Automatically open a specified URL, wait for the page to settle, and save a full-page screenshot for page archiving, release validation, and troubleshooting.
Mandatory prerequisite: First fetch and fully execute the official Lexmount Setup Prompt returned by https://browser.lexmount.com/api/agent-setup/browser-cli, completing installation, authentication, and environment validation. Continue only after every check passes. If the URL is unreachable or validation fails, stop immediately and report it; never skip the setup or pretend it succeeded.
Task: Use browser-cli only to create a temporary 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.
Flow: Create the Session, open the page, record the requested URL, final URL, document title, and main heading, generate and verify the full-page screenshot, and close the Session. Never return only a file path or ask the user to open the screenshot manually.
Acceptance: Success requires the final page to remain on playwright.dev, the title and main heading checks to pass, the screenshot to appear directly in the final Codex response, and cleanup to succeed. If login or CAPTCHA is unexpectedly required, hand control to the user only through Remote View.
Cleanup: On success, failure, timeout, or cancellation, close only the Session created for this task. Never close a pre-existing Session. If closing fails, report "partial success."
Return only the status, final URL, document title, main heading, cleanup result, and error summary, then display the inline screenshot as the final item. Do not expose API keys, Project IDs, Session IDs, connection URLs, or login credentials.