Adsq

#2968 I sent a pull request that completely solves this problem by loading reactively. However, it hasn’t been reviewed, and now there are conflicts. Using which in Rust makes your...

### ⚠️ Problem: Context Bloat (aka *Context Window Explosion*) in Codex/LLMs Suppose each file has ~10k tokens. There are **two possible patterns** for how context grows: --- #### 1. Sequential...

@snipeship Exactly the same thing with the assistant’s repeated message I noticed yesterday.

I’ll try to sort something out if no one beats me to it :) I’m juggling a few projects at the moment, so we’ll see how it goes :)

> > I’ll try to sort something out if no one beats me to it :) I’m juggling a few projects at the moment, so we’ll see how it goes...

@mdbro Partially I checked — Codex claims it has snapshots. However, when you have 28k tokens in context and try to load another ~14k, you get an error. **Besides, it’s...

@mdbro Ah, I thought the API had a limit of 30k. I was mistaken—I didn’t check carefully. That makes things even more difficult, because just two iterations of 15k within...

I think that increasing the per-minute limit while reducing the context window (to prevent overload) for tier 1 would be a better option and would allow Codex to be used...

@mdbro I described both above :) Both are true — you can’t push more than 30k tokens at once if the limit is 30k per minute, so without trimming it...

"On the 128K question: raising the TPM cap to 128k/min would let a single 20-40K prompt + 10-15K completion call complete, because 30K → 128K removes the per minute choke....