fix(models): hide unsupported Gemini Live discovery (#11710)

Obrigado! Validado em lote combinado (8 PRs, release/v3.8.51):

- Follow-up correto de #10590/#10591 — omite modelos Gemini Live-only da descoberta dinâmica, preserva chat para modelos híbridos.
- Teste focado atualizado: `tests/unit/gemini-models-parser.test.ts` — 6/6 verde.
- Gates estáticos do lote OK (typecheck, lint sem regressão, complexity, cognitive, file-size, changelog-integrity).

tests/unit/gemini-models-parser.test.ts

@@ -72,14 +72,21 @@ test("parseGeminiModelsList maps generateContent image models to the chat endpoi
   assert.deepEqual(proImage!.supportedEndpoints, ["chat"]);
 });
 
-test("parseGeminiModelsList maps embedContent and bidiGenerateContent", () => {
+test("parseGeminiModelsList maps embeddings without advertising unsupported Gemini Live", () => {
   const models = parseGeminiModelsList(SAMPLE);
   assert.deepEqual(models.find((m) => m.id === "text-embedding-004")!.supportedEndpoints, [
     "embeddings",
   ]);
-  assert.deepEqual(models.find((m) => m.id === "gemini-live-2.5-flash")!.supportedEndpoints, [
-    "audio",
-  ]);
+  assert.equal(models.some((m) => m.id === "gemini-live-2.5-flash"), false);
+  const [hybrid] = parseGeminiModelsList({
+    models: [
+      {
+        name: "models/gemini-live-hybrid",
+        supportedGenerationMethods: ["generateContent", "bidiGenerateContent"],
+      },
+    ],
+  });
+  assert.deepEqual(hybrid.supportedEndpoints, ["chat"]);
 });
 
 test("parseGeminiModelsList maps Veo predictLongRunning models to the videos endpoint", () => {