Follow Discord
Sweep 27 Oct 2026 · 19:04Z Build v2.1.312 531 read Stable v2.1.308 Latest v2.1.312 Next v2.1.312 Feeds RSS JSON llms.txt llms-full.txt Unofficial

Claude Code v2.1.312 ·

Hooks that call a model now share a limit and may queue

Prompt and agent hooks now wait for a shared slot, and their time limit is the larger of their own and a minimum

You'll notice Improvements
JSON All of v2.1.312
You'll noticeTier: how much it should matter to you
2Useful: my rating, 1 to 5
2Signal: worth watching, 1 to 5
HooksArea: what it touches
ImprovementsKind: in v2.1.312,
ImprovementsSection of the release

Unclear How many model hooks can run at once, and what the minimum time limit is, are not known.

What

A hook is a command you configure to run automatically at certain moments. Prompt hooks and agent hooks are the kinds that ask a model to decide something. For these:

  • Shared limit: they now take turns through a shared limit on how many run at once, so when many fire together, some wait.
  • Time limit: each one's time limit is now the larger of its own timeout and a minimum. Before, it was its own timeout, or 30 seconds if none was set.
  • Overall limit: when any hook in a group calls a model, the time allowed for the whole group is extended by the default once.
Why

Many model hooks at once may now queue instead of all starting together, and a short timeout may be raised to the minimum, so they can finish later than you set.

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 doubtHow many model hooks can run at once, and what the minimum time limit is, are not known.

See this entry in the whole of v2.1.312 →

Feedback