ReleaseMoonshot AI (Kimi)Moonshot AI (Kimi)published Jul 14, 2026seen 1w

MoonshotAI/kimi-code @moonshot-ai/kimi-code@0.24.0

MoonshotAI/kimi-code

Open original ↗

Captured source

source ↗
published Jul 14, 2026seen 1wcaptured 1whttp 200method plain

@moonshot-ai/kimi-code@0.24.0

Repository: MoonshotAI/kimi-code

Tag: @moonshot-ai/kimi-code@0.24.0

Published: 2026-07-14T07:04:34Z

Prerelease: no

Release notes:

Minor Changes

  • #1591 `83e1753` Thanks @liruifengv! - Move foreground Bash commands that hit their timeout to the background instead of killing them, so long-running commands survive the timeout and report back on completion. Set bash_auto_background_on_timeout = false under [background] in config.toml to restore the kill-on-timeout behavior.
  • #1617 `4ec2e7f` Thanks @sailist! - Run the local server (kimi server run / kimi web) on the agent-core-v2 engine by default — the KIMI_CODE_EXPERIMENTAL_FLAG opt-in is no longer needed, and the legacy v1 server package has been removed.
  • #1441 `ceb158d` Thanks @sailist! - Port progressive tool disclosure to the new agent engine: MCP tool schemas stay out of the top-level tool list, and the model loads them by name on demand through the announcements plus the select_tools tool, keeping the prompt cache stable. Off by default; set KIMI_CODE_EXPERIMENTAL_TOOL_SELECT=1 to enable.
  • #1646 `5eb6217` Thanks @wbxl2000! - web: Add session diagnostic export to download a session and bounded metadata-only troubleshooting logs as a ZIP. Run /export or pick Export session from a session's more menu. Web downloads are limited to 64 MiB.

Patch Changes

  • #1638 `7c889f3` Thanks @RealKai42! - In auto permission mode, plan exits are now marked as auto-approved (not user-reviewed) in both the tool result and the transcript, so the agent no longer treats automatic plan approval as a user signal to start executing.
  • #1598 `4feca6b` Thanks @kermanx! - web: Recover transient subagent rate limits without surfacing them as session errors.
  • #1635 `e49b3b8` Thanks @sailist! - Request task-owned work to stop on session close, honoring background.keep_alive_on_exit for independent processes and background.kill_grace_period_ms before attempting force-stop.
  • #1629 `0527ca2` Thanks @sailist! - Fix session fork losing everything except the conversation log: forked sessions now carry over media attachments, plan files, background task output, and cron tasks, and a failed fork no longer leaves a broken half-copy behind.
  • #1631 `2d874fb` Thanks @sailist! - Fix a race where a heartbeat write in flight during server shutdown could recreate the instance file right after it was removed.
  • #1663 `1294a0e` Thanks @7Sageer! - Fix OAuth login hanging after browser authorization when the provider configuration changes during sign-in.
  • #1657 `32a89c3` Thanks @RealKai42! - Prevent oversized image reads from poisoning sessions and recover existing request-too-large failures by removing unsafe media from provider requests.
  • #1635 `e49b3b8` Thanks @sailist! - Store background task records per agent again, so tasks written by older versions are found on resume and one agent's restore no longer marks another agent's tasks as lost.
  • #1632 `a4aae87` Thanks @sailist! - Fix providers without a configured base_url being rejected: anthropic/openai and other protocol providers now fall back to their official default endpoints again, as before.

Excerpt shown — open the source for the full document.