external-browser-driverlisted

# Browser Control Browser Control currently controls Google Chrome through the OneWorks extension. Its browser-facing contract is transport-neutral so future extension transports, such as Firefox, can implement the same capability without renaming the product. 1. Call `chrome_capabilities` before using a capability family for the first time. Missing permissions are recoverable: ask the user to grant the named group from the Chrome extension popup, then retry. The OneWorks page reports permission state but never grants Chrome permissions itself. 2. Discover targets with `chrome_windows`, `chrome_tabs`, and `chrome_frames`. Never guess IDs or rely on an implicit current tab. 3. Reuse the returned `tab_id`, `frame_id`, and `document_id`. Refresh the target/snapshot after `TARGET_NOT_FOUND` or `DOCUMENT_CHANGED`. 4. Prefer `execute_chrome_workflow` for ordered page-local work. Independent tab workflows may be submitted together with `execute_chrome_workflows`. 5. High-risk operations return `CONFIRMATION_REQUIRED`; describe the audit summary and wait for the user to approve it in the extension/OneWorks UI before retrying. 6. Prefer semantic operations. Use `chrome_raw`, `chrome_cookies.list_with_values`, `chrome_page.snapshot_sensitive`, or `chrome_page.type_sensitive` only when the matching OneWorks advanced-access preference has been applied to the connected browser and capability discovery reports it enabled. Raw is a browser-session-wide superset of cookie/sensitive-field a