Discussion about this post

User's avatar
Tirth Patel's avatar

Amazing article on context compaction

Reasoning Under Uncertainty's avatar

A model call produces the summary that becomes the agent's record of its earlier turns once compaction fires. Compaction isn't truncation, it's generation, and whatever the summarising model under-attends to, drops or restates wrong gets written into context as settled fact, with nothing marking which parts drifted.

The harnesses named here, OpenCode, Pi and Claude Code, each run their own implementation, and the token-budget problem gets solved either way; a faithful-summarisation problem takes its place, and it's not clear that one gets measured anywhere. Does any of them check the summary against the session it replaces?

3 more comments...

Ready for more?