feat(inference): add Nemotron 3 Nano Omni to CLOUD_MODEL_OPTIONS

Adds `nvidia/nemotron-3-nano-omni-reasoning-30b-a3b` to the curated
cloud model picker and its matching test entry. Super 120B remains
the default.

Motivation: the multimodal hermes-omni-demo cookbook in
brevdev/nemoclaw-demos currently has to do a post-onboard
`openshell inference set` to switch the gateway from Super to Omni,
because the wizard only exposes Super. Adding Omni here lets users
select it during `nemoclaw onboard` directly and lets cookbooks drop
the manual swap step.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

Author: PicoNVIDIA

src/lib/inference-config.test.ts

@@ -20,6 +20,7 @@ describe("inference selection config", () => {
   it("exposes the curated cloud model picker options", () => {
     expect(CLOUD_MODEL_OPTIONS.map((option: { id: string }) => option.id)).toEqual([
       "nvidia/nemotron-3-super-120b-a12b",
+      "nvidia/nemotron-3-nano-omni-reasoning-30b-a3b",
       "moonshotai/kimi-k2.5",
       "z-ai/glm5",
       "minimaxai/minimax-m2.5",

src/lib/inference-config.ts

@@ -12,6 +12,7 @@ export const INFERENCE_ROUTE_URL = "https://inference.local/v1";
 export const DEFAULT_CLOUD_MODEL = "nvidia/nemotron-3-super-120b-a12b";
 export const CLOUD_MODEL_OPTIONS = [
   { id: "nvidia/nemotron-3-super-120b-a12b", label: "Nemotron 3 Super 120B" },
+  { id: "nvidia/nemotron-3-nano-omni-reasoning-30b-a3b", label: "Nemotron 3 Nano Omni 30B" },
   { id: "moonshotai/kimi-k2.5", label: "Kimi K2.5" },
   { id: "z-ai/glm5", label: "GLM-5" },
   { id: "minimaxai/minimax-m2.5", label: "MiniMax M2.5" },