Follow Discord
Sweep 08 Oct 2026 · 18:53Z Build v2.1.295 516 read Stable v2.1.286 Latest v2.1.295 Next v2.1.295 Feeds RSS JSON llms.txt llms-full.txt Unofficial

Claude Code v2.1.290 ·

Effort setting can be held back for some models

Claude Code can now leave the effort level unset for some models instead of taking it from your settings

You'll notice Improvements
JSON All of v2.1.290
You'll noticeTier: how much it should matter to you
2Useful: my rating, 1 to 5
3Signal: worth watching, 1 to 5
EffortArea: what it touches
ImprovementsKind: in v2.1.290,
ImprovementsSection of the release

Unclear What the model-specific hold value is and which models have one is unclear.

What

Effort is how much thinking the model puts into a reply. When working out the effort level, Claude Code can now leave it unset for a model that has a model-specific hold value, instead of taking it from your settings. Taking the default from the settings table directly now also depends on a condition.

Why

The effort shown or applied for some models may differ from what your settings say.

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 doubtWhat the model-specific hold value is and which models have one is unclear.

See this entry in the whole of v2.1.290 →

Feedback