fix: type error

Merge

README.md

@@ -1,16 +1,17 @@
 <div align="center">
 
-<a href='#企业版'>
+<a href='https://nextchat.dev/chat'>
-  <img src="./docs/images/ent.svg" alt="icon"/>
+  <img src="https://github.com/user-attachments/assets/287c510f-f508-478e-ade3-54d30453dc18" width="1000" alt="icon"/>
 </a>
 
+
 <h1 align="center">NextChat (ChatGPT Next Web)</h1>
 
 English / [简体中文](./README_CN.md)
 
-One-Click to get a well-designed cross-platform ChatGPT web UI, with GPT3, GPT4 & Gemini Pro support.
+One-Click to get a well-designed cross-platform ChatGPT web UI, with Claude, GPT4 & Gemini Pro support.
 
-一键免费部署你的跨平台私人 ChatGPT 应用, 支持 GPT3, GPT4 & Gemini Pro 模型。
+一键免费部署你的跨平台私人 ChatGPT 应用, 支持 Claude, GPT4 & Gemini Pro 模型。
 
 [![Saas][Saas-image]][saas-url]
 [![Web][Web-image]][web-url]
@@ -31,7 +32,7 @@ One-Click to get a well-designed cross-platform ChatGPT web UI, with GPT3, GPT4
 [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%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://svgshare.com/i/1AVg.svg" alt="Deploy to Alibaba Cloud" height="30">](https://computenest.aliyun.com/market/service-f1c9b75e59814dc49d52)
+[<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://github.com/user-attachments/assets/903482d4-3e87-4134-9af1-f2588fa90659" height="60" width="288" >](https://monica.im/?utm=nxcrp)
 
@@ -355,6 +356,13 @@ For ByteDance: use `modelName@bytedance=deploymentName` to customize model name
 
 Change default model
 
+### `VISION_MODELS` (optional)
+
+> Default: Empty
+> Example: `gpt-4-vision,claude-3-opus,my-custom-model` means add vision capabilities to these models in addition to the default pattern matches (which detect models containing keywords like "vision", "claude-3", "gemini-1.5", etc).
+
+Add additional models to have vision capabilities, beyond the default pattern matching. Multiple models should be separated by commas.
+
 ### `WHITE_WEBDAV_ENDPOINTS` (optional)
 
 You can use this option if you want to increase the number of webdav service addresses you are allowed to access, as required by the format：
@@ -469,7 +477,7 @@ If you want to add a new translation, read this [document](./docs/translation.md
 
 ## Donation
 
-[Buy Me a Coffee](https://www.buymeacoffee.com/yidadaa)
+[Buy Me a Coffee](https://1kafei.com/dogtiti)
 
 ## 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%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；
+   [![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；
 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。
 
@@ -235,6 +235,13 @@ ChatGLM Api Url.
 
 更改默认模型
 
+### `VISION_MODELS` (可选)
+
+> 默认值：空
+> 示例：`gpt-4-vision,claude-3-opus,my-custom-model` 表示为这些模型添加视觉能力，作为对默认模式匹配的补充（默认会检测包含"vision"、"claude-3"、"gemini-1.5"等关键词的模型）。
+
+在默认模式匹配之外，添加更多具有视觉能力的模型。多个模型用逗号分隔。
+
 ### `DEFAULT_INPUT_TEMPLATE` （可选）
 
 自定义默认的 template，用于初始化『设置』中的『用户输入预处理』配置项

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%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;
+   [![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;
 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。
 
@@ -217,6 +217,13 @@ ByteDance モードでは、`modelName@bytedance=deploymentName` 形式でモデ
 
 デフォルトのモデルを変更します。
 
+### `VISION_MODELS` (オプション)
+
+> デフォルト：空
+> 例：`gpt-4-vision,claude-3-opus,my-custom-model` は、これらのモデルにビジョン機能を追加します。これはデフォルトのパターンマッチング（"vision"、"claude-3"、"gemini-1.5"などのキーワードを含むモデルを検出）に加えて適用されます。
+
+デフォルトのパターンマッチングに加えて、追加のモデルにビジョン機能を付与します。複数のモデルはカンマで区切ります。
+
 ### `DEFAULT_INPUT_TEMPLATE` （オプション）
 
