Root cause of the long-standing cloud_provider: steel residue: the 2026-07-30 rollback disabled the browser-steel plugin and set browser.engine: camofox but left browser.cloud_provider: steel in config.yaml. The split config was inert-but-wrong, so it survived ~3 months of audits unnoticed. Corrects pages that still described Steel as present, running or configured: - systems/browser-backend.md (incl. gateway-restart env-var note) - comparisons/steel-vs-camoufox.md, comparisons/camoufox-vs-chrome.md - decisions/rollback-steel-to-camofox.md, decisions/index.md - infrastructure/docker-services.md, infrastructure/tailscale.md, infrastructure/hosts.md - systems/homepage-dashboard.md, systems/scheduled-tasks.md - concepts/browser-automation.md, runbooks/recover-docker-service.md - current-state.md, index.md, agents/nanobot.md - log.md (dated entry; supersedes the 00:3x audit's 'endpoint dark' wording) Also restores the Ignis compose row in infrastructure/docker-services.md, which the 2026-10-11 revision dropped (verified: /home/hermes/docker/ignis/docker-compose.yml exists and the ignis container is Up on CT460). Co-Authored-By: Hermes <hermes@local>
97 KiB
title, type, status, created, updated, verified_on, review_after, confidence, tags, sources
| title | type | status | created | updated | verified_on | review_after | confidence | tags | sources | |||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Current State | concept | active | 2026-07-22 | 2026-10-29 | 2026-10-29 | 2026-11-03 | high |
|
|
Current State
Updated: 2026-10-29
Recent Changes (2026-10-28, nightly audit; live probes 2026-10-28 00:2x AWST)
- The radar's silent budget overrun became a recorded failure — and the radar is now two jobs. Window
2026-10-27 settled 172
completed/ 1failed. The failure isdca8482e4f76(Daily Marketing Job Radar - Discovery): 07:01:08 → 11:03:54 (4 h 2 m 46 s), closedfailed, deliverydelivered, and the delivered report opens "INCOMPLETE (tool-call budget exhausted before Notion write stage)" — discovery, verification, dedup and classification completed; Notion ingestion, cover-letter generation and the final cover-letter audit did not execute. The prior day (10-26) had the same overrun but closedcompleted, hiding it in a green row. Incident rowdca848_e93a538ade6bopened 11:03:53,alerted11:03:59, still open at this audit (failure_type: auth— misclassified). → new page incidents/2026-10-27-job-radar-budget-exhausted - Response: the radar was split into a two-stage pipeline the same day. Stage 1
dca8482e4f76— Discovery (0 7 * * 1-5,deliver: local, failures → topic 1030) writes a handoff and triggers stage 2; new stage 25fc292ff0f3b— Daily Marketing Job Radar - Write and Letters (30 11,14 * * 1-5, Telegram topic 1030, created 2026-10-27T17:34:15) lands the Notion entries, cover letters and audit. Two test fires of stage 2 on 10-27 (17:35:00 → 17:36:52, 17:38:38 → 17:43:42) bothcompletedwith deliverysuppressed; the first real 07:00 → 11:30 cycle had not yet run. Fleet 28 → 29 jobs (26 / 3). → runbooks/job-radar - The 2026-10-26 orphan class did not recur, and its two incident rows closed.
ea79a2_a4661554a3c2andea79a2_c3ab2d784ba3auto-closed 00:38:32 (unclosed rows 3 → 2, the 2 being the Facebook birthday monthly scrape from 10-01 and the new radar row). No 10-27 run besides the radar's failed, so the watchdog and every other job were clean all day. - Non-clean
last_status4 → 5 (churn):ea79a2107e36cleared took;dca8482e4f76joined aserror(streak 1) and08eb86f02d37re-joined asdelivery_queued. Still non-clean:0e753e9720fd(error),fad5a86979d4(delivery_failed),066bb5191280(delivery_failed). Pins unchanged. - Also updated:
incidents/2026-10-27-job-radar-budget-exhausted.md(new),incidents/2026-10-26-planned-restart-orphaned-cron-run.md(recurrence check),runbooks/job-radar.md,systems/scheduled-tasks.md,systems/hermes-agent.md(TTS provider correction),systems/conduit.md(voice pipeline),infrastructure/tailscale.md(peer table re-verified),systems/skills-index.md(regenerated 10-27, committed),index.md,log.md. Nothing removed or archived. No secrets written.
Recent Changes (2026-10-28, nightly audit; live probes 2026-10-28 22:00 – 2026-10-29 00:3x AWST)
The radar's two-stage split ran for real, and landed nothing — stage 1 hit the agent iteration cap
dca8482e4f76 (stage 1, Discovery) ran 07:00:32 → 10:33:18 (3 h 32 m 46 s) and closed failed on
"hit the agent iteration cap before the handoff could be written" — failure_streak: 2. Stage 1 never
produced a handoff (~/.hermes/radar-ref/handoff/ holds only 2026-10-27.json), so the first real two-stage
cycle delivered no Notion writes and no cover letters — the same outcome as 10-27, by a different route.
Both stage-2 slots then did exactly what they were built to do: 5fc292ff0f3b fired 11:30:27 → 11:31:31 and
14:30:27 → 14:31:43, both completed with delivery_outcome: suppressed — a stage-2 run with no
handoff is a silent no-op, not a failure (the recovery rule in runbooks/job-radar), now proven in
production. The two post-split failures also stopped at different ceilings: 10-27 at the tool-call budget
(4 h 2 m, writes not started), 10-28 at the iteration cap (3 h 32 m, handoff not written) — less of the
pipeline completed despite the shorter wall clock. Open radar incident rows: dca848_e93a538ade6b (10-27) and
dca848_0a2f03b5952b (10-28), both open. Detail:
incidents/2026-10-28-job-radar-stage1-iteration-cap.
The 03:00 stocktake failed on a provider 400 — and its incident row never alerted
1a8e90ea2271 ran 03:00:28 → 03:37:58 (37 m 30 s) and closed failed (streak 1, delivery
suppressed) with RuntimeError: [400] Failed to deserialize the JSON body into the target type: duplicate field 'reasoning_content' at line 1 column 512203 against custom:omni-101 / free-stack — the response the
provider was asked to deserialize carried a duplicated reasoning_content field. It performed its rebuild
(302 skills → systems/skills-index.md mtime 03:01:40; freshness report raw/stocktake/freshness-20261028.txt
→ 2 stale / 103 fresh / 4 no-date of 109 pages) and then died before the commit, leaving the wiki tree
dirty for the rest of the day. Its incident row 1a8e90_f57ab4cafab8 sits in state detected with no
alert — the only outward sign was the job's own error status. The 2026-10-29 audit committed the two
artefacts.
Steel left the stack: fully removed — Camofox is the sole backend
browser.cloud_provider and browser.camera_provider are back to camofox (engine: auto, cdp_url: "")
in config.yaml (mtime 2026-10-29 00:15:13), with backups taken at every step
(config.yaml.bak-pre-cloudprovider-fix-20261028T220057Z 22:00:57, and
config.yaml.bak-pre-steel-plugin-removal-20261028T161324Z written 00:13:24). The browser-steel plugin was
removed from ~/.hermes/plugins/, and no browser-steel key remains in plugins.disabled or
plugins.entries, so the plugin_steel toolset is no longer selectable. Steel is now fully REMOVED, not
merely down: on CT201 the containers steel-browser-api-1 / steel-browser-ui-1, the steel-network
Docker network, the images (steel-browser-api:fixed and both ghcr.io Steel images) and the project dir
/root/steel-browser were deleted (~6 GB reclaimed; disk 70G used → 64G used), and the Tailscale Serve routes
/steel and /steel-api were removed — CT201's remaining routes are only / → 127.0.0.1:8085 and /mgr →
127.0.0.1:8084 on both :443 and :8443, with nothing listening on 3000, 5173 or 9223. CT333's second,
separate Steel copy (steel-browser, ghcr.io/steel-dev/steel-browser:latest, 5.53 GB, created 2026-05-30)
was removed with its image. Hermes core contains zero Steel references, so there is no Steel fallback path
in the tree — returning to Steel means redeploying it (the compose file and Dockerfile are archived on CT201
under /root/_archived-steel/; the images remain re-pullable from ghcr.io). ⚠ STEEL_BASE_URL is no longer in
~/.hermes/.env — it survived only in the inherited environment of processes already running at the cleanup,
and the gateway was restarted on 2026-10-29 01:21 AWST to clear it (a couple of older, unrelated services
still carry it) — no core Hermes code reads it, so it is a runtime-only leftover, not a config value.
Camofox is the sole
backend and healthy: REST http://100.118.5.51:9377 (and http://localhost:9377), /health → 200,
/tabs → {"running":true,"tabs":[]}. Detail: systems/browser-backend,
decisions/rollback-steel-to-camofox, comparisons/steel-vs-camoufox.
⚠ Superseded: an earlier 2026-10-29 00:3x probe described Steel only as "not reachable — endpoint dark, still running on CT201". That was already out of date — Steel is removed, not down.
Fleet and tallies
29 jobs (26 enabled / 3 disabled) — unchanged. Non-clean last_status: 5 (0e753e9720fd error,
fad5a86979d4 delivery_failed, dca8482e4f76 error streak 2, 066bb5191280 delivery_failed,
1a8e90ea2271 error streak 1). Pins: 12 smart-route / 6 free-stack / 7 unpinned /
1 deepseek-paid-smart. 2026-10-28 settled 168 completed / 2 failed / 1 running; 2026-10-29 so far
6 completed / 1 running; 2026-10-27 settled 173 / 1 (revised up by one late run after the 2026-10-28
audit). No Hindsight service is running on this box (:8888 closed, no hindsight units) — the standing
memory-backend correction still holds and needs no change.
Recent Changes (2026-10-27, nightly audit; live probes 2026-10-27 00:1x–00:5x AWST)
- A planned gateway restart still orphaned a live cron run — and this time it alerted loudly. A planned
SIGTERMat 2026-10-26 14:33:35 produced a shutdown drain that 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— against the 2026-10-20 orphan's silentunknown, and raised twocron_incidentsrows (14:33:37 unverified / reconcile admission, 14:35:59 fire claim) that are stillalerted; the failure was delivered at 14:35:59. Two Mnemosyne Watchdog reds followed and self-resolved at 15:16:12. Window 2026-10-26 settled 169 / 3 and all three failures are this one fault — so the fleet's failure count is one interruption, not a systemic turn. Fleet unchanged at 28 jobs (25 enabled / 3 disabled); non-cleanlast_status5 → 4; unclosed incident rows 2 → 3; pins unchanged. → new page incidents/2026-10-26-planned-restart-orphaned-cron-run - One incident row closed, and the 2026-10-16 503 burst is fully shut.
c0a9fa_764558b5ae83(GitHub Trending Radar) auto-closed 09:13:00 when its 09:00 slot ran clean — the last open row of the resource-pressure fault → incidents/2026-10-16-omniroute-503-resource-pressure. No execution row carries the 503 string on 10-25 or 10-26. The job staysmonitoring: single-node exposure unchanged. - Two quiet degradations worth naming.
fad5a86979d4's 03:08 slot completed but delivereddelivery_failed— Thread 34795 not found (the gateway's own shutdown notice hit the same dead thread at 14:33:37); and the radar's 07:00 slot closedcompletedat 09:10 while delivering “RUN INCOMPLETE — tool-call budget exhausted” — no Notion writes, no cover letters, batch finished by hand. That morning the cover-letter PDF pipeline moved to Chromium over the canonical HTML with modeldeepseek-paid-smartand a 600 s dashboard timeout → runbooks/job-radar - Also updated:
incidents/2026-10-26-planned-restart-orphaned-cron-run.md(new),incidents/2026-10-20-gateway-unclean-exit-orphaned-run.md(recurrence),incidents/2026-10-16-omniroute-503-resource-pressure.md,runbooks/job-radar.md,systems/scheduled-tasks.md,index.md,log.md. Nothing removed or archived.
