name: E2E Desktop on: workflow_call: permissions: contents: read concurrency: group: e2e-desktop-${{ github.ref }} cancel-in-progress: true jobs: e2e: name: Playwright E2E (Linux) runs-on: ubuntu-latest timeout-minutes: 20 steps: - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2 # ── System deps for Electron on headless Ubuntu ─────────────────── # Electron needs GTK, NSS,atk, etc. even under xvfb. Playwright's # install-deps covers browsers; for Electron we install the apt # packages directly. - name: Install system dependencies for Electron run: | sudo apt-get update -qq sudo apt-get install -y -qq \ xvfb \ libgtk-3-0 libnotify4 libnss3 libxss1 libxtst6 \ xdg-utils libatspi2.0-0 libdrm2 libgbm1 libasound2t64 # ── Node ─────────────────────────────────────────────────────────── - uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020 # v4 with: node-version: 22 cache: npm # Full npm ci (not --ignore-scripts): electron's postinstall # downloads the binary we launch, and node-pty's native build is # needed for the terminal pane. - uses: ./.github/actions/retry with: command: npm ci # ── Python (for the hermes serve backend) ────────────────────────── - name: Install uv uses: astral-sh/setup-uv@fac544c07dec837d0ccb6301d7b5580bf5edae39 # 8.2.0 with: enable-cache: true cache-dependency-glob: | pyproject.toml uv.lock - name: Set up Python 3.11 run: uv python install 3.11 - name: Install Python dependencies uses: ./.github/actions/retry with: command: uv sync --locked --python 3.11 --extra all --extra dev # ── Build desktop app ───────────────────────────────────────────── - run: npm run --prefix apps/desktop build # ── Restore visual baseline screenshots from main ────────────────── # Baselines are generated on main (via --update-snapshots) and cached. # On PRs, we restore them so toHaveScreenshot has something to compare # against. The cache key is keyed on the desktop source files so a # UI change naturally invalidates it — but we fall back to the main # cache to avoid cold starts on unrelated PRs. - name: Restore visual baseline screenshots id: restore-baselines uses: actions/cache@0400d5f644dc74513175e3cd8d07132dd4860809 # v4.2.4 with: path: apps/desktop/e2e/*-snapshots key: visual-baselines-${{ github.ref_name }} restore-keys: | visual-baselines-main # ── Run Playwright E2E under xvfb ───────────────────────────────── # xvfb runs at a fixed 1280x1024 screen so the 1220x800 Electron # window always has a consistent viewport for screenshot comparison. # On main, we run with --update-snapshots to generate baselines. - name: Run Playwright E2E tests working-directory: apps/desktop run: | if [ "${{ github.ref_name }}" = "main" ]; then echo "On main — generating/updating baseline screenshots" xvfb-run -a --server-args="-screen 0 1280x1024x24" \ npx playwright test --reporter=list --update-snapshots else echo "On PR — comparing against cached baselines" xvfb-run -a --server-args="-screen 0 1280x1024x24" \ npx playwright test --reporter=list fi env: CI: "true" # Ensure no real API keys leak into the test env. OPENROUTER_API_KEY: "" OPENAI_API_KEY: "" NOUS_API_KEY: "" # ── Save updated baselines to cache (main only) ─────────────────── - name: Save updated baselines to cache if: github.ref_name == 'main' && always() uses: actions/cache/save@0400d5f644dc74513175e3cd8d07132dd4860809 # v4.2.4 with: path: apps/desktop/e2e/*-snapshots key: visual-baselines-main # ── Upload Playwright report (HTML + traces) ────────────────────── - name: Upload Playwright report id: upload-report if: always() uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1 with: name: playwright-report-${{ github.sha }} path: apps/desktop/playwright-report retention-days: 14 overwrite: true # ── Upload test results (screenshots, traces, diffs) ─────────────── - name: