vercel__workflow/.github/workflows/benchmarks.yml

name: Performance Benchmarks

on:
  pull_request:
    branches: [main]
    types: [opened, synchronize, reopened, labeled]
  push:
    branches: [main]
  workflow_dispatch: # Allow manual triggers
    inputs:
      full_suite:
        description: 'Run full benchmark suite (includes long-running 100+ step benchmarks)'
        required: false
        type: boolean
        default: false

concurrency:
  group: ${{ github.workflow }}-${{ github.ref }}
  cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}

jobs:
  # Phase 0: Update PR comment to show benchmarks are running
  pr-comment-start:
    name: Create PR Comment
    runs-on: ubuntu-latest
    if: github.event_name == 'pull_request' && !contains(github.event.pull_request.labels.*.name, 'workflow-server-test')
    timeout-minutes: 2

    steps:
      - name: Find existing benchmark comment
        uses: peter-evans/find-comment@v3
        id: find-comment
        with:
          issue-number: ${{ github.event.pull_request.number }}
          comment-author: 'github-actions[bot]'
          body-includes: '<!-- benchmark-results -->'

      - name: Get existing comment body
        if: steps.find-comment.outputs.comment-id != ''
        id: get-comment
        uses: actions/github-script@v7
        with:
          script: |
            const comment = await github.rest.issues.getComment({
              owner: context.repo.owner,
              repo: context.repo.repo,
              comment_id: ${{ steps.find-comment.outputs.comment-id }}
            });
            // Extract the results section (everything after the header and running message)
            const body = comment.data.body;
            // Remove any existing stale warning and running message
            let resultsSection = body
              .replace(/<!-- benchmark-results -->\n## 📊 Benchmark Results\n\n> ⚠️ \*\*Results below are stale\*\*[^\n]*\n\n/g, '')
              .replace(/<!-- benchmark-results -->\n## 📊 Benchmark Results\n\n/g, '')
              .replace(/⏳ \*\*Benchmarks are running\.\.\.\*\*\n\n---\n_Started at:[^_]*_\n\n---\n\n/g, '')
              .replace(/⏳ \*\*Benchmarks are running\.\.\.\*\*\n\n---\n_Started at:[^_]*_/g, '')
              .trim();

            // If there's actual content left (benchmark tables), save it
            if (resultsSection && resultsSection.includes('|')) {
              core.setOutput('has-results', 'true');
              core.setOutput('previous-results', resultsSection);
            } else {
              core.setOutput('has-results', 'false');
            }

      - name: Create new benchmark comment
        if: steps.find-comment.outputs.comment-id == ''
        uses: marocchino/sticky-pull-request-comment@v2
        with:
          header: benchmark-results
          message: |
            <!-- benchmark-results -->
            ## 📊 Benchmark Results

            ⏳ **Benchmarks are running...**

            This comment will be updated with the results when the benchmarks complete.

            ---
            _Started at: ${{ github.event.pull_request.updated_at }}_

      - name: Update existing benchmark comment with stale warning
        if: steps.find-comment.outputs.comment-id != '' && steps.get-comment.outputs.has-results == 'true'
        uses: marocchino/sticky-pull-request-comment@v2
        with:
          header: benchmark-results
          message: |
            <!-- benchmark-results -->
            ## 📊 Benchmark Results

            > ⚠️ **Results below are stale** and not from the latest commit. This comment will be updated when CI completes on the latest run.

            ⏳ **Benchmarks are running...**

            ---
            _Started at: ${{ github.event.pull_request.updated_at }}_

            ---

            ${{ steps.get-comment.outputs.previous-results }}

      - name: Update existing benchmark comment without results
        if: steps.find-comment.outputs.comment-id != '' && steps.get-comment.outputs.has-results != 'true'
        uses: marocchino/sticky-pull-request-comment@v2
        with:
          header: benchmark-results
          message: |
            <!-- benchmark-results -->
            ## 📊 Benchmark Results

            ⏳ **Benchmarks are running...**

            This comment will be updated with the results when the benchmarks complete.

