优化一键填入过程

README.md

@@ -32,7 +32,7 @@ One-Click to get a well-designed cross-platform ChatGPT web UI, with Claude, GPT
 [MacOS-image]: https://img.shields.io/badge/-MacOS-black?logo=apple
 [Linux-image]: https://img.shields.io/badge/-Linux-333?logo=ubuntu
 
-[<img src="https://vercel.com/button" alt="Deploy on Vercel" height="30">](https://vercel.com/new/clone?repository-url=https://github.com/Dogtiti/ChatGPT-Next-Web-EarlyBird&env=OPENAI_API_KEY&env=CODE&project-name=nextchat-earlyBird&repository-name=NextChat-EarlyBird) [<img src="https://zeabur.com/button.svg" alt="Deploy on Zeabur" height="30">](https://zeabur.com/templates/ZBUEFA)  [<img src="https://gitpod.io/button/open-in-gitpod.svg" alt="Open in Gitpod" height="30">](https://gitpod.io/#https://github.com/Yidadaa/ChatGPT-Next-Web) [<img src="https://img.shields.io/badge/BT_Deploy-Install-20a53a" alt="BT Deply Install" height="30">](https://www.bt.cn/new/download.html)
+[<img src="https://vercel.com/button" alt="Deploy on Vercel" height="30">](https://vercel.com/new/clone?repository-url=https%3A%2F%2Fgithub.com%2FChatGPTNextWeb%2FChatGPT-Next-Web&env=OPENAI_API_KEY&env=CODE&project-name=nextchat&repository-name=NextChat) [<img src="https://zeabur.com/button.svg" alt="Deploy on Zeabur" height="30">](https://zeabur.com/templates/ZBUEFA)  [<img src="https://gitpod.io/button/open-in-gitpod.svg" alt="Open in Gitpod" height="30">](https://gitpod.io/#https://github.com/Yidadaa/ChatGPT-Next-Web) [<img src="https://img.shields.io/badge/BT_Deploy-Install-20a53a" alt="BT Deply Install" height="30">](https://www.bt.cn/new/download.html)
 
 [<img src="https://github.com/user-attachments/assets/903482d4-3e87-4134-9af1-f2588fa90659" height="60" width="288" >](https://monica.im/?utm=nxcrp)
 
@@ -477,7 +477,7 @@ If you want to add a new translation, read this [document](./docs/translation.md
 
 ## Donation
 
-[Buy Me a Coffee](https://1kafei.com/dogtiti)
+[Buy Me a Coffee](https://www.buymeacoffee.com/yidadaa)
 
 ## Special Thanks
 

README_CN.md

@@ -33,7 +33,7 @@
 
 1. 准备好你的 [OpenAI API Key](https://platform.openai.com/account/api-keys);
 2. 点击右侧按钮开始部署：
-   [![Deploy with Vercel](https://vercel.com/button)](https://vercel.com/new/clone?repository-url=https://github.com/Dogtiti/ChatGPT-Next-Web-EarlyBird&env=OPENAI_API_KEY&env=CODE&project-name=nextchat-earlyBird&repository-name=NextChat-EarlyBird)，直接使用 Github 账号登录即可，记得在环境变量页填入 API Key 和[页面访问密码](#配置页面访问密码) CODE；
+   [![Deploy with Vercel](https://vercel.com/button)](https://vercel.com/new/clone?repository-url=https%3A%2F%2Fgithub.com%2FYidadaa%2FChatGPT-Next-Web&env=OPENAI_API_KEY&env=CODE&env=GOOGLE_API_KEY&project-name=chatgpt-next-web&repository-name=ChatGPT-Next-Web)，直接使用 Github 账号登录即可，记得在环境变量页填入 API Key 和[页面访问密码](#配置页面访问密码) CODE；
 3. 部署完毕后，即可开始使用；
 4. （可选）[绑定自定义域名](https://vercel.com/docs/concepts/projects/domains/add-a-domain)：Vercel 分配的域名 DNS 在某些区域被污染了，绑定自定义域名即可直连。
 