Recent Changes (2026-10-25, nightly audit; live probes 2026-10-25 00:1x–00:5x AWST) (superseded by the 2026-10-27 block above)
- A third consecutive clean cron day — and an off-cron fault that is not the fleet's. Window
2026-10-24: 167
completed/ 0failed(+ this auditrunning); 2026-10-23 settled at 170 / 0 (169 at the 10-24 audit). Fleet unchanged at 28 jobs (25 enabled / 3 disabled), 4 non-cleanlast_status, 2 unclosed incident rows — nothing opened, nothing closed in-window — pins unchanged. 14 sessions: 11cron+ 3desktop. → systems/scheduled-tasks - ⚠ New: 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 — whileconduit_call_userwas onetool_searchaway and his call settings were permissive. Capability asserted instead of discovered; the tool itself is fine. → new page incidents/2026-10-24-conduit-call-request-refused - Conduit, corrected and updated. Plugin
0.69.0/ HEADf000bf0(22 commits on) while the gateway process still runs the 10-23 code and the memory-timeout patch is uncommitted and now five releases behind HEAD. Device phone-status contact last 10-23 19:10:30; health ingestion to 10-24 09:59:59; store 569.9 MB / 1,520,229 events / 3,028buckets/ 124windows(the 10-24 page's 308 / 62 was a narrower grouping). ⚠conduit-calls.json → historyis empty — the 10-22 memory-fix incident's “two calls closed cleanly 00:03:23 / 00:06:57” was a false positive (cron turn-ends, not calls), so that fix still has no positive call evidence. → systems/conduit, incidents/2026-10-22-conduit-memory-start-timeout - Also updated:
systems/conduit.md,incidents/2026-10-22-conduit-memory-start-timeout.md(correction),systems/scheduled-tasks.md,index.md,log.md. Nothing removed or archived.
Recent Changes (2026-10-24, nightly audit; live probes 2026-10-24 00:1x–00:3x AWST) (superseded by the 2026-10-25 block above)
- A clean cron day, and the 2026-10-09 timeout storm is finally closed. Window 2026-10-23:
169
completed/ 0failed(+ this auditrunning) — the third zero-failure day in four; 2026-10-22 settled at 173 / 0.1b23c042e17d(Enhanced Weekend Adventure Planner, weekly Fri 08:00) ran clean on its 10-23 slot, closing the storm's last two incident rows (1b23c0_c35703f637b8,1b23c0_103cbe04a79b) at 08:04 — all 12 rows closed, jobokagain. Unclosed incident rows 4 → 2, non-cleanlast_status5 → 4, fleet unchanged at 28 jobs (25 enabled / 3 disabled), pins unchanged. → incidents/2026-10-09-cron-provider-timeout-storm, systems/scheduled-tasks - New: Conduit is documented. The dashboard plugin + iOS app that puts Hermes on Anthony's phone
(voice calls, cards, push) now has a system page — plugin tree, version
0.64.0(HEADeaa14be), upstreamkaishi00/hermes-conduit-notifier, gateway on:9119, one registered device (iPhone, app2.0.0), its state/DB files and their sizes, and the uncommitted patch it carries. → systems/conduit - ⚠ New fault, found and fixed in-window: Conduit voice calls were being abandoned by the memory
layer. The plugin hard-coded a 10 s budget for one request including the Mnemosyne provider
start, while Mnemosyne's cold start for a
conduit-voicesession runs 10–45 s. Three calls hit it (10-22 11:28:17, 10-22 13:16:37, 10-23 18:29:16:Memory provider 'mnemosyne' start for Conduit timed out; abandoning the call) and ran without recall. Patched in the plugin's working tree to a 60 s default (CONDUIT_MEMORY_TIMEOUT_Soverride) plus aTokenErrorguard that proceeds without recall instead of aborting; the dashboard restarted 18:54:43 and no abort line exists after it, with two calls closing cleanly at 00:03:23 and 00:06:57 on 10-24. The patch is uncommitted — a plugin update reverts it. → incidents/2026-10-22-conduit-memory-start-timeout, systems/mnemosyne - Sessions: 14 in the window — 13
cron+ 1desktop(10-23 18:26:12, the phone-call session above); no other interactive sessions. - Stocktake: the 10-22 sixfold overrun did not repeat — the 10-23 03:07 slot ran and committed
(
250c735: freshness 2 stale / 94 fresh, skills-index 306). → systems/skills-index - Housekeeping: frontmatter added to
incidents/2026-07-29-mnemosyne-relay.mdandincidents/2026-08-04-omniroute-free-deepseek-silent-stops.md, both of which sat outside the SCHEMA (rule 4). Freshness: 102 pages; 3 carry averified_onolder than 21 days —infrastructure/hosts.md,runbooks/provider-health.md,runbooks/update-hermes-safely.md(all 94 d). Nothing removed or archived.
Recent Changes (2026-10-23, nightly audit; live probes 2026-10-23 00:0x–00:16 AWST) (superseded by the 2026-10-24 entry above)
- First zero-failure cron day in three days, and five incidents cleared at once. Window 2026-10-22: 172
completed/ 0failed(+ this auditrunning); 4 runs had already completed on 10-23 by 00:0x. Five incident rows closed and none opened —0e5198_be2291809e56+0e5198_ec2fac98a91d(08:01:40),06a0a1_9e0ff4eedc49(10:14:34),c8d529_e8c70250f9be(18:17:59),dca848_014affeb6954(07:59:22) — so unclosed rows fall 9 → 4 (3alerted/ 1detected). Non-cleanlast_statusfalls 9 → 5:1b23c042e17d(error, streak 2, next slot Fri 2026-10-23 08:00),c0a9fa314542(error, 1, Mon 10-26),0e753e9720fd(error, 0, 11-01),fad5a86979d4+066bb5191280(delivery_failed, Mon 10-26 / 11-01). All four cleared job rows had been red since 2026-10-15 (theomni-101503 burst) and each ran clean on its first slot of 10-22. → incidents/2026-10-16-omniroute-503-resource-pressure - Correction to the 2026-10-21 tally. A DB recount by both
started_atandclaimed_at(AWST) puts 2026-10-21 at 168completed/ 1failed, three below the 171 / 1 recorded on 10-22. Retention does not explain it (floor 2026-10-08); the delta is recorded rather than overwritten. → systems/scheduled-tasks - ⚠ The stocktake ran six times long, reported
completed, and committed nothing.1a8e90ea2271ran 2026-10-22 03:00:28 → 04:38:19 (97 m 58 s) against 16 m 01 s on 10-21, deliverysuppressed; its regeneratedsystems/skills-index.md(mtime 03:00) was still uncommitted at audit time and its diagnosed fixes were never applied. Acompletedcron row is not evidence the work happened. → incidents/2026-08-15-skills-index-drift - Skills index fixed at the root tonight. The page counted 41 parked skills under
~/.hermes/skills/.archive/, and two scripts generated it with different shapes (repowiki-maintain.sh,find-based → 347 with a## .Archivesection; stale~/.hermes/scripts/wiki-maintain.sh,rglob-based → 348 without). The repo script now excludes*/.archive/*, prints the archived count as an exclusion, and nameshermes skills listas the authoritative loadable figure. Page regenerated: 306 skills across 69 categories (was 347). Live counts: filesystem 348, with symlinks 376, minus archive (41) +apple/(4) = 331, loader 329 enabled (34 hub / 52 builtin / 243 local). → systems/skills-index - Wiki maintenance deployed. Quartz parsed 102 files, emitted and deployed 602 files, and
hermes-wiki-serve.servicerestarted 00:16 AWST. Freshness: 2 stale / 94 fresh / 6 no-date of 102 pages —reports/communities-wa-social-media-audit-2026.md(56 d) plus, newly over the threshold,systems/model-providers.md(22 d, updated 2026-10-01; needs a pass against the live OmniRoute catalogue). - 27 sessions in the window: 15
cron, 3subagent(the AI-Newsletter research fan-out), 6desktop(voice-chat-backend research 11:28–11:32; incoming-phone-call tests 13:04 / 13:07 / 13:15), 2acp(0 messages), 1oneshotmemory-capture probe. Fleet unchanged at 28 jobs (25 enabled / 3 disabled); 11 pincustom:omni-101/smart-route, 8 carry no pin, 6free-stack, 2custom:omni, 1deepseek-paid-smart(this audit).
Recent Changes (2026-10-22, nightly audit; live probes 2026-10-21 23:59 → 2026-10-22 00:20 AWST)
- Hermes Agent updated to
0.22.3.hermes updateran 2026-10-21 22:47:25 → 22:57:38 AWST (action9eed3a99e799347c691ea52a72e122a1), from pre-update tree0.22.2/d923a5eb487a17c0…to commit5b147ab036d6…(detached, install stampdisplayVersion 0.22.3, built 2026-10-21T14:57:38Z). Stagesplan/apply(git) /deps/buildall succeeded, butsnapshot=skipped(disabled by updates.pre_update_backup (mode: off)). Gateway restarted via systemd — pid868087,phase: running,api_server: connected, heartbeat 2026-10-22 00:13 AWST — and the dashboard was respawned by argv on:9119(pid869852). Post-run advisories, neither yet acted on: rebuild the search index (hermes sessions optimize-storage) and Preparing pinned cua-driver (Computer Use)… (no completion line in the log). → systems/hermes-agent - The only cron failure of 2026-10-21 is a new failure mode. Window: 171
completed/ 1failed(+ this audit).dca8482e4f76(Daily Marketing Job Radar, 07:00 weekday,custom:omni-101/smart-route) failed 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— not the 503 resource-pressure string (zero such rows on 10-21; last 2026-10-19 09:02) — while the sibling 07:00 job85edf6772bcacompleted normally. Incidentdca848_014affeb6954alerted, unclosed; the run produced no output (cron_incomplete_no_output, 82 msgs / 47 tool calls). → incidents/2026-10-21-omniroute-pre-dispatch-filter-skip - Incidents: 1 closed / 1 opened; unclosed stays 9 (8
alerted/ 1detected).08eb86_472c7b609c80resolved 2026-10-21 08:37:21 after the job's 08:30 slot ran clean, which also cleared08eb86f02d37from the non-clean table. Non-cleanlast_statusstays 9 (7error/ 2delivery_failed), one swap in/out. - 2026-10-20 settled at 169
completed/ 1unknown— the orphaned08eb86f02d37run. The previous audit's "168 / 0" was taken before the 23:59 slot landed. → incidents/2026-10-20-gateway-unclean-exit-orphaned-run - Config backup: 76 commits now unpushed. The 2026-10-21 11:00 run created commit
a8486a20and the push failed for the 75th consecutive night; Telegram noticemessage_id 8449was delivered, AgentMail failed. → incidents/2026-08-08-gitea-config-backup-push-dead - 12 sessions in the window, all
cron— no interactive sessions. Fleet unchanged at 28 jobs (25 enabled / 3 disabled); 17 pincustom:omni-101, 7 carry no pin, 1 pinscustom:omni.
Recent Changes (2026-10-21, 03:00 stocktake; live probes 03:00-03:12 AWST)
- Scheduled wiki maintenance ran clean.
wiki-maintain.shcompleted all three steps — skills-index regenerated (346 → 347 skills, newaustralian-tax-return-reviewunder Finance), freshness audit written (raw/stocktake/freshness-20261021.txt), Quartz rebuilt (596 files) and deployed,hermes-wiki-serve.servicerestarted. Job1a8e90ea2271isactive,last_status: ok, pinnedcustom:omni-101/free-stack. - Tailscale node inventory corrected — the table had drifted again.
octop(100.92.163.122) andspringroll(100.100.153.125) were missing from the table entirely;openmausbot/openmausbot-vmappeared in prose but not in the table body;omarchymachad gone offline (was online); every offline age was stale. Rebuilt fromtailscale status --jsonkeyed on DNS name, notHostName— the JSONHostNamefor thefreshrssnode isct260, and both OmniRoute nodes report the hostnameomniroute, which collides silently. Now 51 non-funnel nodes (50 IPv4 peers +hermes). → infrastructure/tailscale - Two Uber Eats monthly reports were missing from the published wiki and have been recovered. The generator wrote
only to
~/wiki/reports/uber-eats/(the~/wikirepo), never to the canonicalagent-estate-wikitree — so 2026-08 and 2026-09 never reached the published site. Root cause fixed: the generator now targets the canonical tree and mirrors to the legacy one, and now emits YAML frontmatter (without it the pages landed in the audit's "no updated DATE" bucket and Quartz could not read the page date). Both months verified against~/.hermes/uber_eats_report.json; the 2026-08 previous-month column corrected from $0.00 to $264.51 / 11 orders. → reports/uber-eats - Two incident pages re-verified live and annotated: incidents/2026-08-15-skills-index-drift (its named
regenerate-skills-index.shno longer exists — regeneration now lives inwiki-maintain.shstep 1/3) and incidents/2026-09-02-sftpgo-outage (CT299 running, health endpoint HTTP 401 = auth required, service up). - One page left stale on purpose: reports/communities-wa-social-media-audit-2026 (54d) — its source document
/home/hermes/.hermes/cache/documents/doc_3cc87da4957f_deep-research-report.mdno longer exists, so the baseline cannot be re-verified against a live source. Flagged, not edited.
