64 KiB
title, type, status, created, updated, verified_on, confidence, tags, sources
| title | type | status | created | updated | verified_on | confidence | tags | sources | |||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Anthony's Systems Wiki | collection | active | 2026-07-22 | 2026-11-09 | 2026-11-09 | high |
|
|
Anthony's Systems Wiki
Operational knowledge for Anthony's agents, infrastructure, model routing and automation. Last updated: 2026-11-09.
2026-11-09 (nightly audit — window 2026-11-08) — the day's fault was a hook, not a schedule, and it is fixed. The
conduit_pushplugin is the onlypre_tool_callregistrant on the host (__init__.py:119), and its callback overran Hermes's 30 s hook budget 58 times between 2026-11-07 14:14:03 and 2026-11-08 08:21:03 —errors.logholds 12 lines on 11-07 and 46 on 11-08, plus 89 "skipped after previous timeout or while still running" suppression lines. Every tool call degraded to slow-then-suppressed, which is what stretched the day. Fixed 2026-11-08 13:35 AWST:plugins.hook_callback_timeout30 → 120 in~/.hermes/config.yaml— verified live, and verified effective (the last timeout line is still 08:21:03, re-checked at audit time). ⚠ The obvious suspect was measured and acquitted: the plugin's caching is fine (session_titles.py:21 CACHE_SECONDS = 30.0; timed in-process at 3.1 s cold, 0.00 s warm), so the "re-opens a 1.87 GBstate.dbper call, ~9 s each" theory was wrong — the trigger is load on the 2-core CT460 (load average 5.89at 13:27:50,state.dbcheckpointing a 40 MB WAL on the same spindle) → incidents/2026-11-08-pre-tool-call-hook-timeout-cascade. Cost of the fault: Mnemosyne Health Monitor ran 00:01:20 → 08:29:05 (8 h 27 m) and 12:00:51 → 18:00:42 (5 h 59 m 51 s) — its two slowest slots on record, both delivered; FreshRSS Midday Briefing took 2 h 09 m 53 s; and the stocktake failed a third consecutive day (1a8e90ea2271, 03:01:11 → 04:36:08,failure_streak: 3) on a new terminal signature —RuntimeError: ⚠️ No reply: the turn stopped while a tool result was still pending and the model produced no follow-up text.where the previous two red days read "lost its durable fire claim ownership". Working hypothesis, not proven: an open tool result is exactly what a suppressedpre_tool_callwould produce, but the string does not name the hook. 11-08 settled: 169 rows — 168completed/ 1failed/ 1running(this audit, 23:59:33); deliveries 8 / 8delivered; fleet 29 jobs (26 / 3) — a sixth consecutive audit at the same count with nothing added, retired, disabled or repinned, thoughupdated_atmoved to2026-11-09T00:06:50+08:00as a run-state stamp. Unclosed incident rows 2 → 3, all three the stocktake's and all silent (detected,alerted_at: null) — but the alerting path is not the fault: the Newsletter Digest row85edf6_0877ca1e0eacalerted 07:23:07 andresolved08:06:54 in the same window. ✅ Two verified resolutions: the Mnemosyne Health Monitor's no-agent conversion works — its first script slot ran 2026-11-09 00:00:48 → 00:02:02 = 73 s, exit 0, silent, writing a 159 B output file against 105,982 B for the last agent-mode run (coverage live at working 1030/1030 = 100.0 %, episodic 1192/1192 = 100.0 %, so the< 95 %alert is correctly quiet; the script usesawkbecausebcis not installed on this host); and the 1.89 GBstate.dbwas re-measured (1,890,656,256 B, 2,901 sessions / 197,682 messages, live 40 MB WAL) with the 2026-08-11 remnantstate.db.corrupted.20260811_151052(624.1 MB) deleted. New page: incidents/2026-11-08-pre-tool-call-hook-timeout-cascade.2026-11-08 (nightly audit — window 2026-11-07) — two runs orphaned mid-restart, and two incident rows that never alerted. The gateway restart that arrived at 05:01:00 (after a requested restart sat in after-turn mode for the full 1800 s) drained two in-flight cron executions; both closed
failedonlost its durable fire claim ownership— Mnemosyne Health Monitor (ea79a2107e36, 00:00:42 → 05:02:22) and wiki-stocktake-maintenance (1a8e90ea2271, 03:00:31 → 05:02:22, second consecutive failed day,failure_streak: 2). The restart was requested at ~04:29:52 — inside theconduit_pushself-update window (0.122.2 → 0.134.4, 04:27:55→04:32:32, its own ledger recordingrestarting_gateway= failed) — working hypothesis, not proven; the 0.22.5 → 0.23.0 updater is excluded (its receipt starts 05:05:13). Day counts: 163 rows — 159completed/ 3failed/ 1running; the third failure is the agent-log watchdog correctly reporting the event 19 s later. ⚠ Both stocktake incident rows are stilldetectedwithalerted_at: null— closed 0 → 2, and neither alerted. Elsewhere in the window: Hermes 0.22.5 → 0.23.0 on CT460 (snapshot stage skipped again — still no rollback point), thecamofoxbrowser backend arrived as an enabled plugin (1.1.0),conduit_pushself-updated to 0.134.4,hermes-hq-pushreinstalled 0.9.27 → 0.9.42 (routes reloaded by the 11:11 restart), and the OpenCode Go credential is expired (HTTP 401api_key_expired— configuration alive, credential dead, nothing consuming it yet). New page: incidents/2026-11-07-cron-claim-loss-in-gateway-restart-drain.2026-11-05 (stocktake) - the
systems/skills-index.mdflip-flop is fixed at the root: two different scripts were writing the page, and the nightly audit was pointed at the stale one; it is now a delegating wrapper -> incidents/2026-11-05-skills-index-generator-divergence. Docker inventory corrected against live probes on all five hosts -the⚠ CORRECTED 2026-11-06: false - the seeders are transient systemd-timer-driven containers, absent only between runs, not removed. Tailscale node table re-verified programmatically - 52 rows, 52 live peers,worldmonitor-seeder-scheduledcontainer recorded yesterday does not exist on any hostevery state matching⚠ CORRECTED 2026-11-06:anthonys-mac-minihas since come back online. Freshness 0 stale / 122 fresh / 3 no-date of 125.)2026-11-07 (nightly audit - window 2026-11-06) - a red row with no alert: 2026-11-06 settled 172 execution rows across 16 jobs - 170