            ---
            _Started at: ${{ github.event.pull_request.updated_at }}_

  # Phase 1: Build all packages (not workbenches)
  build:
    name: Build Packages
    runs-on: ubuntu-latest
    if: ${{ !contains(github.event.pull_request.labels.*.name, 'workflow-server-test') }}
    timeout-minutes: 30
    env:
      TURBO_TOKEN: ${{ secrets.TURBO_TOKEN }}
      TURBO_TEAM: ${{ vars.TURBO_TEAM }}

    steps:
      - uses: actions/checkout@v4

      - name: Setup environment
        uses: ./.github/actions/setup-workflow-dev
        with:
          build-packages: 'true'

      # Cache node_modules and package build outputs
      - name: Upload build artifacts
        uses: actions/upload-artifact@v4
        with:
          name: build-artifacts
          path: |
            node_modules
            packages/*/dist
            packages/core/src/version.ts
          retention-days: 1

  # Phase 2a: Local benchmarks (no postgres)
  benchmark-local:
    name: Benchmark Local (${{ matrix.app }})
    runs-on: ubuntu-latest
    needs: build
    if: ${{ !contains(github.event.pull_request.labels.*.name, 'workflow-server-test') }}
    timeout-minutes: 60
    strategy:
      fail-fast: false
      matrix:
        # Note: Use actual directory names, not symlinks (nitro -> nitro-v3)
        app: [nextjs-turbopack, nitro-v3, express]

    env:
      TURBO_TOKEN: ${{ secrets.TURBO_TOKEN }}
      TURBO_TEAM: ${{ vars.TURBO_TEAM }}
      WORKFLOW_PUBLIC_MANIFEST: '1'

    steps:
      - uses: actions/checkout@v4

      - name: Setup environment
        uses: ./.github/actions/setup-workflow-dev
        with:
          install-dependencies: 'false'
          build-packages: 'false'

      - name: Download build artifacts
        uses: actions/download-artifact@v4
        with:
          name: build-artifacts
          path: .

      - name: Install dependencies
        run: pnpm install --frozen-lockfile

      # For PRs, download baseline results from the PR's base branch
      - name: Download baseline from PR base branch
        if: github.event_name == 'pull_request'
        continue-on-error: true
        uses: dawidd6/action-download-artifact@v6
        with:
          workflow: benchmarks.yml
          branch: ${{ github.event.pull_request.base.ref }}
          name: baseline-benchmark-results
          path: baseline-results
          if_no_artifact_found: warn

      - name: Build workbench
        run: pnpm turbo run build --filter='./workbench/${{ matrix.app }}'

      - name: Run benchmarks
        env:
          DEPLOYMENT_URL: "http://localhost:3000"
          APP_NAME: ${{ matrix.app }}
          # Run full suite on nextjs-turbopack only (stress tests are too slow to run on all apps)
          BENCHMARK_FULL_SUITE: ${{ matrix.app == 'nextjs-turbopack' && ((github.event_name == 'workflow_dispatch' && inputs.full_suite) || contains(github.event.pull_request.labels.*.name, 'stress-test')) }}
        run: |
          cd workbench/${{ matrix.app }}
          pnpm start &
          echo "Waiting for server to start..."
          sleep 15
          cd ../..
          pnpm vitest bench packages/core/e2e/bench.bench.ts --run --outputJson=bench-results-${{ matrix.app }}-local.json

      - name: Render benchmark results
        uses: ./.github/actions/render-benchmarks
        with:
          benchmark-file: bench-results-${{ matrix.app }}-local.json
          app-name: ${{ matrix.app }}
          backend: local
          baseline-file: baseline-results/bench-results-${{ matrix.app }}-local.json

      - name: Upload benchmark results
        uses: actions/upload-artifact@v4
        with:
          name: bench-results-${{ matrix.app }}-local
          path: |
            bench-results-${{ matrix.app }}-local.json
            bench-timings-${{ matrix.app }}-local.json

