wiki audit 2026-11-20: three-window catch-up (11-17/11-18/11-19, both prior audit slots died)

- new: incidents/2026-11-18-wiki-audit-credit-outage (audit failed 11-18 + 11-19, deliveries suppressed, incident row alerted_at=None)
- new: incidents/2026-11-18-mnemosyne-watchdog-conflict-threshold-storm (115 consecutive slots, 59 unresolved conflicts vs threshold 50)
- corrected: incidents/2026-11-14-mnemosyne-capture-stall + systems/mnemosyne — freeze ENDED 2026-11-18 19:25 AWST (105h52m, no intervention); 'capture dead' reading was conversational silence (every interactive session captured)
- systems/scheduled-tasks: new Count bullet 11-17 173(171/2) / 11-18 172(153/19) / 11-19 176(78/98); fleet 29 (26/3); non-clean last_status 1->4; unclosed incidents 5->4; deliveries 24 (23 delivered / 1 failed)
- index.md feed + incidents + systems lines; log.md dated entry; current-state.md new section; frontmatter dates -> 2026-11-20
This commit is contained in:
Tony0410
2026-11-20 01:02:44 +08:00
parent 16f2c878c0
commit 226767f3ec
8 changed files with 310 additions and 22 deletions
@@ -1,17 +1,21 @@
---
title: Mnemosyne capture stalled for 62+ hours (2026-11-14 09:33 AWST onward) — five unclosed alerts, freeze total on re-read
title: Mnemosyne capture stalled 105 h 52 m (2026-11-14 09:33 → 2026-11-18 19:25 AWST), then quiet again — four unclosed alerts
type: incident
status: active
created: 2026-11-15
updated: 2026-11-17
verified_on: 2026-11-17
review_after: 2026-11-18
updated: 2026-11-20
verified_on: 2026-11-20
review_after: 2026-11-21
confidence: high
tags: [mnemosyne, memory, capture, cron, health-monitor, desktop, pulse, incident, signature-fragmentation, freshness-gate]
sources: [live-mnemosyne-db, live-cron-executions-db, live-cron-incidents, live-hermes-agent-log, live-mnemosyne-health-monitor-log, live-config-yaml, live-state-db, live-mnemosyne-freshness-gate-script]
---
# Mnemosyne capture stalled for 62+ hours (from 2026-11-14 09:33 AWST)
# Mnemosyne capture stalled 105 h 52 m (2026-11-14 09:33 → 2026-11-18 19:25 AWST), then quiet again — four unclosed alerts
> ⚠ **2026-11-20 re-read — the freeze ended by itself at 2026-11-18 19:25 AWST (105 h 52 m total), and every
> interactive session inside the window was captured.** The "capture is dead" reading below is a *quiet estate*,
> not a broken hook. Read the newest re-read section before the earlier readings.
**Open.** Nothing has been written to Mnemosyne's capture tables since **2026-11-14 ~09:33 AWST**,
and on **2026-11-15 00:03:35** the *Mnemosyne Health Monitor* (`ea79a2107e36`) **failed** on it
@@ -144,6 +148,58 @@ total.**
`review_after` 2026-11-18 — this page is re-read at the next audit, and the monitor keeps alerting.
## Re-read 2026-11-20 00:5x AWST — the freeze ended by itself after **105 h 52 m**, and the "capture is dead" reading was wrong
**The capture freeze is over. The alarm is not.** Live reads of `mnemosyne.db` at 2026-11-20 00:0x–00:5x AWST:
| counter | 2026-11-17 00:27 | 2026-11-20 00:5x |
| --- | --- | --- |
| `working_memory` | 1130 | **1131** |
| `episodic_memory` | 1249 | **1250** |
| newest write | `2026-11-14 09:32:59` AWST | **`2026-11-18 19:25:03` AWST** (stored UTC `11:25:03`) |
The break coincides with nothing: no config edit, no restart and no repair is recorded against the capture path
in the window — the only nearby state change is the 11-18 19:18 desktop session itself. The single new
`working_memory` row carries `session_id: hermes_20261118_191808_5c9e08` and its content begins
`[USER] You are helping me migrate contex…`, which identifies the captured turn (the `desktop` session
