For now, we support switching between models within the same provider, but we're currently adding the ability to switch providers mid-session. We're working on agent switching similar to Cursor's LLM switch so you can seamlessly move between Claude Code, Codex, GLM, etc. during development. We're also exploring auto-switching based on task type, our model would automatically select the best agent for each task. For example, using Opus for frontend work and Codex for backend refactoring. The goal is to leverage each agent's strengths without you having to think about it.