Add MemFuseBench retrieval harness and first baseline report.

Wire an offline benchmark over the production pgvector ranking path so Memory V2 recall can be measured with candidate/ranking loss split before lifecycle work lands.

Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
john
2026-09-02 09:50:57 +08:00
parent 61eebb44ec
commit 0b6f79ae16
5 changed files with 1425 additions and 0 deletions
+2
View File
@@ -69,6 +69,8 @@
"repair:memory-v2-candidates": "node scripts/repair-memory-v2-candidates.mjs",
"verify:memory-v2-shadow-audit": "node --test memory-v2-shadow-audit.test.mjs",
"verify:memory-v2-recall-benchmark": "node --test memory-v2-recall-benchmark.test.mjs",
"verify:memory-v2-memfuse-bench": "node --test memory-v2-memfuse-bench.test.mjs",
"bench:memory-v2-memfuse": "node scripts/run-memory-v2-memfuse-bench.mjs",
"trace:mindspace-artifact": "node scripts/trace-mindspace-artifact.mjs",
"check:conversation-package-manifest": "node scripts/check-conversation-package-manifest.mjs",
"check:memory-v2-phase-a": "node scripts/check-memory-v2-phase-a-ready.mjs",