Follow Discord
Sweep 01 Oct 2026 · 17:27Z Build v2.1.287 508 read Stable v2.1.285 Latest v2.1.287 Next v2.1.287 Feeds RSS JSON llms.txt llms-full.txt Unofficial

Claude Code v2.1.286 ·

Thinking display errors and remote tool results handled differently

Claude Code reworked how it spots rejected thinking display settings, and now processes tool results from workers before passing them on

Under the hood Internal Changes
JSON All of v2.1.286
Under the hoodTier: how much it should matter to you
1Useful: my rating, 1 to 5
1Signal: worth watching, 1 to 5
API RequestsArea: what it touches
Internal ChangesKind: in v2.1.286,
Internal ChangesSection of the release
What

The check that spots the API rejecting the setting for how thinking is displayed was moved into a shared, prepared pattern. Separately, tool results coming from worker or remote agents are now processed before Claude Code passes them on.

Why

This may change how Claude Code retries after that error and what tool results look like to programs using Claude Code through its SDK.

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 processing does to tool results, and whether the error pattern itself changed, is not clear.

See this entry in the whole of v2.1.286 →

Feedback