Upload test results id: upload-results if: always() uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1 with: name: playwright-test-results-${{ github.sha }} path: apps/desktop/test-results retention-days: 14 overwrite: true # ── Upload just the visual diffs (small, fast to review) ────────── - name: Upload visual diffs id: upload-diffs if: always() && github.ref_name != 'main' uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1 with: name: visual-diffs-${{ github.sha }} path: | apps/desktop/test-results/**/*-diff.png apps/desktop/test-results/**/*-actual.png apps/desktop/test-results/**/*-expected.png retention-days: 14 overwrite: true if-no-files-found: ignore # ── Generate step summary with visual diff info ─────────────────── # Parse the JSON report + scan for diff images, then post a summary # to the GitHub Actions step output so reviewers can see what changed # without downloading artifacts. Runs AFTER uploads so it can link # the artifact download URLs from their step outputs. - name: Generate visual diff summary if: always() working-directory: apps/desktop env: REPORT_URL: ${{ steps.upload-report.outputs.artifact-url }} RESULTS_URL: ${{ steps.upload-results.outputs.artifact-url }} DIFFS_URL: ${{ steps.upload-diffs.outputs.artifact-url }} run: | echo "## Desktop E2E — Visual Diff Report" >> "$GITHUB_STEP_SUMMARY" echo "" >> "$GITHUB_STEP_SUMMARY" # Count diff images (playwright writes *-diff.png on mismatch) DIFF_COUNT=$(find test-results -name '*-diff.png' 2>/dev/null | wc -l) ACTUAL_COUNT=$(find test-results -name '*-actual.png' 2>/dev/null | wc -l) if [ "$DIFF_COUNT" -eq 0 ]; then echo "✅ All $ACTUAL_COUNT screenshot(s) matched their baselines (or no baselines existed yet)." >> "$GITHUB_STEP_SUMMARY" else echo "📸 **$DIFF_COUNT of $ACTUAL_COUNT screenshot(s) differ from baseline:**" >> "$GITHUB_STEP_SUMMARY" echo "" >> "$GITHUB_STEP_SUMMARY" echo "| Test | Diff | Actual | Expected |" >> "$GITHUB_STEP_SUMMARY" echo "|------|------|--------|----------|" >> "$GITHUB_STEP_SUMMARY" # List each diff image with a link to the artifact for diff in $(find test-results -name '*-diff.png' 2>/dev/null | sort); do base=$(echo "$diff" | sed 's/-diff\.png$//') test_name=$(basename "$base") echo "| $test_name | [diff]($diff) | [actual](${base}-actual.png) | [expected](${base}-expected.png) |" >> "$GITHUB_STEP_SUMMARY" done fi echo "" >> "$GITHUB_STEP_SUMMARY" echo "📥 **Artifacts:**" >> "$GITHUB_STEP_SUMMARY" echo "" >> "$GITHUB_STEP_SUMMARY" if [ -n "$RESULTS_URL" ]; then echo "- [playwright-test-results]($RESULTS_URL) — all screenshots (actual + expected + diff) + traces" >> "$GITHUB_STEP_SUMMARY" fi if [ -n "$REPORT_URL" ]; then echo "- [playwright-report]($REPORT_URL) — interactive HTML report" >> "$GITHUB_STEP_SUMMARY" fi if [ -n "$DIFFS_URL" ]; then echo "- [visual-diffs]($DIFFS_URL) — just the diffed screenshots (small, fast to review)" >> "$GITHUB_STEP_SUMMARY" fi echo "" >> "$GITHUB_STEP_SUMMARY" echo "**To update baselines:** merge to main (baselines auto-update on main runs) or run \`npx playwright test --update-snapshots\` locally." >> "$GITHUB_STEP_SUMMARY" # Also parse the JSON report for pass/fail counts if [ -f playwright-report/results.json ]; then echo "" >> "$GITHUB_STEP_SUMMARY" echo "### Test Results" >> "$GITHUB_STEP_SUMMARY" echo "" >> "$GITHUB_STEP_SUMMARY" node -e " const r = require('./playwright-report/results.json'); const stats = r.stats || {}; console.log('| Status | Count |'); console.log('|--------|-------|'); console.log('| ✅ Passed | ' + (stats.expected || 0) + ' |'); console.log('| ❌ Failed | ' + (stats.unexpected || 0) + ' |'); console.log('| ⏭️ Skipped | ' + (stats.skipped || 0) + ' |'); console.log('| 🔄 Flaky | ' + (stats.flaky || 0) + ' |'); " >> "$GITHUB_STEP_SUMMARY" 2>/dev/null || true fi