Sometimes you resume a session that was last used under a different organisation from the one you are logged in with now. If that conversation already contains Claude's thinking (its reasoning before it answers), Claude Code can now warn you. The warning says:
- Claude's earlier thinking will be removed
- the next response may be slower and use more tokens
The warning appears only when the model supports this check and a server-side switch is on. That switch is off unless it is turned on remotely. In readings taken before this release, it was on for this site's account and for an anonymous baseline.
If you switch between organisations and then resume a session, you get an explanation for a slower, more expensive next turn.
tengu_lexical_glade Off by default, switched on for this accountThe shipped code defaults this off, and the flag server returned on for the one account this site reads on this version. That is the reading that makes the entry above worth a second look, and it still says nothing about your account.
This account: on · anonymous baseline: on · compiled default in v2.1.283: off
These values were read against a different version of Claude Code, so treat them as the nearest reading available instead of one taken on this release.
Read once, for one account on one subscription tier, against v2.1.283. It isn't a statement about your account. What a flag value here can and cannot tell you
It is not clear whether only the warning is new, or whether recording which organisation used a session is new as well.