Follow Discord
Sweep 12 Nov 2026 · 23:00Z Build v2.1.323 540 read Stable v2.1.311 Latest v2.1.323 Next v2.1.323 Feeds RSS JSON llms.txt llms-full.txt Unofficial

Claude Code v2.1.323 ·

Rate-limit messages point to /usage-credits after the weekly overage limit

Hitting the weekly included overage limit now shows how to continue with /usage-credits or /model, and the old Fable limit wording is gone

Group of 2 Use it now Improvements
JSON All of v2.1.323
Use it nowTier: how much it should matter to you
3Useful: my rating, 1 to 5
2Signal: worth watching, 1 to 5
Usage & LimitsArea: what it touches
ImprovementsKind: in v2.1.323,
What probably matters to youSection of the release

What

When you hit a usage limit, Claude Code shows a rate-limit message. This release reworks those messages for the seven_day_overage_included limit, a weekly limit:

  • In the terminal: the message can now end with "Run /usage-credits to continue or switch models with /model." or with "/model to switch models." The longer text appears only when other conditions hold. /usage-credits is new text in this build.
  • In remote sessions: the message tells you to switch to another model to continue.
  • Removed wording: the "You've reached your Fable limit." variant is gone, and the usage-credits text in the spend-limit message is simpler.
  • Gate: a new check combines the gate tengu_sunny_mountain with another condition and falls back to off. A gate is a switch Anthropic can flip from its servers. Nearby are new helpers for the credit balance, the overage state and a blocked state. What this check opens has not been traced, and nothing has been read about the gate yet.
  • Test warnings: the old approaching-weekly, Opus and Sonnet warning cases were removed from the mock rate-limit messages.

Why

If you reach the weekly limit, the message now names the commands that let you keep going: /usage-credits to configure or request usage credits, or /model to switch models.

Read from
Feature flag
tengu_sunny_mountain 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 v2.1.323: 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 v2.1.323. It isn't a statement about your account. What a flag value here can and cannot tell you

How sure we are
Two sources agreeTwo things we can check say the same as this entry.
Anthropic's release notes agreeFixed the model picker and /model showing a picked effort level that CLAUDE_CODE_EFFORT_LEVEL overrides
The name it cites is new in this buildNew in this build: tengu_sunny_mountain

See this entry in the whole of v2.1.323 →

Feedback