  # Phase 2b: Postgres benchmarks (with postgres service)
  benchmark-postgres:
    name: Benchmark Postgres (${{ matrix.app }})
    runs-on: ubuntu-latest
    needs: build
    if: ${{ !contains(github.event.pull_request.labels.*.name, 'workflow-server-test') }}
    timeout-minutes: 60
    strategy:
      fail-fast: false
      matrix:
        # Note: Use actual directory names, not symlinks (nitro -> nitro-v3)
        app: [nextjs-turbopack, nitro-v3, express]

    services:
      postgres:
        image: postgres:18-alpine
        env:
          POSTGRES_USER: world
          POSTGRES_PASSWORD: world
          POSTGRES_DB: world
        ports:
          - 5432:5432
        options: >-
          --health-cmd pg_isready
          --health-interval 10s
          --health-timeout 5s
          --health-retries 5

    env:
      TURBO_TOKEN: ${{ secrets.TURBO_TOKEN }}
      TURBO_TEAM: ${{ vars.TURBO_TEAM }}
      WORKFLOW_PUBLIC_MANIFEST: '1'
      WORKFLOW_TARGET_WORLD: "@workflow/world-postgres"
      WORKFLOW_POSTGRES_URL: "postgres://world:world@localhost:5432/world"

    steps:
      - uses: actions/checkout@v4

      - name: Setup environment
        uses: ./.github/actions/setup-workflow-dev
        with:
          install-dependencies: 'false'
          build-packages: 'false'

      - name: Download build artifacts
        uses: actions/download-artifact@v4
        with:
          name: build-artifacts
          path: .

      - name: Install dependencies
        run: pnpm install --frozen-lockfile

      # For PRs, download baseline results from the PR's base branch
      - name: Download baseline from PR base branch
        if: github.event_name == 'pull_request'
        continue-on-error: true
        uses: dawidd6/action-download-artifact@v6
        with:
          workflow: benchmarks.yml
          branch: ${{ github.event.pull_request.base.ref }}
          name: baseline-benchmark-results
          path: baseline-results
          if_no_artifact_found: warn

      - name: Setup PostgreSQL database
        run: ./packages/world-postgres/bin/setup.js

      # Build workbench with postgres world (build output differs based on target world)
      - name: Build workbench for postgres
        run: pnpm turbo run build --filter='./workbench/${{ matrix.app }}'

      - name: Run benchmarks
        env:
          DEPLOYMENT_URL: "http://localhost:3000"
          APP_NAME: ${{ matrix.app }}
          # Run full suite on nextjs-turbopack only (stress tests are too slow to run on all apps)
          BENCHMARK_FULL_SUITE: ${{ matrix.app == 'nextjs-turbopack' && ((github.event_name == 'workflow_dispatch' && inputs.full_suite) || contains(github.event.pull_request.labels.*.name, 'stress-test')) }}
        run: |
          cd workbench/${{ matrix.app }}
          pnpm start &
          echo "Waiting for server to start..."
          sleep 15
          cd ../..
          pnpm vitest bench packages/core/e2e/bench.bench.ts --run --outputJson=bench-results-${{ matrix.app }}-postgres.json

      - name: Render benchmark results
        uses: ./.github/actions/render-benchmarks
        with:
          benchmark-file: bench-results-${{ matrix.app }}-postgres.json
          app-name: ${{ matrix.app }}
          backend: postgres
          baseline-file: baseline-results/bench-results-${{ matrix.app }}-postgres.json

      - name: Upload benchmark results
        uses: actions/upload-artifact@v4
        with:
          name: bench-results-${{ matrix.app }}-postgres
          path: |
            bench-results-${{ matrix.app }}-postgres.json
            bench-timings-${{ matrix.app }}-postgres.json