README_JA.md

@@ -30,7 +30,7 @@
 
 1. [OpenAI API Key](https://platform.openai.com/account/api-keys)を準備する;
 2. 右側のボタンをクリックしてデプロイを開始：
-   [![Deploy with Vercel](https://vercel.com/button)](https://vercel.com/new/clone?repository-url=https://github.com/Dogtiti/ChatGPT-Next-Web-EarlyBird&env=OPENAI_API_KEY&env=CODE&project-name=nextchat-earlyBird&repository-name=NextChat-EarlyBird) 、GitHubアカウントで直接ログインし、環境変数ページにAPI Keyと[ページアクセスパスワード](#設定ページアクセスパスワード) CODEを入力してください;
+   [![Deploy with Vercel](https://vercel.com/button)](https://vercel.com/new/clone?repository-url=https%3A%2F%2Fgithub.com%2FYidadaa%2FChatGPT-Next-Web&env=OPENAI_API_KEY&env=CODE&env=GOOGLE_API_KEY&project-name=chatgpt-next-web&repository-name=ChatGPT-Next-Web) 、GitHubアカウントで直接ログインし、環境変数ページにAPI Keyと[ページアクセスパスワード](#設定ページアクセスパスワード) CODEを入力してください;
 3. デプロイが完了したら、すぐに使用を開始できます;
 4. （オプション）[カスタムドメインをバインド](https://vercel.com/docs/concepts/projects/domains/add-a-domain)：Vercelが割り当てたドメインDNSは一部の地域で汚染されているため、カスタムドメインをバインドすると直接接続できます。
 

app/api/config/route.ts

@@ -13,6 +13,7 @@ const DANGER_CONFIG = {
   hideBalanceQuery: serverConfig.hideBalanceQuery,
   disableFastLink: serverConfig.disableFastLink,
   customModels: serverConfig.customModels,
+  visionModels: serverConfig.visionModels,
   defaultModel: serverConfig.defaultModel,
 };
 

app/client/platforms/anthropic.ts

@@ -84,10 +84,13 @@ export class ClaudeApi implements LLMApi {
     return res?.content?.[0]?.text;
   }
   async chat(options: ChatOptions): Promise<void> {
-    const visionModel = isVisionModel(options.config.model);
-
     const accessStore = useAccessStore.getState();
 
+    const visionModel = isVisionModel(
+      options.config.model,
+      accessStore.visionModels,
+    );
+
     const shouldStream = !!options.config.stream;
 
     const modelConfig = {

app/client/platforms/glm.ts

@@ -25,103 +25,12 @@ import { getMessageTextContent } from "@/app/utils";
 import { RequestPayload } from "./openai";
 import { fetch } from "@/app/utils/stream";
 
-interface BasePayload {
-  model: string;
-}
-
-interface ChatPayload extends BasePayload {
-  messages: ChatOptions["messages"];
-  stream?: boolean;
-  temperature?: number;
-  presence_penalty?: number;
-  frequency_penalty?: number;
-  top_p?: number;
-}
-
-interface ImageGenerationPayload extends BasePayload {
-  prompt: string;
-  size?: string;
-  user_id?: string;
-}
-
-interface VideoGenerationPayload extends BasePayload {
-  prompt: string;
-  duration?: number;
-  resolution?: string;
-  user_id?: string;
-}
-
-type ModelType = "chat" | "image" | "video";
-
 export class ChatGLMApi implements LLMApi {
   private disableListModels = true;
 
