Codex的上下文压缩很强，但Pi用户默认享受不到。装这个插件就能用上，长任务性能直接起飞。
Codex使用OpenAI的gpt模型时，依赖服务端加密的上下文压缩，效果优于其他方案。但第三方框架如Pi默认不启用此功能，导致长任务性能下降。用户可通过安装alexisgallagher开发的插件（github.com/algal/pi-opena…）在Pi中启用相同压缩。该插件的benchmark结果支持OpenAI服务端压缩确实更优的结论。
Codex 的上下文压缩确实做的挺好的，不过是服务端实现的，并且加密了的，在第三方框架比如 Pi 中默认不会启用，但是可以通过插件启用服务端上下文压缩，具体参考原推文
Codex 的上下文压缩确实做的挺好的，不过是服务端实现的，并且加密了的，在第三方框架比如 Pi 中默认不会启用，但是可以通过插件启用服务端上下文压缩，具体参考原推文 Kun Chen @kunchenguid pro tip - when you use OpenAI's gpt models in Codex, it uses a server-side encrypted compaction that seems to work better than anything else out there, which allows Codex to just keep hammering on long running tasks like there's infinite context window that's great, but if you run gpt in other harnesses like Pi, most of them don't inherit that by default, resulting in worse performance in long running tasks but - because of how extensible Pi is, i just found this cool extension from @alexisgallagher that enables the same server-side compaction in Pi - github.com/algal/pi-opena… benchmark seems to support the argument that OpenAI server side compaction is indeed superior - github.com/algal/pi-opena… so if you are using gpt models in Pi, install that extension to improve long running task performance. firstmate benefits a lot from this if you are using other harnesses, be aware of this difference and see if you can find a similar solution 🔗 View Quoted Tweet 💬 2 🔄 0 ❤️ 2 👀 688 📊 2 ⚡