  # Phase 2c: Vercel benchmarks (needs build artifacts for packages)
  benchmark-vercel:
    name: Benchmark Vercel (${{ matrix.app.name }})
    runs-on: ubuntu-latest
    needs: build
    if: ${{ !contains(github.event.pull_request.labels.*.name, 'workflow-server-test') }}
    timeout-minutes: 90
    permissions:
      id-token: write
      contents: read
      deployments: read
    strategy:
      fail-fast: false
      matrix:
        app:
          - name: "nextjs-turbopack"
            project-id: "prj_yjkM7UdHliv8bfxZ1sMJQf1pMpdi"
            project-slug: "example-nextjs-workflow-turbopack"
          - name: "nitro-v3"
            project-id: "prj_e7DZirYdLrQKXNrlxg7KmA6ABx8r"
            project-slug: "workbench-nitro-workflow"
          - name: "express"
            project-id: "prj_cCZjpBy92VRbKHHbarDMhOHtkuIr"
            project-slug: "workbench-express-workflow"

    steps:
      - uses: actions/checkout@v4

      - name: Setup environment
        uses: ./.github/actions/setup-workflow-dev
        with:
          install-dependencies: 'false'
          build-packages: 'false'

      - name: Download build artifacts
        uses: actions/download-artifact@v4
        with:
          name: build-artifacts
          path: .

      - name: Install dependencies
        run: pnpm install --frozen-lockfile

      # For PRs, download baseline results from the PR's base branch
      - name: Download baseline from PR base branch
        if: github.event_name == 'pull_request'
        continue-on-error: true
        uses: dawidd6/action-download-artifact@v6
        with:
          workflow: benchmarks.yml
          branch: ${{ github.event.pull_request.base.ref }}
          name: baseline-benchmark-results
          path: baseline-results
          if_no_artifact_found: warn

      - name: Wait for Vercel deployment
        id: waitForDeployment
        uses: ./.github/actions/wait-for-vercel-project
        with:
          team-id: "team_nO2mCG4W8IxPIeKoSsqwAxxB"
          project-id: ${{ matrix.app.project-id }}
          vercel-token: ${{ secrets.VERCEL_LABS_TOKEN }}
          timeout: 1000
          check-interval: 15
          environment: ${{ github.ref == 'refs/heads/main' && 'production' || 'preview' }}

      - name: Run benchmarks
        env:
          DEPLOYMENT_URL: ${{ steps.waitForDeployment.outputs.deployment-url }}
          APP_NAME: ${{ matrix.app.name }}
          VERCEL_DEPLOYMENT_ID: ${{ steps.waitForDeployment.outputs.deployment-id }}
          WORKFLOW_VERCEL_ENV: ${{ github.ref == 'refs/heads/main' && 'production' || 'preview' }}
          WORKFLOW_VERCEL_AUTH_TOKEN: ${{ secrets.VERCEL_LABS_TOKEN }}
          WORKFLOW_VERCEL_TEAM: "team_nO2mCG4W8IxPIeKoSsqwAxxB"
          WORKFLOW_VERCEL_PROJECT: ${{ matrix.app.project-id }}
          WORKFLOW_VERCEL_PROJECT_SLUG: ${{ matrix.app.project-slug }}
          # Trusted-sources OIDC token is minted on demand by
          # scripts/trusted-sources-headers.mjs via the runner's
          # ACTIONS_ID_TOKEN_REQUEST_URL/_TOKEN env vars (auto-set when
          # `permissions: id-token: write` is on the job) and re-minted
          # before its 5-minute expiry, so long benchmark runs keep a
          # fresh token throughout.
          # See: https://vercel.com/docs/deployment-protection/methods-to-bypass-deployment-protection/trusted-sources
          # Run full suite on nextjs-turbopack only (stress tests are too slow to run on all apps)
          BENCHMARK_FULL_SUITE: ${{ matrix.app.name == 'nextjs-turbopack' && ((github.event_name == 'workflow_dispatch' && inputs.full_suite) || contains(github.event.pull_request.labels.*.name, 'stress-test')) }}
        run: |
          pnpm vitest bench packages/core/e2e/bench.bench.ts --run --outputJson=bench-results-${{ matrix.app.name }}-vercel.json

