Thinking is the step where the model reasons before it answers, and a keyboard shortcut normally lets you turn it on or off. On models where thinking is always on, that shortcut now shows a notification saying thinking can't be turned off for that model. Before, it opened the toggle.
Why
You are told directly that thinking stays on for that model, instead of getting a toggle that has no effect.
How sure we are
One source agreesOne thing we can check says the same as this entry.
Anthropic's release notes agreeImproved screen-reader output in /mcp: a disabled server is read as "off" instead of "pending"
