refactor: streamline Copilot model fetching and remove unused streaming option

Author: NaccOll

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

@@ -106,7 +106,6 @@ describe("CopilotHandler", () => {
 		mockOptions = {
 			copilotModelId: "gpt-4",
 			apiModelId: "gpt-4",
-			openAiStreamingEnabled: true,
 		}
 
 		// Mock successful authentication
@@ -344,47 +343,6 @@ describe("CopilotHandler", () => {
 			expect(chunk.cacheReadTokens).toBe(2)
 		})
 
-		it("should handle non-streaming requests", async () => {
-			const nonStreamingHandler = new CopilotHandler({
-				...mockOptions,
-				openAiStreamingEnabled: false,
-			})
-
-			const stream = nonStreamingHandler.createMessage(systemPrompt, messages)
-			const chunks: any[] = []
-			for await (const chunk of stream) {
-				chunks.push(chunk)
-			}
-
-			const textChunks = chunks.filter((chunk) => chunk.type === "text")
-			expect(textChunks).toHaveLength(1)
-			expect(textChunks[0].text).toBe("Test Copilot response")
-
-			const usageChunks = chunks.filter((chunk) => chunk.type === "usage")
-			expect(usageChunks).toHaveLength(1)
-		})
-
-		it("should add max_tokens when includeMaxTokens is enabled", async () => {
-			const handlerWithMaxTokens = new CopilotHandler({
-				...mockOptions,
-				includeMaxTokens: true,
-				modelMaxTokens: 4096,
-			})
-
-			const stream = handlerWithMaxTokens.createMessage(systemPrompt, messages)
-			const chunks: any[] = []
-			for await (const chunk of stream) {
-				chunks.push(chunk)
-			}
-
-			expect(mockCreate).toHaveBeenCalledWith(
-				expect.objectContaining({
-					max_completion_tokens: 4096,
-				}),
-				expect.any(Object),
-			)
-		})
-
 		it("should handle authentication failures gracefully", async () => {
 			mockAuthenticator.getApiKey.mockRejectedValueOnce(new Error("Auth failed"))
 

src/api/providers/copilot.ts

@@ -122,55 +122,32 @@ export class CopilotHandler extends BaseProvider implements SingleCompletionHand
 			"X-Initiator": initiator,
 		}
 
-		if (this.options.openAiStreamingEnabled ?? true) {
-			const requestOptions: OpenAI.Chat.Completions.ChatCompletionCreateParamsStreaming = {
-				model: modelId,
-				temperature: this.options.modelTemperature ?? 0,
-				messages: convertedMessages,
-				stream: true as const,
-				stream_options: { include_usage: true },
-			}
-
-			// Add max_tokens if needed
-			this.addMaxTokensIfNeeded(requestOptions, modelInfo)
-
-			const stream = await this.client.chat.completions.create(requestOptions, {
-				headers,
-			})
+		const requestOptions: OpenAI.Chat.Completions.ChatCompletionCreateParamsStreaming = {
+			model: modelId,
+			temperature: this.options.modelTemperature ?? 0,
+			messages: convertedMessages,
+			stream: true as const,
+			stream_options: { include_usage: true },
+			max_completion_tokens: modelInfo.maxTokens,
+		}
 
-			for await (const chunk of stream) {
-				const delta = chunk.choices?.[0]?.delta
-				if (delta?.content) {
-					yield {
-						type: "text",
-						text: delta.content,
-					}
-				}
+		const stream = await this.client.chat.completions.create(requestOptions, {
+			headers,
+		})
 
-				// Handle usage information
-				if (chunk.usage) {
-					yield this.processUsageMetrics(chunk.usage)
+		for await (const chunk of stream) {
+			const delta = chunk.choices?.[0]?.delta
+			if (delta?.content) {
+				yield {
+					type: "text",
+					text: delta.content,
 				}
 			}
-		} else {
-			// Non-streaming implementation
-			const requestOptions: OpenAI.Chat.Completions.ChatCompletionCreateParamsNonStreaming = {
-				model: modelId,
-				temperature: this.options.modelTemperature ?? 0,
-				messages: convertedMessages,
-			}
-
-			this.addMaxTokensIfNeeded(requestOptions, modelInfo)
-
-			const response = await this.client.chat.completions.create(requestOptions, {
-				headers,
-			})
 