-  private getModelType(model: string): ModelType {
-    if (model.startsWith("cogview-")) return "image";
-    if (model.startsWith("cogvideo-")) return "video";
-    return "chat";
-  }
-
-  private getModelPath(type: ModelType): string {
-    switch (type) {
-      case "image":
-        return ChatGLM.ImagePath;
-      case "video":
-        return ChatGLM.VideoPath;
-      default:
-        return ChatGLM.ChatPath;
-    }
-  }
-
-  private createPayload(
-    messages: ChatOptions["messages"],
-    modelConfig: any,
-    options: ChatOptions,
-  ): BasePayload {
-    const modelType = this.getModelType(modelConfig.model);
-    const lastMessage = messages[messages.length - 1];
-    const prompt =
-      typeof lastMessage.content === "string"
-        ? lastMessage.content
-        : lastMessage.content.map((c) => c.text).join("\n");
-
-    switch (modelType) {
-      case "image":
-        return {
-          model: modelConfig.model,
-          prompt,
-          size: options.config.size,
-        } as ImageGenerationPayload;
-      default:
-        return {
-          messages,
-          stream: options.config.stream,
-          model: modelConfig.model,
-          temperature: modelConfig.temperature,
-          presence_penalty: modelConfig.presence_penalty,
-          frequency_penalty: modelConfig.frequency_penalty,
-          top_p: modelConfig.top_p,
-        } as ChatPayload;
-    }
-  }
-
-  private parseResponse(modelType: ModelType, json: any): string {
-    switch (modelType) {
-      case "image": {
-        const imageUrl = json.data?.[0]?.url;
-        return imageUrl ? `![Generated Image](${imageUrl})` : "";
-      }
-      case "video": {
-        const videoUrl = json.data?.[0]?.url;
-        return videoUrl ? `<video controls src="${videoUrl}"></video>` : "";
-      }
-      default:
-        return this.extractMessage(json);
-    }
-  }
-
   path(path: string): string {
     const accessStore = useAccessStore.getState();
+
     let baseUrl = "";
 
     if (accessStore.useCustomConfig) {
@@ -142,6 +51,7 @@ export class ChatGLMApi implements LLMApi {
     }
 
     console.log("[Proxy Endpoint] ", baseUrl, path);
+
     return [baseUrl, path].join("/");
   }
 
@@ -169,16 +79,24 @@ export class ChatGLMApi implements LLMApi {
       },
     };
 
-    const modelType = this.getModelType(modelConfig.model);
+    const requestPayload: RequestPayload = {
-    const requestPayload = this.createPayload(messages, modelConfig, options);
+      messages,
-    const path = this.path(this.getModelPath(modelType));
+      stream: options.config.stream,
+      model: modelConfig.model,
+      temperature: modelConfig.temperature,
+      presence_penalty: modelConfig.presence_penalty,
+      frequency_penalty: modelConfig.frequency_penalty,
+      top_p: modelConfig.top_p,
+    };
 
-    console.log(`[Request] glm ${modelType} payload: `, requestPayload);
+    console.log("[Request] glm payload: ", requestPayload);
 
+    const shouldStream = !!options.config.stream;
     const controller = new AbortController();
     options.onController?.(controller);
 
     try {
+      const chatPath = this.path(ChatGLM.ChatPath);
       const chatPayload = {
         method: "POST",
         body: JSON.stringify(requestPayload),
@@ -186,23 +104,12 @@ export class ChatGLMApi implements LLMApi {
         headers: getHeaders(),
       };
 
+      // make a fetch request
       const requestTimeoutId = setTimeout(
         () => controller.abort(),
         REQUEST_TIMEOUT_MS,
       );
 
