Is anyone else seeing GPT-5.5/OpenAI-Codex context crashes?
I just found out compaction is firing too late because "codex_gpt55_autoraise: true" pushes it near ~85%, while file/context reads were raised from 20k to 100k.
So a couple large file reads can blow the session up before compaction catches it.
Thinking the fix is lowering reads back to 20k and making summary failures stop the run instead of continuing.
Anyone else run into this?