Execute Playwright/TypeScript automation code against an existing Kernel browser session. This is the primary way to drive a browser: navigation, clicks, form fills, and extraction all belong here rather than in raw coordinate input. This tool is a thin passthrough: it runs your code in the browser’s VM and returns the result. It does not manage browser lifecycle — create and delete sessions with manage_browsers.
session_id is required. Unlike earlier versions, this tool no longer creates a browser when session_id is omitted, and no longer deletes the browser after execution. Create a session with manage_browsers (action create), pass its session_id here, then delete it with manage_browsers when done.
Use the
screenshot tool instead of
page.screenshot() in your code. To read page state, return only what you need — prefer a targeted selector (e.g.
await page.locator('h1').innerText()) or a region-scoped accessibility snapshot (e.g.
await page.locator('main').ariaSnapshot()) rather than dumping the whole page. An
ariaSnapshot() gives you the accessibility tree, which is usually a better way to locate an element than reading pixels off a screenshot.
Parameters
Example
Returns:
To capture a video recording around your automation, start a recording with
manage_replays before your calls and stop it when done.