-      if (modelType === "image" || modelType === "video") {
-        const res = await fetch(path, chatPayload);
-        clearTimeout(requestTimeoutId);
-
-        const resJson = await res.json();
-        console.log(`[Response] glm ${modelType}:`, resJson);
-        const message = this.parseResponse(modelType, resJson);
-        options.onFinish(message, res);
-        return;
-      }
-
-      const shouldStream = !!options.config.stream;
       if (shouldStream) {
         const [tools, funcs] = usePluginStore
           .getState()
@@ -210,7 +117,7 @@ export class ChatGLMApi implements LLMApi {
             useChatStore.getState().currentSession().mask?.plugin || [],
           );
         return stream(
-          path,
+          chatPath,
           requestPayload,
           getHeaders(),
           tools as any,
@@ -218,6 +125,7 @@ export class ChatGLMApi implements LLMApi {
           controller,
           // parseSSE
           (text: string, runTools: ChatMessageTool[]) => {
+            // console.log("parseSSE", text, runTools);
             const json = JSON.parse(text);
             const choices = json.choices as Array<{
               delta: {
@@ -246,7 +154,7 @@ export class ChatGLMApi implements LLMApi {
             }
             return choices[0]?.delta?.content;
           },
-          // processToolMessage
+          // processToolMessage, include tool_calls message and tool call results
           (
             requestPayload: RequestPayload,
             toolCallMessage: any,
@@ -264,7 +172,7 @@ export class ChatGLMApi implements LLMApi {
           options,
         );
       } else {
-        const res = await fetch(path, chatPayload);
+        const res = await fetch(chatPath, chatPayload);
         clearTimeout(requestTimeoutId);
 
         const resJson = await res.json();
@@ -276,7 +184,6 @@ export class ChatGLMApi implements LLMApi {
       options.onError?.(e as Error);
     }
   }
-
   async usage() {
     return {
       used: 0,

app/client/platforms/google.ts

@@ -83,7 +83,7 @@ export class GeminiProApi implements LLMApi {
     }
     const messages = _messages.map((v) => {
       let parts: any[] = [{ text: getMessageTextContent(v) }];
-      if (isVisionModel(options.config.model)) {
+      if (isVisionModel(options.config.model, accessStore.visionModels)) {
         const images = getMessageImages(v);
         if (images.length > 0) {
           multimodal = true;

app/client/platforms/openai.ts

@@ -24,7 +24,7 @@ import {
   stream,
 } from "@/app/utils/chat";
 import { cloudflareAIGatewayUrl } from "@/app/utils/cloudflare";
-import { ModelSize, DalleQuality, DalleStyle } from "@/app/typing";
+import { DalleSize, DalleQuality, DalleStyle } from "@/app/typing";
 
 import {
   ChatOptions,
@@ -73,7 +73,7 @@ export interface DalleRequestPayload {
   prompt: string;
   response_format: "url" | "b64_json";
   n: number;
-  size: ModelSize;
+  size: DalleSize;
   quality: DalleQuality;
   style: DalleStyle;
 }
@@ -194,6 +194,8 @@ export class ChatGPTApi implements LLMApi {
 
     let requestPayload: RequestPayload | DalleRequestPayload;
 
+    const accessStore = useAccessStore.getState();
+
     const isDalle3 = _isDalle3(options.config.model);
     const isO1 = options.config.model.startsWith("o1");
     if (isDalle3) {
@@ -211,7 +213,10 @@ export class ChatGPTApi implements LLMApi {
         style: options.config?.style ?? "vivid",
       };
     } else {
-      const visionModel = isVisionModel(options.config.model);
+      const visionModel = isVisionModel(
+        options.config.model,
+        accessStore.visionModels,
+      );
       const messages: ChatOptions["messages"] = [];
       for (const v of options.messages) {
         const content = visionModel

app/client/platforms/tencent.ts

@@ -94,7 +94,11 @@ export class HunyuanApi implements LLMApi {
   }
 
   async chat(options: ChatOptions) {
-    const visionModel = isVisionModel(options.config.model);
+    const accessStore = useAccessStore.getState();
+    const visionModel = isVisionModel(
+      options.config.model,
+      accessStore.visionModels,
+    );
     const messages = options.messages.map((v, index) => ({
       // "Messages 中 system 角色必须位于列表的最开始"
       role: index !== 0 && v.role === "system" ? "user" : v.role,