Recent Changes (2026-10-21, nightly audit; live probes 2026-10-21 00:03-00:15 AWST)
- A clean day: 2026-10-20 closed 168
completed/ 0failed(plus 1unknown, plus this audit) — the first zero-failure day since 2026-10-12, ending a seven-day run of failures. Theomni-101503 fault did not recur (the last failure row carrying the resource-pressure string remains 2026-10-19), and zero new incident rows were opened across the whole window; 4 closed, so unclosed rows fall 13 → 9 (8alerted/ 1detected). → incidents/2026-10-16-omniroute-503-resource-pressure (status back tomonitoring) - A gateway unclean exit orphaned a cron run, and nothing reported it.
08eb86f02d37(Gmail Action Digest, 08:30 slot) was claimed 08:31:03 and closed asunknown: “Scheduler restarted after this execution's owner exited before a durable terminal state; whether side effects ran is unknown.” The previous gateway life (pid 2496376, started 2026-10-17 05:14) was recorded UNCLEANLY at 09:09:01 — last heartbeat 08:50:28, RSS 394 MB, 12.2 GB free,suspected_oom=False.delivery_outcomeis NULL and no delivery row exists for the slot, so the ledger offers no evidence the digest arrived; no incident row was created, and the job table still shows the previous slot's 503. First recorded orphan of its kind; first unclean exit since 2026-09-21. → incidents/2026-10-20-gateway-unclean-exit-orphaned-run - ⚠ A green cron row is not evidence the work happened — second instance, and this one is 2.5 months old.
e27da6c34bbb(Hermes Config Backup to Gitea, daily 11:00) readslast_status: ok,last_error: null, and its 2026-10-20 execution readscompleted— while nothing has reached Gitea since 2026-08-07 11:00:47. The repo is 75 commits ahead oforigin/main;backup.logendscould not read Username for 'https://gitea.kangaroo-eel.ts.net'→✗ Push to Gitea FAILED→--- Backup complete: FAIL ---.originis HTTPS with no credential in the URL and no helper, so the non-interactive push cannot authenticate: no off-box~/.hermesbackup since 2026-08-08. Telegram failure notices have been firing all along (last 2026-10-20 11:00,message_id 8447); the AgentMail step failed. → incidents/2026-08-08-gitea-config-backup-push-dead, infrastructure/backups - The global model default moved off OmniRoute.
model.provider: custom→nous(https://inference-api.nousresearch.com/v1),model.default: smart-route→meituan/longcat-2.5-preview:free(not in place 2026-10-09 19:42; in place by 2026-10-20 11:00). Pins are unchanged — 20 of 28 jobs still pin OmniRoute (smart-route×11,free-stack×6,deepseek-paid-smart×1,custom:omni×2) — but the 8 jobs with no pin now call Nous direct instead of the router, so the fleet runs two upstream paths for the first time. → systems/current-profile, systems/scheduled-tasks - A user question was answered with a canned non-answer, and the request is still outstanding. Desktop
session
20261020_183748_6d40ea(2026-10-20 18:37,model: minimax/minimax-m3.1-flash:free) asked how to use Nous OAuth dashboard auth for the gateway and whether a gateway token could be configured; the turn endedreason=rebuilt_restart_limit_exceeded … response_len=0and the only assistant message is “Your request was not processed. Send it again if you still want me to carry it out.” Nothing was configured in response to that request — it needs re-asking. → incidents/2026-10-18-degenerate-stream-canned-substitute dashboard.basic_authnow carries asecretandsession_ttl_seconds: 43200(present 2026-10-21 00:0x). The plugin's “no 'secret' configured; generating a random per-process signing key … sessions will not survive a restart” warning last appeared 2026-10-20 18:45:14, so dashboard sessions should now persist across restarts.- Interactive sessions returned after weeks of cron-only windows:
talaria-ios(10:49 → 19:27, 25 messages, 12 tool calls, “Get Australian tax return done”,provider: custom:command-code) and thedesktopsession above. Non-cleanlast_status12 → 9 (7error/ 2delivery_failed); fleet unchanged at 28 jobs / 25 enabled / 3 disabled. → systems/scheduled-tasks
Recent Changes (2026-10-20, nightly audit; live probes 2026-10-20 00:03-00:12 AWST)
- The
omni-101503 resource-pressure fault returned 44 hours after the incident page was downgraded tomonitoring— same node, same error string, same blast radius. 2026-10-19 closed 159 completed / 13 failed against 10-18's 168 / 1 and 10-17's 163 / 5. 9 genuine model-call failures across 8 jobs all readRuntimeError: HTTP 503: Service temporarily unavailable due to resource pressure. Retry shortly.oncustom:omni-101, in two clusters — 06:01 (one job) and 07:01 → 12:01 (seven more runs, seven jobs). The remaining 4 failed rows are the Mnemosyne Watchdog quoting the coverage monitor's error: the same derivative double-count as burst 1. → incidents/2026-10-16-omniroute-503-resource-pressure (status back toactive) - Single pin, verified this time. Every job that failed in burst 2 reads
provider: custom:omni-101,model: smart-routeinjobs.jsonas of 2026-10-20 — there is no alias diversity left to fail over to. ⚠ The burst-1 note recording a wider mix (deepseek-paid-smart,free-IA,dark) no longer matchesjobs.json; it needs confirming with Anthony before either reading is relied on. - The node stayed green through all of it.
omniroute-1(100.78.63.20:20128) answered/api/health→200 {"status":"ok"}and/v1/models→401at 2026-10-20 00:03, before, during and after the burst. Reachability probes cannot see this failure class — only job-level error text can. c0a9fa314542(GitHub Trending Radar) lost its scheduled Monday slot (0 9 * * 1, 09:01) to the 503, so this week's roundup never ran and its revoked-token status is untested for a second consecutive Monday. Its next real test is Mon 2026-10-26 09:00.- Non-clean
last_statusmoved 7 → 12 (10error, 2delivery_failed) as of 2026-10-20 00:09. Newly dirtied:dca8482e4f76,85edf6772bca,08eb86f02d37,c0a9fa314542; deepened:0e519874d280andecc1fc13655a(both streak 2).fad5a86979d4added adelivery_failed(bare-telegramtarget, thread 34795 not found — no incident row created for it).b63ed5817212,96eb95ce12f2andea79a2107e36all cleared on their next slots. Unclosed incident rows: 13 (12alerted/ 1detected). → systems/scheduled-tasks - Unchanged otherwise: fleet still 28 jobs / 25 enabled / 3 disabled; CT255 Mattermost
(
100.96.100.255:8065) still unreachable; 15 sessions in the window, allcron— no interactive sessions.
Recent Changes (2026-10-19, nightly audit; live probes 2026-10-19 00:04-00:2x AWST)
- A model stream started repeating itself — and Hermes delivered the placeholder to Telegram before it
aborted. The FreshRSS Midday slot (
ecc1fc13655a, 12:00) endedfailedat 12:08:25 withRuntimeError: Model output entered a repetition loop and the stream was cut mid-loop; discarding the degenerate response.The run had already written and delivered a canned line — "Your request was not processed. Send it again if you still want me to carry it out." — at 12:08:11 (delivery_outcome: delivered), so the digest topic received a non-answer that does not read as an error. A delivered message is not evidence of delivered content. Open question: should the guard suppress delivery or re-queue, instead of substituting text on the job's normal route? → incidents/2026-10-18-degenerate-stream-canned-substitute - Window tally:
10-18 = 168 completed / 1 failed— that row is the only failure of the day;10-17 = 163 / 5, and10-19so far5 / 0plus this audit. Non-cleanlast_status8 → 7; open incidents 8 → 7 (6alerted/ 1detected), with 1 opened and 2 resolved in-window (cbfe434a3b5e00:42:54,1a8e90ea227103:01:22 — both auto-closed by their own next clean slot). 11 sessions in the window, allcron; no interactive sessions. → systems/scheduled-tasks - The 10-18 03:00 stocktake landed and closed the two-day gap the last audit flagged:
1a8e90ea2271exited 0,raw/stocktake/freshness-20261018.txtexists, systems/skills-index was regenerated (346 skills / 70 categories; freshness 47 stale / 41 fresh / 7 no-date) and committed (dd53e5f). - Mattermost's cause is finally known: CT255 is stopped. The adapter's 5-minute reconnect loop is
unchanged (
attempt 471at 00:14:07;mattermost connect timed out after 30s), the peer is offline (last seen 29d), and the host answers neither TCP:8065nor ICMP from CT460. The 10-11 entry's "cause not determined" is now superseded. → systems/messaging-integrations - New page: systems/push-notifications — and the push bridge is broken, and has been for a long
time.
status.jsonsaysconnected: falsewithconnection refused (nothing listens there on this machine): the bridge dialsHERMES_PUSH_GATEWAY_URL=https://hermes.kangaroo-eel.ts.net, which resolves on this host to127.0.1.1via/etc/hosts— where nothing serves 443 — while the gateway itself is healthy (0.0.0.0:9119,/→ 302) and the tailnet Serve route is intact. The error string appears 23,469 times in the retained logs. Fix not applied (change the dial target, or the name resolution). → systems/push-notifications - One more standing alert, unchanged: the GitHub Trending Radar delivery token is still dead
(
getMe→ 401, re-verified 10-18), and its next exercise is Mon 2026-10-19 09:00. Not repaired — a replacement bot token is Anthony's call. → systems/scheduled-tasks
Recent Changes (2026-10-18, nightly audit; live probes 2026-10-18 00:31-00:36 AWST)
- The
omniroute-1node is up — and this time it shed load instead of refusing connections. Three days after the 34-hour TCP blackout, the same node produced a second, different failure mode: 9 model calls across 7 jobs died withRuntimeError: HTTP 503: Service temporarily unavailable due to resource pressure.between 10-16 08:00:37 and 10-17 03:00:28 (~19 h), while/api/healthanswered200 {"status":"ok"}and/v1/modelsanswered401before, during and after (re-probed 10-18 00:33). → incidents/2026-10-16-omniroute-503-resource-pressure - It cleared itself and the fleet is green again.
10-16 = 165 completed / 8 failed,10-17 = 162 / 5(all five before 03:01; a 2026-10-20 DB re-read gives 163 / 5 — one 10-17 row was counted twice at the time),10-18so far7 / 0— no failure row of any kind since 10-17 03:00. Every job that failed re-ran clean on its next slot:b63ed581721210-17 06:01,08eb86f02d3710-17 08:31,ecc1fc13655aandea79a2107e36both 10-17 12:02, each of those auto-closing its own incident. - Fleet count fell 29 → 28: the Mosquito Tracker was removed.
1b31187397a5is absent fromjobs.json(fileupdated_at 2026-10-18T00:36:17+08:00); its last execution was 10-16 15:00 (completed, delivered). The three disabled jobs are unchanged — 25 enabled / 3 disabled. - Non-clean
last_status: 12 → 8 — and seven of the eight cannot clear until their next slot, because every one of them is a weekly, Mon/Thu or monthly job:1b23c042e17d(error, streak 2, last failure 10-16 08:03 with the 503, next Fri 10-23 08:00),0e519874d280(Mon 10-19 08:00),c8d52904e1d6(Thu 10-22 18:00),06a0a1c8704f(Thu 10-22 10:00), and the monthlies0e753e9720fdand066bb5191280(both 11-01). The eighth iscbfe434a3b5e— this audit, whose 10-17 run died on the 503 and whose 10-18 run clears it. Open incidents 12 → 8 (5alerted/ 3detected); 9 opened and 6 closed in-window. → systems/scheduled-tasks - The watchdog double-counts — 4 of the 13 failure rows are one sentinel.
