wiki audit 2026-11-21: session-scoped capture re-diagnosis (124 Pulse rows, ~57 uncaptured turns, gateway-restart hypothesis NOT proven); NEW page — first content_policy_blocked digest failures (gmail 08eb86f02d37 + freshrss ecc1fc13655a); watchdog streak 115->210 (single incident row); wiki-audit credit outage RESOLVED (two nights lost, 11-20 delivery suppressed); ledger corrections (4 unclosed health-monitor rows, not 5; audit incident closed 2026-11-20T01:19:13; 7 unclosed cron_incidents); skills-index regenerated 299 skills/67 cats; freshness 5 stale/132 fresh/3 no-date; Quartz rebuilt+deployed (879 files)

This commit is contained in:
Tony0410
2026-11-21 00:40:00 +08:00
parent f603c29d17
commit ca0ff5aa80
11 changed files with 484 additions and 31 deletions
+52
View File
@@ -1360,3 +1360,55 @@ completed at **2026-11-07T00:45:32+08:00**, run **after** this audit's writes:
condition), [[current-state]], [[index]], `log.md`, and the vault mirror (`/home/hermes/wiki`, both
- **No wiki page removed or archived**, no job added, retired, disabled or repinned; no system obsoleted; no
decision reversed. The only archival action in-window was the four *skills* above, at the filesystem level.
## Re-verified 2026-11-21 (window 2026-11-20, AWST; live reads 2026-11-21 00:0x–00:5x)
**Fleet flat at 29 jobs / 26 enabled** (twelfth-plus consecutive window). Ledger, deliveries and the two
standing incidents re-read; **two new failure signatures appeared on 11-20**, both raised by the model-facing
API rather than by job logic.
### Non-clean `last_status`
| Job | ID | Schedule | Streak | Cause |
|---|---|---|---|---|
| Mnemosyne Watchdog | `96eb95ce12f2` | `*/15 * * * *` | **210** | 59 unresolved conflicts vs threshold 50 (standing since 11-18 20:01) |
| Mnemosyne Health Monitor | `ea79a2107e36` | `0 */12 * * *` | **4** | `STALE MEMORY PIPELINE: capture missed: user message` |
| Gmail Action Digest | `08eb86f02d37` | `30 8 * * *` | **1** | `content_policy_blocked` (11-20 08:31:06) |
| FreshRSS Midday News Briefing | `ecc1fc13655a` | `0 12 * * *` | **1** | `content_policy_blocked` (11-20 12:01:14) |
All four are `enabled: true`. `failure_streak = 1` on the two digests means **isolated failures, not chronic** —
the preceding slot of each completed (FreshRSS Midday ran clean on 11-19 12:01).
### New failure class: provider content filter
Both digests died on the identical string — `RuntimeError: content_policy_blocked: Output data may contain
inappropriate content.` — hours apart, with every other job in the window clean. Both **alerted** (incident
rows `08eb86_c0cca1a55b96`, `ecc1fc_5a10b70830d1`, both unclosed) and both are classified
**`failure_type: unknown`**, so the classifier cannot group or auto-close this class.
→ [[incidents/2026-11-20-content-policy-blocked-digest-failures]]
### Standing reds
- **Watchdog: 210 consecutive 15-minute slots**, one stable incident id `96eb95_98ade422d195`
(`first_seen_at` 11-18 20:01:15, `last_seen_at` 11-21 00:31:16 (00:16:15 at the first read), `alerted_at` 11-20 21:31:24, unclosed) —
**no signature fragmentation**, contrary to the 11-20 page's concern.
- **Health monitor: the opposite.** One standing condition re-forms a **fresh incident id every slot**
(`ea79a2_f2be2db3bfce` 11-19 12:01:58, `ea79a2_aae4d914f3c9` 11-20 00:03:36, `ea79a2_ace0f263e18a`
11-21 00:03:12) — three rows for one fault. The two monitors differ in de-duplication behaviour and it is
worth knowing which is which when reading the ledger.
- **Capture:** `working_memory` **1,131** / `episodic_memory` **1,250**, unchanged; corrected diagnosis on
[[incidents/2026-11-14-mnemosyne-capture-stall]].
- **Consolidation 0 items** in 199 of the last 200 cycles.
### Freshness / files touched
- `python3 raw/stocktake/_freshness_audit.py . raw/stocktake/freshness-20261121.txt 21` →
**5 stale / 131 fresh / 3 no-date of 139 pages**. The five at exactly 21 d are the predicted cohort:
`job-radar` ×2, `conduit-voice`, `m93p-nfs`, `homepage-dashboard`.
- **Pages touched by this audit:** [[incidents/2026-11-20-content-policy-blocked-digest-failures]] (new),
[[incidents/2026-11-14-mnemosyne-capture-stall]] (title + fifth read),
[[incidents/2026-11-18-mnemosyne-watchdog-conflict-threshold-storm]] (115 → 210 slots),
[[incidents/2026-11-18-wiki-audit-credit-outage]] (→ resolved), [[systems/mnemosyne]],
[[current-state]], [[index]], `log.md`.
- **No job added, retired, disabled or repinned; no page removed or archived; no system obsoleted; no decision
reversed.**