Unfortunately I’ve used Claude and GPT models for a long time in a variety of harnesses and I agree with you and I think it’s the compaction.
For some reason, codex compaction is like black magic. I’ve never felt like I can just one one continuous thread with other models, Claude I carefully curate when I compact
For some reason, codex compaction is like black magic. I’ve never felt like I can just one one continuous thread with other models, Claude I carefully curate when I compact