Mark-don't-delete: the CT450 '3 commits behind' follow-up and the two mnemosyne-vector-recall follow-ups are struck through with their verified 2026-10-26 resolution rather than removed. - CT450 tracks origin/main (there is no origin/master on that remote) and is 0 commits behind. - Coverage monitor b63ed5817212 is enabled, last_status ok, working coverage 96.8% — correctly has nothing to fire on. - fastembed 0.8.1 now imports in both managed runtimes plus the legacy venv.
5.2 KiB
title, type, status, created, updated, verified_on, confidence, tags, sources
| title | type | status | created | updated | verified_on | confidence | tags | sources | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Mnemosyne Vector Recall Ran FTS-Only | incident | resolved | 2026-10-04 | 2026-10-26 | 2026-10-26 | high |
|
|
Mnemosyne Vector Recall Ran FTS-Only
Summary
Until 2026-10-03, mnemosyne_recall was scoring keyword-only. fastembed was missing from every UV-managed runtime, so the dense (vector) leg of recall contributed no candidates. Nothing errored — recall still returned results, just worse ones. Detected and repaired 2026-10-03; re-verified live 2026-10-04.
Impact
- Semantic similarity search silently degraded to keyword/
FTS5matching. - No user-visible error, no failed cron job, no alert. The failure mode of a missing embedding backend is quiet recall degradation, not a crash — which is why it survived unnoticed.
- Nothing was lost: the residue is un-embedded rows, not missing rows (26 working / 6 episodic as of 2026-10-04). New writes embed normally.
Root Cause
Three overlapping conditions:
fastembedabsent from the managed runtimes. The gateway runs from a uv-managed venv under~/.hermes/installs/<install>/environments/<hash>/venv, and none of them hadfastembed. The legacy/home/hermes/.hermes/hermes-agent/venvhad it (0.8.0), which is why CLI-side checks looked healthy while the gateway could not embed.FASTEMBED_CACHE_PATHunset in~/.hermes/.env, so the local model directory was resolved implicitly rather than pinned.- Isolated-mode launches. The embedding worker can be launched with
python -I, which ignoresPYTHONPATH/PYTHONHOME— any path-based injection of the dependency does not survive that launch mode.
Fix (2026-10-03)
- Installed
fastembed(0.8.1) into the runtime the bootstrap actually selects. - Pinned
FASTEMBED_CACHE_PATH(models cached under~/.hermes/cache/fastembed,BAAI/bge-small-en-v1.5). - Extended
~/.hermes/scripts/hermes-runtime-deps-guard.sh— run every 15 min bymnemosyne-watchdog.py— so it now asserts, in the bootstrap-selected venv:fastembedimportable,FASTEMBED_CACHE_PATHset, and the model directory present, on top of its existingdotenv+mnemosynechecks in the installer python and every managed venv. - No gateway restart required.
Verification (live, 2026-10-04)
Memories with embeddings: 1759 / 2194 (80.2%)
Working memory: 726 / 752 (96.5%)
Episodic memory: 1033 / 1039 (99.4%)
vec_episodes_rowids: 1035
vec_working_rowids: 739
Embeddings generated (24h): 13 (working: 7, episodic: 6)
onnxruntime threads now appear in ~/.hermes/logs/mcp-stderr.log on each model load — direct evidence the embedding model is executing inside the gateway runtime. The dependency guard exits 0.
Caveat — do not misread mnemosyne doctor
mnemosyne doctor and the recall CLI run under the legacy venv/ (Python 3.11), where the sqlite_vec extension is not importable. Doctor therefore prints vec0: present_but_unloadable and marks the working/episodic vector tiers unavailable, even while the gateway embeds normally. The managed Python 3.14 venvs cannot import sqlite_vec either when probed directly. Judge vector health with ~/.hermes/scripts/check_embedding_coverage.py, not with doctor's vec0 line.
Benign noise
[E:onnxruntime:Default, env.cc:228 ThreadMain] pthread_setaffinity_np failed for thread: … mask: {0,} — a container CPU-affinity warning emitted on every model load. Not an error; do not chase it.
Current state (re-verified 2026-10-26)
The 2026-10-03 follow-up is satisfied: fastembed 0.8.1 is importable in both managed runtimes (19da945341ad4794ac2bc8ff9fdd3643, d41b16c8b6674454a4a819bd4acced1f) as well as 0.8.0 in the legacy venv, and FASTEMBED_CACHE_PATH is pinned in ~/.hermes/.env.
Current check_embedding_coverage.py output:
Memories with embeddings: 1899 / 2350 (80.8%)
Working memory: 815 / 842 (96.8%)
Episodic memory: 1084 / 1090 (99.4%)
vec_episodes_rowids: 1086
vec_working_rowids: 828
Embeddings generated (24h): 15 (working: 9, episodic: 6)
Both tiers are above the 95 % working-coverage reindex threshold, so the 6-hourly
monitor job b63ed5817212 (last_status: ok) has nothing to fire on. The 2026-10-04
figures below are superseded.
Follow-ups
Confirm the embedding-coverage alert job (CONFIRMED 2026-10-26 — the job isb63ed5817212, every 6h, Telegram topic 102) still fires when working coverage drops below 95%.enabledwithlast_status: ok; working coverage is 96.8 %, above the threshold, so it correctly has nothing to fire on.Consider assertingDONE 2026-10-26 —fastembedin all managed runtimes, not only the bootstrap-selected one, so a runtime switch cannot reintroduce this.fastembed0.8.1 now imports in both managed runtimes (19da945341ad4794ac2bc8ff9fdd3643,d41b16c8b6674454a4a819bd4acced1f) as well as 0.8.0 in the legacy venv.