The hint at the end of a summarized thinking block (a condensed version of Claude's reasoning) is now chosen by a fixed rule rather than remote switches:
- Models with a particular server-declared capability show no hint at all.
- Every other model shows a faint " · summary".
Before, with neither switch on, the hint read " · summarized". The terminal interface uses the same rule, and the VS Code extension receives the result as narration_hint. The two remote switches that used to pick the style, tengu_lilac_dune and tengu_quizzical_shore, are no longer read.
The faint " · summary" wording is now the default for everyone, so most people will see the hint change.
tengu_lilac_dune Off in both readingsThe flag server returned off for the account this site reads and for the anonymous baseline. A reading of off cannot rule out a rollout these two readings sit outside of.
This account: off · anonymous baseline: off · compiled default in v2.1.282: 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.
tengu_quizzical_shore Off in both readingsThe flag server returned off for the account this site reads and for the anonymous baseline. A reading of off cannot rule out a rollout these two readings sit outside of.
This account: off · anonymous baseline: off · compiled default in v2.1.282: 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 v2.1.282. It isn't a statement about your account. What a flag value here can and cannot tell you
Which models declare the capability that hides the hint is decided by the server and is not known.