 『設定』の『ユーザー入力前処理』の初期設定に使用するテンプレートをカスタマイズします。

app/api/openai.ts

@@ -14,7 +14,7 @@ function getModels(remoteModelRes: OpenAIListModelResponse) {
   if (config.disableGPT4) {
     remoteModelRes.data = remoteModelRes.data.filter(
       (m) =>
-        !(m.id.startsWith("gpt-4") || m.id.startsWith("chatgpt-4o")) ||
+        !(m.id.startsWith("gpt-4") || m.id.startsWith("chatgpt-4o") || m.id.startsWith("o1")) ||
         m.id.startsWith("gpt-4o-mini"),
     );
   }

app/client/platforms/glm.ts

@@ -25,12 +25,103 @@ 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) {
@@ -51,7 +142,6 @@ export class ChatGLMApi implements LLMApi {
     }
 
     console.log("[Proxy Endpoint] ", baseUrl, path);
-
     return [baseUrl, path].join("/");
   }
 
@@ -79,24 +169,16 @@ export class ChatGLMApi implements LLMApi {
       },
     };
 
-    const requestPayload: RequestPayload = {
+    const modelType = this.getModelType(modelConfig.model);
-      messages,
+    const requestPayload = this.createPayload(messages, modelConfig, options);
-      stream: options.config.stream,
+    const path = this.path(this.getModelPath(modelType));
-      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 payload: ", requestPayload);
+    console.log(`[Request] glm ${modelType} 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),
@@ -104,12 +186,23 @@ 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()
@@ -117,7 +210,7 @@ export class ChatGLMApi implements LLMApi {
             useChatStore.getState().currentSession().mask?.plugin || [],
           );
         return stream(
-          chatPath,
+          path,
           requestPayload,
           getHeaders(),
           tools as any,
@@ -125,7 +218,6 @@ 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: {
@@ -154,7 +246,7 @@ export class ChatGLMApi implements LLMApi {
             }
             return choices[0]?.delta?.content;
           },
-          // processToolMessage, include tool_calls message and tool call results
+          // processToolMessage
           (
             requestPayload: RequestPayload,
             toolCallMessage: any,
@@ -172,7 +264,7 @@ export class ChatGLMApi implements LLMApi {
           options,
         );
       } else {
-        const res = await fetch(chatPath, chatPayload);
+        const res = await fetch(path, chatPayload);
         clearTimeout(requestTimeoutId);
 
         const resJson = await res.json();
@@ -184,6 +276,7 @@ export class ChatGLMApi implements LLMApi {
       options.onError?.(e as Error);
     }
   }
+
   async usage() {
     return {
       used: 0,

app/client/platforms/google.ts

@@ -29,7 +29,7 @@ import { RequestPayload } from "./openai";
 import { fetch } from "@/app/utils/stream";
 
 export class GeminiProApi implements LLMApi {
-  path(path: string): string {
+  path(path: string, shouldStream = false): string {
     const accessStore = useAccessStore.getState();
 
     let baseUrl = "";
@@ -51,8 +51,10 @@ export class GeminiProApi implements LLMApi {
     console.log("[Proxy Endpoint] ", baseUrl, path);
 
     let chatPath = [baseUrl, path].join("/");
-
+    if (shouldStream) {
       chatPath += chatPath.includes("?") ? "&alt=sse" : "?alt=sse";
+    }
+
     return chatPath;
   }
   extractMessage(res: any) {
@@ -60,6 +62,7 @@ export class GeminiProApi implements LLMApi {
 
     return (
       res?.candidates?.at(0)?.content?.parts.at(0)?.text ||
+      res?.at(0)?.candidates?.at(0)?.content?.parts.at(0)?.text ||
       res?.error?.message ||
       ""
     );
@@ -166,7 +169,10 @@ export class GeminiProApi implements LLMApi {
     options.onController?.(controller);
     try {
       // https://github.com/google-gemini/cookbook/blob/main/quickstarts/rest/Streaming_REST.ipynb
-      const chatPath = this.path(Google.ChatPath(modelConfig.model));
+      const chatPath = this.path(
+        Google.ChatPath(modelConfig.model),
+        shouldStream,
+      );
 
