Unclear Only the description of the signal changed visibly, so it is not confirmed that the code computing it changed the same way.
Claude Code keeps an internal signal for whether your account is in a grace window, a short allowance past a usage limit. Before, the signal stayed set once it had been seen on a response to a request that asked for extended usage.
Now it follows the latest response to either the main conversation or a subagent, which is a helper Claude runs separately for a task. It clears when the limiter reports no grace use. It ignores:
- side calls outside the main conversation and subagents
- responses that carry no usage-limit status
- refusals of requests that were over the limit
The grace indicator may now turn on and off at different moments than before. The request for extended usage is sent only when a server-side switch allows it, and that switch is off unless it is turned on remotely.
tengu_lantern_spool 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 v2.1.282: 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 v2.1.282. 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.
Only the description of the signal changed visibly, so it is not confirmed that the code computing it changed the same way.