test.yml

name: Tests

on:
  pull_request:
    types:
      - opened
      - synchronize
      - reopened
      - ready_for_review
    paths:
      - .github/workflows/test.yml
      - packages/browseros-agent/**
  workflow_dispatch:

permissions:
  contents: read

env:
  BROWSEROS_APPIMAGE_URL: https://files.browseros.com/download/BrowserOS.AppImage

jobs:
  test:
    name: Tests / ${{ matrix.suite }}
    runs-on: ubuntu-latest
    timeout-minutes: 20
    defaults:
      run:
        working-directory: packages/browseros-agent
    strategy:
      fail-fast: false
      matrix:
        include:
          - suite: agent-core-agent
            command: (cd packages/agent-core && bun run test:agent)
            junit_path: test-results/agent-core-agent.xml
            needs_browser: false
          - suite: agent-core-skills
            command: (cd packages/agent-core && bun run test:skills)
            junit_path: test-results/agent-core-skills.xml
            needs_browser: false
          - suite: agent-core-tools
            command: (cd packages/agent-core && bun run test:tools)
            junit_path: test-results/agent-core-tools.xml
            needs_browser: true
            needs_trios_server: true
          - suite: agent-core-browser
            command: (cd packages/agent-core && bun run test:browser)
            junit_path: test-results/agent-core-browser.xml
            needs_browser: false
          - suite: agent-core-integration
            command: (cd packages/agent-core && bun run test:integration)
            junit_path: test-results/agent-core-integration.xml
            needs_browser: true
          - suite: agent-core-lib
            command: (cd packages/agent-core && bun run test:lib)
            junit_path: test-results/agent-core-lib.xml
            needs_browser: false
          - suite: agent-core-root
            command: (cd packages/agent-core && bun run test:root)
            junit_path: test-results/agent-core-root.xml
            needs_browser: false
          - suite: agent
            command: (cd apps/agent && bun run test)
            junit_path: test-results/agent.xml
            needs_browser: false
          - suite: agent-typecheck
            command: (cd apps/agent && bun run typecheck)
            junit_path: test-results/agent-typecheck.xml
            needs_browser: false
          - suite: eval
            command: (cd apps/eval && bun run test)
            junit_path: test-results/eval.xml
            needs_browser: false
          - suite: shared
            command: (cd packages/shared && bun test --reporter=junit --reporter-outfile="$BROWSEROS_JUNIT_PATH")
            junit_path: test-results/shared.xml
            needs_browser: false
          - suite: cdp-protocol
            command: (cd packages/cdp-protocol && bun test --reporter=junit --reporter-outfile="$BROWSEROS_JUNIT_PATH")
            junit_path: test-results/cdp-protocol.xml
            needs_browser: false
          - suite: build
            command: bun run ./scripts/run-bun-test.ts ./scripts/build
            junit_path: test-results/build.xml
            needs_browser: false

    steps:
      - name: Checkout code
        uses: actions/checkout@v6

      - name: Setup Bun
        uses: oven-sh/setup-bun@v2

      - name: Install dependencies
        run: bun ci

      - name: Resolve BrowserOS cache key
        if: matrix.needs_browser == true
        id: browseros-cache-key
        run: |
          set -euo pipefail
          headers="$(curl -fsSI "$BROWSEROS_APPIMAGE_URL")"
          etag="$(printf '%s\n' "$headers" | awk 'BEGIN{IGNORECASE=1} /^etag:/ {sub(/\r$/, "", $2); gsub(/"/, "", $2); print $2; exit}')"
          last_modified="$(printf '%s\n' "$headers" | awk 'BEGIN{IGNORECASE=1} /^last-modified:/ {$1=""; sub(/^ /, ""); sub(/\r$/, ""); print; exit}')"
          raw_key="${etag:-$last_modified}"
          if [ -z "$raw_key" ]; then
            raw_key="$BROWSEROS_APPIMAGE_URL"
          fi
          cache_key="$(printf '%s' "$raw_key" | shasum -a 256 | awk '{print $1}')"
          echo "key=browseros-appimage-${{ runner.os }}-$cache_key" >> "$GITHUB_OUTPUT"

      - name: Restore BrowserOS cache
        if: matrix.needs_browser == true
        id: browseros-cache
        uses: actions/cache@v4
        with:
          path: packages/browseros-agent/.ci/bin/BrowserOS.AppImage
          key: ${{ steps.browseros-cache-key.outputs.key }}

