Tony0410
3271ff12a5
audit 2026-10-25: third consecutive clean cron day; new incident (agent refused 3 Conduit call requests); correct 10-22 memory-fix evidence; conduit 0.69.0/f000bf0
2026-10-25 00:16:26 +08:00
Tony0410
573a4a2434
audit 2026-10-24: conduit page + memory-start-timeout incident; 10-09 storm resolved; window 169/0; frontmatter for 2 legacy incident pages
2026-10-24 00:24:44 +08:00
Tony0410
3919ec8557
🦉 wiki audit 2026-10-22: omni-101 pre-dispatch filter skip (3rd failure mode, new page), Hermes 0.22.3 update with snapshot skipped, Gitea backup backlog 76
...
- new: incidents/2026-10-21-omniroute-pre-dispatch-filter-skip.md
- systems/hermes-agent.md: version -> 0.22.3 (5b147ab036), 22:47-22:57 update, snapshot stage skipped, advisories unactioned
- systems/scheduled-tasks.md: 2026-10-21 = 171 completed / 1 failed; non-clean stays 9 with 08eb86f02d37 out, dca8482e4f76 in
- systems/omniroute.md: one pin, three signatures in eight days
- incidents/2026-10-16-omniroute-503-resource-pressure.md: window update, stays monitoring
- incidents/2026-08-08-gitea-config-backup-push-dead.md: 2026-10-21 run, backlog 75 -> 76, message_id 8449
- infrastructure/backups.md: 76 commits; pre_update_backup:false now exercised
- current-state.md, index.md, log.md updated
2026-10-22 00:16:39 +08:00
Tony0410
b662254569
🦉 wiki audit 2026-10-21: gateway unclean-exit orphaned run (new), Gitea config-backup push dead since 2026-08-08 (new), model default → nous, 503 back to monitoring, canned-substitute trigger corrected
2026-10-21 00:11:44 +08:00
Hermes Rhino
95fd7d33f1
audit(2026-10-20): omni-101 503 burst 2 — incident back to active; scheduled-tasks rebuilt from jobs.json
...
- burst 2 (2026-10-19): 9 model calls across 8 jobs, 159/13 day
- burst-2 table names/schedules/aliases corrected from live jobs.json
- non-clean last_status 7 -> 12; unclosed incident rows 13 (query stated)
- 2026-10-17 tail corrected 162/5 -> 163/5
2026-10-20 00:12:39 +08:00
Tony0410
0ed522bfb8
audit(2026-10-19): degenerate-stream incident page + push-notifications page; refresh scheduled-tasks, current-state, index, log, messaging, mnemosyne, tailscale, proxmox
2026-10-19 00:21:26 +08:00
hermes-audit
4137dd6945
audit 2026-10-18: new incident page (omniroute-1 503 resource pressure, 9 calls / 7 jobs), fleet re-verified 28 jobs / 25 enabled / 8 non-clean, Mosquito Tracker removed, radar bot token dead
2026-10-18 00:41:38 +08:00
hermes
2061b8607b
audit(2026-10-16): fleet-wide 34h cron blackout 10-14 -> 10-15 — omniroute-1 refused connections
...
omniroute-1 (100.78.63.20:20128, provider custom:omni-101) TCP-unreachable 10-14 08:30 -> 10-15 18:07
(httpcore.ConnectError Errno 111 -> openai.APIConnectionError -> RuntimeError: Connection error).
36 failure rows across 13 jobs = 24 genuine model-call failures on 12 jobs + 12 Mnemosyne Watchdog
symptom rows. 10-14 160/12, 10-15 151/24 (vs 10-12 175/0, 10-13 167/1).
STRUCTURAL: all 18 enabled agent-mode jobs are pinned to custom:omni-101; the only other model-capable
pin (custom:omni, CT600) sits on a no_agent job -> no model-call failover, and zero model calls
completed in 34h. Corrects a first-pass reading of Evening Stand-Down's green rows as CT600 evidence.
New: incidents/2026-10-14-omniroute-node-connection-refused-storm.md (resolved, verified live).
Updated: systems/scheduled-tasks (frontmatter, Count, new Re-verified block), systems/omniroute,
systems/mnemosyne (monitor blast-radius note), current-state, index, log.
