Files
OmniRoute/tests/unit/opencode-muse-spark-responses-10867.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

21 lines
992 B
TypeScript

import test from "node:test";
import assert from "node:assert/strict";
import { opencodeProvider } from "../../open-sse/config/providers/registry/opencode/index.ts";
// #10867: Muse Spark is served by OpenCode Zen only on the OpenAI Responses API
// (/responses), not /chat/completions. Without targetFormat:"openai-responses"
// these models fall through to the default chat/completions pass-through and the
// upstream returns null/empty content.
test("muse-spark-1.2 and muse-spark-1.2-contributor-free route to the Responses API", () => {
for (const id of ["muse-spark-1.2", "muse-spark-1.2-contributor-free"]) {
const model = opencodeProvider.models.find((m) => m.id === id);
assert.ok(model, `${id} should be registered in the opencode provider`);
assert.equal(
model?.targetFormat,
"openai-responses",
`${id} must target the Responses API, not the default chat/completions pass-through`
);
assert.equal(model?.supportsReasoning, true);
}
});