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
+16 -5
View File
@@ -3,16 +3,27 @@ title: Current State
type: concept
status: active
created: 2026-07-22
updated: 2026-11-20
verified_on: 2026-11-20
review_after: 2026-11-21
updated: 2026-11-21
verified_on: 2026-11-21
review_after: 2026-11-22
confidence: high
tags: [system]
sources: [live-cron-list, live-sqlite-cron-executions, live-sqlite-sessions, live-probe, live-executions-db, live-cron-incidents, live-deliveries-db, live-sessions-db]
sources: [live-cron-list, live-sqlite-cron-executions, live-sqlite-sessions, live-probe, live-executions-db, live-cron-incidents, live-deliveries-db, live-sessions-db, live-sqlite-mnemosyne]
---
# Current State
Updated: 2026-11-20
Updated: 2026-11-21
## Recent Changes (2026-11-20, nightly audit; live probes 2026-11-21 00:0x – 00:5x AWST)
**Three things moved: the capture fault was re-diagnosed as session-scoped (correcting the 11-20 read), two digests died on a provider content filter, and the audit itself came back.**
- **⚠ Capture — the 11-20 "every interactive session was captured" finding is WITHDRAWN.** That read counted *sessions*; capture is per *message*. Per message, the desktop DM session `20261031_190813_95fbde` owns **124** Pulse/automation rows in `working_memory`, spanning **2026-10-31 11:09:16 → 2026-11-13 13:10:35 AWST**, and **nothing after** — while the session kept producing turns: **~57** since (last captured turn **13:06:05**, first uncaptured **13:21:00**, verified in `state.db`). The **11-13 13:14 gateway restart** sits inside that 15-minute boundary — **leading hypothesis, explicitly NOT proven** (`agent.log`'s oldest surviving file begins **11-13 19:03:34**; the window has rotated out). Capture is **not** globally dead: the only write since, **`2026-11-18 19:25:03` AWST**, came from the new session `hermes_20261118_191808_5c9e08`. Counters frozen at `working_memory` **1,131** / `episodic_memory` **1,250**; silence since the last write **52 h 35 m**. The health monitor already reports it in its own words: `STALE MEMORY PIPELINE: capture missed: user message`, `failure_streak: 4`. → [[incidents/2026-11-14-mnemosyne-capture-stall]], [[systems/mnemosyne]]
- **New failure class — `content_policy_blocked`.** Two unrelated digests died on the identical provider string on 11-20: **Gmail Action Digest** `08eb86f02d37` at **08:31:06** and **FreshRSS Midday News Briefing** `ecc1fc13655a` at **12:01:14**. Both `failure_streak: 1` (**isolated**), both **alerted**, both **unclosed**, both classified `failure_type: unknown`. → [[incidents/2026-11-20-content-policy-blocked-digest-failures]]
- **The audit came back — and the outage was two nights, not one.** `cbfe434a3b5e` reads `last_status: ok` / streak 0. Ledger: **11-18 00:00 failed**, **11-19 00:00 failed**, **11-20 00:00 completed** (report not delivered — `delivery_outcome: suppressed`), **11-21 00:00** this run. The 11-20 run absorbed windows **11-17 and 11-18** via its three-window catch-up. **No re-run was forced.** → [[incidents/2026-11-18-wiki-audit-credit-outage]] now `resolved`.
- **Watchdog still red — 210 consecutive 15-minute slots** (was 115 at the 11-20 read), **59 unresolved conflicts vs a threshold of 50**. Its incident `96eb95_98ade422d195` held **one id** from **11-18 20:01:15** to **11-21 00:31:16 (00:16:15 at the first read)** (**no fragmentation**) — unlike the **health monitor**, which re-forms a fresh incident id every slot for one standing condition (`ea79a2_f2be2db3bfce` → `…aae4d914f3c9` → `…ace0f263e18a`). → [[incidents/2026-11-18-mnemosyne-watchdog-conflict-threshold-storm]]
- **Consolidation still zero-item:** 199 of the last 200 cycles. Fleet **29 jobs / 26 enabled** (flat). Freshness audit **5 stale / 131 fresh / 3 no-date of 139** — the five at exactly 21 d are the predicted cohort (`job-radar` ×2, `conduit-voice`, `m93p-nfs`, `homepage-dashboard`).
- **Pages touched:** [[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), [[incidents/2026-11-18-wiki-audit-credit-outage]] (→ resolved), [[systems/mnemosyne]], [[systems/scheduled-tasks]], [[index]], `log.md` — frontmatter dates → **2026-11-21**.
## Recent Changes (2026-11-17 → 2026-11-20, three-window audit; live probes 2026-11-20 00:0x – 00:5x AWST)