completed/ 1failed/ 1running(this audit). The single failure is a new, non-restart signature: the Job Radar's 11:30 slot (5fc292ff0f3b, 11:30:32 -> 13:26:44) was discarded as stale onFire claim ownership lost; stale result was discarded.because adirectfire of the same job (08:27:09 -> 13:26:22, 4 h 59 m 13 s) was still holding the claim and delivered first. Every earlier occurrence of this string came from a restart/reload orphaning a run; this one had no restart -> incidents/2026-11-06-job-radar-concurrent-fire-claim-discard. It raised nocron_incidentsrow (newest ledger activity remains the 2026-11-05T12:36:17 closures) and nothing alerted; the failed run left no output file. The day still landed in full via the 14:30 slot (12 m 27 s,SAME_DAY_STRONG_COUNT 4,MISSING_COVER_LETTER_COUNT 0, cache 494, Run status: COMPLETE). Deliveries 10 rows / 10delivered/ 0for_failure; fleet 29 jobs (26 / 3) - fifth consecutive audit at the same count, nothing added/retired/disabled/repinned, non-cleanlast_statusstill 1 (066bb5191280). The stocktake's overrun fully unwound (1a8e90ea2271, 03:00:32 -> 04:11:35 = 1 h 11 m 03 s against 7 h 40 m / 5 h 41 m / 3 h 02 m on 11-03 -> 11-05) and Stage 1 ran clean for a second day (dca8482e4f76, 1 h 28 m 37 s,suppressed), clearing the 11-04 Open entry in substance. The last audit's open question closed itself: the Mnemosyne Health Monitor's 11-05 12:00:45 slot (12 h+ in flight, undelivered at the last audit) completed at 2026-11-06T00:14:39 after 12 h 13 m 54 s and delivered; its 11-06 slot took 7 h 47 m 56 s and delivered too - ballooned on consecutive days, never lost, watching, not open. The one open page remains incidents/2026-11-05-secrets-at-rest-in-mnemosyne-and-cron-prompts (untouched in-window).2026-11-06 (nightly audit - window 2026-11-05) - a clean ledger day and an empty incident ledger: 2026-11-05 settled 175 rows - 173
completed/ 2running/ 0failedacross 18 jobs, the first zero-failedday since 2026-11-02. The only tworunningrows are the Mnemosyne Health Monitor (12:00:45 slot, still in flight 12 h+ at audit time) and this audit itself. Unclosed incident rows 3 -> 0 - the Newsletter Digest row closed at 07:07:42 and both Job Radar - Discovery rows at 12:36:17, whendca8482e4f76finally completed after 5 h 35 m 35 s; that closes out incidents/2026-11-04-upstream-stream-failure-0700-cohort and incidents/2026-11-03-job-radar-stream-active-timeout in full. Fleet non-cleanlast_status3 -> 1 (only066bb5191280,delivery_failed, streak 0); deliveries 10 rows / 10delivered; the 03:00 stocktake overran 3 h 01 m 58 s (down from 7 h 40 m and 5 h 41 m) and committed2f3fc99at 05:55. Fleet unchanged at 29 jobs (26 / 3) - a fourth audit at the same count. ⚠ New and open: live.envvalues (TELEGRAM_BOT_TOKEN,MATTERMOST_TOKEN,HERMES_CUSTOM_OMNIROUTE_20128_API_KEY) sit verbatim in 17 rows ofmnemosyne.db(memories,episodic_memory,working_memory,gists,memoria_facts.context_snippetand the FTS mirrors) - reproduced in full by each of the 7 uncompressed rotation snapshots - and all four values sit verbatim in the 1.7 GB session storestate.dbtoo;CAMOFOX_API_KEYsits verbatim in the prompts of two enabled Facebook Birthday jobs (0e753e9720fd,fad5a86979d4) and therefore incron/deliveries.db-> incidents/2026-11-05-secrets-at-rest-in-mnemosyne-and-cron-prompts.2026-11-05 (nightly audit) - a dead route, a rescued pipeline, and a second freeze: the 11-04 fleet settled 170 rows - 167
completed/ 2failed/ 1running, non-cleanlast_status2 -> 3, unclosed incident rows 1 -> 3, deliveries 8 rows / 8delivered. Both failures are the same upstream fault:dca8482e4f76(Daily Marketing Job Radar - Discovery) and85edf6772bca(Tech & AI Newsletter Digest (Analytical)) died 36 seconds apart at 09:41-09:42, each after 2 h 41 m, onRuntimeError: Upstream stream failed before completion.- both pinnedcustom:omni-101/smart-route. The day was not lost: the 11:30 Stage 2 slot reconstructed the missing handoff from Stage 1's own candidate files, re-verified every candidate live, and still wrote 5 roles (board 479 -> 484) + 1 canonical cover letter (MISSING_COVER_LETTER_COUNT 0) before consuming the handoff at 16:08:59 -> incidents/2026-11-04-upstream-stream-failure-0700-cohort. The cover-letter route survived only on an override:regenerate_cover_letter.pydefaults todeepseek-paid-smart, which threw HTTP 402 mid-run, so the letter was pinned togemini/gemini-3.5-flashviaCL_MODEL- and that override was never written to.env, so it did not persist. And CT299 was frozen twice, not once: a second, manualvzdump 299 ... --storage ssd0wedged from 11-04 08:30:04 until 11-05 ~00:30 (~16 h); the live probe at 00:54:21 AWST showsLOCK: 0, bothcgroup.freezeflags0, guestALIVE,sftpgo: active-> incidents/2026-11-04-vzdump-freeze-ct299-sftpgo-outage. ⚠ Corrected the same night: the first draft of this entry read the fleet as 158 jobs (144 / 14) and the 11-04 ledger as closing1 item_suppressed; live reads give 29 jobs (26 / 3) and a final row of 1running(this audit). Keyed probe 2026-11-05 01:33:deepseek-paid-smartis undispatchable onomniroute:20128(HTTP 503, all targets skipped) but serves normally onomniroute-1(HTTP 200 ->deepseek/deepseek-v4-flash).
2026-11-04 (nightly audit) — the ledger raised its own red row: the **11-03 fleet settled 170
completed/ 1failed/ 1running/ 0unknown(172 rows) — unclosed incident rows 0 → 1, non-cleanlast_status1 → 2, deliveries 7 rows / 7delivered. The single failure is the Job Radar Stage 1 (dca8482e4f76), which ran 07:00:33 → 13:28:52 (6 h 28 m 18 s) and died onRuntimeError: stream active timeout— a new terminal signature, not the iteration cap — after going silent for 65 m 21 s; its incidentdca848_dfd4bea84f2a(timeout) isalertedand open and the notice was delivered (13:28:51.741724) → incidents/2026-11-03-job-radar-stream-active-timeout. That answers the 11-02 page's open question: output is suppressed when the run endscompleted, delivered when it endsfailed— which is what let 11-02 vanish and 11-03 announce itself. Both Stage 2 slots declined correctly, so 2026-11-02's and 2026-11-03's candidate sets are both unrecovered. ⚠ The 03:00 stocktake overran for a second day (1a8e90ea2271, 03:00:30 → 10:41:13 = 7 h 40 m 43 s,suppressed, nothing delivered, artefacts uncommitted again). New page: systems/hermes-hq-push (v0.9.27, enabled; manifest says it replacesdispatch-push, and no trace of the old plugin survives).⚠ Two Proxmox hosts exist — always qualify a guest with its host. A second unclustered hypervisor,
m93p(100.104.51.98, PVE 9.2.10), was discovered during the 2026-10-14 stocktake. Guest IDs collide between the two hosts.