96eb95ce12f2exited 1 on 10-16 12:15 + 12:30 and 10-17 00:15 + 00:30, each row quoting the coverage monitor's own 503 error. Read failures per job, not per row. → systems/mnemosyne - Second consecutive stocktake hole. The 10-17 03:00 slot failed (503), so
raw/stocktake/freshness-20261017.txtdoes not exist andsystems/skills-index.mdis stamped 10-16 (10-15 is missing too, from the storm —RuntimeError: Connection error.). The 10-18 03:00 slot closes it; nothing was regenerated by hand, because a manual run would race the scheduled one. - Fifth consecutive window with no interactive session — 30 sessions across the two days, all
cron, and zero non-cron sessions since 2026-10-15. Every finding here comes from live system state, not conversation. - The GitHub Trending Radar is dead at the delivery end. The Telegram bot token in
~/workspace/github-trending-radar/config.jsonreturns HTTP 401 ongetMe(probed 10-18 00:35); the job's GitHub PAT still answers 200, so only the delivery credential is gone. The cron row stays green becauselast_statuswas set by the 10-12 09:00 run (last_run_at 2026-10-12T09:00:12). Next exercise: Mon 2026-10-19 09:00. Not repaired — a replacement bot token is Anthony's call.
Recent Changes (2026-10-16, nightly audit; live probes 2026-10-16 00:0x–00:2x AWST)
- ⚠ A fleet-wide 34-hour cron blackout just ended —
omniroute-1was refusing TCP connections.10-14 = 160 completed / 12 failedand10-15 = 151 completed / 24 failed, against a clean 10-10→10-12 (175/0,172/0,175/0) and 10-13 (167/1). Root cause:httpcore.ConnectError: [Errno 111] Connection refusedagainsthttp://100.78.63.20:20128(providercustom:omni-101), surfacing in the cron DB asopenai.APIConnectionError: Connection error.→RuntimeError: Connection error.Window 10-14 08:30:27 → 10-15 18:07, recovered by 10-15 22:01. 24 genuine model-call failures on 12 jobs + 12 derivative watchdog reds = 36 failure rows across 13 jobs. → incidents/2026-10-14-omniroute-node-connection-refused-storm - Everything model-calling is pinned to that one node — there is no failover anywhere in the fleet. All 18 enabled
agent-mode cron jobs run oncustom:omni-101(smart-route×10,free-stack×6,deepseek-paid-smart×2). The only other model-capable pin,custom:omni(CT600omniroute:20128), carries just theno_agentjobe530c89f2be0, whose provider field is vestigial;d40085da631cis disabled. Completing runs inside the window: 211 — every single one script-only. Zero model calls succeeded for 34 hours. → systems/omniroute, systems/scheduled-tasks - The cost was silence, not errors. Digests that never went out: Tech & AI, Daily Marketing Job Radar, Political News, Gmail Action Digest ×2, FreshRSS Midday ×2, AI Newsletter Curation for Patrick; the weekly Perth New Restaurant was missed outright (next chance 10-22). The 10-14 23:59 Wiki Audit itself died on the same fault, so the 10-14 window was never audited — this entry spans two days. → systems/scheduled-tasks
- Recovered, verified live.
GET /v1/modelson100.78.63.20:20128→ HTTP 401 in 10 ms (up, auth required); same onomniroute:20128/100.88.81.19. First green model-call job:1b31187397a5at 10-15 22:01:56; thenb63ed5817212(10-16 00:02:29) andea79a2107e36(10-16 00:09:48). - The backlog unwinds on schedule rather than by hand. Non-clean
last_status: 3 → 12 (9 new storm rows; three cleared as their slots came round), open incidents 3 → 12 (9alerted/ 3detected). The two longest-lived —1b23c042e17d(Fri 08:00 slot) and0e753e9720fd(1st 09:00) — pre-date the storm. → systems/scheduled-tasks - Both Mnemosyne monitors sit inside the blast radius. Health (12 h) and Embedding Coverage (6 h) both failed on every slot, so no coverage figures were refreshed for ~34 h — the last explicit read remains 2026-10-12 (working 96.7 %, episodic 99.4 %). The script-only Mnemosyne jobs were unaffected. → systems/mnemosyne
- Self-healing gap, not a manual repair. The failed 10-15 03:00 stocktake left
raw/stocktake/freshness-20261015.txtunwritten andsystems/skills-index.mdstamped 10-14; the 10-16 03:00 slot closes it, so nothing was regenerated by hand here. - Fourth consecutive window with no interactive session — 36 sessions across the two days, all
cron.
Recent Changes (2026-10-14, 03:00 stocktake; live probes 03:01–03:1x AWST)
- ⚠ A second, unclustered Proxmox hypervisor exists —
m93pat100.104.51.98, PVE 9.2.0. DISCOVERED this pass.pvecm nodesis empty on both hosts (no cluster), and guest IDs collide:m93pCT221 is gitea,pveCT103 is cliproxyapi, and both worlds share CT100/CT221/CT245 numbers. It had been in the Tailscale node list as an unremarkableonlinepeer with no wiki page recording it as a hypervisor; a tailnet-wide:8006scan returned onlym93pandpve, which is how it surfaced. Live guests onm93pinclude gitea (CT221), ntfy (CT1241), freshrss (CT1260), openweb (CT245), vaultwarden, obsidian-livesync, rustdesk, homebridge, litellm (CT500), omniroute (CT101), paseo (CT1261), mailflow, social-dashboard, docker-01, rclone, freellmapi;nightbridgestopped. → infrastructure/proxmox, infrastructure/network-map - Four guests the wiki placed on
pveare actually onm93p. CT221 (gitea), CT241 → CT1241 (ntfy), CT260 → CT1260 (freshrss) and CT245 (openweb) are absent from livepct listonpve, yet all four services answer./etc/pve/lxc/onpveholds only260.conf.bakand no vzdump log references them — so they were never deleted, they were never on this host. Every prior audit since 2026-10-11 carried the error forward. Always qualify a guest with its host. → infrastructure/proxmox - VM 282
ubuntu-server-xfceis running, not stopped as recorded. → infrastructure/proxmox - Tailscale node inventory rebuilt: 45 non-funnel nodes (plus 23
funnel-ingress-nodeIPv6 peers, excluded). The 2026-10-11 table had drifted badly — it listed 30 nodes and was missing 15, includingm93p,pve,omniroute-1,paseo,qwenpaw,rustdesk,vaultwarden,social-dashboard,openweb,omarchybook,sftpgo,rclone,omni,runtipi. Several states were wrong too (anthonys-mac-miniis online on a different IP;omarchy-macmini/omarchy-quattroare not live peers;anthonys-iphoneis online not active). Serve routes on CT460 re-verified exactly as recorded — 13 routes,:8443/webhookFunnel,:9443tailnet-only. → infrastructure/tailscale - Mattermost CT255 confirmed stopped, consistent with its Tailscale peer offline 24d — unchanged finding, re-verified. → infrastructure/proxmox
- Camofox recovered from its 2026-10-12 memory ceiling:
camofox-browser.servicenow reportsMemory: 29.9M (high: 2G, max: 3G, swap max: 1G, available: 1.9G, peak: 485.8M)with 16 tasks, active since 2026-10-13 23:42:55. The containment limits held; the workload was the fault. → systems/browser-backend - Stocktake artifacts regenerated:
systems/skills-index.md= 346 skills / 70 categories (the known 347-on-disk off-by-one persists);raw/stocktake/freshness-20261014.txt= 48 stale / 38 fresh / 7 no-date of 93 pages, identical in shape to 10-13. - Quartz rebuild still inert (no
quartz.config.ts, nonpx) —public/was not refreshed. Carried open item.
Recent Changes (2026-10-13 → 2026-10-14, nightly audit; live probes 2026-10-14 00:00-00:30 AWST)
- The four-day clean streak broke: 2026-10-13 =
167 completed/ 1failed(10-12 finalised175 / 0, 10-11172 / 0, 10-10175 / 0). The failure is1a8e90ea2271(wiki-stocktake-maintenance, 03:00) onRuntimeError: HTTP 404: No active credentials for provider: opencode— the third failure of that job in six days, all three on the opencode path (10-08 403 free-tier, 10-09 timeout, 10-13 404). New incident1a8e90_d11698bd7275(detected, streak 1, not alerted); it clears only on a successful 2026-10-14 03:00 run. → systems/scheduled-tasks - The failing run stranded its own generated artifacts. Step 1 (skills-index) and step 2 (freshness report) wrote to disk, then the agent turn died → no commit, no push.
systems/skills-index.md(date-only change; 346 skills / 70 categories unchanged) andraw/stocktake/freshness-20261013.txt(48 stale / 38 fresh / 7 no-date of 93 pages, down from 54 stale) were committed by the 2026-10-14 audit. → systems/skills-index executions.dbretention floor moved to 2026-10-08 07:11 (MAX_TERMINAL_EXECUTIONS = 1000; 1,001 rows = 1,000 terminal + 1 in flight). Days older than the floor now undercount — 10-08 reads126 completed / 1 failed, a partial tally.- Non-clean
last_statusrows: 3 → 4 (clearedfad5a86979d4,dca8482e4f76; added1a8e90ea2271). Open incidents: 2 → 3. Fleet unchanged at 29 jobs / 26 enabled. - No interactive sessions for the third window running: 15 sessions in the window, all
cron, zero interactive.
Recent Changes (2026-10-12 → 2026-10-13, nightly audit; live probes 2026-10-13 00:05-00:45 AWST)
- A clean cron day hid a dead credential. 2026-10-12 ran 174 completed / 0 failed (third consecutive clean day; 10-11 finalised at
172 / 0) — yetc0a9fa314542(GitHub Trending Radar) reportedcompletedwithdelivery_outcome: deliveredwhile its own Telegram send was dying on an invalid token. The delivered artifact was the agent's recovered digest, not the script's. → systems/scheduled-tasks - GitHub Trending Radar's bot token is REVOKED — live-verified, and the 2026-10-06 "refuted" entry was WRONG.
getMeagainsttelegram.bot_tokenin/home/hermes/workspace/github-trending-radar/config.jsonreturns HTTP 401; the token is a valid 46-char shape, so revoked rather than malformed, and no valid replacement exists on the box. The fetch path is healthy (100 repos, 26 cache files in 24 h), so onlydigest.py'ssend()fails. Correction: the 2026-10-06 entry below treated two green runs as proof the token worked; a green cron row only means the agent finished, and neither run exercised the failing call. Fix = new @BotFather token →config.json→ re-rungetMe. Credential present, value not recorded. → systems/scheduled-tasks - Open cron incidents 5 → 2. Closed on 2026-10-12:
fad5a8_a13bbc837e1c+fad5a8_c80b59a907f0at 03:05:39 (bothdeepseek-v4-flash, cleared byfad5a86979d4's first clean scheduled run — 03:00:45 → 03:05:47, 448 unique birthdays, delivered) anddca848_23fcd2b18aaaat 07:33:41 (cleared bydca8482e4f76's own 07:00 run, delivered to topic 1030 after a 32-minute run). Survivors:0e753e_e7f8194a7d06(detectedsince 2026-10-01 — cannot clear until 2026-11-01, the job has no retained executions at all) and1b23c0_c35703f637b8(alertedsince 2026-10-09, next slot Fri 2026-10-16 08:00). Table: alerted 1 / detected 1 / closed 8 / resolved 66. Fleet 29 jobs — 26 enabled / 3 disabled; non-cleanlast_status5 → 3 (0e753e9720fd,1b23c042e17d,066bb5191280). → systems/scheduled-tasks - Camofox hit its memory containment ceiling inside a cron run (NEW). The 2026-10-12 07:01 Daily Marketing Job Radar drove
camofox-browser.serviceto2.5Gwith swap fully consumed,available: 0B, 383 tasks (drop-inMemoryHigh=2G/MemoryMax=3G/MemorySwapMax=1G);/tabsand page evals hung. The agent restarted the service at 07:23:50 and finished one tab at a time, and the job still delivered. A green cron row does not mean the browser layer was healthy — check the unit's peak/swap/tasks when a browser-heavy job runs long. → systems/browser-backend - Browser page corrected against a live probe. REST API is
:9377, not:9093(nothing listened on 9093);:9378does not exist; Camofox is asystemd --userunit on the Hermes host (CT460), not CT450. Containment drop-in documented. → systems/browser-backend - Mnemosyne healthy at 12:02 — working 760/786 = 96.7 %, episodic 1050/1056 = 99.4 % (both above the 95 % floor, no
reindexneeded); orphan embeddings 0; FTS5 aligned exactly (786/786, 1056/1056, 876/876); 0 unconsolidated; 1 unresolved conflict; disk 15 GB free (81 % used). → systems/mnemosyne - Window shape: 18 sessions, all
cron, zero interactive — the other bookend to the previous window'stalaria-iosresearch session. The 03:00 stocktake1a8e90ea2271ran clean and pushed0eee5f1(freshness 54 stale / 32 fresh / 7 no-date of 93 pages; skills index 346 / 70 categories — the known 347-vs-346 off-by-one persists). The execution log's retention floor has moved to 2026-10-07 08:15, so 10-07 rows are now pruned.