2026-10-16 00:19:14 +08:00
Tony0410
deb6a8eec2
stocktake 2026-10-14: SECOND Proxmox host m93p (100.104.51.98, PVE 9.2.0, unclustered, IDs collide) discovered — gitea/ntfy/freshrss/openweb were never on pve; tailnet inventory rebuilt 30 -> 45 nodes (15 missing); VM 282 running; Camofox recovered to 29.9M
...
skills-index 346 skills / 70 cats; freshness 48 stale / 38 fresh / 7 no-date of 93 pages
- infra/proxmox.md: two-host rewrite, m93p LXC+QEMU inventory, 4-entry correction table, VM 282 stopped->running, storage via pvesm (ssd0 88.17%/63GiB free)
- infra/tailscale.md: 45-node inventory rebuilt from live status; 23 funnel-ingress-node IPv6 peers noted+excluded; CT460 serve routes re-verified exactly (13 routes + :8443 Funnel + :9443)
- infra/network-map.md, current-state.md, index.md, log.md updated
- Open: 3 incidents (unverified pages left stale, not rewritten); omniroute/hosts/model-providers/docker-services still single-host in framing — m93p runs its own omniroute CT101, needs a dedicated pass
2026-10-14 03:13:04 +08:00
Tony0410
828913e23b
audit(2026-10-14): 10-13 broke the clean streak — wiki-stocktake failed on a dead opencode credential (HTTP 404, incident 1a8e90_d11698bd7275); stranded skills-index + freshness-20261013 recovered; retention floor moved to 2026-10-08 07:11
2026-10-14 00:17:31 +08:00
hermes-audit
ebf57146f1
audit(2026-10-13): 10-12 clean (174/0, 3rd day) but GitHub Trending Radar token DEAD (getMe 401) - supersedes the wrong 2026-10-06 'refuted' entry
...
Incidents 5->2 (deepseek-v4-flash pair closed 03:05:39, Job Radar timeout 07:33:41); storm page re-tallied 11/12 closed with closure timeline.
NEW: Camofox hit its cgroup ceiling inside the 07:01 Job Radar run (2.5G, swap exhausted, 383 tasks) - containment drop-in documented; browser-backend/steel-vs-camoufox/browser-automation corrected to REST :9377 on CT460 (was :9093 on CT450).
Mnemosyne 96.7%/99.4% coverage green; 18 cron sessions, 0 interactive; retention floor 2026-10-07.
2026-10-13 00:19:15 +08:00
hermes
0eee5f101e
stocktake 2026-10-12: skills-index 346 skills/70 cats; freshness 54 stale/32 fresh/7 no-date; nanobot + home-assistant re-verified live (nanobot web UI back up on :8766, OmniRoute :8900 still closed -> stays degraded; HA HTTP 200 on :8123
2026-10-12 03:17:10 +08:00
Tony0410
6fc109e546
audit(2026-10-12): cron fleet clean 2nd day (10-11 171/0, 10-10 finalised 175/0); UTC-vs-AWST false 'capture stalled' alarm corrected; proxmox storage table + host mounts; queries/retained-research-answers stub filled (VNC); capture-pipeline incident -> superseded; index stale labels fixed
2026-10-12 00:14:11 +08:00
hermes
7bffeab157
audit(2026-10-10): DHL monitor retired (29 jobs / 26 enabled, verified by ID lookup); 10-10 fleet clean 174/0, 7 incidents closed - 5 open; gateway runtime env recurrence (mnemosyne + elevenlabs) verified fixed; new systems/paseo.md; mattermost unreachable; current-state + index + log updated
2026-10-11 00:22:20 +08:00
Hermes
c11f11e652
stocktake 2026-10-10: skills-index + freshness report (62 stale/23 fresh/7 no-date of 92); current-state 10-10 section (timeout-storm window re-tallied 163/15, 10 open incidents, stocktake in-flight); tailscale.md verified vs live serve status; log entry
...
- Wiki maintenance run of wiki-maintain.sh, manual (scheduled 1a8e90ea2271 03:00 run in-flight)
- Verified live: tailscale serve status (all routes match), cron jobs.json (30 jobs), executions.db window, SKILL.md count
- Not verified: docker-services.md (docker.sock permission denied) — left stale; Quartz rebuild inert (no quartz.config.ts)
2026-10-10 03:05:36 +08:00
Tony0410
8cab69bbd0
wiki audit 2026-10-09: fleet-wide cron timeout storm (15 failures/10 jobs) + memory recall-relevance incident; backfill 2026-10-08 window; commit stranded stocktake artifacts
2026-10-10 00:27:15 +08:00
Hermes
659356aa61
wiki audit 2026-10-08: DHL Camofox timeout auto-resolved, stocktake Quartz/skills-count findings, fleet green day 3
2026-10-08 00:12:32 +08:00
Tony0410
01f1db3aae
wiki audit 2026-10-07: stocktake repin verified by live run (344->346 skills), fleet 0 failing; vault skills-index re-mirrored
2026-10-07 00:15:06 +08:00
Tony0410
14b467e91b
audit(2026-10-06): dead-model-pin repin resolved; failing set 7 -> 0
...