**`20261118_191808_5c9e08`**, *"Helping migrate context AI assistant"*, 9 messages, started 19:18 AWST).
**Stall duration: 105 h 52 m** (2026-11-14 09:33 → 2026-11-18 19:25 AWST).
⚠ **The correction that matters — the window contained almost no conversation to capture.** `state.db` lists
**three** non-cron sessions since 2026-11-14 00:00 AWST: two `desktop` sessions on **11-14** (**08:35**, 40
messages; **08:52**, 41 messages — both *before* the 09:33 boundary), then **nothing** until the **11-18 19:18**
session, whose turn is the row that ends the freeze. Every interactive session in the window was captured, so
the earlier figures on this page (`0 writes in 38 h 46 m`, `62 h 54 m`) are real but measure **a quiet estate**,
not a broken hook: `mnemosyne_freshness_gate.py`'s `newest_user_message()` reports the age of the newest message
whose session source is not `cron`/`subagent`, so **silence and failure read identically**. That ambiguity — not
a broken capture path — is the durable defect on this page.
**The monitor is still failing on that same metric, after the break.** `ea79a2107e36` slots since 11-18:
`11-18 00:01:28` failed · `11-18 12:01:13` failed · **`11-19 00:01:34` `completed`** (the only clean slot since
11-17) · `11-19 12:01:17` failed · `11-20 00:01:22` failed — every failure `Script exited with code 1 / 🚨
Mnemosyne Health Monitor — exception(s): STALE MEMORY PIPELINE: capture …`, i.e. **the same signature firing on
a healthy pipeline** (`failure_streak: 2`; incidents `ea79a2_f2be2db3bfce` at 2026-11-19 12:01:58 and
`ea79a2_aae4d914f3c9` at 2026-11-20 00:03:36, both `alerted`, both `failure_type: auth` — the scheduler's
classifier, not a credential fault). The `11-19 00:01` pass and the `12:01` failure bracket the threshold: the
metric is *age of the newest captured conversational turn*, which only grows while the estate is silent.
**The other half of the original finding is unchanged, and larger.** The consolidator still consolidates zero
items: newest `consolidation_log` row **`2026-11-19T16:20:14.587267+00:00`** (= 2026-11-20 00:20 AWST, so it is
running on its ~31-minute cadence) with `items_consolidated: 0` and `summary_preview: "No-op consolidation cycle
— timestamp updated for watchdog"`. **199 of the last 200 cycles are zero-item** (was **120** at the 11-17 read
— consistent with ~31 min cadence over the three days). The zero-item-streak threshold remains **proposed, not
applied**.
**Unclosed incidents: 5 → 4** (one of the rows present at the 11-17 read has since closed). Current four, none
closed automatically: `cbfe43_fa12cca1ad4b` (*auth*, 2026-11-18 00:01:42, `alerted_at: None` — the wiki audit's
silent skip, see [[incidents/2026-11-18-wiki-audit-credit-outage]]), `96eb95_98ade422d195` (*script*,
2026-11-18 20:01:15 → last_seen 2026-11-20 00:31:16 — see
[[incidents/2026-11-18-mnemosyne-watchdog-conflict-threshold-storm]]), `ea79a2_f2be2db3bfce` (2026-11-19
12:01:58) and `ea79a2_aae4d914f3c9` (2026-11-20 00:03:36).
**Standing open question, restated:** not *"why did capture stop"* but **"why does the gate treat conversational
silence as a fault?"** Until that is fixed, this page will keep re-opening on quiet days.
## Symptom (live reads, 2026-11-15 ~00:3x–00:4x AWST)
- Newest `working_memory.created_at`: **`2026-11-14 01:32:59`** — stored **UTC**, i.e.