Recent Changes (2026-10-12, 03:00 stocktake; live probes 2026-10-12 03:0x-03:1x AWST)
- 02 stocktake corrections from live probes. systems/nanobot was DOWN as of 2026-08-07; its web UI on CT333 is back up (HTTP
200on100.122.189.81:8766), though the OmniRoute port8900endpoint is still closed sostatusstaysdegraded. systems/home-assistant confirmed up: HTTP200on100.68.139.5:8123, VMID 100 running, Tailscale node offering an exit node — confidence raised low → medium. → systems/nanobot, systems/home-assistant - Freshness snapshot: 54 stale / 32 fresh / 7 no-date of 93 pages (threshold >21 days). The bulk of the stale list is the 2026-07-22 seeding cohort (concepts, runbooks, comparisons) and is structural, not a regression. →
raw/stocktake/freshness-20261012.txt - Skills index regenerated: 346 skills / 70 categories, unchanged count from the previous run. → systems/skills-index
- Tailscale routes re-verified against
tailscale serve status— the CT460 table in infrastructure/tailscale matches live output exactly (13 tailnet routes +:8443/webhookFunnel +:9443Vite dev). Two nodes joined since 2026-10-11:omarchy(100.73.227.103) andomniroute-1(100.78.63.20, both active).
Recent Changes (2026-10-11 → 2026-10-12, nightly audit; live probes 2026-10-12 00:0x-00:2x AWST)
- The cron fleet is clean for a second consecutive day: 2026-10-11 ran
171 completed / 0 failed(+1running= this audit), after 10-071/ 10-082/ 10-0915failed. 10-10 finalises at175 / 0. Fleet 29 jobs — 26 enabled / 3 disabled; non-cleanlast_statussteady at 5; 0 incidents opened, 0 closed — 5 unresolved (3alerted, 2detected). The two streak-1 jobs (dca8482e4f76,1b23c042e17d) carry Friday 2026-10-09 timeouts and have not had a scheduled slot since. → systems/scheduled-tasks - The 2026-10-11 00:08 "memory capture stalled" EXCEPTION was a timezone mislabel, not a capture fault.
working_memory.created_atis naive UTC; the monitor compared it against AWSTnowand reported a 2.7 h gap as 10.7 h. Capture verified healthy: 786 rows, +2 in the window, coverage 98.3 % working / 99.6 % episodic. → systems/mnemosyne - Proxmox storage documented for the first time:
/mnt/ssd0is the pressure point — 808 GiB used, ~63 GiB free (93 % bydf, 88.1 % bypvesm);SSD186.1 %,fred-qnap76.8 %,iMacHDDinactive. → infrastructure/proxmox - First retained research answer filed: fastest VNC clients (asked 2026-10-11) — the server-side encoder is the real bottleneck, TigerVNC native viewer for standard RFB,
-CompressLevelis a client parameter, RealVNC's "4.7×" is self-referential. → queries/retained-research-answers - Only one interactive session in the window (
talaria-ios, 19:13 → 19:51, 41 messages); the other 17 werecron. The 03:00 stocktake1a8e90ea2271completed on schedule (03:00:40 → 03:11:29) and committedd981e30. - Stale labels corrected: incidents/2026-08-18-mnemosyne-capture-pipeline moved from
activetosuperseded(evidence above); the index's count of open 2026-10-09 storm incidents trimmed to the 2 that are genuinely open.
Recent Changes (2026-10-11, 03:00 stocktake; live probes 03:00-03:30 AWST)
- OmniRoute CT600/CT601 roles are INVERTED. CT600
omniroute(100.88.81.19) is running and serving:20128(combo API returns live combos); CT601omni(100.93.204.4) is stopped withonboot=0(Tailscale peer offline 54d). Hermes resolvescustom:omni→omniroute:20128→ CT600. → systems/omniroute - A third OmniRoute node exists:
omniroute-1at100.78.63.20:20128, live (401 = auth-required), registered in Hermes config as provideromni-101(5384 models, defaultsmart-route). It carriesskills_hub(modelfree-stack) — the same provider family implicated in the 2026-10-09 timeout storm. Not present inpct list; identity unconfirmed. → systems/omniroute - Two Ignis instances exist, on different hosts. CT460
ignis(port 8080, vault/home/hermes/wiki/agent-estate-wiki, serving 200) and CT200ignis-ignis-1(imageignis-server:latest, host port 8092, vault/opt/ignis/vaults, serving 200). Both healthy; they are separate deployments. → systems/ignis - Tailscale route drift fixed:
/agent-estatetargets barehttp://127.0.0.1:8769(page had.../agent-estate-role-dashboard.html); a tailnet-only:9443→127.0.0.1:5173Serve was undocumented. CT201's live routes are 8085-based plus/steel(5173) and/steel-api(3000) — the old:8443→localhost:8082Homepage row is wrong. (The/steeland/steel-apiroutes were deleted on 2026-10-29 — see systems/browser-backend.) → infrastructure/tailscale - Proxmox inventory rebuilt from
pct list+qm list: CT475agentzeroand VM110omarchywere missing entirely; 282ubuntu-server-xfcecorrected to stopped; dead rows removed (310, 500, 104, 106, 101). VM403open-clawand VM401hermes-oldare absent fromqm list— flagged unconfirmed, not deleted. → infrastructure/proxmox - Nanobot verified on CT333:
nanobot-gateway(PID 2259048) alive on 8765/8766. It is not a systemdnanobot.service/gateway.service(both probes returninactive— wrong unit names); it runs as thenanobotuser service plus the gateway process. Port 8900 is no longer listening — previous "Serve API" claim flagged unverified. → agents/nanobot - Docker services page corrected: the old "Docker runtime not available" line was a CT460 socket artifact (
/var/run/docker.sockisroot:docker srw-rw----;hermesuser not in groupdocker; no passwordless sudo in cron). Real fleet: CT200 holds ~50 containers, CT333 holds 9. → infrastructure/docker-services - Mattermost CT255 confirmed stopped, consistent with its Tailscale peer being offline 21d. Root cause of the unreachable endpoint still undetermined.
- ⚠
mycompose-db-1on CT200 is inRestarting (1)— crash-looping. Flagged; root cause NOT investigated this pass. - Stocktake artifacts: skills-index regenerated (346 skills / 70 categories),
raw/stocktake/freshness-20261011.txt= 62 stale / 24 fresh / 7 no-date of 93 pages. - Quartz rebuild still inert (no
quartz.config.ts) —public/was not refreshed. Carried open item; unchanged from prior days. - 62 pages remain >21d stale and were not corrected this pass: they were not probed against a live source, so they stay flagged rather than rewritten.
Recent Changes (2026-10-10 -> 10-11, nightly audit of the 2026-10-09 -> 2026-10-10 window; probes 2026-10-11 00:14-00:20 AWST)
The manual 2026-10-10 stocktake entry follows beneath this one.
- The cron fleet is clean again: 174
completed, 0failedon 2026-10-10 (AWST day,executions.db) - after 10-071/ 10-082/ 10-0915failures. 7 of the 10 storm incidents auto-closed during the day; 5 remain open over 3 jobs (1b23c042e17d+dca8482e4f76timeout/alertedsince 2026-10-09;0e753e9720fd+fad5a86979d4agent). Non-cleanlast_statusdown from 10 to 5. Job count 30 -> 29 (26 enabled / 3 disabled). -> systems/scheduled-tasks - The DHL monitor
62619aa6bcb3is retired - open item #1 closed. Anthony instructed removal again on the evening of 2026-10-10; the job is absent from livejobs.json(verified 2026-10-11 00:19 by direct ID lookup). The 2026-10-07 and 2026-10-09 "deleted" reports were false - they inferred removal from missing output instead of looking up the ID. - The 2026-09-28 runtime-dependency class recurred - in the gateway env this time. The gateway's
activate_dependencies()loads one committed uv env (795020dbf24343cd9c52df24723dca83); it was missingmnemosyne/mnemosyne_hermesplus native deps, andelevenlabswas missing from the live managed env. Repaired 21:26-21:34, verified live from 22:01:19 (Memory provider 'mnemosyne' registered (40 tools)->activated; repeated 23:59 / 00:00 / 00:02). The 15-minute guard does not cover this env - open. -> incidents/2026-09-28-hermes-managed-runtime-deps - New page: systems/paseo - Paseo coding-agent daemon, user unit
paseo-daemon.service, v0.11.2,0.0.0.0:6767, running since 2026-10-10 14:47:28. Pitfalls recorded:daemon runvsdaemon start,/usr/bin/paseois 0.7.2 while the daemon is 0.11.2, and a truncatedclinebinary presenting as a provider fault. - Mattermost unreachable from CT460 - configured endpoint
100.98.116.14:8065gives 100 % ICMP loss and TCP refuse; the gateway retries every 5 minutes. Cause not determined. -> systems/messaging-integrations - Health-monitor follow-ups (2026-10-10): "capture silent" was a false alarm (cron-only window);
check_embedding_coverage.pynow carries mode0755; 13 orphanmemory_embeddingsrows (oldest 2026-08-22) remain unverified. -> systems/mnemosyne
Recent Changes (2026-10-10)
- The 2026-10-09 timeout storm is over — the fleet is green again. Window tally (
executions.db, 2026-10-09 00:00 → 2026-10-10 00:00 AWST): 163completed, 15failed. Every failure wasRuntimeError: Request timed out.on the routing aliases behindcustom:omni-101, confined to 00:00 → 15:00; all runs from 18:00 onward completed. 10 open incidents remain (ecc1fc_58b6c38296f3,08eb86_634f1a296f78,1b23c0_c35703f637b8,85edf6_18bedbeec5cd,dca848_23fcd2b18aaa,1a8e90_dc6b2d40ec44,1a8e90_789224ad589c,0e753e_e7f8194a7d06,fad5a8_c80b59a907f0,fad5a8_a13bbc837e1c). → incidents/2026-10-09-cron-provider-timeout-storm 1a8e90ea2271(stocktake) is running right now, not failed. Its 2026-10-09 03:00 run timed out before the generator produced output (so nofreshness-20261009.txtexists — the two-day artifact gap stands); the 2026-10-10 03:00:17 run isrunningat audit time.failure_streak: 2until it completes. This stocktake (run manually by this audit) regeneratedsystems/skills-index.md(346 → 346 skills / 70 categories, frontmatter dates refreshed) and wroteraw/stocktake/freshness-20261010.txt— 62 stale, 23 fresh, 7 no-date of 92 pages. See systems/scheduled-tasks.- Skills count reconciled: 347
SKILL.mdon disk vs 346 reported — unchanged off-by-one (the generator de-dups the nestedproductivity/obsidian-git-sync/obsidian-git-sync/duplicate). Carried open item. - 8 jobs carry a stale
last_status: error—0e753e9720fd(streak 0),fad5a86979d4(streak 0),dca8482e4f76(streak 1),1b23c042e17d(streak 1),85edf6772bca(streak 1),08eb86f02d37(streak 1),ecc1fc13655a(streak 1),1a8e90ea2271(streak 2). Two are pre-repin stale fields (streak 0), not live failures. Job count unchanged: 30 (27 enabled / 3 disabled). - DHL monitor
62619aa6bcb3still enabled — re-probed 2026-10-10:enabled: True,paused_at: null, schedule0 8,11,14,17,20 * * *. Anthony instructed its deletion on 2026-10-09 21:24 and a session reported it deleted. The parcel (8052838382) wasDelivered2026-10-07, so the monitor is redundant. This audit did not mutate cron state — retirement is open item #1 in systems/scheduled-tasks. - Quartz rebuild step confirmed still inert (no
quartz.config.ts,npxpresent but unreachable forquartz) — thepublic/static site was not refreshed by this stocktake. Skills-index and freshness artifacts regenerated and committed correctly; only the published-HTML step is a no-op. Carried open item from 2026-10-07. - Memory recall ranking fix still not persisted — the 2026-10-09 in-session "config saved" claim is not in live config; carried open item. Capture/vector health unchanged (760/760 working, 1,043/1,047 episodic embedded).
infrastructure/tailscale.mdre-verified 2026-10-10 —tailscale serve statusmatches the page exactly: 13 tailnet Serve routes (/,/ui,/wiki,/ignis,/webui,/gitea,/jobs,/desktop,/vnc-camofox,/synergy-prep,/agent-estate,/evening-grid.html,/ignis/:8443funnel/webhook) + the:8443/webhookpublic Funnel. No drift; page remains fresh (19d).
