diff --git a/frontend/src/lib/components/copilot/chat/AIChatManager.svelte.ts b/frontend/src/lib/components/copilot/chat/AIChatManager.svelte.ts
index faf5da8c2b..966f5ce1c2 100644
--- a/frontend/src/lib/components/copilot/chat/AIChatManager.svelte.ts
+++ b/frontend/src/lib/components/copilot/chat/AIChatManager.svelte.ts
@@ -416,6 +416,10 @@ class AIChatManager {
 			// on each iteration. This is critical for changeModeTool (Navigator → Script/Flow)
 			// which reassigns this.tools, this.helpers, this.systemMessage mid-loop.
 			const self = this
+			const [openai, anthropic] = await Promise.all([
+				workspaceAIClients.getOpenaiClient(),
+				workspaceAIClients.getAnthropicClient()
+			])
 			const result = await runChatLoop({
 				messages,
 				get systemMessage() {
@@ -433,8 +437,8 @@ class AIChatManager {
 					return getCurrentModel()
 				},
 				clients: {
-					openai: workspaceAIClients.getOpenaiClient(),
-					anthropic: workspaceAIClients.getAnthropicClient()
+					openai,
+					anthropic
 				},
 				workspace: get(workspaceStore) ?? '',
 				skipResponsesApi: this.skipResponsesApi,
diff --git a/frontend/src/lib/components/copilot/chat/anthropic.ts b/frontend/src/lib/components/copilot/chat/anthropic.ts
index 4bc581db88..6fd7726b88 100644
--- a/frontend/src/lib/components/copilot/chat/anthropic.ts
+++ b/frontend/src/lib/components/copilot/chat/anthropic.ts
@@ -1,5 +1,5 @@
-import { OpenAI } from 'openai'
-import Anthropic from '@anthropic-ai/sdk'
+import type { OpenAI } from 'openai'
+import type Anthropic from '@anthropic-ai/sdk'
 import type {
 	ChatCompletionMessageParam,
 	ChatCompletionMessageFunctionToolCall
@@ -41,7 +41,7 @@ export async function getAnthropicCompletion(
 	const { system, messages: anthropicMessages } = convertOpenAIToAnthropicMessages(messages)
 	const anthropicTools = convertOpenAIToolsToAnthropic(tools)
 
-	const client = options?.anthropicClient ?? workspaceAIClients.getAnthropicClient()
+	const client = await (options?.anthropicClient ?? workspaceAIClients.getAnthropicClient())
 
 	const anthropicParams = {
 		model: config.model,
diff --git a/frontend/src/lib/components/copilot/chat/chatLoop.ts b/frontend/src/lib/components/copilot/chat/chatLoop.ts
index a624698cc9..08c75a3f48 100644
--- a/frontend/src/lib/components/copilot/chat/chatLoop.ts
+++ b/frontend/src/lib/components/copilot/chat/chatLoop.ts
@@ -1,5 +1,5 @@
-import OpenAI from 'openai'
-import Anthropic from '@anthropic-ai/sdk'
+import type OpenAI from 'openai'
+import type Anthropic from '@anthropic-ai/sdk'
 import type {
 	ChatCompletionMessageParam,
 	ChatCompletionSystemMessageParam,
@@ -8,16 +8,9 @@ import type {
 import type { AIProviderModel } from '$lib/gen'
 import { getCompletion, parseOpenAICompletion } from '../lib'
 import { getAnthropicCompletion, parseAnthropicCompletion } from './anthropic'
-import {
-	getOpenAIResponsesCompletion,
-	parseOpenAIResponsesCompletion
-} from './openai-responses'
+import { getOpenAIResponsesCompletion, parseOpenAIResponsesCompletion } from './openai-responses'
 import type { Tool, ToolCallbacks } from './shared'
-import {
-	addChatTokenUsage,
-	emptyChatTokenUsage,
-	type ChatTokenUsage
-} from './tokenUsage'
+import { addChatTokenUsage, emptyChatTokenUsage, type ChatTokenUsage } from './tokenUsage'
 