      - name: Download BrowserOS
        if: matrix.needs_browser == true && steps.browseros-cache.outputs.cache-hit != 'true'
        run: |
          mkdir -p .ci/bin
          curl -fsSL "$BROWSEROS_APPIMAGE_URL" -o .ci/bin/BrowserOS.AppImage
          chmod +x .ci/bin/BrowserOS.AppImage

      - name: Prepare BrowserOS wrapper
        if: matrix.needs_browser == true
        run: |
          mkdir -p .ci/bin
          cat > .ci/bin/browseros <<'EOF'
          #!/usr/bin/env bash
          set -euo pipefail
          export APPIMAGE_EXTRACT_AND_RUN=1
          exec "$(dirname "$0")/BrowserOS.AppImage" "$@"
          EOF
          chmod +x .ci/bin/browseros

      - name: Checkout trios (Rust production server)
        if: matrix.needs_trios_server == true
        uses: actions/checkout@v6
        with:
          repository: gHashTag/trios
          path: trios-src

      - name: Rust toolchain (trios-server)
        if: matrix.needs_trios_server == true
        uses: dtolnay/rust-toolchain@stable

      - name: Cache trios-server build
        if: matrix.needs_trios_server == true
        uses: actions/cache@v4
        with:
          path: |
            ~/.cargo/registry
            ~/.cargo/git
            trios-src/target
          key: ${{ runner.os }}-trios-server-${{ hashFiles('trios-src/Cargo.lock') }}

      - name: Build trios-server
        if: matrix.needs_trios_server == true
        working-directory: ${{ github.workspace }}/trios-src
        run: cargo build -p trios-server --locked

      - name: Create agent-core env file
        working-directory: packages/browseros-agent/packages/agent-core
        run: cp .env.example .env.development

      - name: Run ${{ matrix.suite }} tests
        id: test
        env:
          BROWSEROS_BINARY: ${{ github.workspace }}/packages/browseros-agent/.ci/bin/browseros
          TRIOS_SERVER_BIN: ${{ matrix.needs_trios_server == true && format('{0}/trios-src/target/debug/trios-server', github.workspace) || '' }}
          BROWSEROS_TEST_HEADLESS: "true"
          BROWSEROS_TEST_EXTRA_ARGS: --no-sandbox --disable-dev-shm-usage
          BROWSEROS_JUNIT_PATH: ${{ github.workspace }}/packages/browseros-agent/${{ matrix.junit_path }}
        run: |
          set +e
          mkdir -p test-results
          ${{ matrix.command }}
          exit_code=$?
          if [ ! -f "${{ matrix.junit_path }}" ]; then
            if [ "$exit_code" = "0" ]; then
              cat > "${{ matrix.junit_path }}" <<EOF
          <?xml version="1.0" encoding="UTF-8"?>
          <testsuites tests="0" failures="0">
            <testsuite name="${{ matrix.suite }}" tests="0" failures="0">
            </testsuite>
          </testsuites>
          EOF
            else
              cat > "${{ matrix.junit_path }}" <<EOF
          <?xml version="1.0" encoding="UTF-8"?>
          <testsuites tests="1" failures="1">
            <testsuite name="${{ matrix.suite }}" tests="1" failures="1">
              <testcase classname="workflow" name="${{ matrix.suite }} setup">
                <failure message="Test run failed before JUnit output was written">See workflow logs for details.</failure>
              </testcase>
            </testsuite>
          </testsuites>
          EOF
            fi
          fi
          echo "exit_code=$exit_code" >> "$GITHUB_OUTPUT"

      - name: Upload JUnit XML
        if: always()
        uses: actions/upload-artifact@v4
        with:
          name: junit-${{ matrix.suite }}
          path: packages/browseros-agent/${{ matrix.junit_path }}

      - name: Summarize suite result
        if: always()
        run: |
          if [ "${{ steps.test.outputs.exit_code }}" = "0" ]; then
            echo "### :white_check_mark: ${{ matrix.suite }} suite passed" >> "$GITHUB_STEP_SUMMARY"
          else
            echo "### :x: ${{ matrix.suite }} suite failed (exit code ${{ steps.test.outputs.exit_code }})" >> "$GITHUB_STEP_SUMMARY"
            echo "" >> "$GITHUB_STEP_SUMMARY"
            echo "See the uploaded \`junit-${{ matrix.suite }}\` artifact for details." >> "$GITHUB_STEP_SUMMARY"
            exit 1
          fi

  comment:
    name: PR test summary
    needs: test
    if: >-
      always()
      && github.event_name == 'pull_request'
      && github.event.pull_request.head.repo.full_name == github.repository
    runs-on: ubuntu-latest
    permissions:
      pull-requests: write
      actions: read
    steps:
      - name: Download JUnit artifacts
        uses: actions/download-artifact@v4
        continue-on-error: true
        with:
          path: junit
          pattern: junit-*

