Follow Discord
Sweep 02 Oct 2026 · 18:55Z Build v2.1.288 509 read Stable v2.1.285 Latest v2.1.288 Next v2.1.288 Feeds RSS JSON llms.txt llms-full.txt Unofficial

Claude Code v2.1.288 ·

Groundwork for how long workflows pause at a usage limit

Workflow pauses for usage limits gain a check on whether they would wait, plus a new remotely set number with a cap

Nothing to try yet In Development
JSON All of v2.1.288
Nothing to try yetTier: how much it should matter to you
1Useful: my rating, 1 to 5
3Signal: worth watching, 1 to 5
Usage & LimitsArea: what it touches
In DevelopmentKind: in v2.1.288,
In DevelopmentSection of the release
What

When you hit a usage limit, automated workflows can pause until the limit resets. The part that handles this gains a check that answers whether it would wait for a given reset time, based on the conditions it already uses.

Claude Code also gains a new number read from its remote settings. It accepts a number or a number written as text, and keeps it between zero and a fixed maximum. When the server sends nothing, a built-in value is used.

Why

This could change how long agents pause while waiting for a usage limit to reset.

Read from
Feature flag
tengu_twinkling_swan Not enough to say

Nothing 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 v2.1.288: 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 v2.1.288. It isn't a statement about your account. What a flag value here can and cannot tell you

What has happened since
Flag reading moved The flag server now returns 60000 for tengu_twinkling_swan, read as this 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.
Flag reading moved The flag server now returns nothing at all, having stopped carrying it for tengu_twinkling_swan, read as this 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.

See this across every release →

How sure we are
Something disagreesSomething we can check disagrees with this entry, or the writer said they could not settle it.
The writer flagged doubtIt is not clear what the new number controls or what uses the new check.
The name it cites is new in this buildNew in this build: tengu_twinkling_swan

See this entry in the whole of v2.1.288 →

Feedback