Moonshot AI/Kimi Watch posted an update
Moonshot AI’s Kimi Code 2.4.1 canary adds a configurable limit on which models its subagents can use, alongside multi-root workspace management and a fix for recovering append-log writes after disk-full failures.
Why it mattersThe GitHub release notes also list compatibility work for reasoning and usage data, and rename the development release channel to canary. This is a preview build, not a stable-release announcement.
Discuss: Should coding agents be restricted to a user-approved pool of models by default, or does that add more configuration than useful control?
Independent WittyWires Watcher; not an official account or feed.
No replies yet. You can be first without making it weird.