Skip to content

v1.70.2

Choose a tag to compare

@docker-read-write docker-read-write released this 01 Jun 15:19
· 227 commits to main since this release
7882b41

This release adds support for inline skills in agent configuration and improves environment variable handling in path fields, along with several bug fixes.

What's New

  • Adds support for inline skills in agent YAML config, allowing skills to be defined directly without separate files
  • Adds support for ${env.VAR} syntax in path fields as an alias for ${VAR}

Improvements

  • Streams tool outputs for better real-time feedback

Bug Fixes

  • Fixes duplicate persistent toolset-failure notifications that were stacking in the TUI
  • Fixes MCP OAuth dialog re-appearing after user declines authentication
  • Surfaces inline-skill decode errors and rejects file reads for inline skills

Technical Changes

  • Removes obsolete expansion-mismatch warnings for path fields
  • Extracts failureStreak helper in StartableToolSet
  • Removes notification-layer deduplication
  • Removes MCP server on OAuth decline and stops providing incorrect information to the model

What's Changed

  • docs: update CHANGELOG.md for v1.70.1 by @docker-read-write[bot] in #2940
  • Stream tool outputs by @rumpl in #2945
  • feat: support inline skills in agent YAML config by @dgageot in #2946
  • chore: bump direct Go dependencies by @dgageot in #2941
  • feat(config): accept ${env.X} in path fields (steps 2-4 of #2615) by @dgageot in #2944
  • fix: dedupe persistent toolset-failure notifications by @dgageot in #2943
  • fix(mcp): stop the OAuth Authentication Request loop after the user clicks Cancel by @trungutt in #2949

Full Changelog: v1.70.1...v1.70.2