Unclear Whether Claude Code now actually keeps the thinking, or only the wording changed, is not settled.
The warning shown when you resume a session holding Claude's thinking from a different organisation has been rewritten. It used to say Claude's earlier thinking would be removed. It now says Claude can't use it, that it isn't deleted, and that you can resume the session signed in to that organisation to use it again.
The warning still depends on the model supporting this check and on a server-side switch that is off unless turned on remotely. In readings taken before this release, that switch was on for this site's account and for an anonymous baseline.
The earlier wording suggested the thinking was lost for good. The new wording says it can be recovered by signing in to the right organisation.
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 v2.1.284: 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 v2.1.284. It isn't a statement about your account. What a flag value here can and cannot tell you
A reading is one sample. Claude Code evaluates its flags remotely, so no client sees the targeting rule behind a value and this says nothing about your account.
A reading is one sample. Claude Code evaluates its flags remotely, so no client sees the targeting rule behind a value and this says nothing about your account.
A reading is one sample. Claude Code evaluates its flags remotely, so no client sees the targeting rule behind a value and this says nothing about your account.
A reading is one sample. Claude Code evaluates its flags remotely, so no client sees the targeting rule behind a value and this says nothing about your account.
A reading is one sample. Claude Code evaluates its flags remotely, so no client sees the targeting rule behind a value and this says nothing about your account.
A reading is one sample. Claude Code evaluates its flags remotely, so no client sees the targeting rule behind a value and this says nothing about your account.
A reading is one sample. Claude Code evaluates its flags remotely, so no client sees the targeting rule behind a value and this says nothing about your account.
A reading is one sample. Claude Code evaluates its flags remotely, so no client sees the targeting rule behind a value and this says nothing about your account.
Whether Claude Code now actually keeps the thinking, or only the wording changed, is not settled.