Summary

The prepareNextTurn hook in Mods returns successfully but the model swap is never applied. The session model stays the same for all turns.

Expected Behavior

When prepareNextTurn returns { model: "minimax-m2.5" }, the next turn should use minimax-m2.5.

Actual Behavior

The model never changes. My usage dashboard shows deepseek-v4-flash (the session model) used for all 4 turns, even though the hook returns a different model.

Steps to reproduce the issue

cmd.hooks({
onStop: async () => {
return {
continue: true,
reason: "next prompt",
prepareNextTurn: {
model: "minimax-m2.5", // or any other model
},
};
},
});
No errors returned. The hook fires. But the model stays the same.

Command Code Version

1.3.0

Operating System

macOS

Terminal/IDE

ghostty

Shell

command

Additional context

ec68a19a-4eaf-4ee8-a987-17e7ee7aabda session