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 v2.1.47 Home All releases ←olderv2.1.45 v2.1.48newer→
Claude Code v2.1.47

Adaptive Thinking with --thinking Flag

What

New --thinking flag provides semantic control over Claude's thinking/reasoning behavior, replacing the deprecated --max-thinking-tokens.

Usage
claude --thinking enabled   # Claude decides when and how much to think
claude --thinking disabled  # No extended thinking
claude --thinking 10000     # Fixed thinking token budget (older models)
Details
  • For Opus 4.6+, adaptive mode lets Claude autonomously decide thinking depth
  • Takes precedence over the deprecated maxThinkingTokens setting
  • The old --max-thinking-tokens flag is now deprecated with guidance to use --thinking instead
Evidence

Thinking mode options (search for "--thinking <mode>", "Claude decides when and how much to think (Opus 4.6+)")

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

See this entry in the whole of v2.1.47 →