Claude Code can now keep extended-thinking content across any model switch, not just upgrades
When you switch the model Claude Code is using mid-session, the app has to decide what to do with 'extended thinking' blocks (the model's visible step-by-step reasoning) produced by the previous model. Previously this was a simple yes/no choice, and thinking blocks were only kept when the switch was an upgrade to a newer model. That setting now has three possible values:
all- keep thinking blocks across any model change, upgrade or notupgrade- keep them only when switching to a newer model, the previous behaviournone- drop them
A new telemetry event, api_keep_thinking_on_model_change, is recorded when the all behaviour applies.
This gives more flexibility around preserving a model's prior reasoning when you change models, rather than only on upgrades. It's controlled by a gate (an internal switch Anthropic uses to turn features on for some accounts), so which behaviour applies isn't something you can tell from this release alone.
tengu_rustling_pixel Not enough to sayNothing here resolved what this flag was doing on this version, so nothing here should be read as on or off.
This account: no value returned · anonymous baseline: no value returned · compiled default in v2.1.280: not a boolean we can read
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 v2.1.280. It isn't a statement about your account. What a flag value here can and cannot tell you
Whether this gate is enabled for any given account, including this site's, is not established by the finding.
New in this build: tengu_rustling_pixel