Files
agent-estate-wiki/decisions/keep-openrouter-as-fallback.md
T
Hermes 341dda95dd stocktake 2026-11-11: 36 stale pages re-verified (0 stale); fallback chain rewritten 4/6 slots; CT333 'clawtest' naming claim corrected; nous 404 credits signature replaces refresh-token 401; estate shrank (VM 310 + CT601 gone)
- freshness: 36 stale / 93 fresh / 3 no-date -> 0 stale / 129 fresh / 3 no-date of 132 (same-day report regenerated after the corrections, per pattern 13)
- skills: 299 skills / 67 categories (count unchanged; generator arithmetic re-verified by hand against the live tree: 300 SKILL.md files - 1 nested duplicate = 299)
- runbooks/test-openrouter: live fallback chain rewritten (primary back to smart-route/custom:omni-101; mimo-v2.5, stepfun, qwen3.5/ollama-cloud out; guacano + kilo-reflection-beam-free in); ollama.com dropped from the URL test list; guacano/litellm noted as internal + key-gated
- comparisons/hermes-vs-nanobot: the 2026-10-20 'CT333 is zeroclaw in Proxmox naming' claim was itself wrong - pct list and hostname both return clawtest
- incidents/2026-10-22-nous: refresh-token failure gone from logs; new signature 404 insufficient_credits_for_paid_model from auxiliary.pulse_memory (ninth slot, back on nous, paid model) - open item revised
- incidents/2026-08-29-gmail: email crons now ok but root cause unfixed 74 days (himalaya message read still in fetch_newsletters.py; goimapnotify back up PID 441; monitor still paused)
- 30 further pages re-verified live and de-flagged with dated probe notes (ct207 ingress, CT205 guanaco v0.8.15, CT270 nextcloud 33.0.2.2, headless stack, hermes-ui both hosts, systemd units + cgroup limits, terminal/tool_search/mnemosyne/custom_providers config blocks, ops profile still deleted, hosts/pve guest lists)
- log.md addendum + index.md date bump; no page deleted, no secrets written
2026-11-11 03:52:48 +08:00

65 lines
3.0 KiB
Markdown

---
title: Keep OpenRouter as fallback
type: decision
status: active
created: 2026-07-22
updated: 2026-11-11
review_after: 2026-10-20 # was 0001-01-01 (bug), fixed during 2026-07-22 audit; real trigger is conditional, see Revisit when
verified_on: 2026-11-11
confidence: high
tags: [routing, provider, decision]
sources: []
---
# 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-101` is the pin on effectively every model-calling cron job, and
> `Omniroute:20128` is a second live OmniRoute endpoint. The estate has **no standalone OpenRouter
> provider**: `custom_providers` in `~/.hermes/config.yaml` holds only `litellm`, `guacano`,
> `Omniroute:20128`, `command-code` and `omni-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 in `custom_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.
> **Re-verified 2026-11-11 — the decision still needs the re-affirmation it was flagged for on
> 2026-10-20, and the position is unchanged.** `custom_providers` still holds exactly
> `litellm`, `guacano`, `Omniroute:20128`, `command-code`, `omni-101` — **no standalone
> OpenRouter provider**. OmniRoute remains the primary path (`smart-route` on
> `custom:omni-101`), so the "revisit trigger" (a self-hosted router running reliably >30 days) is
> still met and the literal reading of the decision is still unsatisfied. Nothing new to decide
> here — the page still says what needs a human call.
## Related
- [[model-routing]]
- [[systems/omniroute]]
- [[systems/openrouter]]