Recent Changes (2026-10-09)
- Cron fleet: the worst day since the repin. 15 failed executions across 10 jobs on 2026-10-09 (10-07: 1, 10-08: 2) — all
RuntimeError: Request timed out.on the aliases behindcustom:omni-101, 00:00 → 15:00 AWST, clean from 18:00. Four incidents auto-closed, eight still open;1a8e90ea2271sits atfailure_streak: 2. → incidents/2026-10-09-cron-provider-timeout-storm - The 2026-10-08 audit window was lost to the same timeout (this job's own 23:59 run); the last committed audit covered 2026-10-07. The 2026-10-09 run covers both days. → log
62619aa6bcb3(DHL Tracking — Parcel 8052838382) is still enabled even though Anthony instructed its deletion on 2026-10-09 21:24 and the session reported it deleted; it runs at 08:00 daily. Retirement is open item #1 in systems/scheduled-tasks.- Memory recall relevance incident — a stale conversational episode outranked current-state facts; capture and vector health verified (760/760 working, 1,043/1,047 episodic), ranking fix not persisted in config. → incidents/2026-10-09-memory-recall-relevance
- Mnemosyne live counts (2026-10-09 22:27): 773 working / 1,047 episodic / 97 canonical slots / 871 facts / 152 conflicts (1 open) / 760 working embeddings / 1,043 episodic embeddings. → systems/mnemosyne
Recent Changes (2026-10-08)
- Cron fleet green for a third consecutive day — 0 failing. Job count unchanged at 30 (27 enabled / 3 disabled) and all 30
failure_streakcounters still read 0. Window tally (executions.db, 2026-10-07 00:00 → 2026-10-08 00:00 AWST): 176completed, 1failed, 1running(the nightly audit itself). 13 sessions started in the window, allsource = cron— no interactive (non-cron) sessions; 12 deliveries, 0 delivery failures. - First detect → notify → auto-resolve incident cycle since the managed-runtime event (DHL, 2026-10-07 08:00 → 11:01).
62619aa6bcb3(DHL Tracking, 5×/day) failed its 08:00 run insideensure_browser()withTimeoutError: timed out— Camofox briefly unresponsive on a browser HTTP call (dhl_tracking_monitor.py:233). The failure notice went out at 08:00:58 and incident62619a_f485ccfd4a0d(failure_type: timeout) auto-resolved at 11:01:13 when the next 3-hourly run completed; the 14:00, 17:00 and 20:00 runs also succeeded. No action needed — and the incident machinery behaved exactly as designed, which it had not been tested on since 2026-09-30. See systems/scheduled-tasks. - The tracked parcel arrived — the DHL monitor is now redundant. The 14:00 run on 2026-10-07 reported waybill
8052838382asDelivered.62619aa6bcb3still runs 5×/day for no remaining benefit; flagged as a removal candidate rather than removed. - The stocktake job proved its repin for a second day.
1a8e90ea2271completed automatically at 2026-10-07 03:00 — 346 skills / 70 categories (unchanged),raw/stocktake/freshness-20261007.txt(62 stale, 21 fresh, 7 no-date of 90 pages), committed to Gitea as8c63ef2. Two script-level findings came out of the run: (1) the Quartz rebuild step is a no-op — noquartz.config.tsis present andnpxis unavailable, so the published site is never refreshed; (2)skills-indexunder-counts by one — 347SKILL.mdfiles exist on disk while the page reports 346, because the generator de-dups the nestedproductivity/obsidian-git-sync/obsidian-git-sync/duplicate away. Both are now recorded as open issues in systems/scheduled-tasks. - Nothing else changed in the window. The three stale pre-repin
last_status: errorjobs (1b23c042e17d,fad5a86979d4,0e753e9720fd) remain — due Fri 08:00 / Mon 03:00 / 1st 09:00. Thecustom:omnistale-key references and the three bare-telegramtargets are unchanged. No new incident page was required, and no page was removed or archived.
Recent Changes (2026-10-07)
- Cron fleet green for a second consecutive day — 0 failing. Job count unchanged at 30 (27 enabled / 3 disabled) and all 30
failure_streakcounters read 0. Window tally (executions.db, 2026-10-06 00:00 → 2026-10-07 00:00 AWST): 176completed, 0failed, 1running(the nightly audit itself) — 177 rows. 14 sessions started in the window, allsource = cron; no interactive (non-cron) sessions. No new incident was opened. The repin wrap-up closures at 00:10–00:12 on 2026-10-06 fall inside this window but were already recorded by the 2026-10-06 audit. - The stocktake job proved its repin — first fully automatic run since 2026-09-25.
1a8e90ea2271(wiki-stocktake-maintenance, 03:00 daily) ran on schedule 2026-10-06 03:00:31 → 03:03:32 on its newcustom:omni-101/free-stackpin and completed cleanly. Its four HTTP-410 incidents (6df957a05ec6,d284168d3663,cda67de5b3e3,e31584909bd2) had already been closed at 00:10–00:11 on 2026-10-06 during the repin wrap-up. It regeneratedsystems/skills-index.md(344 → 346 skills), wroteraw/stocktake/freshness-20261006.txtand committed to Gitea as33f4e95. Its stale pre-repinlast_status: erroris now cleared — livelast_status: ok, streak 0. The daily manualwiki-maintain.shrun is no longer needed. See systems/scheduled-tasks. - Three jobs still carry a stale pre-repin
last_status: error—1b23c042e17d,fad5a86979d4,0e753e9720fd(down from four). Each clears on its next scheduled slot (Fri 08:00 / Mon 03:00 / 1st 09:00); none is a live failure. The bare-telegramtarget warning still stands on066bb5191280and0e753e9720fd(unchanged). - Wiki vault mirror refreshed.
systems/skills-index.mdin/home/hermes/wiki/agent-estate-wiki/had drifted to 2026-10-03 / 344 skills while the canonical copy regenerated to 2026-10-06 / 346; this audit re-mirrored it along with the pages below. The two-wiki-tree drift remains a standing open item.
Recent Changes (2026-10-06)
- Dead model pins cleared across the whole fleet — failing set 7 → 0. All seven jobs that had been failing since 2026-10-01 were repinned on 2026-10-05 23:16 → 2026-10-06 00:05. Each had been pinned to a raw model name that died upstream:
cliprox/terra(HTTP 401 connection auth, 3 jobs),ollama-cloud/qwen3.5:397b(HTTP 410, retired 2026-09-25),nvidia/deepseek-ai/deepseek-v4-flash(HTTP 400, dropped from the live catalog, 2 jobs) andcommand-code/gpt-5.6-terra(HTTP 403MODEL_NOT_IN_PLAN). They were moved tocustom:omni-101on routing aliases —free-stack×6,smart-route×1 — because the fault was raw-pin brittleness, not any one model. Everyfailure_streakinjobs.jsonnow reads 0. Three were verified by live run:79f9bb41ecf5(23:39),06a0a1c8704f(23:45) anddca8482e4f76(23:56, delivered to topic 1030 — its first success since 2026-09-25). The other four are repinned but not yet re-run, so they carry a stalelast_status: erroruntil their next scheduled slot. See incidents/2026-10-05-dead-model-pin-repin. - The
cliprox/terraconnection incident is closed for cron purposes. No enabled job references that pin any more — the jobs were moved off it rather than the proxy connection being re-authenticated. See incidents/2026-10-01-cliproxy-connection-auth-expired. GitHub Trending Radar's revoked-token diagnosis is refuted.SUPERSEDED 2026-10-13 — this conclusion was WRONG.c0a9fa314542ran on schedule at 2026-10-05 09:00 and completed cleanly — a second consecutive success after the off-schedule 2026-09-30 19:22 run. NogetMe→ 401, and no BotFather token replacement is needed. The previous audit correctly refused to treat the claim as standing fact; it can now be retired.- A stale failure notice, not a live outage, opened the review. Anthony acted on a
85edf6772bcanotice that had been sitting in topic346since the 2026-09-29 07:00 run. That job succeeded on every run from 2026-09-30 17:53 onward, and its three incidents were resolved on 2026-09-30 17:55:13; the notice read as current only because its wording matches the live 2026-09-28 managed-runtime incident. Checkexecutions.started_atand thecron_incidentsstate before acting on a notice. - Window tally (
executions.db, 2026-10-05 00:00 → 2026-10-06 00:15 AWST): 185completed, 3failed(all pre-repin, 03:00–07:00), 2unknown(aborted first attempts of79f9bb41ecf5/dca8482e4f76, superseded by their successful re-runs) and 1running(the nightly audit itself). No interactive sessions other than the repin session.
Recent Changes (2026-10-05)
- Cron fleet re-verified 2026-10-05 00:01 AWST — failing set 6 → 7. Job count unchanged at 30 (27 enabled / 3 disabled). The one new failure event in the audit window is
79f9bb41ecf5(Weekly Review, Sun 18:00), which ran on schedule 2026-10-04 18:00 and failed with the identicalcliprox/terraerror the incident predicted:HTTP 401: [openai-compatible-chat-2ea20f63-…] All 1 connection(s) authentication expired — please reconnect in the dashboard. That is the last untested job on the pin, so the provider-connection auth expiry is now 3 of 3 confirmed — settled as a credential fault, not per-job. No review was produced;delivery_outcome: deliveredagain because the failure notice is the deliverable. See incidents/2026-10-01-cliproxy-connection-auth-expired. 1a8e90ea2271failed again — 2026-10-04 03:00 (HTTP 410). Thewiki-stocktake-maintenancejob remains pinned to the Ollama-retiredqwen3.5:397b; no change, still needs a repin. Its script is healthy. See systems/scheduled-tasks.- No interactive (non-cron) sessions in the window — all 10 sessions active in the past 24h were cron. The only durable changes are cron-fleet status, reflected above.
- Streak-number caveat for future audits: the
N failures in a rowfigure inhermes cron listis thefailure_streakcounter fromjobs.json, not a DB-derived count.~/.hermes/cron/executions.dbnow retains only rows from 2026-09-30 onward (1,001 rows), so DB recounts undercount older streaks. Live counters 2026-10-05:1a8e90ea2271×11,dca8482e4f76×7,fad5a86979d4×3. Quote the live counter, and note the retention floor.
Recent Changes (2026-10-04)
- Both Hermes instances updated on 2026-10-03, from opposite directions. CT460 (production) was rebuilt to
v0.21.5+6169.gab86a20(upstreamab86a20a, tree mtime 10:11 AWST) and CT450 (chaos) came up fromv0.19.0tov0.21.5+6170.ga510d6c(upstreama510d6c6, tree mtime 10:22 AWST). Same semver token, different builds, separate state. CT450 now reportsUpdate available: 3 commits behind. CT450 has no SSH — it is reached viassh root@100.96.100.82+pct exec 450, andhermesis not on the defaultpct execPATH. See incidents/2026-10-03-ct450-hermes-update. - Vector recall had been silently running keyword-only — found and fixed 2026-10-03.
fastembedwas missing from every uv-managed runtime, so the dense leg ofmnemosyne_recallcontributed no candidates and recall fell back to FTS5 without erroring. Fixed the same day: fastembed 0.8.1 installed into the bootstrap-selected runtime,FASTEMBED_CACHE_PATHpinned, andhermes-runtime-deps-guard.shextended to assert fastembed + cache path + model dir every 15 min. Live coverage 2026-10-04: working 726/752 (96.5%), episodic 1033/1039 (99.4%), 13 embeddings generated in the previous 24h. The previous "coverage gap" entry (159/1,476) is retired — it was resolved by the 2026-08-02 reindex. See incidents/2026-10-03-mnemosyne-vector-recall-fts-only and systems/mnemosyne. - Managed runtimes pruned 10 → 3. Only 3 uv-managed venvs remain under
~/.hermes/installs/019d0d114d22b7e6/environments/(two created 2026-10-03 09:59/10:00, one surviving from 2026-09-28). Any note that says "ten managed venvs" is stale. - Cron fleet re-verified 2026-10-04 00:12 AWST: 30 jobs (27 enabled / 3 disabled), failing set unchanged at 6, no new failure inside the window.
