Follow Discord
Sweep 06 Nov 2026 · 01:32Z Build v2.1.319 537 read Stable v2.1.311 Latest v2.1.318 Next v2.1.319 Feeds RSS JSON llms.txt llms-full.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

Nothing to try yet Notable No documentation found In Development
JSON All of v2.1.274
Nothing to try yetTier: how much it should matter to you
2Useful: my rating, 1 to 5
3Signal: worth watching, 1 to 5
Prompt ExperimentsArea: what it touches
In DevelopmentKind: in v2.1.274,
What probably matters to youSection of the release
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
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 →

Feedback