Hey, thanks for the detailed feature request. It’s well written, and the split between “reasoning visibility” and “preserving a decision log during compression” is helpful.
The part about controlling the visibility of thinking blocks always / on-demand / hidden, expanded by default is a direction that’s already on our radar, and we’re discussing some aspects internally. Right now, thinking is saved per message, but it’s collapsed by default, and when we do summarization or compression, earlier reasoning isn’t carried over. Your “decision log” idea that survives context compression is a separate and less common request, and I’ve noted it separately.
I can’t give an ETA or any guarantees on implementation, but the request is logged. If you want to strengthen the signal, related discussions about thinking blocks are here: Keep thought process expanded when agent has made new changes and The thinking accordion auto collapse even manually expanded. Feel free to vote there or add more context.