New in v0.32.3 ⋅ /configure-models Routes background requests to a model of your choice. Run compaction on MiniMax M2.5 Assign session titles with DeepSeek V4 Flash. Pick a model for each task, press r to reset. Defaults were a starting point. Now you have choices.

@CommandCodeAI This is awesome but can we also have /goal pls?

@CommandCodeAI this is truly the next step.

@CommandCodeAI can i use a local model

@CommandCodeAI what would you like to see /configure-models do? specific models set for: plan mode, /review, custom agents maybe?

@CommandCodeAI Will switching model consumes more tokens like kn Claude Code?

@CommandCodeAI I'm new here and would like some help x.com/i/status/20631…

@CommandCodeAI configure-models routing sounds really useful

@CommandCodeAI when BYOK ?

Proud to support investment opportunities. Access through SoFi:

@CommandCodeAI When BYOK

@CommandCodeAI This is the direction AI tooling should be heading. Not one model for everything, but the freedom to route each task to the model that does it best. More control, better performance, and a workflow that adapts to the user—not the other way around. 🔥

> Giving users granular control over model routing is a meaningful step forward for AI workflows. The ability to assign specialized models to different background tasks can improve both efficiency and output quality. Great to see Command Code continuing to focus on flexibility, customization, and developer productivity. 🚀💻