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 v1.0.115 Home All releases olderv1.0.114 v1.0.116newer
Claude Code v1.0.115

Thinking Detection Toggle Behavior

What: Improved how the thinking detection disabled state works when users toggle it on/off

Details:

  • Removed automatic re-enabling of thinking when users clear thinking tokens from input (previously in useEffect at line 437586-437588 in v1.0.114)
  • Introduced computed "effective disabled" state (i1 at line 437849) that only treats thinking as disabled when both:
  1. User has disabled thinking, AND
  2. Thinking tokens are present in the input
  • Visual feedback (border colors, shimmer effects) now shows thinking detection state more accurately
  • User preference for disabled thinking now persists instead of being automatically reset
  • Evidence: i1 variable at line 437849 in Yp5(), removed useEffect from previous version

See this entry in the whole of v1.0.115 →