fix OpenAI-compatible request timeout

.vscode/settings.json

@@ -13,5 +13,20 @@
 	// Surface invisible (zero-width) and ambiguous/homoglyph Unicode in the
 	// editor. Pairs with the code-qa.yml invisible-chars CI check.
 	"editor.unicodeHighlight.invisibleCharacters": true,
-	"editor.unicodeHighlight.ambiguousCharacters": true
+	"editor.unicodeHighlight.ambiguousCharacters": true,
+	"workbench.colorCustomizations": {
+		"editor.selectionBackground": "#135564ef",
+		"editor.selectionHighlightBackground": "#13556496",
+		"activityBar.background": "#A02C18",
+		"titleBar.activeBackground": "#DE3F24",
+		"titleBar.activeForeground": "#FEF9F9",
+		"titleBar.inactiveBackground": "#A02C18",
+		"titleBar.inactiveForeground": "#FEF9F9",
+		"statusBar.background": "#A02C18",
+		"statusBar.foreground": "#FEF9F9",
+		"statusBar.debuggingBackground": "#A02C18",
+		"statusBar.debuggingForeground": "#FEF9F9",
+		"statusBar.noFolderBackground": "#A02C18",
+		"statusBar.noFolderForeground": "#FEF9F9"
+	}
 }

src/api/providers/__tests__/kimi-code.spec.ts

@@ -10,6 +10,16 @@ const { mockGetAccessToken, mockForceRefreshAccessToken, mockGetModels } = vi.ho
 	mockGetModels: vi.fn(),
 }))
 
+vi.mock("undici", async (importOriginal) => {
+	const actual = await importOriginal<typeof import("undici")>()
+	return {
+		...actual,
+		fetch: vi.fn().mockImplementation(async (url: RequestInfo | URL, init?: RequestInit) => {
+			return globalThis.fetch(url, init)
+		}),
+	}
+})
+
 vi.mock("../../../integrations/kimi-code/oauth", () => ({
 	kimiCodeOAuthManager: {
 		getAccessToken: mockGetAccessToken,

src/api/providers/openai.ts

@@ -1,6 +1,7 @@
 import { Anthropic } from "@anthropic-ai/sdk"
 import OpenAI, { AzureOpenAI } from "openai"
 import axios from "axios"
+import { Agent, fetch as undiciFetch, Dispatcher } from "undici"
 
 import {
 	type ModelInfo,
@@ -52,34 +53,79 @@
 			...(this.options.openAiHeaders || {}),
 		}
 
+		function resolveTimeoutMs(configuredMs: number | undefined): number {
+			if (configuredMs === undefined || configuredMs === 0) {
+				return 0
+				// return 60 * 60 * 1000;
+			}
+			return configuredMs
+		}
+
+		const timeoutMs = resolveTimeoutMs(this.timeoutMs)
+
+		// VS Code bundles its own undici with a 5-minute `bodyTimeout` default.
+		// For streaming LLM requests, that default terminates the connection.
+		// We bypass the VS Code-bundled undici by injecting our own Agent-backed
+		// fetch into the OpenAI SDK.
+		const agent = new Agent({
+			headersTimeout: timeoutMs,
+			bodyTimeout: timeoutMs,
+			keepAliveTimeout: timeoutMs,
+			keepAliveMaxTimeout: timeoutMs,
+			connect: {
+				timeout: Math.min(timeoutMs, 60_000),
+			},
+		})
+
+		interface UndiciRequestInit extends RequestInit {
+			dispatcher?: Dispatcher
+		}
+
+		const customFetch: typeof fetch = (url, init) => {
+			const undiciInit = { ...init, dispatcher: agent } as UndiciRequestInit
+			return globalThis.fetch(url, undiciInit as RequestInit)
+			// const fetchImpl = undiciFetch as unknown as (
+			// 	url: RequestInfo | URL,
+			// 	init: UndiciRequestInit,
+			// ) => Promise<Response>
+
+			// return fetchImpl(url, undiciInit)
+		}
+
+		const timeoutConfig = {
+			timeout: timeoutMs,
+		}
+
 		if (isAzureAiInference) {
-			// Azure AI Inference Service (e.g., for DeepSeek) uses a different path structure
 			this.client = new OpenAI({
 				baseURL,
 				apiKey,
 				defaultHeaders: headers,
 				defaultQuery: { "api-version": this.options.azureApiVersion || "2024-05-01-preview" },
-				timeout: this.timeoutMs,
+				...timeoutConfig,
 			})
 		} else if (isAzureOpenAi) {
 			// Azure API shape slightly differs from the core API shape:
 			// https://github.com/openai/openai-node?tab=readme-ov-file#microsoft-azure-openai
+
 			const azureBaseURL = `${baseURL.replace(/\/openai\/?$/i, "").replace(/\/$/, "")}/openai`
 			this.client = new AzureOpenAI({
 				baseURL: azureBaseURL,
 				apiKey,
 				apiVersion: this.options.azureApiVersion || azureOpenAiDefaultApiVersion,
 				defaultHeaders: headers,
-				timeout: this.timeoutMs,
+				...timeoutConfig,
 			})
 		} else {
 			this.client = new OpenAI({
 				baseURL,
 				apiKey,
 				defaultHeaders: headers,
-				timeout: this.timeoutMs,
+				...timeoutConfig,
 			})
 		}
+
+		;(this.client as unknown as { fetch: typeof fetch }).fetch = customFetch
 	}
 
 	override async *createMessage(