      - name: Build comment body
        run: |
          python3 <<'PY'
          import glob, os, xml.etree.ElementTree as ET

          run_url = f"{os.environ['GITHUB_SERVER_URL']}/{os.environ['GITHUB_REPOSITORY']}/actions/runs/{os.environ['GITHUB_RUN_ID']}"
          marker = "<!-- browseros-agent-tests-summary -->"

          suites = []
          failed_cases = []
          total_tests = total_failed = total_skipped = 0

          for xml_path in sorted(glob.glob("junit/junit-*/*.xml")):
              suite_name = os.path.basename(os.path.dirname(xml_path)).removeprefix("junit-")
              try:
                  root = ET.parse(xml_path).getroot()
              except ET.ParseError:
                  suites.append({"name": suite_name, "passed": 0, "failed": 1, "skipped": 0, "total": 1})
                  total_tests += 1
                  total_failed += 1
                  failed_cases.append((suite_name, "(could not parse junit XML)"))
                  continue

              testsuites = root.findall("testsuite") if root.tag == "testsuites" else [root]
              s_tests = s_fail = s_err = s_skip = 0
              for ts in testsuites:
                  s_tests += int(ts.get("tests") or 0)
                  s_fail += int(ts.get("failures") or 0)
                  s_err += int(ts.get("errors") or 0)
                  s_skip += int(ts.get("skipped") or 0)
                  for tc in ts.iter("testcase"):
                      if tc.find("failure") is not None or tc.find("error") is not None:
                          cls = tc.get("classname") or ""
                          name = tc.get("name") or "(unnamed)"
                          label = f"{cls} > {name}" if cls else name
                          failed_cases.append((suite_name, label))

              s_failed = s_fail + s_err
              s_passed = max(s_tests - s_failed - s_skip, 0)
              suites.append({"name": suite_name, "passed": s_passed, "failed": s_failed, "skipped": s_skip, "total": s_tests})
              total_tests += s_tests
              total_failed += s_failed
              total_skipped += s_skip

          total_passed = max(total_tests - total_failed - total_skipped, 0)

          if total_tests == 0:
              header = "## :warning: No test results were produced"
          elif total_failed == 0:
              header = f"## :white_check_mark: Tests passed — {total_passed}/{total_tests}"
          else:
              header = f"## :x: Tests failed — {total_failed}/{total_tests} failed"

          lines = [marker, header, ""]
          if suites:
              lines.append("| Suite | Passed | Failed | Skipped |")
              lines.append("|-------|--------|--------|---------|")
              for s in suites:
                  icon = ":white_check_mark:" if s["failed"] == 0 and s["total"] > 0 else ":warning:" if s["total"] == 0 else ":x:"
                  lines.append(f"| {icon} `{s['name']}` | {s['passed']}/{s['total']} | {s['failed']} | {s['skipped']} |")

          if failed_cases:
              lines += ["", "<details open>", "<summary><b>Failed tests</b></summary>", ""]
              for suite_name, label in failed_cases[:50]:
                  lines.append(f"- **{suite_name}** — `{label}`")
              if len(failed_cases) > 50:
                  lines.append(f"- …and {len(failed_cases) - 50} more")
              lines += ["", "</details>"]

          lines += ["", f"[View workflow run]({run_url})"]

          with open("comment.md", "w") as f:
              f.write("\n".join(lines) + "\n")
          PY

      - name: Upsert sticky PR comment
        uses: actions/github-script@v7
        with:
          script: |
            const fs = require('fs');
            const body = fs.readFileSync('comment.md', 'utf8');
            const marker = '<!-- browseros-agent-tests-summary -->';
            const { owner, repo } = context.repo;
            const issue_number = context.payload.pull_request.number;

            const triggerSha = context.payload.pull_request.head.sha;
            const { data: pr } = await github.rest.pulls.get({ owner, repo, pull_number: issue_number });
            if (pr.head.sha !== triggerSha) {
              core.info(`PR head has moved (${pr.head.sha} vs ${triggerSha}) — skipping stale comment.`);
              return;
            }

            const comments = await github.paginate(github.rest.issues.listComments, {
              owner, repo, issue_number, per_page: 100,
            });
            const existing = comments.find(c => c.body && c.body.includes(marker));
            if (existing) {
              await github.rest.issues.updateComment({ owner, repo, comment_id: existing.id, body });
            } else {
              await github.rest.issues.createComment({ owner, repo, issue_number, body });
            }