[Feature Request] Implement context-aware model switching to avoid re-reading conversation history and optimize token usage

Bug Description
i'm building a module for my super admin user for my app, along with practice admin to add users, and re-assign defunct users, a common scenario in medical practices with rotating Medical Assistants (MAs). I want to retain history as they shadow doctors. It used fable 5 initially then it switched to opus 4.8. then i updated my config and switched back to fable 5, when i asked it to switch back to fable 5 it requested to read the whole history back, this is not fair.

Secondly, it flagged me with this message: Fable 5's safeguards flagged this message. The safeguards are intentionally broad right now and may flag safe and routine coding, cybersecurity, or biology work. These measures let us bring you Mythos-level capabilities sooner, and we're working to refine them. Switched to Opus 4.8. Send feedback with /feedback or learn more: https://support.claude.com/en/articles/15363606

In a health tech org, these are real features, so we can serve practices, so please let me know how you can help me folks like us and not double charge on the tokens and also allow for using capable models to build feature sets

Environment Info

• Platform: darwin
• Terminal: Apple_Terminal
• Version: 2.1.207
• Feedback ID: b6bf8a46-6f84-4292-aa4f-e8d2495ff640

Errors

[]