A new bashFirstSteerVariant experiment slot was added, gated by tengu_cozy_teapot and overridable via CLAUDE_CODE_COZY_TEAPOT
The per-session experiment-memoization system gained a new field, bashFirstSteerVariant, joining existing experiment slots like preReadLineDropped, leanPrompt, modelForPrompt, and delegationCostsFirst. It defaults to "strict" and can be controlled by the tengu_cozy_teapot gate or overridden with the CLAUDE_CODE_COZY_TEAPOT environment variable.
This is infrastructure for testing variants of the 'bash-first' steering wording that pushes Claude toward using Bash for edits, allowing the behavior to be adjusted per session without a code change.
Gate state
tengu_cozy_teapot 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 v2.1.274: 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 v2.1.274. It isn't a statement about your account. What a flag value here can and cannot tell you