Files
OmniRoute/tests/unit/github-copilot-gpt-4o-mini.test.ts
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

29 lines
1.3 KiB
TypeScript

import { test } from "node:test";
import assert from "node:assert/strict";
import { getRegistryEntry } from "../../open-sse/config/providerRegistry.ts";
// Regression guard: the GitHub Copilot (`gh`) provider must expose `gpt-4o-mini`
// alongside the curated date-pinned GPT-4o model. Copilot serves the cheaper mini variant via
// chat/completions, so apps that hard-code `gpt-4o-mini` should resolve to the
// Copilot provider.
//
// Ported from upstream decolua/9router (add GPT-4o mini to GitHub Copilot).
test("github (Copilot) provider exposes gpt-4o-mini next to curated GPT-4o", () => {
const entry = getRegistryEntry("github");
assert.ok(entry, "github registry entry should exist");
assert.ok(entry.models, "github registry entry should have a models array");
const ids = entry.models!.map((m) => m.id);
assert.ok(ids.includes("gpt-4o-2024-11-20"), "date-pinned gpt-4o should remain registered");
assert.ok(
ids.includes("gpt-4o-mini"),
"gpt-4o-mini should be registered on the Copilot (gh) provider"
);
const mini = entry.models!.find((m) => m.id === "gpt-4o-mini");
assert.equal(mini?.name, "GPT-4o mini");
assert.equal(mini?.contextLength, 128000);
assert.equal(ids.includes("gpt-4o"), false, "bare gpt-4o is not in the curated list");
});