Kimi Code 0.9.0

0.9.0Desktop
Added 3
  • Add @moonshot-ai/acp-adapter and the kimi acp subcommand to speak Agent Client Protocol 0.23 over stdio for IDEs and custom clients to drive sessions directly
  • Add /btw command for side-channel conversations without steering the active main turn
  • Log enabled experimental flags at startup
Changed 6
  • Allow /btw to open the side-channel panel before entering a question
  • Use the OpenAI completion token field required by newer Chat Completions models
  • Resume saved subagents lazily when they are accessed
  • Allow SDK runtime creation to use a separate RPC client while preserving local CLI startup
  • Unify the interaction and visuals across TUI dialogs and selectors
  • Use configured model output limits for completion token caps
Fixed 2
  • Fix external editor (Ctrl+G) on Windows by removing /bin/sh dependency and using platform-aware shell quoting for temp file paths
  • Fix goal budget tool schemas for OpenAI-compatible providers
Minor Changes

  • #368 3eafa79 - Add @moonshot-ai/acp-adapter and the kimi acp subcommand: kimi-code now speaks Agent Client Protocol 0.23 over stdio so IDEs (Zed, JetBrains AI Chat, custom clients) can drive sessions directly — coverage matrix, Zed configuration and breaking pre-release notes are in kimi acp Subcommand Page.

  • #338 ba7dd73 - Add /btw for side-channel conversations without steering the active main turn.

  • #357 179aecf - Log enabled experimental flags at startup.

  • #378 e0d28b4 - Allow /btw to open the side-channel panel before entering a question.

Patch Changes

  • #246 7d1f889 - Fix external editor (Ctrl+G) on Windows by removing /bin/sh dependency and using platform-aware shell quoting for temp file paths.

  • #365 6a22523 - Fix goal budget tool schemas for OpenAI-compatible providers.

  • #365 6a22523 - Use the OpenAI completion token field required by newer Chat Completions models.

  • #380 8639105 - Resume saved subagents lazily when they are accessed.

  • #339 a6b16ce - Allow SDK runtime creation to use a separate RPC client while preserving local CLI startup.

  • #363 90879f3 - Unify the interaction and visuals across TUI dialogs and selectors.

  • #365 6a22523 - Use configured model output limits for completion token caps.

View original

Upgraded? How did it go?

Discussion