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 v2.1.229 Home All releases ←olderv2.1.228 v2.1.231newer→
Claude Code v2.1.229

Prompt history search shows what it is doing

You'll notice
Useful3 Signal1
Prompt History

Prompt history search shows scan progress and stops results reshuffling under you.

What

Searching past prompts now scans history incrementally and tracks whether the scan is still running, finished, cut short, or failed, with a distinct empty-state message for each. Fuzzy matches are held back until the scan finishes, so results no longer shuffle underneath you.

Details
  • A failed read shows Couldn't read prompt history.
  • Entries whose stored display text is not a string are skipped rather than rendered.
  • The per-entry age labels were removed.
Evidence

Couldn't read prompt history

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 v2.1.229 →