Follow Discord
Sweep 10 Nov 2026 · 02:18Z Build v2.1.322 539 read Stable v2.1.311 Latest v2.1.322 Next v2.1.322 Feeds RSS JSON llms.txt llms-full.txt Unofficial

Claude Code v2.1.281 ·

SDK set_max_thinking_tokens reports when the host refuses part of the request

SDK set_max_thinking_tokens now returns an error when the host refuses part of the request

Under the hood No documentation found Improvements
JSON All of v2.1.281
Under the hoodTier: how much it should matter to you
2Useful: my rating, 1 to 5
2Signal: worth watching, 1 to 5
SDKArea: what it touches
ImprovementsKind: in v2.1.281,
ImprovementsSection of the release

Unclear The finding does not say which parts of the request a host may refuse.

What

set_max_thinking_tokens is an SDK request that sets how much the model may spend on thinking before it answers. The SDK is the toolkit programs use to drive Claude Code. If the host (the environment Claude Code runs in) refuses part of that request, the program that sent it now gets an error back: "set_max_thinking_tokens: host refused part of the request".

Why

A program that sets the thinking budget now learns when its request was not fully applied, instead of assuming it all went through.

Read from
Names in the bundleset_max_thinking_tokens
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 doubtThe finding does not say which parts of the request a host may refuse.

See this entry in the whole of v2.1.281 →

Feedback