Run a search in a cloud browser and extract result titles, links, and snippets as structured JSON for technical research and result aggregation.
Mandatory prerequisite: First fetch and fully execute the official Lexmount Setup Prompt returned by https://browser.lexmount.cn/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 open https://www.baidu.com/, search for “Playwright 浏览器自动化,” extract the first three non-advertising results, and save them to artifacts/search-results.json in the working directory.
Flow: Create a temporary Session, inspect the page and locate the search box, submit the query, wait for the results, extract each title, absolute URL, and optional summary, validate the JSON, and close the Session.
Acceptance: Success requires an existing, non-empty, parseable JSON file containing three valid results. If login or CAPTCHA is required, hand control to the user only through Remote View without reading or recording anything the user enters.
Cleanup: On success, failure, timeout, or cancellation, close only the Session created for this task. If closing fails, report “partial success.” Never close a pre-existing Session.
Return: Report only the status, final URL, result count, file path, cleanup result, and error summary. Do not expose API keys, Project IDs, Session IDs, connection URLs, or login credentials.