ratatoskr/persistent-memory.d/2026-06-15-diagnostic-our-recall-search-is-sound-the-cro.md at 4bd9abdebc04ae4d2a3337213ca958620d2e551a

Files

T

vh ff1f9ca1e8 memory: /snapshot — #368 silo test passed; two-tier migration; stores scrubbed

- #368 (user,character) memory silo test DONE + PASSED live (WT b127):
  write-side conjunctive {end_user,agent_self} scoping + read-side cross-
  character isolation both proven end-to-end; betty (throwaway) deleted,
  Sindra intact. Full record in persistent-memory.d/2026-07-18-368-silo-
  test-passed.md. Retired the stale "silo test in progress" in-flight blocks.
- Two-tier migration: split 152 over-threshold dated entries into
  persistent-memory.d/ detail files, leaving one-line pointers in the index
  (startup load ~196KB -> ~53KB; bodies now load on demand).
- Tier-3 stores scrubbed clean (memory 0 / affect 0, provider restarted
  empty); persistent-memory + detail file updated to reflect the scrub.

2026-07-17 21:39:18 -07:00

585 B

Raw Blame History

[2026-06-15] Diagnostic: our recall-search is SOUND — the cross-session recall gap is UPSTREAM, and it caught an upstream bug. Embedded the recall query via gateway qwen3-embedding + searched our live store directly → the fact recalls at cosine 0.60, correctly ranked. So the cold-session recall failure is Worldtree's recall-assembly/injection, NOT our search. ALSO found a latent UPSTREAM bug: a recall QUESTION got promoted as a durable chunk and ranked #1. This is exactly #17's thesis — ratatoskr-as-provider caught an upstream bug invisible from the chat side.

585 B Raw Blame History

585 B

Raw Blame History