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 v1.0.83 Home All releases ←olderv1.0.82 v1.0.84newer→
Claude Code v1.0.83

Extended Beta Features for First-Party and Vertex API Users

What: Users connecting through Anthropic's API or Google Vertex AI now have access to previously restricted beta features How to use:

# For Anthropic API (default - no special configuration needed)
claude "Analyze this 800,000 token codebase"

# For Google Vertex AI
export CLAUDE_CODE_USE_VERTEX=true
claude "Use interleaved thinking to solve this complex problem"

Details:

  • Enables "interleaved-thinking-2025-05-14" beta feature for enhanced reasoning capabilities
  • Enables "context-1m-2025-08-07" beta feature supporting up to 1 million token context windows
  • These features are automatically included in API requests when not using AWS Bedrock
  • No additional flags or configuration needed - features activate automatically based on your backend

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 v1.0.83 →