      - name: Render benchmark results
        uses: ./.github/actions/render-benchmarks
        with:
          benchmark-file: bench-results-${{ matrix.app.name }}-vercel.json
          app-name: ${{ matrix.app.name }}
          backend: vercel
          baseline-file: baseline-results/bench-results-${{ matrix.app.name }}-vercel.json

      - name: Upload benchmark results
        uses: actions/upload-artifact@v4
        with:
          name: bench-results-${{ matrix.app.name }}-vercel
          path: |
            bench-results-${{ matrix.app.name }}-vercel.json
            bench-timings-${{ matrix.app.name }}-vercel.json

  # Phase 2d: Community World benchmarks (dynamically generated from worlds-manifest.json)
  getCommunityWorldsMatrix:
    name: Get Community Worlds Matrix
    runs-on: ubuntu-latest
    if: ${{ !contains(github.event.pull_request.labels.*.name, 'workflow-server-test') }}
    outputs:
      matrix: ${{ steps.set-matrix.outputs.matrix }}
    steps:
      - uses: actions/checkout@v4

      - name: Setup environment
        uses: ./.github/actions/setup-workflow-dev
        with:
          install-dependencies: 'false'
          build-packages: 'false'

      - id: set-matrix
        run: echo "matrix=$(node ./scripts/create-community-worlds-matrix.mjs)" >> $GITHUB_OUTPUT

  benchmark-community:
    name: Benchmark Community World (${{ matrix.world.name }})
    if: ${{ !contains(github.event.pull_request.labels.*.name, 'workflow-server-test') }}
    needs: [build, getCommunityWorldsMatrix]
    strategy:
      fail-fast: false
      matrix: ${{ fromJson(needs.getCommunityWorldsMatrix.outputs.matrix) }}
    uses: ./.github/workflows/benchmark-community-world.yml
    with:
      world-id: ${{ matrix.world.id }}
      world-name: ${{ matrix.world.name }}
      world-package: ${{ matrix.world.package }}
      service-type: ${{ matrix.world.service-type }}
      env-vars: ${{ matrix.world.env-vars }}
      setup-command: ${{ matrix.world.setup-command }}
      # Run full suite only when manually triggered with full_suite=true
      full-suite: ${{ (github.event_name == 'workflow_dispatch' && inputs.full_suite) || contains(github.event.pull_request.labels.*.name, 'stress-test') }}
    secrets: inherit

  # Phase 3: Aggregate all benchmark results and create comparison
  summary:
    name: Benchmark Summary
    runs-on: ubuntu-latest
    needs: [benchmark-local, benchmark-postgres, benchmark-vercel, benchmark-community]
    if: always() && !cancelled()
    timeout-minutes: 10

    steps:
      - uses: actions/checkout@v4

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

      - name: List downloaded files
        run: find benchmark-results -type f -name "*.json" | sort

      # For PRs, download baseline results from the PR's base branch
      - name: Download baseline from PR base branch
        if: github.event_name == 'pull_request'
        continue-on-error: true
        uses: dawidd6/action-download-artifact@v6
        with:
          workflow: benchmarks.yml
          branch: ${{ github.event.pull_request.base.ref }}
          name: baseline-benchmark-results
          path: baseline-results
          if_no_artifact_found: warn

      - name: Aggregate and compare benchmarks
        id: aggregate
        run: |
          # Check if baseline results exist
          BASELINE_ARG=""
          if [ -d "baseline-results" ] && [ "$(ls -A baseline-results 2>/dev/null)" ]; then
            echo "Found baseline results from main branch"
            BASELINE_ARG="--baseline baseline-results"
          else
            echo "No baseline results found, showing results without comparison"
          fi
          # Capture output to both file and step summary
          node .github/scripts/aggregate-benchmarks.js benchmark-results $BASELINE_ARG --run-url "${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}" | tee benchmark-summary.md >> $GITHUB_STEP_SUMMARY

