Files
agent-estate-wiki/incidents/2026-10-09-cron-provider-timeout-storm.md
T
hermes-audit ebf57146f1 audit(2026-10-13): 10-12 clean (174/0, 3rd day) but GitHub Trending Radar token DEAD (getMe 401) - supersedes the wrong 2026-10-06 'refuted' entry
Incidents 5->2 (deepseek-v4-flash pair closed 03:05:39, Job Radar timeout 07:33:41); storm page re-tallied 11/12 closed with closure timeline.

NEW: Camofox hit its cgroup ceiling inside the 07:01 Job Radar run (2.5G, swap exhausted, 383 tasks) - containment drop-in documented; browser-backend/steel-vs-camoufox/browser-automation corrected to REST :9377 on CT460 (was :9093 on CT450).

Mnemosyne 96.7%/99.4% coverage green; 18 cron sessions, 0 interactive; retention floor 2026-10-07.
2026-10-13 00:19:15 +08:00

8.7 KiB
Raw Blame History

title, type, status, created, updated, verified_on, review_after, confidence, tags, sources
title type status created updated verified_on review_after confidence tags sources
Fleet-Wide Provider Timeout Storm — 2026-10-09 incident unresolved 2026-10-09 2026-10-13 2026-10-13 2026-10-16 high
cron
omniroute
router
timeout
incident
unresolved
cron-executions-db
cron-incidents-db
live-jobs-json
session-20261009_225935_7b1cb1

Fleet-Wide Provider Timeout Storm — 2026-10-09

Window: 2026-10-09 00:00 → 15:00 AWST (last failure 15:00; every run from 18:00 onward completed) Status: Unresolved — the storm ended and 11 of its 12 incidents are now closed; only 1b23c0_c35703f637b8 remains open, and it cannot clear before that job's next scheduled slot (Fri 2026-10-16 08:00). Nothing here is still symptomatic. Impact: 15 failed executions across 10 distinct jobs, against baselines of 1 failed on 2026-10-07 and 2 on 2026-10-08

What happened

Every failure in the window is the same shape — RuntimeError: Request timed out. — i.e. the Hermes runtime gave up waiting on the inference call. The ten affected jobs are pinned to routing aliases (smart-route, free-stack, deepseek-paid-smart) on provider custom:omni-101, whose base URL is the local OmniRoute gateway. A job pinned to its own provider+model does not fall back to the global fallback_providers chain, which is why ten unrelated jobs all failed at once instead of quietly rerouting (see incidents/2026-10-05-dead-model-pin-repin).

Timeline (2026-10-09 AWST)

Time Job Error
00:00 ea79a2107e36 (Mnemosyne Health Monitor) RuntimeError: Request timed out.
00:00 b63ed5817212 (Mnemosyne Embedding Coverage Monitor) RuntimeError: Request timed out.
03:00 1a8e90ea2271 (wiki-stocktake-maintenance) RuntimeError: Request timed out.
06:00 b63ed5817212 (Mnemosyne Embedding Coverage Monitor) RuntimeError: Request timed out.
06:30 96eb95ce12f2 (Mnemosyne Watchdog) Script exited with code 1
06:45 96eb95ce12f2 (Mnemosyne Watchdog) Script exited with code 1
07:00 85edf6772bca (Tech & AI Newsletter Digest (Analytical)) RuntimeError: Request timed out.
07:00 1b31187397a5 (Mosquito Tracker) RuntimeError: Request timed out.
07:00 dca8482e4f76 (Daily Marketing Job Radar) RuntimeError: Request timed out.
08:00 1b23c042e17d (Enhanced Weekend Adventure Planner) RuntimeError: Request timed out.
08:30 08eb86f02d37 (Gmail Action Digest) RuntimeError: Request timed out.
12:00 ecc1fc13655a (FreshRSS Midday News Briefing) RuntimeError: Request timed out.
12:00 ea79a2107e36 (Mnemosyne Health Monitor) RuntimeError: Request timed out.
12:00 b63ed5817212 (Mnemosyne Embedding Coverage Monitor) RuntimeError: Request timed out.
15:00 1b31187397a5 (Mosquito Tracker) RuntimeError: Request timed out.
23:59 cbfe434a3b5e (Wiki Audit — Nightly) (no error text recorded)

The 16 failed executions cover 11 distinct jobs:

Job Failures Note
b63ed5817212 (Mnemosyne Embedding Coverage Monitor) 3 provider timeout
ea79a2107e36 (Mnemosyne Health Monitor) 2 provider timeout
96eb95ce12f2 (Mnemosyne Watchdog) 2 cascade — watchdog, not victim
1b31187397a5 (Mosquito Tracker) 2 provider timeout
1a8e90ea2271 (wiki-stocktake-maintenance) 1 provider timeout
85edf6772bca (Tech & AI Newsletter Digest (Analytical)) 1 provider timeout
dca8482e4f76 (Daily Marketing Job Radar) 1 provider timeout
1b23c042e17d (Enhanced Weekend Adventure Planner) 1 provider timeout
08eb86f02d37 (Gmail Action Digest) 1 provider timeout
ecc1fc13655a (FreshRSS Midday News Briefing) 1 provider timeout
cbfe434a3b5e (Wiki Audit — Nightly) 1 provider timeout

Not established: whether the trigger was OmniRoute saturation, an upstream provider outage, or the runtime's own timeout budget. A late-evening probe of the gateway (from a different host alias, not from inside the storm window) failed to connect outright (HTTP 000) — corroborating intermittent reachability, but recorded here as an observation, not a root cause.

