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 v2.0.22 Home All releases olderv2.0.21 v2.0.23newer
Claude Code v2.0.22

SDK Control for Max Thinking Tokens

What: SDK users can now dynamically change the maximum thinking tokens limit mid-session.

How to use:

// Send control request in SDK:
{
  subtype: "set_max_thinking_tokens",
  max_thinking_tokens: 10000  // or null to disable
}

Details:

  • Takes effect immediately for subsequent conversation turns
  • Setting to null disables thinking tokens entirely
  • Useful for adjusting reasoning depth based on task complexity
  • Evidence: MT8() at lines 5859-5862 in v2.0.22

See this entry in the whole of v2.0.22 →