 export interface ChatClients {
 	openai: OpenAI
@@ -137,10 +130,7 @@ export async function runChatLoop(config: ChatLoopConfig): Promise<ChatLoopResul
 						break
 					}
 				} catch (err) {
-					console.warn(
-						'OpenAI Responses API failed, falling back to Completions API:',
-						err
-					)
+					console.warn('OpenAI Responses API failed, falling back to Completions API:', err)
 					const errorMessage = err instanceof Error ? err.message : String(err)
 					if (errorMessage.includes('Responses API is not enabled')) {
 						skipResponsesApi = true
@@ -172,15 +162,10 @@ export async function runChatLoop(config: ChatLoopConfig): Promise<ChatLoopResul
 				}
 			}
 		} else if (isAnthropic) {
-			const completion = await getAnthropicCompletion(
-				messageParams,
-				abortController,
-				toolDefs,
-				{
-					forceModelProvider: modelProvider,
-					anthropicClient: clients.anthropic
-				}
-			)
+			const completion = await getAnthropicCompletion(messageParams, abortController, toolDefs, {
+				forceModelProvider: modelProvider,
+				anthropicClient: clients.anthropic
+			})
 			if (completion) {
 				const continueCompletion = await parseAnthropicCompletion(
 					completion,
diff --git a/frontend/src/lib/components/copilot/chat/openai-responses.ts b/frontend/src/lib/components/copilot/chat/openai-responses.ts
index c557132417..ad6ccf4de0 100644
--- a/frontend/src/lib/components/copilot/chat/openai-responses.ts
+++ b/frontend/src/lib/components/copilot/chat/openai-responses.ts
@@ -1,4 +1,5 @@
-import OpenAI, { OpenAIError } from 'openai'
+import type OpenAI from 'openai'
+import type { OpenAIError } from 'openai'
 import type {
 	ChatCompletionMessageParam,
 	ChatCompletionMessageFunctionToolCall,
@@ -14,10 +15,7 @@ import {
 import { processToolCall, type Tool, type ToolCallbacks } from './shared'
 import type { ResponseStream } from 'openai/lib/responses/ResponseStream.mjs'
 import type { AIProviderModel } from '$lib/gen'
-import {
-	openAIResponsesUsageToChatTokenUsage,
-	type ChatTokenUsage
-} from './tokenUsage'
+import { openAIResponsesUsageToChatTokenUsage, type ChatTokenUsage } from './tokenUsage'
 
 interface ParsedCompletionResult {
 	shouldContinue: boolean
@@ -149,7 +147,7 @@ export async function getOpenAIResponsesCompletion(
 	const { instructions, input } = convertMessagesToResponsesInput(messages)
 	const responsesConfig = convertCompletionConfigToResponsesConfig(config)
 
-	const client = options?.openaiClient ?? workspaceAIClients.getOpenaiClient()
+	const client = await (options?.openaiClient ?? workspaceAIClients.getOpenaiClient())
 
 	const runner = client.responses.stream(
 		{
@@ -178,7 +176,7 @@ export async function* getOpenAIResponsesCompletionStream(
 	const { instructions, input } = convertMessagesToResponsesInput(messages)
 	const responsesConfig = convertCompletionConfigToResponsesConfig(config)
 
-	const openaiClient = workspaceAIClients.getOpenaiClient()
+	const openaiClient = await workspaceAIClients.getOpenaiClient()
 
 	const runner = openaiClient.responses.stream(
 		{
@@ -417,11 +415,11 @@ export async function getNonStreamingOpenAIResponsesCompletion(
 		}
 	}
 
