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

Technical Changes

️ Architecture

  • Modular agent system: Agents now have a more structured configuration with model preferences
  • Improved type safety: Better validation of agent properties including model selection
  • Resource cleanup: Proper cleanup of MCP resources when connections are terminated

Compatibility

  • Backward compatible: Existing agents without model specifications default to Sonnet
  • Survey system: Added force display option via CLAUDE_FORCE_DISPLAY_SURVEY environment variable for testing

See this entry in the whole of v1.0.64 →