Source Intelligence
Follow Discord

DisclaimerUnofficial, and not affiliated with Anthropic. Nearly all of this is read straight out of what ships: npm bundles, captured prompts, published docs. Anthropic's own notes go in verbatim, marked as theirs. The rest is my reading, and every entry carries the strings behind it. If one looks wrong, vote it down and say why.

← All of v2.1.232 Home All releases ←olderv2.1.231 v2.1.233newer→
Claude Code v2.1.232

Security warnings and cutoff notes are length-capped

You'll notice
Useful2 Signal1
Subagents

Security warnings and cutoff notes get trimmed with a marker instead of flooding your transcript.

What

Subagent security-policy warnings and agent cutoff notes are now clamped to a maximum length with an explicit marker saying how much was removed, instead of pasting an unbounded reason string into the transcript.

Evidence

cut from ${e.length} characters]

Strings lifted out of the shipped bundle, so the claim above can be checked against them.

Related

Other releases about the same thing. Found by shared names or similar wording; neither means one caused the other.

See this entry in the whole of v2.1.232 →