Big agentchattr update just went live, https://t.co/mzGJ3WX1Mo
- Session UX improvements: cleaner session proposal cards, better custom-session drafting flow, and improved session-related UI states
- Proposal flow polish: session, rule, and job proposal cards are more consistent and easier to scan
- Deletable system artifacts: more session/job/rule-generated timeline artifacts now behave properly with delete mode and cleanup flows
- Cross-channel notifications: better awareness when activity happens outside the current channel
- Update notifications: a small release pill now appears when a newer GitHub release is available
Kimi support: adds Kimi as a built-in agent option
Under the hood
- major frontend modularization of the chat monolith
CSS token and dedup pass for cleaner styling foundations
- local-only hardening for agent registration endpoints
- general cleanup and bug fixes across sessions, rules, jobs, and notifications
@indio_bns@om_patel5 Not very easily, at all... because it works via composing prompts to tell them to use MCP tools to catch up on chat - would need to figure out a way to do that in VS code which probably won't be possible, it might have to be its own VS code extension to achieve that.
@0xEvinho@om_patel5 It adds about 40 tokens to each command you send to them, and yes they do need to respond with their message as well, if you're building a landing page it's just convenience, if you're frequently running multiple thousand token outputs then it can help ensure the best results.