2.4 KiB
title, type, status, created, updated, review_after, verified_on, confidence, tags, sources
| title | type | status | created | updated | review_after | verified_on | confidence | tags | sources | |||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Keep OpenRouter as fallback | decision | active | 2026-07-22 | 2026-10-20 | 2026-10-20 | 2026-10-20 | high |
|
Keep OpenRouter as fallback
Decision
OpenRouter must remain available as a fallback provider, even if a self-hosted router becomes primary.
Reasons
- Free models are important.
- Broad model coverage.
- Previous migrations disrupted provider availability.
- A fallback reduces the chance of Hermes becoming unusable.
Alternatives considered
- Direct providers only
- OmniRoute exclusively
- Local models exclusively
Revisit when
A self-hosted router has operated reliably for at least 30 days.
Revisit trigger MET (verified 2026-10-20). OmniRoute has been the primary router for well over 30 days —
custom:omni-101is the pin on effectively every model-calling cron job, andOmniroute:20128is a second live OmniRoute endpoint. The estate has no standalone OpenRouter provider:custom_providersin~/.hermes/config.yamlholds onlylitellm,guacano,Omniroute:20128,command-codeandomni-101(see systems/openrouter).But the fallback is now provided through OmniRoute rather than alongside it — OpenRouter-style slugs (
openrouter/auto,freeapi/openrouterfree,or-openrouter-fusion, …) are present in the OmniRoute catalog, so OpenRouter capacity remains reachable without a separate Hermes provider.Status: decision still
active, but the mechanism it protects has changed. The intent (OpenRouter capacity must remain reachable as a fallback) is satisfied via the OmniRoute catalog. The literal reading — a standalone OpenRouter provider incustom_providers— is not satisfied and has not been since at least 2026-07-22. This needs a re-affirmation or a rewrite of the decision text; it should not simply be left to drift on a 30-day timer.Related context: OmniRoute has also been the source of repeated fleet-wide failures — the 2026-10-14 connection-refused storm, the 2026-10-16/17 and 2026-10-19 resource-pressure 503 bursts, and the 2026-10-18 degenerate-stream delivery. A single-node fallback posture carries that concentration risk with it.