feat: add Grok 4.5 model support and fix xAI reasoning format (#867)

Add grok-4.5 model definition with 500K context window, .00/.00
input/output pricing, /bin/sh.50 cache pricing, and configurable reasoning
(low/medium/high, default high). Update xaiDefaultModelId from
grok-4.20 to grok-4.5 as the new flagship model.

Fix a latent bug in the xAI handler where reasoning effort was sent in
Chat Completions format (reasoning: { reasoning_effort }) instead of
the Responses API format (reasoning: { effort }). This affected
grok-3-mini and would have broken grok-4.5's configurable reasoning.

Update tests to cover the reasoning format fix and add grok-4.5
reasoning support tests. Update e2e test primary model to grok-4.5.

Fixes #866

Author: navedmerchant

apps/vscode-e2e/src/suite/providers/xai.test.ts

@@ -12,7 +12,7 @@ const XAI_API_KEY = process.env.XAI_API_KEY
 const XAI_BASE_URL = "https://api.x.ai/v1"
 const XAI_RESPONSES_URL = `${XAI_BASE_URL}/responses`
 // Primary model for the full round-trip test (completion-text assertion included).
-const XAI_MODEL_ID = "grok-4.20"
+const XAI_MODEL_ID = "grok-4.5"
 // Fast variants: tested for API parameter contract only.  They consistently call
 // attempt_completion with an empty result field after a no-tool-error recovery
 // loop, so they cannot satisfy the completion-text assertion at this time.
@@ -492,7 +492,7 @@ suite("xAI provider", function () {
 				const readCallId = modelFixture?.readCallId ?? "call_xai_read_001"
 
 				if (request.functionCallOutputIds.some((id) => id === readCallId)) {
-					// Use recorded turn2 when it contains a function_call (grok-4.20).
+					// Use recorded turn2 when it contains a function_call (grok-4.5).
 					// Fast models return plain text in turn2 — hand-craft attempt_completion
 					// so the task can reach completion.
 					const turn2HasFunctionCall = (modelFixture?.turn2 as ResponsesStreamEvent[] | undefined)?.some(

packages/types/src/providers/xai.ts

@@ -3,9 +3,25 @@ import type { ModelInfo } from "../model.js"
 // https://docs.x.ai/docs/api-reference
 export type XAIModelId = keyof typeof xaiModels
 
-export const xaiDefaultModelId: XAIModelId = "grok-4.20"
+export const xaiDefaultModelId: XAIModelId = "grok-4.5"
 
 export const xaiModels = {
+	"grok-4.5": {
+		maxTokens: 65_536,
+		contextWindow: 500_000,
+		supportsImages: true,
+		supportsPromptCache: true,
+		inputPrice: 2.0,
+		outputPrice: 6.0,
+		cacheWritesPrice: 0.5,
+		cacheReadsPrice: 0.5,
+		description:
+			"xAI's flagship Grok 4.5 model with 500K context, configurable reasoning (low/medium/high), and agentic tool calling via Responses API.",
+		supportsReasoningEffort: ["low", "medium", "high"],
+		reasoningEffort: "high",
+		includedTools: ["search_replace"],
+		excludedTools: ["apply_diff"],
+	},
 	"grok-4.20": {
 		maxTokens: 65_536,
 		contextWindow: 2_000_000,

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

@@ -255,7 +255,7 @@ describe("XAIHandler", () => {
 		await expect(handler.completePrompt("test prompt")).rejects.toThrow(`xAI completion error: ${errorMessage}`)
 	})
 
-	it("should include reasoning_effort for mini models", async () => {
+	it("should include reasoning effort for mini models in Responses API format", async () => {
 		const miniModelHandler = new XAIHandler({
 			apiModelId: "grok-3-mini",
 			reasoningEffort: "high",
@@ -269,7 +269,48 @@ describe("XAIHandler", () => {
 		expect(mockResponsesCreate).toHaveBeenCalledWith(
 			expect.objectContaining({
 				reasoning: expect.objectContaining({
-					reasoning_effort: "high",
+					effort: "high",
+				}),
+			}),
+		)
+	})
+
+	it("should include reasoning effort for grok-4.5 with default high effort", async () => {
+		const grok45Handler = new XAIHandler({
+			apiModelId: "grok-4.5",
+		})
+
+		mockResponsesCreate.mockResolvedValueOnce(mockStream([]))
+
+		const stream = grok45Handler.createMessage("test prompt", [])
+		await stream.next()
+
+		expect(mockResponsesCreate).toHaveBeenCalledWith(
+			expect.objectContaining({
+				model: "grok-4.5",
+				reasoning: expect.objectContaining({
+					effort: "high",
+				}),
+			}),
+		)
+	})
+
+	it("should include reasoning effort for grok-4.5 with custom low effort", async () => {
+		const grok45Handler = new XAIHandler({
+			apiModelId: "grok-4.5",
+			reasoningEffort: "low",
+		})
+
+		mockResponsesCreate.mockResolvedValueOnce(mockStream([]))
+
+		const stream = grok45Handler.createMessage("test prompt", [])
+		await stream.next()
+
+		expect(mockResponsesCreate).toHaveBeenCalledWith(
+			expect.objectContaining({
+				model: "grok-4.5",
+				reasoning: expect.objectContaining({
+					effort: "low",
 				}),
 			}),
 		)

src/api/providers/xai.ts

@@ -120,9 +120,11 @@ export class XAIHandler extends BaseProvider implements SingleCompletionHandler
 			requestBody.parallel_tool_calls = metadata?.parallelToolCalls ?? true
 		}
 
-		// Pass reasoning effort for models that support it (e.g., mini models)
+		// Pass reasoning effort for models that support it (e.g., grok-4.5, grok-3-mini).
+		// The xAI Responses API uses `reasoning: { effort }` format (not `reasoning_effort`
+		// which is the Chat Completions format), so we convert from the OpenAI params shape.
 		if (model.reasoning) {
-			requestBody.reasoning = model.reasoning
+			requestBody.reasoning = { effort: model.reasoning.reasoning_effort }
 		}
 
 		let stream: AsyncIterable<any>