       const chatPayload = {
         method: "POST",

app/client/platforms/openai.ts

@@ -24,7 +24,7 @@ import {
   stream,
 } from "@/app/utils/chat";
 import { cloudflareAIGatewayUrl } from "@/app/utils/cloudflare";
-import { DalleSize, DalleQuality, DalleStyle } from "@/app/typing";
+import { ModelSize, DalleQuality, DalleStyle } from "@/app/typing";
 
 import {
   ChatOptions,
@@ -73,7 +73,7 @@ export interface DalleRequestPayload {
   prompt: string;
   response_format: "url" | "b64_json";
   n: number;
-  size: DalleSize;
+  size: ModelSize;
   quality: DalleQuality;
   style: DalleStyle;
 }
@@ -224,7 +224,7 @@ export class ChatGPTApi implements LLMApi {
       // O1 not support image, tools (plugin in ChatGPTNextWeb) and system, stream, logprobs, temperature, top_p, n, presence_penalty, frequency_penalty yet.
       requestPayload = {
         messages,
-        stream: !isO1 ? options.config.stream : false,
+        stream: options.config.stream,
         model: modelConfig.model,
         temperature: !isO1 ? modelConfig.temperature : 1,
         presence_penalty: !isO1 ? modelConfig.presence_penalty : 0,
@@ -247,7 +247,7 @@ export class ChatGPTApi implements LLMApi {
 
     console.log("[Request] openai payload: ", requestPayload);
 
-    const shouldStream = !isDalle3 && !!options.config.stream && !isO1;
+    const shouldStream = !isDalle3 && !!options.config.stream;
     const controller = new AbortController();
     options.onController?.(controller);
 

app/components/chat.tsx

@@ -72,6 +72,8 @@ import {
   isDalle3,
   showPlugins,
   safeLocalStorage,
+  getModelSizes,
+  supportsCustomSize,
 } from "../utils";
 
 import { uploadImage as uploadImageRemote } from "@/app/utils/chat";
@@ -79,7 +81,7 @@ import { uploadImage as uploadImageRemote } from "@/app/utils/chat";
 import dynamic from "next/dynamic";
 
 import { ChatControllerPool } from "../client/controller";
-import { DalleSize, DalleQuality, DalleStyle } from "../typing";
+import { DalleQuality, DalleStyle, ModelSize } from "../typing";
 import { Prompt, usePromptStore } from "../store/prompt";
 import Locale from "../locales";
 
@@ -519,10 +521,11 @@ export function ChatActions(props: {
   const [showSizeSelector, setShowSizeSelector] = useState(false);
   const [showQualitySelector, setShowQualitySelector] = useState(false);
   const [showStyleSelector, setShowStyleSelector] = useState(false);
-  const dalle3Sizes: DalleSize[] = ["1024x1024", "1792x1024", "1024x1792"];
+  const modelSizes = getModelSizes(currentModel);
   const dalle3Qualitys: DalleQuality[] = ["standard", "hd"];
   const dalle3Styles: DalleStyle[] = ["vivid", "natural"];
-  const currentSize = session.mask.modelConfig?.size ?? "1024x1024";
+  const currentSize =
+    session.mask.modelConfig?.size ?? ("1024x1024" as ModelSize);
   const currentQuality = session.mask.modelConfig?.quality ?? "standard";
   const currentStyle = session.mask.modelConfig?.style ?? "vivid";
 
@@ -673,7 +676,7 @@ export function ChatActions(props: {
           />
         )}
 
