Files
agent-estate-wiki/incidents/2026-10-03-mnemosyne-vector-recall-fts-only.md
T

80 lines
5.7 KiB
Markdown

---
title: Mnemosyne Vector Recall Ran FTS-Only
type: incident
status: resolved
created: 2026-10-04
updated: 2026-11-18
verified_on: 2026-11-18
confidence: high
tags: [mnemosyne, memory, embeddings, fastembed, recall, incident]
sources: [live-probe, check_embedding_coverage.py, session-2026-10-03]
---
# 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/`FTS5` matching.
- 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:
1. **`fastembed` absent from the managed runtimes.** The gateway runs from a uv-managed venv under `~/.hermes/installs/<install>/environments/<hash>/venv`, and none of them had `fastembed`. The *legacy* `/home/hermes/.hermes/hermes-agent/venv` had it (0.8.0), which is why CLI-side checks looked healthy while the gateway could not embed.
2. **`FASTEMBED_CACHE_PATH` unset** in `~/.hermes/.env`, so the local model directory was resolved implicitly rather than pinned.
3. **Isolated-mode launches.** The embedding worker can be launched with `python -I`, which ignores `PYTHONPATH`/`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 by `mnemosyne-watchdog.py` — so it now asserts, in the bootstrap-selected venv: `fastembed` importable, `FASTEMBED_CACHE_PATH` set, and the model directory present, on top of its existing `dotenv` + `mnemosyne` checks 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.
## Current state (re-verified 2026-11-18)
The fix continues to hold. The 6-hourly coverage monitor `b63ed5817212` is `enabled`, `last_status: ok`, `failure_streak: 0`, last run 2026-11-18 00:04 — it has had nothing to fire on, so working coverage remains at/above the 95 % threshold. (The coverage script itself could not be re-run this session — the gateway's lifecycle guard blocks scripts touching the >1 MiB Mnemosyne DB — so the monitor's clean streak is the verification, per the monitor's own design.)
## Follow-ups
- ~~Confirm the embedding-coverage alert job (`b63ed5817212`, every 6h, Telegram topic 102) still fires when working coverage drops below 95%.~~ **CONFIRMED 2026-10-26** — the job is `enabled` with `last_status: ok`; working coverage is 96.8 %, above the threshold, so it correctly has nothing to fire on.
- ~~Consider asserting `fastembed` in **all** managed runtimes, not only the bootstrap-selected one, so a runtime switch cannot reintroduce this.~~ **DONE 2026-10-26** — `fastembed` 0.8.1 now imports in **both** managed runtimes (`19da945341ad4794ac2bc8ff9fdd3643`, `d41b16c8b6674454a4a819bd4acced1f`) as well as 0.8.0 in the legacy venv.
## Related
- [[systems/mnemosyne]]
- [[systems/memory-backend]]
- [[incidents/2026-09-28-hermes-managed-runtime-deps]]
- [[incidents/2026-08-18-mnemosyne-capture-pipeline]]