mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-05-21 03:39:54 +00:00
Teknium
b799bca7a3
The previous commit capped the 1.4x at 95% of context, but the multiplier itself is unnecessary and confusing: 85% threshold × 1.4 = 119% of context → never fires 95% warn × 1.4 = 133% of context → never warns The 85% hygiene threshold already provides ample headroom over the agent's own 50% compressor. Even if rough estimates overestimate by 50%, hygiene would fire at ~57% actual usage — safe and harmless. Remove the multiplier entirely. Both actual and estimated token paths now use the same 85% / 95% thresholds. Update tests and comments.