-        {isDalle3(currentModel) && (
+        {supportsCustomSize(currentModel) && (
           <ChatAction
             onClick={() => setShowSizeSelector(true)}
             text={currentSize}
@@ -684,7 +687,7 @@ export function ChatActions(props: {
         {showSizeSelector && (
           <Selector
             defaultSelectedValue={currentSize}
-            items={dalle3Sizes.map((m) => ({
+            items={modelSizes.map((m) => ({
               title: m,
               value: m,
             }))}
@@ -960,9 +963,24 @@ function _Chat() {
           (scrollRef.current.scrollTop + scrollRef.current.clientHeight),
       ) <= 1
     : false;
+  const isAttachWithTop = useMemo(() => {
+    const lastMessage = scrollRef.current?.lastElementChild as HTMLElement;
+    // if scrolllRef is not ready or no message, return false
+    if (!scrollRef?.current || !lastMessage) return false;
+    const topDistance =
+      lastMessage!.getBoundingClientRect().top -
+      scrollRef.current.getBoundingClientRect().top;
+    // leave some space for user question
+    return topDistance < 100;
+  }, [scrollRef?.current?.scrollHeight]);
+
+  const isTyping = userInput !== "";
+
+  // if user is typing, should auto scroll to bottom
+  // if user is not typing, should auto scroll to bottom only if already at bottom
   const { setAutoScroll, scrollDomToBottom } = useScrollToBottom(
     scrollRef,
-    isScrolledToBottom,
+    (isScrolledToBottom || isAttachWithTop) && !isTyping,
   );
   const [hitBottom, setHitBottom] = useState(true);
   const isMobileScreen = useMobileScreen();
@@ -2071,6 +2089,6 @@ function _Chat() {
 
 export function Chat() {
   const chatStore = useChatStore();
-  const sessionIndex = chatStore.currentSessionIndex;
+  const session = chatStore.currentSession();
-  return <_Chat key={sessionIndex}></_Chat>;
+  return <_Chat key={session.id}></_Chat>;
 }

app/components/emoji.tsx

@@ -37,7 +37,8 @@ export function Avatar(props: { model?: ModelType; avatar?: string }) {
     return (
       <div className="no-dark">
         {props.model?.startsWith("gpt-4") ||
-        props.model?.startsWith("chatgpt-4o") ? (
+        props.model?.startsWith("chatgpt-4o") ||
+        props.model?.startsWith("o1") ? (
           <BlackBotIcon className="user-avatar" />
         ) : (
           <BotIcon className="user-avatar" />

app/components/markdown.tsx

@@ -90,7 +90,11 @@ export function PreCode(props: { children: any }) {
     const refText = ref.current.querySelector("code")?.innerText;
     if (htmlDom) {
       setHtmlCode((htmlDom as HTMLElement).innerText);
-    } else if (refText?.startsWith("<!DOCTYPE")) {
+    } else if (
+      refText?.startsWith("<!DOCTYPE") ||
+      refText?.startsWith("<svg") ||
+      refText?.startsWith("<?xml")
+    ) {
       setHtmlCode(refText);
     }
   }, 600);
@@ -244,6 +248,10 @@ function escapeBrackets(text: string) {
 
 function tryWrapHtmlCode(text: string) {
   // try add wrap html code (fixed: html codeblock include 2 newline)
+  // ignore embed codeblock
+  if (text.includes("```")) {
+    return text;
+  }
   return text
     .replace(
       /([`]*?)(\w*?)([\n\r]*?)(<!DOCTYPE html>)/g,

app/components/settings.tsx

@@ -1771,9 +1771,11 @@ export function Settings() {
           <ListItem
             title={Locale.Settings.Access.CustomModel.Title}
             subTitle={Locale.Settings.Access.CustomModel.SubTitle}
+            vertical={true}
           >
             <input
               aria-label={Locale.Settings.Access.CustomModel.Title}
+              style={{ width: "100%", maxWidth: "unset", textAlign: "left" }}
               type="text"
               value={config.customModels}
               placeholder="model1,model2,model3"

app/config/build.ts

@@ -40,6 +40,7 @@ export const getBuildConfig = () => {
     buildMode,
     isApp,
     template: process.env.DEFAULT_INPUT_TEMPLATE ?? DEFAULT_INPUT_TEMPLATE,
+    visionModels: process.env.VISION_MODELS || "",
   };
 };
 

app/config/server.ts

@@ -129,14 +129,15 @@ export const getServerSideConfig = () => {
     if (customModels) customModels += ",";
     customModels += DEFAULT_MODELS.filter(
       (m) =>
-        (m.name.startsWith("gpt-4") || m.name.startsWith("chatgpt-4o")) &&
+        (m.name.startsWith("gpt-4") || m.name.startsWith("chatgpt-4o") || m.name.startsWith("o1")) &&
         !m.name.startsWith("gpt-4o-mini"),
     )
       .map((m) => "-" + m.name)
       .join(",");
     if (
       (defaultModel.startsWith("gpt-4") ||
-        defaultModel.startsWith("chatgpt-4o")) &&
+        defaultModel.startsWith("chatgpt-4o") ||
+        defaultModel.startsWith("o1")) &&
       !defaultModel.startsWith("gpt-4o-mini")
     )
       defaultModel = "";

