Source Intelligence

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 v2.1.224 Home All releases olderv2.1.223 v2.1.225newer

Assistant text is scanned for harness-shaped tags

Under the hood
Useful2 Signal4
Permissions

Claude's own replies are scanned for text imitating internal control markup, and matches counted only.

What

Main-session assistant messages are now checked for text that looks like Claude Code's own internal control markup, including system reminders, harness envelopes and token-count, session-context, wake and role-turn shaped lines. Nothing is rewritten; the matches are only counted and reported.

Details
  • Runs for main-session, non-error assistant messages only, with no flag involved.
Evidence

tengu_assistant_output_harness_content

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

See this entry in the whole of v2.1.224 →