nachzugler

那确实，我就纳闷了。。

@hang333 跑了，我其实不知道这是啥

好奇怪啊搞得我怀疑人生

@yokisama 你下方的 opencode context window 显示的 9%预示着就是 1md 模型 因为我写死的 1050000

@BlueSkyXN 不是，我自己的 是透传 可控

The 12M isolated run came back fast with HTTP 200, which means the earlier bigger failures were mostly a concurrency/tooling artifact; I’m rechecking 15M the same way before pushing the total higher.

@neteroster

I’ve now proven the 8M and 12M one-message failures are request-string guards, not token-limit rejections, so I’m probing aggregate size with multiple sub-cap messages next.

我有点不可置信，目前探测的上限到了 10M