-	const openaiClient = testOptions?.apiKey
+	const openaiClient = await (testOptions?.apiKey
 		? createOpenAIProxyClient(getAiProxyBaseURL())
 		: testOptions?.workspace
 			? workspaceAIClients.createOpenaiClient(testOptions.workspace)
-			: workspaceAIClients.getOpenaiClient()
+			: workspaceAIClients.getOpenaiClient())
 
 	const response = await openaiClient.responses.create(
 		{
diff --git a/frontend/src/lib/components/copilot/lib.ts b/frontend/src/lib/components/copilot/lib.ts
index e98ff035db..6d9661250c 100644
--- a/frontend/src/lib/components/copilot/lib.ts
+++ b/frontend/src/lib/components/copilot/lib.ts
@@ -1,7 +1,7 @@
 import type { AIProvider, AIProviderModel } from '$lib/gen'
 import { workspaceStore, type DBSchema, type SQLSchema } from '$lib/stores'
 import type { IntrospectionQuery } from 'graphql'
-import OpenAI from 'openai'
+import type OpenAI from 'openai'
 import type {
 	ChatCompletionChunk,
 	ChatCompletionCreateParams,
@@ -10,7 +10,7 @@ import type {
 	ChatCompletionMessageFunctionToolCall,
 	ChatCompletionMessageParam
 } from 'openai/resources/index.mjs'
-import Anthropic from '@anthropic-ai/sdk'
+import type Anthropic from '@anthropic-ai/sdk'
 import { get, type Writable } from 'svelte/store'
 import { OpenAPI, ResourceService, type Script } from '../../gen'
 import { EDIT_CONFIG, FIX_CONFIG, GEN_CONFIG } from './prompts'
@@ -389,8 +389,9 @@ export function getAiProxyBaseURL(workspace?: string): string {
 		: `${location.origin}${OpenAPI.BASE}/ai/proxy`
 }
 
-export function createOpenAIProxyClient(baseURL: string): OpenAI {
-	return new OpenAI({
+export async function createOpenAIProxyClient(baseURL: string): Promise<OpenAI> {
+	const { default: OpenAIClass } = await import('openai')
+	return new OpenAIClass({
 		baseURL,
 		apiKey: 'fake-key',
 		defaultHeaders: {
@@ -400,8 +401,9 @@ export function createOpenAIProxyClient(baseURL: string): OpenAI {
 	})
 }
 
-export function createAnthropicProxyClient(baseURL: string): Anthropic {
-	return new Anthropic({
+export async function createAnthropicProxyClient(baseURL: string): Promise<Anthropic> {
+	const { default: AnthropicClass } = await import('@anthropic-ai/sdk')
+	return new AnthropicClass({
 		baseURL,
 		apiKey: 'fake-key',
 		dangerouslyAllowBrowser: true,
@@ -410,30 +412,30 @@ export function createAnthropicProxyClient(baseURL: string): Anthropic {
 }
 
 class WorkspacedAIClients {
-	private openaiClient: OpenAI | undefined
-	private anthropicClient: Anthropic | undefined
+	private openaiClient: Promise<OpenAI> | undefined
+	private anthropicClient: Promise<Anthropic> | undefined
 
 	init(workspace: string) {
 		this.openaiClient = this.createOpenaiClient(workspace)
 		this.anthropicClient = this.createAnthropicClient(workspace)
 	}
 
-	createOpenaiClient(workspace: string): OpenAI {
+	createOpenaiClient(workspace: string): Promise<OpenAI> {
 		return createOpenAIProxyClient(getAiProxyBaseURL(workspace))
 	}
 
-	createAnthropicClient(workspace: string): Anthropic {
+	createAnthropicClient(workspace: string): Promise<Anthropic> {
 		return createAnthropicProxyClient(getAiProxyBaseURL(workspace))
 	}
 
-	getOpenaiClient() {
+	getOpenaiClient(): Promise<OpenAI> {
 		if (!this.openaiClient) {
 			throw new Error('OpenAI not initialized')
 		}
 		return this.openaiClient
 	}
 