app/components/chat.tsx

@@ -72,8 +72,6 @@ import {
   isDalle3,
   showPlugins,
   safeLocalStorage,
-  getModelSizes,
-  supportsCustomSize,
 } from "../utils";
 
 import { uploadImage as uploadImageRemote } from "@/app/utils/chat";
@@ -81,7 +79,7 @@ import { uploadImage as uploadImageRemote } from "@/app/utils/chat";
 import dynamic from "next/dynamic";
 
 import { ChatControllerPool } from "../client/controller";
-import { DalleQuality, DalleStyle, ModelSize } from "../typing";
+import { DalleSize, DalleQuality, DalleStyle } from "../typing";
 import { Prompt, usePromptStore } from "../store/prompt";
 import Locale from "../locales";
 
@@ -492,6 +490,7 @@ export function ChatActions(props: {
   const currentProviderName =
     session.mask.modelConfig?.providerName || ServiceProvider.OpenAI;
   const allModels = useAllModels();
+  const customVisionModels = useAccessStore().visionModels;
   const models = useMemo(() => {
     const filteredModels = allModels.filter((m) => m.available);
     const defaultModel = filteredModels.find((m) => m.isDefault);
@@ -521,18 +520,17 @@ export function ChatActions(props: {
   const [showSizeSelector, setShowSizeSelector] = useState(false);
   const [showQualitySelector, setShowQualitySelector] = useState(false);
   const [showStyleSelector, setShowStyleSelector] = useState(false);
-  const modelSizes = getModelSizes(currentModel);
+  const dalle3Sizes: DalleSize[] = ["1024x1024", "1792x1024", "1024x1792"];
   const dalle3Qualitys: DalleQuality[] = ["standard", "hd"];
   const dalle3Styles: DalleStyle[] = ["vivid", "natural"];
-  const currentSize =
+  const currentSize = session.mask.modelConfig?.size ?? "1024x1024";
-    session.mask.modelConfig?.size ?? ("1024x1024" as ModelSize);
   const currentQuality = session.mask.modelConfig?.quality ?? "standard";
   const currentStyle = session.mask.modelConfig?.style ?? "vivid";
 
   const isMobileScreen = useMobileScreen();
 
   useEffect(() => {
-    const show = isVisionModel(currentModel);
+    const show = isVisionModel(currentModel, customVisionModels);
     setShowUploadImage(show);
     if (!show) {
       props.setAttachImages([]);
@@ -676,7 +674,7 @@ export function ChatActions(props: {
           />
         )}
 
-        {supportsCustomSize(currentModel) && (
+        {isDalle3(currentModel) && (
           <ChatAction
             onClick={() => setShowSizeSelector(true)}
             text={currentSize}
@@ -687,7 +685,7 @@ export function ChatActions(props: {
         {showSizeSelector && (
           <Selector
             defaultSelectedValue={currentSize}
-            items={modelSizes.map((m) => ({
+            items={dalle3Sizes.map((m) => ({
               title: m,
               value: m,
             }))}
@@ -1413,6 +1411,7 @@ function _Chat() {
         const payload = JSON.parse(text) as {
           key?: string;
           url?: string;
+          code?: string;
         };
 
         console.log("[Command] got settings from url: ", payload);
@@ -1434,6 +1433,16 @@ function _Chat() {
             accessStore.update((access) => (access.useCustomConfig = true));
           });
         }
+
+        if (payload.code) {
+          accessStore.update((access) => (access.accessCode = payload.code!));
+          if (accessStore.isAuthorized()) {
+            context.pop();
+            const copiedHello = Object.assign({}, BOT_HELLO);
+            context.push(copiedHello);
+            setUserInput(" ");
+          }
+        }
       } catch {
         console.error("[Command] failed to get settings from url: ", text);
       }
@@ -1460,10 +1469,12 @@ function _Chat() {
     // eslint-disable-next-line react-hooks/exhaustive-deps
   }, []);
 
