Show HN: Running over 80M tokens in one agent session with no compaction
By andrew_ocs · 2026-07-14 · 3 points · 0 comments
https://github.com/Kiz8-Team/pi-cwl
We ran a single agent session through all 89 sequential tasks of Terminal Bench 2.0 or over 80 million tokens, with no measurable accuracy loss versus running each task in its own fresh session. We didn't use compaction. Compaction is the standard fix for finite context windows,…
Open the full discussion on BetterNews