Start here
- current-state — Current systems status
- systems/hermes-agent — Hermes Agent overview and version
- systems/current-profile — Active Hermes profile details
Systems
Core
- systems/hermes-agent — Agent version, install, config paths
- systems/current-profile — Active profile details
- systems/nextcloud — Nextcloud file sharing (CT270)
- systems/guanaco — Guanaco LLM proxy on CT205 (Ollama stack)
- systems/model-providers — LiteLLM + OmniRoute providers, routing setup
- systems/memory-backend — Mnemosyne vector memory, settings
- systems/mnemosyne — Mnemosyne cron jobs and config evidence
- systems/omniroute — OmniRoute catalog, combos, and host path
- systems/openrouter — OpenRouter current state and history
- systems/opencode-go — OpenCode Go subscription, model limits, pricing
- systems/nanobot — Nanobot current state and history
- systems/browser-backend — Camofox (primary,
systemd --useron CT460, REST:9377) — the only backend; Steel was fully removed from the stack on 2026-10-29 (plugin deleted,cloud_providerback tocamofox, CT201 and CT333 deployments torn down, Serve routes deleted;STEEL_BASE_URLsurvives only in already-running process environments); memory-containment drop-in and the 2026-10-12 ceiling event documented - systems/hermes-ui — Browser Hermes Desktop (przbadu/hermes-ui)
- systems/paseo — Paseo coding-agent daemon + web terminal workspace (CT460, :6767)
- systems/ignis — Ignis browser-native Obsidian (wiki interface)
- systems/terminal-backend — Shell persistence, working directory
- systems/tool-search — Always-on lazy discovery for external tools
Integrations
- systems/conduit — Conduit: Hermes on Anthony's phone (dashboard plugin + iOS app — voice calls, cards, push). Plugin tree
~/.hermes/plugins/conduit_push, v0.122.2(HEAD9eac857, 2026-10-31 12:04 — "Every profile that turns Conduit on runs the main install (#482)"; +148 commits on since the0.69.2/942ddb8baseline, working tree clean), upstreamkaishi00/hermes-conduit-notifier. Gateway on:9119is now pid 176771, started 2026-10-31 19:35:02 (superseded: restarted 2026-10-25 18:42:33, which is when the upstream commits went live). One registered device (iPhone app 2.2.0). ✅ The first two real calls in the product's history are now on record — 2026-10-29 08:38:04 and 08:49:36 — after three faults in series were repaired (truncated speech-server URL →…/v1/realtime; 12 h dashboard session TTL → 30 d; deadgroqSTT →local, deadopenaiTTS →ollama_local) → incidents/2026-10-29-conduit-voice-silence. So the memory fix is no longer evidence-free. ✅ That patch is gone — the tree is clean andMEMORY_TIMEOUT_Sships upstream indashboard/api/memory.py. ⚠ New fault: "local" voice mode never applies — the Mac mini speech server's LLM proxy is disabled (LLM endpoint → 501,/v1/usagereadsllm_proxy.requests: 0, realtime socket rejectssession.update), while the app's "test connection" checks socket reachability only → incidents/2026-10-31-conduit-voice-local-mode-not-applying. The call store was re-shaped:historyis empty andlast_request_atisnull, so the two 10-29 calls are no longer in it. The 10-24 refusal fault has not recurred → incidents/2026-10-24-conduit-call-request-refused. - systems/messaging-integrations — Telegram, Discord, email, Slack, etc. Mattermost's long-running red now has a cause: CT255 is stopped — still stopped on 2026-10-26 (peer offline 36 d,
tx 312 / rx 0; host answers neither:8065nor ICMP). 268 connect timeouts on 10-25 vs 264 on 10-24; the reconnect attempt counter reset to 54 at the 19:27:13 gateway restart — a per-process number, not an outage length. No cron job delivers via Mattermost. - systems/push-notifications — Cadu/Vory push bridge (
hermes-push,vory-push): gateway on:9119, state in~/.hermes/push/. Broken —connected: false(the bridge dials a name that resolves to127.0.1.1where nothing serves 443); chronic, not a blip. - systems/hermes-hq-push — Hermes HQ iPhone app plugin (standalone, v0.9.27,
kind: standalone, author Hermes HQ; tree mtime 2026-11-03 11:06).hermes plugins list→ enabled (stateuser);config.yamlplugins.enabledline 7556. Host side of the Hermes HQ app: Apple push (finished turns, lock-screen approvals, "waiting for a password/login/code" alerts, live Lock Screen cards sealed to the phone), phone device access (contacts, location, reminders, alarms, photos, Health, motion, music), the desktop-app Hermes HQ theme, the app's Terminal page, fast Sessions list on a busy host, cross-posting answers back to Telegram/Discord, a restart guard, and Grok Live voice-token minting (XAI_API_KEYor subscription sign-in; bearer never reaches the phone). Toolsdevice_contacts_search/device_request_result; 7 hooks. Its manifest states it replacesdispatch-push— and the replacement is clean: nodispatch-pushreference survives inconfig.yamland no such directory remains. Different stack from the Cadu/Vory bridge on systems/push-notifications. ⚠ Itspre_tool_callguard also blocks any tool call whose arguments contain the literal text of a launchd one-off-restart command — describe it, never quote it. - systems/scheduled-tasks — As of 2026-10-31 00:3x: 29 jobs (26 enabled, 3 disabled); non-clean
last_status4 → 3; failing 1 → 0; unclosed incident rows 2 → 1; 2026-10-30 closed 138 / 0 after a 5 h 30 m CT460 host outage (PVE reboot, ≈39 slots lost, 8 catch-up runs at 16:37:21), andea79a2107e36is ENABLED again (last_status: ok, streak 0) after its 00:01:08 slot closedcompletedat 10:02:48; deliveries 8/8delivered. Prior window — as of 2026-10-30 03:3x: 29 jobs (25 enabled, 4 disabled); non-cleanlast_status3 → 4; unclosed incident rows 1 → 2; 2026-10-29 settled 177 / 0 (the first clean cron day since 10-24) with 10 deliveries alldelivered. ⚠ea79a2107e36(Mnemosyne Health Monitor) was AUTO-PAUSED at 01:04:22 after its 00:01:08 slot closedunknownon a gateway-connection failure — and its failure notice was NEVER DELIVERED (deliveries.dbhas zero rows for 2026-10-30), so the incident row is the only trace → incidents/2026-10-30-mnemosyne-health-monitor-paused. Every other previously-red job has cleared took/streak 0; the retired DHL row was removed from the job table.** Prior window — as of 2026-10-30 00:0x: 29 jobs (26 enabled, 3 disabled); non-cleanlast_status5 → 3 (all three are stale re-runs of old faults and everyfailure_streakread 0); unclosed incident rows 4 → 1; 2026-10-29 settled 176 / 0 — the first clean cron day since 10-24, with 10 deliveries alldelivered. The Job Radar's two-stage split worked end to end for the first time: stage 1 wrote its handoff (170 discovered / 33 duplicates avoided / 37 verified) and stage 2 landed 20 pages + 2 cover letters withmissing_cover_letter_count 0(Notion 455 → 475). Both stage-1 incident rows closedresolvedat 10:16:12; the lone survivor is the Facebook monthly's0e753e_e7f8194a7d06.** Prior window — as of 2026-10-29 00:3x: 29 jobs, 5 non-clean, 4 unclosed; 2026-10-28 settled 168 / 2 — radar stage 1 hit the iteration cap (no handoff, both stage-2 slots no-oped) and the 03:00 stocktake failed on a 400 that never alerted; 2026-10-27 settled 173 / 1 (revised). Prior window — as of 2026-10-28 00:2x: 29 jobs, 5 non-clean, 2 unclosed; 2026-10-27 settled 172 / 1, and the single failure is the radar's second consecutive tool-budget overrun.