app/constant.ts

@@ -233,6 +233,8 @@ 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
@@ -264,6 +266,7 @@ export const KnowledgeCutOffDate: Record<string, string> = {
   "gpt-4o": "2023-10",
   "gpt-4o-2024-05-13": "2023-10",
   "gpt-4o-2024-08-06": "2023-10",
+  "gpt-4o-2024-11-20": "2023-10",
   "chatgpt-4o-latest": "2023-10",
   "gpt-4o-mini": "2023-10",
   "gpt-4o-mini-2024-07-18": "2023-10",
@@ -290,6 +293,22 @@ export const DEFAULT_TTS_VOICES = [
   "shimmer",
 ];
 
+export const VISION_MODEL_REGEXES = [
+  /vision/,
+  /gpt-4o/,
+  /claude-3/,
+  /gemini-1\.5/,
+  /gemini-exp/,
+  /gemini-2\.0/,
+  /learnlm/,
+  /qwen-vl/,
+  /qwen2-vl/,
+  /gpt-4-turbo(?!.*preview)/, // Matches "gpt-4-turbo" but not "gpt-4-turbo-preview"
+  /^dall-e-3$/, // Matches exactly "dall-e-3"
+];
+
+export const EXCLUDE_VISION_MODEL_REGEXES = [/claude-3-5-haiku-20241022/];
+
 const openaiModels = [
   "gpt-3.5-turbo",
   "gpt-3.5-turbo-1106",
@@ -303,6 +322,7 @@ const openaiModels = [
   "gpt-4o",
   "gpt-4o-2024-05-13",
   "gpt-4o-2024-08-06",
+  "gpt-4o-2024-11-20",
   "chatgpt-4o-latest",
   "gpt-4o-mini",
   "gpt-4o-mini-2024-07-18",
@@ -315,10 +335,23 @@ const openaiModels = [
 ];
 
 const googleModels = [
-  "gemini-1.0-pro",
+  "gemini-1.0-pro", // Deprecated on 2/15/2025
   "gemini-1.5-pro-latest",
+  "gemini-1.5-pro",
+  "gemini-1.5-pro-002",
+  "gemini-1.5-pro-exp-0827",
   "gemini-1.5-flash-latest",
-  "gemini-pro-vision",
+  "gemini-1.5-flash-8b-latest",
+  "gemini-1.5-flash",
+  "gemini-1.5-flash-8b",
+  "gemini-1.5-flash-002",
+  "gemini-1.5-flash-exp-0827",
+  "learnlm-1.5-pro-experimental",
+  "gemini-exp-1114",
+  "gemini-exp-1121",
+  "gemini-exp-1206",
+  "gemini-2.0-flash-exp",
+  "gemini-2.0-flash-thinking-exp-1219",
 ];
 
 const anthropicModels = [
@@ -400,6 +433,15 @@ 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/masks/cn.ts