      - name: Check benchmark job statuses
        id: check-status
        run: |
          # Check if any benchmark jobs failed
          LOCAL_STATUS="${{ needs.benchmark-local.result }}"
          POSTGRES_STATUS="${{ needs.benchmark-postgres.result }}"
          VERCEL_STATUS="${{ needs.benchmark-vercel.result }}"
          COMMUNITY_STATUS="${{ needs.benchmark-community.result }}"

          echo "local=$LOCAL_STATUS" >> $GITHUB_OUTPUT
          echo "postgres=$POSTGRES_STATUS" >> $GITHUB_OUTPUT
          echo "vercel=$VERCEL_STATUS" >> $GITHUB_OUTPUT
          echo "community=$COMMUNITY_STATUS" >> $GITHUB_OUTPUT

          # Community world failures are warnings, not errors
          if [[ "$LOCAL_STATUS" == "failure" || "$POSTGRES_STATUS" == "failure" || "$VERCEL_STATUS" == "failure" ]]; then
            echo "has_failures=true" >> $GITHUB_OUTPUT
          else
            echo "has_failures=false" >> $GITHUB_OUTPUT
          fi

          if [[ "$COMMUNITY_STATUS" == "failure" ]]; then
            echo "has_warnings=true" >> $GITHUB_OUTPUT
          else
            echo "has_warnings=false" >> $GITHUB_OUTPUT
          fi

      - name: Update PR comment with results
        if: github.event_name == 'pull_request'
        uses: marocchino/sticky-pull-request-comment@v2
        with:
          header: benchmark-results
          path: benchmark-summary.md

      - name: Append failure notice to PR comment
        if: github.event_name == 'pull_request' && steps.check-status.outputs.has_failures == 'true'
        uses: marocchino/sticky-pull-request-comment@v2
        with:
          header: benchmark-results
          append: true
          message: |

            ---
            ❌ **Some benchmark jobs failed:**
            - Local: ${{ needs.benchmark-local.result }}
            - Postgres: ${{ needs.benchmark-postgres.result }}
            - Vercel: ${{ needs.benchmark-vercel.result }}

            Check the [workflow run](${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}) for details.

      - name: Append community warning to PR comment
        if: github.event_name == 'pull_request' && steps.check-status.outputs.has_warnings == 'true'
        uses: marocchino/sticky-pull-request-comment@v2
        with:
          header: benchmark-results
          append: true
          message: |

            ---
            ⚠️ **Community world benchmarks failed** (non-blocking):
            - Community Worlds: ${{ needs.benchmark-community.result }}

            Check the [workflow run](${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}) for details.

      # On main branch, save results as baseline for future PR comparisons
      - name: Upload baseline results
        if: github.event_name == 'push' && github.ref == 'refs/heads/main'
        uses: actions/upload-artifact@v4
        with:
          name: baseline-benchmark-results
          path: benchmark-results/
          retention-days: 90

  # Publish benchmark results to GitHub Pages (main branch only)
  publish-results:
    name: Publish Benchmark Results
    runs-on: ubuntu-latest
    needs: [summary]
    if: github.event_name == 'push' && github.ref == 'refs/heads/main'
    timeout-minutes: 5

    permissions:
      contents: write

    steps:
      - uses: actions/checkout@v4

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

      - name: Generate docs data
        run: |
          mkdir -p docs-data
          node .github/scripts/generate-docs-data.js \
            --type benchmarks \
            --results-dir benchmark-results \
            --output docs-data/benchmark-results.json \
            --commit "${{ github.sha }}" \
            --branch "${{ github.ref_name }}"

      - name: Deploy to GitHub Pages
        uses: peaceiris/actions-gh-pages@v4
        with:
          github_token: ${{ secrets.GITHUB_TOKEN }}
          publish_dir: ./docs-data
          destination_dir: ci
          keep_files: true