**dca8482e4f76ran 07:01:08 → 11:03:54 (4 h 2 m 46 s), closedfailed, and delivered "INCOMPLETE (tool-call budget exhausted before Notion write stage)" — discovery finished, no Notion writes and no cover letters. Incident rowdca848_e93a538ade6bopened 11:03:53 and is still open. The same day the single radar job was split into two: stage 1dca8482e4f76(Discovery, 07:00,deliver: local) + new stage 25fc292ff0f3b(Write and Letters, 11:30/14:30, topic 1030, created 17:34:15, twocompletedtest fires that evening). The two incident rows the 2026-10-26 planned restart raised auto-closed 00:38:32, and the 2026-10-26 orphan class did not recur. → incidents/2026-10-27-job-radar-budget-exhausted, runbooks/job-radar. Prior window — as of 2026-10-27 00:1x: 28 jobs (25 enabled, 3 disabled), 4 non-cleanlast_status, 3 unclosed incident rows; 2026-10-26 settled 169 / 3 — and all three failures are one fault.ea79a2107e36(Mnemosyne Health Monitor, 12:01 slot) was interrupted by a planned 14:33:35SIGTERMrestart that timed the drain out after 1.35 s, killed after 2 h 34 m on a new string (lost its durable fire claim ownership), and raised twocron_incidentsrows; the Mnemosyne Watchdog then fired twice and self-resolved at 15:16:12 → incidents/2026-10-26-planned-restart-orphaned-cron-run. New fleet precedent: a planned stop can orphan a long-running run just as an unclean exit can — and this time it alerted (the 10-20 orphan did not). Unclosed incident rows 2 → 3; one closed:c0a9fa_764558b5ae83auto-closed 09:13:00 when the radar's 09:00 slot ran clean, so every row of the 2026-10-16 503 resource-pressure incident is now closed → incidents/2026-10-16-omniroute-503-resource-pressure. Non-cleanlast_status5 → 4:c0a9fa314542and08eb86f02d37cleared took;ea79a2107e36joins aserror, streak 2. Pins unchanged. ⚠fad5a86979d4's 03:08 slot completed but delivereddelivery_failed— Thread 34795 not found (the gateway's own shutdown notice hit the same dead thread). ⚠ The radar's 07:00 slot delivered “RUN INCOMPLETE — tool-call budget exhausted” and its cover-letter pipeline changed that morning → runbooks/job-radar. Prior window — as of 2026-10-26 00:1x: 28 jobs (25 enabled, 3 disabled), 5 non-cleanlast_status, unclosed incident rows still 2; 2026-10-25 settled 172 / 2 and 2026-10-24 settled 168 / 0. ⚠ Both 10-25 failures are08eb86f02d37(Gmail Action Digest), which also fired six times that day — and neither raised an incident row → incidents/2026-10-25-gmail-digest-runaway-and-refire. ⚠ The global default reverted tocustom:omni-101/smart-routeon 2026-10-24 19:06, so the 8 unpinned jobs are back on OmniRoute and the fleet is a single path again → systems/current-profile. ⚠ Nous Portal credentials still invalid — all 8auxiliaryslots moved tono-think/freeapi/autoat 19:13 → incidents/2026-10-22-nous-portal-refresh-token-invalid. Three gateway starts on 10-25 (00:32:20, 18:30:04, 19:27:13). Prior window — as of 2026-10-25 00:1x: 28 jobs (25 enabled, 3 disabled), 4 non-cleanlast_status, unclosed incident rows still 2, and 2026-10-24 closed 167 / 0 — the third consecutive clean day (10-22 → 10-24); 2026-10-23 settled at 170 / 0. Zero incident rows opened or closed in-window; pins unchanged. ⚠ Off-cron fault, open: three Conduit call requests were refused by the agent on 2026-10-24 12:53–12:56, with zero tool calls → incidents/2026-10-24-conduit-call-request-refused. Prior window: As of 2026-10-24 00:2x: 28 jobs (25 enabled, 3 disabled), 4 non-cleanlast_status, and 2026-10-23 closed 169 / 0 — the third zero-failure day in four. The 2026-10-09 provider timeout storm is now fully closed:1b23c042e17dran clean on its 10-23 08:04 slot, closing the storm's last two rows, so all 12 are closed and unclosed incident rows fell 4 → 2. ⚠ New off-cron fault, fixed in-window: Conduit voice calls were being abandoned by the memory layer — the plugin hard-coded a 10 s budget for a request that includes Mnemosyne's 10–45 s cold start; three calls ran without recall. Patched to 60 s (CONDUIT_MEMORY_TIMEOUT_S) + degraded-not-aborted onTokenError; dashboard restarted 18:54:43, no abort since. Patch uncommitted → incidents/2026-10-22-conduit-memory-start-timeout, systems/conduit. The 10-22 stocktake overrun did not repeat (10-23 03:07 committed250c735). Prior window: As of 2026-10-22 00:1x: 28 jobs (25 enabled, 3 disabled), 9 non-cleanlast_status, and 2026-10-21 closed 171 / 1 — where the single failure is a failure mode this wiki had not seen.dca8482e4f76(Daily Marketing Job Radar) died at 07:40:48 after 40 m 36 s onRuntimeError: Service temporarily unavailable: all targets were skipped by pre-dispatch filters reset after 19m 20s→ incidents/2026-10-21-omniroute-pre-dispatch-filter-skip.08eb86f02d37cleared (08:30 slot clean; incident resolved 08:37:21) and 2026-10-20 settled at 169 / 0 + 1unknown. ⚠ Hermes Agent was updated to0.22.3at 22:47 → 22:57 with its pre-update snapshotskipped→ systems/hermes-agent. Prior window: 2026-10-20 closed 168 / 0 — the first zero-failure day since 10-12. Theomni-101503 fault did not recur (back tomonitoring) and 4 incident rows closed → 9 unclosed. ⚠ Two new findings: the Gitea config backup has not pushed since 2026-08-08 (75 unpushed commits) while its row readsok→ incidents/2026-08-08-gitea-config-backup-push-dead; and a gateway unclean exit on 2026-10-20 orphaned a digest run — no delivery row, no incident → incidents/2026-10-20-gateway-unclean-exit-orphaned-run. Also: the global model default moved tonousdirect (meituan/longcat-2.5-preview:free) on 2026-10-20, taking the 8 unpinned jobs off OmniRoute while 20 of 28 still pin it → systems/current-profile. Prior window: 28 cron jobs (25 enabled, 3 disabled); 12 carry a non-cleanlast_statusas of 2026-10-20 00:09 — up from 7, because theomniroute-1503 resource-pressure fault returned on 2026-10-19 (second burst in four days: 9 model calls across 8 jobs, 06:01 and 07:01 → 12:01, allmodel: smart-routeoncustom:omni-101, while/api/healthstayed200 ok) → incidents/2026-10-16-omniroute-503-resource-pressure. 2026-10-19 closed 159 / 13 against 10-18's 168 / 1. The Mosquito Tracker was removed (29 → 28 jobs), and the 2026-10-18 degenerate-stream placeholder-delivery mode remains an open question → incidents/2026-10-18-degenerate-stream-canned-substitute. Earlier: the connection-refused storm (2026-10-14 → 10-15) — 24 model-call failures across 12 jobs, ~34 h of digests blanked. All 18 model-calling jobs still sit oncustom:omni-101with no failover. - systems/skills-index — Installed skills inventory (299 skills (67 categories) as of the 2026-11-08 audit; regenerated daily by the 03:00 job). The generator excludes
.archive/(50 archived skills) — the earlier 346/347 counts included it. ⚠ 2026-11-07 07:43 — four skills moved into.archive/in one pass (cron-model-repair,fleet-wide-failure-triage,hermes-instance-update,mail-lookup), taking the count 302 → 299 and the parked archive 46 → 50; theCron Model Repaircategory went with its only member. No activeSKILL.mdreferences any of the four, so if this was a consolidation the "absorbed into X" pointer is missing. One skill appeared in the same window (microsoft-office, Productivity 25 → 26). Freshness at the 2026-11-08 run: 0 stale / 126 fresh / 3 no-date of 129 pages (freshness-20261108.txt). Note:SKILL.mdfiles on disk still exceed the index by one (300 vs 299) — the generator de-dups one nested duplicate, so 299 is the correct unique-skill figure; see systems/scheduled-tasks. ✅ 2026-11-05 — the generator divergence that made this page flip-flop is FIXED at the root: two different scripts were writing this page (the repo script → 302/68; the stale~/.hermes/scripts/wiki-maintain.shcopy → 349/26, because it usedPath.rglob()and so counted the parked archive), and the nightly audit was pointed at the stale one. The stale copy is now a delegating wrapper with no generator logic of its own → incidents/2026-11-05-skills-index-generator-divergence. ⚠ The 2026-10-22 slot ran 97 m 58 s (vs 16 m 01 s on 10-21), finishedcompletedwith deliverysuppressedand committed nothing; the 10-23 slot closed that hole.