+  const customVisionModels = useAccessStore().visionModels;
+
   const handlePaste = useCallback(
     async (event: React.ClipboardEvent<HTMLTextAreaElement>) => {
       const currentModel = chatStore.currentSession().mask.modelConfig.model;
-      if (!isVisionModel(currentModel)) {
+      if (!isVisionModel(currentModel, customVisionModels)) {
         return;
       }
       const items = (event.clipboardData || window.clipboardData).items;
@@ -1500,7 +1511,7 @@ function _Chat() {
         }
       }
     },
-    [attachImages, chatStore],
+    [attachImages, chatStore, customVisionModels],
   );
 
   async function uploadImage() {
@@ -1548,7 +1559,7 @@ function _Chat() {
     setAttachImages(images);
   }
 
-  // 快捷键 shortcut keys
+  // 捷键 shortcut keys
   const [showShortcutKeyModal, setShowShortcutKeyModal] = useState(false);
 
   useEffect(() => {

app/config/server.ts

@@ -21,6 +21,7 @@ declare global {
       ENABLE_BALANCE_QUERY?: string; // allow user to query balance or not
       DISABLE_FAST_LINK?: string; // disallow parse settings from url or not
       CUSTOM_MODELS?: string; // to control custom models
+      VISION_MODELS?: string; // to control vision models
       DEFAULT_MODEL?: string; // to control default model in every new chat window
 
       // stability only
@@ -123,13 +124,16 @@ export const getServerSideConfig = () => {
 
   const disableGPT4 = !!process.env.DISABLE_GPT4;
   let customModels = process.env.CUSTOM_MODELS ?? "";
+  let visionModels = process.env.VISION_MODELS ?? "";
   let defaultModel = process.env.DEFAULT_MODEL ?? "";
 
   if (disableGPT4) {
     if (customModels) customModels += ",";
     customModels += DEFAULT_MODELS.filter(
       (m) =>
-        (m.name.startsWith("gpt-4") || m.name.startsWith("chatgpt-4o") || m.name.startsWith("o1")) &&
+        (m.name.startsWith("gpt-4") ||
+          m.name.startsWith("chatgpt-4o") ||
+          m.name.startsWith("o1")) &&
         !m.name.startsWith("gpt-4o-mini"),
     )
       .map((m) => "-" + m.name)
@@ -247,6 +251,7 @@ export const getServerSideConfig = () => {
     hideBalanceQuery: !process.env.ENABLE_BALANCE_QUERY,
     disableFastLink: !!process.env.DISABLE_FAST_LINK,
     customModels,
+    visionModels,
     defaultModel,
     allowedWebDavEndpoints,
   };

app/constant.ts

@@ -233,8 +233,6 @@ export const XAI = {
 export const ChatGLM = {
   ExampleEndpoint: CHATGLM_BASE_URL,
   ChatPath: "api/paas/v4/chat/completions",
-  ImagePath: "api/paas/v4/images/generations",
-  VideoPath: "api/paas/v4/videos/generations",
 };
 
 export const DEFAULT_INPUT_TEMPLATE = `{{input}}`; // input / time / model / lang
@@ -433,15 +431,6 @@ const chatglmModels = [
   "glm-4-long",
   "glm-4-flashx",
   "glm-4-flash",
-  "glm-4v-plus",
-  "glm-4v",
-  "glm-4v-flash", // free
-  "cogview-3-plus",
-  "cogview-3",
-  "cogview-3-flash", // free
-  // 目前无法适配轮询任务
-  //   "cogvideox",
-  //   "cogvideox-flash", // free
 ];
 
 let seq = 1000; // 内置的模型序号生成器从1000开始

app/store/access.ts

@@ -123,6 +123,7 @@ const DEFAULT_ACCESS_STATE = {
   disableGPT4: false,
   disableFastLink: false,
   customModels: "",
+  visionModels: "",
   defaultModel: "",
 