@@ -3,7 +3,7 @@ import { BuiltinMask } from "./typing";
 export const CN_MASKS: BuiltinMask[] = [
   {
     avatar: "1f5bc-fe0f",
-    name: "以文搜图",
+    name: "AI文生图",
     context: [
       {
         id: "text-to-pic-0",
@@ -28,7 +28,7 @@ export const CN_MASKS: BuiltinMask[] = [
         id: "text-to-pic-3",
         role: "system",
         content:
-          "助手善于判断用户意图，当确定需要提供图片时，助手会变得沉默寡言，只使用以下格式输出markdown图片：![描述](https://image.pollinations.ai/prompt/描述)，因为这个语法可以自动按照提示生成并渲染图片。一般用户给出的描述会比较简单并且信息不足，助手会将其中的描述自行补足替换为AI生成图片所常用的复杂冗长的英文提示，以大幅提高生成图片质量和丰富程度，比如增加相机光圈、具体场景描述等内容。助手会避免用代码块或原始块包围markdown标记，因为那样只会渲染出代码块或原始块而不是图片。",
+          "助手善于判断用户意图，当确定需要提供图片时，助手会变得沉默寡言，只使用以下格式输出markdown图片：![description](https://image.pollinations.ai/prompt/description?nologo=true)，因为这个语法可以自动按照提示生成并渲染图片。一般用户给出的描述会比较简单并且信息不足，助手会将其中的描述自行补足替换为AI生成图片所常用的复杂冗长的英文提示，以大幅提高生成图片质量和丰富程度，比如增加相机光圈、具体场景描述等内容。助手会避免用代码块或原始块包围markdown标记，因为那样只会渲染出代码块或原始块而不是图片。url中的空格等符号需要转义。",
         date: "",
       },
     ],

app/store/config.ts

@@ -1,5 +1,5 @@
 import { LLMModel } from "../client/api";
-import { DalleSize, DalleQuality, DalleStyle } from "../typing";
+import { DalleQuality, DalleStyle, ModelSize } from "../typing";
 import { getClientConfig } from "../config/client";
 import {
   DEFAULT_INPUT_TEMPLATE,
@@ -78,7 +78,7 @@ export const DEFAULT_CONFIG = {
     compressProviderName: "",
     enableInjectSystemPrompts: true,
     template: config?.template ?? DEFAULT_INPUT_TEMPLATE,
-    size: "1024x1024" as DalleSize,
+    size: "1024x1024" as ModelSize,
     quality: "standard" as DalleQuality,
     style: "vivid" as DalleStyle,
   },

app/typing.ts

@@ -11,3 +11,14 @@ 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

@@ -5,6 +5,9 @@ import { RequestMessage } from "./client/api";
 import { ServiceProvider } from "./constant";
 // import { fetch as tauriFetch, ResponseType } from "@tauri-apps/api/http";
 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";
 
 export function trimTopic(topic: string) {
   // Fix an issue where double quotes still show in the Indonesian language
@@ -252,25 +255,16 @@ export function getMessageImages(message: RequestMessage): string[] {
 }
 
 export function isVisionModel(model: string) {
-  // Note: This is a better way using the TypeScript feature instead of `&&` or `||` (ts v5.5.0-dev.20240314 I've been using)
+  const clientConfig = getClientConfig();
-
+  const envVisionModels = clientConfig?.visionModels
-  const excludeKeywords = ["claude-3-5-haiku-20241022"];
+    ?.split(",")
-  const visionKeywords = [
+    .map((m) => m.trim());
-    "vision",
+  if (envVisionModels?.includes(model)) {
-    "claude-3",
+    return true;
-    "gemini-1.5-pro",
+  }
-    "gemini-1.5-flash",
-    "gpt-4o",
-    "gpt-4o-mini",
-  ];
-  const isGpt4Turbo =
-    model.includes("gpt-4-turbo") && !model.includes("preview");
-
   return (
-    !excludeKeywords.some((keyword) => model.includes(keyword)) &&
+    !EXCLUDE_VISION_MODEL_REGEXES.some((regex) => regex.test(model)) &&
-    (visionKeywords.some((keyword) => model.includes(keyword)) ||
+    VISION_MODEL_REGEXES.some((regex) => regex.test(model))
-      isGpt4Turbo ||
-      isDalle3(model))
   );
 }
 
@@ -278,6 +272,28 @@ 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 ||

package.json

@@ -59,8 +59,8 @@
     "@tauri-apps/api": "^1.6.0",
     "@tauri-apps/cli": "1.5.11",
     "@testing-library/dom": "^10.4.0",
-    "@testing-library/jest-dom": "^6.6.2",
+    "@testing-library/jest-dom": "^6.6.3",
-    "@testing-library/react": "^16.0.1",
+    "@testing-library/react": "^16.1.0",
     "@types/jest": "^29.5.14",
     "@types/js-yaml": "4.0.9",
     "@types/lodash-es": "^4.17.12",