79f9bb41ecf5— the last untestedcliprox/terrajob — is due 2026-10-04 18:00 AWST. See systems/scheduled-tasks. - Mattermost is unreachable from CT460 right now (
mattermost connect timed out after 30s, next retry in 300s, every 5 min, live 2026-10-04). Host-side condition; Mattermost delivery should be treated as down until probed. - Wiki maintenance gotcha worth remembering:
mnemosyne doctorruns under the legacy Python 3.11venv/, wheresqlite_vecis not importable, so it printsvec0: present_but_unloadableand marks vector tiersunavailableeven when the gateway is embedding fine. Judge vector health withcheck_embedding_coverage.py, never with doctor'svec0line.
Recent Changes (2026-10-03)
- Cron fleet re-verified: 30 jobs, 27 enabled / 3 disabled (live
~/.hermes/cron/jobs.json). Failing set stays at 6, but the composition changed:1b23c042e17d(Enhanced Weekend Adventure Planner, Fri 08:00) failed on 2026-10-02 with the identical HTTP 401 the cliprox incident predicted —HTTP 401: [openai-compatible-chat-2ea20f63-…] All 1 connection(s) authentication expired — please reconnect in the dashboard. That makes 2 of the 3cliprox/terrajobs confirmed broken, so the provider-connection auth expiry is a real credential fault, not a one-job fluke.79f9bb41ecf5(Weekly Review, Sun 18:00) is the last untested one — its only run (2026-09-27) predates the expiry and succeeded; next due 2026-10-04 18:00. See incidents/2026-10-01-cliproxy-connection-auth-expired. - Streaks recounted from
executions.db— one number corrected:dca8482e4f766 → 7 (one more daily run), but1a8e90ea22718 → 7 — the ×8 carried since 2026-10-01 was an overcount; that job has exactly 7 recorded runs and all 7 failed. Recount before quoting a streak. - A delivered notice is not a successful job. Both
cliprox/terrafailures are recordeddelivery_outcome: deliveredbecause the failure notice is itself a deliverable — the executionstatusisfailedand no digest/plan was produced. Judge cron health on thestatuscolumn, not the delivery outcome. - Resolved —
1b23c042e17dstaledelivery_failedflag cleared: the 2026-09-30 retarget totelegram:-1004321904721:102worked exactly as predicted; its 2026-10-02 run delivered (then failed on the model pin). The prediction held. - systems/skills-index regenerated by hand: 341 → 344 skills. The daily stocktake job (
1a8e90ea2271) is still blocked on a retired model (HTTP 410,qwen3.5:397b), but its script is healthy —wiki-maintain.shwas run manually on 2026-10-03 and completed cleanly, refreshing the index and writingraw/stocktake/freshness-20261003.txt. One new skill appeared:fleet-wide-failure-triage(devops). Only the scheduled wrapper is broken; every non-model step of the stocktake now needs a manual run each day until it is repinned. - Work mailbox blocker documented — and it is older than it looks. A new incident page records that the
workOutlook account has been unreachable since 2026-08-26, not this week: the account uses password auth while the tenant advertises onlyXOAuth2, sohimalaya -a workdies withlogin not supported. The TCP/TLS path is fine — it is a tenant policy wall, not a bad password, and re-running the credential helper can never fix it. It needs an OAuth2 path. No cron job polls that mailbox, so this is an on-demand capability gap. See incidents/2026-08-26-work-outlook-basic-auth-disabled. - GitHub Trending Radar token claim downgraded to "unverified": the revoked-bot-token (
getMe→ 401) diagnosis could not be reproduced —c0a9fa314542's last recorded run (2026-09-30 19:22, off-schedule) completed and delivered. Re-confirm at the next scheduled run (Mon 2026-10-05 09:00) before acting on it.
Recent Changes (2026-10-02)
- Cron fleet re-verified: 30 jobs, 27 enabled / 3 disabled (live
~/.hermes/cron/jobs.json). Failing set 3 → 6: two new failures landed on 2026-10-01 —06a0a1c8704f(AI Newsletter Curation for Patrick, Thu 10:00) —HTTP 401 … All 1 connection(s) authentication expired — please reconnect in the dashboardon providercustom:Omniroute:20128, modelcliprox/terra. Its failure notice reached topic 346; no digest was produced. Not self-recovering — needs the OmniRoute connection re-authenticated. Two other enabled jobs share that pin (1b23c042e17d,79f9bb41ecf5) and will fail next run.0e753e9720fd(Facebook Birthday Monthly Scrape, 09:00) —HTTP 400,nvidia/deepseek-ai/deepseek-v4-flashabsent from the active NVIDIA catalog, confirming the earlier diagnosis that this is a shared-pin problem (siblingfad5a86979d4uses the same model).066bb5191280(Uber Eats Monthly Spend Report, 02:11) — report generated correctly; delivery failed withconfigured thread_id 34795 for telegram:1793951355 was not found.
- Carried-over failures, streaks advanced:
dca8482e4f76403MODEL_NOT_IN_PLAN→ streak 6;1a8e90ea2271HTTP 410 (retiredqwen3.5:397b) → streak 8;fad5a86979d4HTTP 400 → streak 3. All three still need a model repin. - Telegram delivery semantics corrected — a "failed" delivery is not always a lost message. Against
~/.hermes/cron/executions.db, the 2026-10-01 failures carry the fallback variant:configured thread_id <n> for telegram:<dm> was not found; delivered without thread_id. Content reaches the DM, yet the run is recordeddelivery_outcome: failed. The 2026-09-30 incident'sMessage thread not foundvariant is the one that truly loses the message. Both variants are now documented in systems/messaging-integrations. - The wiki has two trees, and they have drifted in both directions (new finding, 2026-10-02): the canonical source is
/home/hermes/workspace/agent-estate-wiki— it holds the Gitea remote (Anthony/agent-estate-wiki), the Quartz build (serve.py,package.json,public/) and is whatwiki-maintain.shcommits./home/hermes/wiki/agent-estate-wikiis the Obsidian/Ignis vault copy (pages nested underwiki/, no git remote) that the iPad reads. The nightly audit is told to write to the vault path, so edits that skip the canonical tree never reach Gitea or the published site. Worse, the trees have diverged backwards too:systems/ignis.md,systems/nextcloud.mdand threeincidents/pages exist only in the vault, whileraw/stocktake/*,incidents/2026-09-02-sftpgo-outage.md,reports/communities-wa-social-media-audit-2026.mdandagents/exist only in canonical.index.mdin canonical links[[systems/ignis]]and[[systems/nextcloud]], both of which are broken there. Any one-way sync will silently delete pages — reconcile before trusting either tree. See systems/scheduled-tasks. - Skills inventory: 344
SKILL.mdunder~/.hermes/skills/(live count 2026-10-02), against 341 in the last generated systems/skills-index (2026-09-27). The page cannot refresh while the stocktake job stays broken.
Recent Changes (2026-10-01)
- Cron fleet re-verified: 30 jobs, 27 enabled / 3 disabled (live
~/.hermes/cron/jobs.json). Failing set 4 → 3:cbfe434a3b5ereturned tookas predicted on 2026-09-30. The residual1a8e90ea2271dispatch error also cleared — its current failure is a different, upstream problem (below). - Telegram delivery failures root-caused and fixed: the target, not the topic, was wrong — a bare
deliver: "telegram"resolves to the home DM (1793951355), where group topic IDs cannot exist, so sends hard-failed and the message was lost.1b23c042e17dandc8d52904e1d6retargeted totelegram:-1004321904721:102and verified. Three jobs still carry baretelegramtargets (0e753e9720fd,fad5a86979d4,066bb5191280). See systems/messaging-integrations. - Three jobs pinned to models that no longer exist upstream — cannot self-recover:
1a8e90ea2271→qwen3.5:397bretired by Ollama 2026-09-25 (HTTP 410, streak 7; daily 03:00 wiki stocktake is consequently not running);dca8482e4f76→gpt-5.6-terraplan-gated (403MODEL_NOT_IN_PLAN, streak 5);fad5a86979d4→nvidia/…/deepseek-v4-flashabsent from the live catalog (HTTP 400, streak 3). Repin to thesmart-routealias. See systems/model-providers. - GitHub Trending Radar — revoked Telegram bot token:
c0a9fa314542builds its digest then fails the push (getMe→ 401). Token in/home/hermes/workspace/github-trending-radar/config.jsonneeds replacing from @BotFather. - Memory hygiene pass (2026-09-30): 36 gateway background-process notifications had been written into Mnemosyne as
[USER] [Anthony Martin]memories — i.e. machine status text surfacing as the user's own words. Rows purged; canonical factshermes_cron_model_defaultand the job-radar model corrected. See systems/mnemosyne. - Provider stack rebuilt from live config: 5 custom providers (
omni-101,Omniroute:20128,litellm,command-code,guacano). The provider keycustom:omnino longer exists; two cron jobs (e530c89f2be0,d40085da631c) still name it but have not failed, because the defaultcustomblock resolves to the same base URL. - Vision routing — request recorded, not applied: Anthony asked on 2026-09-30 that vision calls use the local Ollama at
http://anthonys-mac-mini:11434(gemma4). Live config still points atnous / stepfun/step-3.7-flash:freeas at 2026-10-01.
Recent Changes (2026-09-30)
- Managed-runtime dependency failure — cron fleet down (2026-09-28 → 30), resolved 19:13 AWST: Jobs failed with
Restart-safe cron worker dispatch failed … external worker exited before ownership acknowledgement (exit 1). Real cause: the uv-managed runtime venvs (10 under~/.hermes/installs/019d0d114d22b7e6/environments/*/venv) were missingdotenvandmnemosyne, so the worker died on import before acknowledging the job (ModuleNotFoundError: No module named 'dotenv'— 459 occurrences in worker stderr). Mnemosyne Watchdog failed 176 consecutive runs. Fixed byhermes-runtime-deps-guard.shv2 (checks/repairs all managed venvs viapip install --target), run every 15 min by job96eb95ce12f2.weekly-save-restricted-bot-restartscript restored 19:17; that job isokagain. See incidents/2026-09-28-hermes-managed-runtime-deps. - Hermes upgraded since last audit: v0.19.0 (2026.7.20) → v0.21.5+3837.gbfda74c (2026.9.24), upstream
27062c34, update available. Skills 330 → 341. - Provider routing drift: default provider is
custom→http://100.78.63.20:20128(OmniRoute) with default modelsmart-route; auxiliary curatoropenai-codex / gpt-5.6-terra. Verified live 2026-09-30. - Open — Daily Marketing Job Radar blocked: job
dca8482e4f76pinned tocustom:omni-101/gpt-5.6-terra; upstreamcommand-codereturns403 MODEL_NOT_IN_PLAN. 5 consecutive failures (2026-09-26 → 30). See runbooks/job-radar. - Open — Telegram thread delivery failures (root cause found 2026-10-01):
telegram:1793951355thread34795"not found" for jobsfad5a86979d4and1b23c042e17d;c8d52904e1d6reports "Message thread not found". Cause was the delivery target, not the topic — a baretelegramresolves to the home DM. Fixed for two of the three jobs on 2026-09-30; see the 2026-10-01 entry above. - Wiki tree structure confirmed (drift unresolved):
/home/hermes/workspace/agent-estate-wikiis the Gitea/Quartz source (this repo);/home/hermes/wiki/agent-estate-wikiis the Obsidian/Ignis vault (pages underwiki/, no remote). Content is mirrored by hand — the nightly stocktake only maintains this tree. - Multi-bot group chat question raised: Anthony asked whether other estate Hermes instances can share a group chat. Preferred shape is a Telegram supergroup with one forum topic per bot (Mattermost rejected). Design question only — nothing deployed.
