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 v1.0.64 Home All releases olderv1.0.63 v1.0.65newer
Claude Code v1.0.64

Improvements

UI/UX Enhancements

  • Model display in agent info: Agent model selection is now displayed in the agent information
  • Better model descriptions: Clear descriptions for each model option:
  • Sonnet: "Balanced performance - best for most agents"
  • Opus: "Most capable for complex reasoning tasks"
  • Haiku: "Fast and efficient for simple tasks"
  • Inherit: "Use the same model as the main conversation"

Bug Fixes

  • Removed duplicate MCP management code: Cleaned up redundant MCP server management implementation
  • Fixed agent file path handling: Improved path resolution for agent files across different locations
  • Better error messages: More descriptive error messages for invalid agent configurations

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 v1.0.64 →