Claude could be told to wrap up and list remaining work when your usage is nearly spent.
A one-shot wrap-up hint at high five-hour usage sits behind a flag that falls back to false.
tengu_vellum_anchor 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 v2.1.229: on
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 v2.1.229. It isn't a statement about your account. What a flag value here can and cannot tell you
What's wrong with this entry?
When five-hour usage crosses a threshold, and you are not using or allowed extra overage, Claude Code arms a one-shot hint that tells the model to finish the current step, list at most 3 bullets of the most impactful remaining work, and not start subagents or long-running work. Off in this build: tengu_vellum_anchor falls back to false. Reports as usage_limit_near_wrapup.
- fires at most once per session, injected as a meta message rather than shown as UI text
[Usage limit approaching. Checkpoint now: finish the current step, then list up to 3 short bullets of the most impactful remaining work. Don't start subagents or long-running work.]
Strings lifted out of the shipped bundle, so the claim above can be checked against them.
Related
Other releases about the same thing. Found by shared names or similar wording; neither means one caused the other.
-
v2.1.234
Rate-limit prompts resolve model aliases to the model that actually answers
Both mention rate limit
-
v2.1.234
Quota rejections feed a new auto-resume controller
Both mention rate limit
-
v2.1.239
Spend and rate limit notices say when the limit resets
Both mention rate limit