test: update xai test to match corrected maxTokens for grok-4-fast

The test was expecting 30,000 maxTokens but we corrected this to 8,192 to match grok-4, as xAI doesn't publish a maximum output token limit for grok-4-fast.

Author: daniel-lxs

src/api/providers/__tests__/xai.spec.ts

@@ -77,7 +77,7 @@ describe("XAIHandler", () => {
 		expect(model.id).toBe(testModelId)
 		expect(model.info).toEqual(xaiModels[testModelId])
 		expect(model.info.contextWindow).toBe(2_000_000)
-		expect(model.info.maxTokens).toBe(30_000)
+		expect(model.info.maxTokens).toBe(8192)
 	})
 
 	it("should include reasoning_effort parameter for mini models", async () => {