Whether the "stone shell" memory prompt is served and whether the skill and plugin suggestion rollout is on are now fields on the per-process config object rather than loose module variables. Behaviour is unchanged.
- Both default to off: the suggestion rollout is decided by
tengu_saddle_lantern, the memory prompt bytengu_stone_shell. - The suggestion accessor still declines to latch a value whose source is a fallback, so it can be re-evaluated later.
return ((e.suggestRolloutEnabled ??= wBf().value), e.suggestRolloutEnabled);
Strings lifted out of the shipped bundle, so the claim above can be checked against them.
tengu_saddle_lantern Gate removed from the codeThis release deleted the gate from the code while it was still reading on for the account this site reads, so the code path no longer asks a flag before running.
This account: on · anonymous baseline: on · compiled default in v2.1.232: 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_stone_shell 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 v2.1.232: off
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 v2.1.232. 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.
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.
The code path no longer asks a flag before it runs.
The code path no longer asks a flag before it runs.