-	getAnthropicClient() {
+	getAnthropicClient(): Promise<Anthropic> {
 		if (!this.anthropicClient) {
 			throw new Error('Anthropic not initialized')
 		}
@@ -522,11 +524,11 @@ async function testAnthropicKey({
 		headers['X-API-Key'] = apiKey
 	}
 
-	const anthropicClient = apiKey
+	const anthropicClient = await (apiKey
 		? createAnthropicProxyClient(getAiProxyBaseURL())
 		: workspace
 			? workspaceAIClients.createAnthropicClient(workspace)
-			: workspaceAIClients.getAnthropicClient()
+			: workspaceAIClients.getAnthropicClient())
 
 	await anthropicClient.messages.create(
 		{
@@ -800,11 +802,11 @@ export async function getNonStreamingCompletion(
 			'X-API-Key': testOptions.apiKey
 		}
 	}
-	const openaiClient = testOptions?.apiKey
+	const openaiClient = await (testOptions?.apiKey
 		? createOpenAIProxyClient(getAiProxyBaseURL())
 		: testOptions?.workspace
 			? workspaceAIClients.createOpenaiClient(testOptions.workspace)
-			: workspaceAIClients.getOpenaiClient()
+			: workspaceAIClients.getOpenaiClient())
 
 	const completion = await openaiClient.chat.completions.create(config, fetchOptions)
 	response = completion.choices?.[0]?.message.content || ''
@@ -911,7 +913,7 @@ export async function getCompletion(
 	}
 
 	// Use Completions API for other providers
-	const client = options?.openaiClient ?? workspaceAIClients.getOpenaiClient()
+	const client = await (options?.openaiClient ?? workspaceAIClients.getOpenaiClient())
 	const completionConfig =
 		(provider === 'openai' || provider === 'azure_openai' || provider === 'googleai') &&
 		config.stream
diff --git a/frontend/vite.config.js b/frontend/vite.config.js
index 8f49dc1ba4..8d0759fe0b 100644
--- a/frontend/vite.config.js
+++ b/frontend/vite.config.js
@@ -111,6 +111,53 @@ const config = {
 		dedupe: ['vscode', 'monaco-editor']
 	},
 	assetsInclude: ['**/*.wasm'],
+	build: {
+		rollupOptions: {
+			output: {
+				manualChunks(id) {
+					if (id.includes('node_modules')) {
+						if (id.includes('monaco-editor') || id.includes('@codingame/monaco-vscode')) {
+							return 'vendor-monaco'
+						}
+						if (id.includes('/openai/') || id.includes('/@anthropic-ai/')) {
+							return 'vendor-ai'
+						}
+						if (id.includes('@xyflow/svelte') || id.includes('d3-dag')) {
+							return 'vendor-flow'
+						}
+						if (id.includes('/yjs/') || id.includes('y-websocket') || id.includes('y-monaco')) {
+							return 'vendor-collab'
+						}
+						if (id.includes('ag-grid') || id.includes('ag-charts')) {
+							return 'vendor-ag'
+						}
+						if (id.includes('pdfjs-dist')) {
+							return 'vendor-pdf'
+						}
+						if (
+							id.includes('svelte-exmarkdown') ||
+							id.includes('/parse5/') ||
+							id.includes('/rehype-') ||
+							id.includes('/remark-') ||
+							id.includes('/mdast-') ||
+							id.includes('/micromark')
+						) {
+							return 'vendor-markdown'
+						}
+						if (id.includes('quicktype-core')) {
+							return 'vendor-quicktype'
+						}
+						if (id.includes('/quill/')) {
+							return 'vendor-quill'
+						}
+						if (id.includes('/chart.js/') || id.includes('chartjs-')) {
+							return 'vendor-chart'
+						}
+					}
+				}
+			}
+		}
+	},
 	test: {
 		expect: { requireAssertions: true },
 		projects: [