Follow Discord
Sweep 30 Oct 2026 · 21:36Z Build v2.1.315 533 read Stable v2.1.308 Latest v2.1.314 Next v2.1.315 Feeds RSS JSON llms.txt llms-full.txt Unofficial

Claude Code v2.1.315 ·

Another model override now turns off relative subagent effort

Asking a subagent for lower or higher effort is now also turned off when a second kind of model override is set

You'll notice Improvements
JSON All of v2.1.315
You'll noticeTier: how much it should matter to you
2Useful: my rating, 1 to 5
2Signal: worth watching, 1 to 5
SubagentsArea: what it touches
ImprovementsKind: in v2.1.315,
ImprovementsSection of the release

Unclear It is not stated which setting the new model override reads.

What

The option that lets Claude ask a subagent (a helper it starts for part of a task) for lower or higher effort than its own now has one more condition. It is also turned off when a second kind of model override is in place, alongside CLAUDE_CODE_SUBAGENT_MODEL_FORCE and the override it already checked.

It is otherwise unchanged. It stays off unless CLAUDE_CODE_SNAPPY_PELICAN is set or it is switched on remotely. The server returned off for this site's account and for an anonymous check, both read before this release.

Why

Fewer sessions will get this option, because any of these model overrides now switches it off.

Read from
Feature flag
tengu_snappy_pelican Off in both readings

The 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 v2.1.315: 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 v2.1.315. It isn't a statement about your account. What a flag value here can and cannot tell you

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 stated which setting the new model override reads.

See this entry in the whole of v2.1.315 →

Feedback