Incidents
-
incidents/2026-11-08-pre-tool-call-hook-timeout-cascade - RESOLVED (same day) — the hook was the fault, not the schedule. The
conduit_pushplugin is the onlypre_tool_callregistrant on the host (__init__.py:119) and its callback overran Hermes's 30 s hook budget 58 times between 2026-11-07 14:14:03 and 2026-11-08 08:21:03 (errors.log: 12 lines on 11-07, 46 on 11-08) plus 89 "skipped after previous timeout or while still running" suppression lines — every tool call degraded to slow-then-suppressed. Fixed 2026-11-08 13:35 AWST:plugins.hook_callback_timeout30 -> 120 in~/.hermes/config.yaml; the last timeout line remains 08:21:03 (re-verified at audit time). ⚠ The plugin's caching was measured, not assumed, and was innocent —session_titles.py:21 CACHE_SECONDS = 30.0, timed in-process at 3.1 s cold / 0.00 s warm, so the "re-opens a 1.87 GBstate.dbper call, ~9 s each" theory was wrong; the trigger is load on the 2-core CT460 (load average 5.89,state.dbcheckpointing a 40 MB WAL). Cost: Mnemosyne Health Monitor 8 h 27 m and 5 h 59 m 51 s; FreshRSS Midday 2 h 09 m 53 s; stocktake failed a third day. Next lever isstate.dbcheckpoint/retention, not more caching. → systems/conduit, systems/hermes-agent -
incidents/2026-11-07-cron-claim-loss-in-gateway-restart-drain - OPEN. A restart requested at ~04:29:52 sat in after-turn mode for the full 1800 s, then timed out and drained at 05:00:43/47 — the same
#77184behaviour as the 10-31 reload, but this time it killed two in-flight cron executions: Mnemosyne Health Monitor (ea79a2107e36, 00:00:42.918 -> 05:02:22.870) and wiki-stocktake-maintenance (1a8e90ea2271, 03:00:31.515 -> 05:02:22.174), both closedfailedonlost its durable fire claim ownership; systemd restarted the unit at 05:01:00 (restart counter is at 3). A third failure that night was the agent-log ERROR watchdog correctly catching the event 19 s later. The request landed inside theconduit_pushself-update window (04:27:55 -> 04:32:32, its own ledger recordingrestarting_gateway= failed) — the working hypothesis for the requester, not proven; the 0.22.5 -> 0.23.0 updater is excluded (receipt starts 05:05:13). ⚠ Closed 0 -> 2 incident rows and neither alerted: both1a8e90_*rows sitdetectedwithalerted_at: null. The stocktake slot has now failed two days running (failure_streak: 2). Job Radar ran clean. → systems/scheduled-tasks, systems/hermes-agent, systems/conduit, systems/mnemosyne -
incidents/2026-11-06-job-radar-concurrent-fire-claim-discard - OPEN. A
direct-source fire of5fc292ff0f3b(08:27:09 -> 13:26:22, 4 h 59 m 13 s, delivered) settled the claim while the scheduler's own 11:30:32 slot was still running, so that slot was interrupted at 13:26:38 and closedfailedat 13:26:44 onFire claim ownership lost; stale result was discarded.- a new string variant and the first claim-loss failure with no gateway restart involved. It raised nocron_incidentsrow, so afailedexecution with no alert was the day's only red row; the discarded run left no output file. The 14:30 slot recovered the day in a normal 12 m 27 s cycle. Candidate fixes (slot suppression when a claim is live, consuming the next slot for out-of-band fires, raising an incident row on discard) are listed on the page and none was applied. -
incidents/2026-11-05-secrets-at-rest-in-mnemosyne-and-cron-prompts - OPEN. Live
.envvalues were found stored verbatim in 17 rows ofmnemosyne.db(memories4,episodic_memory3,working_memory1,gists4,memoria_facts.context_snippet1, FTS mirrors 4 - per-key counts in the page), reproduced in full by each of the 7 uncompressed rotation snapshots, and all four values also sit verbatim in the 1.89 GB session storestate.db(1,890,656,256 B, 2,901 sessions / 197,682 messages, live 40 MB WAL as at 2026-11-09), which is the likely capture origin. The Camofox key is embedded verbatim in the prompts of two enabled Facebook Birthday jobs (0e753e9720fd,fad5a86979d4) and hence incron/deliveries.db. Nothing rotated, deleted or scrubbed; no value recorded. -
incidents/2026-11-04-upstream-stream-failure-0700-cohort -
dca8482e4f76+85edf6772bcadied 36 s apart onRuntimeError: Upstream stream failed before completion.after 2 h 41 m each; Stage 2 recovered the Job Radar's day (5 roles + 1 cover letter). -
incidents/2026-11-05-skills-index-generator-divergence — RESOLVED — the skills index flip-flop had two writers. The repo
wiki-maintain.sh(302 skills / 68 categories) and the stale~/.hermes/scripts/wiki-maintain.shcopy (349 / 26, because it usedPath.rglob()and counted the parked.archive/) were different scripts, and SKILL.md pointed the 23:59 nightly audit at the stale one — so each job overwrote the other's page and the wiki oscillated nightly with no error raised by either. The stale copy is now a delegating wrapper; the repo script gained--no-buildso the wrapper honours the old interface without a second generator. -
incidents/2026-10-31-conduit-voice-local-mode-not-applying — OPEN — the app's "local" voice mode never applies, and the connection test lies. The test checks socket reachability only, while every local turn is still impossible: the Mac mini speech server's LLM proxy is disabled (LLM endpoint → HTTP 501 "Start the server with
--enable_llm_proxy"),/v1/usagereadsllm_proxy.requests: 0, and its realtime socket accepts the connection but rejectssession.updateas an unknown event.voice.modeis a phone-side selector — nomodekey exists inconfig.yaml → voiceorconduit-settings.json— so a "mode did not apply" cannot be diagnosed on host config. Found via session20261031_193709_40b9c2(19:37:09, 30 msgs / 17 tool calls);voice.local_live.front_modelwas repointed tomistral/voxtral-small-latestduring it and nothing was changed on the Mac. → systems/conduit -
incidents/2026-10-31-gateway-reload-force-drain-orphaned-run — A gateway reload waited its full 1,800 s drain cap, then force-drained and orphaned a live cron run. At 18:06:41 the gateway took the reload; the drain reported
timed_out=Trueat the cap and force-drained at 18:37:38 (new gateway 18:38:43).ea79a2107e36(Mnemosyne Health Monitor, 12:01:06 slot, 6 h 38 m 09 s in) closedfailedat 18:39:15 on "lost its durable fire claim ownership". Same class as incidents/2026-10-26-planned-restart-orphaned-cron-run — second instance, and the first on a plain reload. A second, clean restart followed at 19:23:39 → 19:24:40; 2026-10-31 closed 160 / 4. → systems/scheduled-tasks, systems/hermes-agent -
incidents/2026-10-31-asana-access-failures — Both Asana paths on CT460 are non-functional. The MCP server
asana(https://mcp.asana.com/v2/mcp,auth: oauth,enabled: true) has never authenticated —~/.hermes/mcp-tokens/holds onlyasana.client.json(319 B, mtime 2026-10-26 01:07) and the logs carry "MCP OAuth setup failed for 'asana': … non-interactive environment and no cached tokens found. Runhermes mcp login asanainteractively first"; the hosted connector also rejects the call shape. The fix needs an interactivehermes mcp login asana, which a cron context cannot perform. → systems/hermes-agent -
incidents/2026-10-30-ct460-host-outage-scheduler-gap — RESOLVED (root cause not established). CT460 went dark for 5 h 30 m on 2026-10-30: the PVE host
pverebooted (boot 16:24:00), CT460 returned 16:28:00, the previous gateway life (pid=3913841) was logged as exited UNCLEANLY at 16:35:50 ("no exit path ran — SIGKILL / OOM / VM death"), and the scheduler resumed at 16:37:21 with 8 catch-up runs. Zero execution rows exist between 10:58:20 and 16:37:21; the day still closed 138 / 0 against 10-29's 177 / 0 (≈39 slots lost, no failures). No monitor alerted — the two jobs that could have (cbfe434a3b5e,1a8e90ea2271) are disabled. -
incidents/2026-10-30-mnemosyne-health-monitor-paused — RESOLVED 2026-10-30T10:02:48 (its 00:01:08 slot was still running, not dead: it closed
