Browser agents see their screenshots and keep their page

Screenshots from the browser and browserless_screenshot tools now reach the model. Before, any image over 64 KiB (almost every screenshot) was silently dropped; images now have their own 5 MiB budget, and a dropped image is named in the tool result.

Browserless tools and the browser tool share one browser per session, and now run one at a time instead of racing on the same page. browserless_content, browserless_scrape and browserless_screenshot read in a tab of their own, so they no longer move the page the agent is working in.

A browser key press now reports where focus landed (Pressed Tab. Focus is on link "Vision".), and read_page marks the focused element, which makes keyboard and accessibility testing practical.

Connecting a connector that is turned off for the organization now says so, and where an admin turns it on, instead of reporting an unknown connector.