test: test for issue 41348

[dgozman]

References #41348.

[github-actions]

Test results for "MCP"

7792 passed, 1269 skipped

---

Merge workflow run.

[github-actions]

Test results for "tests 1"

1 failed
❌ [playwright-test] › reporter.spec.ts:251 › merged › should not have internal error when steps are finished after timeout @windows-latest-node22

3 flaky

⚠️ [chromium-library] › library/beforeunload.spec.ts:130 › should support dismissing the dialog multiple times `@chromium-ubuntu-22.04-arm-node20`
⚠️ [chromium-library] › library/chromium/oopif.spec.ts:282 › should click `@chromium-ubuntu-22.04-arm-node20`
⚠️ [chromium-library] › library/video.spec.ts:699 › screencast › should capture full viewport on hidpi `@chromium-ubuntu-22.04-node20`

50188 passed, 1190 skipped

---

Merge workflow run.

[github-actions]

Hi, I'm the Playwright bot and I took a first look at the CI failures here.

🟡 The one failure is unrelated to your change, but I can't prove it's a known flake

[playwright-test] › reporter.spec.ts:251 › merged › should not have internal error when steps are finished after timeout timed out on windows-latest-node22. This PR only adds a test to tests/page/page-navigation.spec.ts, so the diff can't reach the test-runner reporter suite — but the same test hasn't failed on any other SHA in the results DB, so I'm calling it uncertain rather than a confirmed flake.

Details

Your diff adds a single page test and changes no product code or shared helper. The failing test exercises the @playwright/test reporter's timeout handling — a completely separate suite from tests/page/ — so there's no code path your change could influence.

Uncertain

• [playwright-test] › reporter.spec.ts:251 › should not have internal error when steps are finished after timeout — in the aggregated CI results this test is green in 4967 of 4968 runs; the single failure is this PR's own run (sha 81330e3, run 29911466278). A test about timeout behaviour that itself timedOut on Windows is a textbook infra/slowness signature, and the diff can't reach it — but per the triage hard rule I have no independent run where this test failed, so I can't stamp it a pre-existing flake outright. To be sure it's noise, I'd want to see it fail on an unrelated SHA, or a rerun of this job go green.

Everything else in the report is flaky/passed:

• tests 1 also lists 3 flaky tests (beforeunload.spec.ts:130, oopif.spec.ts:282, video.spec.ts:699) that passed on retry — all Chromium library tests untouched by this navigation-only change.

A rerun of the failed Windows job should clear this. My read: not caused by this PR.

_{Triaged by the Playwright bot - agent run}