mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-09 13:21:42 +00:00
1ddf7a1021
The default lumpy-turn fixture's tool bodies are tiny (2/7/18 short lines), so W3 (HERMES_TUI_TOOL_OUTPUTS=off) shows no RSS delta at realistic sizes — the saved bytes sit below the ~20MB run-to-run noise floor. This adds an env knob to scale every tool result body to N lines, making the retention asymmetry measurable in the bench (a `find /` / big-file-read class fixture). UNSET = the original tiny bodies, byte-identical — existing benches and the determinism digest are unaffected. Set HERMES_BENCH_TOOL_BODY_LINES=N (the bench harness inherits it at fixture-generation time) for a fat run. Measured with this (mem300, ~100KB/tool, ~27MB retained tool text): OpenTUI OFF 244-259MB vs ON 260-261MB vs Ink 269-279MB — i.e. W3 OFF is a real ~5-15MB win at heavy output, and OpenTUI's windowing actually beats Ink at scale (Ink mounts every row; OpenTUI windows). |
||
|---|---|---|
| .. | ||
| acceptance.sh | ||
| build.mjs | ||
| check.sh | ||
| demo.tsx | ||
| fixture.ts | ||
| mem-bench.tsx | ||
| update-parsers.mjs | ||