completedafter 10 h 01 m 40 s and delivered, auto-closingea79a2_d93c3acdc4f2;ea79a2107e36is enabled again withlast_status: ok/ streak 0). The Mnemosyne Health Monitor cron job was auto-paused overnight and its failure notice never reached Telegram — the only trace is the incident row.ea79a2107e36's 2026-10-30 00:01:08 slot closedunknownat 01:04:22 on "Cron execution unverified; reconcile~/.hermes/cron/admissions/ad897cbc9f…json: Gateway connection failed; no local fallback", opening incidentea79a2_d93c3acdc4f2(failure_type: unknown,detected) — and the scheduler paused the job at that moment. Fleet is now 29 jobs (25 enabled / 4 disabled); livelast_status: error,failure_streak: 1. ⚠ Two traps in one fault: the failure notice itself failed to send (send_path_degraded; live adapter delivery to telegram:-1004321904721:102 failed—deliveries.dbhas zero rows for 2026-10-30), and the run closedunknownrather thanfailed. The job was not re-enabled and the gateway was not restarted by the stocktake — root cause is unverified. → systems/scheduled-tasks, systems/mnemosyne -
incidents/2026-10-29-conduit-voice-silence — Every Conduit voice call connected and then died silently; three faults sat in series, and the first two real calls in the product's history were placed on 2026-10-29 after all three were fixed. (A)
voice.speech_server.urlwas the truncatedwss://…:8443/v1/— the plugin dials it verbatim and the bare path answers 403, reported as "the speech server refused the key." (B)dashboard.basic_auth.session_ttl_secondswas the 12 h default, so an expired phone session gets WS 4401 with no Hermes turn and no error on the device (the phone re-authenticated at 08:00:59, minutes after a silent call). (C) Both host providers were dead —tts.provider: openai→ Mac/v1/speech502,stt.provider: groq→ 403/Cloudflare 1010 (blocked, not mis-keyed). Fixed 08:02–08:4x: URL →…/v1/realtime, TTL → 2 592 000 s (30 d),stt.provider: local(faster-whisperbase),tts.provider: ollama_local; dashboard restarted 08:03:26. Verified by driving the whole call path for real, then by calls at 08:38:04 and 08:49:36. ⚠ Two TTL keys exist —dashboard.basic_auth.session_ttl_seconds(raised) vsdashboard.session_ttl_seconds(still 43 200).status: resolved. -
incidents/2026-10-28-job-radar-stage1-iteration-cap — The radar's two-stage split ran for real on 2026-10-28 and landed nothing: stage 1 stopped at the agent iteration cap before writing its handoff, so both stage-2 slots correctly no-oped (silent). Two consecutive stage-1 failures, two different ceilings (tool-call budget 10-27, iteration cap 10-28); no Notion writes for a second day. RESOLVED 2026-10-29 — the next stage-1 run (
dca8482e4f76, 07:00:59 → 10:16:12, 3 h 15 m 13 s) closedcompletedand wrotehandoff/2026-10-29.json, which stage 2 consumed at 10:40:59 and delivered as 20 pages + 2 cover letters (missing_cover_letter_count 0).status: resolved, review 2026-11-13. -
incidents/2026-10-27-job-radar-budget-exhausted — The Daily Marketing Job Radar exhausted its tool-call budget for the second day running — and this time the run is recorded as
failed, notcompleted. On 2026-10-27 the 07:00 slot ran 07:01:08 → 11:03:54 (4 h 2 m 46 s) and its delivered report opens "INCOMPLETE (tool-call budget exhausted before Notion write stage)": discovery/verify/dedup/classify finished, Notion writes, cover letters and the final audit never ran (Notion DB held 451 entries, 0 added for the day). Incident rowdca848_e93a538ade6bopened 11:03:53 (alerted11:03:59,failure_type: auth— wrong for a budget fault) and was still open at the 2026-10-28 audit. Response the same day: the radar was split into stage 1dca8482e4f76(Discovery, 07:00,deliver: local) and new stage 25fc292ff0f3b(Write and Letters, 11:30/14:30, topic 1030), created 17:34:15, twocompletedtest fires that evening → runbooks/job-radar. RESOLVED 2026-10-29: both of this incident's ledger rows (dca848_e93a538ade6b,dca848_0a2f03b5952b) closedresolvedat 10:16:12 on the first successful post-split run —dca8482e4f76restored delivery tolocal, wrote the handoff inside budget, and no cover letter went missing (missing_cover_letter_count 0).status: resolved, review 2026-11-13. -
incidents/2026-10-26-planned-restart-orphaned-cron-run — A planned gateway restart orphaned a live cron run — the second instance of the orphan class, and the first that alerted. On 2026-10-26 at 14:33:35 AWST the gateway took a planned
SIGTERM(under_systemd=yes); the shutdown drain reportedtimed_out=Trueafter just 1.35 s of its 30 s budget and interruptedea79a2107e36(Mnemosyne Health Monitor, 12:01 slot) 2 h 34 m in. It closedfailedon a new string —lost its durable fire claim ownership— raised twocron_incidentsrows (14:33:37 unverified / reconcile admission + 14:35:59 fire claim), delivered the failure at 14:35:59, and left the job onfailure_streak: 2from one interrupted fire. Two Mnemosyne Watchdog reds followed at 14:46 and 15:01 and self-resolved at 15:16:12. Net = 169 / 3 for 10-26. Unresolved: why a planned stop bypasses the drain deadline, and whetherfailure_streakshould count the unverified row. → also updates incidents/2026-10-20-gateway-unclean-exit-orphaned-run (the class now recurs without a crash). -
incidents/2026-10-25-gmail-digest-runaway-and-refire — The Gmail Action Digest ran 1 h 55 m and fired six times on 2026-10-25. The 08:30 slot started 08:31:14 and closed 10:26:37
failedonRuntimeError: Operation interrupted: waiting for model response (347.2s elapsed)— against 91 s (10-23) and 104 s (10-24). The same job then fired five more times (17:19:36, 18:40:06, 19:18:41, 19:30:31, 19:38:53); the 19:18:41 fire died on a new signature —Cron admission missing: the owner never admitted this fire(distinct from the 10-20 orphan) — and all six fires, failures included, carrydelivery_outcome: delivered, so up to six digests reached Anthony. Neither failure raised acron_incidentsrow; the job now readslast_status: delivery_queuedwith an emptylast_error. Hypothesis (unconfirmed): the 08:31 fire adopted an unrelated long-lived session — its worker made 70terminalcalls on VM101/dev/sdbbackup work with context growing 66 k → 148 k tokens, while context compression was unavailable all day (invalid_grant). → systems/scheduled-tasks, incidents/2026-10-22-nous-portal-refresh-token-invalid -
incidents/2026-10-22-nous-portal-refresh-token-invalid —
Invalid refresh token— Nous Portal runtime credentials are dead, so context summarisation failed. Gateway-log counts: 1 line 2026-10-22, 3 on 10-24, 20 on 10-25 (last 14:53:04,agent.context_compressor: Failed to generate context summary), 0 since the 19:27:13 restart. ⚠ Masked, not fixed: at 2026-10-25 19:13 all eightauxiliary:slots (approval, compression, curator, mcp, profile_describer, skills_hub, title_generation, vision) moved offnoustono-think/freeapi/autooncustom:omni-101(fallbackno-think/freeapi/deepseek-v4-flash→no-think/kg/kilo-auto/free,free_only: true; compression timeout 90 s, vision 180 s). Nohermes modelre-authentication has been run andnousis still the first entry infallback_providers, so failover tries a dead credential. → systems/model-providers, systems/current-profile -
incidents/2026-10-24-conduit-call-request-refused — The agent refused to phone Anthony, three times, on 2026-10-24 (12:53–12:56). He asked to be called to test Conduit calls (
Call me now to test calls.→Yes. You do→CAL ME); all three replies asserted the agent has no calling capability, with zero tool calls in the session.conduit_call_user(toolsetconduit) exists, is registered for every session, is reachable viatool_search, and the plugin ships thecalling-the-userskill; his call settings (enabled/when_asked/decides) were permissive and the device was paired. Root cause: capability asserted instead of discovered — the first reply came fromkilo-auto/free, but the switch tosmart-routerepeated it. Same audit also corrects the 10-22 incident's closing evidence:conduit-calls.json → endsrecords turn-ends that fire a watch, not calls, so “two calls closed cleanly 00:03:23 / 00:06:57” were the two Mnemosyne cron sessions —history(real calls) is empty and no call has been placed since (superseded 2026-10-29 — two real calls are now on record: 08:38:04 / 08:49:36 → incidents/2026-10-29-conduit-voice-silence) the memory fix. → systems/conduit, incidents/2026-10-22-conduit-memory-start-timeout -
