Open a webpage and capture a screenshot

Prerequisite:
Fetch and fully execute the official Lexmount Setup Prompt returned by https://browser.lexmount.cn/api/agent-setup/browser-cli.
Continue only after installation, authentication, and environment validation all pass; otherwise stop and report the failure truthfully.

Task:
Use browser-cli only to create one temporary Lexmount Cloud Browser Session, open https://playwright.dev/docs/intro, wait for the page to become stable, verify that the document title contains "Playwright" and the main heading is "Installation," and capture a full-page screenshot for direct display in the final Codex response.

Execution:
1. Record the requested URL, final URL, document title, and main heading.
2. Generate the full-page screenshot and verify that it exists, is non-empty, and is a valid PNG.
3. If login or CAPTCHA is unexpectedly required, hand control to the user only through Remote View.
4. Close the Session.

Acceptance:
The final page must remain on playwright.dev, the title and heading checks must pass, and the screenshot must appear directly in the final Codex response. If the main task succeeds but cleanup fails, report partial success.

Cleanup:
On success, failure, timeout, or cancellation, close only the Session created by this task. Never close a pre-existing Session.

Return:
Report only the status, final URL, document title, main heading, cleanup result, and sanitized error summary, then display the inline screenshot as the final item. Do not expose API keys, Project IDs, Session IDs, connect URLs, WebSocket URLs, or login credentials.

npx create-lexmount-app --template screenshot --language typescript --cloud cn