Files
OmniRoute/docs/OMNIROUTE_PROVIDER_FAILOVER.md
Praveen K Palaniswamy 65e81158ab fix(ollama): route models by advertised capability (#11088)
Landed with the design call resolved per the owner's pick — **option 1**: the synced store is now endpoint-agnostic (persistDiscoveredModels and managedModelImport no longer drop non-chat models at write time), and chat selectability moved to read time (auto-pool expansion in autoStrategy applies filterChatSelectableModels; the models-route projection already had its chatOnly filter). Your discovery test now passes end-to-end (3/3): /api/show capabilities persist per connection and image/embedding requests route through the advertising host.

Reconciliation notes: conflicted areas merged onto the current tip (adobe discovery import, requestedModel preflight signature, resolvedProvider fast-path coexists with the synced-route override — explicit resolution wins); carried base-red drains (#10055 memoization, #11071 test variants) dropped as already-landed; the managed-model-import exclusion test was propagated to the new contract (image/video models persist; the read filter still hides them from chat pickers — pinned by a new assertion). Full battery: 205/206 focused (the one red is a confirmed periodic-timer timing flake on the loaded devbox — 20/20 isolated), autoCombo vitest 30/30, combo suites 46/46, gates + typecheck clean.

Thank you @yourspraveen — the capability probe + routing design was right; it just needed the store contract opened up. Fixes #11087.
2026-08-23 11:45:01 -03:00

668 B

OmniRoute Provider Failover

Failures are classified before retry decisions are made.

Transient failures such as timeouts, network errors, rate limits, and provider 5xx responses may fail over. Authentication errors, permission errors, invalid requests, unavailable models, and unknown failures are not retried blindly.

The default cross-provider policy allows up to three provider attempts, retries rate limits and timeouts, and keeps administrative disablement separate from temporary circuit state.

Circuit states are closed, open, and half_open. A cooldown schedules a bounded probe; a successful probe closes the circuit and a failed probe reopens it.