A new system-prompt section named willow_tern tells the model how its final message should read: lead with the answer, one idea per sentence of roughly 20 words, no em-dashes or parentheticals, keep code and numbers out of prose, and no headers under about 500 words. Set CLAUDE_CODE_WILLOW_TERN to any truthy value to force it on. Otherwise it needs a server-side decision, and the flag it falls back to is compiled off.
- Three inputs are checked in order: the environment variable, a boolean
tengu_willow_ternkey in client data (non-boolean values are ignored with a debug line), then the flag itself with fallback false. - Even when the flag says yes, the section only applies to models carrying the
opus_5_prompt_bundletag. - When applied, a
tengu_willow_tern_appliedevent records whether client data supplied the decision.
- No em-dashes, no parentheticals, no arrows., tengu_willow_tern_applied
Strings lifted out of the shipped bundle, so the claim above can be checked against them.
tengu_willow_tern 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 v2.1.247: not a boolean we can read
Read once, for one account on one subscription tier, against v2.1.247. It isn't a statement about your account. What a flag value here can and cannot tell you
A reading is one sample. Claude Code evaluates its flags remotely, so no client sees the targeting rule behind a value and this says nothing about your account.
A reading is one sample. Claude Code evaluates its flags remotely, so no client sees the targeting rule behind a value and this says nothing about your account.
New in this build: CLAUDE_CODE_WILLOW_TERN