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 v2.1.238 Home All releases ←olderv2.1.237 v2.1.239newer→
Claude Code v2.1.238

Prompt-history secret redaction catches more cases

You'll notice
Useful3 Signal2
Prompt History

Prompts containing secrets are kept out of your history in more cases, including ! commands.

What

The check that keeps a prompt with a secret in it out of your history now also inspects shell commands typed with a leading !, scans long text in overlapping pieces so a secret spanning a boundary is still caught, and only looks at pasted blocks the typed text actually refers to.

Details
  • The old helper that only examined slash commands was removed.
  • Runs unconditionally, aside from the existing CLAUDE_CODE_SKIP_PROMPT_HISTORY opt-out.
Evidence

CLAUDE_CODE_SKIP_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 v2.1.238 →