-			yield {
-				type: "text",
-				text: response.choices[0]?.message.content || "",
+			// Handle usage information
+			if (chunk.usage) {
+				yield this.processUsageMetrics(chunk.usage)
 			}
-			yield this.processUsageMetrics(response.usage)
 		}
 	}
 

src/core/webview/__tests__/webviewMessageHandler.spec.ts

@@ -6,13 +6,14 @@ vi.mock("../../../api/providers/fetchers/copilot")
 
 import { webviewMessageHandler } from "../webviewMessageHandler"
 import type { ClineProvider } from "../ClineProvider"
-import { getModels } from "../../../api/providers/fetchers/modelCache"
+import { flushModels, getModels } from "../../../api/providers/fetchers/modelCache"
 import { getCopilotModels, CopilotAuthenticator } from "../../../api/providers/fetchers/copilot"
 import type { ModelRecord } from "../../../shared/api"
 
 const mockGetModels = getModels as Mock<typeof getModels>
 const mockGetCopilotModels = getCopilotModels as Mock<typeof getCopilotModels>
 const mockCopilotAuthenticator = CopilotAuthenticator as any
+const mockFlushModels = flushModels as Mock<typeof flushModels>
 
 // Mock ClineProvider
 const mockClineProvider = {
@@ -560,21 +561,22 @@ describe("webviewMessageHandler - requestCopilotModels", () => {
 		}
 
 		// Mock getCopilotModels to return mock models
-		mockGetCopilotModels.mockResolvedValue(mockCopilotModels)
+		mockGetModels.mockResolvedValue(mockCopilotModels)
 
 		await webviewMessageHandler(mockClineProvider, {
 			type: "requestCopilotModels",
 		})
 
-		expect(mockGetCopilotModels).toHaveBeenCalledTimes(1)
+		expect(mockFlushModels).toHaveBeenCalledTimes(1)
+		expect(mockGetModels).toHaveBeenCalledTimes(1)
 		expect(mockClineProvider.postMessageToWebview).toHaveBeenCalledWith({
 			type: "copilotModels",
 			copilotModels: mockCopilotModels,
 		})
 	})
 
 	it("handles errors when fetching Copilot models", async () => {
-		mockGetCopilotModels.mockRejectedValue(new Error("Authentication failed"))
+		mockGetModels.mockRejectedValue(new Error("Authentication failed"))
 
 		// Spy on console.error
 		const consoleSpy = vi.spyOn(console, "error").mockImplementation(() => {})
@@ -583,7 +585,8 @@ describe("webviewMessageHandler - requestCopilotModels", () => {
 			type: "requestCopilotModels",
 		})
 
-		expect(mockGetCopilotModels).toHaveBeenCalledTimes(1)
+		expect(mockFlushModels).toHaveBeenCalledTimes(1)
+		expect(mockGetModels).toHaveBeenCalledTimes(1)
 		expect(consoleSpy).toHaveBeenCalledWith("Failed to fetch Copilot models:", expect.any(Error))
 		expect(mockClineProvider.postMessageToWebview).toHaveBeenCalledWith({
 			type: "copilotModels",

src/core/webview/message-handle/copilot/requestCopilotModels.ts

@@ -1,6 +1,6 @@
 import { MessageHandlerStrategy, MessageHandlerContext } from "../types"
-import { getCopilotModels } from "../../../../api/providers/fetchers/copilot"
 import { ModelRecord } from "../../../../shared/api"
+import { flushModels, getModels } from "../../../../api/providers/fetchers/modelCache"
 
 /**
  * Strategy for handling requestCopilotModels message
@@ -10,7 +10,11 @@ export class RequestCopilotModelsStrategy implements MessageHandlerStrategy {
 		const { provider } = context
 
 		try {
-			const copilotModels = await getCopilotModels()
+			await flushModels("copilot")
+
+			const copilotModels = await getModels({
+				provider: "copilot",
+			})
 			provider.postMessageToWebview({
 				type: "copilotModels",
 				copilotModels,