incidents/2026-10-22-conduit-memory-start-timeout — Conduit voice calls were silently running without memory, 2026-10-22 → 10-23. The phone plugin gave one request — including the Mnemosyne provider start — a hard-coded 10 s budget (
MEMORY_TIMEOUT_S), while Mnemosyne's cold start for aconduit-voicesession runs 10–45 s. Three calls were abandoned at the memory layer (Memory provider 'mnemosyne' start for Conduit timed out; abandoning the call: 10-22 11:28:17, 10-22 13:16:37, 10-23 18:29:16) and answered with no recall of prior conversation. Fixed 10-23 in the plugin's working tree: default 60 s (CONDUIT_MEMORY_TIMEOUT_Soverride) plus aTokenErrorguard that logs and proceeds without recall instead of aborting; dashboard restarted 18:54:43 and no abort line exists after it. ⚠ Corrected 2026-10-25: the “two calls closed cleanly 00:03:23 / 00:06:57 on 10-24” was a false positive — those were the two Mnemosyne cron turn-ends of that night, andconduit-calls.json → history(real calls) is empty, so the fix has no positive call evidence and no call has been placed since (superseded 2026-10-29 — two real calls are now on record: 08:38:04 / 08:49:36 → incidents/2026-10-29-conduit-voice-silence). The patch is uncommitted — a plugin update reverts it. The cold start itself was not optimised. → systems/conduit, systems/mnemosyne -
incidents/2026-10-21-omniroute-pre-dispatch-filter-skip — A third failure signature from the
custom:omni-101/smart-routepin, 2026-10-21. The Daily Marketing Job Radar (dca8482e4f76, 07:00 weekday) died at 07:40:48 after 40 m 36 s onRuntimeError: Service temporarily unavailable: all targets were skipped by pre-dispatch filters reset after 19m 20s— no 503, no connection error, no repetition loop, and zero 503 rows exist for that day (last 2026-10-19 09:02). Its 07:00 sibling85edf6772bcacompleted normally, so the node was serving; the run wrote no output (cron_incomplete_no_output, 82 msgs / 47 tool calls). Incidentdca848_014affeb6954was closed 2026-10-22 07:59:22 when the next daily slot ran clean. Not caused by the 22:47hermes update— that landed 15 h later. → systems/omniroute -
incidents/2026-10-20-gateway-unclean-exit-orphaned-run — The gateway exited uncleanly on 2026-10-20 (09:09:01,
suspected_oom=False) and orphaned a live cron run.08eb86f02d37(Gmail Action Digest, 08:30 slot) was claimed 08:31:03 and closedunknown— “Scheduler restarted after this execution's owner exited before a durable terminal state; whether side effects ran is unknown.” No delivery row exists for the slot and no incident row was created; the job table keeps showing the previous slot's 503. 20 unclean exits since 2026-08-01 (5 clustered on 2026-08-14/15); this one ended a 27-day clean run. Open: orphan-recovery on restart, and treating a delivery-targetedunknownas a probable non-delivery. -
incidents/2026-11-02-job-radar-stage1-iteration-cap-recurrence — Third iteration-cap in seven days, and the first that raised no incident at all. Job Radar Stage 1 (
dca8482e4f76) ran 07:00:33 → 16:01:52 = 9 h 01 m 19 s on 2026-11-02, hit the agent iteration cap before the handoff was written, and closedstatus: completed/error: NULL/delivery_outcome: suppressed. Both Stage 2 slots declined correctly (92665337…11:30 and the05a3f00b…14:30 safety net both exited[SILENT]), so nothing reached Notion, no cover letters were generated, and the day's 164 deduped candidates were never persisted — a state astatus-only health check reports as green. Contrast 10-27 (dca848_e93a538ade6b) and 10-28 (dca848_0a2f03b5952b), where the identical cap did open rows whoseerrortext is the run's own INCOMPLETE report: on 11-02 the ledger lost the red row it used to produce. Discovery itself worked — SEEK 51, LinkedIn 60 IDs, Indeed live, WA Government 35 (197 raw / 164 new after three-level dedup) — and a URL-canonicalisation bug was found and fixed mid-run (au.seek.comvsau.seek.com.auhad been dropping SEEK and Indeed entries from the consolidated list). → systems/scheduled-tasks -
incidents/2026-11-01-weekly-review-lost-to-gateway-handoff-failure — The Sunday 18:00 Weekly Review did not run on 2026-11-01 and nothing was delivered: its execution closed
unknownat 18:05:13 with "Cron execution unverified … Gateway connection failed; no local fallback", its incident row is stillalerted, the job sits aterror/failure_streak: 1, anddeliveries.dbshows no row after 11:01:12 for the rest of the day. Its batch-mateb63ed5817212took the identical error and self-healed in 68 s. Same page records the inverse silent failure:ecc1fc13655areadserrorwithlast_run 11-01T12:01:00while owning no execution row and no incident row at all. ✅ RESOLVED 2026-11-02T01:27:21 — the review was never lost. The same execution row (be6ec11a8e68428084af9ab18fb148db) closedcompleted/deliveredat 01:27:22 after 7 h 26 m 43 s, the delivery lands at 01:27:21.802246 and incident79f9bb_9c443b602eecauto-closed at 01:27:21.606691 — so the 18:05:13unknownwas a reconciler timing artefact on a still-running job, not a verdict (page nowresolved). Batch-mateb63ed5closed in 68 s and79f9bbin 7 h 26 m, bothcompleted; anunknownrow on a long job is a timing artefact, not a failure.ecc1fc13655a's ghosterrorcleared too (12:00:33 →completed/delivered12:29:26), taking non-cleanlast_status2 → 1. -
incidents/2026-11-01-cron-worker-sigterm-orphaned-claims — Three restart-safe cron workers killed by
SIGTERM(-15) after adopting their claim, so the scheduler recorded "whether side effects ran is unknown":85edf6772bca@07:30:46,96eb95ce12f2+0e753e9720fd@09:02:18. A fourth variant of the orphan class — and the first with no gateway restart, reload or drain anywhere in the window (PID175269up since 10-31 19:24:40; relay counter monotonic through both signals), so it cannot be attributed to reload behaviour. Likely trigger: a 30 s worker-ack window smaller than this host's cold start (83 plugins / 69 enabled discovered in 70 s). All three rows nowresolved; one execution leftunknown. -
incidents/2026-11-03-job-radar-stream-active-timeout — The Stage-1 slot lost a second consecutive day — and this time the harness killed the turn, so the ledger went red.
dca8482e4f76ran 07:00:33.819190 → 13:28:52.305995 = 6 h 28 m 18 s on 2026-11-03 and closedfailed/RuntimeError: stream active timeout, with the failure notice delivered (13:28:51.741724) and incidentdca848_dfd4bea84f2a(failure_type: timeout,alerted, open) — unclosed rows 0 → 1. The run's activity stops at 12:23:28; the harness does not declare the turn dead until 13:28:49 — a 65 m 21 s silence with no tool call, no model turn and nothing in the ledger, and no "maximum number of tool-calling iterations" message anywhere (this is a provider-stream timeout, not the cap that ended 10-27 / 10-28 / 11-02). It compacted five times (08:04:35, 08:47:19, 09:31:50, 10:49:26, 11:39:21) in 363 messages. Both Stage 2 slots declined correctly (5fc292ff0f3b11:30:36 → 11:32:16; 14:30:32 → 14:33:11) because no handoff was written, andradar-ref/handoff/still holds only 10-27 / 10-29 / 10-30 — so 11-02's 164 deduped candidates and 11-03's discovery are both unrecovered. Pulse carried it to Anthony in the desktop session. Answers the 11-02 page's open question 3: suppression tracks the terminal state —completed→ nothing delivered,failed→ notice delivered. → incidents/2026-11-02-job-radar-stage1-iteration-cap-recurrence, systems/scheduled-tasks -
incidents/2026-08-08-gitea-config-backup-push-dead — Green row, dead job, 2.5 months: the daily Hermes Config Backup to Gitea has not pushed since 2026-08-07 11:00:47.
