Kimi Code 0.11.0

0.11.0Desktop
Added 5
  • Add experimental sub-skill discovery gated by the KIMI_CODE_EXPERIMENTAL_SUB_SKILL environment variable with sub-skill builtin bundle (sub-skill.review, sub-skill.consolidate) for inventorying and consolidating skills into hierarchical groups
  • Migrate environment variables KIMI_MODEL_TEMPERATURE, KIMI_MODEL_TOP_P for sampling parameters applied globally to any kimi provider
  • Migrate environment variable KIMI_MODEL_THINKING_KEEP for Moonshot preserved-thinking passthrough (thinking.keep) injected only while Thinking is on
  • Migrate environment variable KIMI_CODE_NO_AUTO_UPDATE (legacy alias KIMI_CLI_NO_AUTO_UPDATE) to fully disable the update preflight
  • Support multiline edits when managing upcoming goals
Changed 7
  • Show built-in skills as direct slash commands and group them ahead of external skill commands
  • Use a fixed 30-minute timeout for subagents and show concise resume instructions when they time out
  • Show the upcoming-goal confirmation with the same accent treatment as goal lifecycle messages
  • Show concise provider filtering errors when responses are blocked before visible output
  • Ask before starting goals in YOLO mode so users can switch to Auto for unattended work
  • Start upcoming goals immediately when there is no active goal to wait for
  • Highlight goal queue subcommands while typing slash commands
Fixed 7
  • Fix slash command autocomplete so goal text can be submitted when the cursor is before existing text
  • Fix queued goals so failed promotion attempts do not lose or duplicate queued work
  • Show unknown command instead of too many arguments when an invalid subcommand is entered
  • Fix upcoming-goal queue handling while editing or pasting queued goals
  • Clamp OpenAI Chat Completions xhigh and max thinking effort to high unless the model supports xhigh on v1/chat/completions
  • Preserve thinking effort when compacting long conversations
  • Refresh provider model metadata when capabilities change without model ID changes
Minor Changes

  • #468 df4f2d6 - Add experimental sub-skill discovery gated by the KIMI_CODE_EXPERIMENTAL_SUB_SKILL environment variable. Ships the sub-skill builtin bundle (sub-skill.review, sub-skill.consolidate) for inventorying and consolidating skills into hierarchical groups.

  • #480 f555c89 - Show built-in skills as direct slash commands and group them ahead of external skill commands.

  • #458 93eb70a - Migrate still-relevant environment variables from kimi-cli:

    • KIMI_MODEL_TEMPERATURE, KIMI_MODEL_TOP_P — sampling parameters applied globally to any kimi provider (not tied to KIMI_MODEL_NAME).
    • KIMI_MODEL_THINKING_KEEP — Moonshot preserved-thinking passthrough (thinking.keep), injected only while Thinking is on.
    • KIMI_CODE_NO_AUTO_UPDATE (legacy alias KIMI_CLI_NO_AUTO_UPDATE) — fully disables the update preflight (no check, background install, or prompt).

  • #470 aa610e2 - Use a fixed 30-minute timeout for subagents and show concise resume instructions when they time out.

Patch Changes

  • #474 658e465 - Show the upcoming-goal confirmation with the same accent treatment as goal lifecycle messages.

  • #474 658e465 - Fix slash command autocomplete so goal text can be submitted when the cursor is before existing text.

  • #474 658e465 - Fix queued goals so failed promotion attempts do not lose or duplicate queued work.

  • #456 3a98713 - Show concise provider filtering errors when responses are blocked before visible output.

  • #442 960a0e2 - Show "unknown command" instead of "too many arguments" when an invalid subcommand is entered.

  • #474 658e465 - Fix upcoming-goal queue handling while editing or pasting queued goals.

  • #457 1fe5d55 - Clamp OpenAI Chat Completions xhigh and max thinking effort to high unless the model supports xhigh on v1/chat/completions.

  • #464 4f9977d - Preserve thinking effort when compacting long conversations.

  • #474 658e465 - Ask before starting goals in YOLO mode so users can switch to Auto for unattended work.

  • #461 2af19e2 - Refresh provider model metadata when capabilities change without model ID changes.

  • #474 658e465 - Start upcoming goals immediately when there is no active goal to wait for. Support multiline edits when managing upcoming goals.

  • #474 658e465 - Highlight goal queue subcommands while typing slash commands.

View original

Upgraded? How did it go?

Discussion