Unclear What this experiment and the new beta entry control is not known.
Claude Code now looks up a remote experiment setting named tengu_curried_trinket. An experiment setting is a value the server sends to decide which version of a feature an account gets. The name existed before, and it now appears in two more lists of settings Claude Code checks. If the server sends nothing, it falls back to control, the usual name for the unchanged version.
A new entry was also added to the list of beta features Claude Code can ask the API for. Beta features are API capabilities that are still being tested. This one is requested only when a certain condition holds.
This looks like an experiment being prepared. It changes nothing you can see until it is used.
tengu_curried_trinket 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 v2.1.318: 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 v2.1.318. 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.
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.
What this experiment and the new beta entry control is not known.