Sweep 19 Sep 2026 · 02:36Z Build v2.1.278 500 read Stable v2.1.267 Latest v2.1.278 Next v2.1.278 Feeds RSS JSON llms.txt Unofficial
Claude Code v2.1.274 ·

New bash-first prompt steer variant experiment slot

A new bashFirstSteerVariant experiment slot was added, gated by tengu_cozy_teapot and overridable via CLAUDE_CODE_COZY_TEAPOT

TierNothing to try yethow much it should matter to you
Useful2my rating, 1 to 5
Signal3worth watching, 1 to 5
AreaPrompt Experimentswhat it touches
KindIn Developmentin v2.1.274,
Nothing to try yet Notable No documentation found

A new bashFirstSteerVariant experiment slot was added, gated by tengu_cozy_teapot and overridable via CLAUDE_CODE_COZY_TEAPOT

What

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.

Why

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

Read from
Names in the bundletengu_cozy_teapotCLAUDE_CODE_COZY_TEAPOT
Feature flag
tengu_cozy_teapot Not enough to say

Nothing 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

See this entry in the whole of v2.1.274 →