8月30日 Tibo 预告重置：将于 2:30pm PST 落地

Tibo 自己之前的帖子（被回复）· 原帖

我们正在为 Codex 和 ChatGPT Work 的所有付费用户重置用量。
请继续往下读，了解 Codex 用量额度的最新进展。团队一直在连轴转，梳理了数千条报告并陆续发布修复。
取决于你使用 Codex 的方式，你的用量应该能比之前多用 10% 到 50%。
我们真的是拿细梳子一点点梳理，很多被发现的细小问题其实由来已久，以下是我们发现并修复的内容：
- 压缩（Compaction）。我们在压缩过程中保留了旧图片，有时会让上下文大到再次触发压缩。修复后，重度使用图片的用户用量下降了约 10%。已修复。
- 记忆（Memory）。后台记忆 worker 可能会继承 Stop 钩子，在钩子不允许其结束时仍持续运行。这影响了不到 1% 的用户，但长尾情况相当糟糕，我们见过一个示例线程检查自己能否停止多达 15,000 次。已修复。
- 目标（Goals）。某些情况下，设定好的 /goal 完成后仍会越过预期的停止条件继续运行，或者模型会不断重试失效的工具而不停止。我们见过一些例子消耗了每周额度的 15% 到 70%。已修复。
- 自动化（Automations）。一些自定义计划任务可能比配置的频率运行得更频繁。已修复。
- 子代理（Subagents）。较小的模型（例如 Luna）有时会在未被明确要求的情况下挑选能力更强的帮手。同样的情况也出现在：未以 /fast 模式运行的编排模型可能要求子代理以 /fast 运行。已修复。
- 电脑操作历史（Computer History）。较旧的实现可能导致对重叠的活动反复进行摘要。在某些情况下，我们看到它每周最多消耗五分之一的每周用量。已修复。
- 滚动任务摘要（Rolling task summaries）。普通轮次会触发额外的后台请求。这让 token 用量增加了约 1%。每次都不多，但会累积。我们已经禁用这一功能。
- MCP。一些工具结果可能被重复编码。我们还发现工具说明被截断后又被重新获取。已修复。
我们还做了一些架构层面的改动，防止这些问题再次出现；无论怎样，一旦发生，我们的团队都会收到告警。我们也在努力让你直接在应用里看到用量都花在了哪里，这样你就不用再靠猜了。
不用说，我们正在重置用量额度，希望你们度过一个非常愉快的周六！

We are reseting usage for all paid users of Codex and ChatGPT Work.
Please continue reading for an update on Codex usage limits. The team has been working around the clock, going through thousands of reports and shipping fixes.
Depending on how you use Codex, you should see your usage go between 10% and 50% further than before.
We really went with a fine comb, with many uncovered small things being longstanding and here is what we found and fixed:
- Compaction. We were keeping old images during compaction, sometimes making the context large enough to trigger compaction again. After the fix, usage dropped around 10% for users making heavy use of images. Fixed.
- Memory. Background memory workers could inherit Stop hooks and keep running when the hook wouldn’t let them finish. This affected fewer than 1% of users, with the long tail being pretty bad and we saw one example thread check whether it could stop 15,000 times. Fixed.
- Goals. In some cases, a set /goal could finish and then keep going past the intended stop condition, or the model would keep retrying broken tools without stopping. We saw examples consume anywhere from 15% to 70% of a weekly allowance. Fixed.
- Automations. Some custom schedules could run more frequently than configured. Fixed.
- Subagents. Smaller models (e.g. Luna) sometimes picked more capable helpers without being explicitly asked. The same was true where the orchestrating model not running in /fast mode could request sub-agents to run /fast. Fixed.
- Computer History. The older implementation could lead to repeatedly summarizing overlapping activity. For some cases we saw it consume up to one fifth of the weekly usage per week. Fixed.
- Rolling task summaries. Ordinary turns were triggering extra background requests. These added about 1% to token usage. Small each time, but it adds up. We have disabled this.
- MCP. Some tool results could be encoded twice. We also found tool instructions getting cut off and fetched again. Fixed.
We’ve also made architectural changes to prevent these from regressing and our teams will get paged if it happens regardless. We are also working on showing you directly in the app where your usage goes so you don’t have to guess.
Goes without saying that we’re resetting usage limits and I hope you enjoy a very nice Saturday!