval artifacts
        uses: actions/download-artifact@v4
        with:
          pattern: eval-*
          path: /tmp/eval-results
          merge-multiple: true

      - name: Post PR comment
        env:
          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
        run: |
          # shellcheck disable=SC2086,SC2059
          RESULTS=$(find /tmp/eval-results -name '*.json' 2>/dev/null | sort)
          if [ -z "$RESULTS" ]; then
            echo "No eval results found"
            exit 0
          fi

          TOTAL=0; PASSED=0; FAILED=0; COST="0"
          SUITE_LINES=""
          for f in $RESULTS; do
            T=$(jq -r '.total_tests // 0' "$f")
            P=$(jq -r '.passed // 0' "$f")
            F=$(jq -r '.failed // 0' "$f")
            C=$(jq -r '.total_cost_usd // 0' "$f")
            TIER=$(jq -r '.tier // "unknown"' "$f")
            [ "$T" -eq 0 ] && continue
            TOTAL=$((TOTAL + T))
            PASSED=$((PASSED + P))
            FAILED=$((FAILED + F))
            COST=$(echo "$COST + $C" | bc)
            STATUS_ICON="✅"
            [ "$F" -gt 0 ] && STATUS_ICON="❌"
            SUITE_LINES="${SUITE_LINES}| ${TIER} | ${P}/${T} | ${STATUS_ICON} | \$${C} |\n"
          done

          STATUS="✅ PASS"
          [ "$FAILED" -gt 0 ] && STATUS="❌ FAIL"

          BODY="## E2E Evals: ${STATUS}

          **${PASSED}/${TOTAL}** tests passed | **\$${COST}** total cost | **12 parallel runners**

          | Suite | Result | Status | Cost |
          |-------|--------|--------|------|
          $(echo -e "$SUITE_LINES")

          ---
          *12x ubicloud-standard-2 (Docker: pre-baked toolchain + deps) | wall clock ≈ slowest suite*"

          if [ "$FAILED" -gt 0 ]; then
            FAILURES=""
            for f in $RESULTS; do
              F=$(jq -r '.failed // 0' "$f")
              [ "$F" -eq 0 ] && continue
              FAILS=$(jq -r '.tests[] | select(.passed == false) | "- ❌ \(.name): \(.exit_reason // "unknown")"' "$f")
              FAILURES="${FAILURES}${FAILS}\n"
            done
            BODY="${BODY}

          ### Failures
          $(echo -e "$FAILURES")"
          fi

          # Update existing comment or create new one
          COMMENT_ID=$(gh api repos/${{ github.repository }}/issues/${{ github.event.pull_request.number }}/comments \
            --jq '.[] | select(.body | startswith("## E2E Evals")) | .id' | tail -1)

          if [ -n "$COMMENT_ID" ]; then
            gh api "repos/${{ github.repository }}/issues/comments/${COMMENT_ID}" \
              -X PATCH -f body="$BODY"
          else
            gh pr comment "${{ github.event.pull_request.number }}" --body "$BODY"
          fi