Files
hermes-agent/agent
teknium1 3f59b5c594 refactor(agent): /context breakdown and native-compaction retention use the canonical token estimator
context_breakdown._chars_to_tokens and native_compaction._approx_tokens did raw
chars//4, under-counting CJK/Cyrillic by 2-4x next to the conversation slice
that already used estimate_tokens_rough — the /context pie chart mixed two
estimators. Both now call the canonical. The four private `= 4` ratio
constants import one CHARS_PER_TOKEN from agent/model_metadata.py. Estimates
only feed UI and budgets; no prompt or message bytes change.
2026-09-13 05:09:43 -07:00
..