- new incident: incidents/2026-10-05-dead-model-pin-repin.md
- scheduled-tasks.md: Count block -> 0 failing, all streaks 0; 8 job rows updated;
new 'Resolved 2026-10-05' subsection; 5 resolved bullets pruned from Open
- cliprox incident closed for cron (status: open -> resolved) + resolution section
- index.md: new incident linked, cron line + cliprox line updated
- current-state.md + log.md: 2026-10-06 entries
2026-10-06 00:20:53 +08:00
Tony0410
543e7782f8
wiki audit 2026-10-05: cliprox/terra pin settled 3/3 (Weekly Review failed 2026-10-04 18:00), failing set 6->7, streak-counter/executions.db-retention caveat
2026-10-05 00:09:58 +08:00
Tony0410
78048bdf0b
wiki audit 2026-10-04: CT450 v0.21.5 update incident, mnemosyne vector-recall FTS-only repair + coverage refresh, managed runtimes 10->3, doctor vec0 caveat
2026-10-04 00:15:35 +08:00
Tony0410
b9f69d3f75
wiki audit 2026-10-03: cliprox second job confirmed (2/3), work-mailbox incident page, streak recount, skills-index 341->344
2026-10-03 00:18:51 +08:00
Tony0410
0c4ed3350b
wiki audit 2026-10-02: 2 new cron failures, cliprox/terra connection auth incident, delivery-failure semantics corrected, profile rewrite, broken wikilinks repaired
...
- new: incidents/2026-10-01-cliproxy-connection-auth-expired.md (HTTP 401, credential fault, cannot self-recover)
- systems/scheduled-tasks.md: 30 jobs / 27 enabled; failing 3 -> 6; streaks advanced; wiki-tree drift recorded
- systems/messaging-integrations.md: two distinct thread-failure variants (lost vs thread-less fallback)
- systems/current-profile.md: full rewrite from live config (no profiles/default/, smart-route, OmniRoute)
- current-state.md / index.md / log.md: 2026-10-02 entry
- repair: copied 5 vault-only pages referenced by index.md (ignis, nextcloud, 3 incidents) so wikilinks resolve
- include pending stocktake output: skills-index.md 2026-09-27, raw/stocktake/freshness-2026-09-2{6,7}.txt
2026-10-02 00:17:15 +08:00
Tony0410
a32475bd54
wiki: nightly audit 2026-10-01 — cron fleet re-verified, Telegram delivery root cause, memory hygiene
2026-10-01 00:10:55 +08:00
Tony0410
58312cb434
Wiki audit 2026-09-30: managed-runtime dependency incident, cron fleet reconciliation, provider/model refresh
2026-09-30 19:38:49 +08:00
Tony0410
f9ac274bac
Weekly maintenance: regenerate skills-index (340 skills), freshness audit 2026-09-20 (67 stale, 5 fresh, 7 no-date)
2026-09-20 03:02:05 +08:00
Tony0410
77250ea8c9
incident: SFTPGo outage 2026-09-02 — CT299 tailscaled death + stale lxc-attach recovery
...
- New incident page documenting CT299 SFTPGo outage (02:18 AWST)
- Root cause: swap exhaustion (43Gi, 100%) killed tailscaled; 5 stale lxc-attach PIDs blocked pct start
- Resolution: killed PIDs 3037951/3334928/3352203/3402511/4004148, pct stop/start 299
- Updated current-state.md with Recent Changes (2026-09-02), bumped updated to 2026-09-04
- Updated log.md with incident entry
- Updated index.md last-updated date
No secrets written. Verified end-to-end: tailscale direct, SFTPGo WebAdmin HTTP 401, SFTP banner SSH-2.0-SFTPGo_2.7.0.
2026-09-04 00:05:32 +08:00
Tony0410
f518ff7c66
docs: add CONTRIBUTING.md defining read/write governance for all agents
...
- Who owns which section (scope rules per agent)
- What to save vs never save (no secrets, no session chatter)
- Mandatory conventions (frontmatter, wikilinks, auto-generated pages)
- Git workflow for contributing agents
- Freshness responsibility: each agent keeps its own section current
Link CONTRIBUTING from index.md start-here block.
2026-08-16 02:33:41 +08:00
Tony0410
c8565c62ac
feat: add agent estate section with 7 pages
...
Add agents/ directory with comprehensive documentation for all agents:
- agents/index.md — estate map and relationships
- agents/hermes-production.md — CT460 production Command Centre
- agents/hermes-chaos.md — CT450 experimental Chaos Lab
- agents/nanobot.md — CT333 Scout (quota notifications)
- agents/qwenpaw.md — CT465 multi-agent gateway
- agents/zeroclaw.md — CT333 autonomous daemon (TOML)
- agents/open-claw.md — VM 403 autonomous gateway
Updated index.md with Agent Estate section and links.
All pages follow existing SCHEMA.md conventions with YAML frontmatter.
2026-08-15 22:21:32 +08:00
Tony0410
92e8028bb8
snapshot: preserve central wiki state 2026-08-15 (7 modified + 1 new file)
2026-08-15 22:11:30 +08:00