e27da6c34bbbreadslast_status: okand its executions readcompletedevery night while 75 commits sit unpushed (fatal: could not read Username for 'https://gitea.kangaroo-eel.ts.net'— HTTPS remote, no credential, no helper). Telegram failure notices have fired daily (message_id 8447, 2026-10-20 11:00); AgentMail failed. No off-box~/.hermesbackup in 2.5 months. Second instance of the pattern after the GitHub Trending Radar token revocation. → infrastructure/backups -
incidents/2026-10-18-degenerate-stream-canned-substitute — The repetition-loop failure mode, 2026-10-18: the FreshRSS Midday run (
ecc1fc13655a) wrote "Your request was not processed…", delivered it to topic:346at 12:08:11, then died at 12:08:25 onRuntimeError: Model output entered a repetition loop and the stream was cut mid-loop. A delivered message is not evidence of delivered content — open question: should the guard suppress delivery / re-queue instead of substituting text on the job's normal route? Second surface (2026-10-20 18:37): an interactivedesktopsession received the same canned line afterRebuilt-message restart limit (3) exceeded→reason=rebuilt_restart_limit_exceeded … response_len=0, so the substitute is emitted by the harness's failure path generally, not only by the repetition-loop guard. The user's question in that session — Nous OAuth dashboard auth plus a gateway token — was never answered. -
incidents/2026-10-16-omniroute-503-resource-pressure —
omniroute-1load-sheds model calls withHTTP 503 … resource pressure— two bursts: 2026-10-16 → 10-17, and again 2026-10-19. Burst 1: 9 model calls across 7 jobs over ~19 h, self-cleared (reported then as10-17 = 162 / 5; the DB reads 163 / 5 — corrected 2026-10-20). Burst 2, 44 h later with an identical signature and blast radius: 9 model calls across 8 jobs on 2026-10-19 (06:01 + 07:01 → 12:01, whole day 159 / 13)./api/healthread200 okthroughout both. Status:active→ back tomonitoringon 2026-10-21 — 2026-10-20 ran 168 / 0 with zero rows carrying the resource-pressure string, so the second burst is over; it stays a standing risk until the single-node topology changes. 4 rows closed on 10-20 (dca848_867d9caa96a8,85edf6_256c5e150bc4,ecc1fc_c9976ea24553,ecc1fc_21a72aa11cc4); unclosed rows 13 → 9 (8alerted/ 1detected); the ledger still tags every 503 rowfailure_type: unknown, so triage on error text. Single-node topology still open — and every job that failed readsmodel: smart-route,provider: custom:omni-101. -
incidents/2026-10-14-omniroute-node-connection-refused-storm — Fleet-wide 34-hour cron blackout, 2026-10-14 → 10-15:
omniroute-1(100.78.63.20:20128, providercustom:omni-101) refused TCP connections, so every model-calling cron job failed on every slot — 24 genuine model-call failures across 12 jobs (+12 derivative watchdog reds), and all digests for ~34 h were silently suppressed. All 18 enabled model-calling jobs ride this one node with no failover. Recovered 10-15 22:01 (resolved) -
incidents/2026-10-09-cron-provider-timeout-storm — Fleet-wide provider timeout storm: 15 failed executions across 10 jobs on 2026-10-09, all
RuntimeError: Request timed out.on the aliases behindcustom:omni-101, 00:00 → 15:00 AWST. CLOSED — all 12 incident rows are now resolved; the last two (1b23c0_c35703f637b8,1b23c0_103cbe04a79b, both on the weekly Friday job1b23c042e17d) closed 2026-10-23 08:04 when that slot ran clean, and the job readsokagain -
incidents/2026-10-09-memory-recall-relevance — Recall relevance: a stale conversational episode outranked current-state facts on an open question. ✅ RESOLVED 2026-11-01 — the ranking weights were persisted, in
~/.hermes/mnemosyne/config.yamlrather than the file the 2026-10-10 probe read; the original regression query now returns only current-state facts, and conflict152was auto-resolved on 2026-10-29 -
incidents/2026-10-05-dead-model-pin-repin — Seven cron jobs on dead model pins (
cliprox/terra,qwen3.5:397b,deepseek-v4-flash,gpt-5.6-terra) repinned to routing aliases oncustom:omni-101; failing set 7 → 0 (resolved 2026-10-05) -
incidents/2026-10-03-mnemosyne-vector-recall-fts-only — Mnemosyne recall had been scoring keyword-only (fastembed missing from the managed runtimes); repaired 2026-10-03, coverage re-verified at 96.5% working / 99.4% episodic
-
incidents/2026-10-03-ct450-hermes-update — Chaos instance CT450 updated v0.19.0 → v0.21.5 (resolved); access path and pre-flight checks documented
-
incidents/2026-10-01-cliproxy-connection-auth-expired — OmniRoute
cliprox/terraconnection credential expired (all 3 jobs on the pin failed, settled 2026-10-04); closed 2026-10-05 when all three were repinned off the pin -
incidents/2026-08-26-work-outlook-basic-auth-disabled — Work Outlook mailbox unreachable: tenant allows only
XOAuth2, himalaya configured for password (open since 2026-08-26) -
incidents/2026-09-28-hermes-managed-runtime-deps — Managed-runtime venvs missing
dotenv/mnemosynebroke every cron worker (resolved 2026-09-30); dependency guard now runs every 15 min. Recurred 2026-10-10 inside the gateway runtime env —mnemosyneandelevenlabsmissing from the committed uv env the gateway loads; both repaired and verified the same evening -
incidents/2026-08-18-mnemosyne-capture-pipeline — Mnemosyne capture pipeline broken (Aug 2026, superseded): capture verified healthy 2026-10-12 — 786 working rows, +2 that day, 98.3 % embedded
-
incidents/2026-08-15-skills-index-drift — Skills index 4x undercount (66 vs 330 installed); fixed via auto-regeneration
Monitoring & Dashboards
- systems/homepage-dashboard — Homepage dashboard (CT201)
- systems/home-assistant — Home Assistant integration
Reports
- reports/uber-eats/index — Uber Eats monthly spend reports
- reports/communities-wa-social-media-audit-2026 — Department of Communities WA social media audit and first-day brief
- systems/obsidian — Obsidian vault structure and conventions
- queries/retained-research-answers — Retained research answers (fastest VNC clients, 2026-10-11)
Infrastructure
Services
- infrastructure/hosts — Hosts, containers, important paths
- infrastructure/docker-services — Docker compose files
- infrastructure/credentials-map — Where credentials live (no values)
- infrastructure/network-map — Zones, hosts, and ports across LAN, Tailscale, and the public tunnel
- infrastructure/domains-and-tunnels — martinwa.org hostnames and Cloudflare Tunnel routing
- infrastructure/backups — hermes backup CLI, retention, and gaps
Networking
- infrastructure/proxmox — PVE hosts (two:
pve9.2.10 +m93p9.2.10, unclustered, IDs collide), VMs, LXC containers, storage (/mnt/ssd078.29 % / ~152 GiB free, 2026-11-07) - infrastructure/tailscale — Tailscale serve routes (CT460 verified exactly) and the 52-node tailnet inventory (re-verified 2026-11-07:
octopback online; 9 offline ages refreshed; CT107mem0added to the m93p guest list) - systems/cloudflare-tunnel — ct207-hosted tunnel serving Hermes publicly
Concepts
- concepts/agent-memory — Memory model
- concepts/model-routing — Routing concepts
- concepts/persistent-shells — Terminal persistence
- concepts/browser-automation — Browser automation concepts
- concepts/tool-calling — Tool calling patterns
Decisions
- decisions/index — Decision index
- decisions/keep-openrouter-as-fallback — Keep OpenRouter as fallback provider
- decisions/persistent-shell-enabled — Enable shell persistence
Comparisons
- comparisons/camoufox-vs-chrome — Camoufox vs Chrome
- comparisons/hermes-vs-nanobot — Hermes vs Nanobot
- comparisons/memory-backends — Memory backend comparison
- comparisons/model-routers — Model router comparison
Runbooks
- runbooks/multiplexer-setup — Multi-profile gateway multiplexer setup
- runbooks/diagnose-docker — Docker diagnosis
- runbooks/recover-docker-service — Docker service recovery
- runbooks/restart-hermes — Hermes restart procedure
- runbooks/restart-browser — Browser restart procedure
- runbooks/update-hermes-safely — Safe Hermes update
- runbooks/restore-openrouter — OpenRouter restoration
- runbooks/provider-health — Provider health check
- runbooks/troubleshoot-tool-loop — Tool loop troubleshooting
- runbooks/gateway-resource-resilience — Gateway resilience
- runbooks/job-radar — Job Radar search, Notion, dashboard and recovery procedure (two-stage since 2026-10-27:
dca8482e4f76discovery →5fc292ff0f3bwrite and letters)
Raw
- raw/configs/hermes-config-sanitized.txt — Sanitized config