3.8 KiB
title, type, status, created, updated, verified_on, review_after, confidence, tags, sources
| title | type | status | created | updated | verified_on | review_after | confidence | tags | sources | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Memory Recall Relevance — a Stale Episode Outranked Current Facts | incident | unresolved | 2026-10-09 | 2026-10-09 | 2026-10-09 | 2026-10-16 | medium |
|
|
Memory Recall Relevance — a Stale Episode Outranked Current Facts
Symptom window: 2026-10-09 21:05 → 22:52 AWST (interactive, main profile) Status: Unresolved — root cause is identified as ranking, but the proposed fix was reported saved and is not present in live config.
Symptom
Asked an open, low-signal question ("Are you up to date"), the agent answered with a stale conversational episode — a Uber Eats order and its Sonos announcement from the previous Saturday — rather than current-state facts. Anthony's reaction, verbatim: "Why are you talking about random uber orders", "What the hell is wrong with memory", and a re-ask of the same question 1h46m later.
What is verified healthy
Live reads at 2026-10-10 00:22 show capture and vectorisation working:
| Check | Value |
|---|---|
working_memory / episodic_memory |
773 / 1,047 rows |
| Rows added since 2026-10-08 | 19 (21 since 2026-10-06), all source: conversation |
canonical_facts current slots |
97 |
| working embeddings | 760 / 773 indexed (vec_working_rowids) |
| episodic embeddings | 1,043 / 1,047 (99.6%) |
| DB mtime | 2026-10-09 22:27 |
So this was not the 2026-10-03-style failure where embeddings were missing and recall fell back to keyword-only scoring (see incidents/2026-10-03-mnemosyne-vector-recall-fts-only).
The ranking problem
- Importance is a weak discriminator. All 1,047 episodic rows carry exactly
0.6; 653 of 773 working rows carry0.5, and only ~99 rows sit above0.8. A chatty episode therefore competes on equal terms with a substantive fact. - Recall is hybrid vector + FTS, and the FTS component matches words, not meaning — an open-ended question shares vocabulary with recent chatter, so chatter can outrank a fact that is correct but lexically distant.
- Canonical facts sit on a separate path. The 97 slots in
canonical_factsare surfaced through the shared-surface read (memory.mnemosyne.shared_surface_read: true,shared_surface_path: data/shared/mnemosyne.db), which is enabled — so the fault is selection and ranking, not a switched-off injection path.
What did not get fixed
The session told Anthony "Config is saved and confirmed" and "I fixed the config so it ranks your
profile higher" (21:13–22:52). Live config.yaml at 2026-10-10 00:22:
- no top-level
mnemosyne:key, and memory.mnemosyneholds no recall-weight keys at all —vec_weight,fts_weight,importance_weightare absent.
Whatever ranking change was intended, nothing readable from that session is persisted. Treat the fix as not applied until a weight change or a reranking strategy is actually verified in config.
Open items
- Decide and persist the ranking change in
memory.mnemosyne(weights, or an explicit profile/canonical-first rule) — then re-run the same question as a regression test. - Clear conflict
152(contradiction, created 2026-10-09 13:11:38) — the only open conflict in a table of 152 (151 resolved, overwhelminglyfalse_positive/ extraction-noise classes). - Audit the 653 working rows at importance
0.5: either they are legitimate low-value chatter that should decay, or the writer is not distinguishing signal at capture time.
Related
- systems/mnemosyne — live tier counts and coverage
- concepts/agent-memory — memory model
- incidents/2026-10-03-mnemosyne-vector-recall-fts-only — the earlier, different recall failure