   // tts config

app/store/config.ts

@@ -1,10 +1,9 @@
 import { LLMModel } from "../client/api";
-import { DalleQuality, DalleStyle, ModelSize } from "../typing";
+import { DalleSize, DalleQuality, DalleStyle } from "../typing";
 import { getClientConfig } from "../config/client";
 import {
   DEFAULT_INPUT_TEMPLATE,
   DEFAULT_MODELS,
-  DEFAULT_SIDEBAR_WIDTH,
   DEFAULT_TTS_ENGINE,
   DEFAULT_TTS_ENGINES,
   DEFAULT_TTS_MODEL,
@@ -46,18 +45,20 @@ export const DEFAULT_CONFIG = {
   fontSize: 14,
   fontFamily: "",
   theme: Theme.Auto as Theme,
-  tightBorder: !!config?.isApp,
+  // tightBorder: !!config?.isApp,
-  sendPreviewBubble: true,
+  tightBorder: true,
+  sendPreviewBubble: false,
   enableAutoGenerateTitle: true,
-  sidebarWidth: DEFAULT_SIDEBAR_WIDTH,
+  // sidebarWidth: DEFAULT_SIDEBAR_WIDTH,
+  sidebarWidth: 100,
 
   enableArtifacts: true, // show artifacts config
 
   enableCodeFold: true, // code fold config
 
-  disablePromptHint: false,
+  disablePromptHint: true,
 
-  dontShowMaskSplashScreen: false, // dont show splash screen when create chat
+  dontShowMaskSplashScreen: true, // dont show splash screen when create chat
   hideBuiltinMasks: false, // dont add builtin masks
 
   customModels: "",
@@ -68,17 +69,17 @@ export const DEFAULT_CONFIG = {
     providerName: "OpenAI" as ServiceProvider,
     temperature: 0.5,
     top_p: 1,
-    max_tokens: 4000,
+    max_tokens: 8000,
     presence_penalty: 0,
     frequency_penalty: 0,
     sendMemory: true,
-    historyMessageCount: 4,
+    historyMessageCount: 16,
-    compressMessageLengthThreshold: 1000,
+    compressMessageLengthThreshold: 1000000,
     compressModel: "",
     compressProviderName: "",
     enableInjectSystemPrompts: true,
     template: config?.template ?? DEFAULT_INPUT_TEMPLATE,
-    size: "1024x1024" as ModelSize,
+    size: "1024x1024" as DalleSize,
     quality: "standard" as DalleQuality,
     style: "vivid" as DalleStyle,
   },

app/typing.ts

@@ -11,14 +11,3 @@ export interface RequestMessage {
 export type DalleSize = "1024x1024" | "1792x1024" | "1024x1792";
 export type DalleQuality = "standard" | "hd";
 export type DalleStyle = "vivid" | "natural";
-
-export type ModelSize =
-  | "1024x1024"
-  | "1792x1024"
-  | "1024x1792"
-  | "768x1344"
-  | "864x1152"
-  | "1344x768"
-  | "1152x864"
-  | "1440x720"
-  | "720x1440";

app/utils.ts

@@ -7,7 +7,7 @@ import { ServiceProvider } from "./constant";
 import { fetch as tauriStreamFetch } from "./utils/stream";
 import { VISION_MODEL_REGEXES, EXCLUDE_VISION_MODEL_REGEXES } from "./constant";
 import { getClientConfig } from "./config/client";
-import { ModelSize } from "./typing";
+import { getModelProvider } from "./utils/model";
 
 export function trimTopic(topic: string) {
   // Fix an issue where double quotes still show in the Indonesian language
@@ -254,12 +254,15 @@ export function getMessageImages(message: RequestMessage): string[] {
   return urls;
 }
 