test/vision-model-checker.test.ts

@@ -0,0 +1,67 @@
+import { isVisionModel } from "../app/utils";
+
+describe("isVisionModel", () => {
+  const originalEnv = process.env;
+
+  beforeEach(() => {
+    jest.resetModules();
+    process.env = { ...originalEnv };
+  });
+
+  afterEach(() => {
+    process.env = originalEnv;
+  });
+
+  test("should identify vision models using regex patterns", () => {
+    const visionModels = [
+      "gpt-4-vision",
+      "claude-3-opus",
+      "gemini-1.5-pro",
+      "gemini-2.0",
+      "gemini-exp-vision",
+      "learnlm-vision",
+      "qwen-vl-max",
+      "qwen2-vl-max",
+      "gpt-4-turbo",
+      "dall-e-3",
+    ];
+
+    visionModels.forEach((model) => {
+      expect(isVisionModel(model)).toBe(true);
+    });
+  });
+
+  test("should exclude specific models", () => {
+    expect(isVisionModel("claude-3-5-haiku-20241022")).toBe(false);
+  });
+
+  test("should not identify non-vision models", () => {
+    const nonVisionModels = [
+      "gpt-3.5-turbo",
+      "gpt-4-turbo-preview",
+      "claude-2",
+      "regular-model",
+    ];
+
+    nonVisionModels.forEach((model) => {
+      expect(isVisionModel(model)).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("another-vision-model")).toBe(true);
+    expect(isVisionModel("unrelated-model")).toBe(false);
+  });
+
+  test("should handle empty or missing VISION_MODELS", () => {
+    process.env.VISION_MODELS = "";
+    expect(isVisionModel("unrelated-model")).toBe(false);
+
+    delete process.env.VISION_MODELS;
+    expect(isVisionModel("unrelated-model")).toBe(false);
+    expect(isVisionModel("gpt-4-vision")).toBe(true);
+  });
+});

yarn.lock

@@ -2114,10 +2114,10 @@
     lz-string "^1.5.0"
     pretty-format "^27.0.2"
 
-"@testing-library/jest-dom@^6.6.2":
+"@testing-library/jest-dom@^6.6.3":
-  version "6.6.2"
+  version "6.6.3"
-  resolved "https://registry.yarnpkg.com/@testing-library/jest-dom/-/jest-dom-6.6.2.tgz#8186aa9a07263adef9cc5a59a4772db8c31f4a5b"
+  resolved "https://registry.yarnpkg.com/@testing-library/jest-dom/-/jest-dom-6.6.3.tgz#26ba906cf928c0f8172e182c6fe214eb4f9f2bd2"
-  integrity sha512-P6GJD4yqc9jZLbe98j/EkyQDTPgqftohZF5FBkHY5BUERZmcf4HeO2k0XaefEg329ux2p21i1A1DmyQ1kKw2Jw==
+  integrity sha512-IteBhl4XqYNkM54f4ejhLRJiZNqcSCoXUOG2CPK7qbD322KjQozM4kHQOfkG2oln9b9HTYqs+Sae8vBATubxxA==
   dependencies:
     "@adobe/css-tools" "^4.4.0"
     aria-query "^5.0.0"
@@ -2127,10 +2127,10 @@
     lodash "^4.17.21"
     redent "^3.0.0"
 
-"@testing-library/react@^16.0.1":
+"@testing-library/react@^16.1.0":
-  version "16.0.1"
+  version "16.1.0"
-  resolved "https://registry.yarnpkg.com/@testing-library/react/-/react-16.0.1.tgz#29c0ee878d672703f5e7579f239005e4e0faa875"
+  resolved "https://registry.yarnpkg.com/@testing-library/react/-/react-16.1.0.tgz#aa0c61398bac82eaf89776967e97de41ac742d71"
-  integrity sha512-dSmwJVtJXmku+iocRhWOUFbrERC76TX2Mnf0ATODz8brzAZrMBbzLwQixlBSanZxR6LddK3eiwpSFZgDET1URg==
+  integrity sha512-Q2ToPvg0KsVL0ohND9A3zLJWcOXXcO8IDu3fj11KhNt0UlCWyFyvnCIBkd12tidB2lkiVRG8VFqdhcqhqnAQtg==
   dependencies:
     "@babel/runtime" "^7.12.5"