Recent Changes (2026-09-02)
- SFTPGo outage resolved (02:18 AWST): Dashboard flagged "service down". CT299 swap fully exhausted (43Gi used, 100%); CT299's
tailscaledhad died, breaking tailnet reachability; PVE'spct startthen failed because 5 stalelxc-attachprobes from earlier diagnostics pinned CT299's cgroup (/sys/fs/cgroup/lxc/299/ns/.lxc). Killed those PIDs (3037951/3334928/3352203/3402511/4004148),pct stop 299 --skiplock+pct start 299, fresh PID 3471141, tailscaled reconnected direct. Verified end-to-end:tailscale ping sftpgo→ direct 192.168.178.92:41641, SFTPGo WebAdmin HTTP 401, SFTP bannerSSH-2.0-SFTPGo_2.7.0. See incidents/2026-09-02-sftpgo-outage.
Attested facts
- Config version:
_config_version: 46— Verified,~/.hermes/config.yaml, 2026-09-30 (previously recorded as 33 on 2026-07-25) - Default profile:
default— Verified, WebUI prompt, 2026-07-22 - Timezone:
Australia/Perth— User-provided + Verified in config, 2026-07-22 - Main provider:
custom→http://100.78.63.20:20128(OmniRoute) — Verified,~/.hermes/config.yaml, 2026-09-30 (previouslycustom:litellm→litellm:4000, thencustom:omni→omni.kangaroo-eel.ts.net) - Default model:
smart-route— Verified,~/.hermes/config.yaml, 2026-09-30 (previouslyfreellmapi-auto) - Fallback providers:
opencode-go / mimo-v2.5,opencode-zen / deepseek-v4-flash-free,nous / stepfun/step-3.7-flash:free,ollama-cloud / qwen3.5:397b,kilocode / poolside/laguna-m.1:free,custom / litellm:4000— Verified, config, 2026-09-30 - Auxiliary curator model:
openai-codex / gpt-5.6-terra— Verified, config, 2026-09-30 - Memory backend: Mnemosyne — Verified, config, 2026-07-22
- Memory enabled: true — Verified, config, 2026-07-22
- Streaming enabled: true — Verified, config, 2026-07-22
- Dashboard public URL:
https://hermes.martinwa.org/— Verified, config, 2026-07-22 - Pet config: enabled/slug null — Verified, config, 2026-07-22
- WebUI connected platforms: local, api_server, discord, email, homeassistant, mattermost, ntfy, slack, telegram, webhook — Verified, WebUI session, 2026-07-22
Recent Changes (2026-08-02)
- Browser backend reverted: Camoufox restored as primary on 2026-07-30. Steel Browser (CT201) experiment ended — CDP issues + DeepSeek 0731 tool name validation.
browser.cloud_provider: camofox,camera_provider: camofox. Steel plugin disabled (the 2026-08-02 state — the plugin and the Steel deployments were later removed entirely on 2026-10-29, see systems/browser-backend). See comparisons/steel-vs-camoufox and decisions/rollback-steel-to-camofox. - Mnemosyne capture fix (2026-08-01): Automatic conversational capture was broken by stringified YAML (
sync_roles: "['user']"). Fixed by rewriting structured Mnemosyne settings with native YAML types. See incidents/2026-08-01-mnemosyne-capture-failure. - Mnemosyne vector coverage gap discovered: Only 159/1,476 working memories (10.8%) have vector embeddings. 0/458 episodic memories have embeddings. Semantic search is mostly FTS5 fallback.
- DeepSeek V4 Flash 0731: Post-training bump, same model ID, same pricing. Terminal Bench 2.1: 82.7 (up from 61.8). Stricter tool name validation (
^[a-zA-Z0-9_-]+$) — may cause issues with OmniRoute-transformed tool names. - Uber Eats report upgraded: Now uses Camofox authenticated session (not stale cookies.txt). HTML + wiki report generated. Cron job updated with
camofox-browser-automation+browser-backend-verificationskills. - GitHub Trending Radar — Daily Digest removed: Stopped by user on 2026-08-02. Weekly roundup still active.
- Ops profile renamed: Tembo → Tusk. All SOUL.md, skill references, and memory entries updated.
- Wiki audit cron job created: Runs nightly at 23:59 AWST — reviews past 24h of conversation for wiki changes.
- Ops profile Mnemosyne enabled: Mnemosyne plugin enabled on ops profile with
profile_isolation: true— Tusk gets its own memory bank, separate from default (Rhino). Zero cross-contamination. Verified end-to-end 2026-08-02. Config:~/.hermes/profiles/ops/config.yaml(memory.mnemosyne.profile_isolation: true,allow_tool_override: false). - OmniRoute free-DeepSeek silent-stop mitigation (2026-08-04): Free-DeepSeek upstreams returning empty-after-tool responses since Aug 1 → silent turn stops on
deepseek-flash-freeandsmart-route/good-freeacross both instances. Reworked both combos: strategypriority→fill-first, dropped proven culprits (238d5978/deepseek-v4-flash+-0731,nvidiadeepseek), healthy free models promoted, deepseek demoted to last resort. See incidents/2026-08-04-omniroute-free-deepseek-silent-stops. - OmniRoute three-layer fix (2026-08-07): npm package
.envoverride (ENABLE_SOCKS5_PROXY=true re-installed by npm update), dead nanobot provider connection (CT333 DOWN), PVE host load leaking into CT600 via nesting=1. First-request-after-cache-expiry stall documented. See systems/omniroute. - Nanobot status degraded (2026-08-07): CT333 nanobot confirmed DOWN — connection refused on 8900. OmniRoute provider connection disabled. See systems/nanobot.
- CT460 memory bumped (2026-08-07): 5096MB → 14GB RAM. Was causing swap thrashing at load 8+.
Recent Changes (2026-08-08)
- Cron job model repinning: 3 jobs repinned from dead
freeapi/minimax-m2.7→smart-route(IDs:c8d52904e1d6,1b23c042e17d,d40085da631c). Mosquito Tracker repinned from deadfreeapi/auto→smart-route(ID:1b31187397a5). 9 stale-named cron jobs (e.g.vertex/gemini-2.5-flash,gpt-5.6-terra,deepseek-v4-flash-free) repinned tosmart-route. Daily Marketing Job Radar swapped togpt-5.6-terra. - Hermes UI vite config revert: Vite config had been changed to HTTPS with self-signed certs (~16:00 Aug 8), breaking iPad access (plain HTTP → HTTPS-only without trusted cert). Reverted to pre-HTTPS config, restarted
hermes-ui.service. Production build now serves/ui/path correctly with relative asset paths.hermes-desktop.martinwa.orgidentified as separate Cloudflare infrastructure (likely on CT450), not fixable from CT460. - Phase One estate review completed: Manual cron run verified CT450's 11 duplicate publishing jobs remain paused (zero executions since Aug 1), CT460's 11 production jobs remain enabled with
last_status=ok, and CT333 Nanobot has a livejobs.jsonwith 9 jobs. The cron review report contained two inaccuracies (wrong date, false claim about CT333 having no scheduler) — verified via live system probes instead.
Recent Changes (2026-08-09)
- Portainer password reset (CT245): Admin user is
anthony(notadmin). Password was forgotten; reset viadocker run --rm -v portainer_data:/data portainer/helper-reset-passwordafter stopping the Portainer container. Verified end-to-end withPOST /api/auth→ HTTP 200 + valid JWT. Portainer now uses Tailscale/Let's Encrypt cert on:9443(see systems/homepage-dashboard). Recovery procedure: stop container → run helper image → restart → verify with auth API. - SFTPGo security review (CT299): Anthony shared SFTPGo WebAdmin PDF settings for audit. Key findings: (1) remote SFTP root path
//resolves to/— full filesystem access, (2) host fingerprints empty (low-risk on Tailscale but should be pinned for hygiene), (3) remote user isroot, (4) quota valueF1on Cloudflare-R2 virtual folder is non-standard (may be display artifact). No action taken — flagged for Anthony's review.
Recent Changes (2026-08-10)
- Cron job failures — session storage issue: Four cron jobs failed on 2026-08-10 with two distinct error patterns:
- TimeoutError (idle for 601–602s): "Daily Marketing Job Radar" (dca8482e4f76) at 07:12, "Political News Digest (Mon/Thu)" (0e519874d280) at 08:12. Jobs stuck initializing, exceeded 600s idle limit.
- RuntimeError (session storage): "Tech & AI Newsletter Digest (Analytical)" (85edf6772bca) at 07:12, "GitHub Trending Radar — Weekly Roundup" (c0a9fa314542) at 09:03. Error: "session storage could not be written (the transcript would have been lost on restart). This is often a full disk — free some space (or fix state.db permissions)."
- Root cause: Disk at 83% (11GB free on 65GB).
state.dbis 593MB. Not critically full but may be triggering write failures. Sessions.json shows only 1 active session in past 24h — session DB likely needs cleanup or WAL checkpoint. - Impact: News digests and GitHub Trending did not deliver. Job Radar did not run.
- See: systems/scheduled-tasks Known Issues section.
- OpenCode WebSocket proxy errors: Repeated "OpenCode service unavailable" errors in hermes node journal (Aug 11 00:08). Process running (PID 809564,
opencode serve), but WebSocket proxy failing to connect. Likely transient — service was available earlier in the day.
Recent Changes (2026-08-14)
- OmniRoute factory reset on CT601: Database wiped clean (0 combos, 0 providers, 0 API keys, 115 built-in auto entries). Backup at
/opt/omniroute/factory-reset-backup-20260814-225524. Providers re-added from Notion API vault: Anthropic, Google Gemini, Groq, Mistral, OpenRouter (all passed live tests). OpenAI keys tested but invalid — removed. See systems/omniroute. - Hermes default model changed:
auto/best-free→resilient-freein~/.hermes/config.yaml.auto/best-freewas misconfigured (no combo definition, routed to paidgpt-5.6-sol). - Multiple free combos broken by upstream model ID changes: OpenRouter Poolside
laguna-s-2-1:free→laguna-s-2.1:free(dash→dot); Groqllama-4-scout-17b-16e-instructretired. Affected:resilient-free,free-IA,free-stack,good-free,deepseek-flash-free,mimo-free. - Guanaco router updated: CT205
ollamacontainer — Guanaco v0.8.11 → v0.8.14. DSML tag leakage fixes (tool-call formatting no longer leaks raw syntax), dashboard performance fix. See systems/guanaco. - GPT-5.6 Luna research: Community consensus — Luna cleaner/polished; DeepSeek V4 Flash more persistent/cheaper. Provider route matters more than model name. Luna recommended for planning/review, DeepSeek for execution. See systems/model-providers.
- Hermes UI restart: Port 8787 service restarted, now properly binding 0.0.0.0 for external access. Confirmed reachable from Tailscale.
- LiteLLM routing issue identified: Hermes was previously pointed at LiteLLM (
http://litellm:4000/v1, modelfree-auto) causing 6–26s per call. OmniRouteauto/best-freetested at 265ms. Config now points at OmniRoute.
Recent Changes (2026-08-13)
- OmniRoute migrated CT600 → CT601: Provider renamed
custom:omniroute→custom:omni; base URLhttp://omniroute:20128/v1→http://omni:20128/v1. Hostomni.kangaroo-eel.ts.net(100.93.204.4, active) replacesomniroute(100.88.81.19, offline). CT600 stopped, CT601 running. DB path/var/lib/omniroute/storage.sqlite→/opt/omniroute/storage.sqlite; API key unchanged. All config (14) + cron-job (22)custom:omnirouterefs repointed tocustom:omni. Backup:~/.hermes/config.yaml.bak.omniroute-removal. See systems/omniroute. - Evening stand-down briefing weather bugfix: Weather collector returns a plain string (
+16°C Sunny), but the three dashboard widgets (evening.html,evening-grid.html,evening-briefing.html) read object fields →undefined. Added string-vs-object guards; verified served HTML no longer contains broken raw field refs.