Source Intelligence
Reading a new release v2.1.251 Analysing changes · 2/5 Deeper second pass · 4/5 agents 427 findings $12.75 so far

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 v0.2.103 Home All releases olderv0.2.102 v0.2.104newer

User-Facing Improvements

Tool Enhancements

  • MCP content size validation: Added protection against oversized MCP tool responses exceeding token limits
  • IDE integration improvements: Better handling of IDE-specific tools when ENABLE_IDE_INTEGRATION=true
  • Tool filtering: Certain IDE tools are now properly filtered based on environment settings

Usage Tracking

  • Rate limit visibility: Enhanced display of Claude AI usage limits with reset times
  • Token usage display: More detailed token counting across parallel agent operations
  • Cost tracking: Improved cost calculations including cache tokens

See this entry in the whole of v0.2.103 →