3.4 KiB
3.4 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 | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Degenerate Model Stream Delivered a Canned Non-Answer — FreshRSS Midday Briefing | incident | active | 2026-10-18 | 2026-10-19 | 2026-10-19 | 2026-10-25 | high |
|
|
Degenerate Model Stream Delivered a Canned Non-Answer — FreshRSS Midday Briefing (2026-10-18)
What happened
The 2026-10-18 12:00 slot of FreshRSS Midday News Briefing (ecc1fc13655a, 0 12 * * *,
delivery telegram:-1004321904721:346, pin custom:omni-101 / smart-route) delivered a
placeholder sentence to Telegram instead of the midday briefing, then failed.
The delivered message, stored verbatim as the run's assistant output:
Your request was not processed. Send it again if you still want me to carry it out.
Timeline (AWST; executions.db row c53b69ce19e24d888635b38b7552d200)
| Time | Event |
|---|---|
| 12:00:56 | run claimed |
| 12:01:11 | run started |
| 12:08:11 | progress_at — canned reply written and delivered (delivery_outcome: delivered) |
| 12:08:22 | incident ecc1fc_21a72aa11cc4 opened — state alerted, failure_type: agent |
| 12:08:25 | run ended failed — RuntimeError: Model output entered a repetition loop and the stream was cut mid-loop; discarding the degenerate response. |
Impact
- The user-visible Sunday midday news briefing for 2026-10-18 was replaced by a non-answer. The run's own incident alert fired, but the Telegram message that arrived did not read as a failure — it read as a terse prompt. A delivered message is not evidence of delivered content.
last_status: error,failure_streak: 1; the row clears on the job's next clean slot (2026-10-19 12:00).- The 2026-10-18 18:01
79f9bb41ecf5weekly review run correctly listed it (“Oct 18 (today): FreshRSS Midday News Briefing — repetition loop, stream cut”), so the failure was visible in the weekly health summary even though the delivered message was not.
Cause and open questions
- Confirmed: the model stream hit a repetition loop; Hermes's degenerate-stream guard cut the stream, discarded the response, and substituted a canned “not processed” line — which was then delivered on the job's normal route before the run aborted.
- Only recorded instance in the retained logs: the string
repetition loopappears inagent.log*only on 2026-10-18 (2 lines: the guard message and the cron error). Log retention is short, so this is “first recorded”, not “first occurrence”. - Open: should the guard suppress delivery (or re-queue the run) instead of delivering a non-answer under the job's delivery route? To a reader scanning a digest topic, a canned sentence is indistinguishable from content.
- Open: whether the repetition loop is a model/provider-quality symptom. The job rides the same
custom:omni-101alias family that produced the 2026-10-14 → 10-15 connection-refused storm and the 2026-10-16 → 10-17 resource-pressure 503 burst. Single-node topology unchanged.
Related
- systems/scheduled-tasks
- incidents/2026-10-16-omniroute-503-resource-pressure
- incidents/2026-10-14-omniroute-node-connection-refused-storm
No secrets recorded; job IDs, incident IDs, timestamps and status codes only.