mempalace

Files

T

Igor Lins e Silva e8017ca2ec bench: add per-room recall threshold test

Concentrates all drawers into a single wing+room to isolate the
embedding model's retrieval limit independent of palace filtering.
Confirms recall degrades to ~0.4-0.5 at 5K drawers per room even
with wing+room filters applied — the spatial structure helps by
keeping buckets small, but can't fix the underlying embedding ceiling.

2026-04-08 05:06:31 -03:00

benchmarks

bench: add per-room recall threshold test

2026-04-08 05:06:31 -03:00

conftest.py

fix: update dialect tests for PR #147 stats API and remove unused fixture param

2026-04-07 18:58:25 -03:00

test_config.py

bench: add benchmark runners, results docs, and test suite

2026-04-04 18:33:42 -07:00

test_convo_miner.py

bench: add benchmark runners, results docs, and test suite