Recovery

Every run from 18:00 onward completed, and four incidents auto-closed on the next clean run: 96eb95_acb3ae5ec223 07:01, b63ed5_f2c93dd24181 18:01, 1b3118_f49c8d2c6e7f 22:05, and ea79a2_6fb70b032305 at 2026-10-10 00:03:44 (the first post-window run). The gateway was therefore serving normally again well before the window closed.

Incidents

Incident Job State Failure type First seen Closed
1a8e90_789224ad589c 1a8e90ea2271 (wiki-stocktake-maintenance) resolved unknown 2026-10-08 03:01 2026-10-10 03:06
ea79a2_6fb70b032305 ea79a2107e36 (Mnemosyne Health Monitor) resolved timeout 2026-10-09 00:18 2026-10-10 00:03
b63ed5_f2c93dd24181 b63ed5817212 (Mnemosyne Embedding Coverage Monitor) resolved timeout 2026-10-09 00:18 2026-10-09 18:01
cbfe43_fa81052baaf7 cbfe434a3b5e (Wiki Audit — Nightly) resolved timeout 2026-10-09 00:32 2026-10-10 00:27
1a8e90_dc6b2d40ec44 1a8e90ea2271 (wiki-stocktake-maintenance) resolved timeout 2026-10-09 03:17 2026-10-10 03:06
96eb95_acb3ae5ec223 96eb95ce12f2 (Mnemosyne Watchdog) resolved timeout 2026-10-09 06:30 2026-10-09 07:01
dca848_23fcd2b18aaa dca8482e4f76 (Daily Marketing Job Radar) resolved timeout 2026-10-09 07:18 2026-10-12 07:33
1b3118_f49c8d2c6e7f 1b31187397a5 (Mosquito Tracker) resolved timeout 2026-10-09 07:18 2026-10-09 22:05
85edf6_18bedbeec5cd 85edf6772bca (Tech & AI Newsletter Digest (Analytical)) resolved timeout 2026-10-09 07:18 2026-10-10 07:04
1b23c0_c35703f637b8 1b23c042e17d (Enhanced Weekend Adventure Planner) alerted — still open timeout 2026-10-09 08:17 — (next slot Fri 2026-10-16 08:00)
08eb86_634f1a296f78 08eb86f02d37 (Gmail Action Digest) resolved timeout 2026-10-09 08:48 2026-10-10 08:32
ecc1fc_58b6c38296f3 ecc1fc13655a (FreshRSS Midday News Briefing) resolved timeout 2026-10-09 12:21 2026-10-10 12:05

Closure timeline (re-read 2026-10-13): four closed inside the storm window itself (2026-10-09 07:01 → 22:05); five more closed on 2026-10-10 (00:03, 00:27, 03:06 ×2, 07:04, 08:32, 12:05); the in-window dca848_23fcd2b18aaa — the last one to hold out — only cleared on 2026-10-12 07:33:41, nine seconds before its own job's 07:00 run finished successfully. That is the pattern worth remembering: each incident clears on the next successful scheduled run of its own job, so a weekly job carries its incident for up to a week after the underlying fault is gone. 1b23c042e17d is the remaining example — its fault is long gone, but the row cannot close until Friday.

Why it reached Anthony

b63ed5817212 (Embedding Coverage, every 6h) failed three consecutive runs (00:00, 06:00, 12:00) while pinned to its own provider/model, so the framework's "failed N runs in a row — it does not fall back" notice was delivered; Anthony replied to it at 20:26 on 2026-10-09. That same exchange is where the DHL-monitor retirement was requested (see systems/scheduled-tasks, open item #1).

The watchdog cascade

96eb95ce12f2 (Mnemosyne Watchdog) failed twice at 06:30 and 06:45 with Script exited with code 1 — 🚨 Log ERROR in agent.log, which is the watchdog reporting the storm rather than suffering it. Read its failures as a symptom, not as two more victims.

Evidence (how to re-check)

sqlite3 ~/.hermes/cron/executions.db \
  "SELECT status,count(*) FROM executions
   WHERE substr(datetime(started_at,'+8 hours'),1,10)='2026-10-09' GROUP BY 1"
# today's read: completed 162 | failed 15 | running 1

sqlite3 ~/.hermes/cron/executions.db \
  "SELECT job_id,started_at,substr(error,1,60) FROM executions
   WHERE status!='completed' AND substr(datetime(started_at,'+8 hours'),1,10)='2026-10-09'"

sqlite3 ~/.hermes/cron/executions.db \
  "SELECT id,job_id,state,first_seen_at,closed_at FROM cron_incidents WHERE closed_at IS NULL"

Baselines read the same way: 2026-10-07 → {'completed': 177, 'failed': 1}, 2026-10-08 → {'completed': 178, 'failed': 2}.