-export function isVisionModel(model: string) {
+export function isVisionModel(model: string, customVisionModels: string) {
   const clientConfig = getClientConfig();
-  const envVisionModels = clientConfig?.visionModels
+  const allVisionModelsList = [customVisionModels, clientConfig?.visionModels]
-    ?.split(",")
+    ?.join(",")
-    .map((m) => m.trim());
+    .split(",")
-  if (envVisionModels?.includes(model)) {
+    .map((m) => m.trim())
+    .filter(Boolean)
+    .map((m) => getModelProvider(m)[0]);
+  if (allVisionModelsList?.includes(model)) {
     return true;
   }
   return (
@@ -272,28 +275,6 @@ export function isDalle3(model: string) {
   return "dall-e-3" === model;
 }
 
-export function getModelSizes(model: string): ModelSize[] {
-  if (isDalle3(model)) {
-    return ["1024x1024", "1792x1024", "1024x1792"];
-  }
-  if (model.toLowerCase().includes("cogview")) {
-    return [
-      "1024x1024",
-      "768x1344",
-      "864x1152",
-      "1344x768",
-      "1152x864",
-      "1440x720",
-      "720x1440",
-    ];
-  }
-  return [];
-}
-
-export function supportsCustomSize(model: string): boolean {
-  return getModelSizes(model).length > 0;
-}
-
 export function showPlugins(provider: ServiceProvider, model: string) {
   if (
     provider == ServiceProvider.OpenAI ||

test/vision-model-checker.test.ts

@@ -2,6 +2,7 @@ import { isVisionModel } from "../app/utils";
 
 describe("isVisionModel", () => {
   const originalEnv = process.env;
+  const customVisionModels = "custom-vlm,another-vlm";
 
   beforeEach(() => {
     jest.resetModules();
@@ -27,12 +28,12 @@ describe("isVisionModel", () => {
     ];
 
     visionModels.forEach((model) => {
-      expect(isVisionModel(model)).toBe(true);
+      expect(isVisionModel(model, customVisionModels)).toBe(true);
     });
   });
 
   test("should exclude specific models", () => {
-    expect(isVisionModel("claude-3-5-haiku-20241022")).toBe(false);
+    expect(isVisionModel("claude-3-5-haiku-20241022", customVisionModels)).toBe(false);
   });
 
   test("should not identify non-vision models", () => {
@@ -44,24 +45,26 @@ describe("isVisionModel", () => {
     ];
 
     nonVisionModels.forEach((model) => {
-      expect(isVisionModel(model)).toBe(false);
+      expect(isVisionModel(model, customVisionModels)).toBe(false);
     });
   });
 
   test("should identify models from VISION_MODELS env var", () => {
     process.env.VISION_MODELS = "custom-vision-model,another-vision-model";
-    
+
-    expect(isVisionModel("custom-vision-model")).toBe(true);
+    expect(isVisionModel("custom-vision-model", customVisionModels)).toBe(true);
-    expect(isVisionModel("another-vision-model")).toBe(true);
+    expect(isVisionModel("another-vision-model", customVisionModels)).toBe(true);
-    expect(isVisionModel("unrelated-model")).toBe(false);
+    expect(isVisionModel("custom-vlm", customVisionModels)).toBe(true);
+    expect(isVisionModel("another-vlm", customVisionModels)).toBe(true);
+    expect(isVisionModel("unrelated-model", customVisionModels)).toBe(false);
   });
 
   test("should handle empty or missing VISION_MODELS", () => {
     process.env.VISION_MODELS = "";
-    expect(isVisionModel("unrelated-model")).toBe(false);
+    expect(isVisionModel("unrelated-model", customVisionModels)).toBe(false);
 
     delete process.env.VISION_MODELS;
-    expect(isVisionModel("unrelated-model")).toBe(false);
+    expect(isVisionModel("unrelated-model", customVisionModels)).toBe(false);
-    expect(isVisionModel("gpt-4-vision")).toBe(true);
+    expect(isVisionModel("gpt-4-vision", customVisionModels)).toBe(true);
   });
 });